System

Abstract

A system is provided.SOLUTION: A system, comprising: means for receiving a search query entered by a user and extracting relevant data from a database; means for analyzing the extracted data to identify a trend for each attribute; and means for formatting and presenting the analysis results to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Survey results presented in news and articles as "voices from the streets" or "public opinion polls" are problematic due to biased populations and low reliability. Another issue is the difficulty of individually surveying and collecting statistically valuable data, and the fact that much of the data is released in an unregulated manner and eventually becomes worthless. Given this background, there is a demand for a system that allows users to easily obtain and analyze reliable public opinion data. [Means for solving the problem]

[0005] A system is provided that includes means for receiving a search query entered by a user and extracting corresponding data from a database, means for analyzing the extracted data to identify trends for each attribute, and means for forming and presenting the analysis results to the user. The system also includes means for collecting statistical data and real-time user comment logs published on the Internet and storing them in a database, and means for providing an interface that displays the analysis results in graphs and text format.

[0006] A "search query" is a string or phrase that a user enters to search for specific information.

[0007] A "database" is an organized collection of data for efficiently storing, managing, and retrieving information.

[0008] "Extract" refers to the act of retrieving specific information from a database or other source.

[0009] "Analysis" is the process of examining the data in detail to find meaning and patterns.

[0010] "Trends by attribute" refers to trends and characteristics of data categorized based on specific attributes (such as age or gender).

[0011] "Distinguishing" is the act of recognizing a particular feature or pattern and distinguishing it from others.

[0012] "Forming" is the process of processing data or information into a particular form or shape.

[0013] "Presentation" refers to the act of displaying analysis results and information in a form that can be seen by the user.

[0014] A "system" is a collection of integrated devices and processes in which multiple related elements interact with each other to achieve a specific function.

[0015] An "interface" is the means by which information is exchanged between a user and a computer system.

[0016] "Real time" refers to a state in which processing and reaction occur in parallel with real-world events that occur almost simultaneously.

[0017] A "graph" is a diagram that visually represents data.

[0018] "Text format" is a format in which information is written using only sentences or character strings.

[0019] "Statistical data" is a collection of quantitative data about a particular phenomenon that can be used for analysis and interpretation.

[0020] "User comment log" means a record of comments posted by a user on an online platform.

[0021] "Collecting" is the act of gathering data or information for a specific purpose. [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 showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[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 present invention provides a system that allows users to easily and reliably obtain specific information by receiving a user's search query, extracting relevant data from a database, analyzing it, forming results, and presenting them to the user.

[0044] Server Processing

[0045] The server has a function to collect statistical data and real-time user comment logs that are publicly available on the Internet and store them in a database. Specifically, automated scripts periodically retrieve data from websites and APIs and add it to the database.

[0046] Next, when a user's search query is received, the server extracts relevant data from the database based on the query. The extracted data is stored in a temporary buffer and analyzed by an AI model. During this analysis process, the data is classified based on attributes such as age and gender, and specific trends are clearly identified.

[0047] The parsed results are formatted and formatted in a user-friendly format (for example, JSON). The server finally returns this formatted data to the terminal as an HTTP response.

[0048] Terminal handling

[0049] The device, such as a web browser on a user's PC or smartphone, provides an interface to the server. When a user enters a specific query into a search box and presses the search button, the device sends the query to the server.

[0050] When the analysis results are returned from the server, the device analyzes the data and displays it in an easy-to-read format for the user. For example, if a user enters the query "Tokyo Olympics public opinion," the device receives the results sent back from the server and displays them in a format such as "70% of men in their 30s have a positive opinion."

[0051] User operations

[0052] The user interacts with the system by entering a keyword or phrase into the search box on their device, clicking the search button, and sending the query to the server. The user waits for the results to appear, and then makes their own research or decision based on the results.

[0053] As a concrete example, to search for information on "Tokyo Olympics public opinion," a user would enter "Tokyo Olympics public opinion" into the search box and press the search button. The server receives this query, extracts and analyzes all relevant information from the database (e.g., comment logs and statistical data), formats the results, and sends them to the terminal. The terminal then displays the analysis results as graphs or text, allowing the user to view the information.

[0054] This system allows users to easily obtain and analyze reliable data, enabling them to utilize practical information in a wide range of fields, including news reporting, marketing research, and academic research.

[0055] The processing flow will be explained below.

[0056] Step 1:

[0057] The server collects publicly available statistical data and real-time user comment logs from the internet, including information obtained from specific websites and APIs. This data is periodically updated and stored in a database.

[0058] Step 2:

[0059] Users enter the keyword or phrase they want to research into the search box on their device's web browser, for example, "Tokyo Olympics public opinion," and click the search button.

[0060] Step 3:

[0061] The device sends the search query entered by the user as form data to the server via a POST request, which includes the keywords or phrases entered by the user.

[0062] Step 4:

[0063] The server analyzes the POST request received from the device and obtains the query, based on which the server connects to the database and searches for the appropriate data.

[0064] Step 5:

[0065] The server stores data extracted from the database in a temporary buffer, including relevant statistical data and user comment logs.

[0066] Step 6:

[0067] The server analyzes the data stored in a temporary buffer using AI models that categorize the data based on attributes such as age and gender, and identify specific trends.

[0068] Step 7:

[0069] The server converts the analysis results from the AI ​​model into a format such as JSON. The converted data may include information such as "70% of men in their 30s have a positive opinion of the Tokyo Olympics."

[0070] Step 8:

[0071] The server sends the formatted data to the terminal as an HTTP response, which includes details of the analysis results.

[0072] Step 9:

[0073] The device analyzes the response data received from the server and displays it in an easy-to-read format for the user. The analysis results are displayed in graphs and text format, and may show something like, "70% of men in their 30s have a positive opinion."

[0074] Step 10:

[0075] Users can check the results displayed on their devices and obtain the necessary information, allowing them to conduct their own research and make decisions based on the data obtained.

[0076] Example 1

[0077] 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."

[0078] In today's information society, users need to be able to quickly and easily obtain reliable information. However, the vast amount of data available on the Internet, with unreliable information scattered throughout, makes it difficult for users to accurately collect and analyze the information they need. Furthermore, advanced analytical techniques and visualization methods are required to convert the collected data into an easily understandable format, but it is not realistic for individual users to do this. A solution to these problems is needed.

[0079] 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.

[0080] In this invention, the server includes means for receiving a search query entered by a user and extracting corresponding data from a database, means for temporarily storing the extracted data in a buffer and analyzing the data using a generative AI model, and means for identifying the analysis results based on trends for each attribute such as age and gender, and converting the results into an easy-to-read format such as JSON format, thereby enabling users to quickly and easily obtain reliable information and view it in an easy-to-understand format.

[0081] A "search query" is a keyword or phrase that a user enters to retrieve specific information.

[0082] A "database" is a system for effectively storing, managing, and searching collected data.

[0083] A "temporary buffer" is a memory area for temporarily storing intermediate results of data processing.

[0084] A "generative AI model" is an algorithm that uses machine learning technology to analyze various data and identify its trends and characteristics.

[0085] "Analysis" is the process of breaking down data according to certain criteria and methods and extracting meaningful information from it.

[0086] "JSON format" is an abbreviation for JavaScript Object Notation, a standard format for expressing data in a human-readable text format.

[0087] An "HTTP response" is a response message sent from a server to a client in communication using the HTTP protocol.

[0088] A "terminal" is an electronic device such as a computer or smartphone that a user uses to access the system.

[0089] A "graph" is a diagram that visually represents data and makes comparisons and trends easy to understand.

[0090] "Text format" refers to a format for visually displaying textual information.

[0091] This invention provides a system that allows users to quickly and reliably obtain specific information. The central components of the system are a server and a terminal, which are operated by the user. The specific operation of each component will be described below.

[0092] Server Operation

[0093] The server has the ability to collect statistical data and real-time user comment logs published on the Internet and store them in a database. This ensures that the latest information is always collected and stored in the database. Tools such as the Python requests library and BeautifulSoup are used to collect the data.

[0094] When a search query is received from a user, the server extracts relevant data from the database based on the query. This data is stored in a temporary buffer and analyzed by a generative AI model (e.g., using TensorFlow or PyTorch). During this analysis process, the data is classified based on attributes such as age and gender, and specific trends are identified. The analysis results are formatted into an easy-to-read format, such as JSON, and sent back to the device as an HTTP response.

[0095] Device behavior

[0096] The device is, for example, a web browser on a user's PC or smartphone, and provides an interface with the server. When a user enters a specific query into a search box and presses the search button, the device sends the query to the server. When the server returns the analysis results, the device analyzes the data and displays the results in an easy-to-read format for the user, for example, using JavaScript and HTML.

[0097] User operations

[0098] The user enters the keyword or phrase they want to research into the device's search box and clicks the search button. The server receives this query, extracts all relevant information from the database, analyzes it using a generative AI model, formats the results, and sends them to the device. The device displays the analysis results, allowing the user to view the information.

[0099] Specific examples

[0100] For example, to search for information on "Tokyo Olympics public opinion," a user would enter "Tokyo Olympics public opinion" in the search box and press the search button. The server receives this query, extracts all relevant information (comment logs and statistical data) from the database, and analyzes it using a generative AI model. The result is then formatted as, for example, "70% of men in their 30s have a positive opinion," and sent to the device. The device then displays the results as graphs and text, which the user can view.

[0101] Prompt Sentence Examples

[0102] Here are some example prompts to input to a generative AI model:

[0103] Example prompt: "Analyze opinions on the Tokyo Olympics by men in their 30s and return the results in JSON format."

[0104] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0105] Step 1:

[0106] Data collection

[0107] The server collects data from external sources. In this step, for example, Python's requests library or BeautifulSoup is used to retrieve statistical data and user comment logs from specific websites or APIs. Examples of collected data include economic data from government statistics APIs and comment logs from social media. The input is data from external sources, and the output is the collected data.

[0108] Step 2:

[0109] Data Storage

[0110] The server stores the collected data in a database. In this step, the specific operation of inserting data into the database is performed, for example, using MySQL or PostgreSQL. The input is the data collected in step 1, and the output is the data stored in the database.

[0111] Step 3:

[0112] Receiving user queries

[0113] The device receives a search query from the user. In this step, the user enters a query into the search box of a web browser and clicks the search button. The query is sent to the server using a JavaScript API such as Fetch. The input is the search query entered by the user, and the output is the query sent to the server.

[0114] Step 4:

[0115] Data Extraction

[0116] The server extracts the relevant data from the database. In this step, data is selected from the database using an SQL statement based on the received query. Specifically, a query such as "SELECT FROM comments WHERE event='Tokyo Olympics' AND topic='public opinion'" is executed. The input is the search query received by the server, and the output is the data extracted from the database.

[0117] Step 5:

[0118] Data analysis

[0119] The server stores the extracted data in a temporary buffer and analyzes it using a generative AI model. In this step, for example, TensorFlow or PyTorch are used to classify the data by age and gender and identify specific trends. The input is the data extracted from the database, and the output is the analysis results.

[0120] Step 6:

[0121] Shaping the result

[0122] The server formats the analysis results into an easy-to-read format such as JSON. In this step, the analysis results are converted into structured data using a Python module such as json. The input is the analysis result from the generative AI model, and the output is the formatted data.

[0123] Step 7:

[0124] Sending the results

[0125] The server sends the formed result data to the terminal as an HTTP response. In this step, the specific operation of returning JSON data to the terminal using the HTTP response is performed. The input is the formed JSON data, and the output is the HTTP response sent to the terminal.

[0126] Step 8:

[0127] Displaying the results

[0128] The device displays the data received from the server in a format that is easy for the user to view. In this step, JavaScript is used to parse the JSON data and display the results as graphs and text using HTML and libraries such as Chart.js. The input is the JSON data received from the server, and the output is the graphs and text displayed to the user.

[0129] (Application example 1)

[0130] 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."

[0131] In recent years, in this age of information overload, it has become increasingly difficult for users to efficiently collect and understand reliable data. In particular, conventional systems are inadequate when it is necessary to quickly grasp data that changes in real time or information integrated from multiple sources. Furthermore, there is a demand for functions that can immediately present the results of data analysis in a visually understandable format. Against this background, there is an urgent need to provide a system that allows users to efficiently obtain and understand reliable information.

[0132] 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.

[0133] In this invention, the server includes means for receiving a search query entered by a user and extracting corresponding data from a database, means for analyzing the extracted data to identify trends by attribute, means for formatting the analysis results and presenting them to the user, means for collecting data from data sources on the Internet based on the search query, means for analyzing the collected data using an AI model, and means for formatting the analysis results in JSON format and returning them to the user terminal. This enables users to quickly obtain reliable data from various information sources and instantly grasp trends by various attributes such as age and gender.

[0134] A "search query" is a word or phrase that a user enters to retrieve specific information.

[0135] A "database" is a collection of data that is organized and managed according to specific rules, allowing for quick search and retrieval.

[0136] An "AI model" is a computational model that uses artificial intelligence technology to analyze data and identify specific patterns or trends.

[0137] "Internet data sources" are information resources accessible via the Internet, such as websites and APIs.

[0138] "JSON format" is an abbreviation for JavaScript Object Notation, a lightweight format for structuring data to improve readability and operability.

[0139] An "attribute" is a specific characteristic or feature used to classify data. For example, age and gender are examples of attributes.

[0140] "Analysis results" refer to the conclusions and insights obtained after analyzing collected data using AI models, etc.

[0141] "Shaping" is the process of preparing analysis results and data in a format that is easy for users to understand.

[0142] A "terminal" is a digital device that a user uses to enter information and view results.

[0143] An "interface" is a means of communication between a user and a system for exchanging information.

[0144] The system based on this invention receives a search query entered by a user, collects relevant data from data sources on the Internet, and analyzes it using an AI model, thereby quickly providing reliable data.

[0145] System Configuration and Operation

[0146] server

[0147] The server has the following features:

[0148] 1. A function to receive search queries from users.

[0149] 2. The ability to collect data from internet data sources based on a search query. Here, we use the requests module to get data from an API and use BeautifulSoup for HTML parsing.

[0150] 3. The function to analyze collected data using AI models. The AI ​​models use machine learning algorithms and deep learning models. To analyze the data, pandas is used to convert it into a data frame and calculate the average value by age and gender using groupby and mean.

[0151] 4. A function to format the analysis results in JSON format and return them to the user's device.

[0152] For example, when the server receives a search query for "movie box office revenue trends," it collects related movie data from APIs on the Internet, analyzes it using an AI model, and then formats box office revenue data by user attributes (age, gender) in JSON format and sends it back to the device.

[0153] Terminal

[0154] The terminal has the following features:

[0155] 1. The ability to provide a search box and allow users to enter a search query.

[0156] 2. A function that provides an interface to the server and sends search queries to the server.

[0157] 3. A function to receive the analysis results returned from the server and display them in a format that is easy for the user to view, such as a graph or text format.

[0158] For example, if a user searches for "movie box office trends" using a smartphone app, the app will display the analysis results obtained from the server as graphs and text, such as "70% of women in their 20s gave high marks to the most recent movie, 'Spider-Man'."

[0159] User

[0160] The user does the following:

[0161] 1. Enter the keyword or phrase you want to research into the search box on your smartphone or PC.

[0162] 2. Click the search button to send the query to the server.

[0163] 3. Wait for the results to appear and use them to investigate and make decisions.

[0164] For example, if a user types in "movie box office trends" and presses the search button, the result displayed will be "70% of women in their 20s highly rated the latest movie." Based on this information, users can quickly grasp the latest movie trends and use it to help with movie selection and marketing strategies.

[0165] Prompt Sentence Examples

[0166] Search Query: Movie Box Office Trends

[0167] Information you need: The latest movie box office statistics and user comments

[0168] Data by age group: 20s, 30s, 40s and over

[0169] Gender-specific data: Male and female data

[0170] Output format: JSON

[0171] This invention allows users to easily obtain efficient and reliable real-time data, making it possible to use useful information in a variety of fields, including news reporting, marketing research, and academic research.

[0172] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0173] Step 1:

[0174] A user enters a keyword or phrase they want to research into the search box on their smartphone or PC. The entered search query is prepared as a request to be sent to the server. The input here is the search query itself, and the output is a request to the server. For example, a user might enter "movie box office trends."

[0175] Step 2:

[0176] The terminal sends a search query from the user to the server. Specifically, the terminal sends the search query as an HTTP request, including the search query in the payload. The input is the user's search query, and the output is an HTTP request.

[0177] Step 3:

[0178] The server analyzes the received search query and collects the relevant data from a data source. The data source can be an API on the Internet or public statistical data, and the data is retrieved using the requests module. The input is the search query in the HTTP request, and the output is the collected raw data. For example, collecting data related to movie box office revenue from an API.

[0179] Step 4:

[0180] The server analyzes the collected data using an AI model. For this analysis, pandas is used to convert the collected data into a data frame, and the groupby and mean methods are used to classify the data by age and gender and identify trends. The input is the collected raw data, and the output is the analyzed data. For example, the collected data can be classified by age and gender (20s, 30s, and over 40s) and analyzed.

[0181] Step 5:

[0182] The server formats the analysis results into JSON format. In this process, the data frame analyzed by pandas is converted into JSON format using the to_dict method. The input is the analyzed data, and the output is JSON format data. For example, the analysis results can be formatted into JSON data such as "70% of women in their 20s gave the movie 'Spider-Man' a high rating."

[0183] Step 6:

[0184] The server returns the analysis results in JSON format to the user device as an HTTP response. The input is the analysis results in JSON format, and the output is an HTTP response. For example, a response including the JSON data of the analysis results is sent to the terminal.

[0185] Step 7:

[0186] The terminal receives the analysis results sent back from the server and displays them in a format that is easy for the user to view. This display can be in the form of graphs or text. The input is the analysis results in the HTTP response, and the output is the visual information displayed to the user. For example, a graph can be generated based on the analysis results, displaying "70% of women in their 20s gave the movie 'Spider-Man' a high rating."

[0187] 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.

[0188] This invention provides a system that allows users to easily obtain specific information in a reliable manner and provides comprehensive information, including sentiment analysis of the original data. The system receives a user's search query, extracts relevant data from a database, analyzes it, forms results, and presents them to the user. It also performs sentiment analysis using an emotion engine and provides the results to the user.

[0189] Server Processing

[0190] The server has the function of collecting statistical data and real-time user comment logs that are publicly available on the Internet and storing them in a database. This data is periodically updated and added to the database.

[0191] When a user's search query is received, the server extracts relevant data from the database based on the query. The extracted data is stored in a temporary buffer and analyzed by an AI model. Furthermore, this analysis incorporates an emotion engine that analyzes the emotional information contained in the retrieved data. During this analysis process, the data is classified based on attributes such as age and gender, and specific trends and emotional tendencies are identified.

[0192] The analysis results are converted into a format such as JSON and sent back to the device as an HTTP response from the server. This response includes not only trends by attribute but also the results of sentiment analysis.

[0193] Terminal handling

[0194] The device, such as a web browser on a user's PC or smartphone, provides an interface to the server. When the user enters a specific query into a search box and presses the search button, the device sends the query to the server.

[0195] When the analysis results are returned from the server, the device analyzes the data and displays it in an easy-to-read format for the user. For example, if a user enters the query "Tokyo Olympics public opinion," the device receives the results sent back from the server and displays not only the results in the form of "70% of men in their 30s have a positive opinion of the Tokyo Olympics," but also the sentiment trend, such as "Many comments show positive sentiment."

[0196] User operations

[0197] The user interacts with the system by entering a keyword or phrase into the search box on their device, clicking the search button, and sending the query to the server. The user waits for the results to appear, and then makes their own research or decision based on the results.

[0198] As a concrete example, to search for information on "Tokyo Olympics public opinion," a user would enter "Tokyo Olympics public opinion" in the search box and press the search button. The server receives this query, extracts all relevant information from the database (for example, comment logs and statistical data), and analyzes it. It also uses an emotion engine to analyze the emotional information contained in the data. The final, formatted data is sent back to the device, which displays it in an easy-to-read format for the user. In addition to trends by attribute, such as "70% of men in their 30s have a positive opinion of the Tokyo Olympics," the user is also presented with emotion analysis results, such as "the majority of total comments show positive emotions."

[0199] This system allows users to easily obtain reliable data and interpret sentiment trends from that data, making it possible to utilize practical information in a wide range of fields, including news reporting, marketing surveys, and academic research.

[0200] The processing flow will be explained below.

[0201] Step 1:

[0202] The server collects statistical data and real-time user comment logs that are publicly available on the Internet, and the collected data is periodically updated and stored in a database.

[0203] Step 2:

[0204] Users enter the keyword or phrase they want to research into the search box on their device's web browser, for example, "Tokyo Olympics public opinion," and click the search button.

[0205] Step 3:

[0206] The device sends the search query entered by the user as form data to the server via a POST request, which includes the keywords or phrases entered by the user.

[0207] Step 4:

[0208] The server analyzes the POST request received from the device and obtains the query, based on which the server connects to the database and searches for the appropriate data.

[0209] Step 5:

[0210] The server stores the data extracted from the database in a temporary buffer, including relevant statistics and user comment logs.

[0211] Step 6:

[0212] The server analyzes the data stored in a temporary buffer using AI models that categorize the data based on attributes such as age and gender, and identify specific trends.

[0213] Step 7:

[0214] The server uses an emotion engine to perform emotion analysis on the data stored in the temporary buffer. The emotion engine extracts user emotions from the comment logs in the database and classifies them as positive, negative, or neutral.

[0215] Step 8:

[0216] The server formats the analysis results, including the sentiment analysis results, into a format such as JSON. The formatted data may include information such as "70% of men in their 30s have a positive opinion of the Tokyo Olympics."

[0217] Step 9:

[0218] The server sends the formatted data to the terminal as an HTTP response, which includes details of the analysis results.

[0219] Step 10:

[0220] The device analyzes the response data received from the server and displays it in an easy-to-read format for the user. The analysis results are displayed in graph and text format, and may show, for example, "70% of men in their 30s have positive opinions." Sentiment analysis results are also displayed, and information such as "The majority of comments express positive sentiment" is presented.

[0221] Step 11:

[0222] Users can view the results displayed on their devices and obtain the information they need. They can then use the data to conduct their own research and make decisions. This data includes demographic trends as well as sentiment analysis results, allowing for deeper insights.

[0223] Example 2

[0224] 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."

[0225] In today's information society, it is difficult for users to quickly obtain specific information in a reliable manner. Furthermore, advanced analytical skills are required to interpret emotional trends from the information obtained, making sentiment analysis a high hurdle for average users. Furthermore, there is a lack of a means to centrally manage various data and present it in a visually understandable manner. This presents a challenge for users, making it difficult to make quick and accurate decisions.

[0226] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0227] In this invention, the server includes means for receiving a search query entered by a user and extracting corresponding data from a database, means for analyzing the extracted data to identify trends for each attribute, emotion analysis means for analyzing emotion information contained in the extracted data, and means for forming and presenting the analysis results to the user. This allows the user to quickly and easily obtain highly reliable data and understand emotional trends from that data. In addition, because the information is presented in a visually easy-to-understand format, the user can make decisions quickly based on the analysis results.

[0228] A "search query" is a keyword or phrase that a user enters to retrieve specific information.

[0229] A "database" is a structured collection of data for efficiently storing, managing, and retrieving large amounts of data.

[0230] "Extraction" is the process of retrieving relevant information from a database based on specific criteria.

[0231] "Analysis" is the act of understanding the information contained in data and deriving specific patterns or trends.

[0232] An "attribute" is a specific characteristic or category used to classify data, such as age or gender.

[0233] "Emotional information" is information that indicates the emotional tendency (positive, negative, neutral, etc.) contained in the data.

[0234] "Emotion analysis means" refers to functions and tools for analyzing emotional information contained in data and identifying emotional trends.

[0235] "Shaping" is an operation that arranges the analysis results in a form that is easy for the user to understand.

[0236] "Presenting" is the act of displaying or providing shaped information to a user.

[0237] An "interface" refers to the means by which a user can interact with a system, as well as the screens and tools that allow a user to operate the system.

[0238] "Statistical data" is a collection of data that compiles numerical information about a specific phenomenon.

[0239] A "user comment log" is a set of data that records user opinions and impressions posted in real time on the Internet.

[0240] This invention provides a system that allows users to easily obtain specific information in a reliable manner and provides comprehensive information, including sentiment analysis of the original data. The system operates in cooperation with the elements of a server, a terminal, and a user.

[0241] server

[0242] The server has the function of collecting statistical data published on the Internet and real-time user comment logs and storing them in a database. Specifically, it periodically obtains data from specified data sources (for example, government statistical bureaus or news site APIs) using automated scripts. The obtained data is stored in the database and updated by merging it with existing data.

[0243] When a search query is received from a user, the server extracts relevant data from the database based on the query. The extracted data is stored in a temporary buffer and analyzed using a natural language processing library (e.g., NLTK, SpaCy). An emotion engine (e.g., VADER, TextBlob) is then used to classify the emotional information contained in the data into positive, negative, or neutral. Furthermore, the data is classified based on attributes such as age and gender, and specific trends are identified.

[0244] The analysis results are converted into JSON format and sent back to the device as an HTTP response, which includes not only trends by attribute but also the results of sentiment analysis.

[0245] Terminal

[0246] A terminal (a device used by a user, such as a PC or smartphone) provides an interface to the server via a web browser. When a user enters a specific query into a search box and presses the search button, the terminal sends the query to the server as an HTTP request. By using JavaScript or AJAX, the query can be sent asynchronously and a response from the server can be waited for.

[0247] When the analysis results are returned from the server, the device analyzes the data and displays it in an easy-to-read format for the user. The analysis results are presented visually using HTML and graphs (e.g., Chart.js). For example, attribute-specific information such as "70% of men in their 30s have a positive opinion of the Tokyo Olympics" or emotional trends such as "Many comments indicate positive sentiment" are visually displayed.

[0248] User

[0249] Users use the system to enter a search query to research specific information. They enter the keyword or phrase they want to look up in the search box, press the search button, and the query is sent to the server. The system returns analytical results in response, allowing the user to conduct their own research and make decisions.

[0250] As a concrete example, if a user wants to search for information on "Tokyo Olympics public opinion," they enter "Tokyo Olympics public opinion" in the search box and press the search button. The server receives this query, extracts and analyzes related statistical data and comment logs. It also utilizes an emotion engine to analyze the emotional information contained in the data, and the final, formatted data is sent back to the device. The device visually presents the analysis results to the user, displaying specific information such as "70% of men in their 30s have a positive opinion of the Tokyo Olympics" along with the emotion analysis results.

[0251] Examples of prompt statements

[0252] Below is an example of a prompt sentence to input to the generative AI model.

[0253] "Please tell me the results of the latest public opinion polls regarding the Tokyo Olympics. I'd particularly like to know the sentiment trends by age and gender. Also, what is the percentage of positive, negative, and neutral opinions?"

[0254] This system allows users to quickly and easily obtain reliable data and interpret sentiment trends from that data, providing actionable information for a wide range of fields, including news reporting, marketing research, and academic research.

[0255] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0256] Step 1:

[0257] The server collects statistical data and real-time user comment logs that are publicly available on the Internet and stores them in a database.

[0258] As input, the server accesses a specified data source (e.g., a government statistical agency or a news site's API) to retrieve new data.

[0259] Specifically, an automated script runs every morning at 3:00 AM, and new data is stored in the database, merging it with existing data to update the database.

[0260] As output, the latest statistics and user comment logs are stored in a database.

[0261] Step 2:

[0262] The user enters a specific search query (e.g., "Tokyo Olympics public opinion") into the device's search box and presses the search button.

[0263] As input, the user enters keywords or phrases related to the information they are interested in into a search box.

[0264] Specifically, when a user clicks the search button, the device sends an HTTP request to the server. The request is sent with a URL in the format http: / / example.com / search?q=Tokyo Olympics+public opinion.

[0265] As an output, the search query is sent to the server.

[0266] Step 3:

[0267] The server analyzes the search query received from the user and extracts relevant data from the database.

[0268] As input, the server receives a search query submitted by a user.

[0269] Specifically, the server breaks down the query into keywords and searches for and extracts the relevant data. For example, in the case of "Tokyo Olympics public opinion," data related to "Tokyo Olympics" and "public opinion" will be extracted.

[0270] As output, relevant statistical data and comment logs are extracted from the database.

[0271] Step 4:

[0272] The server stores the extracted data in a temporary buffer and analyzes it using a natural language processing library (e.g., NLTK, SpaCy).

[0273] As input, the extracted data is stored in a temporary buffer.

[0274] Specifically, the server uses a natural language processing library to analyze the data content and extract the meaning and trends of the text.

[0275] As an output, the analysis results are produced.

[0276] Step 5:

[0277] The server uses a sentiment analysis engine (e.g., VADER, TextBlob) to analyze the sentiment information contained in the data and classify it as positive, negative, or neutral.

[0278] As input, the server receives the parsed data.

[0279] Specifically, the server uses a sentiment analysis engine to analyze the emotional expressions in the data and displays the emotional evaluation of each comment or piece of data as a numerical value. For example, a positive comment is classified as "1" and a negative comment as "-1."

[0280] As an output, sentiment analysis results are generated.

[0281] Step 6:

[0282] The server categorizes the data based on attributes such as age and gender to identify specific trends.

[0283] As input, the server uses the sentiment analysis results.

[0284] Specifically, the server sorts the data based on attributes such as age and gender, and extracts specific trends (for example, 70% of men in their 30s have positive opinions).

[0285] The output is a trend by attribute.

[0286] Step 7:

[0287] The server formats the analysis results in JSON format and returns them to the terminal as an HTTP response.

[0288] As input, the server receives the identified trends and sentiment analysis results.

[0289] Specifically, the server converts the data into JSON format and generates an HTTP response.

[0290] As an output, the server sends a response containing the analysis results to the terminal.

[0291] Step 8:

[0292] The terminal receives the analysis results returned from the server and displays them in an easy-to-read format for the user.

[0293] As input, the terminal receives data in JSON format received from the server.

[0294] Specifically, the device parses the response using JavaScript and displays the data in HTML or a graphical format (e.g., Chart.js).

[0295] As an output, the analysis results are presented to the user in a visually easy-to-understand format.

[0296] Step 9:

[0297] The user bases their research and decisions on the results displayed.

[0298] As input, the user receives the analysis results displayed on the terminal.

[0299] Specifically, users can view the displayed information to gain necessary insights, for example, to help with report creation and marketing strategy development.

[0300] As an output, the user can obtain decision-making and research results.

[0301] (Application example 2)

[0302] 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."

[0303] In conventional information provision systems, when a user searches for a specific keyword, it is difficult to understand other users' reactions to that information or their emotional tendencies. Furthermore, there was a lack of means to efficiently analyze attribute-specific and emotional tendencies in information and provide them to users, so the information available to users was limited. The present invention aims to provide users with more reliable data by analyzing the emotional tendencies of news and articles that interest them and providing information that includes these tendencies.

[0304] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving a search query entered by a user and extracting relevant data from a database, means for analyzing the extracted data to identify trends for each attribute and emotional trends, means for forming the analysis results and presenting them to the user, and means for performing emotional analysis on news and article data and displaying the results. This allows the user to easily grasp more detailed information and the emotional trends associated with that information.

[0305] A "search query" is a word or phrase that a user enters into a system to search for specific information.

[0306] A "database" is an information collection system built to efficiently manage, search, and use data.

[0307] "Extraction" is the process of selecting required data based on specific conditions.

[0308] "Analysis" is the process of processing acquired data and clarifying its meaning and trends.

[0309] An "attribute" refers to a specific characteristic or category of data or an object.

[0310] A "trend" refers to a direction or pattern that multiple data or attributes show in common.

[0311] "Emotional trends" refers to the overall tendency of the emotional reactions of people included in the data.

[0312] "Forming" is the process of preparing acquired data and analysis results in a format that can be easily displayed to users.

[0313] "Presenting" refers to the act of displaying the analysis results in a form that can be used by the user.

[0314] An "interface" refers to the contact points or tools through which users and systems interact with each other.

[0315] A "prompt sentence" refers to an input sentence that prompts a generative AI model to respond or take a specific action.

[0316] The system that realizes this application example allows users to easily and credibly obtain specific information and performs sentiment analysis on that information. Here, we will explain a specific embodiment of a news reader that has a sentiment analysis function for news and article data.

[0317] Server Processing

[0318] The server receives search queries entered by users and uses a backend application to extract relevant data from the database. Django (a Python framework) is used for the backend. The Django application uses TextBlob (a natural language processing library) to analyze the content of news articles extracted from the database. TextBlob's sentiment analysis function can be used to detect positive, negative, and neutral sentiment trends contained in news articles. The analysis results are returned to the frontend in JSON format.

[0319] Front-end processing

[0320] The front-end is developed using React (a JavaScript framework). When a user enters a specific query in the search box and presses the search button, the React application retrieves the query and sends a request to the server using Axios (an HTTP client). The analysis results received from the server are displayed in a user-friendly format using React's state management functionality. This display includes the title, content, and sentiment score of the news article.

[0321] User operations

[0322] A user logs into the system and enters the keyword or phrase they want to research in the search box. For example, they enter the query "coronavirus vaccination" and press the search button. After this operation, the user waits for the analysis results provided by the server. The search results display a list of news articles with sentiment analysis. The sentiment analysis results include information on whether the user's sentiment toward the news article is positive, negative, or neutral.

[0323] Prompt Sentence Examples

[0324] A specific example of a prompt sentence is: Search for the latest news about the "Tokyo Olympics" and display the user's sentiment (positive, negative, neutral) after analyzing it.

[0325] This allows users to understand not only the news and articles that interest them, but also the emotional trends of other users regarding that information. This system is expected to be used in a wide range of fields, including news reporting, marketing surveys, and academic research.

[0326] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0327] Step 1:

[0328] A user enters a query to search for information on a specific topic. For example, they enter the query "coronavirus vaccination" and press the search button. The entered string is sent to the next step.

[0329] Step 2:

[0330] The device receives a query entered by the user and sends it to the backend server as an HTTP request. For example, React is used to manage the state of user input, and Axios is used to send the request to the server. The input is a search query, and the output is an HTTP request.

[0331] Step 3:

[0332] The server processes the request and retrieves the relevant news articles from the database. Specifically, the Django application searches the database based on the query and selects the relevant articles. The input is the search query, and the output is a list of relevant news articles.

[0333] Step 4:

[0334] The server performs sentiment analysis on the extracted news articles. Here, it calculates a sentiment score for each article using TextBlob. Sentiment analysis takes the article text as input and outputs a sentiment score of positive, negative, or neutral.

[0335] Step 5:

[0336] The server formats the sentiment analysis results into JSON format and sends it to the device as a response. Specifically, the news article title, content, and sentiment score are included in the JSON object. The input is the news article and its sentiment score, and the output is the analysis results in JSON format.

[0337] Step 6:

[0338] The device parses the JSON-formatted analysis results received from the server and displays them in an easy-to-read format for the user. Specifically, React renders the data and displays the title, content, and sentiment score of the news article. The input is the JSON-formatted analysis results, and the output is a list of news articles displayed to the user.

[0339] Step 7:

[0340] The user views the displayed news and sentiment analysis results, and inputs additional queries as needed. Based on this input, the process begins again from step 1.

[0341] 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.

[0342] 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.

[0343] 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.

[0344] [Second embodiment]

[0345] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0346] 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.

[0347] 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).

[0348] 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.

[0349] 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.

[0350] 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).

[0351] 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.

[0352] 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.

[0353] 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.

[0354] 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.

[0355] 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.

[0356] 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."

[0357] The present invention provides a system that allows users to easily and reliably obtain specific information by receiving a user's search query, extracting relevant data from a database, analyzing it, forming results, and presenting them to the user.

[0358] Server Processing

[0359] The server has a function to collect statistical data and real-time user comment logs that are publicly available on the Internet and store them in a database. Specifically, automated scripts periodically retrieve data from websites and APIs and add it to the database.

[0360] Next, when a user's search query is received, the server extracts relevant data from the database based on the query. The extracted data is stored in a temporary buffer and analyzed by an AI model. During this analysis process, the data is classified based on attributes such as age and gender, and specific trends are clearly identified.

[0361] The parsed results are formatted and formatted in a user-friendly format (for example, JSON). The server finally returns this formatted data to the terminal as an HTTP response.

[0362] Terminal handling

[0363] The device, such as a web browser on a user's PC or smartphone, provides an interface to the server. When a user enters a specific query into a search box and presses the search button, the device sends the query to the server.

[0364] When the analysis results are returned from the server, the device analyzes the data and displays it in an easy-to-read format for the user. For example, if a user enters the query "Tokyo Olympics public opinion," the device receives the results sent back from the server and displays them in a format such as "70% of men in their 30s have a positive opinion."

[0365] User operations

[0366] The user interacts with the system by entering a keyword or phrase into the search box on their device, clicking the search button, and sending the query to the server. The user waits for the results to appear, and then makes their own research or decision based on the results.

[0367] As a concrete example, to search for information on "Tokyo Olympics public opinion," a user would enter "Tokyo Olympics public opinion" into the search box and press the search button. The server receives this query, extracts and analyzes all relevant information from the database (e.g., comment logs and statistical data), formats the results, and sends them to the terminal. The terminal then displays the analysis results as graphs or text, allowing the user to view the information.

[0368] This system allows users to easily obtain and analyze reliable data, enabling them to utilize practical information in a wide range of fields, including news reporting, marketing research, and academic research.

[0369] The processing flow will be explained below.

[0370] Step 1:

[0371] The server collects publicly available statistical data and real-time user comment logs from the internet, including information obtained from specific websites and APIs. This data is periodically updated and stored in a database.

[0372] Step 2:

[0373] Users enter the keyword or phrase they want to research into the search box on their device's web browser, for example, "Tokyo Olympics public opinion," and click the search button.

[0374] Step 3:

[0375] The device sends the search query entered by the user as form data to the server via a POST request, which includes the keywords or phrases entered by the user.

[0376] Step 4:

[0377] The server analyzes the POST request received from the device and obtains the query, based on which the server connects to the database and searches for the appropriate data.

[0378] Step 5:

[0379] The server stores data extracted from the database in a temporary buffer, including relevant statistical data and user comment logs.

[0380] Step 6:

[0381] The server analyzes the data stored in a temporary buffer using AI models that categorize the data based on attributes such as age and gender, and identify specific trends.

[0382] Step 7:

[0383] The server converts the analysis results from the AI ​​model into a format such as JSON. The converted data may include information such as "70% of men in their 30s have a positive opinion of the Tokyo Olympics."

[0384] Step 8:

[0385] The server sends the formatted data to the terminal as an HTTP response, which includes details of the analysis results.

[0386] Step 9:

[0387] The device analyzes the response data received from the server and displays it in an easy-to-read format for the user. The analysis results are displayed in graphs and text format, and may show something like, "70% of men in their 30s have a positive opinion."

[0388] Step 10:

[0389] Users can check the results displayed on their devices and obtain the necessary information, allowing them to conduct their own research and make decisions based on the data obtained.

[0390] Example 1

[0391] 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."

[0392] In today's information society, users need to be able to quickly and easily obtain reliable information. However, the vast amount of data available on the Internet, with unreliable information scattered throughout, makes it difficult for users to accurately collect and analyze the information they need. Furthermore, advanced analytical techniques and visualization methods are required to convert the collected data into an easily understandable format, but it is not realistic for individual users to do this. A solution to these problems is needed.

[0393] 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.

[0394] In this invention, the server includes means for receiving a search query entered by a user and extracting corresponding data from a database, means for temporarily storing the extracted data in a buffer and analyzing the data using a generative AI model, and means for identifying the analysis results based on trends for each attribute such as age and gender, and converting the results into an easy-to-read format such as JSON format, thereby enabling users to quickly and easily obtain reliable information and view it in an easy-to-understand format.

[0395] A "search query" is a keyword or phrase that a user enters to retrieve specific information.

[0396] A "database" is a system for effectively storing, managing, and searching collected data.

[0397] A "temporary buffer" is a memory area for temporarily storing intermediate results of data processing.

[0398] A "generative AI model" is an algorithm that uses machine learning technology to analyze various data and identify its trends and characteristics.

[0399] "Analysis" is the process of breaking down data according to certain criteria and methods and extracting meaningful information from it.

[0400] "JSON format" is an abbreviation for JavaScript Object Notation, a standard format for expressing data in a human-readable text format.

[0401] An "HTTP response" is a response message sent from a server to a client in communication using the HTTP protocol.

[0402] A "terminal" is an electronic device such as a computer or smartphone that a user uses to access the system.

[0403] A "graph" is a diagram that visually represents data and makes comparisons and trends easy to understand.

[0404] "Text format" refers to a format for visually displaying textual information.

[0405] This invention provides a system that allows users to quickly and reliably obtain specific information. The central components of the system are a server and a terminal, which are operated by the user. The specific operation of each component will be described below.

[0406] Server Operation

[0407] The server has the ability to collect statistical data and real-time user comment logs published on the Internet and store them in a database. This ensures that the latest information is always collected and stored in the database. Tools such as the Python requests library and BeautifulSoup are used to collect the data.

[0408] When a search query is received from a user, the server extracts relevant data from the database based on the query. This data is stored in a temporary buffer and analyzed by a generative AI model (e.g., using TensorFlow or PyTorch). During this analysis process, the data is classified based on attributes such as age and gender, and specific trends are identified. The analysis results are formatted into an easy-to-read format, such as JSON, and sent back to the device as an HTTP response.

[0409] Device behavior

[0410] The device is, for example, a web browser on a user's PC or smartphone, and provides an interface with the server. When a user enters a specific query into a search box and presses the search button, the device sends the query to the server. When the server returns the analysis results, the device analyzes the data and displays the results in an easy-to-read format for the user, for example, using JavaScript and HTML.

[0411] User operations

[0412] The user enters the keyword or phrase they want to research into the device's search box and clicks the search button. The server receives this query, extracts all relevant information from the database, analyzes it using a generative AI model, formats the results, and sends them to the device. The device displays the analysis results, allowing the user to view the information.

[0413] Specific examples

[0414] For example, to search for information on "Tokyo Olympics public opinion," a user would enter "Tokyo Olympics public opinion" in the search box and press the search button. The server receives this query, extracts all relevant information (comment logs and statistical data) from the database, and analyzes it using a generative AI model. The result is then formatted as, for example, "70% of men in their 30s have a positive opinion," and sent to the device. The device then displays the results as graphs and text, which the user can view.

[0415] Prompt Sentence Examples

[0416] Here are some example prompts to input to a generative AI model:

[0417] Example prompt: "Analyze opinions on the Tokyo Olympics by men in their 30s and return the results in JSON format."

[0418] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0419] Step 1:

[0420] Data collection

[0421] The server collects data from external sources. In this step, for example, Python's requests library or BeautifulSoup is used to retrieve statistical data and user comment logs from specific websites or APIs. Examples of collected data include economic data from government statistics APIs and comment logs from social media. The input is data from external sources, and the output is the collected data.

[0422] Step 2:

[0423] Data Storage

[0424] The server stores the collected data in a database. In this step, the specific operation of inserting data into the database is performed, for example, using MySQL or PostgreSQL. The input is the data collected in step 1, and the output is the data stored in the database.

[0425] Step 3:

[0426] Receiving user queries

[0427] The device receives a search query from the user. In this step, the user enters a query into the search box of a web browser and clicks the search button. The query is sent to the server using a JavaScript API such as Fetch. The input is the search query entered by the user, and the output is the query sent to the server.

[0428] Step 4:

[0429] Data Extraction

[0430] The server extracts the relevant data from the database. In this step, data is selected from the database using an SQL statement based on the received query. Specifically, a query such as "SELECT FROM comments WHERE event='Tokyo Olympics' AND topic='public opinion'" is executed. The input is the search query received by the server, and the output is the data extracted from the database.

[0431] Step 5:

[0432] Data analysis

[0433] The server stores the extracted data in a temporary buffer and analyzes it using a generative AI model. In this step, for example, TensorFlow or PyTorch are used to classify the data by age and gender and identify specific trends. The input is the data extracted from the database, and the output is the analysis results.

[0434] Step 6:

[0435] Shaping the result

[0436] The server formats the analysis results into an easy-to-read format such as JSON. In this step, the analysis results are converted into structured data using a Python module such as json. The input is the analysis result from the generative AI model, and the output is the formatted data.

[0437] Step 7:

[0438] Sending the results

[0439] The server sends the formed result data to the terminal as an HTTP response. In this step, the specific operation of returning JSON data to the terminal using the HTTP response is performed. The input is the formed JSON data, and the output is the HTTP response sent to the terminal.

[0440] Step 8:

[0441] Displaying the results

[0442] The device displays the data received from the server in a format that is easy for the user to view. In this step, JavaScript is used to parse the JSON data and display the results as graphs and text using HTML and libraries such as Chart.js. The input is the JSON data received from the server, and the output is the graphs and text displayed to the user.

[0443] (Application example 1)

[0444] 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."

[0445] In recent years, in this age of information overload, it has become increasingly difficult for users to efficiently collect and understand reliable data. In particular, conventional systems are inadequate when it is necessary to quickly grasp data that changes in real time or information integrated from multiple sources. Furthermore, there is a demand for functions that can immediately present the results of data analysis in a visually understandable format. Against this background, there is an urgent need to provide a system that allows users to efficiently obtain and understand reliable information.

[0446] 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.

[0447] In this invention, the server includes means for receiving a search query entered by a user and extracting corresponding data from a database, means for analyzing the extracted data to identify trends by attribute, means for formatting the analysis results and presenting them to the user, means for collecting data from data sources on the Internet based on the search query, means for analyzing the collected data using an AI model, and means for formatting the analysis results in JSON format and returning them to the user terminal. This enables users to quickly obtain reliable data from various information sources and instantly grasp trends by various attributes such as age and gender.

[0448] A "search query" is a word or phrase that a user enters to retrieve specific information.

[0449] A "database" is a collection of data that is organized and managed according to specific rules, allowing for quick search and retrieval.

[0450] An "AI model" is a computational model that uses artificial intelligence technology to analyze data and identify specific patterns or trends.

[0451] "Internet data sources" are information resources accessible via the Internet, such as websites and APIs.

[0452] "JSON format" is an abbreviation for JavaScript Object Notation, a lightweight format for structuring data to improve readability and operability.

[0453] An "attribute" is a specific characteristic or feature used to classify data. For example, age and gender are examples of attributes.

[0454] "Analysis results" refer to the conclusions and insights obtained after analyzing collected data using AI models, etc.

[0455] "Shaping" is the process of preparing analysis results and data in a format that is easy for users to understand.

[0456] A "terminal" is a digital device that a user uses to enter information and view results.

[0457] An "interface" is a means of communication between a user and a system for exchanging information.

[0458] The system based on this invention receives a search query entered by a user, collects relevant data from data sources on the Internet, and analyzes it using an AI model, thereby quickly providing reliable data.

[0459] System Configuration and Operation

[0460] server

[0461] The server has the following features:

[0462] 1. A function to receive search queries from users.

[0463] 2. The ability to collect data from internet data sources based on a search query. Here, we use the requests module to get data from an API and use BeautifulSoup for HTML parsing.

[0464] 3. The function to analyze collected data using AI models. The AI ​​models use machine learning algorithms and deep learning models. To analyze the data, pandas is used to convert it into a data frame and calculate the average value by age and gender using groupby and mean.

[0465] 4. A function to format the analysis results in JSON format and return them to the user's device.

[0466] For example, when the server receives a search query for "movie box office revenue trends," it collects related movie data from APIs on the Internet, analyzes it using an AI model, and then formats box office revenue data by user attributes (age, gender) in JSON format and sends it back to the device.

[0467] Terminal

[0468] The terminal has the following features:

[0469] 1. The ability to provide a search box and allow users to enter a search query.

[0470] 2. A function that provides an interface to the server and sends search queries to the server.

[0471] 3. A function to receive the analysis results returned from the server and display them in a format that is easy for the user to view, such as a graph or text format.

[0472] For example, if a user searches for "movie box office trends" using a smartphone app, the app will display the analysis results obtained from the server as graphs and text, such as "70% of women in their 20s gave high marks to the most recent movie, 'Spider-Man'."

[0473] User

[0474] The user does the following:

[0475] 1. Enter the keyword or phrase you want to research into the search box on your smartphone or PC.

[0476] 2. Click the search button to send the query to the server.

[0477] 3. Wait for the results to appear and use them to investigate and make decisions.

[0478] For example, if a user types in "movie box office trends" and presses the search button, the result displayed will be "70% of women in their 20s highly rated the latest movie." Based on this information, users can quickly grasp the latest movie trends and use it to help with movie selection and marketing strategies.

[0479] Prompt Sentence Examples

[0480] Search Query: Movie Box Office Trends

[0481] Information you need: The latest movie box office statistics and user comments

[0482] Data by age group: 20s, 30s, 40s and over

[0483] Gender-specific data: Male and female data

[0484] Output format: JSON

[0485] This invention allows users to easily obtain efficient and reliable real-time data, making it possible to use useful information in a variety of fields, including news reporting, marketing research, and academic research.

[0486] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0487] Step 1:

[0488] A user enters a keyword or phrase they want to research into the search box on their smartphone or PC. The entered search query is prepared as a request to be sent to the server. The input here is the search query itself, and the output is a request to the server. For example, a user might enter "movie box office trends."

[0489] Step 2:

[0490] The terminal sends a search query from the user to the server. Specifically, the terminal sends the search query as an HTTP request, including the search query in the payload. The input is the user's search query, and the output is an HTTP request.

[0491] Step 3:

[0492] The server analyzes the received search query and collects the relevant data from a data source. The data source can be an API on the Internet or public statistical data, and the data is retrieved using the requests module. The input is the search query in the HTTP request, and the output is the collected raw data. For example, collecting data related to movie box office revenue from an API.

[0493] Step 4:

[0494] The server analyzes the collected data using an AI model. For this analysis, pandas is used to convert the collected data into a data frame, and the groupby and mean methods are used to classify the data by age and gender and identify trends. The input is the collected raw data, and the output is the analyzed data. For example, the collected data can be classified by age and gender (20s, 30s, and over 40s) and analyzed.

[0495] Step 5:

[0496] The server formats the analysis results into JSON format. In this process, the data frame analyzed by pandas is converted into JSON format using the to_dict method. The input is the analyzed data, and the output is JSON format data. For example, the analysis results can be formatted into JSON data such as "70% of women in their 20s gave the movie 'Spider-Man' a high rating."

[0497] Step 6:

[0498] The server returns the analysis results in JSON format to the user device as an HTTP response. The input is the analysis results in JSON format, and the output is an HTTP response. For example, a response including the JSON data of the analysis results is sent to the terminal.

[0499] Step 7:

[0500] The terminal receives the analysis results sent back from the server and displays them in a format that is easy for the user to view. This display can be in the form of graphs or text. The input is the analysis results in the HTTP response, and the output is the visual information displayed to the user. For example, a graph can be generated based on the analysis results, displaying "70% of women in their 20s gave the movie 'Spider-Man' a high rating."

[0501] 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.

[0502] This invention provides a system that allows users to easily obtain specific information in a reliable manner and provides comprehensive information, including sentiment analysis of the original data. The system receives a user's search query, extracts relevant data from a database, analyzes it, forms results, and presents them to the user. It also performs sentiment analysis using an emotion engine and provides the results to the user.

[0503] Server Processing

[0504] The server has the function of collecting statistical data and real-time user comment logs that are publicly available on the Internet and storing them in a database. This data is periodically updated and added to the database.

[0505] When a user's search query is received, the server extracts relevant data from the database based on the query. The extracted data is stored in a temporary buffer and analyzed by an AI model. Furthermore, this analysis incorporates an emotion engine that analyzes the emotional information contained in the retrieved data. During this analysis process, the data is classified based on attributes such as age and gender, and specific trends and emotional tendencies are identified.

[0506] The analysis results are converted into a format such as JSON and sent back to the device as an HTTP response from the server. This response includes not only trends by attribute but also the results of sentiment analysis.

[0507] Terminal handling

[0508] The device, such as a web browser on a user's PC or smartphone, provides an interface to the server. When the user enters a specific query into a search box and presses the search button, the device sends the query to the server.

[0509] When the analysis results are returned from the server, the device analyzes the data and displays it in an easy-to-read format for the user. For example, if a user enters the query "Tokyo Olympics public opinion," the device receives the results sent back from the server and displays not only the results in the form of "70% of men in their 30s have a positive opinion of the Tokyo Olympics," but also the sentiment trend, such as "Many comments show positive sentiment."

[0510] User operations

[0511] The user interacts with the system by entering a keyword or phrase into the search box on their device, clicking the search button, and sending the query to the server. The user waits for the results to appear, and then makes their own research or decision based on the results.

[0512] As a concrete example, to search for information on "Tokyo Olympics public opinion," a user would enter "Tokyo Olympics public opinion" in the search box and press the search button. The server receives this query, extracts all relevant information from the database (for example, comment logs and statistical data), and analyzes it. It also uses an emotion engine to analyze the emotional information contained in the data. The final, formatted data is sent back to the device, which displays it in an easy-to-read format for the user. In addition to trends by attribute, such as "70% of men in their 30s have a positive opinion of the Tokyo Olympics," the user is also presented with emotion analysis results, such as "the majority of total comments show positive emotions."

[0513] This system allows users to easily obtain reliable data and interpret sentiment trends from that data, making it possible to utilize practical information in a wide range of fields, including news reporting, marketing surveys, and academic research.

[0514] The processing flow will be explained below.

[0515] Step 1:

[0516] The server collects statistical data and real-time user comment logs that are publicly available on the Internet, and the collected data is periodically updated and stored in a database.

[0517] Step 2:

[0518] Users enter the keyword or phrase they want to research into the search box on their device's web browser, for example, "Tokyo Olympics public opinion," and click the search button.

[0519] Step 3:

[0520] The device sends the search query entered by the user as form data to the server via a POST request, which includes the keywords or phrases entered by the user.

[0521] Step 4:

[0522] The server analyzes the POST request received from the device and obtains the query, based on which the server connects to the database and searches for the appropriate data.

[0523] Step 5:

[0524] The server stores the data extracted from the database in a temporary buffer, including relevant statistics and user comment logs.

[0525] Step 6:

[0526] The server analyzes the data stored in a temporary buffer using AI models that categorize the data based on attributes such as age and gender, and identify specific trends.

[0527] Step 7:

[0528] The server uses an emotion engine to perform emotion analysis on the data stored in the temporary buffer. The emotion engine extracts user emotions from the comment logs in the database and classifies them as positive, negative, or neutral.

[0529] Step 8:

[0530] The server formats the analysis results, including the sentiment analysis results, into a format such as JSON. The formatted data may include information such as "70% of men in their 30s have a positive opinion of the Tokyo Olympics."

[0531] Step 9:

[0532] The server sends the formatted data to the terminal as an HTTP response, which includes details of the analysis results.

[0533] Step 10:

[0534] The device analyzes the response data received from the server and displays it in an easy-to-read format for the user. The analysis results are displayed in graph and text format, and may show, for example, "70% of men in their 30s have positive opinions." Sentiment analysis results are also displayed, and information such as "The majority of comments express positive sentiment" is presented.

[0535] Step 11:

[0536] Users can view the results displayed on their devices and obtain the information they need. They can then use the data to conduct their own research and make decisions. This data includes demographic trends as well as sentiment analysis results, allowing for deeper insights.

[0537] Example 2

[0538] 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."

[0539] In today's information society, it is difficult for users to quickly obtain specific information in a reliable manner. Furthermore, advanced analytical skills are required to interpret emotional trends from the information obtained, making sentiment analysis a high hurdle for average users. Furthermore, there is a lack of a means to centrally manage various data and present it in a visually understandable manner. This presents a challenge for users, making it difficult to make quick and accurate decisions.

[0540] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0541] In this invention, the server includes means for receiving a search query entered by a user and extracting corresponding data from a database, means for analyzing the extracted data to identify trends for each attribute, emotion analysis means for analyzing emotion information contained in the extracted data, and means for forming and presenting the analysis results to the user. This allows the user to quickly and easily obtain highly reliable data and understand emotional trends from that data. In addition, because the information is presented in a visually easy-to-understand format, the user can make decisions quickly based on the analysis results.

[0542] A "search query" is a keyword or phrase that a user enters to retrieve specific information.

[0543] A "database" is a structured collection of data for efficiently storing, managing, and retrieving large amounts of data.

[0544] "Extraction" is the process of retrieving relevant information from a database based on specific criteria.

[0545] "Analysis" is the act of understanding the information contained in data and deriving specific patterns or trends.

[0546] An "attribute" is a specific characteristic or category used to classify data, such as age or gender.

[0547] "Emotional information" is information that indicates the emotional tendency (positive, negative, neutral, etc.) contained in the data.

[0548] "Emotion analysis means" refers to functions and tools for analyzing emotional information contained in data and identifying emotional trends.

[0549] "Shaping" is an operation that arranges the analysis results in a form that is easy for the user to understand.

[0550] "Presenting" is the act of displaying or providing shaped information to a user.

[0551] An "interface" refers to the means by which a user can interact with a system, as well as the screens and tools that allow a user to operate the system.

[0552] "Statistical data" is a collection of data that compiles numerical information about a specific phenomenon.

[0553] A "user comment log" is a set of data that records user opinions and impressions posted in real time on the Internet.

[0554] This invention provides a system that allows users to easily obtain specific information in a reliable manner and provides comprehensive information, including sentiment analysis of the original data. The system operates in cooperation with the elements of a server, a terminal, and a user.

[0555] server

[0556] The server has the function of collecting statistical data published on the Internet and real-time user comment logs and storing them in a database. Specifically, it periodically obtains data from specified data sources (for example, government statistical bureaus or news site APIs) using automated scripts. The obtained data is stored in the database and updated by merging it with existing data.

[0557] When a search query is received from a user, the server extracts relevant data from the database based on the query. The extracted data is stored in a temporary buffer and analyzed using a natural language processing library (e.g., NLTK, SpaCy). An emotion engine (e.g., VADER, TextBlob) is then used to classify the emotional information contained in the data into positive, negative, or neutral. Furthermore, the data is classified based on attributes such as age and gender, and specific trends are identified.

[0558] The analysis results are converted into JSON format and sent back to the device as an HTTP response, which includes not only trends by attribute but also the results of sentiment analysis.

[0559] Terminal

[0560] A terminal (a device used by a user, such as a PC or smartphone) provides an interface to the server via a web browser. When a user enters a specific query into a search box and presses the search button, the terminal sends the query to the server as an HTTP request. By using JavaScript or AJAX, the query can be sent asynchronously and a response from the server can be waited for.

[0561] When the analysis results are returned from the server, the device analyzes the data and displays it in an easy-to-read format for the user. The analysis results are presented visually using HTML and graphs (e.g., Chart.js). For example, attribute-specific information such as "70% of men in their 30s have a positive opinion of the Tokyo Olympics" or emotional trends such as "Many comments indicate positive sentiment" are visually displayed.

[0562] User

[0563] Users use the system to enter a search query to research specific information. They enter the keyword or phrase they want to look up in the search box, press the search button, and the query is sent to the server. The system returns analytical results in response, allowing the user to conduct their own research and make decisions.

[0564] As a concrete example, if a user wants to search for information on "Tokyo Olympics public opinion," they enter "Tokyo Olympics public opinion" in the search box and press the search button. The server receives this query, extracts and analyzes related statistical data and comment logs. It also utilizes an emotion engine to analyze the emotional information contained in the data, and the final, formatted data is sent back to the device. The device visually presents the analysis results to the user, displaying specific information such as "70% of men in their 30s have a positive opinion of the Tokyo Olympics" along with the emotion analysis results.

[0565] Examples of prompt statements

[0566] Below is an example of a prompt sentence to input to the generative AI model.

[0567] "Please tell me the results of the latest public opinion polls regarding the Tokyo Olympics. I'd particularly like to know the sentiment trends by age and gender. Also, what is the percentage of positive, negative, and neutral opinions?"

[0568] This system allows users to quickly and easily obtain reliable data and interpret sentiment trends from that data, providing actionable information for a wide range of fields, including news reporting, marketing research, and academic research.

[0569] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0570] Step 1:

[0571] The server collects statistical data and real-time user comment logs that are publicly available on the Internet and stores them in a database.

[0572] As input, the server accesses a specified data source (e.g., a government statistical agency or a news site's API) to retrieve new data.

[0573] Specifically, an automated script runs every morning at 3:00 AM, and new data is stored in the database, merging it with existing data to update the database.

[0574] As output, the latest statistics and user comment logs are stored in a database.

[0575] Step 2:

[0576] The user enters a specific search query (e.g., "Tokyo Olympics public opinion") into the device's search box and presses the search button.

[0577] As input, the user enters keywords or phrases related to the information they are interested in into a search box.

[0578] Specifically, when a user clicks the search button, the device sends an HTTP request to the server. The request is sent with a URL in the format http: / / example.com / search?q=Tokyo Olympics+public opinion.

[0579] As an output, the search query is sent to the server.

[0580] Step 3:

[0581] The server analyzes the search query received from the user and extracts relevant data from the database.

[0582] As input, the server receives a search query submitted by a user.

[0583] Specifically, the server breaks down the query into keywords and searches for and extracts the relevant data. For example, in the case of "Tokyo Olympics public opinion," data related to "Tokyo Olympics" and "public opinion" will be extracted.

[0584] As output, relevant statistical data and comment logs are extracted from the database.

[0585] Step 4:

[0586] The server stores the extracted data in a temporary buffer and analyzes it using a natural language processing library (e.g., NLTK, SpaCy).

[0587] As input, the extracted data is stored in a temporary buffer.

[0588] Specifically, the server uses a natural language processing library to analyze the data content and extract the meaning and trends of the text.

[0589] As an output, the analysis results are produced.

[0590] Step 5:

[0591] The server uses a sentiment analysis engine (e.g., VADER, TextBlob) to analyze the sentiment information contained in the data and classify it as positive, negative, or neutral.

[0592] As input, the server receives the parsed data.

[0593] Specifically, the server uses a sentiment analysis engine to analyze the emotional expressions in the data and displays the emotional evaluation of each comment or piece of data as a numerical value. For example, a positive comment is classified as "1" and a negative comment as "-1."

[0594] As an output, sentiment analysis results are generated.

[0595] Step 6:

[0596] The server categorizes the data based on attributes such as age and gender to identify specific trends.

[0597] As input, the server uses the sentiment analysis results.

[0598] Specifically, the server sorts the data based on attributes such as age and gender, and extracts specific trends (for example, 70% of men in their 30s have positive opinions).

[0599] The output is a trend by attribute.

[0600] Step 7:

[0601] The server formats the analysis results in JSON format and returns them to the terminal as an HTTP response.

[0602] As input, the server receives the identified trends and sentiment analysis results.

[0603] Specifically, the server converts the data into JSON format and generates an HTTP response.

[0604] As an output, the server sends a response containing the analysis results to the terminal.

[0605] Step 8:

[0606] The terminal receives the analysis results returned from the server and displays them in an easy-to-read format for the user.

[0607] As input, the terminal receives data in JSON format received from the server.

[0608] Specifically, the device parses the response using JavaScript and displays the data in HTML or a graphical format (e.g., Chart.js).

[0609] As an output, the analysis results are presented to the user in a visually easy-to-understand format.

[0610] Step 9:

[0611] The user bases their research and decisions on the results displayed.

[0612] As input, the user receives the analysis results displayed on the terminal.

[0613] Specifically, users can view the displayed information to gain necessary insights, for example, to help with report creation and marketing strategy development.

[0614] As an output, the user can obtain decision-making and research results.

[0615] (Application example 2)

[0616] 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."

[0617] In conventional information provision systems, when a user searches for a specific keyword, it is difficult to understand other users' reactions to that information or their emotional tendencies. Furthermore, there was a lack of means to efficiently analyze attribute-specific and emotional tendencies in information and provide them to users, so the information available to users was limited. The present invention aims to provide users with more reliable data by analyzing the emotional tendencies of news and articles that interest them and providing information that includes these tendencies.

[0618] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving a search query entered by a user and extracting relevant data from a database, means for analyzing the extracted data to identify trends for each attribute and emotional trends, means for forming the analysis results and presenting them to the user, and means for performing emotional analysis on news and article data and displaying the results. This allows the user to easily grasp more detailed information and the emotional trends associated with that information.

[0619] A "search query" is a word or phrase that a user enters into a system to search for specific information.

[0620] A "database" is an information collection system built to efficiently manage, search, and use data.

[0621] "Extraction" is the process of selecting required data based on specific conditions.

[0622] "Analysis" is the process of processing acquired data and clarifying its meaning and trends.

[0623] An "attribute" refers to a specific characteristic or category of data or an object.

[0624] A "trend" refers to a direction or pattern that multiple data or attributes show in common.

[0625] "Emotional trends" refers to the overall tendency of the emotional reactions of people included in the data.

[0626] "Forming" is the process of preparing acquired data and analysis results in a format that can be easily displayed to users.

[0627] "Presenting" refers to the act of displaying the analysis results in a form that can be used by the user.

[0628] An "interface" refers to the contact points or tools through which users and systems interact with each other.

[0629] A "prompt sentence" refers to an input sentence that prompts a generative AI model to respond or take a specific action.

[0630] The system that realizes this application example allows users to easily and credibly obtain specific information and performs sentiment analysis on that information. Here, we will explain a specific embodiment of a news reader that has a sentiment analysis function for news and article data.

[0631] Server Processing

[0632] The server receives search queries entered by users and uses a backend application to extract relevant data from the database. Django (a Python framework) is used for the backend. The Django application uses TextBlob (a natural language processing library) to analyze the content of news articles extracted from the database. TextBlob's sentiment analysis function can be used to detect positive, negative, and neutral sentiment trends contained in news articles. The analysis results are returned to the frontend in JSON format.

[0633] Front-end processing

[0634] The front-end is developed using React (a JavaScript framework). When a user enters a specific query in the search box and presses the search button, the React application retrieves the query and sends a request to the server using Axios (an HTTP client). The analysis results received from the server are displayed in a user-friendly format using React's state management functionality. This display includes the title, content, and sentiment score of the news article.

[0635] User operations

[0636] A user logs into the system and enters the keyword or phrase they want to research in the search box. For example, they enter the query "coronavirus vaccination" and press the search button. After this operation, the user waits for the analysis results provided by the server. The search results display a list of news articles with sentiment analysis. The sentiment analysis results include information on whether the user's sentiment toward the news article is positive, negative, or neutral.

[0637] Prompt Sentence Examples

[0638] A specific example of a prompt sentence is: Search for the latest news about the "Tokyo Olympics" and display the user's sentiment (positive, negative, neutral) after analyzing it.

[0639] This allows users to understand not only the news and articles that interest them, but also the emotional trends of other users regarding that information. This system is expected to be used in a wide range of fields, including news reporting, marketing surveys, and academic research.

[0640] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0641] Step 1:

[0642] A user enters a query to search for information on a specific topic. For example, they enter the query "coronavirus vaccination" and press the search button. The entered string is sent to the next step.

[0643] Step 2:

[0644] The device receives a query entered by the user and sends it to the backend server as an HTTP request. For example, React is used to manage the state of user input, and Axios is used to send the request to the server. The input is a search query, and the output is an HTTP request.

[0645] Step 3:

[0646] The server processes the request and retrieves the relevant news articles from the database. Specifically, the Django application searches the database based on the query and selects the relevant articles. The input is the search query, and the output is a list of relevant news articles.

[0647] Step 4:

[0648] The server performs sentiment analysis on the extracted news articles. Here, it calculates a sentiment score for each article using TextBlob. Sentiment analysis takes the article text as input and outputs a sentiment score of positive, negative, or neutral.

[0649] Step 5:

[0650] The server formats the sentiment analysis results into JSON format and sends it to the device as a response. Specifically, the news article title, content, and sentiment score are included in the JSON object. The input is the news article and its sentiment score, and the output is the analysis results in JSON format.

[0651] Step 6:

[0652] The device parses the JSON-formatted analysis results received from the server and displays them in an easy-to-read format for the user. Specifically, React renders the data and displays the title, content, and sentiment score of the news article. The input is the JSON-formatted analysis results, and the output is a list of news articles displayed to the user.

[0653] Step 7:

[0654] The user views the displayed news and sentiment analysis results, and inputs additional queries as needed. Based on this input, the process begins again from step 1.

[0655] 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.

[0656] 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.

[0657] 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.

[0658] [Third embodiment]

[0659] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0660] 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.

[0661] 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).

[0662] 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.

[0663] 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.

[0664] 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).

[0665] 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.

[0666] 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.

[0667] 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.

[0668] 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.

[0669] 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.

[0670] 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."

[0671] The present invention provides a system that allows users to easily and reliably obtain specific information by receiving a user's search query, extracting relevant data from a database, analyzing it, forming results, and presenting them to the user.

[0672] Server Processing

[0673] The server has a function to collect statistical data and real-time user comment logs that are publicly available on the Internet and store them in a database. Specifically, automated scripts periodically retrieve data from websites and APIs and add it to the database.

[0674] Next, when a user's search query is received, the server extracts relevant data from the database based on the query. The extracted data is stored in a temporary buffer and analyzed by an AI model. During this analysis process, the data is classified based on attributes such as age and gender, and specific trends are clearly identified.

[0675] The parsed results are formatted and formatted in a user-friendly format (for example, JSON). The server finally returns this formatted data to the terminal as an HTTP response.

[0676] Terminal handling

[0677] The device, such as a web browser on a user's PC or smartphone, provides an interface to the server. When a user enters a specific query into a search box and presses the search button, the device sends the query to the server.

[0678] When the analysis results are returned from the server, the device analyzes the data and displays it in an easy-to-read format for the user. For example, if a user enters the query "Tokyo Olympics public opinion," the device receives the results sent back from the server and displays them in a format such as "70% of men in their 30s have a positive opinion."

[0679] User operations

[0680] The user interacts with the system by entering a keyword or phrase into the search box on their device, clicking the search button, and sending the query to the server. The user waits for the results to appear, and then makes their own research or decision based on the results.

[0681] As a concrete example, to search for information on "Tokyo Olympics public opinion," a user would enter "Tokyo Olympics public opinion" into the search box and press the search button. The server receives this query, extracts and analyzes all relevant information from the database (e.g., comment logs and statistical data), formats the results, and sends them to the terminal. The terminal then displays the analysis results as graphs or text, allowing the user to view the information.

[0682] This system allows users to easily obtain and analyze reliable data, enabling them to utilize practical information in a wide range of fields, including news reporting, marketing research, and academic research.

[0683] The processing flow will be explained below.

[0684] Step 1:

[0685] The server collects publicly available statistical data and real-time user comment logs from the internet, including information obtained from specific websites and APIs. This data is periodically updated and stored in a database.

[0686] Step 2:

[0687] Users enter the keyword or phrase they want to research into the search box on their device's web browser, for example, "Tokyo Olympics public opinion," and click the search button.

[0688] Step 3:

[0689] The device sends the search query entered by the user as form data to the server via a POST request, which includes the keywords or phrases entered by the user.

[0690] Step 4:

[0691] The server analyzes the POST request received from the device and obtains the query, based on which the server connects to the database and searches for the appropriate data.

[0692] Step 5:

[0693] The server stores data extracted from the database in a temporary buffer, including relevant statistical data and user comment logs.

[0694] Step 6:

[0695] The server analyzes the data stored in a temporary buffer using AI models that categorize the data based on attributes such as age and gender, and identify specific trends.

[0696] Step 7:

[0697] The server converts the analysis results from the AI ​​model into a format such as JSON. The converted data may include information such as "70% of men in their 30s have a positive opinion of the Tokyo Olympics."

[0698] Step 8:

[0699] The server sends the formatted data to the terminal as an HTTP response, which includes details of the analysis results.

[0700] Step 9:

[0701] The device analyzes the response data received from the server and displays it in an easy-to-read format for the user. The analysis results are displayed in graphs and text format, and may show something like, "70% of men in their 30s have a positive opinion."

[0702] Step 10:

[0703] Users can check the results displayed on their devices and obtain the necessary information, allowing them to conduct their own research and make decisions based on the data obtained.

[0704] Example 1

[0705] 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."

[0706] In today's information society, users need to be able to quickly and easily obtain reliable information. However, the vast amount of data available on the Internet, with unreliable information scattered throughout, makes it difficult for users to accurately collect and analyze the information they need. Furthermore, advanced analytical techniques and visualization methods are required to convert the collected data into an easily understandable format, but it is not realistic for individual users to do this. A solution to these problems is needed.

[0707] 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.

[0708] In this invention, the server includes means for receiving a search query entered by a user and extracting corresponding data from a database, means for temporarily storing the extracted data in a buffer and analyzing the data using a generative AI model, and means for identifying the analysis results based on trends for each attribute such as age and gender, and converting the results into an easy-to-read format such as JSON format, thereby enabling users to quickly and easily obtain reliable information and view it in an easy-to-understand format.

[0709] A "search query" is a keyword or phrase that a user enters to retrieve specific information.

[0710] A "database" is a system for effectively storing, managing, and searching collected data.

[0711] A "temporary buffer" is a memory area for temporarily storing intermediate results of data processing.

[0712] A "generative AI model" is an algorithm that uses machine learning technology to analyze various data and identify its trends and characteristics.

[0713] "Analysis" is the process of breaking down data according to certain criteria and methods and extracting meaningful information from it.

[0714] "JSON format" is an abbreviation for JavaScript Object Notation, a standard format for expressing data in a human-readable text format.

[0715] An "HTTP response" is a response message sent from a server to a client in communication using the HTTP protocol.

[0716] A "terminal" is an electronic device such as a computer or smartphone that a user uses to access the system.

[0717] A "graph" is a diagram that visually represents data and makes comparisons and trends easy to understand.

[0718] "Text format" refers to a format for visually displaying textual information.

[0719] This invention provides a system that allows users to quickly and reliably obtain specific information. The central components of the system are a server and a terminal, which are operated by the user. The specific operation of each component will be described below.

[0720] Server Operation

[0721] The server has the ability to collect statistical data and real-time user comment logs published on the Internet and store them in a database. This ensures that the latest information is always collected and stored in the database. Tools such as the Python requests library and BeautifulSoup are used to collect the data.

[0722] When a search query is received from a user, the server extracts relevant data from the database based on the query. This data is stored in a temporary buffer and analyzed by a generative AI model (e.g., using TensorFlow or PyTorch). During this analysis process, the data is classified based on attributes such as age and gender, and specific trends are identified. The analysis results are formatted into an easy-to-read format, such as JSON, and sent back to the device as an HTTP response.

[0723] Device behavior

[0724] The device is, for example, a web browser on a user's PC or smartphone, and provides an interface with the server. When a user enters a specific query into a search box and presses the search button, the device sends the query to the server. When the server returns the analysis results, the device analyzes the data and displays the results in an easy-to-read format for the user, for example, using JavaScript and HTML.

[0725] User operations

[0726] The user enters the keyword or phrase they want to research into the device's search box and clicks the search button. The server receives this query, extracts all relevant information from the database, analyzes it using a generative AI model, formats the results, and sends them to the device. The device displays the analysis results, allowing the user to view the information.

[0727] Specific examples

[0728] For example, to search for information on "Tokyo Olympics public opinion," a user would enter "Tokyo Olympics public opinion" in the search box and press the search button. The server receives this query, extracts all relevant information (comment logs and statistical data) from the database, and analyzes it using a generative AI model. The result is then formatted as, for example, "70% of men in their 30s have a positive opinion," and sent to the device. The device then displays the results as graphs and text, which the user can view.

[0729] Prompt Sentence Examples

[0730] Here are some example prompts to input to a generative AI model:

[0731] Example prompt: "Analyze opinions on the Tokyo Olympics by men in their 30s and return the results in JSON format."

[0732] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0733] Step 1:

[0734] Data collection

[0735] The server collects data from external sources. In this step, for example, Python's requests library or BeautifulSoup is used to retrieve statistical data and user comment logs from specific websites or APIs. Examples of collected data include economic data from government statistics APIs and comment logs from social media. The input is data from external sources, and the output is the collected data.

[0736] Step 2:

[0737] Data Storage

[0738] The server stores the collected data in a database. In this step, the specific operation of inserting data into the database is performed, for example, using MySQL or PostgreSQL. The input is the data collected in step 1, and the output is the data stored in the database.

[0739] Step 3:

[0740] Receiving user queries

[0741] The device receives a search query from the user. In this step, the user enters a query into the search box of a web browser and clicks the search button. The query is sent to the server using a JavaScript API such as Fetch. The input is the search query entered by the user, and the output is the query sent to the server.

[0742] Step 4:

[0743] Data Extraction

[0744] The server extracts the relevant data from the database. In this step, data is selected from the database using an SQL statement based on the received query. Specifically, a query such as "SELECT FROM comments WHERE event='Tokyo Olympics' AND topic='public opinion'" is executed. The input is the search query received by the server, and the output is the data extracted from the database.

[0745] Step 5:

[0746] Data analysis

[0747] The server stores the extracted data in a temporary buffer and analyzes it using a generative AI model. In this step, for example, TensorFlow or PyTorch are used to classify the data by age and gender and identify specific trends. The input is the data extracted from the database, and the output is the analysis results.

[0748] Step 6:

[0749] Shaping the result

[0750] The server formats the analysis results into an easy-to-read format such as JSON. In this step, the analysis results are converted into structured data using a Python module such as json. The input is the analysis result from the generative AI model, and the output is the formatted data.

[0751] Step 7:

[0752] Sending the results

[0753] The server sends the formed result data to the terminal as an HTTP response. In this step, the specific operation of returning JSON data to the terminal using the HTTP response is performed. The input is the formed JSON data, and the output is the HTTP response sent to the terminal.

[0754] Step 8:

[0755] Displaying the results

[0756] The device displays the data received from the server in a format that is easy for the user to view. In this step, JavaScript is used to parse the JSON data and display the results as graphs and text using HTML and libraries such as Chart.js. The input is the JSON data received from the server, and the output is the graphs and text displayed to the user.

[0757] (Application example 1)

[0758] 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."

[0759] In recent years, in this age of information overload, it has become increasingly difficult for users to efficiently collect and understand reliable data. In particular, conventional systems are inadequate when it is necessary to quickly grasp data that changes in real time or information integrated from multiple sources. Furthermore, there is a demand for functions that can immediately present the results of data analysis in a visually understandable format. Against this background, there is an urgent need to provide a system that allows users to efficiently obtain and understand reliable information.

[0760] 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.

[0761] In this invention, the server includes means for receiving a search query entered by a user and extracting corresponding data from a database, means for analyzing the extracted data to identify trends by attribute, means for formatting the analysis results and presenting them to the user, means for collecting data from data sources on the Internet based on the search query, means for analyzing the collected data using an AI model, and means for formatting the analysis results in JSON format and returning them to the user terminal. This enables users to quickly obtain reliable data from various information sources and instantly grasp trends by various attributes such as age and gender.

[0762] A "search query" is a word or phrase that a user enters to retrieve specific information.

[0763] A "database" is a collection of data that is organized and managed according to specific rules, allowing for quick search and retrieval.

[0764] An "AI model" is a computational model that uses artificial intelligence technology to analyze data and identify specific patterns or trends.

[0765] "Internet data sources" are information resources accessible via the Internet, such as websites and APIs.

[0766] "JSON format" is an abbreviation for JavaScript Object Notation, a lightweight format for structuring data to improve readability and operability.

[0767] An "attribute" is a specific characteristic or feature used to classify data. For example, age and gender are examples of attributes.

[0768] "Analysis results" refer to the conclusions and insights obtained after analyzing collected data using AI models, etc.

[0769] "Shaping" is the process of preparing analysis results and data in a format that is easy for users to understand.

[0770] A "terminal" is a digital device that a user uses to enter information and view results.

[0771] An "interface" is a means of communication between a user and a system for exchanging information.

[0772] The system based on this invention receives a search query entered by a user, collects relevant data from data sources on the Internet, and analyzes it using an AI model, thereby quickly providing reliable data.

[0773] System Configuration and Operation

[0774] server

[0775] The server has the following features:

[0776] 1. A function to receive search queries from users.

[0777] 2. The ability to collect data from internet data sources based on a search query. Here, we use the requests module to get data from an API and use BeautifulSoup for HTML parsing.

[0778] 3. The function to analyze collected data using AI models. The AI ​​models use machine learning algorithms and deep learning models. To analyze the data, pandas is used to convert it into a data frame and calculate the average value by age and gender using groupby and mean.

[0779] 4. A function to format the analysis results in JSON format and return them to the user's device.

[0780] For example, when the server receives a search query for "movie box office revenue trends," it collects related movie data from APIs on the Internet, analyzes it using an AI model, and then formats box office revenue data by user attributes (age, gender) in JSON format and sends it back to the device.

[0781] Terminal

[0782] The terminal has the following features:

[0783] 1. The ability to provide a search box and allow users to enter a search query.

[0784] 2. A function that provides an interface to the server and sends search queries to the server.

[0785] 3. A function to receive the analysis results returned from the server and display them in a format that is easy for the user to view, such as a graph or text format.

[0786] For example, if a user searches for "movie box office trends" using a smartphone app, the app will display the analysis results obtained from the server as graphs and text, such as "70% of women in their 20s gave high marks to the most recent movie, 'Spider-Man'."

[0787] User

[0788] The user does the following:

[0789] 1. Enter the keyword or phrase you want to research into the search box on your smartphone or PC.

[0790] 2. Click the search button to send the query to the server.

[0791] 3. Wait for the results to appear and use them to investigate and make decisions.

[0792] For example, if a user types in "movie box office trends" and presses the search button, the result displayed will be "70% of women in their 20s highly rated the latest movie." Based on this information, users can quickly grasp the latest movie trends and use it to help with movie selection and marketing strategies.

[0793] Prompt Sentence Examples

[0794] Search Query: Movie Box Office Trends

[0795] Information you need: The latest movie box office statistics and user comments

[0796] Data by age group: 20s, 30s, 40s and over

[0797] Gender-specific data: Male and female data

[0798] Output format: JSON

[0799] This invention allows users to easily obtain efficient and reliable real-time data, making it possible to use useful information in a variety of fields, including news reporting, marketing research, and academic research.

[0800] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0801] Step 1:

[0802] A user enters a keyword or phrase they want to research into the search box on their smartphone or PC. The entered search query is prepared as a request to be sent to the server. The input here is the search query itself, and the output is a request to the server. For example, a user might enter "movie box office trends."

[0803] Step 2:

[0804] The terminal sends a search query from the user to the server. Specifically, the terminal sends the search query as an HTTP request, including the search query in the payload. The input is the user's search query, and the output is an HTTP request.

[0805] Step 3:

[0806] The server analyzes the received search query and collects the relevant data from a data source. The data source can be an API on the Internet or public statistical data, and the data is retrieved using the requests module. The input is the search query in the HTTP request, and the output is the collected raw data. For example, collecting data related to movie box office revenue from an API.

[0807] Step 4:

[0808] The server analyzes the collected data using an AI model. For this analysis, pandas is used to convert the collected data into a data frame, and the groupby and mean methods are used to classify the data by age and gender and identify trends. The input is the collected raw data, and the output is the analyzed data. For example, the collected data can be classified by age and gender (20s, 30s, and over 40s) and analyzed.

[0809] Step 5:

[0810] The server formats the analysis results into JSON format. In this process, the data frame analyzed by pandas is converted into JSON format using the to_dict method. The input is the analyzed data, and the output is JSON format data. For example, the analysis results can be formatted into JSON data such as "70% of women in their 20s gave the movie 'Spider-Man' a high rating."

[0811] Step 6:

[0812] The server returns the analysis results in JSON format to the user device as an HTTP response. The input is the analysis results in JSON format, and the output is an HTTP response. For example, a response including the JSON data of the analysis results is sent to the terminal.

[0813] Step 7:

[0814] The terminal receives the analysis results sent back from the server and displays them in a format that is easy for the user to view. This display can be in the form of graphs or text. The input is the analysis results in the HTTP response, and the output is the visual information displayed to the user. For example, a graph can be generated based on the analysis results, displaying "70% of women in their 20s gave the movie 'Spider-Man' a high rating."

[0815] 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.

[0816] This invention provides a system that allows users to easily obtain specific information in a reliable manner and provides comprehensive information, including sentiment analysis of the original data. The system receives a user's search query, extracts relevant data from a database, analyzes it, forms results, and presents them to the user. It also performs sentiment analysis using an emotion engine and provides the results to the user.

[0817] Server Processing

[0818] The server has the function of collecting statistical data and real-time user comment logs that are publicly available on the Internet and storing them in a database. This data is periodically updated and added to the database.

[0819] When a user's search query is received, the server extracts relevant data from the database based on the query. The extracted data is stored in a temporary buffer and analyzed by an AI model. Furthermore, this analysis incorporates an emotion engine that analyzes the emotional information contained in the retrieved data. During this analysis process, the data is classified based on attributes such as age and gender, and specific trends and emotional tendencies are identified.

[0820] The analysis results are converted into a format such as JSON and sent back to the device as an HTTP response from the server. This response includes not only trends by attribute but also the results of sentiment analysis.

[0821] Terminal handling

[0822] The device, such as a web browser on a user's PC or smartphone, provides an interface to the server. When the user enters a specific query into a search box and presses the search button, the device sends the query to the server.

[0823] When the analysis results are returned from the server, the device analyzes the data and displays it in an easy-to-read format for the user. For example, if a user enters the query "Tokyo Olympics public opinion," the device receives the results sent back from the server and displays not only the results in the form of "70% of men in their 30s have a positive opinion of the Tokyo Olympics," but also the sentiment trend, such as "Many comments show positive sentiment."

[0824] User operations

[0825] The user interacts with the system by entering a keyword or phrase into the search box on their device, clicking the search button, and sending the query to the server. The user waits for the results to appear, and then makes their own research or decision based on the results.

[0826] As a concrete example, to search for information on "Tokyo Olympics public opinion," a user would enter "Tokyo Olympics public opinion" in the search box and press the search button. The server receives this query, extracts all relevant information from the database (for example, comment logs and statistical data), and analyzes it. It also uses an emotion engine to analyze the emotional information contained in the data. The final, formatted data is sent back to the device, which displays it in an easy-to-read format for the user. In addition to trends by attribute, such as "70% of men in their 30s have a positive opinion of the Tokyo Olympics," the user is also presented with emotion analysis results, such as "the majority of total comments show positive emotions."

[0827] This system allows users to easily obtain reliable data and interpret sentiment trends from that data, making it possible to utilize practical information in a wide range of fields, including news reporting, marketing surveys, and academic research.

[0828] The processing flow will be explained below.

[0829] Step 1:

[0830] The server collects statistical data and real-time user comment logs that are publicly available on the Internet, and the collected data is periodically updated and stored in a database.

[0831] Step 2:

[0832] Users enter the keyword or phrase they want to research into the search box on their device's web browser, for example, "Tokyo Olympics public opinion," and click the search button.

[0833] Step 3:

[0834] The device sends the search query entered by the user as form data to the server via a POST request, which includes the keywords or phrases entered by the user.

[0835] Step 4:

[0836] The server analyzes the POST request received from the device and obtains the query, based on which the server connects to the database and searches for the appropriate data.

[0837] Step 5:

[0838] The server stores the data extracted from the database in a temporary buffer, including relevant statistics and user comment logs.

[0839] Step 6:

[0840] The server analyzes the data stored in a temporary buffer using AI models that categorize the data based on attributes such as age and gender, and identify specific trends.

[0841] Step 7:

[0842] The server uses an emotion engine to perform emotion analysis on the data stored in the temporary buffer. The emotion engine extracts user emotions from the comment logs in the database and classifies them as positive, negative, or neutral.

[0843] Step 8:

[0844] The server formats the analysis results, including the sentiment analysis results, into a format such as JSON. The formatted data may include information such as "70% of men in their 30s have a positive opinion of the Tokyo Olympics."

[0845] Step 9:

[0846] The server sends the formatted data to the terminal as an HTTP response, which includes details of the analysis results.

[0847] Step 10:

[0848] The device analyzes the response data received from the server and displays it in an easy-to-read format for the user. The analysis results are displayed in graph and text format, and may show, for example, "70% of men in their 30s have positive opinions." Sentiment analysis results are also displayed, and information such as "The majority of comments express positive sentiment" is presented.

[0849] Step 11:

[0850] Users can view the results displayed on their devices and obtain the information they need. They can then use the data to conduct their own research and make decisions. This data includes demographic trends as well as sentiment analysis results, allowing for deeper insights.

[0851] Example 2

[0852] 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."

[0853] In today's information society, it is difficult for users to quickly obtain specific information in a reliable manner. Furthermore, advanced analytical skills are required to interpret emotional trends from the information obtained, making sentiment analysis a high hurdle for average users. Furthermore, there is a lack of a means to centrally manage various data and present it in a visually understandable manner. This presents a challenge for users, making it difficult to make quick and accurate decisions.

[0854] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0855] In this invention, the server includes means for receiving a search query entered by a user and extracting corresponding data from a database, means for analyzing the extracted data to identify trends for each attribute, emotion analysis means for analyzing emotion information contained in the extracted data, and means for forming and presenting the analysis results to the user. This allows the user to quickly and easily obtain highly reliable data and understand emotional trends from that data. In addition, because the information is presented in a visually easy-to-understand format, the user can make decisions quickly based on the analysis results.

[0856] A "search query" is a keyword or phrase that a user enters to retrieve specific information.

[0857] A "database" is a structured collection of data for efficiently storing, managing, and retrieving large amounts of data.

[0858] "Extraction" is the process of retrieving relevant information from a database based on specific criteria.

[0859] "Analysis" is the act of understanding the information contained in data and deriving specific patterns or trends.

[0860] An "attribute" is a specific characteristic or category used to classify data, such as age or gender.

[0861] "Emotional information" is information that indicates the emotional tendency (positive, negative, neutral, etc.) contained in the data.

[0862] "Emotion analysis means" refers to functions and tools for analyzing emotional information contained in data and identifying emotional trends.

[0863] "Shaping" is an operation that arranges the analysis results in a form that is easy for the user to understand.

[0864] "Presenting" is the act of displaying or providing shaped information to a user.

[0865] An "interface" refers to the means by which a user can interact with a system, as well as the screens and tools that allow a user to operate the system.

[0866] "Statistical data" is a collection of data that compiles numerical information about a specific phenomenon.

[0867] A "user comment log" is a set of data that records user opinions and impressions posted in real time on the Internet.

[0868] This invention provides a system that allows users to easily obtain specific information in a reliable manner and provides comprehensive information, including sentiment analysis of the original data. The system operates in cooperation with the elements of a server, a terminal, and a user.

[0869] server

[0870] The server has the function of collecting statistical data published on the Internet and real-time user comment logs and storing them in a database. Specifically, it periodically obtains data from specified data sources (for example, government statistical bureaus or news site APIs) using automated scripts. The obtained data is stored in the database and updated by merging it with existing data.

[0871] When a search query is received from a user, the server extracts relevant data from the database based on the query. The extracted data is stored in a temporary buffer and analyzed using a natural language processing library (e.g., NLTK, SpaCy). An emotion engine (e.g., VADER, TextBlob) is then used to classify the emotional information contained in the data into positive, negative, or neutral. Furthermore, the data is classified based on attributes such as age and gender, and specific trends are identified.

[0872] The analysis results are converted into JSON format and sent back to the device as an HTTP response, which includes not only trends by attribute but also the results of sentiment analysis.

[0873] Terminal

[0874] A terminal (a device used by a user, such as a PC or smartphone) provides an interface to the server via a web browser. When a user enters a specific query into a search box and presses the search button, the terminal sends the query to the server as an HTTP request. By using JavaScript or AJAX, the query can be sent asynchronously and a response from the server can be waited for.

[0875] When the analysis results are returned from the server, the device analyzes the data and displays it in an easy-to-read format for the user. The analysis results are presented visually using HTML and graphs (e.g., Chart.js). For example, attribute-specific information such as "70% of men in their 30s have a positive opinion of the Tokyo Olympics" or emotional trends such as "Many comments indicate positive sentiment" are visually displayed.

[0876] User

[0877] Users use the system to enter a search query to research specific information. They enter the keyword or phrase they want to look up in the search box, press the search button, and the query is sent to the server. The system returns analytical results in response, allowing the user to conduct their own research and make decisions.

[0878] As a concrete example, if a user wants to search for information on "Tokyo Olympics public opinion," they enter "Tokyo Olympics public opinion" in the search box and press the search button. The server receives this query, extracts and analyzes related statistical data and comment logs. It also utilizes an emotion engine to analyze the emotional information contained in the data, and the final, formatted data is sent back to the device. The device visually presents the analysis results to the user, displaying specific information such as "70% of men in their 30s have a positive opinion of the Tokyo Olympics" along with the emotion analysis results.

[0879] Examples of prompt statements

[0880] Below is an example of a prompt sentence to input to the generative AI model.

[0881] "Please tell me the results of the latest public opinion polls regarding the Tokyo Olympics. I'd particularly like to know the sentiment trends by age and gender. Also, what is the percentage of positive, negative, and neutral opinions?"

[0882] This system allows users to quickly and easily obtain reliable data and interpret sentiment trends from that data, providing actionable information for a wide range of fields, including news reporting, marketing research, and academic research.

[0883] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0884] Step 1:

[0885] The server collects statistical data and real-time user comment logs that are publicly available on the Internet and stores them in a database.

[0886] As input, the server accesses a specified data source (e.g., a government statistical agency or a news site's API) to retrieve new data.

[0887] Specifically, an automated script runs every morning at 3:00 AM, and new data is stored in the database, merging it with existing data to update the database.

[0888] As output, the latest statistics and user comment logs are stored in a database.

[0889] Step 2:

[0890] The user enters a specific search query (e.g., "Tokyo Olympics public opinion") into the device's search box and presses the search button.

[0891] As input, the user enters keywords or phrases related to the information they are interested in into a search box.

[0892] Specifically, when a user clicks the search button, the device sends an HTTP request to the server. The request is sent with a URL in the format http: / / example.com / search?q=Tokyo Olympics+public opinion.

[0893] As an output, the search query is sent to the server.

[0894] Step 3:

[0895] The server analyzes the search query received from the user and extracts relevant data from the database.

[0896] As input, the server receives a search query submitted by a user.

[0897] Specifically, the server breaks down the query into keywords and searches for and extracts the relevant data. For example, in the case of "Tokyo Olympics public opinion," data related to "Tokyo Olympics" and "public opinion" will be extracted.

[0898] As output, relevant statistical data and comment logs are extracted from the database.

[0899] Step 4:

[0900] The server stores the extracted data in a temporary buffer and analyzes it using a natural language processing library (e.g., NLTK, SpaCy).

[0901] As input, the extracted data is stored in a temporary buffer.

[0902] Specifically, the server uses a natural language processing library to analyze the data content and extract the meaning and trends of the text.

[0903] As an output, the analysis results are produced.

[0904] Step 5:

[0905] The server uses a sentiment analysis engine (e.g., VADER, TextBlob) to analyze the sentiment information contained in the data and classify it as positive, negative, or neutral.

[0906] As input, the server receives the parsed data.

[0907] Specifically, the server uses a sentiment analysis engine to analyze the emotional expressions in the data and displays the emotional evaluation of each comment or piece of data as a numerical value. For example, a positive comment is classified as "1" and a negative comment as "-1."

[0908] As an output, sentiment analysis results are generated.

[0909] Step 6:

[0910] The server categorizes the data based on attributes such as age and gender to identify specific trends.

[0911] As input, the server uses the sentiment analysis results.

[0912] Specifically, the server sorts the data based on attributes such as age and gender, and extracts specific trends (for example, 70% of men in their 30s have positive opinions).

[0913] The output is a trend by attribute.

[0914] Step 7:

[0915] The server formats the analysis results in JSON format and returns them to the terminal as an HTTP response.

[0916] As input, the server receives the identified trends and sentiment analysis results.

[0917] Specifically, the server converts the data into JSON format and generates an HTTP response.

[0918] As an output, the server sends a response containing the analysis results to the terminal.

[0919] Step 8:

[0920] The terminal receives the analysis results returned from the server and displays them in an easy-to-read format for the user.

[0921] As input, the terminal receives data in JSON format received from the server.

[0922] Specifically, the device parses the response using JavaScript and displays the data in HTML or a graphical format (e.g., Chart.js).

[0923] As an output, the analysis results are presented to the user in a visually easy-to-understand format.

[0924] Step 9:

[0925] The user bases their research and decisions on the results displayed.

[0926] As input, the user receives the analysis results displayed on the terminal.

[0927] Specifically, users can view the displayed information to gain necessary insights, for example, to help with report creation and marketing strategy development.

[0928] As an output, the user can obtain decision-making and research results.

[0929] (Application example 2)

[0930] 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."

[0931] In conventional information provision systems, when a user searches for a specific keyword, it is difficult to understand other users' reactions to that information or their emotional tendencies. Furthermore, there was a lack of means to efficiently analyze attribute-specific and emotional tendencies in information and provide them to users, so the information available to users was limited. The present invention aims to provide users with more reliable data by analyzing the emotional tendencies of news and articles that interest them and providing information that includes these tendencies.

[0932] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving a search query entered by a user and extracting relevant data from a database, means for analyzing the extracted data to identify trends for each attribute and emotional trends, means for forming the analysis results and presenting them to the user, and means for performing emotional analysis on news and article data and displaying the results. This allows the user to easily grasp more detailed information and the emotional trends associated with that information.

[0933] A "search query" is a word or phrase that a user enters into a system to search for specific information.

[0934] A "database" is an information collection system built to efficiently manage, search, and use data.

[0935] "Extraction" is the process of selecting required data based on specific conditions.

[0936] "Analysis" is the process of processing acquired data and clarifying its meaning and trends.

[0937] An "attribute" refers to a specific characteristic or category of data or an object.

[0938] A "trend" refers to a direction or pattern that multiple data or attributes show in common.

[0939] "Emotional trends" refers to the overall tendency of the emotional reactions of people included in the data.

[0940] "Forming" is the process of preparing acquired data and analysis results in a format that can be easily displayed to users.

[0941] "Presenting" refers to the act of displaying the analysis results in a form that can be used by the user.

[0942] An "interface" refers to the contact points or tools through which users and systems interact with each other.

[0943] A "prompt sentence" refers to an input sentence that prompts a generative AI model to respond or take a specific action.

[0944] The system that realizes this application example allows users to easily and credibly obtain specific information and performs sentiment analysis on that information. Here, we will explain a specific embodiment of a news reader that has a sentiment analysis function for news and article data.

[0945] Server Processing

[0946] The server receives search queries entered by users and uses a backend application to extract relevant data from the database. Django (a Python framework) is used for the backend. The Django application uses TextBlob (a natural language processing library) to analyze the content of news articles extracted from the database. TextBlob's sentiment analysis function can be used to detect positive, negative, and neutral sentiment trends contained in news articles. The analysis results are returned to the frontend in JSON format.

[0947] Front-end processing

[0948] The front-end is developed using React (a JavaScript framework). When a user enters a specific query in the search box and presses the search button, the React application retrieves the query and sends a request to the server using Axios (an HTTP client). The analysis results received from the server are displayed in a user-friendly format using React's state management functionality. This display includes the title, content, and sentiment score of the news article.

[0949] User operations

[0950] A user logs into the system and enters the keyword or phrase they want to research in the search box. For example, they enter the query "coronavirus vaccination" and press the search button. After this operation, the user waits for the analysis results provided by the server. The search results display a list of news articles with sentiment analysis. The sentiment analysis results include information on whether the user's sentiment toward the news article is positive, negative, or neutral.

[0951] Prompt Sentence Examples

[0952] A specific example of a prompt sentence is: Search for the latest news about the "Tokyo Olympics" and display the user's sentiment (positive, negative, neutral) after analyzing it.

[0953] This allows users to understand not only the news and articles that interest them, but also the emotional trends of other users regarding that information. This system is expected to be used in a wide range of fields, including news reporting, marketing surveys, and academic research.

[0954] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0955] Step 1:

[0956] A user enters a query to search for information on a specific topic. For example, they enter the query "coronavirus vaccination" and press the search button. The entered string is sent to the next step.

[0957] Step 2:

[0958] The device receives a query entered by the user and sends it to the backend server as an HTTP request. For example, React is used to manage the state of user input, and Axios is used to send the request to the server. The input is a search query, and the output is an HTTP request.

[0959] Step 3:

[0960] The server processes the request and retrieves the relevant news articles from the database. Specifically, the Django application searches the database based on the query and selects the relevant articles. The input is the search query, and the output is a list of relevant news articles.

[0961] Step 4:

[0962] The server performs sentiment analysis on the extracted news articles. Here, it calculates a sentiment score for each article using TextBlob. Sentiment analysis takes the article text as input and outputs a sentiment score of positive, negative, or neutral.

[0963] Step 5:

[0964] The server formats the sentiment analysis results into JSON format and sends it to the device as a response. Specifically, the news article title, content, and sentiment score are included in the JSON object. The input is the news article and its sentiment score, and the output is the analysis results in JSON format.

[0965] Step 6:

[0966] The device parses the JSON-formatted analysis results received from the server and displays them in an easy-to-read format for the user. Specifically, React renders the data and displays the title, content, and sentiment score of the news article. The input is the JSON-formatted analysis results, and the output is a list of news articles displayed to the user.

[0967] Step 7:

[0968] The user views the displayed news and sentiment analysis results, and inputs additional queries as needed. Based on this input, the process begins again from step 1.

[0969] 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.

[0970] 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.

[0971] 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.

[0972] [Fourth embodiment]

[0973] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0974] 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.

[0975] 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).

[0976] 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.

[0977] 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.

[0978] 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).

[0979] 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.

[0980] 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.

[0981] 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.

[0982] 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.

[0983] 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.

[0984] 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.

[0985] 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."

[0986] The present invention provides a system that allows users to easily and reliably obtain specific information by receiving a user's search query, extracting relevant data from a database, analyzing it, forming results, and presenting them to the user.

[0987] Server Processing

[0988] The server has a function to collect statistical data and real-time user comment logs that are publicly available on the Internet and store them in a database. Specifically, automated scripts periodically retrieve data from websites and APIs and add it to the database.

[0989] Next, when a user's search query is received, the server extracts relevant data from the database based on the query. The extracted data is stored in a temporary buffer and analyzed by an AI model. During this analysis process, the data is classified based on attributes such as age and gender, and specific trends are clearly identified.

[0990] The parsed results are formatted and formatted in a user-friendly format (for example, JSON). The server finally returns this formatted data to the terminal as an HTTP response.

[0991] Terminal handling

[0992] The device, such as a web browser on a user's PC or smartphone, provides an interface to the server. When a user enters a specific query into a search box and presses the search button, the device sends the query to the server.

[0993] When the analysis results are returned from the server, the device analyzes the data and displays it in an easy-to-read format for the user. For example, if a user enters the query "Tokyo Olympics public opinion," the device receives the results sent back from the server and displays them in a format such as "70% of men in their 30s have a positive opinion."

[0994] User operations

[0995] The user interacts with the system by entering a keyword or phrase into the search box on their device, clicking the search button, and sending the query to the server. The user waits for the results to appear, and then makes their own research or decision based on the results.

[0996] As a concrete example, to search for information on "Tokyo Olympics public opinion," a user would enter "Tokyo Olympics public opinion" into the search box and press the search button. The server receives this query, extracts and analyzes all relevant information from the database (e.g., comment logs and statistical data), formats the results, and sends them to the terminal. The terminal then displays the analysis results as graphs or text, allowing the user to view the information.

[0997] This system allows users to easily obtain and analyze reliable data, enabling them to utilize practical information in a wide range of fields, including news reporting, marketing research, and academic research.

[0998] The processing flow will be explained below.

[0999] Step 1:

[1000] The server collects publicly available statistical data and real-time user comment logs from the internet, including information obtained from specific websites and APIs. This data is periodically updated and stored in a database.

[1001] Step 2:

[1002] Users enter the keyword or phrase they want to research into the search box on their device's web browser, for example, "Tokyo Olympics public opinion," and click the search button.

[1003] Step 3:

[1004] The device sends the search query entered by the user as form data to the server via a POST request, which includes the keywords or phrases entered by the user.

[1005] Step 4:

[1006] The server analyzes the POST request received from the device and obtains the query, based on which the server connects to the database and searches for the appropriate data.

[1007] Step 5:

[1008] The server stores data extracted from the database in a temporary buffer, including relevant statistical data and user comment logs.

[1009] Step 6:

[1010] The server analyzes the data stored in a temporary buffer using AI models that categorize the data based on attributes such as age and gender, and identify specific trends.

[1011] Step 7:

[1012] The server converts the analysis results from the AI ​​model into a format such as JSON. The converted data may include information such as "70% of men in their 30s have a positive opinion of the Tokyo Olympics."

[1013] Step 8:

[1014] The server sends the formatted data to the terminal as an HTTP response, which includes details of the analysis results.

[1015] Step 9:

[1016] The device analyzes the response data received from the server and displays it in an easy-to-read format for the user. The analysis results are displayed in graphs and text format, and may show something like, "70% of men in their 30s have a positive opinion."

[1017] Step 10:

[1018] Users can check the results displayed on their devices and obtain the necessary information, allowing them to conduct their own research and make decisions based on the data obtained.

[1019] Example 1

[1020] 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."

[1021] In today's information society, users need to be able to quickly and easily obtain reliable information. However, the vast amount of data available on the Internet, with unreliable information scattered throughout, makes it difficult for users to accurately collect and analyze the information they need. Furthermore, advanced analytical techniques and visualization methods are required to convert the collected data into an easily understandable format, but it is not realistic for individual users to do this. A solution to these problems is needed.

[1022] 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.

[1023] In this invention, the server includes means for receiving a search query entered by a user and extracting corresponding data from a database, means for temporarily storing the extracted data in a buffer and analyzing the data using a generative AI model, and means for identifying the analysis results based on trends for each attribute such as age and gender, and converting the results into an easy-to-read format such as JSON format, thereby enabling users to quickly and easily obtain reliable information and view it in an easy-to-understand format.

[1024] A "search query" is a keyword or phrase that a user enters to retrieve specific information.

[1025] A "database" is a system for effectively storing, managing, and searching collected data.

[1026] A "temporary buffer" is a memory area for temporarily storing intermediate results of data processing.

[1027] A "generative AI model" is an algorithm that uses machine learning technology to analyze various data and identify its trends and characteristics.

[1028] "Analysis" is the process of breaking down data according to certain criteria and methods and extracting meaningful information from it.

[1029] "JSON format" is an abbreviation for JavaScript Object Notation, a standard format for expressing data in a human-readable text format.

[1030] An "HTTP response" is a response message sent from a server to a client in communication using the HTTP protocol.

[1031] A "terminal" is an electronic device such as a computer or smartphone that a user uses to access the system.

[1032] A "graph" is a diagram that visually represents data and makes comparisons and trends easy to understand.

[1033] "Text format" refers to a format for visually displaying textual information.

[1034] This invention provides a system that allows users to quickly and reliably obtain specific information. The central components of the system are a server and a terminal, which are operated by the user. The specific operation of each component will be described below.

[1035] Server Operation

[1036] The server has the ability to collect statistical data and real-time user comment logs published on the Internet and store them in a database. This ensures that the latest information is always collected and stored in the database. Tools such as the Python requests library and BeautifulSoup are used to collect the data.

[1037] When a search query is received from a user, the server extracts relevant data from the database based on the query. This data is stored in a temporary buffer and analyzed by a generative AI model (e.g., using TensorFlow or PyTorch). During this analysis process, the data is classified based on attributes such as age and gender, and specific trends are identified. The analysis results are formatted into an easy-to-read format, such as JSON, and sent back to the device as an HTTP response.

[1038] Device behavior

[1039] The device is, for example, a web browser on a user's PC or smartphone, and provides an interface with the server. When a user enters a specific query into a search box and presses the search button, the device sends the query to the server. When the server returns the analysis results, the device analyzes the data and displays the results in an easy-to-read format for the user, for example, using JavaScript and HTML.

[1040] User operations

[1041] The user enters the keyword or phrase they want to research into the device's search box and clicks the search button. The server receives this query, extracts all relevant information from the database, analyzes it using a generative AI model, formats the results, and sends them to the device. The device displays the analysis results, allowing the user to view the information.

[1042] Specific examples

[1043] For example, to search for information on "Tokyo Olympics public opinion," a user would enter "Tokyo Olympics public opinion" in the search box and press the search button. The server receives this query, extracts all relevant information (comment logs and statistical data) from the database, and analyzes it using a generative AI model. The result is then formatted as, for example, "70% of men in their 30s have a positive opinion," and sent to the device. The device then displays the results as graphs and text, which the user can view.

[1044] Prompt Sentence Examples

[1045] Here are some example prompts to input to a generative AI model:

[1046] Example prompt: "Analyze opinions on the Tokyo Olympics by men in their 30s and return the results in JSON format."

[1047] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1048] Step 1:

[1049] Data collection

[1050] The server collects data from external sources. In this step, for example, Python's requests library or BeautifulSoup is used to retrieve statistical data and user comment logs from specific websites or APIs. Examples of collected data include economic data from government statistics APIs and comment logs from social media. The input is data from external sources, and the output is the collected data.

[1051] Step 2:

[1052] Data Storage

[1053] The server stores the collected data in a database. In this step, the specific operation of inserting data into the database is performed, for example, using MySQL or PostgreSQL. The input is the data collected in step 1, and the output is the data stored in the database.

[1054] Step 3:

[1055] Receiving user queries

[1056] The device receives a search query from the user. In this step, the user enters a query into the search box of a web browser and clicks the search button. The query is sent to the server using a JavaScript API such as Fetch. The input is the search query entered by the user, and the output is the query sent to the server.

[1057] Step 4:

[1058] Data Extraction

[1059] The server extracts the relevant data from the database. In this step, data is selected from the database using an SQL statement based on the received query. Specifically, a query such as "SELECT FROM comments WHERE event='Tokyo Olympics' AND topic='public opinion'" is executed. The input is the search query received by the server, and the output is the data extracted from the database.

[1060] Step 5:

[1061] Data analysis

[1062] The server stores the extracted data in a temporary buffer and analyzes it using a generative AI model. In this step, for example, TensorFlow or PyTorch are used to classify the data by age and gender and identify specific trends. The input is the data extracted from the database, and the output is the analysis results.

[1063] Step 6:

[1064] Shaping the result

[1065] The server formats the analysis results into an easy-to-read format such as JSON. In this step, the analysis results are converted into structured data using a Python module such as json. The input is the analysis result from the generative AI model, and the output is the formatted data.

[1066] Step 7:

[1067] Sending the results

[1068] The server sends the formed result data to the terminal as an HTTP response. In this step, the specific operation of returning JSON data to the terminal using the HTTP response is performed. The input is the formed JSON data, and the output is the HTTP response sent to the terminal.

[1069] Step 8:

[1070] Displaying the results

[1071] The device displays the data received from the server in a format that is easy for the user to view. In this step, JavaScript is used to parse the JSON data and display the results as graphs and text using HTML and libraries such as Chart.js. The input is the JSON data received from the server, and the output is the graphs and text displayed to the user.

[1072] (Application example 1)

[1073] 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."

[1074] In recent years, in this age of information overload, it has become increasingly difficult for users to efficiently collect and understand reliable data. In particular, conventional systems are inadequate when it is necessary to quickly grasp data that changes in real time or information integrated from multiple sources. Furthermore, there is a demand for functions that can immediately present the results of data analysis in a visually understandable format. Against this background, there is an urgent need to provide a system that allows users to efficiently obtain and understand reliable information.

[1075] 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.

[1076] In this invention, the server includes means for receiving a search query entered by a user and extracting corresponding data from a database, means for analyzing the extracted data to identify trends by attribute, means for formatting the analysis results and presenting them to the user, means for collecting data from data sources on the Internet based on the search query, means for analyzing the collected data using an AI model, and means for formatting the analysis results in JSON format and returning them to the user terminal. This enables users to quickly obtain reliable data from various information sources and instantly grasp trends by various attributes such as age and gender.

[1077] A "search query" is a word or phrase that a user enters to retrieve specific information.

[1078] A "database" is a collection of data that is organized and managed according to specific rules, allowing for quick search and retrieval.

[1079] An "AI model" is a computational model that uses artificial intelligence technology to analyze data and identify specific patterns or trends.

[1080] "Internet data sources" are information resources accessible via the Internet, such as websites and APIs.

[1081] "JSON format" is an abbreviation for JavaScript Object Notation, a lightweight format for structuring data to improve readability and operability.

[1082] An "attribute" is a specific characteristic or feature used to classify data. For example, age and gender are examples of attributes.

[1083] "Analysis results" refer to the conclusions and insights obtained after analyzing collected data using AI models, etc.

[1084] "Shaping" is the process of preparing analysis results and data in a format that is easy for users to understand.

[1085] A "terminal" is a digital device that a user uses to enter information and view results.

[1086] An "interface" is a means of communication between a user and a system for exchanging information.

[1087] The system based on this invention receives a search query entered by a user, collects relevant data from data sources on the Internet, and analyzes it using an AI model, thereby quickly providing reliable data.

[1088] System Configuration and Operation

[1089] server

[1090] The server has the following features:

[1091] 1. A function to receive search queries from users.

[1092] 2. The ability to collect data from internet data sources based on a search query. Here, we use the requests module to get data from an API and use BeautifulSoup for HTML parsing.

[1093] 3. The function to analyze collected data using AI models. The AI ​​models use machine learning algorithms and deep learning models. To analyze the data, pandas is used to convert it into a data frame and calculate the average value by age and gender using groupby and mean.

[1094] 4. A function to format the analysis results in JSON format and return them to the user's device.

[1095] For example, when the server receives a search query for "movie box office revenue trends," it collects related movie data from APIs on the Internet, analyzes it using an AI model, and then formats box office revenue data by user attributes (age, gender) in JSON format and sends it back to the device.

[1096] Terminal

[1097] The terminal has the following features:

[1098] 1. The ability to provide a search box and allow users to enter a search query.

[1099] 2. A function that provides an interface to the server and sends search queries to the server.

[1100] 3. A function to receive the analysis results returned from the server and display them in a format that is easy for the user to view, such as a graph or text format.

[1101] For example, if a user searches for "movie box office trends" using a smartphone app, the app will display the analysis results obtained from the server as graphs and text, such as "70% of women in their 20s gave high marks to the most recent movie, 'Spider-Man'."

[1102] User

[1103] The user does the following:

[1104] 1. Enter the keyword or phrase you want to research into the search box on your smartphone or PC.

[1105] 2. Click the search button to send the query to the server.

[1106] 3. Wait for the results to appear and use them to investigate and make decisions.

[1107] For example, if a user types in "movie box office trends" and presses the search button, the result displayed will be "70% of women in their 20s highly rated the latest movie." Based on this information, users can quickly grasp the latest movie trends and use it to help with movie selection and marketing strategies.

[1108] Prompt Sentence Examples

[1109] Search Query: Movie Box Office Trends

[1110] Information you need: The latest movie box office statistics and user comments

[1111] Data by age group: 20s, 30s, 40s and over

[1112] Gender-specific data: Male and female data

[1113] Output format: JSON

[1114] This invention allows users to easily obtain efficient and reliable real-time data, making it possible to use useful information in a variety of fields, including news reporting, marketing research, and academic research.

[1115] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1116] Step 1:

[1117] A user enters a keyword or phrase they want to research into the search box on their smartphone or PC. The entered search query is prepared as a request to be sent to the server. The input here is the search query itself, and the output is a request to the server. For example, a user might enter "movie box office trends."

[1118] Step 2:

[1119] The terminal sends a search query from the user to the server. Specifically, the terminal sends the search query as an HTTP request, including the search query in the payload. The input is the user's search query, and the output is an HTTP request.

[1120] Step 3:

[1121] The server analyzes the received search query and collects the relevant data from a data source. The data source can be an API on the Internet or public statistical data, and the data is retrieved using the requests module. The input is the search query in the HTTP request, and the output is the collected raw data. For example, collecting data related to movie box office revenue from an API.

[1122] Step 4:

[1123] The server analyzes the collected data using an AI model. For this analysis, pandas is used to convert the collected data into a data frame, and the groupby and mean methods are used to classify the data by age and gender and identify trends. The input is the collected raw data, and the output is the analyzed data. For example, the collected data can be classified by age and gender (20s, 30s, and over 40s) and analyzed.

[1124] Step 5:

[1125] The server formats the analysis results into JSON format. In this process, the data frame analyzed by pandas is converted into JSON format using the to_dict method. The input is the analyzed data, and the output is JSON format data. For example, the analysis results can be formatted into JSON data such as "70% of women in their 20s gave the movie 'Spider-Man' a high rating."

[1126] Step 6:

[1127] The server returns the analysis results in JSON format to the user device as an HTTP response. The input is the analysis results in JSON format, and the output is an HTTP response. For example, a response including the JSON data of the analysis results is sent to the terminal.

[1128] Step 7:

[1129] The terminal receives the analysis results sent back from the server and displays them in a format that is easy for the user to view. This display can be in the form of graphs or text. The input is the analysis results in the HTTP response, and the output is the visual information displayed to the user. For example, a graph can be generated based on the analysis results, displaying "70% of women in their 20s gave the movie 'Spider-Man' a high rating."

[1130] 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.

[1131] This invention provides a system that allows users to easily obtain specific information in a reliable manner and provides comprehensive information, including sentiment analysis of the original data. The system receives a user's search query, extracts relevant data from a database, analyzes it, forms results, and presents them to the user. It also performs sentiment analysis using an emotion engine and provides the results to the user.

[1132] Server Processing

[1133] The server has the function of collecting statistical data and real-time user comment logs that are publicly available on the Internet and storing them in a database. This data is periodically updated and added to the database.

[1134] When a user's search query is received, the server extracts relevant data from the database based on the query. The extracted data is stored in a temporary buffer and analyzed by an AI model. Furthermore, this analysis incorporates an emotion engine that analyzes the emotional information contained in the retrieved data. During this analysis process, the data is classified based on attributes such as age and gender, and specific trends and emotional tendencies are identified.

[1135] The analysis results are converted into a format such as JSON and sent back to the device as an HTTP response from the server. This response includes not only trends by attribute but also the results of sentiment analysis.

[1136] Terminal handling

[1137] The device, such as a web browser on a user's PC or smartphone, provides an interface to the server. When the user enters a specific query into a search box and presses the search button, the device sends the query to the server.

[1138] When the analysis results are returned from the server, the device analyzes the data and displays it in an easy-to-read format for the user. For example, if a user enters the query "Tokyo Olympics public opinion," the device receives the results sent back from the server and displays not only the results in the form of "70% of men in their 30s have a positive opinion of the Tokyo Olympics," but also the sentiment trend, such as "Many comments show positive sentiment."

[1139] User operations

[1140] The user interacts with the system by entering a keyword or phrase into the search box on their device, clicking the search button, and sending the query to the server. The user waits for the results to appear, and then makes their own research or decision based on the results.

[1141] As a concrete example, to search for information on "Tokyo Olympics public opinion," a user would enter "Tokyo Olympics public opinion" in the search box and press the search button. The server receives this query, extracts all relevant information from the database (for example, comment logs and statistical data), and analyzes it. It also uses an emotion engine to analyze the emotional information contained in the data. The final, formatted data is sent back to the device, which displays it in an easy-to-read format for the user. In addition to trends by attribute, such as "70% of men in their 30s have a positive opinion of the Tokyo Olympics," the user is also presented with emotion analysis results, such as "the majority of total comments show positive emotions."

[1142] This system allows users to easily obtain reliable data and interpret sentiment trends from that data, making it possible to utilize practical information in a wide range of fields, including news reporting, marketing surveys, and academic research.

[1143] The processing flow will be explained below.

[1144] Step 1:

[1145] The server collects statistical data and real-time user comment logs that are publicly available on the Internet, and the collected data is periodically updated and stored in a database.

[1146] Step 2:

[1147] Users enter the keyword or phrase they want to research into the search box on their device's web browser, for example, "Tokyo Olympics public opinion," and click the search button.

[1148] Step 3:

[1149] The device sends the search query entered by the user as form data to the server via a POST request, which includes the keywords or phrases entered by the user.

[1150] Step 4:

[1151] The server analyzes the POST request received from the device and obtains the query, based on which the server connects to the database and searches for the appropriate data.

[1152] Step 5:

[1153] The server stores the data extracted from the database in a temporary buffer, including relevant statistics and user comment logs.

[1154] Step 6:

[1155] The server analyzes the data stored in a temporary buffer using AI models that categorize the data based on attributes such as age and gender, and identify specific trends.

[1156] Step 7:

[1157] The server uses an emotion engine to perform emotion analysis on the data stored in the temporary buffer. The emotion engine extracts user emotions from the comment logs in the database and classifies them as positive, negative, or neutral.

[1158] Step 8:

[1159] The server formats the analysis results, including the sentiment analysis results, into a format such as JSON. The formatted data may include information such as "70% of men in their 30s have a positive opinion of the Tokyo Olympics."

[1160] Step 9:

[1161] The server sends the formatted data to the terminal as an HTTP response, which includes details of the analysis results.

[1162] Step 10:

[1163] The device analyzes the response data received from the server and displays it in an easy-to-read format for the user. The analysis results are displayed in graph and text format, and may show, for example, "70% of men in their 30s have positive opinions." Sentiment analysis results are also displayed, and information such as "The majority of comments express positive sentiment" is presented.

[1164] Step 11:

[1165] Users can view the results displayed on their devices and obtain the information they need. They can then use the data to conduct their own research and make decisions. This data includes demographic trends as well as sentiment analysis results, allowing for deeper insights.

[1166] Example 2

[1167] 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."

[1168] In today's information society, it is difficult for users to quickly obtain specific information in a reliable manner. Furthermore, advanced analytical skills are required to interpret emotional trends from the information obtained, making sentiment analysis a high hurdle for average users. Furthermore, there is a lack of a means to centrally manage various data and present it in a visually understandable manner. This presents a challenge for users, making it difficult to make quick and accurate decisions.

[1169] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1170] In this invention, the server includes means for receiving a search query entered by a user and extracting corresponding data from a database, means for analyzing the extracted data to identify trends for each attribute, emotion analysis means for analyzing emotion information contained in the extracted data, and means for forming and presenting the analysis results to the user. This allows the user to quickly and easily obtain highly reliable data and understand emotional trends from that data. In addition, because the information is presented in a visually easy-to-understand format, the user can make decisions quickly based on the analysis results.

[1171] A "search query" is a keyword or phrase that a user enters to retrieve specific information.

[1172] A "database" is a structured collection of data for efficiently storing, managing, and retrieving large amounts of data.

[1173] "Extraction" is the process of retrieving relevant information from a database based on specific criteria.

[1174] "Analysis" is the act of understanding the information contained in data and deriving specific patterns or trends.

[1175] An "attribute" is a specific characteristic or category used to classify data, such as age or gender.

[1176] "Emotional information" is information that indicates the emotional tendency (positive, negative, neutral, etc.) contained in the data.

[1177] "Emotion analysis means" refers to functions and tools for analyzing emotional information contained in data and identifying emotional trends.

[1178] "Shaping" is an operation that arranges the analysis results in a form that is easy for the user to understand.

[1179] "Presenting" is the act of displaying or providing shaped information to a user.

[1180] An "interface" refers to the means by which a user can interact with a system, as well as the screens and tools that allow a user to operate the system.

[1181] "Statistical data" is a collection of data that compiles numerical information about a specific phenomenon.

[1182] A "user comment log" is a set of data that records user opinions and impressions posted in real time on the Internet.

[1183] This invention provides a system that allows users to easily obtain specific information in a reliable manner and provides comprehensive information, including sentiment analysis of the original data. The system operates in cooperation with the elements of a server, a terminal, and a user.

[1184] server

[1185] The server has the function of collecting statistical data published on the Internet and real-time user comment logs and storing them in a database. Specifically, it periodically obtains data from specified data sources (for example, government statistical bureaus or news site APIs) using automated scripts. The obtained data is stored in the database and updated by merging it with existing data.

[1186] When a search query is received from a user, the server extracts relevant data from the database based on the query. The extracted data is stored in a temporary buffer and analyzed using a natural language processing library (e.g., NLTK, SpaCy). An emotion engine (e.g., VADER, TextBlob) is then used to classify the emotional information contained in the data into positive, negative, or neutral. Furthermore, the data is classified based on attributes such as age and gender, and specific trends are identified.

[1187] The analysis results are converted into JSON format and sent back to the device as an HTTP response, which includes not only trends by attribute but also the results of sentiment analysis.

[1188] Terminal

[1189] A terminal (a device used by a user, such as a PC or smartphone) provides an interface to the server via a web browser. When a user enters a specific query into a search box and presses the search button, the terminal sends the query to the server as an HTTP request. By using JavaScript or AJAX, the query can be sent asynchronously and a response from the server can be waited for.

[1190] When the analysis results are returned from the server, the device analyzes the data and displays it in an easy-to-read format for the user. The analysis results are presented visually using HTML and graphs (e.g., Chart.js). For example, attribute-specific information such as "70% of men in their 30s have a positive opinion of the Tokyo Olympics" or emotional trends such as "Many comments indicate positive sentiment" are visually displayed.

[1191] User

[1192] Users use the system to enter a search query to research specific information. They enter the keyword or phrase they want to look up in the search box, press the search button, and the query is sent to the server. The system returns analytical results in response, allowing the user to conduct their own research and make decisions.

[1193] As a concrete example, if a user wants to search for information on "Tokyo Olympics public opinion," they enter "Tokyo Olympics public opinion" in the search box and press the search button. The server receives this query, extracts and analyzes related statistical data and comment logs. It also utilizes an emotion engine to analyze the emotional information contained in the data, and the final, formatted data is sent back to the device. The device visually presents the analysis results to the user, displaying specific information such as "70% of men in their 30s have a positive opinion of the Tokyo Olympics" along with the emotion analysis results.

[1194] Examples of prompt statements

[1195] Below is an example of a prompt sentence to input to the generative AI model.

[1196] "Please tell me the results of the latest public opinion polls regarding the Tokyo Olympics. I'd particularly like to know the sentiment trends by age and gender. Also, what is the percentage of positive, negative, and neutral opinions?"

[1197] This system allows users to quickly and easily obtain reliable data and interpret sentiment trends from that data, providing actionable information for a wide range of fields, including news reporting, marketing research, and academic research.

[1198] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1199] Step 1:

[1200] The server collects statistical data and real-time user comment logs that are publicly available on the Internet and stores them in a database.

[1201] As input, the server accesses a specified data source (e.g., a government statistical agency or a news site's API) to retrieve new data.

[1202] Specifically, an automated script runs every morning at 3:00 AM, and new data is stored in the database, merging it with existing data to update the database.

[1203] As output, the latest statistics and user comment logs are stored in a database.

[1204] Step 2:

[1205] The user enters a specific search query (e.g., "Tokyo Olympics public opinion") into the device's search box and presses the search button.

[1206] As input, the user enters keywords or phrases related to the information they are interested in into a search box.

[1207] Specifically, when a user clicks the search button, the device sends an HTTP request to the server. The request is sent with a URL in the format http: / / example.com / search?q=Tokyo Olympics+public opinion.

[1208] As an output, the search query is sent to the server.

[1209] Step 3:

[1210] The server analyzes the search query received from the user and extracts relevant data from the database.

[1211] As input, the server receives a search query submitted by a user.

[1212] Specifically, the server breaks down the query into keywords and searches for and extracts the relevant data. For example, in the case of "Tokyo Olympics public opinion," data related to "Tokyo Olympics" and "public opinion" will be extracted.

[1213] As output, relevant statistical data and comment logs are extracted from the database.

[1214] Step 4:

[1215] The server stores the extracted data in a temporary buffer and analyzes it using a natural language processing library (e.g., NLTK, SpaCy).

[1216] As input, the extracted data is stored in a temporary buffer.

[1217] Specifically, the server uses a natural language processing library to analyze the data content and extract the meaning and trends of the text.

[1218] As an output, the analysis results are produced.

[1219] Step 5:

[1220] The server uses a sentiment analysis engine (e.g., VADER, TextBlob) to analyze the sentiment information contained in the data and classify it as positive, negative, or neutral.

[1221] As input, the server receives the parsed data.

[1222] Specifically, the server uses a sentiment analysis engine to analyze the emotional expressions in the data and displays the emotional evaluation of each comment or piece of data as a numerical value. For example, a positive comment is classified as "1" and a negative comment as "-1."

[1223] As an output, sentiment analysis results are generated.

[1224] Step 6:

[1225] The server categorizes the data based on attributes such as age and gender to identify specific trends.

[1226] As input, the server uses the sentiment analysis results.

[1227] Specifically, the server sorts the data based on attributes such as age and gender, and extracts specific trends (for example, 70% of men in their 30s have positive opinions).

[1228] The output is a trend by attribute.

[1229] Step 7:

[1230] The server formats the analysis results in JSON format and returns them to the terminal as an HTTP response.

[1231] As input, the server receives the identified trends and sentiment analysis results.

[1232] Specifically, the server converts the data into JSON format and generates an HTTP response.

[1233] As an output, the server sends a response containing the analysis results to the terminal.

[1234] Step 8:

[1235] The terminal receives the analysis results returned from the server and displays them in an easy-to-read format for the user.

[1236] As input, the terminal receives data in JSON format received from the server.

[1237] Specifically, the device parses the response using JavaScript and displays the data in HTML or a graphical format (e.g., Chart.js).

[1238] As an output, the analysis results are presented to the user in a visually easy-to-understand format.

[1239] Step 9:

[1240] The user bases their research and decisions on the results displayed.

[1241] As input, the user receives the analysis results displayed on the terminal.

[1242] Specifically, users can view the displayed information to gain necessary insights, for example, to help with report creation and marketing strategy development.

[1243] As an output, the user can obtain decision-making and research results.

[1244] (Application example 2)

[1245] 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."

[1246] In conventional information provision systems, when a user searches for a specific keyword, it is difficult to understand other users' reactions to that information or their emotional tendencies. Furthermore, there was a lack of means to efficiently analyze attribute-specific and emotional tendencies in information and provide them to users, so the information available to users was limited. The present invention aims to provide users with more reliable data by analyzing the emotional tendencies of news and articles that interest them and providing information that includes these tendencies.

[1247] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving a search query entered by a user and extracting relevant data from a database, means for analyzing the extracted data to identify trends for each attribute and emotional trends, means for forming the analysis results and presenting them to the user, and means for performing emotional analysis on news and article data and displaying the results. This allows the user to easily grasp more detailed information and the emotional trends associated with that information.

[1248] A "search query" is a word or phrase that a user enters into a system to search for specific information.

[1249] A "database" is an information collection system built to efficiently manage, search, and use data.

[1250] "Extraction" is the process of selecting required data based on specific conditions.

[1251] "Analysis" is the process of processing acquired data and clarifying its meaning and trends.

[1252] An "attribute" refers to a specific characteristic or category of data or an object.

[1253] A "trend" refers to a direction or pattern that multiple data or attributes show in common.

[1254] "Emotional trends" refers to the overall tendency of the emotional reactions of people included in the data.

[1255] "Forming" is the process of preparing acquired data and analysis results in a format that can be easily displayed to users.

[1256] "Presenting" refers to the act of displaying the analysis results in a form that can be used by the user.

[1257] An "interface" refers to the contact points or tools through which users and systems interact with each other.

[1258] A "prompt sentence" refers to an input sentence that prompts a generative AI model to respond or take a specific action.

[1259] The system that realizes this application example allows users to easily and credibly obtain specific information and performs sentiment analysis on that information. Here, we will explain a specific embodiment of a news reader that has a sentiment analysis function for news and article data.

[1260] Server Processing

[1261] The server receives search queries entered by users and uses a backend application to extract relevant data from the database. Django (a Python framework) is used for the backend. The Django application uses TextBlob (a natural language processing library) to analyze the content of news articles extracted from the database. TextBlob's sentiment analysis function can be used to detect positive, negative, and neutral sentiment trends contained in news articles. The analysis results are returned to the frontend in JSON format.

[1262] Front-end processing

[1263] The front-end is developed using React (a JavaScript framework). When a user enters a specific query in the search box and presses the search button, the React application retrieves the query and sends a request to the server using Axios (an HTTP client). The analysis results received from the server are displayed in a user-friendly format using React's state management functionality. This display includes the title, content, and sentiment score of the news article.

[1264] User operations

[1265] A user logs into the system and enters the keyword or phrase they want to research in the search box. For example, they enter the query "coronavirus vaccination" and press the search button. After this operation, the user waits for the analysis results provided by the server. The search results display a list of news articles with sentiment analysis. The sentiment analysis results include information on whether the user's sentiment toward the news article is positive, negative, or neutral.

[1266] Prompt Sentence Examples

[1267] A specific example of a prompt sentence is: Search for the latest news about the "Tokyo Olympics" and display the user's sentiment (positive, negative, neutral) after analyzing it.

[1268] This allows users to understand not only the news and articles that interest them, but also the emotional trends of other users regarding that information. This system is expected to be used in a wide range of fields, including news reporting, marketing surveys, and academic research.

[1269] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1270] Step 1:

[1271] A user enters a query to search for information on a specific topic. For example, they enter the query "coronavirus vaccination" and press the search button. The entered string is sent to the next step.

[1272] Step 2:

[1273] The device receives a query entered by the user and sends it to the backend server as an HTTP request. For example, React is used to manage the state of user input, and Axios is used to send the request to the server. The input is a search query, and the output is an HTTP request.

[1274] Step 3:

[1275] The server processes the request and retrieves the relevant news articles from the database. Specifically, the Django application searches the database based on the query and selects the relevant articles. The input is the search query, and the output is a list of relevant news articles.

[1276] Step 4:

[1277] The server performs sentiment analysis on the extracted news articles. Here, it calculates a sentiment score for each article using TextBlob. Sentiment analysis takes the article text as input and outputs a sentiment score of positive, negative, or neutral.

[1278] Step 5:

[1279] The server formats the sentiment analysis results into JSON format and sends it to the device as a response. Specifically, the news article title, content, and sentiment score are included in the JSON object. The input is the news article and its sentiment score, and the output is the analysis results in JSON format.

[1280] Step 6:

[1281] The device parses the JSON-formatted analysis results received from the server and displays them in an easy-to-read format for the user. Specifically, React renders the data and displays the title, content, and sentiment score of the news article. The input is the JSON-formatted analysis results, and the output is a list of news articles displayed to the user.

[1282] Step 7:

[1283] The user views the displayed news and sentiment analysis results, and inputs additional queries as needed. Based on this input, the process begins again from step 1.

[1284] 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.

[1285] 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.

[1286] 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.

[1287] 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.

[1288] FIG. 9 illustrates 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 behaviors 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.

[1289] 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.

[1290] 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).

[1291] 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.

[1292] 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."

[1293] 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.

[1294] 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).

[1295] 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.

[1296] 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.

[1297] 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.

[1298] 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.

[1299] 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.

[1300] 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.

[1301] 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.

[1302] 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.

[1303] 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.

[1304] 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.

[1305] The following is further disclosed regarding the above embodiment.

[1306] (Claim 1)

[1307] means for receiving a search query entered by a user and extracting corresponding data from a database;

[1308] A means for analyzing the extracted data to identify trends by attribute;

[1309] means for shaping and presenting the analysis results to a user;

[1310] A system including:

[1311] (Claim 2)

[1312] 10. The system of claim 1, further comprising means for collecting statistical data and real-time user comment logs published on the Internet and storing them in a database.

[1313] (Claim 3)

[1314] 10. The system according to claim 1, further comprising means for providing an interface for displaying the analysis results in a graph or text format.

[1315] "Example 1"

[1316] (Claim 1)

[1317] means for receiving a search query entered by a user and extracting corresponding data from a database;

[1318] a means for storing the extracted data in a temporary buffer and analyzing the data using a generative AI model;

[1319] A means of identifying the analysis results based on trends for attributes such as age and gender, and converting them into an easy-to-read format such as JSON format,

[1320] The formed data is returned to the terminal as an HTTP response, and the analysis results are displayed on the terminal in graph or text format.

[1321] A system including:

[1322] (Claim 2)

[1323] 10. The system of claim 1, further comprising means for collecting statistical data and real-time user comment logs published on the Internet and storing them in a database.

[1324] (Claim 3)

[1325] 10. The system according to claim 1, further comprising means for providing an interface for displaying the analysis results in a graph or text format.

[1326] "Application Example 1"

[1327] (Claim 1)

[1328] means for receiving a search query entered by a user and extracting corresponding data from a database;

[1329] A means for analyzing the extracted data to identify trends by attribute;

[1330] means for shaping and presenting the analysis results to a user;

[1331] means for collecting data from internet data sources based on the search query;

[1332] A means of analyzing the collected data using an AI model;

[1333] A means to format the analysis results in JSON format and return them to the user's device,

[1334] A system including:

[1335] (Claim 2)

[1336] 10. The system of claim 1, further comprising means for collecting statistical data and real-time user comment logs published on the Internet and storing them in a database.

[1337] (Claim 3)

[1338] 10. The system according to claim 1, further comprising means for providing an interface for displaying the analysis results in a graph or text format.

[1339] "Example 2: Combining Emotion Engines"

[1340] (Claim 1)

[1341] means for receiving a search query entered by a user and extracting corresponding data from a database;

[1342] A means for analyzing the extracted data to identify trends by attribute;

[1343] emotion analysis means for analyzing emotion information contained in the extracted data;

[1344] means for shaping and presenting the analysis results to a user;

[1345] A system including:

[1346] (Claim 2)

[1347] 10. The system of claim 1, further comprising means for collecting statistical data and real-time user comment logs published on the Internet and storing them in a database.

[1348] (Claim 3)

[1349] 10. The system according to claim 1, further comprising means for providing an interface for displaying the analysis results in a graph or text format.

[1350] "Application example 2 when combining emotion engines"

[1351] (Claim 1)

[1352] means for receiving a search query entered by a user and extracting corresponding data from a database;

[1353] A means for analyzing the extracted data to identify trends and sentiment trends by attribute;

[1354] means for shaping and presenting the analysis results to a user;

[1355] A means of performing sentiment analysis on news and article data and displaying the results,

[1356] A system including:

[1357] (Claim 2)

[1358] 10. The system of claim 1, further comprising means for collecting statistical data and real-time user comment logs published on the Internet and storing them in a database.

[1359] (Claim 3)

[1360] 10. The system according to claim 1, further comprising means for providing an interface for displaying the analysis results in a graph or text format. [Explanation of symbols]

[1361] 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. means for receiving a search query entered by a user and extracting corresponding data from a database; A means for analyzing the extracted data to identify trends by attribute; means for shaping and presenting the analysis results to a user; A system including:

2. 10. The system of claim 1, further comprising means for collecting statistical data and real-time user comment logs published on the Internet and storing them in a database.

3. 10. The system according to claim 1, further comprising means for providing an interface for displaying the analysis results in a graph or text format.

Images