System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving a user's input regarding a travel or dining venue; means for collecting data from a plurality of multimedia platforms based on the input; means for analyzing the collected data and generating a positive or negative summary of the data; and means for displaying the summarized data 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] When deciding where to travel or eat, many users have to check multiple review sites and social media, which takes a huge amount of time and effort. Until now, there has been no method to reduce the burden of gathering information and make decisions efficiently. In addition, there has been a lack of ways to evaluate the reliability of the collected information, which has often made it difficult for users to make decisions. [Means for solving the problem]

[0005] The present invention provides a system for automatically collecting data from multiple multimedia platforms based on information about travel destinations or dining places provided by a user, and analyzing and summarizing the data. The system of the present invention solves the problems of the related art by including a means for receiving user input information about travel destinations or dining places, a means for collecting data from multiple multimedia platforms based on the input information, a means for analyzing the collected data and generating a positive or negative summary of the data, and a means for displaying the summarized data to the user, and further including a means for calculating a reliability score for the collected data, generating multiple routes and spots based on the input information, and displaying the information about them.

[0006] "User input information" is data provided by the user by entering information about destinations and desired meal conditions into an input form.

[0007] "Multimedia platform" refers to a variety of internet services and applications, including review sites and social networking sites.

[0008] "Means of collecting data" refers to the part of the system that has the ability to obtain information about specific destinations and conditions from the internet using scraping or APIs.

[0009] The "means for analyzing data" refers to the part of the system that processes collected data using machine learning and natural language processing, and has the function of summarizing and classifying its contents.

[0010] "Positive or negative summary" is information that analyzes collected word-of-mouth data, classifies it into positive and negative content, and displays it in a concise form.

[0011] A "reliability score" is an index that evaluates and quantifies how reliable the collected data is.

[0012] The "means for generating routes and spots" is the part of the system that has the function of calculating and selecting optimal travel routes and recommended tourist spots based on the information input by the user. [Brief explanation of the drawings]

[0013] [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

[0014] 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.

[0015] First, the terms used in the following description will be explained.

[0016] 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).

[0017] 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.

[0018] 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.

[0019] 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.

[0020] 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."

[0021] [First embodiment]

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

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0028] 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.

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

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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."

[0034] This invention relates to a system called "Tabikomi," designed to streamline travel and dining destination decisions. The system collects data from multiple multimedia platforms based on user input, analyzes, summarizes, and displays the data.

[0035] 1. The user enters the destination and conditions

[0036] The user enters their desired destination and dining preferences into the application's input form, such as "Barcelona" and "delicious tapas."

[0037] 2. The device sends the input information to the server

[0038] The terminal transmits the information entered by the user to the server, including the destination, purpose of the trip, meal requirements, etc.

[0039] 3. The server collects reviews and social media data

[0040] Based on the received information, the server automatically collects relevant data from review sites and social media, using an API to retrieve reviews, ratings, and ratings related to the specified destination and conditions.

[0041] 4. The server analyzes the data and generates a summary

[0042] The server analyzes the collected data using AI models (machine learning and natural language processing technology), which categorizes the data into positive and negative elements.

[0043] For example, a positive summary might be "Lots of fresh ingredients and it's delicious!", while a negative summary might be "It's a bit pricey, but it's worth it."

[0044] 5. The server calculates the reliability score

[0045] The server evaluates the reliability of the collected data and calculates a reliability score for each review, which helps users determine the trustworthiness of the reviews.

[0046] 6. The server generates multiple routes and spots

[0047] The server will then suggest suitable travel routes and tourist spots based on the user's input information. For example, it will generate a tourist route in Barcelona that includes spots such as Sagrada Familia and Park Güell.

[0048] 7. The server sends the summary information to the terminal.

[0049] The server sends the analyzed and summarized data, reliability scores, and route information to the terminal.

[0050] 8. The device displays the information to the user

[0051] The device displays the transmitted information in a user interface, allowing the user to view information about different tapas bars in tabular format and visually confirm the tourist route on a map.

[0052] Specific examples

[0053] Example user input

[0054] A user types "Barcelona" and "delicious tapas" into the app.

[0055] Data collection example

[0056] The server collects reviews about "Barcelona" and "tapas" from TripAdvisor, Yelp, Twitter, etc. and temporarily stores them in a database.

[0057] Data analysis example

[0058] The server analyzes the collected review data using a natural language processing model and classifies it as follows:

[0059] Positive: "Lots of fresh ingredients and delicious!"

[0060] Negative: "It's expensive, but it's worth it."

[0061] Example of reliability score calculation

[0062] The server calculates a reliability score based on the analyzed data, giving a high score if there are many positive comments, and a low score if there are many negative comments, for example.

[0063] Route and Spot Generation Example

[0064] The server uses the Google Maps API to calculate tourist routes within Barcelona and generates routes that include major tourist spots such as Sagrada Familia and Park Güell.

[0065] Information display example

[0066] The device will show the user a summary and credibility score for the tapas bar "La Boqueria" and plot a tourist route on a map.

[0067] This allows users to efficiently select a destination based on compiled, highly reliable information, without having to go through the tedious process of collecting information.

[0068] The processing flow will be explained below.

[0069] Step 1:

[0070] The user enters a destination and selection criteria into the application's input form, for example, "Barcelona" and "good tapas," and presses the "Search" button.

[0071] Step 2:

[0072] The device converts the user's input information into JSON format and sends it to the server. The data sent includes the user ID, destination, purpose of the trip, and meal preferences.

[0073] Step 3:

[0074] Based on the input information received by the server, it collects relevant data from multiple multimedia platforms (e.g., review sites, social media) and retrieves word-of-mouth, ratings, and reviews related to the specified destination and conditions through scraping and API calls.

[0075] Step 4:

[0076] The server temporarily stores the collected data in a database, where it is prepared for analysis.

[0077] Step 5:

[0078] The server uses machine learning or natural language processing models to analyze the stored data, categorize the data into positive and negative comments, and generate summaries.

[0079] Step 6:

[0080] The server calculates a credibility score for the summarized data, which is a numerical indicator that evaluates the trustworthiness of each comment or review.

[0081] Step 7:

[0082] The server runs an algorithm to generate multiple tourist routes and attractions based on the destination. It uses Google Maps API to generate appropriate travel routes and tourist attractions and also collects information on these.

[0083] Step 8:

[0084] The server sends the summarized data, reliability scores, and generated route and spot information to the device in JSON format.

[0085] Step 9:

[0086] The device displays the information received from the server in a user interface, showing information about different tapas bars in tabular format, plotting tourist routes on a map, and displaying a summary of reviews and a reliability score for each spot.

[0087] Step 10:

[0088] Users can then use the information displayed to select and plan trips and dining options, while also taking into account positive and negative summaries, reliability scores, and visualized route information.

[0089] Example 1

[0090] 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."

[0091] In recent years, the development of the Internet has made it easier to gather information about travel and dining out. However, it remains difficult for users to select reliable data from the vast amount of information and efficiently decide on destinations and dining locations. In particular, the wide variety of word-of-mouth and reviews about travel destinations and dining locations makes it difficult to determine which information is trustworthy. In addition, the time and effort required to collect, integrate, and summarize information from multiple platforms is a significant burden.

[0092] 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.

[0093] In this invention, the server includes means for receiving user input information, means for transmitting the input information to the server, means for collecting data from multiple information sources based on the input information, means for analyzing the collected data and generating a positive or negative summary of the data, means for proposing the summarized data and travel routes and tourist spots, means for transmitting the analyzed data, reliability scores, and generated route information to a terminal, and means for displaying the transmitted information on a user interface, thereby enabling a user to efficiently decide on a destination or a place to eat based on reliable information.

[0094] "User" means an end user who uses the system to search, input, and review travel and dining destination information.

[0095] A "server" is a central processing unit that receives information from users, collects and analyzes data, and transmits the results to terminals.

[0096] "Input information" refers to information such as travel destinations, places to eat, and desired conditions that a user inputs into the system.

[0097] A "terminal" is a device that is directly operated by a user, sends input information to a server, and displays the results from the server.

[0098] "Sources" are the multiple online platforms and databases that the server accesses to collect data.

[0099] "Data" refers to information collected from sources such as word of mouth, reviews, ratings, and social media posts.

[0100] "Collecting" refers to the act of the server obtaining and storing the necessary data from the source.

[0101] "Analyzing" refers to the act of processing the data collected by the server and extracting valuable information.

[0102] A "positive summary" is a summary of positive evaluations and comments extracted from the collected data.

[0103] A "negative summary" is a summary of negative evaluations and comments extracted from the collected data.

[0104] The "trust score" is a numerical value that evaluates the reliability of the data collected by the server. This score indicates the reliability of word-of-mouth and reviews.

[0105] A "travel route" is a travel route or a route connecting tourist spots that is generated by the server based on information input by the user.

[0106] "Tourist attractions" are tourist attractions and places worth visiting at a travel destination.

[0107] "Sending to terminal" refers to the act of the server transferring the analysis results and generated information to the user's terminal.

[0108] A "user interface" refers to the screen display and input means that allow a user to interact with a system through a terminal.

[0109] This invention relates to a system designed to streamline travel and dining destination decisions. The system collects data from multiple sources based on user input, analyzes and summarizes the data, and provides it to the user.

[0110] The system primarily utilizes the following hardware and software:

[0111] The device used by the user (smartphone, tablet, PC, etc.)

[0112] Server as a central processing unit

[0113] APIs used for data collection (various information source APIs, e.g., TripAdvisor API, Yelp API, Twitter API)

[0114] Generative AI models used for data analysis (e.g., natural language processing models such as BERT and GPT-3)

[0115] When a user inputs their destination and other requirements, the device sends that information to the server. For example, if a user inputs "Barcelona" and "delicious tapas," the device sends this information to the server in the form of an HTTP request.

[0116] Based on the input information, the server collects relevant data from multiple information source APIs, including travel review sites, online review sites, social media, etc. Data obtained through the APIs is temporarily stored on the server.

[0117] The server then analyzes the collected data using a generative AI model, which categorizes the collected data into positive and negative elements and generates a summary for each, including positive and negative sentiment.

[0118] Based on the analysis results, the server calculates a credibility score, which represents the trustworthiness of each review numerically and helps users determine the reliability of the information.

[0119] The server then suggests travel routes and tourist attractions based on the input information, for example, using the Google Maps API to generate a route that visits the main tourist attractions in Barcelona.

[0120] Finally, the server sends the analysis results, reliability scores, and generated route information to the device, which displays this information on the user interface, allowing the user to efficiently determine destinations and dining locations.

[0121] For example, if a user types "Barcelona" and "delicious tapas," the server collects related reviews and generates positive and negative summary statements such as "Lots of fresh ingredients and delicious!" and "Prices are high, but worth it." Based on the reliability score, the server recommends a tapas bar called "La Boqueria" and suggests a sightseeing route that includes "Sagrada Familia" and "Park Güell" using the Google Maps API.

[0122] Examples of prompt sentences include "Barcelona," "delicious tapas," "recommended tourist spots and routes," etc. This invention enables users to efficiently obtain reliable information and make quick and accurate travel planning decisions.

[0123] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0124] Step 1:

[0125] The user inputs the destination and conditions. The user inputs the desired conditions for travel destinations and dining places into the application's input form. For example, the user inputs "Barcelona" and "delicious tapas." After inputting, the user presses the submit button.

[0126] Input: Destination and desired conditions (e.g. Barcelona, ​​delicious tapas)

[0127] Output: Input information ready to send

[0128] Step 2:

[0129] The terminal sends the input information to the server. The terminal sends the destination and conditions entered by the user to the server as an HTTP request (POST request). The data sent is in JSON format.

[0130] Input: User's destination and desired conditions

[0131] Output: Input sent to the server

[0132] Step 3:

[0133] The server collects user reviews and social media data. Based on the destination and conditions received, the server calls APIs from multiple sources to collect data. Specifically, it uses APIs from TripAdvisor, Yelp, Twitter, and other sources to obtain related user reviews, comments, and social media posts.

[0134] Input: User's destination and desired conditions

[0135] Output: Collected data (e.g., word of mouth, reviews, social media posts)

[0136] Step 4:

[0137] The server analyzes the data and generates summaries. The server analyzes the collected data using a generative AI model (e.g., a natural language processing model such as BERT or GPT-3), classifies the data into positive and negative elements, and generates summaries for each.

[0138] Input: Collected data

[0139] Output: Positive and negative summaries

[0140] Step 5:

[0141] The server calculates the credibility score. Based on the collected data, the server evaluates the credibility of each review and calculates a score. The credibility score uses an AI model to filter spam and assign higher scores to reviews that are more trustworthy.

[0142] Input: Parsed data

[0143] Output: Confidence score

[0144] Step 6:

[0145] The server generates multiple routes and spots. The server suggests tourist routes and spots based on the user's input information and reliability scores. It uses the Google Maps API to generate routes that include major tourist spots.

[0146] Input: User input information and confidence score

[0147] Output: Suggested tourist routes and spots

[0148] Step 7:

[0149] The server sends the summarized information to the device. The server sends the analyzed and summarized data, reliability scores, and generated route information in JSON format to the device.

[0150] Inputs: Summarized data, reliability scores, generated route information

[0151] Output: Information sent to the terminal

[0152] Step 8:

[0153] The device displays the information to the user. The device then displays the received information in a user interface, where the user can view information about each tapas bar and its reliability score in a tabular format, and visually check the tourist route on a map.

[0154] Input: Information received from the server

[0155] Output: The result displayed in the user interface

[0156] This series of steps allows users to efficiently make travel and dining decisions based on reliable information.

[0157] (Application example 1)

[0158] 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."

[0159] Conventional systems for deciding on travel destinations and dining locations require users to collect information themselves and make decisions based on a large amount of information, which is time-consuming and labor-intensive. Furthermore, when it comes to providing information in physical stores, word-of-mouth and review information on products and services is not provided in real time, making it difficult for consumers to make quick decisions based on reliable information. To solve this problem, a system is needed that streamlines travel destination and dining location decisions and quickly provides reliable information in physical stores.

[0160] 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.

[0161] In this invention, the server includes: means for receiving user input information regarding travel destinations or dining locations; means for collecting data from multiple multimedia platforms based on the input information; means for analyzing the collected data and generating a positive or negative summary of the data; means for displaying the summarized data to the user; means for collecting related word-of-mouth and review information based on the conditions of products and services in the store; means for calculating a reliability score from the collected word-of-mouth and review information; means for summarizing product and service information based on the reliability score and displaying it to the user; and means for recommending appropriate routes and spots in the store. This allows users to efficiently select destinations based on the compiled, reliable information without having to collect information in a cumbersome manner. Furthermore, even in physical stores, users can obtain reliable information about products and services in real time and engage in optimal consumption behavior.

[0162] A "destination" is a geographic location that a user intends to visit.

[0163] A "dining location" is a location selected by a user to eat a meal.

[0164] "User" means an individual or group that uses the system.

[0165] "Input information" refers to data including requests and desired conditions that a user provides to the system.

[0166] A "multimedia platform" is an internet service that includes multiple information sources.

[0167] "Data" means digital information, including information related to word of mouth, reviews, and ratings.

[0168] "Means of collection" refers to the method for obtaining the specified information from the Internet.

[0169] "Means of analysis" are methods for examining collected data and generating specific meanings or summaries.

[0170] A "positive or negative summary" is a short sentence that summarizes the content of the data in a positive or negative way.

[0171] A "confidence score" is a number or metric used to assess the trustworthiness of collected data.

[0172] "Display means" refers to the method by which the analyzed data and summary are visually presented to the user.

[0173] A "store" is a physical location for offering goods and services.

[0174] "Conditions" are specific requirements or criteria desired by the user.

[0175] "Word of mouth" refers to the opinions and reviews that consumers give about products and services.

[0176] "Review information" refers to detailed evaluations and opinions about specific products or services.

[0177] A "route" is the optimal path for a user to travel to a particular location.

[0178] A "spot" is a specific location to visit within a travel destination or store.

[0179] A "recommendation method" is a method for suggesting specific information or routes to a user.

[0180] As an embodiment of the present invention, the configuration and operation of a real-time customer guide system will be specifically described.

[0181] This system mainly consists of a server, a user's device, and various means for collecting data from multiple multimedia platforms based on user input, analyzing it, and displaying it to the user. The main hardware used is a smartphone, a tablet, and smart glasses. The software used is AWS, Python, TensorFlow, Google Maps API, and React Native.

[0182] System Programming and Processing

[0183] Data collection

[0184] The server receives the criteria information entered by the user into the device. This input information includes specific requests such as "new sneakers" and "good reviews." Based on this information, the server collects related data from multiple multimedia platforms on the Internet (review sites, social media, etc.). This collection is done using AWS's API Gateway.

[0185] Data analysis and summary generation

[0186] The collected data is analyzed on the server by a Python program using natural language processing techniques. An AI model trained with TensorFlow classifies the collected data into positive and negative elements and generates short summaries. For example, "comfortable" is a positive summary, and "expensive" is a negative summary.

[0187] Calculating the reliability score

[0188] The server evaluates the reliability of the analyzed word-of-mouth and review information and calculates a reliability score, which also takes into account the user review history and reputation.

[0189] Route and spot recommendations

[0190] Furthermore, the server uses the Google Maps API to calculate the optimal route and spots within the store based on the user's interests, for example, proposing the optimal route from the fashion section to the food and drink section.

[0191] Displaying Information

[0192] The analyzed information, summary, and route suggestions are sent to the user's device. The user interface is developed using React Native, and the analysis results and recommended routes are visually presented to the user.

[0193] Specific examples

[0194] For example, if a user is interested in "new sneakers," they can input "Tell me the latest reviews about new sneakers" into the system. The server collects relevant data, generates summaries such as "comfortable" and "expensive," calculates a reliability score, and suggests the best route to the fashion section.

[0195] Here is a prompt used as an example:

[0196] "What are the latest reviews of new sneakers?"

[0197] "Tell me the recommended route within the store"

[0198] As described above, this system enables users to make efficient decisions based on compiled, highly reliable information, without the need for tedious information gathering, and supports optimal consumer behavior even in physical stores.

[0199] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0200] Step 1:

[0201] The user inputs condition information into the terminal. The input contents include requests such as "new sneakers" and "good reviews." The information input by the user is sent from the terminal to the server. The input of this step is the user's request, and the output is the input information sent to the server.

[0202] Step 2:

[0203] The server receives input information sent by the user. Based on the received information, the server collects related data from multiple multimedia platforms (review sites, social media, etc.). This collection is performed using AWS's API Gateway. The input of this step is the user's input information, and the output is the collected multimedia data.

[0204] Step 3:

[0205] The server analyzes the collected data. This analysis is performed using Python programs and TensorFlow. First, the collected data is analyzed using natural language processing techniques to generate positive and negative summaries. The input of this step is the collected data, and the output is positive and negative summaries.

[0206] Step 4:

[0207] The server calculates a credibility score for the parsed data. The credibility score takes into account the history and reputation of the user reviews, allowing us to quantify the trustworthiness of each review. The input for this step is the parsed data, and the output is the credibility score.

[0208] Step 5:

[0209] The server uses the Google Maps API to calculate the optimal route and spots within the store based on the user's interests. For example, it proposes the optimal route from the fashion section to the food and drink section. This provides the user with an efficient travel path. The input of this step is the user's interest information, and the output is the calculated route and spots.

[0210] Step 6:

[0211] The server sends the parsed information, confidence scores, and route suggestions to the device. This information is processed to be visually presented to the user in a user interface. The user interface, developed using React Native, displays the information in an easy-to-understand manner. The input of this step is the parsed and calculated information, and the output is the information displayed to the user.

[0212] Step 7:

[0213] The user uses the device to check the provided information and take optimal purchasing actions. For example, a user may start with a prompt such as "Tell me the latest reviews of new sneakers," and then obtain more information to make a purchasing decision. The input for this step is the information displayed on the device, and the output is the user's actions.

[0214] 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.

[0215] This invention relates to a system called "Tabikomi," designed to streamline travel and dining destination decisions. This system collects data from multiple multimedia platforms based on user input, analyzes, summarizes, and displays the data. Furthermore, by combining it with an emotion engine that recognizes and analyzes user emotions, it is possible to provide appropriate recommendation information based on the user's emotions.

[0216] 1. The user enters the destination and conditions

[0217] The user enters their destination and selection criteria into the application's input form, for example, "Barcelona" and "delicious tapas," and then presses the "Search" button.

[0218] 2. The device sends the input information to the server

[0219] The device converts the user's input information into JSON format and sends it to the server. The data sent includes the user ID, destination, purpose of the trip, and meal preferences.

[0220] 3. The server collects reviews and social media data

[0221] The server collects relevant data from multiple multimedia platforms (e.g., review sites, social media) based on the received input information, and uses APIs and scraping technology to obtain word-of-mouth, ratings, and reviews related to the specified destination and conditions.

[0222] 4. The server analyzes the data and generates a summary

[0223] The server analyzes the collected data using machine learning or natural language processing models, categorizing the data into positive and negative comments and generating summaries.

[0224] For example, a positive summary might be "Lots of fresh ingredients and it's delicious!", while a negative summary might be "It's a bit pricey, but it's worth it."

[0225] 5. The server calculates the reliability score

[0226] The server evaluates the reliability of the collected data and calculates a reliability score for each review, which helps users determine the trustworthiness of the reviews.

[0227] 6. The server generates multiple routes and spots

[0228] The server proposes suitable travel routes and tourist spots based on the user's input information. For example, it uses the Google Maps API to generate a tourist route in Barcelona that includes spots such as Sagrada Familia and Park Güell.

[0229] 7. The server sends the summary information to the terminal.

[0230] The server sends the analyzed and summarized data, reliability scores, and route information in JSON format to the device.

[0231] 8. The device displays the information to the user

[0232] The device displays the information in a user interface, where users can browse different tapas bars in tabular format and visualize their tourist route on a map, along with a summary of reviews and a credibility score for each spot.

[0233] 9. Emotion engine recognizes user emotions

[0234] The device's emotion engine recognizes the user's emotions based on the user's input and reactions to the displayed information, and this emotion data is sent to the server for analysis.

[0235] 10. The server analyzes the emotion data and provides recommendations

[0236] The server provides appropriate recommendation information based on the user's emotions recognized by the emotion engine. For example, if the user expresses positive emotions, similar recommended spots will be displayed, and if the user expresses negative emotions, different candidates will be presented.

[0237] 11. Feedback function reflects the results for the next test

[0238] The server accumulates the results of the user's sentiment analysis as feedback and reflects it in the next search results, thereby making better recommendations to the user.

[0239] Specific examples

[0240] Example user input

[0241] A user types "Barcelona" and "delicious tapas" into the app.

[0242] Data collection example

[0243] The server collects reviews about "Barcelona" and "tapas" from TripAdvisor, Yelp, Twitter, etc. and temporarily stores them in a database.

[0244] Data analysis example

[0245] The server analyzes the collected review data using a natural language processing model and classifies it as follows:

[0246] Positive: "Lots of fresh ingredients and delicious!"

[0247] Negative: "It's expensive, but it's worth it."

[0248] Example of reliability score calculation

[0249] The server calculates a reliability score based on the analyzed data, giving a high score if there are many positive comments, and a low score if there are many negative comments, for example.

[0250] Route and Spot Generation Example

[0251] The server uses the Google Maps API to calculate tourist routes within Barcelona and generates routes that include major tourist spots such as Sagrada Familia and Park Güell.

[0252] Information display example

[0253] The device will show the user a summary and credibility score for the tapas bar "La Boqueria" and plot a tourist route on a map.

[0254] Emotion recognition example

[0255] The device's emotion engine recognizes that the user has responded positively to the summary information for "La Boqueria," and sends this information to the server.

[0256] Examples of recommendation information

[0257] If the user expresses positive emotions, the server will recommend more similar tapas bars, widening the selection.

[0258] Example of applying the feedback function

[0259] The server stores the recognized emotion data and reflects it in the next search results, thereby providing information that matches the user's preferences.

[0260] This allows users to efficiently select travel destinations and places to eat by referring to reliable information based on word-of-mouth, ratings, and emotional data.

[0261] The processing flow will be explained below.

[0262] Step 1:

[0263] The user enters a destination and selection criteria into the application's input form, for example, "Barcelona" and "good tapas," and presses the "Search" button.

[0264] Step 2:

[0265] The device converts the user's input information into JSON format and sends it to the server. The data sent includes the user ID, destination, purpose of the trip, and meal preferences.

[0266] Step 3:

[0267] Based on the input information received by the server, the server collects relevant data from multiple multimedia platforms (e.g., review sites, social media), and uses APIs and scraping technology to obtain word-of-mouth, ratings, and reviews related to the specified destination and conditions.

[0268] Step 4:

[0269] The server temporarily stores the collected data in a database, where it is prepared for analysis.

[0270] Step 5:

[0271] The server uses machine learning or natural language processing models to analyze the stored data, categorize the data into positive and negative comments, and generate summaries.

[0272] For example, a positive summary might be "Lots of fresh ingredients and it's delicious!", while a negative summary might be "It's a bit pricey, but it's worth it."

[0273] Step 6:

[0274] The server calculates a credibility score for the summarized data, which is a numerical indicator that evaluates the trustworthiness of each comment or review.

[0275] Step 7:

[0276] The server generates multiple tourist routes and spots based on the destination, and uses Google Maps API to calculate the appropriate travel route and tourist spots, and also collects this information.

[0277] For example, generate a tourist route in Barcelona that includes Sagrada Familia and Park Güell.

[0278] Step 8:

[0279] The server sends the summarized data, reliability scores, and generated route and spot information to the device in JSON format.

[0280] Step 9:

[0281] The device displays the information received from the server in a user interface, showing information about different tapas bars in tabular format, plotting tourist routes on a map, and displaying a summary of reviews and a reliability score for each spot.

[0282] Step 10:

[0283] The emotion engine recognizes the user's input and reaction to the displayed information, for example, by analyzing the user's facial expressions and tone of voice to obtain emotion data.

[0284] Step 11:

[0285] The device transmits the recognized user emotion data to the server, including whether the user is expressing positive or negative emotion in response to the displayed information.

[0286] Step 12:

[0287] The server analyzes the emotion data and provides appropriate recommendations based on the user's emotion. For example, if the user expresses positive emotion, similar recommended spots will be displayed, and if the user expresses negative emotion, other candidates will be presented.

[0288] Step 13:

[0289] The server accumulates the emotion recognition results as feedback and reflects them in the next search results, allowing for better recommendations based on the user's preferences.

[0290] Specific examples

[0291] Example user input

[0292] A user types "Barcelona" and "good tapas" into an application.

[0293] Data collection example

[0294] The server collects reviews about "Barcelona" and "tapas" from TripAdvisor, Yelp, Twitter, etc. and temporarily stores them in a database.

[0295] Data analysis example

[0296] The server analyzes the collected customer reviews using a natural language processing model and categorizes them as "Lots of fresh ingredients and it's delicious!" (positive) or "It's a bit pricey, but it's worth it" (negative).

[0297] Example of reliability score calculation

[0298] The server calculates a reliability score for the analyzed data and gives a higher score to reviews that are more reliable.

[0299] Route and Spot Generation Example

[0300] The server uses the Google Maps API to generate a route that includes tourist attractions such as Sagrada Familia and Park Güell.

[0301] Information display example

[0302] The device displays a summary and reliability score for a tapas bar called "La Boqueria" and plots a tourist route on a map.

[0303] Emotion recognition example

[0304] The emotion engine recognizes that the user responded positively to the summary information for "La Boqueria" and sends it to the server.

[0305] Examples of recommendation information

[0306] If the user expresses positive emotions, the server will recommend similar tapas bars, widening the selection.

[0307] Example of applying the feedback function

[0308] The server accumulates emotion recognition data and reflects it in the next search results, thereby providing information that matches the user's preferences.

[0309] Example 2

[0310] 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."

[0311] Conventional travel and dining destination selection systems have difficulty providing appropriate recommendations based on the information entered by the user. They also have problems with insufficient evaluation of the reliability of collected data and insufficient provision of recommendations based on the user's emotions. Furthermore, they lack a means to efficiently generate multiple routes and tourist spots and present them to the user in a visually easy-to-understand format.

[0312] 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.

[0313] In this invention, the server includes a means for receiving user input information regarding travel destinations or dining locations, a means for collecting data from multiple information collection platforms based on the input information, and a means for analyzing the collected data and generating a positive or negative summary of the data. This allows users to efficiently select travel destinations or dining locations by referring to reliable information based on word-of-mouth reviews, ratings, reliability scores, and emotional data. Furthermore, by including a means for recognizing the user's emotions regarding the displayed information and a means for providing appropriate recommendation information based on the recognized emotional data, information tailored to the user's preferences can be provided. Furthermore, by including a means for generating multiple routes and spots and displaying that information, it is possible to propose travel plans to the user in a visually easy-to-understand format.

[0314] "Input information" refers to information such as travel destinations and places to eat that a user enters into an input form.

[0315] "Information collection platforms" refer to multiple multimedia platforms where data is collected, such as review sites and social networking sites.

[0316] "Data collection" refers to using APIs and scraping technology to obtain data such as word-of-mouth, ratings, and reviews related to specified destinations and conditions.

[0317] The "summary" is a sentence that briefly summarizes the collected data, classifying them into positive and negative comments.

[0318] The "display means" is a means for visually displaying the analyzed summary data on a user interface.

[0319] The "means for recognizing emotions" is a means for analyzing the user's input information and their reactions to the displayed information, and recognizing the user's emotions.

[0320] A "reliability score" is a numerical value obtained by evaluating the reliability of collected data.

[0321] "Recommended information" is information on travel destinations and dining places that are suitable for the user and is provided based on the user's recognized emotional data.

[0322] A "route" is a travel route generated based on destinations specified by the user.

[0323] "Spots" refer to destinations such as tourist attractions and restaurants included in a travel route.

[0324] The present invention is a system that improves the efficiency of travel destination and dining location decisions, collecting and analyzing a large amount of data based on information entered by the user and providing the user with appropriate information. Specific embodiments of the system are described below.

[0325] Hardware and Software Configuration

[0326] server

[0327] The server receives user input, collects data from multiple information collection platforms, analyzes it, assigns reliability scores, and generates summaries. It also analyzes user sentiment data and provides appropriate recommendations. It also generates multiple routes and tourist spots using Google Maps APIs and sends them to the device.

[0328] Specific technologies used include APIs (e.g., Twitter API, Google Maps API), scraping techniques, and natural language processing (NLP) models (e.g., BERT, GPT).

[0329] Terminal

[0330] The device receives input information from the user via a user interface and sends it to the server. It displays the information received from the server, such as summary data, reliability scores, and travel routes, to the user. It also has an emotion engine that analyzes the user's reactions and sends emotional data to the server.

[0331] User

[0332] Users input information about the travel destinations and dining places they want to visit into the terminal, and then make a final decision based on the summary information, reliability score, recommendations, travel route, etc. provided by the system.

[0333] Processing flow (overview)

[0334] 1. The user enters the destination and conditions. For example, "Barcelona" and "delicious tapas" and presses the "Search" button.

[0335] 2. The device sends the input information to the server. Data such as the user ID, destination, purpose of the trip, and meal preferences is converted into JSON format and sent.

[0336] 3. The server collects word-of-mouth, ratings, and reviews from multiple information gathering platforms, such as TripAdvisor, Yelp, and Twitter.

[0337] 4. The server analyzes the collected data using an NLP model (e.g., BERT, GPT), classifies the comments into positive and negative, and generates summaries such as "Lots of fresh ingredients and it's delicious!" or "It's a bit pricey, but it's worth it."

[0338] 5. The server calculates the credibility score. Based on the analyzed data, the server calculates the credibility score for the review. For example, if there are many positive comments, a high score is assigned, and if there are many negative comments, a low score is assigned.

[0339] 6. The server uses the Google Maps API to calculate tourist routes within Barcelona and generates routes that include major tourist attractions such as Sagrada Familia and Park Güell.

[0340] 7. The device displays the transmitted summary data, reliability score, and route information in the user interface. The user can see the summary and reliability score of the tapas bar "La Boqueria" and see a visual representation of the tourist route on the map.

[0341] 8. The emotion engine analyzes the user's reaction, and if the user shows positive emotion towards the displayed information, it recognizes this and sends it to the server.

[0342] 9. The server generates additional recommendations based on the recognized emotion data, for example, recommending more similar tapas bars if the user expresses positive emotions.

[0343] Specific examples

[0344] Prompt Sentence Examples

[0345] A user types "Barcelona" and "delicious tapas" into the app.

[0346] The server collects reviews about "Barcelona" and "tapas" from TripAdvisor, Yelp, Twitter, etc. and temporarily stores them in a database.

[0347] The server analyzes the collected review data using a natural language processing model and classifies it as follows:

[0348] Positive: "Lots of fresh ingredients and delicious!"

[0349] Negative: "It's expensive, but it's worth it."

[0350] The server calculates a reliability score based on the analyzed data and awards a high score.

[0351] The server uses the Google Maps API to calculate tourist routes within Barcelona and generates routes that include places like Sagrada Familia and Park Güell.

[0352] The device displays a summary and reliability score for a tapas bar called "La Boqueria" and plots a tourist route on a map.

[0353] The emotion engine analyzes the user's reaction, determines that the user has had a positive reaction, and sends it to the server.

[0354] If the server finds that the user has expressed positive emotions, they will recommend more similar tapas bars.

[0355] In this way, users can efficiently choose travel destinations and dining places based on reliable information based on reviews, ratings, trustworthiness scores, and sentiment data.

[0356] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0357] Step 1:

[0358] The user inputs their destination and requirements. The user enters information about their travel destination and dining options into the application's input form. For example, they enter "Barcelona" and "delicious tapas" and press the "Search" button. This sends the user's desired conditions to the device as input information.

[0359] Step 2:

[0360] The device sends the input information to the server. The device converts the user's input information into JSON format and sends it to the server. Specifically, the input information (user ID, destination, purpose of the trip, desired meal conditions, etc.) is generated and sent to the server.

[0361] Step 3:

[0362] The server collects data from multiple information gathering platforms. Using APIs and scraping technology, the server gathers data such as word-of-mouth, ratings, and reviews related to specified destinations and conditions. For example, it collects data related to "Barcelona" and "tapas" from TripAdvisor, Yelp, Twitter, etc., and temporarily stores that data in a database.

[0363] Step 4:

[0364] The server analyzes the collected data and generates summaries. The server analyzes the collected data using a natural language processing model (e.g., BERT, GPT). It classifies the data into positive and negative comments and generates summaries for each. For example, as a result of the analysis, a positive comment might be "Lots of fresh ingredients, delicious!", and a negative comment might be "It's a bit pricey, but it's worth it."

[0365] Step 5:

[0366] The server calculates the trustworthiness score for each review based on the analyzed data. Specifically, it uses criteria such as the source of the data and the number of reviews to assign a high score if there are many positive comments, and a low score if there are many negative comments.

[0367] Step 6:

[0368] The server generates multiple routes and spots. Using the Google Maps API, the server generates travel routes and tourist spots suitable for the user's destination. For example, it calculates and generates a tourist route that includes "Sagrada Familia" and "Park Güell."

[0369] Step 7:

[0370] The server sends the summary information to the terminal. The server then sends the generated summary data, reliability scores, tourist routes, etc. in JSON format to the terminal. The data sent includes the analysis results and related information.

[0371] Step 8:

[0372] The device displays the information to the user. The device displays the information sent from the server in a user interface. The user sees a summary and credibility score for the tapas bar "La Boqueria" and a visual representation of the tourist route on a map.

[0373] Step 9:

[0374] The emotion engine recognizes the user's emotions. The device uses the emotion engine to analyze the user's reaction to the displayed information. For example, if the user smiles after viewing the summary information for "La Boqueria," it will recognize this as a positive emotion and send this emotion data to the server.

[0375] Step 10:

[0376] The server analyzes the emotion data and provides recommendation information. The server generates additional recommendation information based on the emotion data recognized by the emotion engine. For example, if the user expresses positive emotion, the server will recommend similar tapas bars, and if the user expresses negative emotion, it will suggest other options.

[0377] Step 11:

[0378] Feedback function reflects next results. The server accumulates the user's sentiment analysis results as feedback and reflects them in the next search results and recommendation information. This allows for better recommendations to be made to the user.

[0379] (Application example 2)

[0380] 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."

[0381] Conventional methods for deciding travel destinations or dining locations have the problem that a large amount of information is scattered across the Internet, making it difficult for users to efficiently collect and analyze the information they need. Furthermore, recommendations do not take into account the user's emotions, making it difficult to increase user satisfaction. The present invention aims to solve these problems by providing a system that provides efficient and accurate information and improves user satisfaction.

[0382] 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 user input information regarding travel destinations or dining places, means for collecting data from multiple content distribution platforms based on the input information, means for analyzing the collected data and generating a positive or negative summary of the data, means for displaying the summarized data to the user, means for recognizing the user's emotions, and means for providing recommended information based on the recognized emotions. This enables the user to efficiently collect and analyze the information they need and obtain appropriate recommended information based on their emotions.

[0383] "User input information regarding travel destinations or dining places" refers to information that a user inputs into the system regarding conditions regarding travel destinations or desired dining places.

[0384] "Content distribution infrastructure" refers to multiple digital media platforms and information sources such as social networking sites.

[0385] "Means of collecting data" refers to the technical means for obtaining relevant information from multiple content distribution platforms on the Internet.

[0386] "Positive or negative summary" refers to the analysis of collected data and classification of the content as a positive or negative summary.

[0387] "Means for displaying summarized data to a user" refers to an interface for visually presenting the analyzed and summarized data to a user.

[0388] "Means for recognizing user emotions" refers to an algorithm or system that determines emotions from user input information and behavior.

[0389] "Means for providing recommended information" refers to technology that suggests suitable travel destinations and dining places based on the recognized user's emotions.

[0390] This invention relates to a system that helps users efficiently decide on travel destinations and dining locations. This system collects, analyzes, and summarizes relevant data based on user input, and provides that information to the user. It also uses an emotion engine to recognize the user's emotions and provide emotion-based recommendation information.

[0391] The system is configured as follows:

[0392] 1. Data Collection

[0393] When a user inputs travel or dining destination information from their device, that information is sent to a server. The server then uses the input information to collect data from multiple content distribution platforms (such as review sites and social media) using techniques such as API calls and web scraping.

[0394] 2. Data Analysis and Summary

[0395] The server analyzes the collected data using natural language processing technology to generate summaries of positive and negative comments. Specifically, text analysis techniques are used to classify the collected word-of-mouth and reviews into positive and negative comments and generate summaries of each element. For example, the data analysis is performed using the TextBlob library and the BERT model.

[0396] 3. Data display

[0397] The summarized information is sent from the server to the device and presented to the user. The user interface is designed to present the information in a visually appealing format, including travel and dining recommendation lists, summaries, and user ratings.

[0398] 4. Emotion recognition

[0399] The device uses an emotion engine to recognize the user's emotions based on the user's input and reactions to the displayed information. This emotion data is sent to the server, where an emotion recognition algorithm is used to analyze how the user reacted to the information on the display.

[0400] 5. Providing Recommendations

[0401] The server then recommends more suitable travel destinations and dining places based on the user's recognized emotions. For example, if the user expresses positive emotions, it will recommend additional similar spots, and if the user expresses negative emotions, it will suggest other spots. This process also takes into account past feedback information.

[0402] Hardware and software used

[0403] Hardware: Servers, smartphones, tablets, and other devices

[0404] Software: Flask, TextBlob, BERT model, various APIs (SNS and review sites)

[0405] Specific examples

[0406] Example user input

[0407] A user types "pizza Tokyo perfect for a date" into a terminal.

[0408] Data collection example

[0409] The server uses the Yelp API to collect reviews about "Pizza Tokyo."

[0410] Data analysis example

[0411] Using TextBlob, we classify the collected word-of-mouth data into positive and negative, and summarize it as follows:

[0412] Positive: "Great pizza and great atmosphere!" "Great service."

[0413] Negatives: "The prices are a little high" "It was crowded"

[0414] Information display example

[0415] The terminal displays the summarized information to the user and a list of recommended restaurants.

[0416] Emotion recognition example

[0417] If a user comments, "Looks delicious, I want to go there!", the emotion engine will recognize this as a positive.

[0418] Prompt Sentence Examples

[0419] Enter: "Pizza Tokyo perfect for a date"

[0420] Collection: "Collecting reviews of "Pizza Tokyo" using the Yelp API..."

[0421] Parsing: "Start parsing data in TextBlob..."

[0422] Show: "Positive review: Great pizza and great atmosphere! Great service."

[0423] Emotion recognition: "We recognized positive emotions from user comments."

[0424] Recommendation: "Recommend new restaurants to the user."

[0425] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0426] Step 1:

[0427] The user enters travel or dining destination requirements

[0428] The user inputs information about their travel destination and desired dining location into the device's application. For example, input information such as "Pizza in Tokyo, perfect for a date" is sent to the device.

[0429] Input: User's requirements for travel destinations and dining locations

[0430] Output: Sending condition information from the terminal to the server

[0431] Step 2:

[0432] The server receives the input information and starts collecting data.

[0433] Based on the input information received from the device, the server collects related data from content distribution platforms (such as review sites and social media. For example, it uses the Yelp API to obtain review data about "Pizza Tokyo."

[0434] Input: Condition information from the terminal

[0435] Output: Acquisition of relevant data from review sites and social media

[0436] Step 3:

[0437] Analyze the data collected by the server

[0438] The server analyzes the acquired review data using natural language processing techniques (e.g., TextBlob or BERT model). The data is classified into positive and negative categories, and summaries are generated.

[0439] Input: Collected review data

[0440] Output: Summary data categorized into positive and negative

[0441] Step 4:

[0442] The server sends the summarized data to the terminal and displays it to the user.

[0443] The server then sends the parsed and summarized data to the device, which then visually displays it to the user, such as a list of summarized reviews and ratings, or restaurant recommendations.

[0444] Input: Summarized data

[0445] Output: Visual information displayed to the user (summary of reviews and restaurant recommendations)

[0446] Step 5:

[0447] The device recognizes the user's emotions

[0448] When a user reacts to the displayed information, the device's emotion engine analyzes the reaction and recognizes the user's emotion. For example, a comment like "It looks delicious, I want to go there!" will be interpreted as a positive emotion.

[0449] Input: User responses (comments, etc.)

[0450] Output: Recognized user emotion data (positive, negative, etc.)

[0451] Step 6:

[0452] The server provides recommendations based on the recognized emotions.

[0453] The server then recommends more suitable travel destinations and dining places based on the recognized emotion data. For example, if the user expresses positive emotion, it will recommend similar spots or new restaurants.

[0454] Input: Recognized user emotion data

[0455] Output: New recommendations (additional restaurants and attractions)

[0456] 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.

[0457] 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.

[0458] 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.

[0459] [Second embodiment]

[0460] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0461] 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.

[0462] 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).

[0463] 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.

[0464] 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.

[0465] 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).

[0466] 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.

[0467] 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.

[0468] 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.

[0469] 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.

[0470] 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.

[0471] 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."

[0472] This invention relates to a system called "Tabikomi," designed to streamline travel and dining destination decisions. The system collects data from multiple multimedia platforms based on user input, analyzes, summarizes, and displays the data.

[0473] 1. The user enters the destination and conditions

[0474] The user enters their desired destination and dining preferences into the application's input form, such as "Barcelona" and "delicious tapas."

[0475] 2. The device sends the input information to the server

[0476] The terminal transmits the information entered by the user to the server, including the destination, purpose of the trip, meal requirements, etc.

[0477] 3. The server collects reviews and social media data

[0478] Based on the received information, the server automatically collects relevant data from review sites and social media, using an API to retrieve reviews, ratings, and ratings related to the specified destination and conditions.

[0479] 4. The server analyzes the data and generates a summary

[0480] The server analyzes the collected data using AI models (machine learning and natural language processing technology), which categorizes the data into positive and negative elements.

[0481] For example, a positive summary might be "Lots of fresh ingredients and it's delicious!", while a negative summary might be "It's a bit pricey, but it's worth it."

[0482] 5. The server calculates the reliability score

[0483] The server evaluates the reliability of the collected data and calculates a reliability score for each review, which helps users determine the trustworthiness of the reviews.

[0484] 6. The server generates multiple routes and spots

[0485] The server will then suggest suitable travel routes and tourist spots based on the user's input information. For example, it will generate a tourist route in Barcelona that includes spots such as Sagrada Familia and Park Güell.

[0486] 7. The server sends the summary information to the terminal.

[0487] The server sends the analyzed and summarized data, reliability scores, and route information to the terminal.

[0488] 8. The device displays the information to the user

[0489] The device displays the transmitted information in a user interface, allowing the user to view information about different tapas bars in tabular format and visually confirm the tourist route on a map.

[0490] Specific examples

[0491] Example user input

[0492] A user types "Barcelona" and "delicious tapas" into the app.

[0493] Data collection example

[0494] The server collects reviews about "Barcelona" and "tapas" from TripAdvisor, Yelp, Twitter, etc. and temporarily stores them in a database.

[0495] Data analysis example

[0496] The server analyzes the collected review data using a natural language processing model and classifies it as follows:

[0497] Positive: "Lots of fresh ingredients and delicious!"

[0498] Negative: "It's expensive, but it's worth it."

[0499] Example of reliability score calculation

[0500] The server calculates a reliability score based on the analyzed data, giving a high score if there are many positive comments, and a low score if there are many negative comments, for example.

[0501] Route and Spot Generation Example

[0502] The server uses the Google Maps API to calculate tourist routes within Barcelona and generates routes that include major tourist spots such as Sagrada Familia and Park Güell.

[0503] Information display example

[0504] The device will show the user a summary and credibility score for the tapas bar "La Boqueria" and plot a tourist route on a map.

[0505] This allows users to efficiently select a destination based on compiled, highly reliable information, without having to go through the tedious process of collecting information.

[0506] The processing flow will be explained below.

[0507] Step 1:

[0508] The user enters a destination and selection criteria into the application's input form, for example, "Barcelona" and "good tapas," and presses the "Search" button.

[0509] Step 2:

[0510] The device converts the user's input information into JSON format and sends it to the server. The data sent includes the user ID, destination, purpose of the trip, and meal preferences.

[0511] Step 3:

[0512] Based on the input information received by the server, it collects relevant data from multiple multimedia platforms (e.g., review sites, social media) and retrieves word-of-mouth, ratings, and reviews related to the specified destination and conditions through scraping and API calls.

[0513] Step 4:

[0514] The server temporarily stores the collected data in a database, where it is prepared for analysis.

[0515] Step 5:

[0516] The server uses machine learning or natural language processing models to analyze the stored data, categorize the data into positive and negative comments, and generate summaries.

[0517] Step 6:

[0518] The server calculates a credibility score for the summarized data, which is a numerical indicator that evaluates the trustworthiness of each comment or review.

[0519] Step 7:

[0520] The server runs an algorithm to generate multiple tourist routes and attractions based on the destination. It uses Google Maps API to generate appropriate travel routes and tourist attractions and also collects information on these.

[0521] Step 8:

[0522] The server sends the summarized data, reliability scores, and generated route and spot information to the device in JSON format.

[0523] Step 9:

[0524] The device displays the information received from the server in a user interface, showing information about different tapas bars in tabular format, plotting tourist routes on a map, and displaying a summary of reviews and a reliability score for each spot.

[0525] Step 10:

[0526] Users can then use the information displayed to select and plan trips and dining options, while also taking into account positive and negative summaries, reliability scores, and visualized route information.

[0527] Example 1

[0528] 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."

[0529] In recent years, the development of the Internet has made it easier to gather information about travel and dining out. However, it remains difficult for users to select reliable data from the vast amount of information and efficiently decide on destinations and dining locations. In particular, the wide variety of word-of-mouth and reviews about travel destinations and dining locations makes it difficult to determine which information is trustworthy. In addition, the time and effort required to collect, integrate, and summarize information from multiple platforms is a significant burden.

[0530] 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.

[0531] In this invention, the server includes means for receiving user input information, means for transmitting the input information to the server, means for collecting data from multiple information sources based on the input information, means for analyzing the collected data and generating a positive or negative summary of the data, means for proposing the summarized data and travel routes and tourist spots, means for transmitting the analyzed data, reliability scores, and generated route information to a terminal, and means for displaying the transmitted information on a user interface, thereby enabling a user to efficiently decide on a destination or a place to eat based on reliable information.

[0532] "User" means an end user who uses the system to search, input, and review travel and dining destination information.

[0533] A "server" is a central processing unit that receives information from users, collects and analyzes data, and transmits the results to terminals.

[0534] "Input information" refers to information such as travel destinations, places to eat, and desired conditions that a user inputs into the system.

[0535] A "terminal" is a device that is directly operated by a user, sends input information to a server, and displays the results from the server.

[0536] "Sources" are the multiple online platforms and databases that the server accesses to collect data.

[0537] "Data" refers to information collected from sources such as word of mouth, reviews, ratings, and social media posts.

[0538] "Collecting" refers to the act of the server obtaining and storing the necessary data from the source.

[0539] "Analyzing" refers to the act of processing the data collected by the server and extracting valuable information.

[0540] A "positive summary" is a summary of positive evaluations and comments extracted from the collected data.

[0541] A "negative summary" is a summary of negative evaluations and comments extracted from the collected data.

[0542] The "trust score" is a numerical value that evaluates the reliability of the data collected by the server. This score indicates the reliability of word-of-mouth and reviews.

[0543] A "travel route" is a travel route or a route connecting tourist spots that is generated by the server based on information input by the user.

[0544] "Tourist attractions" are tourist attractions and places worth visiting at a travel destination.

[0545] "Sending to terminal" refers to the act of the server transferring the analysis results and generated information to the user's terminal.

[0546] A "user interface" refers to the screen display and input means that allow a user to interact with a system through a terminal.

[0547] This invention relates to a system designed to streamline travel and dining destination decisions. The system collects data from multiple sources based on user input, analyzes and summarizes the data, and provides it to the user.

[0548] The system primarily utilizes the following hardware and software:

[0549] The device used by the user (smartphone, tablet, PC, etc.)

[0550] Server as a central processing unit

[0551] APIs used for data collection (various information source APIs, e.g., TripAdvisor API, Yelp API, Twitter API)

[0552] Generative AI models used for data analysis (e.g., natural language processing models such as BERT and GPT-3)

[0553] When a user inputs their destination and other requirements, the device sends that information to the server. For example, if a user inputs "Barcelona" and "delicious tapas," the device sends this information to the server in the form of an HTTP request.

[0554] Based on the input information, the server collects relevant data from multiple information source APIs, including travel review sites, online review sites, social media, etc. Data obtained through the APIs is temporarily stored on the server.

[0555] The server then analyzes the collected data using a generative AI model, which categorizes the collected data into positive and negative elements and generates a summary for each, including positive and negative sentiment.

[0556] Based on the analysis results, the server calculates a credibility score, which represents the trustworthiness of each review numerically and helps users determine the reliability of the information.

[0557] The server then suggests travel routes and tourist attractions based on the input information, for example, using the Google Maps API to generate a route that visits the main tourist attractions in Barcelona.

[0558] Finally, the server sends the analysis results, reliability scores, and generated route information to the device, which displays this information on the user interface, allowing the user to efficiently determine destinations and dining locations.

[0559] For example, if a user types "Barcelona" and "delicious tapas," the server collects related reviews and generates positive and negative summary statements such as "Lots of fresh ingredients and delicious!" and "Prices are high, but worth it." Based on the reliability score, the server recommends a tapas bar called "La Boqueria" and suggests a sightseeing route that includes "Sagrada Familia" and "Park Güell" using the Google Maps API.

[0560] Examples of prompt sentences include "Barcelona," "delicious tapas," "recommended tourist spots and routes," etc. This invention enables users to efficiently obtain reliable information and make quick and accurate travel planning decisions.

[0561] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0562] Step 1:

[0563] The user inputs the destination and conditions. The user inputs the desired conditions for travel destinations and dining places into the application's input form. For example, the user inputs "Barcelona" and "delicious tapas." After inputting, the user presses the submit button.

[0564] Input: Destination and desired conditions (e.g. Barcelona, ​​delicious tapas)

[0565] Output: Input information ready to send

[0566] Step 2:

[0567] The terminal sends the input information to the server. The terminal sends the destination and conditions entered by the user to the server as an HTTP request (POST request). The data sent is in JSON format.

[0568] Input: User's destination and desired conditions

[0569] Output: Input sent to the server

[0570] Step 3:

[0571] The server collects user reviews and social media data. Based on the destination and conditions received, the server calls APIs from multiple sources to collect data. Specifically, it uses APIs from TripAdvisor, Yelp, Twitter, and other sources to obtain related user reviews, comments, and social media posts.

[0572] Input: User's destination and desired conditions

[0573] Output: Collected data (e.g., word of mouth, reviews, social media posts)

[0574] Step 4:

[0575] The server analyzes the data and generates summaries. The server analyzes the collected data using a generative AI model (e.g., a natural language processing model such as BERT or GPT-3), classifies the data into positive and negative elements, and generates summaries for each.

[0576] Input: Collected data

[0577] Output: Positive and negative summaries

[0578] Step 5:

[0579] The server calculates the credibility score. Based on the collected data, the server evaluates the credibility of each review and calculates a score. The credibility score uses an AI model to filter spam and assign higher scores to reviews that are more trustworthy.

[0580] Input: Parsed data

[0581] Output: Confidence score

[0582] Step 6:

[0583] The server generates multiple routes and spots. The server suggests tourist routes and spots based on the user's input information and reliability scores. It uses the Google Maps API to generate routes that include major tourist spots.

[0584] Input: User input information and confidence score

[0585] Output: Suggested tourist routes and spots

[0586] Step 7:

[0587] The server sends the summarized information to the device. The server sends the analyzed and summarized data, reliability scores, and generated route information in JSON format to the device.

[0588] Inputs: Summarized data, reliability scores, generated route information

[0589] Output: Information sent to the terminal

[0590] Step 8:

[0591] The device displays the information to the user. The device then displays the received information in a user interface, where the user can view information about each tapas bar and its reliability score in a tabular format, and visually check the tourist route on a map.

[0592] Input: Information received from the server

[0593] Output: The result displayed in the user interface

[0594] This series of steps allows users to efficiently make travel and dining decisions based on reliable information.

[0595] (Application example 1)

[0596] 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."

[0597] Conventional systems for deciding on travel destinations and dining locations require users to collect information themselves and make decisions based on a large amount of information, which is time-consuming and labor-intensive. Furthermore, when it comes to providing information in physical stores, word-of-mouth and review information on products and services is not provided in real time, making it difficult for consumers to make quick decisions based on reliable information. To solve this problem, a system is needed that streamlines travel destination and dining location decisions and quickly provides reliable information in physical stores.

[0598] 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.

[0599] In this invention, the server includes: means for receiving user input information regarding travel destinations or dining locations; means for collecting data from multiple multimedia platforms based on the input information; means for analyzing the collected data and generating a positive or negative summary of the data; means for displaying the summarized data to the user; means for collecting related word-of-mouth and review information based on the conditions of products and services in the store; means for calculating a reliability score from the collected word-of-mouth and review information; means for summarizing product and service information based on the reliability score and displaying it to the user; and means for recommending appropriate routes and spots in the store. This allows users to efficiently select destinations based on the compiled, reliable information without having to collect information in a cumbersome manner. Furthermore, even in physical stores, users can obtain reliable information about products and services in real time and engage in optimal consumption behavior.

[0600] A "destination" is a geographic location that a user intends to visit.

[0601] A "dining location" is a location selected by a user to eat a meal.

[0602] "User" means an individual or group that uses the system.

[0603] "Input information" refers to data including requests and desired conditions that a user provides to the system.

[0604] A "multimedia platform" is an internet service that includes multiple information sources.

[0605] "Data" means digital information, including information related to word of mouth, reviews, and ratings.

[0606] "Means of collection" refers to the method for obtaining the specified information from the Internet.

[0607] "Means of analysis" are methods for examining collected data and generating specific meanings or summaries.

[0608] A "positive or negative summary" is a short sentence that summarizes the content of the data in a positive or negative way.

[0609] A "confidence score" is a number or metric used to assess the trustworthiness of collected data.

[0610] "Display means" refers to the method by which the analyzed data and summary are visually presented to the user.

[0611] A "store" is a physical location for offering goods and services.

[0612] "Conditions" are specific requirements or criteria desired by the user.

[0613] "Word of mouth" refers to the opinions and reviews that consumers give about products and services.

[0614] "Review information" refers to detailed evaluations and opinions about specific products or services.

[0615] A "route" is the optimal path for a user to travel to a particular location.

[0616] A "spot" is a specific location to visit within a travel destination or store.

[0617] A "recommendation method" is a method for suggesting specific information or routes to a user.

[0618] As an embodiment of the present invention, the configuration and operation of a real-time customer guide system will be specifically described.

[0619] This system mainly consists of a server, a user's device, and various means for collecting data from multiple multimedia platforms based on user input, analyzing it, and displaying it to the user. The main hardware used is a smartphone, a tablet, and smart glasses. The software used is AWS, Python, TensorFlow, Google Maps API, and React Native.

[0620] System Programming and Processing

[0621] Data collection

[0622] The server receives the criteria information entered by the user into the device. This input information includes specific requests such as "new sneakers" and "good reviews." Based on this information, the server collects related data from multiple multimedia platforms on the Internet (review sites, social media, etc.). This collection is done using AWS's API Gateway.

[0623] Data analysis and summary generation

[0624] The collected data is analyzed on the server by a Python program using natural language processing techniques. An AI model trained with TensorFlow classifies the collected data into positive and negative elements and generates short summaries. For example, "comfortable" is a positive summary, and "expensive" is a negative summary.

[0625] Calculating the reliability score

[0626] The server evaluates the reliability of the analyzed word-of-mouth and review information and calculates a reliability score, which also takes into account the user review history and reputation.

[0627] Route and spot recommendations

[0628] Furthermore, the server uses the Google Maps API to calculate the optimal route and spots within the store based on the user's interests, for example, proposing the optimal route from the fashion section to the food and drink section.

[0629] Displaying Information

[0630] The analyzed information, summary, and route suggestions are sent to the user's device. The user interface is developed using React Native, and the analysis results and recommended routes are visually presented to the user.

[0631] Specific examples

[0632] For example, if a user is interested in "new sneakers," they can input "Tell me the latest reviews about new sneakers" into the system. The server collects relevant data, generates summaries such as "comfortable" and "expensive," calculates a reliability score, and suggests the best route to the fashion section.

[0633] Here is a prompt used as an example:

[0634] "What are the latest reviews of new sneakers?"

[0635] "Tell me the recommended route within the store"

[0636] As described above, this system enables users to make efficient decisions based on compiled, highly reliable information, without the need for tedious information gathering, and supports optimal consumer behavior even in physical stores.

[0637] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0638] Step 1:

[0639] The user inputs condition information into the terminal. The input contents include requests such as "new sneakers" and "good reviews." The information input by the user is sent from the terminal to the server. The input of this step is the user's request, and the output is the input information sent to the server.

[0640] Step 2:

[0641] The server receives input information sent by the user. Based on the received information, the server collects related data from multiple multimedia platforms (review sites, social media, etc.). This collection is performed using AWS's API Gateway. The input of this step is the user's input information, and the output is the collected multimedia data.

[0642] Step 3:

[0643] The server analyzes the collected data. This analysis is performed using Python programs and TensorFlow. First, the collected data is analyzed using natural language processing techniques to generate positive and negative summaries. The input of this step is the collected data, and the output is positive and negative summaries.

[0644] Step 4:

[0645] The server calculates a credibility score for the parsed data. The credibility score takes into account the history and reputation of the user reviews, allowing us to quantify the trustworthiness of each review. The input for this step is the parsed data, and the output is the credibility score.

[0646] Step 5:

[0647] The server uses the Google Maps API to calculate the optimal route and spots within the store based on the user's interests. For example, it proposes the optimal route from the fashion section to the food and drink section. This provides the user with an efficient travel path. The input of this step is the user's interest information, and the output is the calculated route and spots.

[0648] Step 6:

[0649] The server sends the parsed information, confidence scores, and route suggestions to the device. This information is processed to be visually presented to the user in a user interface. The user interface, developed using React Native, displays the information in an easy-to-understand manner. The input of this step is the parsed and calculated information, and the output is the information displayed to the user.

[0650] Step 7:

[0651] The user uses the device to check the provided information and take optimal purchasing actions. For example, a user may start with a prompt such as "Tell me the latest reviews of new sneakers," and then obtain more information to make a purchasing decision. The input for this step is the information displayed on the device, and the output is the user's actions.

[0652] 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.

[0653] This invention relates to a system called "Tabikomi," designed to streamline travel and dining destination decisions. This system collects data from multiple multimedia platforms based on user input, analyzes, summarizes, and displays the data. Furthermore, by combining it with an emotion engine that recognizes and analyzes user emotions, it is possible to provide appropriate recommendation information based on the user's emotions.

[0654] 1. The user enters the destination and conditions

[0655] The user enters their destination and selection criteria into the application's input form, for example, "Barcelona" and "delicious tapas," and then presses the "Search" button.

[0656] 2. The device sends the input information to the server

[0657] The device converts the user's input information into JSON format and sends it to the server. The data sent includes the user ID, destination, purpose of the trip, and meal preferences.

[0658] 3. The server collects reviews and social media data

[0659] The server collects relevant data from multiple multimedia platforms (e.g., review sites, social media) based on the received input information, and uses APIs and scraping technology to obtain word-of-mouth, ratings, and reviews related to the specified destination and conditions.

[0660] 4. The server analyzes the data and generates a summary

[0661] The server analyzes the collected data using machine learning or natural language processing models, categorizing the data into positive and negative comments and generating summaries.

[0662] For example, a positive summary might be "Lots of fresh ingredients and it's delicious!", while a negative summary might be "It's a bit pricey, but it's worth it."

[0663] 5. The server calculates the reliability score

[0664] The server evaluates the reliability of the collected data and calculates a reliability score for each review, which helps users determine the trustworthiness of the reviews.

[0665] 6. The server generates multiple routes and spots

[0666] The server proposes suitable travel routes and tourist spots based on the user's input information. For example, it uses the Google Maps API to generate a tourist route in Barcelona that includes spots such as Sagrada Familia and Park Güell.

[0667] 7. The server sends the summary information to the terminal.

[0668] The server sends the analyzed and summarized data, reliability scores, and route information in JSON format to the device.

[0669] 8. The device displays the information to the user

[0670] The device displays the information in a user interface, where users can browse different tapas bars in tabular format and visualize their tourist route on a map, along with a summary of reviews and a credibility score for each spot.

[0671] 9. Emotion engine recognizes user emotions

[0672] The device's emotion engine recognizes the user's emotions based on the user's input and reactions to the displayed information, and this emotion data is sent to the server for analysis.

[0673] 10. The server analyzes the emotion data and provides recommendations

[0674] The server provides appropriate recommendation information based on the user's emotions recognized by the emotion engine. For example, if the user expresses positive emotions, similar recommended spots will be displayed, and if the user expresses negative emotions, different candidates will be presented.

[0675] 11. Feedback function reflects the results for the next test

[0676] The server accumulates the results of the user's sentiment analysis as feedback and reflects it in the next search results, thereby making better recommendations to the user.

[0677] Specific examples

[0678] Example user input

[0679] A user types "Barcelona" and "delicious tapas" into the app.

[0680] Data collection example

[0681] The server collects reviews about "Barcelona" and "tapas" from TripAdvisor, Yelp, Twitter, etc. and temporarily stores them in a database.

[0682] Data analysis example

[0683] The server analyzes the collected review data using a natural language processing model and classifies it as follows:

[0684] Positive: "Lots of fresh ingredients and delicious!"

[0685] Negative: "It's expensive, but it's worth it."

[0686] Example of reliability score calculation

[0687] The server calculates a reliability score based on the analyzed data, giving a high score if there are many positive comments, and a low score if there are many negative comments, for example.

[0688] Route and Spot Generation Example

[0689] The server uses the Google Maps API to calculate tourist routes within Barcelona and generates routes that include major tourist spots such as Sagrada Familia and Park Güell.

[0690] Information display example

[0691] The device will show the user a summary and credibility score for the tapas bar "La Boqueria" and plot a tourist route on a map.

[0692] Emotion recognition example

[0693] The device's emotion engine recognizes that the user has responded positively to the summary information for "La Boqueria," and sends this information to the server.

[0694] Examples of recommendation information

[0695] If the user expresses positive emotions, the server will recommend more similar tapas bars, widening the selection.

[0696] Example of applying the feedback function

[0697] The server stores the recognized emotion data and reflects it in the next search results, thereby providing information that matches the user's preferences.

[0698] This allows users to efficiently select travel destinations and places to eat by referring to reliable information based on word-of-mouth, ratings, and emotional data.

[0699] The processing flow will be explained below.

[0700] Step 1:

[0701] The user enters a destination and selection criteria into the application's input form, for example, "Barcelona" and "good tapas," and presses the "Search" button.

[0702] Step 2:

[0703] The device converts the user's input information into JSON format and sends it to the server. The data sent includes the user ID, destination, purpose of the trip, and meal preferences.

[0704] Step 3:

[0705] Based on the input information received by the server, the server collects relevant data from multiple multimedia platforms (e.g., review sites, social media), and uses APIs and scraping technology to obtain word-of-mouth, ratings, and reviews related to the specified destination and conditions.

[0706] Step 4:

[0707] The server temporarily stores the collected data in a database, where it is prepared for analysis.

[0708] Step 5:

[0709] The server uses machine learning or natural language processing models to analyze the stored data, categorize the data into positive and negative comments, and generate summaries.

[0710] For example, a positive summary might be "Lots of fresh ingredients and it's delicious!", while a negative summary might be "It's a bit pricey, but it's worth it."

[0711] Step 6:

[0712] The server calculates a credibility score for the summarized data, which is a numerical indicator that evaluates the trustworthiness of each comment or review.

[0713] Step 7:

[0714] The server generates multiple tourist routes and spots based on the destination, and uses Google Maps API to calculate the appropriate travel route and tourist spots, and also collects this information.

[0715] For example, generate a tourist route in Barcelona that includes Sagrada Familia and Park Güell.

[0716] Step 8:

[0717] The server sends the summarized data, reliability scores, and generated route and spot information to the device in JSON format.

[0718] Step 9:

[0719] The device displays the information received from the server in a user interface, showing information about different tapas bars in tabular format, plotting tourist routes on a map, and displaying a summary of reviews and a reliability score for each spot.

[0720] Step 10:

[0721] The emotion engine recognizes the user's input and reaction to the displayed information, for example, by analyzing the user's facial expressions and tone of voice to obtain emotion data.

[0722] Step 11:

[0723] The device transmits the recognized user emotion data to the server, including whether the user is expressing positive or negative emotion in response to the displayed information.

[0724] Step 12:

[0725] The server analyzes the emotion data and provides appropriate recommendations based on the user's emotion. For example, if the user expresses positive emotion, similar recommended spots will be displayed, and if the user expresses negative emotion, other candidates will be presented.

[0726] Step 13:

[0727] The server accumulates the emotion recognition results as feedback and reflects them in the next search results, allowing for better recommendations based on the user's preferences.

[0728] Specific examples

[0729] Example user input

[0730] A user types "Barcelona" and "good tapas" into an application.

[0731] Data collection example

[0732] The server collects reviews about "Barcelona" and "tapas" from TripAdvisor, Yelp, Twitter, etc. and temporarily stores them in a database.

[0733] Data analysis example

[0734] The server analyzes the collected customer reviews using a natural language processing model and categorizes them as "Lots of fresh ingredients and it's delicious!" (positive) or "It's a bit pricey, but it's worth it" (negative).

[0735] Example of reliability score calculation

[0736] The server calculates a reliability score for the analyzed data and gives a higher score to reviews that are more reliable.

[0737] Route and Spot Generation Example

[0738] The server uses the Google Maps API to generate a route that includes tourist attractions such as Sagrada Familia and Park Güell.

[0739] Information display example

[0740] The device displays a summary and reliability score for a tapas bar called "La Boqueria" and plots a tourist route on a map.

[0741] Emotion recognition example

[0742] The emotion engine recognizes that the user responded positively to the summary information for "La Boqueria" and sends it to the server.

[0743] Examples of recommendation information

[0744] If the user expresses positive emotions, the server will recommend similar tapas bars, widening the selection.

[0745] Example of applying the feedback function

[0746] The server accumulates emotion recognition data and reflects it in the next search results, thereby providing information that matches the user's preferences.

[0747] Example 2

[0748] 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."

[0749] Conventional travel and dining destination selection systems have difficulty providing appropriate recommendations based on the information entered by the user. They also have problems with insufficient evaluation of the reliability of collected data and insufficient provision of recommendations based on the user's emotions. Furthermore, they lack a means to efficiently generate multiple routes and tourist spots and present them to the user in a visually easy-to-understand format.

[0750] 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.

[0751] In this invention, the server includes a means for receiving user input information regarding travel destinations or dining locations, a means for collecting data from multiple information collection platforms based on the input information, and a means for analyzing the collected data and generating a positive or negative summary of the data. This allows users to efficiently select travel destinations or dining locations by referring to reliable information based on word-of-mouth reviews, ratings, reliability scores, and emotional data. Furthermore, by including a means for recognizing the user's emotions regarding the displayed information and a means for providing appropriate recommendation information based on the recognized emotional data, information tailored to the user's preferences can be provided. Furthermore, by including a means for generating multiple routes and spots and displaying that information, it is possible to propose travel plans to the user in a visually easy-to-understand format.

[0752] "Input information" refers to information such as travel destinations and places to eat that a user enters into an input form.

[0753] "Information collection platforms" refer to multiple multimedia platforms where data is collected, such as review sites and social networking sites.

[0754] "Data collection" refers to using APIs and scraping technology to obtain data such as word-of-mouth, ratings, and reviews related to specified destinations and conditions.

[0755] The "summary" is a sentence that briefly summarizes the collected data, classifying them into positive and negative comments.

[0756] The "display means" is a means for visually displaying the analyzed summary data on a user interface.

[0757] The "means for recognizing emotions" is a means for analyzing the user's input information and their reactions to the displayed information, and recognizing the user's emotions.

[0758] A "reliability score" is a numerical value obtained by evaluating the reliability of collected data.

[0759] "Recommended information" is information on travel destinations and dining places that are suitable for the user and is provided based on the user's recognized emotional data.

[0760] A "route" is a travel route generated based on destinations specified by the user.

[0761] "Spots" refer to destinations such as tourist attractions and restaurants included in a travel route.

[0762] The present invention is a system that improves the efficiency of travel destination and dining location decisions, collecting and analyzing a large amount of data based on information entered by the user and providing the user with appropriate information. Specific embodiments of the system are described below.

[0763] Hardware and Software Configuration

[0764] server

[0765] The server receives user input, collects data from multiple information collection platforms, analyzes it, assigns reliability scores, and generates summaries. It also analyzes user sentiment data and provides appropriate recommendations. It also generates multiple routes and tourist spots using Google Maps APIs and sends them to the device.

[0766] Specific technologies used include APIs (e.g., Twitter API, Google Maps API), scraping techniques, and natural language processing (NLP) models (e.g., BERT, GPT).

[0767] Terminal

[0768] The device receives input information from the user via a user interface and sends it to the server. It displays the information received from the server, such as summary data, reliability scores, and travel routes, to the user. It also has an emotion engine that analyzes the user's reactions and sends emotional data to the server.

[0769] User

[0770] Users input information about the travel destinations and dining places they want to visit into the terminal, and then make a final decision based on the summary information, reliability score, recommendations, travel route, etc. provided by the system.

[0771] Processing flow (overview)

[0772] 1. The user enters the destination and conditions. For example, "Barcelona" and "delicious tapas" and presses the "Search" button.

[0773] 2. The device sends the input information to the server. Data such as the user ID, destination, purpose of the trip, and meal preferences is converted into JSON format and sent.

[0774] 3. The server collects word-of-mouth, ratings, and reviews from multiple information gathering platforms, such as TripAdvisor, Yelp, and Twitter.

[0775] 4. The server analyzes the collected data using an NLP model (e.g., BERT, GPT), classifies the comments into positive and negative, and generates summaries such as "Lots of fresh ingredients and it's delicious!" or "It's a bit pricey, but it's worth it."

[0776] 5. The server calculates the credibility score. Based on the analyzed data, the server calculates the credibility score for the review. For example, if there are many positive comments, a high score is assigned, and if there are many negative comments, a low score is assigned.

[0777] 6. The server uses the Google Maps API to calculate tourist routes within Barcelona and generates routes that include major tourist attractions such as Sagrada Familia and Park Güell.

[0778] 7. The device displays the transmitted summary data, reliability score, and route information in the user interface. The user can see the summary and reliability score of the tapas bar "La Boqueria" and see a visual representation of the tourist route on the map.

[0779] 8. The emotion engine analyzes the user's reaction, and if the user shows positive emotion towards the displayed information, it recognizes this and sends it to the server.

[0780] 9. The server generates additional recommendations based on the recognized emotion data, for example, recommending more similar tapas bars if the user expresses positive emotions.

[0781] Specific examples

[0782] Prompt Sentence Examples

[0783] A user types "Barcelona" and "delicious tapas" into the app.

[0784] The server collects reviews about "Barcelona" and "tapas" from TripAdvisor, Yelp, Twitter, etc. and temporarily stores them in a database.

[0785] The server analyzes the collected review data using a natural language processing model and classifies it as follows:

[0786] Positive: "Lots of fresh ingredients and delicious!"

[0787] Negative: "It's expensive, but it's worth it."

[0788] The server calculates a reliability score based on the analyzed data and awards a high score.

[0789] The server uses the Google Maps API to calculate tourist routes within Barcelona and generates routes that include places like Sagrada Familia and Park Güell.

[0790] The device displays a summary and reliability score for a tapas bar called "La Boqueria" and plots a tourist route on a map.

[0791] The emotion engine analyzes the user's reaction, determines that the user has had a positive reaction, and sends it to the server.

[0792] If the server finds that the user has expressed positive emotions, they will recommend more similar tapas bars.

[0793] In this way, users can efficiently choose travel destinations and dining places based on reliable information based on reviews, ratings, trustworthiness scores, and sentiment data.

[0794] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0795] Step 1:

[0796] The user inputs their destination and requirements. The user enters information about their travel destination and dining options into the application's input form. For example, they enter "Barcelona" and "delicious tapas" and press the "Search" button. This sends the user's desired conditions to the device as input information.

[0797] Step 2:

[0798] The device sends the input information to the server. The device converts the user's input information into JSON format and sends it to the server. Specifically, the input information (user ID, destination, purpose of the trip, desired meal conditions, etc.) is generated and sent to the server.

[0799] Step 3:

[0800] The server collects data from multiple information gathering platforms. Using APIs and scraping technology, the server gathers data such as word-of-mouth, ratings, and reviews related to specified destinations and conditions. For example, it collects data related to "Barcelona" and "tapas" from TripAdvisor, Yelp, Twitter, etc., and temporarily stores that data in a database.

[0801] Step 4:

[0802] The server analyzes the collected data and generates summaries. The server analyzes the collected data using a natural language processing model (e.g., BERT, GPT). It classifies the data into positive and negative comments and generates summaries for each. For example, as a result of the analysis, a positive comment might be "Lots of fresh ingredients, delicious!", and a negative comment might be "It's a bit pricey, but it's worth it."

[0803] Step 5:

[0804] The server calculates the trustworthiness score for each review based on the analyzed data. Specifically, it uses criteria such as the source of the data and the number of reviews to assign a high score if there are many positive comments, and a low score if there are many negative comments.

[0805] Step 6:

[0806] The server generates multiple routes and spots. Using the Google Maps API, the server generates travel routes and tourist spots suitable for the user's destination. For example, it calculates and generates a tourist route that includes "Sagrada Familia" and "Park Güell."

[0807] Step 7:

[0808] The server sends the summary information to the terminal. The server then sends the generated summary data, reliability scores, tourist routes, etc. in JSON format to the terminal. The data sent includes the analysis results and related information.

[0809] Step 8:

[0810] The device displays the information to the user. The device displays the information sent from the server in a user interface. The user sees a summary and credibility score for the tapas bar "La Boqueria" and a visual representation of the tourist route on a map.

[0811] Step 9:

[0812] The emotion engine recognizes the user's emotions. The device uses the emotion engine to analyze the user's reaction to the displayed information. For example, if the user smiles after viewing the summary information for "La Boqueria," it will recognize this as a positive emotion and send this emotion data to the server.

[0813] Step 10:

[0814] The server analyzes the emotion data and provides recommendation information. The server generates additional recommendation information based on the emotion data recognized by the emotion engine. For example, if the user expresses positive emotion, the server will recommend similar tapas bars, and if the user expresses negative emotion, it will suggest other options.

[0815] Step 11:

[0816] Feedback function reflects next results. The server accumulates the user's sentiment analysis results as feedback and reflects them in the next search results and recommendation information. This allows for better recommendations to be made to the user.

[0817] (Application example 2)

[0818] 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."

[0819] Conventional methods for deciding travel destinations or dining locations have the problem that a large amount of information is scattered across the Internet, making it difficult for users to efficiently collect and analyze the information they need. Furthermore, recommendations do not take into account the user's emotions, making it difficult to increase user satisfaction. The present invention aims to solve these problems by providing a system that provides efficient and accurate information and improves user satisfaction.

[0820] 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 user input information regarding travel destinations or dining places, means for collecting data from multiple content distribution platforms based on the input information, means for analyzing the collected data and generating a positive or negative summary of the data, means for displaying the summarized data to the user, means for recognizing the user's emotions, and means for providing recommended information based on the recognized emotions. This enables the user to efficiently collect and analyze the information they need and obtain appropriate recommended information based on their emotions.

[0821] "User input information regarding travel destinations or dining places" refers to information that a user inputs into the system regarding conditions regarding travel destinations or desired dining places.

[0822] "Content distribution infrastructure" refers to multiple digital media platforms and information sources such as social networking sites.

[0823] "Means of collecting data" refers to the technical means for obtaining relevant information from multiple content distribution platforms on the Internet.

[0824] "Positive or negative summary" refers to the analysis of collected data and classification of the content as a positive or negative summary.

[0825] "Means for displaying summarized data to a user" refers to an interface for visually presenting the analyzed and summarized data to a user.

[0826] "Means for recognizing user emotions" refers to an algorithm or system that determines emotions from user input information and behavior.

[0827] "Means for providing recommended information" refers to technology that suggests suitable travel destinations and dining places based on the recognized user's emotions.

[0828] This invention relates to a system that helps users efficiently decide on travel destinations and dining locations. This system collects, analyzes, and summarizes relevant data based on user input, and provides that information to the user. It also uses an emotion engine to recognize the user's emotions and provide emotion-based recommendation information.

[0829] The system is configured as follows:

[0830] 1. Data Collection

[0831] When a user inputs travel or dining destination information from their device, that information is sent to a server. The server then uses the input information to collect data from multiple content distribution platforms (such as review sites and social media) using techniques such as API calls and web scraping.

[0832] 2. Data Analysis and Summary

[0833] The server analyzes the collected data using natural language processing technology to generate summaries of positive and negative comments. Specifically, text analysis techniques are used to classify the collected word-of-mouth and reviews into positive and negative comments and generate summaries of each element. For example, the data analysis is performed using the TextBlob library and the BERT model.

[0834] 3. Data display

[0835] The summarized information is sent from the server to the device and presented to the user. The user interface is designed to present the information in a visually appealing format, including travel and dining recommendation lists, summaries, and user ratings.

[0836] 4. Emotion recognition

[0837] The device uses an emotion engine to recognize the user's emotions based on the user's input and reactions to the displayed information. This emotion data is sent to the server, where an emotion recognition algorithm is used to analyze how the user reacted to the information on the display.

[0838] 5. Providing Recommendations

[0839] The server then recommends more suitable travel destinations and dining places based on the user's recognized emotions. For example, if the user expresses positive emotions, it will recommend additional similar spots, and if the user expresses negative emotions, it will suggest other spots. This process also takes into account past feedback information.

[0840] Hardware and software used

[0841] Hardware: Servers, smartphones, tablets, and other devices

[0842] Software: Flask, TextBlob, BERT model, various APIs (SNS and review sites)

[0843] Specific examples

[0844] Example user input

[0845] A user types "pizza Tokyo perfect for a date" into a terminal.

[0846] Data collection example

[0847] The server uses the Yelp API to collect reviews about "Pizza Tokyo."

[0848] Data analysis example

[0849] Using TextBlob, we classify the collected word-of-mouth data into positive and negative, and summarize it as follows:

[0850] Positive: "Great pizza and great atmosphere!" "Great service."

[0851] Negatives: "The prices are a little high" "It was crowded"

[0852] Information display example

[0853] The terminal displays the summarized information to the user and a list of recommended restaurants.

[0854] Emotion recognition example

[0855] If a user comments, "Looks delicious, I want to go there!", the emotion engine will recognize this as a positive.

[0856] Prompt Sentence Examples

[0857] Enter: "Pizza Tokyo perfect for a date"

[0858] Collection: "Collecting reviews of "Pizza Tokyo" using the Yelp API..."

[0859] Parsing: "Start parsing data in TextBlob..."

[0860] Show: "Positive review: Great pizza and great atmosphere! Great service."

[0861] Emotion recognition: "We recognized positive emotions from user comments."

[0862] Recommendation: "Recommend new restaurants to the user."

[0863] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0864] Step 1:

[0865] The user enters travel or dining destination requirements

[0866] The user inputs information about their travel destination and desired dining location into the device's application. For example, input information such as "Pizza in Tokyo, perfect for a date" is sent to the device.

[0867] Input: User's requirements for travel destinations and dining locations

[0868] Output: Sending condition information from the terminal to the server

[0869] Step 2:

[0870] The server receives the input information and starts collecting data.

[0871] Based on the input information received from the device, the server collects related data from content distribution platforms (such as review sites and social media. For example, it uses the Yelp API to obtain review data about "Pizza Tokyo."

[0872] Input: Condition information from the terminal

[0873] Output: Acquisition of relevant data from review sites and social media

[0874] Step 3:

[0875] Analyze the data collected by the server

[0876] The server analyzes the acquired review data using natural language processing techniques (e.g., TextBlob or BERT model). The data is classified into positive and negative categories, and summaries are generated.

[0877] Input: Collected review data

[0878] Output: Summary data categorized into positive and negative

[0879] Step 4:

[0880] The server sends the summarized data to the terminal and displays it to the user.

[0881] The server then sends the parsed and summarized data to the device, which then visually displays it to the user, such as a list of summarized reviews and ratings, or restaurant recommendations.

[0882] Input: Summarized data

[0883] Output: Visual information displayed to the user (summary of reviews and restaurant recommendations)

[0884] Step 5:

[0885] The device recognizes the user's emotions

[0886] When a user reacts to the displayed information, the device's emotion engine analyzes the reaction and recognizes the user's emotion. For example, a comment like "It looks delicious, I want to go there!" will be interpreted as a positive emotion.

[0887] Input: User responses (comments, etc.)

[0888] Output: Recognized user emotion data (positive, negative, etc.)

[0889] Step 6:

[0890] The server provides recommendations based on the recognized emotions.

[0891] The server then recommends more suitable travel destinations and dining places based on the recognized emotion data. For example, if the user expresses positive emotion, it will recommend similar spots or new restaurants.

[0892] Input: Recognized user emotion data

[0893] Output: New recommendations (additional restaurants and attractions)

[0894] 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.

[0895] 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.

[0896] 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.

[0897] [Third embodiment]

[0898] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0899] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0900] 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).

[0901] 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.

[0902] 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.

[0903] 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).

[0904] 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.

[0905] 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.

[0906] 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.

[0907] 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.

[0908] 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.

[0909] 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."

[0910] This invention relates to a system called "Tabikomi," designed to streamline travel and dining destination decisions. The system collects data from multiple multimedia platforms based on user input, analyzes, summarizes, and displays the data.

[0911] 1. The user enters the destination and conditions

[0912] The user enters their desired destination and dining preferences into the application's input form, such as "Barcelona" and "delicious tapas."

[0913] 2. The device sends the input information to the server

[0914] The terminal transmits the information entered by the user to the server, including the destination, purpose of the trip, meal requirements, etc.

[0915] 3. The server collects reviews and social media data

[0916] Based on the received information, the server automatically collects relevant data from review sites and social media, using an API to retrieve reviews, ratings, and ratings related to the specified destination and conditions.

[0917] 4. The server analyzes the data and generates a summary

[0918] The server analyzes the collected data using AI models (machine learning and natural language processing technology), which categorizes the data into positive and negative elements.

[0919] For example, a positive summary might be "Lots of fresh ingredients and it's delicious!", while a negative summary might be "It's a bit pricey, but it's worth it."

[0920] 5. The server calculates the reliability score

[0921] The server evaluates the reliability of the collected data and calculates a reliability score for each review, which helps users determine the trustworthiness of the reviews.

[0922] 6. The server generates multiple routes and spots

[0923] The server will then suggest suitable travel routes and tourist spots based on the user's input information. For example, it will generate a tourist route in Barcelona that includes spots such as Sagrada Familia and Park Güell.

[0924] 7. The server sends the summary information to the terminal.

[0925] The server sends the analyzed and summarized data, reliability scores, and route information to the terminal.

[0926] 8. The device displays the information to the user

[0927] The device displays the transmitted information in a user interface, allowing the user to view information about different tapas bars in tabular format and visually confirm the tourist route on a map.

[0928] Specific examples

[0929] Example user input

[0930] A user types "Barcelona" and "delicious tapas" into the app.

[0931] Data collection example

[0932] The server collects reviews about "Barcelona" and "tapas" from TripAdvisor, Yelp, Twitter, etc. and temporarily stores them in a database.

[0933] Data analysis example

[0934] The server analyzes the collected review data using a natural language processing model and classifies it as follows:

[0935] Positive: "Lots of fresh ingredients and delicious!"

[0936] Negative: "It's expensive, but it's worth it."

[0937] Example of reliability score calculation

[0938] The server calculates a reliability score based on the analyzed data, giving a high score if there are many positive comments, and a low score if there are many negative comments, for example.

[0939] Route and Spot Generation Example

[0940] The server uses the Google Maps API to calculate tourist routes within Barcelona and generates routes that include major tourist spots such as Sagrada Familia and Park Güell.

[0941] Information display example

[0942] The device will show the user a summary and credibility score for the tapas bar "La Boqueria" and plot a tourist route on a map.

[0943] This allows users to efficiently select a destination based on compiled, highly reliable information, without having to go through the tedious process of collecting information.

[0944] The processing flow will be explained below.

[0945] Step 1:

[0946] The user enters a destination and selection criteria into the application's input form, for example, "Barcelona" and "good tapas," and presses the "Search" button.

[0947] Step 2:

[0948] The device converts the user's input information into JSON format and sends it to the server. The data sent includes the user ID, destination, purpose of the trip, and meal preferences.

[0949] Step 3:

[0950] Based on the input information received by the server, it collects relevant data from multiple multimedia platforms (e.g., review sites, social media) and retrieves word-of-mouth, ratings, and reviews related to the specified destination and conditions through scraping and API calls.

[0951] Step 4:

[0952] The server temporarily stores the collected data in a database, where it is prepared for analysis.

[0953] Step 5:

[0954] The server uses machine learning or natural language processing models to analyze the stored data, categorize the data into positive and negative comments, and generate summaries.

[0955] Step 6:

[0956] The server calculates a credibility score for the summarized data, which is a numerical indicator that evaluates the trustworthiness of each comment or review.

[0957] Step 7:

[0958] The server runs an algorithm to generate multiple tourist routes and attractions based on the destination. It uses Google Maps API to generate appropriate travel routes and tourist attractions and also collects information on these.

[0959] Step 8:

[0960] The server sends the summarized data, reliability scores, and generated route and spot information to the device in JSON format.

[0961] Step 9:

[0962] The device displays the information received from the server in a user interface, showing information about different tapas bars in tabular format, plotting tourist routes on a map, and displaying a summary of reviews and a reliability score for each spot.

[0963] Step 10:

[0964] Users can then use the information displayed to select and plan trips and dining options, while also taking into account positive and negative summaries, reliability scores, and visualized route information.

[0965] Example 1

[0966] 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."

[0967] In recent years, the development of the Internet has made it easier to gather information about travel and dining out. However, it remains difficult for users to select reliable data from the vast amount of information and efficiently decide on destinations and dining locations. In particular, the wide variety of word-of-mouth and reviews about travel destinations and dining locations makes it difficult to determine which information is trustworthy. In addition, the time and effort required to collect, integrate, and summarize information from multiple platforms is a significant burden.

[0968] 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.

[0969] In this invention, the server includes means for receiving user input information, means for transmitting the input information to the server, means for collecting data from multiple information sources based on the input information, means for analyzing the collected data and generating a positive or negative summary of the data, means for proposing the summarized data and travel routes and tourist spots, means for transmitting the analyzed data, reliability scores, and generated route information to a terminal, and means for displaying the transmitted information on a user interface, thereby enabling a user to efficiently decide on a destination or a place to eat based on reliable information.

[0970] "User" means an end user who uses the system to search, input, and review travel and dining destination information.

[0971] A "server" is a central processing unit that receives information from users, collects and analyzes data, and transmits the results to terminals.

[0972] "Input information" refers to information such as travel destinations, places to eat, and desired conditions that a user inputs into the system.

[0973] A "terminal" is a device that is directly operated by a user, sends input information to a server, and displays the results from the server.

[0974] "Sources" are the multiple online platforms and databases that the server accesses to collect data.

[0975] "Data" refers to information collected from sources such as word of mouth, reviews, ratings, and social media posts.

[0976] "Collecting" refers to the act of the server obtaining and storing the necessary data from the source.

[0977] "Analyzing" refers to the act of processing the data collected by the server and extracting valuable information.

[0978] A "positive summary" is a summary of positive evaluations and comments extracted from the collected data.

[0979] A "negative summary" is a summary of negative evaluations and comments extracted from the collected data.

[0980] The "trust score" is a numerical value that evaluates the reliability of the data collected by the server. This score indicates the reliability of word-of-mouth and reviews.

[0981] A "travel route" is a travel route or a route connecting tourist spots that is generated by the server based on information input by the user.

[0982] "Tourist attractions" are tourist attractions and places worth visiting at a travel destination.

[0983] "Sending to terminal" refers to the act of the server transferring the analysis results and generated information to the user's terminal.

[0984] A "user interface" refers to the screen display and input means that allow a user to interact with a system through a terminal.

[0985] This invention relates to a system designed to streamline travel and dining destination decisions. The system collects data from multiple sources based on user input, analyzes and summarizes the data, and provides it to the user.

[0986] The system primarily utilizes the following hardware and software:

[0987] The device used by the user (smartphone, tablet, PC, etc.)

[0988] Server as a central processing unit

[0989] APIs used for data collection (various information source APIs, e.g., TripAdvisor API, Yelp API, Twitter API)

[0990] Generative AI models used for data analysis (e.g., natural language processing models such as BERT and GPT-3)

[0991] When a user inputs their destination and other requirements, the device sends that information to the server. For example, if a user inputs "Barcelona" and "delicious tapas," the device sends this information to the server in the form of an HTTP request.

[0992] Based on the input information, the server collects relevant data from multiple information source APIs, including travel review sites, online review sites, social media, etc. Data obtained through the APIs is temporarily stored on the server.

[0993] The server then analyzes the collected data using a generative AI model, which categorizes the collected data into positive and negative elements and generates a summary for each, including positive and negative sentiment.

[0994] Based on the analysis results, the server calculates a credibility score, which represents the trustworthiness of each review numerically and helps users determine the reliability of the information.

[0995] The server then suggests travel routes and tourist attractions based on the input information, for example, using the Google Maps API to generate a route that visits the main tourist attractions in Barcelona.

[0996] Finally, the server sends the analysis results, reliability scores, and generated route information to the device, which displays this information on the user interface, allowing the user to efficiently determine destinations and dining locations.

[0997] For example, if a user types "Barcelona" and "delicious tapas," the server collects related reviews and generates positive and negative summary statements such as "Lots of fresh ingredients and delicious!" and "Prices are high, but worth it." Based on the reliability score, the server recommends a tapas bar called "La Boqueria" and suggests a sightseeing route that includes "Sagrada Familia" and "Park Güell" using the Google Maps API.

[0998] Examples of prompt sentences include "Barcelona," "delicious tapas," "recommended tourist spots and routes," etc. This invention enables users to efficiently obtain reliable information and make quick and accurate travel planning decisions.

[0999] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1000] Step 1:

[1001] The user inputs the destination and conditions. The user inputs the desired conditions for travel destinations and dining places into the application's input form. For example, the user inputs "Barcelona" and "delicious tapas." After inputting, the user presses the submit button.

[1002] Input: Destination and desired conditions (e.g. Barcelona, ​​delicious tapas)

[1003] Output: Input information ready to send

[1004] Step 2:

[1005] The terminal sends the input information to the server. The terminal sends the destination and conditions entered by the user to the server as an HTTP request (POST request). The data sent is in JSON format.

[1006] Input: User's destination and desired conditions

[1007] Output: Input sent to the server

[1008] Step 3:

[1009] The server collects user reviews and social media data. Based on the destination and conditions received, the server calls APIs from multiple sources to collect data. Specifically, it uses APIs from TripAdvisor, Yelp, Twitter, and other sources to obtain related user reviews, comments, and social media posts.

[1010] Input: User's destination and desired conditions

[1011] Output: Collected data (e.g., word of mouth, reviews, social media posts)

[1012] Step 4:

[1013] The server analyzes the data and generates summaries. The server analyzes the collected data using a generative AI model (e.g., a natural language processing model such as BERT or GPT-3), classifies the data into positive and negative elements, and generates summaries for each.

[1014] Input: Collected data

[1015] Output: Positive and negative summaries

[1016] Step 5:

[1017] The server calculates the credibility score. Based on the collected data, the server evaluates the credibility of each review and calculates a score. The credibility score uses an AI model to filter spam and assign higher scores to reviews that are more trustworthy.

[1018] Input: Parsed data

[1019] Output: Confidence score

[1020] Step 6:

[1021] The server generates multiple routes and spots. The server suggests tourist routes and spots based on the user's input information and reliability scores. It uses the Google Maps API to generate routes that include major tourist spots.

[1022] Input: User input information and confidence score

[1023] Output: Suggested tourist routes and spots

[1024] Step 7:

[1025] The server sends the summarized information to the device. The server sends the analyzed and summarized data, reliability scores, and generated route information in JSON format to the device.

[1026] Inputs: Summarized data, reliability scores, generated route information

[1027] Output: Information sent to the terminal

[1028] Step 8:

[1029] The device displays the information to the user. The device then displays the received information in a user interface, where the user can view information about each tapas bar and its reliability score in a tabular format, and visually check the tourist route on a map.

[1030] Input: Information received from the server

[1031] Output: The result displayed in the user interface

[1032] This series of steps allows users to efficiently make travel and dining decisions based on reliable information.

[1033] (Application example 1)

[1034] 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."

[1035] Conventional systems for deciding on travel destinations and dining locations require users to collect information themselves and make decisions based on a large amount of information, which is time-consuming and labor-intensive. Furthermore, when it comes to providing information in physical stores, word-of-mouth and review information on products and services is not provided in real time, making it difficult for consumers to make quick decisions based on reliable information. To solve this problem, a system is needed that streamlines travel destination and dining location decisions and quickly provides reliable information in physical stores.

[1036] 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.

[1037] In this invention, the server includes: means for receiving user input information regarding travel destinations or dining locations; means for collecting data from multiple multimedia platforms based on the input information; means for analyzing the collected data and generating a positive or negative summary of the data; means for displaying the summarized data to the user; means for collecting related word-of-mouth and review information based on the conditions of products and services in the store; means for calculating a reliability score from the collected word-of-mouth and review information; means for summarizing product and service information based on the reliability score and displaying it to the user; and means for recommending appropriate routes and spots in the store. This allows users to efficiently select destinations based on the compiled, reliable information without having to collect information in a cumbersome manner. Furthermore, even in physical stores, users can obtain reliable information about products and services in real time and engage in optimal consumption behavior.

[1038] A "destination" is a geographic location that a user intends to visit.

[1039] A "dining location" is a location selected by a user to eat a meal.

[1040] "User" means an individual or group that uses the system.

[1041] "Input information" refers to data including requests and desired conditions that a user provides to the system.

[1042] A "multimedia platform" is an internet service that includes multiple information sources.

[1043] "Data" means digital information, including information related to word of mouth, reviews, and ratings.

[1044] "Means of collection" refers to the method for obtaining the specified information from the Internet.

[1045] "Means of analysis" are methods for examining collected data and generating specific meanings or summaries.

[1046] A "positive or negative summary" is a short sentence that summarizes the content of the data in a positive or negative way.

[1047] A "confidence score" is a number or metric used to assess the trustworthiness of collected data.

[1048] "Display means" refers to the method by which the analyzed data and summary are visually presented to the user.

[1049] A "store" is a physical location for offering goods and services.

[1050] "Conditions" are specific requirements or criteria desired by the user.

[1051] "Word of mouth" refers to the opinions and reviews that consumers give about products and services.

[1052] "Review information" refers to detailed evaluations and opinions about specific products or services.

[1053] A "route" is the optimal path for a user to travel to a particular location.

[1054] A "spot" is a specific location to visit within a travel destination or store.

[1055] A "recommendation method" is a method for suggesting specific information or routes to a user.

[1056] As an embodiment of the present invention, the configuration and operation of a real-time customer guide system will be specifically described.

[1057] This system mainly consists of a server, a user's device, and various means for collecting data from multiple multimedia platforms based on user input, analyzing it, and displaying it to the user. The main hardware used is a smartphone, a tablet, and smart glasses. The software used is AWS, Python, TensorFlow, Google Maps API, and React Native.

[1058] System Programming and Processing

[1059] Data collection

[1060] The server receives the criteria information entered by the user into the device. This input information includes specific requests such as "new sneakers" and "good reviews." Based on this information, the server collects related data from multiple multimedia platforms on the Internet (review sites, social media, etc.). This collection is done using AWS's API Gateway.

[1061] Data analysis and summary generation

[1062] The collected data is analyzed on the server by a Python program using natural language processing techniques. An AI model trained with TensorFlow classifies the collected data into positive and negative elements and generates short summaries. For example, "comfortable" is a positive summary, and "expensive" is a negative summary.

[1063] Calculating the reliability score

[1064] The server evaluates the reliability of the analyzed word-of-mouth and review information and calculates a reliability score, which also takes into account the user review history and reputation.

[1065] Route and spot recommendations

[1066] Furthermore, the server uses the Google Maps API to calculate the optimal route and spots within the store based on the user's interests, for example, proposing the optimal route from the fashion section to the food and drink section.

[1067] Displaying Information

[1068] The analyzed information, summary, and route suggestions are sent to the user's device. The user interface is developed using React Native, and the analysis results and recommended routes are visually presented to the user.

[1069] Specific examples

[1070] For example, if a user is interested in "new sneakers," they can input "Tell me the latest reviews about new sneakers" into the system. The server collects relevant data, generates summaries such as "comfortable" and "expensive," calculates a reliability score, and suggests the best route to the fashion section.

[1071] Here is a prompt used as an example:

[1072] "What are the latest reviews of new sneakers?"

[1073] "Tell me the recommended route within the store"

[1074] As described above, this system enables users to make efficient decisions based on compiled, highly reliable information, without the need for tedious information gathering, and supports optimal consumer behavior even in physical stores.

[1075] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1076] Step 1:

[1077] The user inputs condition information into the terminal. The input contents include requests such as "new sneakers" and "good reviews." The information input by the user is sent from the terminal to the server. The input of this step is the user's request, and the output is the input information sent to the server.

[1078] Step 2:

[1079] The server receives input information sent by the user. Based on the received information, the server collects related data from multiple multimedia platforms (review sites, social media, etc.). This collection is performed using AWS's API Gateway. The input of this step is the user's input information, and the output is the collected multimedia data.

[1080] Step 3:

[1081] The server analyzes the collected data. This analysis is performed using Python programs and TensorFlow. First, the collected data is analyzed using natural language processing techniques to generate positive and negative summaries. The input of this step is the collected data, and the output is positive and negative summaries.

[1082] Step 4:

[1083] The server calculates a credibility score for the parsed data. The credibility score takes into account the history and reputation of the user reviews, allowing us to quantify the trustworthiness of each review. The input for this step is the parsed data, and the output is the credibility score.

[1084] Step 5:

[1085] The server uses the Google Maps API to calculate the optimal route and spots within the store based on the user's interests. For example, it proposes the optimal route from the fashion section to the food and drink section. This provides the user with an efficient travel path. The input of this step is the user's interest information, and the output is the calculated route and spots.

[1086] Step 6:

[1087] The server sends the parsed information, confidence scores, and route suggestions to the device. This information is processed to be visually presented to the user in a user interface. The user interface, developed using React Native, displays the information in an easy-to-understand manner. The input of this step is the parsed and calculated information, and the output is the information displayed to the user.

[1088] Step 7:

[1089] The user uses the device to check the provided information and take optimal purchasing actions. For example, a user may start with a prompt such as "Tell me the latest reviews of new sneakers," and then obtain more information to make a purchasing decision. The input for this step is the information displayed on the device, and the output is the user's actions.

[1090] 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.

[1091] This invention relates to a system called "Tabikomi," designed to streamline travel and dining destination decisions. This system collects data from multiple multimedia platforms based on user input, analyzes, summarizes, and displays the data. Furthermore, by combining it with an emotion engine that recognizes and analyzes user emotions, it is possible to provide appropriate recommendation information based on the user's emotions.

[1092] 1. The user enters the destination and conditions

[1093] The user enters their destination and selection criteria into the application's input form, for example, "Barcelona" and "delicious tapas," and then presses the "Search" button.

[1094] 2. The device sends the input information to the server

[1095] The device converts the user's input information into JSON format and sends it to the server. The data sent includes the user ID, destination, purpose of the trip, and meal preferences.

[1096] 3. The server collects reviews and social media data

[1097] The server collects relevant data from multiple multimedia platforms (e.g., review sites, social media) based on the received input information, and uses APIs and scraping technology to obtain word-of-mouth, ratings, and reviews related to the specified destination and conditions.

[1098] 4. The server analyzes the data and generates a summary

[1099] The server analyzes the collected data using machine learning or natural language processing models, categorizing the data into positive and negative comments and generating summaries.

[1100] For example, a positive summary might be "Lots of fresh ingredients and it's delicious!", while a negative summary might be "It's a bit pricey, but it's worth it."

[1101] 5. The server calculates the reliability score

[1102] The server evaluates the reliability of the collected data and calculates a reliability score for each review, which helps users determine the trustworthiness of the reviews.

[1103] 6. The server generates multiple routes and spots

[1104] The server proposes suitable travel routes and tourist spots based on the user's input information. For example, it uses the Google Maps API to generate a tourist route in Barcelona that includes spots such as Sagrada Familia and Park Güell.

[1105] 7. The server sends the summary information to the terminal.

[1106] The server sends the analyzed and summarized data, reliability scores, and route information in JSON format to the device.

[1107] 8. The device displays the information to the user

[1108] The device displays the information in a user interface, where users can browse different tapas bars in tabular format and visualize their tourist route on a map, along with a summary of reviews and a credibility score for each spot.

[1109] 9. Emotion engine recognizes user emotions

[1110] The device's emotion engine recognizes the user's emotions based on the user's input and reactions to the displayed information, and this emotion data is sent to the server for analysis.

[1111] 10. The server analyzes the emotion data and provides recommendations

[1112] The server provides appropriate recommendation information based on the user's emotions recognized by the emotion engine. For example, if the user expresses positive emotions, similar recommended spots will be displayed, and if the user expresses negative emotions, different candidates will be presented.

[1113] 11. Feedback function reflects the results for the next test

[1114] The server accumulates the results of the user's sentiment analysis as feedback and reflects it in the next search results, thereby making better recommendations to the user.

[1115] Specific examples

[1116] Example user input

[1117] A user types "Barcelona" and "delicious tapas" into the app.

[1118] Data collection example

[1119] The server collects reviews about "Barcelona" and "tapas" from TripAdvisor, Yelp, Twitter, etc. and temporarily stores them in a database.

[1120] Data analysis example

[1121] The server analyzes the collected review data using a natural language processing model and classifies it as follows:

[1122] Positive: "Lots of fresh ingredients and delicious!"

[1123] Negative: "It's expensive, but it's worth it."

[1124] Example of reliability score calculation

[1125] The server calculates a reliability score based on the analyzed data, giving a high score if there are many positive comments, and a low score if there are many negative comments, for example.

[1126] Route and Spot Generation Example

[1127] The server uses the Google Maps API to calculate tourist routes within Barcelona and generates routes that include major tourist spots such as Sagrada Familia and Park Güell.

[1128] Information display example

[1129] The device will show the user a summary and credibility score for the tapas bar "La Boqueria" and plot a tourist route on a map.

[1130] Emotion recognition example

[1131] The device's emotion engine recognizes that the user has responded positively to the summary information for "La Boqueria," and sends this information to the server.

[1132] Examples of recommendation information

[1133] If the user expresses positive emotions, the server will recommend more similar tapas bars, widening the selection.

[1134] Example of applying the feedback function

[1135] The server stores the recognized emotion data and reflects it in the next search results, thereby providing information that matches the user's preferences.

[1136] This allows users to efficiently select travel destinations and places to eat by referring to reliable information based on word-of-mouth, ratings, and emotional data.

[1137] The processing flow will be explained below.

[1138] Step 1:

[1139] The user enters a destination and selection criteria into the application's input form, for example, "Barcelona" and "good tapas," and presses the "Search" button.

[1140] Step 2:

[1141] The device converts the user's input information into JSON format and sends it to the server. The data sent includes the user ID, destination, purpose of the trip, and meal preferences.

[1142] Step 3:

[1143] Based on the input information received by the server, the server collects relevant data from multiple multimedia platforms (e.g., review sites, social media), and uses APIs and scraping technology to obtain word-of-mouth, ratings, and reviews related to the specified destination and conditions.

[1144] Step 4:

[1145] The server temporarily stores the collected data in a database, where it is prepared for analysis.

[1146] Step 5:

[1147] The server uses machine learning or natural language processing models to analyze the stored data, categorize the data into positive and negative comments, and generate summaries.

[1148] For example, a positive summary might be "Lots of fresh ingredients and it's delicious!", while a negative summary might be "It's a bit pricey, but it's worth it."

[1149] Step 6:

[1150] The server calculates a credibility score for the summarized data, which is a numerical indicator that evaluates the trustworthiness of each comment or review.

[1151] Step 7:

[1152] The server generates multiple tourist routes and spots based on the destination, and uses Google Maps API to calculate the appropriate travel route and tourist spots, and also collects this information.

[1153] For example, generate a tourist route in Barcelona that includes Sagrada Familia and Park Güell.

[1154] Step 8:

[1155] The server sends the summarized data, reliability scores, and generated route and spot information to the device in JSON format.

[1156] Step 9:

[1157] The device displays the information received from the server in a user interface, showing information about different tapas bars in tabular format, plotting tourist routes on a map, and displaying a summary of reviews and a reliability score for each spot.

[1158] Step 10:

[1159] The emotion engine recognizes the user's input and reaction to the displayed information, for example, by analyzing the user's facial expressions and tone of voice to obtain emotion data.

[1160] Step 11:

[1161] The device transmits the recognized user emotion data to the server, including whether the user is expressing positive or negative emotion in response to the displayed information.

[1162] Step 12:

[1163] The server analyzes the emotion data and provides appropriate recommendations based on the user's emotion. For example, if the user expresses positive emotion, similar recommended spots will be displayed, and if the user expresses negative emotion, other candidates will be presented.

[1164] Step 13:

[1165] The server accumulates the emotion recognition results as feedback and reflects them in the next search results, allowing for better recommendations based on the user's preferences.

[1166] Specific examples

[1167] Example user input

[1168] A user types "Barcelona" and "good tapas" into an application.

[1169] Data collection example

[1170] The server collects reviews about "Barcelona" and "tapas" from TripAdvisor, Yelp, Twitter, etc. and temporarily stores them in a database.

[1171] Data analysis example

[1172] The server analyzes the collected customer reviews using a natural language processing model and categorizes them as "Lots of fresh ingredients and it's delicious!" (positive) or "It's a bit pricey, but it's worth it" (negative).

[1173] Example of reliability score calculation

[1174] The server calculates a reliability score for the analyzed data and gives a higher score to reviews that are more reliable.

[1175] Route and Spot Generation Example

[1176] The server uses the Google Maps API to generate a route that includes tourist attractions such as Sagrada Familia and Park Güell.

[1177] Information display example

[1178] The device displays a summary and reliability score for a tapas bar called "La Boqueria" and plots a tourist route on a map.

[1179] Emotion recognition example

[1180] The emotion engine recognizes that the user responded positively to the summary information for "La Boqueria" and sends it to the server.

[1181] Examples of recommendation information

[1182] If the user expresses positive emotions, the server will recommend similar tapas bars, widening the selection.

[1183] Example of applying the feedback function

[1184] The server accumulates emotion recognition data and reflects it in the next search results, thereby providing information that matches the user's preferences.

[1185] Example 2

[1186] 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."

[1187] Conventional travel and dining destination selection systems have difficulty providing appropriate recommendations based on the information entered by the user. They also have problems with insufficient evaluation of the reliability of collected data and insufficient provision of recommendations based on the user's emotions. Furthermore, they lack a means to efficiently generate multiple routes and tourist spots and present them to the user in a visually easy-to-understand format.

[1188] 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.

[1189] In this invention, the server includes a means for receiving user input information regarding travel destinations or dining locations, a means for collecting data from multiple information collection platforms based on the input information, and a means for analyzing the collected data and generating a positive or negative summary of the data. This allows users to efficiently select travel destinations or dining locations by referring to reliable information based on word-of-mouth reviews, ratings, reliability scores, and emotional data. Furthermore, by including a means for recognizing the user's emotions regarding the displayed information and a means for providing appropriate recommendation information based on the recognized emotional data, information tailored to the user's preferences can be provided. Furthermore, by including a means for generating multiple routes and spots and displaying that information, it is possible to propose travel plans to the user in a visually easy-to-understand format.

[1190] "Input information" refers to information such as travel destinations and places to eat that a user enters into an input form.

[1191] "Information collection platforms" refer to multiple multimedia platforms where data is collected, such as review sites and social networking sites.

[1192] "Data collection" refers to using APIs and scraping technology to obtain data such as word-of-mouth, ratings, and reviews related to specified destinations and conditions.

[1193] The "summary" is a sentence that briefly summarizes the collected data, classifying them into positive and negative comments.

[1194] The "display means" is a means for visually displaying the analyzed summary data on a user interface.

[1195] The "means for recognizing emotions" is a means for analyzing the user's input information and their reactions to the displayed information, and recognizing the user's emotions.

[1196] A "reliability score" is a numerical value obtained by evaluating the reliability of collected data.

[1197] "Recommended information" is information on travel destinations and dining places that are suitable for the user and is provided based on the user's recognized emotional data.

[1198] A "route" is a travel route generated based on destinations specified by the user.

[1199] "Spots" refer to destinations such as tourist attractions and restaurants included in a travel route.

[1200] The present invention is a system that improves the efficiency of travel destination and dining location decisions, collecting and analyzing a large amount of data based on information entered by the user and providing the user with appropriate information. Specific embodiments of the system are described below.

[1201] Hardware and Software Configuration

[1202] server

[1203] The server receives user input, collects data from multiple information collection platforms, analyzes it, assigns reliability scores, and generates summaries. It also analyzes user sentiment data and provides appropriate recommendations. It also generates multiple routes and tourist spots using Google Maps APIs and sends them to the device.

[1204] Specific technologies used include APIs (e.g., Twitter API, Google Maps API), scraping techniques, and natural language processing (NLP) models (e.g., BERT, GPT).

[1205] Terminal

[1206] The device receives input information from the user via a user interface and sends it to the server. It displays the information received from the server, such as summary data, reliability scores, and travel routes, to the user. It also has an emotion engine that analyzes the user's reactions and sends emotional data to the server.

[1207] User

[1208] Users input information about the travel destinations and dining places they want to visit into the terminal, and then make a final decision based on the summary information, reliability score, recommendations, travel route, etc. provided by the system.

[1209] Processing flow (overview)

[1210] 1. The user enters the destination and conditions. For example, "Barcelona" and "delicious tapas" and presses the "Search" button.

[1211] 2. The device sends the input information to the server. Data such as the user ID, destination, purpose of the trip, and meal preferences is converted into JSON format and sent.

[1212] 3. The server collects word-of-mouth, ratings, and reviews from multiple information gathering platforms, such as TripAdvisor, Yelp, and Twitter.

[1213] 4. The server analyzes the collected data using an NLP model (e.g., BERT, GPT), classifies the comments into positive and negative, and generates summaries such as "Lots of fresh ingredients and it's delicious!" or "It's a bit pricey, but it's worth it."

[1214] 5. The server calculates the credibility score. Based on the analyzed data, the server calculates the credibility score for the review. For example, if there are many positive comments, a high score is assigned, and if there are many negative comments, a low score is assigned.

[1215] 6. The server uses the Google Maps API to calculate tourist routes within Barcelona and generates routes that include major tourist attractions such as Sagrada Familia and Park Güell.

[1216] 7. The device displays the transmitted summary data, reliability score, and route information in the user interface. The user can see the summary and reliability score of the tapas bar "La Boqueria" and see a visual representation of the tourist route on the map.

[1217] 8. The emotion engine analyzes the user's reaction, and if the user shows positive emotion towards the displayed information, it recognizes this and sends it to the server.

[1218] 9. The server generates additional recommendations based on the recognized emotion data, for example, recommending more similar tapas bars if the user expresses positive emotions.

[1219] Specific examples

[1220] Prompt Sentence Examples

[1221] A user types "Barcelona" and "delicious tapas" into the app.

[1222] The server collects reviews about "Barcelona" and "tapas" from TripAdvisor, Yelp, Twitter, etc. and temporarily stores them in a database.

[1223] The server analyzes the collected review data using a natural language processing model and classifies it as follows:

[1224] Positive: "Lots of fresh ingredients and delicious!"

[1225] Negative: "It's expensive, but it's worth it."

[1226] The server calculates a reliability score based on the analyzed data and awards a high score.

[1227] The server uses the Google Maps API to calculate tourist routes within Barcelona and generates routes that include places like Sagrada Familia and Park Güell.

[1228] The device displays a summary and reliability score for a tapas bar called "La Boqueria" and plots a tourist route on a map.

[1229] The emotion engine analyzes the user's reaction, determines that the user has had a positive reaction, and sends it to the server.

[1230] If the server finds that the user has expressed positive emotions, they will recommend more similar tapas bars.

[1231] In this way, users can efficiently choose travel destinations and dining places based on reliable information based on reviews, ratings, trustworthiness scores, and sentiment data.

[1232] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1233] Step 1:

[1234] The user inputs their destination and requirements. The user enters information about their travel destination and dining options into the application's input form. For example, they enter "Barcelona" and "delicious tapas" and press the "Search" button. This sends the user's desired conditions to the device as input information.

[1235] Step 2:

[1236] The device sends the input information to the server. The device converts the user's input information into JSON format and sends it to the server. Specifically, the input information (user ID, destination, purpose of the trip, desired meal conditions, etc.) is generated and sent to the server.

[1237] Step 3:

[1238] The server collects data from multiple information gathering platforms. Using APIs and scraping technology, the server gathers data such as word-of-mouth, ratings, and reviews related to specified destinations and conditions. For example, it collects data related to "Barcelona" and "tapas" from TripAdvisor, Yelp, Twitter, etc., and temporarily stores that data in a database.

[1239] Step 4:

[1240] The server analyzes the collected data and generates summaries. The server analyzes the collected data using a natural language processing model (e.g., BERT, GPT). It classifies the data into positive and negative comments and generates summaries for each. For example, as a result of the analysis, a positive comment might be "Lots of fresh ingredients, delicious!", and a negative comment might be "It's a bit pricey, but it's worth it."

[1241] Step 5:

[1242] The server calculates the trustworthiness score for each review based on the analyzed data. Specifically, it uses criteria such as the source of the data and the number of reviews to assign a high score if there are many positive comments, and a low score if there are many negative comments.

[1243] Step 6:

[1244] The server generates multiple routes and spots. Using the Google Maps API, the server generates travel routes and tourist spots suitable for the user's destination. For example, it calculates and generates a tourist route that includes "Sagrada Familia" and "Park Güell."

[1245] Step 7:

[1246] The server sends the summary information to the terminal. The server then sends the generated summary data, reliability scores, tourist routes, etc. in JSON format to the terminal. The data sent includes the analysis results and related information.

[1247] Step 8:

[1248] The device displays the information to the user. The device displays the information sent from the server in a user interface. The user sees a summary and credibility score for the tapas bar "La Boqueria" and a visual representation of the tourist route on a map.

[1249] Step 9:

[1250] The emotion engine recognizes the user's emotions. The device uses the emotion engine to analyze the user's reaction to the displayed information. For example, if the user smiles after viewing the summary information for "La Boqueria," it will recognize this as a positive emotion and send this emotion data to the server.

[1251] Step 10:

[1252] The server analyzes the emotion data and provides recommendation information. The server generates additional recommendation information based on the emotion data recognized by the emotion engine. For example, if the user expresses positive emotion, the server will recommend similar tapas bars, and if the user expresses negative emotion, it will suggest other options.

[1253] Step 11:

[1254] Feedback function reflects next results. The server accumulates the user's sentiment analysis results as feedback and reflects them in the next search results and recommendation information. This allows for better recommendations to be made to the user.

[1255] (Application example 2)

[1256] 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."

[1257] Conventional methods for deciding travel destinations or dining locations have the problem that a large amount of information is scattered across the Internet, making it difficult for users to efficiently collect and analyze the information they need. Furthermore, recommendations do not take into account the user's emotions, making it difficult to increase user satisfaction. The present invention aims to solve these problems by providing a system that provides efficient and accurate information and improves user satisfaction.

[1258] 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 user input information regarding travel destinations or dining places, means for collecting data from multiple content distribution platforms based on the input information, means for analyzing the collected data and generating a positive or negative summary of the data, means for displaying the summarized data to the user, means for recognizing the user's emotions, and means for providing recommended information based on the recognized emotions. This enables the user to efficiently collect and analyze the information they need and obtain appropriate recommended information based on their emotions.

[1259] "User input information regarding travel destinations or dining places" refers to information that a user inputs into the system regarding conditions regarding travel destinations or desired dining places.

[1260] "Content distribution infrastructure" refers to multiple digital media platforms and information sources such as social networking sites.

[1261] "Means of collecting data" refers to the technical means for obtaining relevant information from multiple content distribution platforms on the Internet.

[1262] "Positive or negative summary" refers to the analysis of collected data and classification of the content as a positive or negative summary.

[1263] "Means for displaying summarized data to a user" refers to an interface for visually presenting the analyzed and summarized data to a user.

[1264] "Means for recognizing user emotions" refers to an algorithm or system that determines emotions from user input information and behavior.

[1265] "Means for providing recommended information" refers to technology that suggests suitable travel destinations and dining places based on the recognized user's emotions.

[1266] This invention relates to a system that helps users efficiently decide on travel destinations and dining locations. This system collects, analyzes, and summarizes relevant data based on user input, and provides that information to the user. It also uses an emotion engine to recognize the user's emotions and provide emotion-based recommendation information.

[1267] The system is configured as follows:

[1268] 1. Data Collection

[1269] When a user inputs travel or dining destination information from their device, that information is sent to a server. The server then uses the input information to collect data from multiple content distribution platforms (such as review sites and social media) using techniques such as API calls and web scraping.

[1270] 2. Data Analysis and Summary

[1271] The server analyzes the collected data using natural language processing technology to generate summaries of positive and negative comments. Specifically, text analysis techniques are used to classify the collected word-of-mouth and reviews into positive and negative comments and generate summaries of each element. For example, the data analysis is performed using the TextBlob library and the BERT model.

[1272] 3. Data display

[1273] The summarized information is sent from the server to the device and presented to the user. The user interface is designed to present the information in a visually appealing format, including travel and dining recommendation lists, summaries, and user ratings.

[1274] 4. Emotion recognition

[1275] The device uses an emotion engine to recognize the user's emotions based on the user's input and reactions to the displayed information. This emotion data is sent to the server, where an emotion recognition algorithm is used to analyze how the user reacted to the information on the display.

[1276] 5. Providing Recommendations

[1277] The server then recommends more suitable travel destinations and dining places based on the user's recognized emotions. For example, if the user expresses positive emotions, it will recommend additional similar spots, and if the user expresses negative emotions, it will suggest other spots. This process also takes into account past feedback information.

[1278] Hardware and software used

[1279] Hardware: Servers, smartphones, tablets, and other devices

[1280] Software: Flask, TextBlob, BERT model, various APIs (SNS and review sites)

[1281] Specific examples

[1282] Example user input

[1283] A user types "pizza Tokyo perfect for a date" into a terminal.

[1284] Data collection example

[1285] The server uses the Yelp API to collect reviews about "Pizza Tokyo."

[1286] Data analysis example

[1287] Using TextBlob, we classify the collected word-of-mouth data into positive and negative, and summarize it as follows:

[1288] Positive: "Great pizza and great atmosphere!" "Great service."

[1289] Negatives: "The prices are a little high" "It was crowded"

[1290] Information display example

[1291] The terminal displays the summarized information to the user and a list of recommended restaurants.

[1292] Emotion recognition example

[1293] If a user comments, "Looks delicious, I want to go there!", the emotion engine will recognize this as a positive.

[1294] Prompt Sentence Examples

[1295] Enter: "Pizza Tokyo perfect for a date"

[1296] Collection: "Collecting reviews of "Pizza Tokyo" using the Yelp API..."

[1297] Parsing: "Start parsing data in TextBlob..."

[1298] Show: "Positive review: Great pizza and great atmosphere! Great service."

[1299] Emotion recognition: "We recognized positive emotions from user comments."

[1300] Recommendation: "Recommend new restaurants to the user."

[1301] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1302] Step 1:

[1303] The user enters travel or dining destination requirements

[1304] The user inputs information about their travel destination and desired dining location into the device's application. For example, input information such as "Pizza in Tokyo, perfect for a date" is sent to the device.

[1305] Input: User's requirements for travel destinations and dining locations

[1306] Output: Sending condition information from the terminal to the server

[1307] Step 2:

[1308] The server receives the input information and starts collecting data.

[1309] Based on the input information received from the device, the server collects related data from content distribution platforms (such as review sites and social media. For example, it uses the Yelp API to obtain review data about "Pizza Tokyo."

[1310] Input: Condition information from the terminal

[1311] Output: Acquisition of relevant data from review sites and social media

[1312] Step 3:

[1313] Analyze the data collected by the server

[1314] The server analyzes the acquired review data using natural language processing techniques (e.g., TextBlob or BERT model). The data is classified into positive and negative categories, and summaries are generated.

[1315] Input: Collected review data

[1316] Output: Summary data categorized into positive and negative

[1317] Step 4:

[1318] The server sends the summarized data to the terminal and displays it to the user.

[1319] The server then sends the parsed and summarized data to the device, which then visually displays it to the user, such as a list of summarized reviews and ratings, or restaurant recommendations.

[1320] Input: Summarized data

[1321] Output: Visual information displayed to the user (summary of reviews and restaurant recommendations)

[1322] Step 5:

[1323] The device recognizes the user's emotions

[1324] When a user reacts to the displayed information, the device's emotion engine analyzes the reaction and recognizes the user's emotion. For example, a comment like "It looks delicious, I want to go there!" will be interpreted as a positive emotion.

[1325] Input: User responses (comments, etc.)

[1326] Output: Recognized user emotion data (positive, negative, etc.)

[1327] Step 6:

[1328] The server provides recommendations based on the recognized emotions.

[1329] The server then recommends more suitable travel destinations and dining places based on the recognized emotion data. For example, if the user expresses positive emotion, it will recommend similar spots or new restaurants.

[1330] Input: Recognized user emotion data

[1331] Output: New recommendations (additional restaurants and attractions)

[1332] 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.

[1333] 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.

[1334] 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.

[1335] [Fourth embodiment]

[1336] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1337] 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.

[1338] 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).

[1339] 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.

[1340] 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.

[1341] 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).

[1342] 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.

[1343] 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.

[1344] 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.

[1345] 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.

[1346] 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.

[1347] 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.

[1348] 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."

[1349] This invention relates to a system called "Tabikomi," designed to streamline travel and dining destination decisions. The system collects data from multiple multimedia platforms based on user input, analyzes, summarizes, and displays the data.

[1350] 1. The user enters the destination and conditions

[1351] The user enters their desired destination and dining preferences into the application's input form, such as "Barcelona" and "delicious tapas."

[1352] 2. The device sends the input information to the server

[1353] The terminal transmits the information entered by the user to the server, including the destination, purpose of the trip, meal requirements, etc.

[1354] 3. The server collects reviews and social media data

[1355] Based on the received information, the server automatically collects relevant data from review sites and social media, using an API to retrieve reviews, ratings, and ratings related to the specified destination and conditions.

[1356] 4. The server analyzes the data and generates a summary

[1357] The server analyzes the collected data using AI models (machine learning and natural language processing technology), which categorizes the data into positive and negative elements.

[1358] For example, a positive summary might be "Lots of fresh ingredients and it's delicious!", while a negative summary might be "It's a bit pricey, but it's worth it."

[1359] 5. The server calculates the reliability score

[1360] The server evaluates the reliability of the collected data and calculates a reliability score for each review, which helps users determine the trustworthiness of the reviews.

[1361] 6. The server generates multiple routes and spots

[1362] The server will then suggest suitable travel routes and tourist spots based on the user's input information. For example, it will generate a tourist route in Barcelona that includes spots such as Sagrada Familia and Park Güell.

[1363] 7. The server sends the summary information to the terminal.

[1364] The server sends the analyzed and summarized data, reliability scores, and route information to the terminal.

[1365] 8. The device displays the information to the user

[1366] The device displays the transmitted information in a user interface, allowing the user to view information about different tapas bars in tabular format and visually confirm the tourist route on a map.

[1367] Specific examples

[1368] Example user input

[1369] A user types "Barcelona" and "delicious tapas" into the app.

[1370] Data collection example

[1371] The server collects reviews about "Barcelona" and "tapas" from TripAdvisor, Yelp, Twitter, etc. and temporarily stores them in a database.

[1372] Data analysis example

[1373] The server analyzes the collected review data using a natural language processing model and classifies it as follows:

[1374] Positive: "Lots of fresh ingredients and delicious!"

[1375] Negative: "It's expensive, but it's worth it."

[1376] Example of reliability score calculation

[1377] The server calculates a reliability score based on the analyzed data, giving a high score if there are many positive comments, and a low score if there are many negative comments, for example.

[1378] Route and Spot Generation Example

[1379] The server uses the Google Maps API to calculate tourist routes within Barcelona and generates routes that include major tourist spots such as Sagrada Familia and Park Güell.

[1380] Information display example

[1381] The device will show the user a summary and credibility score for the tapas bar "La Boqueria" and plot a tourist route on a map.

[1382] This allows users to efficiently select a destination based on compiled, highly reliable information, without having to go through the tedious process of collecting information.

[1383] The processing flow will be explained below.

[1384] Step 1:

[1385] The user enters a destination and selection criteria into the application's input form, for example, "Barcelona" and "good tapas," and presses the "Search" button.

[1386] Step 2:

[1387] The device converts the user's input information into JSON format and sends it to the server. The data sent includes the user ID, destination, purpose of the trip, and meal preferences.

[1388] Step 3:

[1389] Based on the input information received by the server, it collects relevant data from multiple multimedia platforms (e.g., review sites, social media) and retrieves word-of-mouth, ratings, and reviews related to the specified destination and conditions through scraping and API calls.

[1390] Step 4:

[1391] The server temporarily stores the collected data in a database, where it is prepared for analysis.

[1392] Step 5:

[1393] The server uses machine learning or natural language processing models to analyze the stored data, categorize the data into positive and negative comments, and generate summaries.

[1394] Step 6:

[1395] The server calculates a credibility score for the summarized data, which is a numerical indicator that evaluates the trustworthiness of each comment or review.

[1396] Step 7:

[1397] The server runs an algorithm to generate multiple tourist routes and attractions based on the destination. It uses Google Maps API to generate appropriate travel routes and tourist attractions and also collects information on these.

[1398] Step 8:

[1399] The server sends the summarized data, reliability scores, and generated route and spot information to the device in JSON format.

[1400] Step 9:

[1401] The device displays the information received from the server in a user interface, showing information about different tapas bars in tabular format, plotting tourist routes on a map, and displaying a summary of reviews and a reliability score for each spot.

[1402] Step 10:

[1403] Users can then use the information displayed to select and plan trips and dining options, while also taking into account positive and negative summaries, reliability scores, and visualized route information.

[1404] Example 1

[1405] 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."

[1406] In recent years, the development of the Internet has made it easier to gather information about travel and dining out. However, it remains difficult for users to select reliable data from the vast amount of information and efficiently decide on destinations and dining locations. In particular, the wide variety of word-of-mouth and reviews about travel destinations and dining locations makes it difficult to determine which information is trustworthy. In addition, the time and effort required to collect, integrate, and summarize information from multiple platforms is a significant burden.

[1407] 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.

[1408] In this invention, the server includes means for receiving user input information, means for transmitting the input information to the server, means for collecting data from multiple information sources based on the input information, means for analyzing the collected data and generating a positive or negative summary of the data, means for proposing the summarized data and travel routes and tourist spots, means for transmitting the analyzed data, reliability scores, and generated route information to a terminal, and means for displaying the transmitted information on a user interface, thereby enabling a user to efficiently decide on a destination or a place to eat based on reliable information.

[1409] "User" means an end user who uses the system to search, input, and review travel and dining destination information.

[1410] A "server" is a central processing unit that receives information from users, collects and analyzes data, and transmits the results to terminals.

[1411] "Input information" refers to information such as travel destinations, places to eat, and desired conditions that a user inputs into the system.

[1412] A "terminal" is a device that is directly operated by a user, sends input information to a server, and displays the results from the server.

[1413] "Sources" are the multiple online platforms and databases that the server accesses to collect data.

[1414] "Data" refers to information collected from sources such as word of mouth, reviews, ratings, and social media posts.

[1415] "Collecting" refers to the act of the server obtaining and storing the necessary data from the source.

[1416] "Analyzing" refers to the act of processing the data collected by the server and extracting valuable information.

[1417] A "positive summary" is a summary of positive evaluations and comments extracted from the collected data.

[1418] A "negative summary" is a summary of negative evaluations and comments extracted from the collected data.

[1419] The "trust score" is a numerical value that evaluates the reliability of the data collected by the server. This score indicates the reliability of word-of-mouth and reviews.

[1420] A "travel route" is a travel route or a route connecting tourist spots that is generated by the server based on information input by the user.

[1421] "Tourist attractions" are tourist attractions and places worth visiting at a travel destination.

[1422] "Sending to terminal" refers to the act of the server transferring the analysis results and generated information to the user's terminal.

[1423] A "user interface" refers to the screen display and input means that allow a user to interact with a system through a terminal.

[1424] This invention relates to a system designed to streamline travel and dining destination decisions. The system collects data from multiple sources based on user input, analyzes and summarizes the data, and provides it to the user.

[1425] The system primarily utilizes the following hardware and software:

[1426] The device used by the user (smartphone, tablet, PC, etc.)

[1427] Server as a central processing unit

[1428] APIs used for data collection (various information source APIs, e.g., TripAdvisor API, Yelp API, Twitter API)

[1429] Generative AI models used for data analysis (e.g., natural language processing models such as BERT and GPT-3)

[1430] When a user inputs their destination and other requirements, the device sends that information to the server. For example, if a user inputs "Barcelona" and "delicious tapas," the device sends this information to the server in the form of an HTTP request.

[1431] Based on the input information, the server collects relevant data from multiple information source APIs, including travel review sites, online review sites, social media, etc. Data obtained through the APIs is temporarily stored on the server.

[1432] The server then analyzes the collected data using a generative AI model, which categorizes the collected data into positive and negative elements and generates a summary for each, including positive and negative sentiment.

[1433] Based on the analysis results, the server calculates a credibility score, which represents the trustworthiness of each review numerically and helps users determine the reliability of the information.

[1434] The server then suggests travel routes and tourist attractions based on the input information, for example, using the Google Maps API to generate a route that visits the main tourist attractions in Barcelona.

[1435] Finally, the server sends the analysis results, reliability scores, and generated route information to the device, which displays this information on the user interface, allowing the user to efficiently determine destinations and dining locations.

[1436] For example, if a user types "Barcelona" and "delicious tapas," the server collects related reviews and generates positive and negative summary statements such as "Lots of fresh ingredients and delicious!" and "Prices are high, but worth it." Based on the reliability score, the server recommends a tapas bar called "La Boqueria" and suggests a sightseeing route that includes "Sagrada Familia" and "Park Güell" using the Google Maps API.

[1437] Examples of prompt sentences include "Barcelona," "delicious tapas," "recommended tourist spots and routes," etc. This invention enables users to efficiently obtain reliable information and make quick and accurate travel planning decisions.

[1438] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1439] Step 1:

[1440] The user inputs the destination and conditions. The user inputs the desired conditions for travel destinations and dining places into the application's input form. For example, the user inputs "Barcelona" and "delicious tapas." After inputting, the user presses the submit button.

[1441] Input: Destination and desired conditions (e.g. Barcelona, ​​delicious tapas)

[1442] Output: Input information ready to send

[1443] Step 2:

[1444] The terminal sends the input information to the server. The terminal sends the destination and conditions entered by the user to the server as an HTTP request (POST request). The data sent is in JSON format.

[1445] Input: User's destination and desired conditions

[1446] Output: Input sent to the server

[1447] Step 3:

[1448] The server collects user reviews and social media data. Based on the destination and conditions received, the server calls APIs from multiple sources to collect data. Specifically, it uses APIs from TripAdvisor, Yelp, Twitter, and other sources to obtain related user reviews, comments, and social media posts.

[1449] Input: User's destination and desired conditions

[1450] Output: Collected data (e.g., word of mouth, reviews, social media posts)

[1451] Step 4:

[1452] The server analyzes the data and generates summaries. The server analyzes the collected data using a generative AI model (e.g., a natural language processing model such as BERT or GPT-3), classifies the data into positive and negative elements, and generates summaries for each.

[1453] Input: Collected data

[1454] Output: Positive and negative summaries

[1455] Step 5:

[1456] The server calculates the credibility score. Based on the collected data, the server evaluates the credibility of each review and calculates a score. The credibility score uses an AI model to filter spam and assign higher scores to reviews that are more trustworthy.

[1457] Input: Parsed data

[1458] Output: Confidence score

[1459] Step 6:

[1460] The server generates multiple routes and spots. The server suggests tourist routes and spots based on the user's input information and reliability scores. It uses the Google Maps API to generate routes that include major tourist spots.

[1461] Input: User input information and confidence score

[1462] Output: Suggested tourist routes and spots

[1463] Step 7:

[1464] The server sends the summarized information to the device. The server sends the analyzed and summarized data, reliability scores, and generated route information in JSON format to the device.

[1465] Inputs: Summarized data, reliability scores, generated route information

[1466] Output: Information sent to the terminal

[1467] Step 8:

[1468] The device displays the information to the user. The device then displays the received information in a user interface, where the user can view information about each tapas bar and its reliability score in a tabular format, and visually check the tourist route on a map.

[1469] Input: Information received from the server

[1470] Output: The result displayed in the user interface

[1471] This series of steps allows users to efficiently make travel and dining decisions based on reliable information.

[1472] (Application example 1)

[1473] 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."

[1474] Conventional systems for deciding on travel destinations and dining locations require users to collect information themselves and make decisions based on a large amount of information, which is time-consuming and labor-intensive. Furthermore, when it comes to providing information in physical stores, word-of-mouth and review information on products and services is not provided in real time, making it difficult for consumers to make quick decisions based on reliable information. To solve this problem, a system is needed that streamlines travel destination and dining location decisions and quickly provides reliable information in physical stores.

[1475] 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.

[1476] In this invention, the server includes: means for receiving user input information regarding travel destinations or dining locations; means for collecting data from multiple multimedia platforms based on the input information; means for analyzing the collected data and generating a positive or negative summary of the data; means for displaying the summarized data to the user; means for collecting related word-of-mouth and review information based on the conditions of products and services in the store; means for calculating a reliability score from the collected word-of-mouth and review information; means for summarizing product and service information based on the reliability score and displaying it to the user; and means for recommending appropriate routes and spots in the store. This allows users to efficiently select destinations based on the compiled, reliable information without having to collect information in a cumbersome manner. Furthermore, even in physical stores, users can obtain reliable information about products and services in real time and engage in optimal consumption behavior.

[1477] A "destination" is a geographic location that a user intends to visit.

[1478] A "dining location" is a location selected by a user to eat a meal.

[1479] "User" means an individual or group that uses the system.

[1480] "Input information" refers to data including requests and desired conditions that a user provides to the system.

[1481] A "multimedia platform" is an internet service that includes multiple information sources.

[1482] "Data" means digital information, including information related to word of mouth, reviews, and ratings.

[1483] "Means of collection" refers to the method for obtaining the specified information from the Internet.

[1484] "Means of analysis" are methods for examining collected data and generating specific meanings or summaries.

[1485] A "positive or negative summary" is a short sentence that summarizes the content of the data in a positive or negative way.

[1486] A "confidence score" is a number or metric used to assess the trustworthiness of collected data.

[1487] "Display means" refers to the method by which the analyzed data and summary are visually presented to the user.

[1488] A "store" is a physical location for offering goods and services.

[1489] "Conditions" are specific requirements or criteria desired by the user.

[1490] "Word of mouth" refers to the opinions and reviews that consumers give about products and services.

[1491] "Review information" refers to detailed evaluations and opinions about specific products or services.

[1492] A "route" is the optimal path for a user to travel to a particular location.

[1493] A "spot" is a specific location to visit within a travel destination or store.

[1494] A "recommendation method" is a method for suggesting specific information or routes to a user.

[1495] As an embodiment of the present invention, the configuration and operation of a real-time customer guide system will be specifically described.

[1496] This system mainly consists of a server, a user's device, and various means for collecting data from multiple multimedia platforms based on user input, analyzing it, and displaying it to the user. The main hardware used is a smartphone, a tablet, and smart glasses. The software used is AWS, Python, TensorFlow, Google Maps API, and React Native.

[1497] System Programming and Processing

[1498] Data collection

[1499] The server receives the criteria information entered by the user into the device. This input information includes specific requests such as "new sneakers" and "good reviews." Based on this information, the server collects related data from multiple multimedia platforms on the Internet (review sites, social media, etc.). This collection is done using AWS's API Gateway.

[1500] Data analysis and summary generation

[1501] The collected data is analyzed on the server by a Python program using natural language processing techniques. An AI model trained with TensorFlow classifies the collected data into positive and negative elements and generates short summaries. For example, "comfortable" is a positive summary, and "expensive" is a negative summary.

[1502] Calculating the reliability score

[1503] The server evaluates the reliability of the analyzed word-of-mouth and review information and calculates a reliability score, which also takes into account the user review history and reputation.

[1504] Route and spot recommendations

[1505] Furthermore, the server uses the Google Maps API to calculate the optimal route and spots within the store based on the user's interests, for example, proposing the optimal route from the fashion section to the food and drink section.

[1506] Displaying Information

[1507] The analyzed information, summary, and route suggestions are sent to the user's device. The user interface is developed using React Native, and the analysis results and recommended routes are visually presented to the user.

[1508] Specific examples

[1509] For example, if a user is interested in "new sneakers," they can input "Tell me the latest reviews about new sneakers" into the system. The server collects relevant data, generates summaries such as "comfortable" and "expensive," calculates a reliability score, and suggests the best route to the fashion section.

[1510] Here is a prompt used as an example:

[1511] "What are the latest reviews of new sneakers?"

[1512] "Tell me the recommended route within the store"

[1513] As described above, this system enables users to make efficient decisions based on compiled, highly reliable information, without the need for tedious information gathering, and supports optimal consumer behavior even in physical stores.

[1514] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1515] Step 1:

[1516] The user inputs condition information into the terminal. The input contents include requests such as "new sneakers" and "good reviews." The information input by the user is sent from the terminal to the server. The input of this step is the user's request, and the output is the input information sent to the server.

[1517] Step 2:

[1518] The server receives input information sent by the user. Based on the received information, the server collects related data from multiple multimedia platforms (review sites, social media, etc.). This collection is performed using AWS's API Gateway. The input of this step is the user's input information, and the output is the collected multimedia data.

[1519] Step 3:

[1520] The server analyzes the collected data. This analysis is performed using Python programs and TensorFlow. First, the collected data is analyzed using natural language processing techniques to generate positive and negative summaries. The input of this step is the collected data, and the output is positive and negative summaries.

[1521] Step 4:

[1522] The server calculates a credibility score for the parsed data. The credibility score takes into account the history and reputation of the user reviews, allowing us to quantify the trustworthiness of each review. The input for this step is the parsed data, and the output is the credibility score.

[1523] Step 5:

[1524] The server uses the Google Maps API to calculate the optimal route and spots within the store based on the user's interests. For example, it proposes the optimal route from the fashion section to the food and drink section. This provides the user with an efficient travel path. The input of this step is the user's interest information, and the output is the calculated route and spots.

[1525] Step 6:

[1526] The server sends the parsed information, confidence scores, and route suggestions to the device. This information is processed to be visually presented to the user in a user interface. The user interface, developed using React Native, displays the information in an easy-to-understand manner. The input of this step is the parsed and calculated information, and the output is the information displayed to the user.

[1527] Step 7:

[1528] The user uses the device to check the provided information and take optimal purchasing actions. For example, a user may start with a prompt such as "Tell me the latest reviews of new sneakers," and then obtain more information to make a purchasing decision. The input for this step is the information displayed on the device, and the output is the user's actions.

[1529] 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.

[1530] This invention relates to a system called "Tabikomi," designed to streamline travel and dining destination decisions. This system collects data from multiple multimedia platforms based on user input, analyzes, summarizes, and displays the data. Furthermore, by combining it with an emotion engine that recognizes and analyzes user emotions, it is possible to provide appropriate recommendation information based on the user's emotions.

[1531] 1. The user enters the destination and conditions

[1532] The user enters their destination and selection criteria into the application's input form, for example, "Barcelona" and "delicious tapas," and then presses the "Search" button.

[1533] 2. The device sends the input information to the server

[1534] The device converts the user's input information into JSON format and sends it to the server. The data sent includes the user ID, destination, purpose of the trip, and meal preferences.

[1535] 3. The server collects reviews and social media data

[1536] The server collects relevant data from multiple multimedia platforms (e.g., review sites, social media) based on the received input information, and uses APIs and scraping technology to obtain word-of-mouth, ratings, and reviews related to the specified destination and conditions.

[1537] 4. The server analyzes the data and generates a summary

[1538] The server analyzes the collected data using machine learning or natural language processing models, categorizing the data into positive and negative comments and generating summaries.

[1539] For example, a positive summary might be "Lots of fresh ingredients and it's delicious!", while a negative summary might be "It's a bit pricey, but it's worth it."

[1540] 5. The server calculates the reliability score

[1541] The server evaluates the reliability of the collected data and calculates a reliability score for each review, which helps users determine the trustworthiness of the reviews.

[1542] 6. The server generates multiple routes and spots

[1543] The server proposes suitable travel routes and tourist spots based on the user's input information. For example, it uses the Google Maps API to generate a tourist route in Barcelona that includes spots such as Sagrada Familia and Park Güell.

[1544] 7. The server sends the summary information to the terminal.

[1545] The server sends the analyzed and summarized data, reliability scores, and route information in JSON format to the device.

[1546] 8. The device displays the information to the user

[1547] The device displays the information in a user interface, where users can browse different tapas bars in tabular format and visualize their tourist route on a map, along with a summary of reviews and a credibility score for each spot.

[1548] 9. Emotion engine recognizes user emotions

[1549] The device's emotion engine recognizes the user's emotions based on the user's input and reactions to the displayed information, and this emotion data is sent to the server for analysis.

[1550] 10. The server analyzes the emotion data and provides recommendations

[1551] The server provides appropriate recommendation information based on the user's emotions recognized by the emotion engine. For example, if the user expresses positive emotions, similar recommended spots will be displayed, and if the user expresses negative emotions, different candidates will be presented.

[1552] 11. Feedback function reflects the results for the next test

[1553] The server accumulates the results of the user's sentiment analysis as feedback and reflects it in the next search results, thereby making better recommendations to the user.

[1554] Specific examples

[1555] Example user input

[1556] A user types "Barcelona" and "delicious tapas" into the app.

[1557] Data collection example

[1558] The server collects reviews about "Barcelona" and "tapas" from TripAdvisor, Yelp, Twitter, etc. and temporarily stores them in a database.

[1559] Data analysis example

[1560] The server analyzes the collected review data using a natural language processing model and classifies it as follows:

[1561] Positive: "Lots of fresh ingredients and delicious!"

[1562] Negative: "It's expensive, but it's worth it."

[1563] Example of reliability score calculation

[1564] The server calculates a reliability score based on the analyzed data, giving a high score if there are many positive comments, and a low score if there are many negative comments, for example.

[1565] Route and Spot Generation Example

[1566] The server uses the Google Maps API to calculate tourist routes within Barcelona and generates routes that include major tourist spots such as Sagrada Familia and Park Güell.

[1567] Information display example

[1568] The device will show the user a summary and credibility score for the tapas bar "La Boqueria" and plot a tourist route on a map.

[1569] Emotion recognition example

[1570] The device's emotion engine recognizes that the user has responded positively to the summary information for "La Boqueria," and sends this information to the server.

[1571] Examples of recommendation information

[1572] If the user expresses positive emotions, the server will recommend more similar tapas bars, widening the selection.

[1573] Example of applying the feedback function

[1574] The server stores the recognized emotion data and reflects it in the next search results, thereby providing information that matches the user's preferences.

[1575] This allows users to efficiently select travel destinations and places to eat by referring to reliable information based on word-of-mouth, ratings, and emotional data.

[1576] The processing flow will be explained below.

[1577] Step 1:

[1578] The user enters a destination and selection criteria into the application's input form, for example, "Barcelona" and "good tapas," and presses the "Search" button.

[1579] Step 2:

[1580] The device converts the user's input information into JSON format and sends it to the server. The data sent includes the user ID, destination, purpose of the trip, and meal preferences.

[1581] Step 3:

[1582] Based on the input information received by the server, the server collects relevant data from multiple multimedia platforms (e.g., review sites, social media), and uses APIs and scraping technology to obtain word-of-mouth, ratings, and reviews related to the specified destination and conditions.

[1583] Step 4:

[1584] The server temporarily stores the collected data in a database, where it is prepared for analysis.

[1585] Step 5:

[1586] The server uses machine learning or natural language processing models to analyze the stored data, categorize the data into positive and negative comments, and generate summaries.

[1587] For example, a positive summary might be "Lots of fresh ingredients and it's delicious!", while a negative summary might be "It's a bit pricey, but it's worth it."

[1588] Step 6:

[1589] The server calculates a credibility score for the summarized data, which is a numerical indicator that evaluates the trustworthiness of each comment or review.

[1590] Step 7:

[1591] The server generates multiple tourist routes and spots based on the destination, and uses Google Maps API to calculate the appropriate travel route and tourist spots, and also collects this information.

[1592] For example, generate a tourist route in Barcelona that includes Sagrada Familia and Park Güell.

[1593] Step 8:

[1594] The server sends the summarized data, reliability scores, and generated route and spot information to the device in JSON format.

[1595] Step 9:

[1596] The device displays the information received from the server in a user interface, showing information about different tapas bars in tabular format, plotting tourist routes on a map, and displaying a summary of reviews and a reliability score for each spot.

[1597] Step 10:

[1598] The emotion engine recognizes the user's input and reaction to the displayed information, for example, by analyzing the user's facial expressions and tone of voice to obtain emotion data.

[1599] Step 11:

[1600] The device transmits the recognized user emotion data to the server, including whether the user is expressing positive or negative emotion in response to the displayed information.

[1601] Step 12:

[1602] The server analyzes the emotion data and provides appropriate recommendations based on the user's emotion. For example, if the user expresses positive emotion, similar recommended spots will be displayed, and if the user expresses negative emotion, other candidates will be presented.

[1603] Step 13:

[1604] The server accumulates the emotion recognition results as feedback and reflects them in the next search results, allowing for better recommendations based on the user's preferences.

[1605] Specific examples

[1606] Example user input

[1607] A user types "Barcelona" and "good tapas" into an application.

[1608] Data collection example

[1609] The server collects reviews about "Barcelona" and "tapas" from TripAdvisor, Yelp, Twitter, etc. and temporarily stores them in a database.

[1610] Data analysis example

[1611] The server analyzes the collected customer reviews using a natural language processing model and categorizes them as "Lots of fresh ingredients and it's delicious!" (positive) or "It's a bit pricey, but it's worth it" (negative).

[1612] Example of reliability score calculation

[1613] The server calculates a reliability score for the analyzed data and gives a higher score to reviews that are more reliable.

[1614] Route and Spot Generation Example

[1615] The server uses the Google Maps API to generate a route that includes tourist attractions such as Sagrada Familia and Park Güell.

[1616] Information display example

[1617] The device displays a summary and reliability score for a tapas bar called "La Boqueria" and plots a tourist route on a map.

[1618] Emotion recognition example

[1619] The emotion engine recognizes that the user responded positively to the summary information for "La Boqueria" and sends it to the server.

[1620] Examples of recommendation information

[1621] If the user expresses positive emotions, the server will recommend similar tapas bars, widening the selection.

[1622] Example of applying the feedback function

[1623] The server accumulates emotion recognition data and reflects it in the next search results, thereby providing information that matches the user's preferences.

[1624] Example 2

[1625] 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."

[1626] Conventional travel and dining destination selection systems have difficulty providing appropriate recommendations based on the information entered by the user. They also have problems with insufficient evaluation of the reliability of collected data and insufficient provision of recommendations based on the user's emotions. Furthermore, they lack a means to efficiently generate multiple routes and tourist spots and present them to the user in a visually easy-to-understand format.

[1627] 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.

[1628] In this invention, the server includes a means for receiving user input information regarding travel destinations or dining locations, a means for collecting data from multiple information collection platforms based on the input information, and a means for analyzing the collected data and generating a positive or negative summary of the data. This allows users to efficiently select travel destinations or dining locations by referring to reliable information based on word-of-mouth reviews, ratings, reliability scores, and emotional data. Furthermore, by including a means for recognizing the user's emotions regarding the displayed information and a means for providing appropriate recommendation information based on the recognized emotional data, information tailored to the user's preferences can be provided. Furthermore, by including a means for generating multiple routes and spots and displaying that information, it is possible to propose travel plans to the user in a visually easy-to-understand format.

[1629] "Input information" refers to information such as travel destinations and places to eat that a user enters into an input form.

[1630] "Information collection platforms" refer to multiple multimedia platforms where data is collected, such as review sites and social networking sites.

[1631] "Data collection" refers to using APIs and scraping technology to obtain data such as word-of-mouth, ratings, and reviews related to specified destinations and conditions.

[1632] The "summary" is a sentence that briefly summarizes the collected data, classifying them into positive and negative comments.

[1633] The "display means" is a means for visually displaying the analyzed summary data on a user interface.

[1634] The "means for recognizing emotions" is a means for analyzing the user's input information and their reactions to the displayed information, and recognizing the user's emotions.

[1635] A "reliability score" is a numerical value obtained by evaluating the reliability of collected data.

[1636] "Recommended information" is information on travel destinations and dining places that are suitable for the user and is provided based on the user's recognized emotional data.

[1637] A "route" is a travel route generated based on destinations specified by the user.

[1638] "Spots" refer to destinations such as tourist attractions and restaurants included in a travel route.

[1639] The present invention is a system that improves the efficiency of travel destination and dining location decisions, collecting and analyzing a large amount of data based on information entered by the user and providing the user with appropriate information. Specific embodiments of the system are described below.

[1640] Hardware and Software Configuration

[1641] server

[1642] The server receives user input, collects data from multiple information collection platforms, analyzes it, assigns reliability scores, and generates summaries. It also analyzes user sentiment data and provides appropriate recommendations. It also generates multiple routes and tourist spots using Google Maps APIs and sends them to the device.

[1643] Specific technologies used include APIs (e.g., Twitter API, Google Maps API), scraping techniques, and natural language processing (NLP) models (e.g., BERT, GPT).

[1644] Terminal

[1645] The device receives input information from the user via a user interface and sends it to the server. It displays the information received from the server, such as summary data, reliability scores, and travel routes, to the user. It also has an emotion engine that analyzes the user's reactions and sends emotional data to the server.

[1646] User

[1647] Users input information about the travel destinations and dining places they want to visit into the terminal, and then make a final decision based on the summary information, reliability score, recommendations, travel route, etc. provided by the system.

[1648] Processing flow (overview)

[1649] 1. The user enters the destination and conditions. For example, "Barcelona" and "delicious tapas" and presses the "Search" button.

[1650] 2. The device sends the input information to the server. Data such as the user ID, destination, purpose of the trip, and meal preferences is converted into JSON format and sent.

[1651] 3. The server collects word-of-mouth, ratings, and reviews from multiple information gathering platforms, such as TripAdvisor, Yelp, and Twitter.

[1652] 4. The server analyzes the collected data using an NLP model (e.g., BERT, GPT), classifies the comments into positive and negative, and generates summaries such as "Lots of fresh ingredients and it's delicious!" or "It's a bit pricey, but it's worth it."

[1653] 5. The server calculates the credibility score. Based on the analyzed data, the server calculates the credibility score for the review. For example, if there are many positive comments, a high score is assigned, and if there are many negative comments, a low score is assigned.

[1654] 6. The server uses the Google Maps API to calculate tourist routes within Barcelona and generates routes that include major tourist attractions such as Sagrada Familia and Park Güell.

[1655] 7. The device displays the transmitted summary data, reliability score, and route information in the user interface. The user can see the summary and reliability score of the tapas bar "La Boqueria" and see a visual representation of the tourist route on the map.

[1656] 8. The emotion engine analyzes the user's reaction, and if the user shows positive emotion towards the displayed information, it recognizes this and sends it to the server.

[1657] 9. The server generates additional recommendations based on the recognized emotion data, for example, recommending more similar tapas bars if the user expresses positive emotions.

[1658] Specific examples

[1659] Prompt Sentence Examples

[1660] A user types "Barcelona" and "delicious tapas" into the app.

[1661] The server collects reviews about "Barcelona" and "tapas" from TripAdvisor, Yelp, Twitter, etc. and temporarily stores them in a database.

[1662] The server analyzes the collected review data using a natural language processing model and classifies it as follows:

[1663] Positive: "Lots of fresh ingredients and delicious!"

[1664] Negative: "It's expensive, but it's worth it."

[1665] The server calculates a reliability score based on the analyzed data and awards a high score.

[1666] The server uses the Google Maps API to calculate tourist routes within Barcelona and generates routes that include places like Sagrada Familia and Park Güell.

[1667] The device displays a summary and reliability score for a tapas bar called "La Boqueria" and plots a tourist route on a map.

[1668] The emotion engine analyzes the user's reaction, determines that the user has had a positive reaction, and sends it to the server.

[1669] If the server finds that the user has expressed positive emotions, they will recommend more similar tapas bars.

[1670] In this way, users can efficiently choose travel destinations and dining places based on reliable information based on reviews, ratings, trustworthiness scores, and sentiment data.

[1671] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1672] Step 1:

[1673] The user inputs their destination and requirements. The user enters information about their travel destination and dining options into the application's input form. For example, they enter "Barcelona" and "delicious tapas" and press the "Search" button. This sends the user's desired conditions to the device as input information.

[1674] Step 2:

[1675] The device sends the input information to the server. The device converts the user's input information into JSON format and sends it to the server. Specifically, the input information (user ID, destination, purpose of the trip, desired meal conditions, etc.) is generated and sent to the server.

[1676] Step 3:

[1677] The server collects data from multiple information gathering platforms. Using APIs and scraping technology, the server gathers data such as word-of-mouth, ratings, and reviews related to specified destinations and conditions. For example, it collects data related to "Barcelona" and "tapas" from TripAdvisor, Yelp, Twitter, etc., and temporarily stores that data in a database.

[1678] Step 4:

[1679] The server analyzes the collected data and generates summaries. The server analyzes the collected data using a natural language processing model (e.g., BERT, GPT). It classifies the data into positive and negative comments and generates summaries for each. For example, as a result of the analysis, a positive comment might be "Lots of fresh ingredients, delicious!", and a negative comment might be "It's a bit pricey, but it's worth it."

[1680] Step 5:

[1681] The server calculates the trustworthiness score for each review based on the analyzed data. Specifically, it uses criteria such as the source of the data and the number of reviews to assign a high score if there are many positive comments, and a low score if there are many negative comments.

[1682] Step 6:

[1683] The server generates multiple routes and spots. Using the Google Maps API, the server generates travel routes and tourist spots suitable for the user's destination. For example, it calculates and generates a tourist route that includes "Sagrada Familia" and "Park Güell."

[1684] Step 7:

[1685] The server sends the summary information to the terminal. The server then sends the generated summary data, reliability scores, tourist routes, etc. in JSON format to the terminal. The data sent includes the analysis results and related information.

[1686] Step 8:

[1687] The device displays the information to the user. The device displays the information sent from the server in a user interface. The user sees a summary and credibility score for the tapas bar "La Boqueria" and a visual representation of the tourist route on a map.

[1688] Step 9:

[1689] The emotion engine recognizes the user's emotions. The device uses the emotion engine to analyze the user's reaction to the displayed information. For example, if the user smiles after viewing the summary information for "La Boqueria," it will recognize this as a positive emotion and send this emotion data to the server.

[1690] Step 10:

[1691] The server analyzes the emotion data and provides recommendation information. The server generates additional recommendation information based on the emotion data recognized by the emotion engine. For example, if the user expresses positive emotion, the server will recommend similar tapas bars, and if the user expresses negative emotion, it will suggest other options.

[1692] Step 11:

[1693] Feedback function reflects next results. The server accumulates the user's sentiment analysis results as feedback and reflects them in the next search results and recommendation information. This allows for better recommendations to be made to the user.

[1694] (Application example 2)

[1695] 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."

[1696] Conventional methods for deciding travel destinations or dining locations have the problem that a large amount of information is scattered across the Internet, making it difficult for users to efficiently collect and analyze the information they need. Furthermore, recommendations do not take into account the user's emotions, making it difficult to increase user satisfaction. The present invention aims to solve these problems by providing a system that provides efficient and accurate information and improves user satisfaction.

[1697] 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 user input information regarding travel destinations or dining places, means for collecting data from multiple content distribution platforms based on the input information, means for analyzing the collected data and generating a positive or negative summary of the data, means for displaying the summarized data to the user, means for recognizing the user's emotions, and means for providing recommended information based on the recognized emotions. This enables the user to efficiently collect and analyze the information they need and obtain appropriate recommended information based on their emotions.

[1698] "User input information regarding travel destinations or dining places" refers to information that a user inputs into the system regarding conditions regarding travel destinations or desired dining places.

[1699] "Content distribution infrastructure" refers to multiple digital media platforms and information sources such as social networking sites.

[1700] "Means of collecting data" refers to the technical means for obtaining relevant information from multiple content distribution platforms on the Internet.

[1701] "Positive or negative summary" refers to the analysis of collected data and classification of the content as a positive or negative summary.

[1702] "Means for displaying summarized data to a user" refers to an interface for visually presenting the analyzed and summarized data to a user.

[1703] "Means for recognizing user emotions" refers to an algorithm or system that determines emotions from user input information and behavior.

[1704] "Means for providing recommended information" refers to technology that suggests suitable travel destinations and dining places based on the recognized user's emotions.

[1705] This invention relates to a system that helps users efficiently decide on travel destinations and dining locations. This system collects, analyzes, and summarizes relevant data based on user input, and provides that information to the user. It also uses an emotion engine to recognize the user's emotions and provide emotion-based recommendation information.

[1706] The system is configured as follows:

[1707] 1. Data Collection

[1708] When a user inputs travel or dining destination information from their device, that information is sent to a server. The server then uses the input information to collect data from multiple content distribution platforms (such as review sites and social media) using techniques such as API calls and web scraping.

[1709] 2. Data Analysis and Summary

[1710] The server analyzes the collected data using natural language processing technology to generate summaries of positive and negative comments. Specifically, text analysis techniques are used to classify the collected word-of-mouth and reviews into positive and negative comments and generate summaries of each element. For example, the data analysis is performed using the TextBlob library and the BERT model.

[1711] 3. Data display

[1712] The summarized information is sent from the server to the device and presented to the user. The user interface is designed to present the information in a visually appealing format, including travel and dining recommendation lists, summaries, and user ratings.

[1713] 4. Emotion recognition

[1714] The device uses an emotion engine to recognize the user's emotions based on the user's input and reactions to the displayed information. This emotion data is sent to the server, where an emotion recognition algorithm is used to analyze how the user reacted to the information on the display.

[1715] 5. Providing Recommendations

[1716] The server then recommends more suitable travel destinations and dining places based on the user's recognized emotions. For example, if the user expresses positive emotions, it will recommend additional similar spots, and if the user expresses negative emotions, it will suggest other spots. This process also takes into account past feedback information.

[1717] Hardware and software used

[1718] Hardware: Servers, smartphones, tablets, and other devices

[1719] Software: Flask, TextBlob, BERT model, various APIs (SNS and review sites)

[1720] Specific examples

[1721] Example user input

[1722] A user types "pizza Tokyo perfect for a date" into a terminal.

[1723] Data collection example

[1724] The server uses the Yelp API to collect reviews about "Pizza Tokyo."

[1725] Data analysis example

[1726] Using TextBlob, we classify the collected word-of-mouth data into positive and negative, and summarize it as follows:

[1727] Positive: "Great pizza and great atmosphere!" "Great service."

[1728] Negatives: "The prices are a little high" "It was crowded"

[1729] Information display example

[1730] The terminal displays the summarized information to the user and a list of recommended restaurants.

[1731] Emotion recognition example

[1732] If a user comments, "Looks delicious, I want to go there!", the emotion engine will recognize this as a positive.

[1733] Prompt Sentence Examples

[1734] Enter: "Pizza Tokyo perfect for a date"

[1735] Collection: "Collecting reviews of "Pizza Tokyo" using the Yelp API..."

[1736] Parsing: "Start parsing data in TextBlob..."

[1737] Show: "Positive review: Great pizza and great atmosphere! Great service."

[1738] Emotion recognition: "We recognized positive emotions from user comments."

[1739] Recommendation: "Recommend new restaurants to the user."

[1740] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1741] Step 1:

[1742] The user enters travel or dining destination requirements

[1743] The user inputs information about their travel destination and desired dining location into the device's application. For example, input information such as "Pizza in Tokyo, perfect for a date" is sent to the device.

[1744] Input: User's requirements for travel destinations and dining locations

[1745] Output: Sending condition information from the terminal to the server

[1746] Step 2:

[1747] The server receives the input information and starts collecting data.

[1748] Based on the input information received from the device, the server collects related data from content distribution platforms (such as review sites and social media. For example, it uses the Yelp API to obtain review data about "Pizza Tokyo."

[1749] Input: Condition information from the terminal

[1750] Output: Acquisition of relevant data from review sites and social media

[1751] Step 3:

[1752] Analyze the data collected by the server

[1753] The server analyzes the acquired review data using natural language processing techniques (e.g., TextBlob or BERT model). The data is classified into positive and negative categories, and summaries are generated.

[1754] Input: Collected review data

[1755] Output: Summary data categorized into positive and negative

[1756] Step 4:

[1757] The server sends the summarized data to the terminal and displays it to the user.

[1758] The server then sends the parsed and summarized data to the device, which then visually displays it to the user, such as a list of summarized reviews and ratings, or restaurant recommendations.

[1759] Input: Summarized data

[1760] Output: Visual information displayed to the user (summary of reviews and restaurant recommendations)

[1761] Step 5:

[1762] The device recognizes the user's emotions

[1763] When a user reacts to the displayed information, the device's emotion engine analyzes the reaction and recognizes the user's emotion. For example, a comment like "It looks delicious, I want to go there!" will be interpreted as a positive emotion.

[1764] Input: User responses (comments, etc.)

[1765] Output: Recognized user emotion data (positive, negative, etc.)

[1766] Step 6:

[1767] The server provides recommendations based on the recognized emotions.

[1768] The server then recommends more suitable travel destinations and dining places based on the recognized emotion data. For example, if the user expresses positive emotion, it will recommend similar spots or new restaurants.

[1769] Input: Recognized user emotion data

[1770] Output: New recommendations (additional restaurants and attractions)

[1771] 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.

[1772] 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.

[1773] 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.

[1774] 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.

[1775] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1776] 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.

[1777] 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).

[1778] 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.

[1779] 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."

[1780] 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.

[1781] 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).

[1782] 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.

[1783] 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.

[1784] 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.

[1785] 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.

[1786] 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.

[1787] 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.

[1788] 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.

[1789] 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.

[1790] 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.

[1791] 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.

[1792] The following is further disclosed regarding the above embodiment.

[1793] (Claim 1)

[1794] means for receiving user input information regarding travel destinations or dining locations;

[1795] means for collecting data from a plurality of multimedia platforms based on the input information;

[1796] means for analyzing the collected data and generating a positive or negative summary of said data;

[1797] means for displaying the summarized data to a user;

[1798] A system including:

[1799] (Claim 2)

[1800] The system of claim 1 further comprising means for calculating a reliability score for the collected data.

[1801] (Claim 3)

[1802] The system according to claim 1, further comprising means for generating a plurality of routes and spots based on the input information and displaying the information.

[1803] "Example 1"

[1804] (Claim 1)

[1805] means for receiving user input information regarding travel destinations or dining locations;

[1806] means for transmitting the input information to a server;

[1807] means for collecting data from a plurality of sources based on the input information;

[1808] means for analyzing the collected data and generating a positive or negative summary of said data;

[1809] means for suggesting the summarized data and travel routes and tourist spots;

[1810] means for transmitting the analyzed data, reliability scores and generated route information to a terminal;

[1811] means for displaying the transmitted information on a user interface;

[1812] A system including:

[1813] (Claim 2)

[1814] The system of claim 1 further comprising means for calculating a reliability score for the collected data.

[1815] (Claim 3)

[1816] The system according to claim 1, further comprising means for generating a plurality of routes and tourist spots based on the input information and displaying the information.

[1817] "Application Example 1"

[1818] (Claim 1)

[1819] means for receiving user input information regarding travel destinations or dining locations;

[1820] means for collecting data from a plurality of multimedia platforms based on the input information;

[1821] means for analyzing the collected data and generating a positive or negative summary of said data;

[1822] means for displaying the summarized data to a user;

[1823] A means of collecting relevant word-of-mouth and review information based on the conditions of products and services in the store, and

[1824] A method for calculating a reliability score from collected word-of-mouth and review information, and

[1825] means for summarizing product and service information based on the reliability score and displaying the summarization to a user;

[1826] A means of recommending appropriate routes and spots within the store,

[1827] A system including:

[1828] (Claim 2)

[1829] The system of claim 1 further comprising means for calculating a reliability score for the collected data.

[1830] (Claim 3)

[1831] The system according to claim 1, further comprising means for generating a plurality of routes and spots based on the input information and displaying the information.

[1832] "Example 2: Combining Emotion Engines"

[1833] (Claim 1)

[1834] means for receiving user input information regarding travel destinations or dining locations;

[1835] means for collecting data from a plurality of information collection platforms based on the input information;

[1836] means for analyzing the collected data and generating a positive or negative summary of said data;

[1837] means for displaying the summarized data to a user;

[1838] means for recognizing a user's emotion regarding the displayed information;

[1839] A means for providing appropriate recommendation information based on the recognized emotion data;

[1840] A system including:

[1841] (Claim 2)

[1842] The system of claim 1 further comprising means for calculating a reliability score for the collected data.

[1843] (Claim 3)

[1844] The system according to claim 1, further comprising means for generating a plurality of routes and spots based on the input information and displaying the information.

[1845] "Application example 2 when combining emotion engines"

[1846] (Claim 1)

[1847] means for receiving user input information regarding travel destinations or dining locations;

[1848] means for collecting data from a plurality of content distribution platforms based on the input information;

[1849] means for analyzing the collected data and generating a positive or negative summary of said data;

[1850] means for displaying the summarized data to a user;

[1851] means for recognizing the emotion of the user;

[1852] means for providing recommendation information based on the recognized emotion;

[1853] A system including:

[1854] (Claim 2)

[1855] The system of claim 1 further comprising means for calculating a reliability score for the collected data.

[1856] (Claim 3)

[1857] 10. The system of claim 1, further comprising means for generating a plurality of routes and points based on the input information and displaying the information. [Explanation of symbols]

[1858] 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 user input information regarding travel destinations or dining locations; means for collecting data from a plurality of multimedia platforms based on the input information; means for analyzing the collected data and generating a positive or negative summary of said data; means for displaying the summarized data to a user; A system including:

2. The system of claim 1 further comprising means for calculating a reliability score for the collected data.

3. The system of claim 1 further comprising means for generating a plurality of routes and spots based on the input information and displaying the information.

Images