System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving a user query; means for analyzing the query; means for searching for relevant information based on the analysis; means for filtering the search results based on user preferences; means for generating and providing the filtered information; and means for displaying the provided information 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] Conventional travel planning systems have faced the challenge of making it difficult for users to gather information about their destinations and plan efficient and appropriate itineraries. In particular, limited information on tourist spots and a lack of information on transportation and accommodation options require a lot of time and effort. Furthermore, users often face problems during their trip and are concerned about their lack of understanding of the local language and culture. There is a need for efficient and accurate solutions to these issues and provide users with a fulfilling travel experience. [Means for solving the problem]

[0005] The present invention provides a system that accepts and analyzes user questions, searches for related information based on the results, and generates and provides information filtered based on the user's preferences. Specifically, the system includes a means for accepting questions from a user terminal, a means for analyzing the content of the question, a means for searching for related information based on the analysis results, a means for filtering the search results based on the user's preferences, a means for generating and providing the filtered information, and a means for displaying the information to the user. This system allows users to efficiently obtain the information they need and to plan a safe and fulfilling trip. Furthermore, by utilizing a generative AI model, information tailored to the user's individual needs can be provided.

[0006] The "means for accepting user questions" provides an interface for users to input questions and information about their travels, and has the function of passing the input to the system.

[0007] The "means for analyzing the question content" has a function that uses natural language processing technology to process question data from users, extract keywords, and understand their intent.

[0008] The "means for searching for related information" has the function of collecting appropriate information from databases and external information sources based on the analyzed question content.

[0009] The "means for filtering based on user preferences" has a function of narrowing down searched information based on the user's past preferences and input data.

[0010] The "means for generating and providing filtered information" refers to a means that processes and configures the filtered information so that it can be presented to the user in an easy-to-understand manner, and ultimately provides the information.

[0011] The "means for displaying information to the user" has the function of visually displaying the generated information on the user's device so that the user can confirm it.

[0012] "Natural language processing means" refers to a technology that converts input text data into a machine-understandable format by segmenting, tagging, and performing semantic analysis.

[0013] "Means for utilizing past user data" refers to a function that retains the user's past behavior history and input data and uses that data to improve the quality of current information provided. [Brief explanation of the drawings]

[0014] [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

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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."

[0035] The present invention relates to a system for streamlining travel planning and providing a fulfilling travel experience to users. This system analyzes questions entered by users and provides relevant information based on the analysis results to generate a travel guide customized to the user's needs.

[0036] First, the user inputs a travel-related question into the terminal. For example, if the user inputs a question such as "What are the recommended tourist spots in Kyoto?", the terminal receives the question and sends it to the server.

[0037] The server analyzes the question using natural language processing. Specifically, it tokenizes the question and extracts keywords. In this example, the keywords extracted are "Kyoto," "recommended," and "tourist spots." The server then uses a generative AI model to understand the user's intent and identify relevant information.

[0038] The server then queries the database to find tourist spot information related to the user's question. The search results include famous tourist spots in Kyoto, such as Kinkaku-ji Temple, Kiyomizu-dera Temple, and Fushimi Inari Taisha Shrine. The server then references the user's past data and preference information, filtering this information to narrow down the recommendations that are most suitable for the user.

[0039] After filtering, the server uses a generative AI model to generate detailed descriptions of each tourist spot and the reasons for its recommendation. For example, it generates information like, "Kinkaku-ji Temple is an especially beautiful piece of architecture, and you can really feel the history of Japan. Visiting early in the morning will help you avoid the crowds."

[0040] Finally, the server converts the generated information into a data structure such as JSON format and sends it to the device as an HTTP response. The device analyzes the received information, updates the GUI components, and displays them to the user. The user can then use the provided information to plan their trip.

[0041] For example, if a user asks, "How can I get around Kyoto city?", the server will go through a similar process to provide information on appropriate transportation options, such as the convenience of city buses, how to use one-day passes, the convenience of JR and subways, and even bicycle rentals.

[0042] In this way, the system of the present invention provides an efficient and accurate travel guide by including a series of processes that analyze the content of the user's question, search, filter, and generate relevant information, and finally provide it to the user.

[0043] The processing flow will be explained below.

[0044] Step 1:

[0045] The user inputs a travel-related question into the terminal. Specifically, for example, the text "What are the recommended tourist spots in Kyoto?" is input.

[0046] Step 2:

[0047] The device receives the input question and prepares an HTTP request to send to the server, converting the question content into a data structure such as JSON.

[0048] Step 3:

[0049] The server receives the HTTP request sent from the terminal and begins the process of analyzing the question.

[0050] Step 4:

[0051] The server uses natural language processing to tokenize the question and extract keywords, such as "Kyoto," "recommended," and "tourist spots."

[0052] Step 5:

[0053] The server inputs the analyzed keywords and question content into a generative AI model to understand the user's intent. This generative AI model then identifies the type of information desired from the user's question.

[0054] Step 6:

[0055] The server generates a query in the database to search for tourist spot information related to the query. The search query includes the extracted keywords.

[0056] Step 7:

[0057] The server receives the search results retrieved from the database and uses a generative AI model to filter them based on the user's preferences and past tastes, for example, by looking at past search history and user profiles.

[0058] Step 8:

[0059] The server generates detailed explanations and reasons for recommendations based on the filtered information. The generative AI model converts this into text. For example, it generates information such as, "Kinkaku-ji Temple is a particularly beautiful piece of architecture, and you can feel the history of Japan."

[0060] Step 9:

[0061] The server converts the generated information into a data structure such as JSON format and sends it to the terminal as an HTTP response.

[0062] Step 10:

[0063] The terminal analyzes the HTTP response received from the server and performs processing to display it on the user interface.

[0064] Step 11:

[0065] The terminal displays the generated information to the user, for example, detailed information about Kinkaku-ji Temple, Kiyomizu-dera Temple, and Fushimi Inari Taisha Shrine.

[0066] Step 12:

[0067] The user consults the provided information and plans their trip, entering further questions as needed and returning to step 1.

[0068] Example 1

[0069] 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."

[0070] Conventional travel guide systems have the problem that when users input travel-related questions, the information provided is general, making it difficult to respond to individual user needs and preferences.In addition, the information is not sufficiently filtered or customized, making it difficult to provide the information users truly want.

[0071] 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.

[0072] In this invention, the server includes means for accepting a user's question, means for performing natural language processing to analyze the content of the question, means for identifying related information using a generative AI model based on the analysis results, means for searching a database for the identified related information, means for filtering search results based on the user's preferences, means for generating and providing the filtered information, and means for displaying the provided information to the user, thereby enabling the provision of information that meets the individual needs and preferences of the user.

[0073] A "user question" is text data that a user inputs into a terminal to obtain information about a trip in which the user is interested.

[0074] "Natural language processing" is a technology that analyzes text data entered by a user and performs keyword extraction and grammatical analysis.

[0075] A "generative AI model" is an algorithm that uses artificial intelligence to understand a user's intent and generate appropriate answers to questions.

[0076] A "database" is a storage device that stores information on tourist spots, transportation options, and the like.

[0077] "Filtering" is the process of selecting information from search results that matches the user's preferences.

[0078] "Information generation" is the process of creating specific answers to provide to users based on the filtered data.

[0079] "Providing information" is the process of presenting the generated answers to the user in an easy-to-understand format.

[0080] "Display" refers to the act of visually showing the generated answer on the user's terminal screen.

[0081] "Past user data" refers to records relating to questions and preferences previously entered by a user, information that is used to generate customized answers.

[0082] MODE FOR CARRYING OUT THE INVENTION

[0083] The present invention relates to a system for improving the efficiency of users' travel planning and providing a fulfilling travel experience, which accepts and analyzes user questions, searches, filters, generates related information, and provides it to users. Specific embodiments of the system are described below.

[0084] Hardware and Software Configuration

[0085] This system consists of a terminal where users can input travel-related questions, a server for analyzing the questions and generating information, and a database.

[0086] Terminal: Users access the system using a terminal such as a smartphone, tablet, or PC. The terminal is equipped with an input interface (e.g., touchscreen, keyboard).

[0087] Server: The server contains a natural language processing (NLP) module, a generative AI model, and a database access module to analyze user questions, identify relevant information, and generate it.

[0088] Database: Contains information on tourist attractions, transportation options, etc.

[0089] Program processing

[0090] A user inputs a travel-related question into a device. For example, if a question is input such as "What are the recommended tourist spots in Kyoto?", the device receives the question and sends it to the server as an HTTP POST request. The server receives the question and analyzes it using a natural language processing module. During the analysis, the question is tokenized and keywords are extracted. For example, the keywords "Kyoto," "recommended," and "tourist spots" are extracted.

[0091] The server then uses a generative AI model to understand the user's intent and identify relevant information. An example prompt might be, "The user is asking about recommended tourist spots in Kyoto." The server then queries the database to search for tourist spot information related to the user's question. For example, the search results might include information about Kyoto's most famous tourist spots, such as Kinkaku-ji Temple, Kiyomizu-dera Temple, and Fushimi Inari Taisha Shrine.

[0092] The server then references the user's past data and preferences, filtering this information to narrow down the recommendations to the most appropriate ones. After filtering, the server uses a generative AI model to generate detailed descriptions of each tourist spot and the reasons for the recommendation. For example, the server generates information such as, "Kinkaku-ji Temple has particularly beautiful architecture and allows you to feel the history of Japan. Visiting early in the morning will help you avoid the crowds."

[0093] Finally, the server converts the generated information into JSON format and sends it to the device as an HTTP response. The device parses the received JSON data, updates the appropriate GUI components, and displays them to the user. The user can then use the provided information to plan their trip.

[0094] Specific examples

[0095] For example, if a user asks, "How can I get around Kyoto city?", the server will go through a similar process to provide information on appropriate transportation options. This includes information on the convenience of city buses, how to use one-day passes, the convenience of trains and subways, and even bicycle rentals. An example prompt would be, "The user is asking about effective transportation options within Kyoto city."

[0096] In this way, the system of the present invention can provide information that meets the individual needs and preferences of each user.

[0097] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0098] Step 1:

[0099] The user inputs a travel-related question into the terminal. For example, "What are the recommended tourist spots in Kyoto?" The text is entered into the input field, and this text data is used as input for subsequent processing.

[0100] Step 2:

[0101] The terminal receives a question from the user and sends it to the server as an HTTP POST request. The input is the user's question text, and the output is the HTTP request.

[0102] Step 3:

[0103] The server analyzes the received question. This question text is passed to a natural language processing (NLP) module. The input is the user's question text, and the output is the analyzed keywords. Specifically, the question text is tokenized to extract keywords. Keywords such as "Kyoto," "recommended," and "tourist spots" are extracted.

[0104] Step 4:

[0105] The server sends a prompt to the generative AI model based on the extracted keywords. The input is the extracted keywords, and the output is related information that understands the user's intent. An example of a prompt is, "The user is asking about recommended tourist spots in Kyoto."

[0106] Step 5:

[0107] The server issues a query to the database to search for relevant tourist spot information. The input is a prompt statement and a query to the database, and the output is tourist spot information as a search result. An example is "SELECT FROM tourist spot WHERE location = 'Kyoto' AND recommended = 1".

[0108] Step 6:

[0109] The server filters the search results, narrowing down the optimal results based on the user's past data and preferences. The input is the search results and the user's past data, and the output is the filtered tourist spot information.

[0110] Step 7:

[0111] The server uses a generative AI model to generate detailed descriptions based on the filtered tourist spot information. The input is the filtered tourist spot information, and the output is the generated detailed description. The generated sentence might be something like, "Kinkaku-ji Temple is a particularly beautiful piece of architecture, and you can really feel the history of Japan. If you visit early in the morning, you can avoid the crowds."

[0112] Step 8:

[0113] The server converts the generated information into JSON format and sends it to the terminal as an HTTP response. The input is the generated description, and the output is JSON format data.

[0114] Step 9:

[0115] The device parses the received JSON data, updates the GUI components, and displays them to the user. The input is JSON data, and the output is the information displayed on the user's screen. The user uses the provided information to plan their trip.

[0116] In this way, specific data processing and data calculations are performed at each step, and the input for the next step is generated based on the results.

[0117] (Application example 1)

[0118] 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."

[0119] Conventional travel guide systems were unable to meet the diverse needs of users and had difficulty providing information in real time. This made it difficult for tourists to efficiently obtain information while traveling and plan trips that suited their preferences. Furthermore, there was a lack of systems that utilized voice input or smart devices, making them less convenient.

[0120] 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.

[0121] In this invention, the server includes means for accepting a user's question, means for analyzing the question, means for searching for related information based on the analysis result, means for filtering the search results based on the user's preferences, means for generating and providing the filtered information, means for displaying the provided information to the user, means for accepting a voice input, means for recognizing the voice input and converting it into text data, and means for displaying or outputting the text on the smart device. This allows the user to input a question using voice, and the answer to the question can be displayed or output as text on the smart device in real time.

[0122] The "means for accepting user questions" is an interface that allows the user to input questions about travel in voice or text format.

[0123] The "means for analyzing the question content" is a system that uses natural language processing technology to analyze the question entered by the user and extract key keywords and intent.

[0124] The "means for searching for related information based on the analysis results" is a system that searches databases and external information sources to obtain related information based on the analyzed question content.

[0125] "Means for filtering search results based on user preferences" refers to a system that scrutinizes acquired information based on the user's past preferences and behavioral data, and selects the information that is deemed most appropriate.

[0126] The "means for generating and providing filtered information" is a system for converting selected information into a form that is easy for users to understand and providing it in text or audio.

[0127] The "means for displaying the provided information to the user" is a system that displays the generated information visually or audibly on the user's terminal.

[0128] The "means for accepting voice input" is an interface that receives questions input by voice from the user through a device such as a microphone.

[0129] "Means for recognizing voice input and converting it into text data" refers to a system that uses voice recognition technology to analyze the voice input by the user and convert it into text data.

[0130] "Means for displaying or outputting audio on a smart device" refers to a system for displaying the generated information on a device such as a smartphone or smart glasses, or outputting it as audio.

[0131] To implement this invention, several steps are required. First, a smart device (e.g., smart glasses) is used as a means for accepting user questions. The user inputs questions by voice through this device. For example, a question such as "What are the recommended tourist spots in Kyoto?" can be input by voice.

[0132] Smart devices have a means of recognizing voice input and converting it into text data. This is done using the speech_recognition library. This recognized text data is sent directly to the server, where it is analyzed.

[0133] The server has the means to analyze the question, using natural language processing techniques (e.g., the "question answering" model from the transformers library). After analyzing the question, the server searches for relevant information based on the analysis results from a database, which is pre-populated with travel information.

[0134] The searched information is filtered using the user's past data (preferences and behavioral history). This filtering selects the information most appropriate for the user. The server then uses a generative AI model to generate detailed explanatory text from the filtered information to provide to the user. For example, information such as "Kinkaku-ji Temple is a particularly beautiful piece of architecture, and is a place where you can feel the history of Japan. Visiting early in the morning will help you avoid the crowds."

[0135] The generated information is displayed on the smart device or output as audio, utilizing the device's standard interface, allowing users to obtain the tourist information they need in real time, facilitating decision-making during their trip.

[0136] For example, if a user asks, "How can I get around Kyoto?", the server might provide information like this: "City buses are very convenient, and you can save money by using a one-day pass. JR and subways are also efficient ways to get around. We also recommend renting a bicycle to tour around Kyoto's tourist attractions."

[0137] Examples of prompts are:

[0138] User dictates: "What are some recommended places to eat in Kyoto?"

[0139] The system responds: "We particularly recommend Japanese restaurants such as Gion Sasagi in Gion and Arashiyama Yoshimura in Arashiyama. Each offers distinctive cuisine and stunning views."

[0140] In this way, the system of the present invention can provide real-time travel guide information that meets the diverse needs of users.

[0141] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0142] Step 1:

[0143] The user starts voice input. The user speaks a question into the smart device (e.g., smart glasses) (e.g., "What are the recommended tourist spots in Kyoto?"). This voice data is input.

[0144] Step 2:

[0145] The device receives the voice data and performs speech recognition. Specifically, it converts the voice data into text data using the speech_recognition library. The converted text data is generated (e.g., "What are the recommended tourist spots in Kyoto?").

[0146] Step 3:

[0147] The terminal transmits the generated text data to the server, which receives the text data.

[0148] Step 4:

[0149] The server analyzes the question, performs natural language processing using the transformers library, and extracts key keywords (e.g., "Kyoto," "recommended," "tourist spots") as the analysis results.

[0150] Step 5:

[0151] The server searches for relevant information based on the analysis results. It obtains data on "Kyoto tourist spots" from internal databases and external information sources. The obtained data is generated (e.g., "Kinkaku-ji Temple," "Kiyomizu-dera Temple," "Fushimi Inari Taisha Shrine").

[0152] Step 6:

[0153] The server filters the search results based on the user's preferences, referencing the user's past preferences and behavioral history to select the most relevant information, and the filtered data is generated.

[0154] Step 7:

[0155] The server uses a generative AI model to generate detailed explanatory text based on the filtered information, using prompts (e.g., "Kinkaku-ji Temple is a particularly beautiful building, and you can feel the history of Japan. Visiting it early in the morning will help you avoid the crowds.").

[0156] Step 8:

[0157] The terminal displays or outputs the provided information as audio, and displays the generated text on the smart device's display or outputs it as audio through the speaker.

[0158] This series of processes allows the user to perform voice input and obtain customized travel guide information in real time as a result.

[0159] 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.

[0160] This invention relates to a system for improving the efficiency of travel planning and providing a fulfilling travel experience to users. This system not only analyzes questions entered by users and provides relevant information based on the analysis results, but also recognizes the user's emotions and customizes the content and presentation of information based on those emotions to provide a more personalized travel guide.

[0161] First, the user inputs a travel-related question into the device. For example, if the user inputs a question such as "What are the recommended tourist spots in Kyoto?", the device receives the question and then an emotion engine analyzes the user's emotional state from the input text and voice.

[0162] The device sends the user's question along with emotion data to the server. The server then uses natural language processing to analyze the question. Specifically, it tokenizes the question and extracts keywords. In this case, the keywords extracted are "Kyoto," "recommended," and "tourist spot." The server then uses a generative AI model to understand the user's intent and identify relevant information.

[0163] The server then queries the database to find tourist spot information related to the user's question. The search results include famous tourist spots in Kyoto, such as Kinkaku-ji Temple, Kiyomizu-dera Temple, and Fushimi Inari Taisha Shrine. The server then references the user's past data, preference information, and emotional data, and filters this information to narrow down the recommendations that are most suitable for the user.

[0164] After filtering, the server uses a generative AI model to generate detailed descriptions of each tourist spot and the reasons for its recommendation. For example, if the user is surprised or excited, the server generates more positive and emotional content, such as "Kinkaku-ji Temple is a particularly beautiful piece of architecture, and you can feel the history of Japan."

[0165] Finally, the server converts the generated information into a data structure such as JSON and sends it to the device as an HTTP response. The device then analyzes the received information, updates the GUI components, and displays them to the user. For example, a user who is surprised or excited could be shown a visually appealing image or video.

[0166] For example, if a user asks, "How do I get around Kyoto City?" and the emotion engine recognizes that the user is confused, the server will go through a similar process to provide information on appropriate transportation options. For example, it will provide detailed information on the convenience of city buses, how to use one-day passes, the convenience of JR and subways, and even how to rent a bicycle. Confused users will be provided with particularly clear and specific guidance.

[0167] In this way, the system of the present invention, which combines an emotion engine, analyzes the content of the user's question, searches, filters, and generates related information, and ultimately provides information customized according to the user's emotions, thereby realizing a more personalized travel guide.

[0168] The processing flow will be explained below.

[0169] Step 1:

[0170] The user inputs a travel-related question into the terminal. Specifically, the user inputs the text "What are the recommended tourist spots in Kyoto?"

[0171] Step 2:

[0172] The device receives the input question, and an emotion engine analyzes the text to determine the user's emotions, such as whether the user is surprised or happy.

[0173] Step 3:

[0174] The device sends the question and the recognized emotion data to the server, which converts the data into a data structure such as JSON.

[0175] Step 4:

[0176] The server receives the question content and emotion data sent from the terminal and starts the process of analyzing the question content.

[0177] Step 5:

[0178] The server uses natural language processing to tokenize the question and extract keywords, such as "Kyoto," "recommended," and "tourist spots."

[0179] Step 6:

[0180] The server uses a generative AI model to identify the type of information sought from the user's question based on the extracted keywords and understand the intent.

[0181] Step 7:

[0182] The server queries the database to find tourist spots related to the user's question, and the search results include "Kinkaku-ji Temple," "Kiyomizu-dera Temple," and "Fushimi Inari Taisha Shrine."

[0183] Step 8:

[0184] The server uses a generative AI model to filter the acquired tourist spot information based on the user's past preference data and recognized emotional data, thereby providing more optimistic content to users in a positive emotional state, for example.

[0185] Step 9:

[0186] Based on the filtered information, the server uses a generative AI model to generate detailed explanations and reasons for the recommendation in text format. For example, if the emotion engine recognizes the user's emotion of surprise, it will generate content that touches on the user's emotion, such as "Kinkaku-ji Temple is a particularly beautiful piece of architecture, and you can feel the history of Japan."

[0187] Step 10:

[0188] The server converts the generated information into a data structure such as JSON format and sends it to the terminal as an HTTP response.

[0189] Step 11:

[0190] The device analyzes the HTTP response received from the server, updates the GUI components, and displays them to the user. For example, it may also display emotive images or videos.

[0191] Step 12:

[0192] The user refers to the provided information and makes travel plans. If the user has further questions, they return to step 1 and enter new questions.

[0193] For example, if a user asks, "How do I get around Kyoto City?" and the emotion engine recognizes the user's confusion, the server will provide detailed information on appropriate transportation methods, such as how to use city buses, how to purchase one-day passes, and the convenience of JR and subways, providing easy-to-understand visual guidance.

[0194] Example 2

[0195] 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."

[0196] Conventional travel guide systems simply provide information in response to user questions, and are insufficient in providing personalized information that reflects the user's emotional state or individual preferences. As a result, it is difficult for users to create satisfying travel plans. Furthermore, when a large number of search results are returned, it is difficult for users to narrow down the specific information they need, which requires time and effort.

[0197] 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.

[0198] In this invention, the server includes a means for analyzing the user's emotional state along with the user's question, a means for searching for related information based on the user's question and emotional state, and a means for generating and providing filtered information using a generative AI model. This makes it possible to provide customized information based on the user's emotional state and past preferences, allowing the user to make more satisfying travel plans.

[0199] "Means for accepting user questions" refers to a function for receiving travel-related questions that users input into the system.

[0200] "Means for analyzing the user's emotional state" refers to a function for analyzing the user's emotional state (for example, excitement, confusion, etc.) from questions or voice data entered by the user.

[0201] "Means for searching related information" refers to the function of searching for related information from databases or the Internet based on the user's question and emotional state.

[0202] "Filtering means" refers to the function of narrowing down searched information based on the user's past data and preference information, and selecting the most appropriate information.

[0203] "Means of providing information using a generative AI model" refers to the function of using AI technology to generate specific, customized information desired by the user and provide it to the user.

[0204] "Natural language processing means" refers to technology that analyzes questions entered by users and extracts important keywords.

[0205] "Means for generating prompt sentences" refers to the function of creating appropriate input sentences for the generative AI model.

[0206] This invention relates to a system for improving the efficiency of travel planning and providing a fulfilling travel experience to users. This system not only analyzes questions entered by users and provides relevant information based on the analysis results, but also recognizes the user's emotions and customizes the content and presentation of information based on those emotions to provide a more personalized travel guide.

[0207] First, the user inputs a travel-related question into the device. For example, if the user inputs a question such as "What are the recommended tourist spots in Kyoto?", the device receives the question and then an emotion engine analyzes the user's emotional state from the input text and voice.

[0208] The device sends the user's question along with emotion data to the server. The server then uses natural language processing to analyze the question. Specifically, it tokenizes the question and extracts keywords. In this case, the keywords extracted are "Kyoto," "recommended," and "tourist spot." The server then uses a generative AI model to understand the user's intent and identify relevant information.

[0209] The server then queries the database to find tourist spot information related to the user's question. The search results include famous tourist spots in Kyoto, such as Kinkaku-ji Temple, Kiyomizu-dera Temple, and Fushimi Inari Taisha Shrine. The server then references the user's past data, preference information, and emotional data, and filters this information to narrow down the recommendations that are most suitable for the user.

[0210] After filtering, the server uses a generative AI model to generate detailed descriptions of each tourist spot and the reasons for its recommendation. For example, if the user is surprised or excited, the server generates more positive and emotional content, such as "Kinkaku-ji Temple is a particularly beautiful piece of architecture, and you can feel the history of Japan."

[0211] Finally, the server converts the generated information into a data structure such as JSON and sends it to the device as an HTTP response. The device then analyzes the received information, updates the GUI components, and displays them to the user. For example, a user who is surprised or excited could be shown a visually appealing image or video.

[0212] For example, if a user asks, "How do I get around Kyoto City?" and the emotion engine recognizes that the user is confused, the server will go through a similar process to provide information on appropriate transportation options. For example, it will provide detailed information on the convenience of city buses, how to use one-day passes, the convenience of JR and subways, and even how to rent a bicycle. Confused users will be provided with particularly clear and specific guidance.

[0213] In this way, the system of the present invention, which combines an emotion engine, analyzes the content of the user's question, searches, filters, and generates related information, and ultimately provides information customized according to the user's emotions, thereby realizing a more personalized travel guide.

[0214] Examples of prompts might include: "The user asked about tourist attractions in Kyoto. The user seems excited. How would you respond?" or "The user asked about transportation options within Kyoto. The user seems confused. Please provide a clear answer."

[0215] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0216] Step 1:

[0217] The user inputs a travel question into the terminal.

[0218] Specific operation: The user enters "What are the recommended tourist spots in Kyoto?" into the input field on the device.

[0219] Input: User question text

[0220] Output: The question text is typed into the terminal.

[0221] Step 2:

[0222] The terminal analyzes the input question text and uses an emotion engine to analyze the user's emotional state.

[0223] Specific operation: The device's emotion engine analyzes the text and extracts emotional states such as "excitement" or "confusion."

[0224] Input: Question text

[0225] Output: Emotion data (e.g. excited)

[0226] Step 3:

[0227] The device sends the question text and emotion data to the server.

[0228] Specific operation: The device uses an HTTP request to send the user's question, "What are the recommended tourist spots in Kyoto?" and emotion data to the server.

[0229] Input: Question text, emotion data

[0230] Output: HTTP request to the server

[0231] Step 4:

[0232] The server analyzes the received question text and extracts keywords using natural language processing means.

[0233] Specific operation: The server uses an NLP library (e.g., NLTK or SpaCy) to tokenize the question and extract keywords. The keywords obtained are "Kyoto," "recommended," and "tourist spot."

[0234] Input: Question text

[0235] Output: Extracted keywords

[0236] Step 5:

[0237] The server inputs prompts into the generative AI model to understand the user's intent and identify relevant information.

[0238] Specific operation: The server inputs a prompt to the generative AI model (e.g., GPT-3): "The user asked about recommended tourist spots in Kyoto. The user is excited. How would you respond?" The generative AI model generates related information such as "Kinkaku-ji Temple," "Kiyomizu-dera Temple," and "Fushimi Inari Taisha Shrine."

[0239] Input: Extracted keywords, prompt sentence

[0240] Output: Related information generated

[0241] Step 6:

[0242] The server queries the database to find the relevant information.

[0243] Specific operation: The server executes a database query to retrieve tourist spot information that matches the keywords: "Kinkaku-ji Temple," "Kiyomizu-dera Temple," and "Fushimi Inari Taisha Shrine."

[0244] Input: Generated related information

[0245] Output: Tourist spot information retrieved from the database

[0246] Step 7:

[0247] The server filters information based on the user's past data, preference information, and emotional data.

[0248] Specific operation: The server compares the user's past search history and preferences to select the most suitable tourist spot. For example, it determines that Kinkaku-ji Temple is the most suitable for the user's preferences.

[0249] Input: Tourist spot information obtained from the database, user's past data, preference information, emotional data

[0250] Output: Filtered tourist spot information

[0251] Step 8:

[0252] The server uses a generative AI model to generate detailed explanations and recommendations based on the filtered information.

[0253] Specific behavior: The generative AI model generates a detailed description that reads, "Kinkaku-ji is a particularly beautiful piece of architecture, and you can feel the history of Japan."

[0254] Input: Filtered tourist spot information

[0255] Output: Detailed description generated

[0256] Step 9:

[0257] The server converts the generated information into a data structure such as JSON format and sends it to the terminal as an HTTP response.

[0258] Specific operation: The information generated by the server is converted into JSON data and sent to the terminal via an HTTP response.

[0259] Input: Generated detailed description

[0260] Output: HTTP response to the device

[0261] Step 10:

[0262] The terminal analyzes the received information, updates the GUI components, and displays them to the user.

[0263] What it does: The device parses the JSON data and displays the information in a GUI with visually appealing images and videos, using particularly positive language for excited users.

[0264] Input: HTTP response to the terminal

[0265] Output: Updated GUI display

[0266] (Application example 2)

[0267] 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."

[0268] While conventional travel guide systems can provide general information in response to user questions, they have difficulty providing personalized information based on the user's emotional state or individual preferences. Furthermore, there is a lack of interactive methods for obtaining necessary information in real time during travel, which has resulted in a lack of sufficient improvement in the user experience.

[0269] 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 accepting a user's question, means for analyzing the content of the question, means for searching for related information based on the analysis result, means for filtering the search results based on the user's preferences, means for generating and providing the filtered information, means for displaying the provided information to the user, and means for analyzing emotions. This makes it possible to provide a personalized travel guide in real time according to the user's emotional state.

[0270] The "means for accepting user questions" is an interface through which users input questions about travel, and is a device or software that accepts questions by text or voice.

[0271] The "means for analyzing the question content" is a device or software that analyzes the question entered by the user and extracts the intent of the question and key keywords.

[0272] The "means for searching for related information" is a device or software that searches for related information from a database or the Internet based on the analyzed question content.

[0273] A "means for filtering based on user preferences" is a device or software that selects the most appropriate information from search results based on the user's past behavior and preference data.

[0274] The "means for generating and providing filtered information" refers to a device or software that automatically generates text such as an explanation or a reason for recommendation in order to provide the filtered information to the user.

[0275] The "means for displaying the provided information to the user" is a device or software for visually displaying the generated information on the user's terminal.

[0276] The "emotion analysis means" is a device or software that analyzes the user's emotional state based on the content of the user's questions and past behavioral data, and customizes the information provided based on the results.

[0277] This invention is a system that allows users to input travel-related questions and provides personalized information based on the content of the question and the user's emotional state. The system aims to improve the user experience by providing an efficient means for users to obtain necessary information in real time while traveling.

[0278] 1. Hardware and Software Used

[0279] The main hardware required to implement this system includes the device used by the user (e.g., smartphone, head-mounted display, etc.) and the server. The main software used includes a natural language processing engine (e.g., spaCy), a sentiment analysis engine (e.g., AWS Comprehend, Hugging Face Transformers), and a Web API server (e.g., Flask, Django). Information is also generated using a generative AI model.

[0280] 2. System Operation Overview

[0281] A user inputs a travel-related question into a terminal. For example, if a question is input such as "What are the recommended tourist spots in Kyoto?", the terminal receives this question. The emotion analysis means analyzes the user's emotional state from the input text and sends the obtained emotion data to the server. The server performs processing in the following steps based on the received question content and emotion data.

[0282] Question analysis: The question is tokenized and keywords are extracted. For example, keywords such as "Kyoto," "recommended," and "tourist spots" are extracted.

[0283] Information retrieval: The server uses a generative AI model to understand the user's intent and identify relevant information, then queries the database to retrieve tourist spot information.

[0284] Information filtering: Search results are filtered to provide the most relevant recommendations to the user based on their past data, preferences, and emotional data.

[0285] Information generation and display: The filtered information is generated as text using a generative AI model. This information is converted into a data structure such as JSON and sent to the device as an HTTP response. The device analyzes the received information, updates the GUI components, and displays it to the user.

[0286] 3. Examples and prompts

[0287] For example, if a user asks, "How do I get around Kyoto City?" and the sentiment analysis tool detects that the user is confused, the server will go through a similar process to provide information on appropriate transportation options. For example, detailed explanations on the convenience of city buses, how to use one-day passes, the convenience of JR and subways, and even how to rent a bicycle are provided. Confused users will be provided with particularly clear and specific guidance.

[0288] Prompt Sentence Examples

[0289] "Please tell me about some beautiful gardens in Kyoto. I am always amazed when I see my favorite scenery."

[0290] This system provides users with real-time travel guides tailored to their emotional state, making the virtual travel experience more personalized.

[0291] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0292] Step 1:

[0293] The user inputs a question into the terminal. For example, the user inputs "What are the recommended tourist spots in Kyoto?" The terminal receives this question and sends it to the sentiment analysis means. The input is the user's question, and the output is text data that is passed to the sentiment analysis.

[0294] Step 2:

[0295] An emotion analysis means installed on the device analyzes the user's emotional state from the input text data. An emotion analysis engine (e.g., AWS Comprehend) analyzes the text and detects emotional states such as "surprise" or "excitement." The input is the user's question, and the output is the detected emotional data. The device then sends this emotional data to a server.

[0296] Step 3:

[0297] The server receives the emotion data and the question. It then uses a natural language processing engine (e.g., spaCy) to analyze the question. It tokenizes the question and extracts key keywords. For example, it extracts keywords such as "Kyoto," "recommended," and "tourist spots." The input is the question and emotion data, and the output is the extracted keywords.

[0298] Step 4:

[0299] The server uses a generative AI model to understand the user's intent and identify relevant information. Based on the extracted keywords, the generative AI model infers the user's intent. The input is the extracted keywords, and the output is the inferred result of the user's intent.

[0300] Step 5:

[0301] The server queries the database to retrieve information about related tourist spots. For example, it retrieves information about "Kinkaku-ji Temple," "Kiyomizu-dera Temple," and "Fushimi Inari Taisha Shrine." The input is the result of inferring the user's intention, and the output is the retrieved tourist spot information.

[0302] Step 6:

[0303] The server filters the search results based on the user's preferences. This filtering refers to the user's past data and preference information to select the most suitable spots. For example, it may select based on places and activities that the user has shown interest in in the past. The input is the search results, and the output is the filtered tourist spot information.

[0304] Step 7:

[0305] The server uses a generative AI model to generate explanatory text based on the filtered information. It also takes into account the user's emotional data to generate text that appeals to the user's emotions. For example, it generates the sentence, "Kinkaku-ji Temple is a particularly beautiful piece of architecture, and you can feel the history of Japan." The input is the filtered information and emotional data, and the output is the generated explanatory text.

[0306] Step 8:

[0307] The server converts the generated information into a data structure such as JSON and sends it to the terminal as an HTTP response. The input is the generated description, and the output is the data sent as the HTTP response.

[0308] Step 9:

[0309] The device analyzes the information it receives and updates GUI components to visually display it to the user, for example displaying generated explanatory text along with attractive images or videos. The input is the data received as an HTTP response, and the output is the visual information displayed to the user.

[0310] Through this step, users can get real-time travel guide information that is personalized according to their emotional state.

[0311] 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.

[0312] 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.

[0313] 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.

[0314] [Second embodiment]

[0315] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0316] 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.

[0317] 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).

[0318] 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.

[0319] 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.

[0320] 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).

[0321] 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.

[0322] 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.

[0323] 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.

[0324] 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.

[0325] 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.

[0326] 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."

[0327] The present invention relates to a system for streamlining travel planning and providing a fulfilling travel experience to users. This system analyzes questions entered by users and provides relevant information based on the analysis results to generate a travel guide customized to the user's needs.

[0328] First, the user inputs a travel-related question into the terminal. For example, if the user inputs a question such as "What are the recommended tourist spots in Kyoto?", the terminal receives the question and sends it to the server.

[0329] The server analyzes the question using natural language processing. Specifically, it tokenizes the question and extracts keywords. In this example, the keywords extracted are "Kyoto," "recommended," and "tourist spots." The server then uses a generative AI model to understand the user's intent and identify relevant information.

[0330] The server then queries the database to find tourist spot information related to the user's question. The search results include famous tourist spots in Kyoto, such as Kinkaku-ji Temple, Kiyomizu-dera Temple, and Fushimi Inari Taisha Shrine. The server then references the user's past data and preference information, filtering this information to narrow down the recommendations that are most suitable for the user.

[0331] After filtering, the server uses a generative AI model to generate detailed descriptions of each tourist spot and the reasons for its recommendation. For example, it generates information like, "Kinkaku-ji Temple is an especially beautiful piece of architecture, and you can really feel the history of Japan. Visiting early in the morning will help you avoid the crowds."

[0332] Finally, the server converts the generated information into a data structure such as JSON format and sends it to the device as an HTTP response. The device analyzes the received information, updates the GUI components, and displays them to the user. The user can then use the provided information to plan their trip.

[0333] For example, if a user asks, "How can I get around Kyoto city?", the server will go through a similar process to provide information on appropriate transportation options, such as the convenience of city buses, how to use one-day passes, the convenience of JR and subways, and even bicycle rentals.

[0334] In this way, the system of the present invention provides an efficient and accurate travel guide by including a series of processes that analyze the content of the user's question, search, filter, and generate relevant information, and finally provide it to the user.

[0335] The processing flow will be explained below.

[0336] Step 1:

[0337] The user inputs a travel-related question into the terminal. Specifically, for example, the text "What are the recommended tourist spots in Kyoto?" is input.

[0338] Step 2:

[0339] The device receives the input question and prepares an HTTP request to send to the server, converting the question content into a data structure such as JSON.

[0340] Step 3:

[0341] The server receives the HTTP request sent from the terminal and begins the process of analyzing the question.

[0342] Step 4:

[0343] The server uses natural language processing to tokenize the question and extract keywords, such as "Kyoto," "recommended," and "tourist spots."

[0344] Step 5:

[0345] The server inputs the analyzed keywords and question content into a generative AI model to understand the user's intent. This generative AI model then identifies the type of information desired from the user's question.

[0346] Step 6:

[0347] The server generates a query in the database to search for tourist spot information related to the query. The search query includes the extracted keywords.

[0348] Step 7:

[0349] The server receives the search results retrieved from the database and uses a generative AI model to filter them based on the user's preferences and past tastes, for example, by looking at past search history and user profiles.

[0350] Step 8:

[0351] The server generates detailed explanations and reasons for recommendations based on the filtered information. The generative AI model converts this into text. For example, it generates information such as, "Kinkaku-ji Temple is a particularly beautiful piece of architecture, and you can feel the history of Japan."

[0352] Step 9:

[0353] The server converts the generated information into a data structure such as JSON format and sends it to the terminal as an HTTP response.

[0354] Step 10:

[0355] The terminal analyzes the HTTP response received from the server and performs processing to display it on the user interface.

[0356] Step 11:

[0357] The terminal displays the generated information to the user, for example, detailed information about Kinkaku-ji Temple, Kiyomizu-dera Temple, and Fushimi Inari Taisha Shrine.

[0358] Step 12:

[0359] The user consults the provided information and plans their trip, entering further questions as needed and returning to step 1.

[0360] Example 1

[0361] 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."

[0362] Conventional travel guide systems have the problem that when users input travel-related questions, the information provided is general, making it difficult to respond to individual user needs and preferences.In addition, the information is not sufficiently filtered or customized, making it difficult to provide the information users truly want.

[0363] 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.

[0364] In this invention, the server includes means for accepting a user's question, means for performing natural language processing to analyze the content of the question, means for identifying related information using a generative AI model based on the analysis results, means for searching a database for the identified related information, means for filtering search results based on the user's preferences, means for generating and providing the filtered information, and means for displaying the provided information to the user, thereby enabling the provision of information that meets the individual needs and preferences of the user.

[0365] A "user question" is text data that a user inputs into a terminal to obtain information about a trip in which the user is interested.

[0366] "Natural language processing" is a technology that analyzes text data entered by a user and performs keyword extraction and grammatical analysis.

[0367] A "generative AI model" is an algorithm that uses artificial intelligence to understand a user's intent and generate appropriate answers to questions.

[0368] A "database" is a storage device that stores information on tourist spots, transportation options, and the like.

[0369] "Filtering" is the process of selecting information from search results that matches the user's preferences.

[0370] "Information generation" is the process of creating specific answers to provide to users based on the filtered data.

[0371] "Providing information" is the process of presenting the generated answers to the user in an easy-to-understand format.

[0372] "Display" refers to the act of visually showing the generated answer on the user's terminal screen.

[0373] "Past user data" refers to records relating to questions and preferences previously entered by a user, information that is used to generate customized answers.

[0374] MODE FOR CARRYING OUT THE INVENTION

[0375] The present invention relates to a system for improving the efficiency of users' travel planning and providing a fulfilling travel experience, which accepts and analyzes user questions, searches, filters, generates related information, and provides it to users. Specific embodiments of the system are described below.

[0376] Hardware and Software Configuration

[0377] This system consists of a terminal where users can input travel-related questions, a server for analyzing the questions and generating information, and a database.

[0378] Terminal: Users access the system using a terminal such as a smartphone, tablet, or PC. The terminal is equipped with an input interface (e.g., touchscreen, keyboard).

[0379] Server: The server contains a natural language processing (NLP) module, a generative AI model, and a database access module to analyze user questions, identify relevant information, and generate it.

[0380] Database: Contains information on tourist attractions, transportation options, etc.

[0381] Program processing

[0382] A user inputs a travel-related question into a device. For example, if a question is input such as "What are the recommended tourist spots in Kyoto?", the device receives the question and sends it to the server as an HTTP POST request. The server receives the question and analyzes it using a natural language processing module. During the analysis, the question is tokenized and keywords are extracted. For example, the keywords "Kyoto," "recommended," and "tourist spots" are extracted.

[0383] The server then uses a generative AI model to understand the user's intent and identify relevant information. An example prompt might be, "The user is asking about recommended tourist spots in Kyoto." The server then queries the database to search for tourist spot information related to the user's question. For example, the search results might include information about Kyoto's most famous tourist spots, such as Kinkaku-ji Temple, Kiyomizu-dera Temple, and Fushimi Inari Taisha Shrine.

[0384] The server then references the user's past data and preferences, filtering this information to narrow down the recommendations to the most appropriate ones. After filtering, the server uses a generative AI model to generate detailed descriptions of each tourist spot and the reasons for the recommendation. For example, the server generates information such as, "Kinkaku-ji Temple has particularly beautiful architecture and allows you to feel the history of Japan. Visiting early in the morning will help you avoid the crowds."

[0385] Finally, the server converts the generated information into JSON format and sends it to the device as an HTTP response. The device parses the received JSON data, updates the appropriate GUI components, and displays them to the user. The user can then use the provided information to plan their trip.

[0386] Specific examples

[0387] For example, if a user asks, "How can I get around Kyoto city?", the server will go through a similar process to provide information on appropriate transportation options. This includes information on the convenience of city buses, how to use one-day passes, the convenience of trains and subways, and even bicycle rentals. An example prompt would be, "The user is asking about effective transportation options within Kyoto city."

[0388] In this way, the system of the present invention can provide information that meets the individual needs and preferences of each user.

[0389] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0390] Step 1:

[0391] The user inputs a travel-related question into the terminal. For example, "What are the recommended tourist spots in Kyoto?" The text is entered into the input field, and this text data is used as input for subsequent processing.

[0392] Step 2:

[0393] The terminal receives a question from the user and sends it to the server as an HTTP POST request. The input is the user's question text, and the output is the HTTP request.

[0394] Step 3:

[0395] The server analyzes the received question. This question text is passed to a natural language processing (NLP) module. The input is the user's question text, and the output is the analyzed keywords. Specifically, the question text is tokenized to extract keywords. Keywords such as "Kyoto," "recommended," and "tourist spots" are extracted.

[0396] Step 4:

[0397] The server sends a prompt to the generative AI model based on the extracted keywords. The input is the extracted keywords, and the output is related information that understands the user's intent. An example of a prompt is, "The user is asking about recommended tourist spots in Kyoto."

[0398] Step 5:

[0399] The server issues a query to the database to search for relevant tourist spot information. The input is a prompt statement and a query to the database, and the output is tourist spot information as a search result. An example is "SELECT FROM tourist spot WHERE location = 'Kyoto' AND recommended = 1".

[0400] Step 6:

[0401] The server filters the search results, narrowing down the optimal results based on the user's past data and preferences. The input is the search results and the user's past data, and the output is the filtered tourist spot information.

[0402] Step 7:

[0403] The server uses a generative AI model to generate detailed descriptions based on the filtered tourist spot information. The input is the filtered tourist spot information, and the output is the generated detailed description. The generated sentence might be something like, "Kinkaku-ji Temple is a particularly beautiful piece of architecture, and you can really feel the history of Japan. If you visit early in the morning, you can avoid the crowds."

[0404] Step 8:

[0405] The server converts the generated information into JSON format and sends it to the terminal as an HTTP response. The input is the generated description, and the output is JSON format data.

[0406] Step 9:

[0407] The device parses the received JSON data, updates the GUI components, and displays them to the user. The input is JSON data, and the output is the information displayed on the user's screen. The user uses the provided information to plan their trip.

[0408] In this way, specific data processing and data calculations are performed at each step, and the input for the next step is generated based on the results.

[0409] (Application example 1)

[0410] 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."

[0411] Conventional travel guide systems were unable to meet the diverse needs of users and had difficulty providing information in real time. This made it difficult for tourists to efficiently obtain information while traveling and plan trips that suited their preferences. Furthermore, there was a lack of systems that utilized voice input or smart devices, making them less convenient.

[0412] 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.

[0413] In this invention, the server includes means for accepting a user's question, means for analyzing the question, means for searching for related information based on the analysis result, means for filtering the search results based on the user's preferences, means for generating and providing the filtered information, means for displaying the provided information to the user, means for accepting a voice input, means for recognizing the voice input and converting it into text data, and means for displaying or outputting the text on the smart device. This allows the user to input a question using voice, and the answer to the question can be displayed or output as text on the smart device in real time.

[0414] The "means for accepting user questions" is an interface that allows the user to input questions about travel in voice or text format.

[0415] The "means for analyzing the question content" is a system that uses natural language processing technology to analyze the question entered by the user and extract key keywords and intent.

[0416] The "means for searching for related information based on the analysis results" is a system that searches databases and external information sources to obtain related information based on the analyzed question content.

[0417] "Means for filtering search results based on user preferences" refers to a system that scrutinizes acquired information based on the user's past preferences and behavioral data, and selects the information that is deemed most appropriate.

[0418] The "means for generating and providing filtered information" is a system for converting selected information into a form that is easy for users to understand and providing it in text or audio.

[0419] The "means for displaying the provided information to the user" is a system that displays the generated information visually or audibly on the user's terminal.

[0420] The "means for accepting voice input" is an interface that receives questions input by voice from the user through a device such as a microphone.

[0421] "Means for recognizing voice input and converting it into text data" refers to a system that uses voice recognition technology to analyze the voice input by the user and convert it into text data.

[0422] "Means for displaying or outputting audio on a smart device" refers to a system for displaying the generated information on a device such as a smartphone or smart glasses, or outputting it as audio.

[0423] To implement this invention, several steps are required. First, a smart device (e.g., smart glasses) is used as a means for accepting user questions. The user inputs questions by voice through this device. For example, a question such as "What are the recommended tourist spots in Kyoto?" can be input by voice.

[0424] Smart devices have a means of recognizing voice input and converting it into text data. This is done using the speech_recognition library. This recognized text data is sent directly to the server, where it is analyzed.

[0425] The server has the means to analyze the question, using natural language processing techniques (e.g., the "question answering" model from the transformers library). After analyzing the question, the server searches for relevant information based on the analysis results from a database, which is pre-populated with travel information.

[0426] The searched information is filtered using the user's past data (preferences and behavioral history). This filtering selects the information most appropriate for the user. The server then uses a generative AI model to generate detailed explanatory text from the filtered information to provide to the user. For example, information such as "Kinkaku-ji Temple is a particularly beautiful piece of architecture, and is a place where you can feel the history of Japan. Visiting early in the morning will help you avoid the crowds."

[0427] The generated information is displayed on the smart device or output as audio, utilizing the device's standard interface, allowing users to obtain the tourist information they need in real time, facilitating decision-making during their trip.

[0428] For example, if a user asks, "How can I get around Kyoto?", the server might provide information like this: "City buses are very convenient, and you can save money by using a one-day pass. JR and subways are also efficient ways to get around. We also recommend renting a bicycle to tour around Kyoto's tourist attractions."

[0429] Examples of prompts are:

[0430] User dictates: "What are some recommended places to eat in Kyoto?"

[0431] The system responds: "We particularly recommend Japanese restaurants such as Gion Sasagi in Gion and Arashiyama Yoshimura in Arashiyama. Each offers distinctive cuisine and stunning views."

[0432] In this way, the system of the present invention can provide real-time travel guide information that meets the diverse needs of users.

[0433] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0434] Step 1:

[0435] The user starts voice input. The user speaks a question into the smart device (e.g., smart glasses) (e.g., "What are the recommended tourist spots in Kyoto?"). This voice data is input.

[0436] Step 2:

[0437] The device receives the voice data and performs speech recognition. Specifically, it converts the voice data into text data using the speech_recognition library. The converted text data is generated (e.g., "What are the recommended tourist spots in Kyoto?").

[0438] Step 3:

[0439] The terminal transmits the generated text data to the server, which receives the text data.

[0440] Step 4:

[0441] The server analyzes the question, performs natural language processing using the transformers library, and extracts key keywords (e.g., "Kyoto," "recommended," "tourist spots") as the analysis results.

[0442] Step 5:

[0443] The server searches for relevant information based on the analysis results. It obtains data on "Kyoto tourist spots" from internal databases and external information sources. The obtained data is generated (e.g., "Kinkaku-ji Temple," "Kiyomizu-dera Temple," "Fushimi Inari Taisha Shrine").

[0444] Step 6:

[0445] The server filters the search results based on the user's preferences, referencing the user's past preferences and behavioral history to select the most relevant information, and the filtered data is generated.

[0446] Step 7:

[0447] The server uses a generative AI model to generate detailed explanatory text based on the filtered information, using prompts (e.g., "Kinkaku-ji Temple is a particularly beautiful building, and you can feel the history of Japan. Visiting it early in the morning will help you avoid the crowds.").

[0448] Step 8:

[0449] The terminal displays or outputs the provided information as audio, and displays the generated text on the smart device's display or outputs it as audio through the speaker.

[0450] This series of processes allows the user to perform voice input and obtain customized travel guide information in real time as a result.

[0451] 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.

[0452] This invention relates to a system for improving the efficiency of travel planning and providing a fulfilling travel experience to users. This system not only analyzes questions entered by users and provides relevant information based on the analysis results, but also recognizes the user's emotions and customizes the content and presentation of information based on those emotions to provide a more personalized travel guide.

[0453] First, the user inputs a travel-related question into the device. For example, if the user inputs a question such as "What are the recommended tourist spots in Kyoto?", the device receives the question and then an emotion engine analyzes the user's emotional state from the input text and voice.

[0454] The device sends the user's question along with emotion data to the server. The server then uses natural language processing to analyze the question. Specifically, it tokenizes the question and extracts keywords. In this case, the keywords extracted are "Kyoto," "recommended," and "tourist spot." The server then uses a generative AI model to understand the user's intent and identify relevant information.

[0455] The server then queries the database to find tourist spot information related to the user's question. The search results include famous tourist spots in Kyoto, such as Kinkaku-ji Temple, Kiyomizu-dera Temple, and Fushimi Inari Taisha Shrine. The server then references the user's past data, preference information, and emotional data, and filters this information to narrow down the recommendations that are most suitable for the user.

[0456] After filtering, the server uses a generative AI model to generate detailed descriptions of each tourist spot and the reasons for its recommendation. For example, if the user is surprised or excited, the server generates more positive and emotional content, such as "Kinkaku-ji Temple is a particularly beautiful piece of architecture, and you can feel the history of Japan."

[0457] Finally, the server converts the generated information into a data structure such as JSON and sends it to the device as an HTTP response. The device then analyzes the received information, updates the GUI components, and displays them to the user. For example, a user who is surprised or excited could be shown a visually appealing image or video.

[0458] For example, if a user asks, "How do I get around Kyoto City?" and the emotion engine recognizes that the user is confused, the server will go through a similar process to provide information on appropriate transportation options. For example, it will provide detailed information on the convenience of city buses, how to use one-day passes, the convenience of JR and subways, and even how to rent a bicycle. Confused users will be provided with particularly clear and specific guidance.

[0459] In this way, the system of the present invention, which combines an emotion engine, analyzes the content of the user's question, searches, filters, and generates related information, and ultimately provides information customized according to the user's emotions, thereby realizing a more personalized travel guide.

[0460] The processing flow will be explained below.

[0461] Step 1:

[0462] The user inputs a travel-related question into the terminal. Specifically, the user inputs the text "What are the recommended tourist spots in Kyoto?"

[0463] Step 2:

[0464] The device receives the input question, and an emotion engine analyzes the text to determine the user's emotions, such as whether the user is surprised or happy.

[0465] Step 3:

[0466] The device sends the question and the recognized emotion data to the server, which converts the data into a data structure such as JSON.

[0467] Step 4:

[0468] The server receives the question content and emotion data sent from the terminal and starts the process of analyzing the question content.

[0469] Step 5:

[0470] The server uses natural language processing to tokenize the question and extract keywords, such as "Kyoto," "recommended," and "tourist spots."

[0471] Step 6:

[0472] The server uses a generative AI model to identify the type of information sought from the user's question based on the extracted keywords and understand the intent.

[0473] Step 7:

[0474] The server queries the database to find tourist spots related to the user's question, and the search results include "Kinkaku-ji Temple," "Kiyomizu-dera Temple," and "Fushimi Inari Taisha Shrine."

[0475] Step 8:

[0476] The server uses a generative AI model to filter the acquired tourist spot information based on the user's past preference data and recognized emotional data, thereby providing more optimistic content to users in a positive emotional state, for example.

[0477] Step 9:

[0478] Based on the filtered information, the server uses a generative AI model to generate detailed explanations and reasons for the recommendation in text format. For example, if the emotion engine recognizes the user's emotion of surprise, it will generate content that touches on the user's emotion, such as "Kinkaku-ji Temple is a particularly beautiful piece of architecture, and you can feel the history of Japan."

[0479] Step 10:

[0480] The server converts the generated information into a data structure such as JSON format and sends it to the terminal as an HTTP response.

[0481] Step 11:

[0482] The device analyzes the HTTP response received from the server, updates the GUI components, and displays them to the user. For example, it may also display emotive images or videos.

[0483] Step 12:

[0484] The user refers to the provided information and makes travel plans. If the user has further questions, they return to step 1 and enter new questions.

[0485] For example, if a user asks, "How do I get around Kyoto City?" and the emotion engine recognizes the user's confusion, the server will provide detailed information on appropriate transportation methods, such as how to use city buses, how to purchase one-day passes, and the convenience of JR and subways, providing easy-to-understand visual guidance.

[0486] Example 2

[0487] 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."

[0488] Conventional travel guide systems simply provide information in response to user questions, and are insufficient in providing personalized information that reflects the user's emotional state or individual preferences. As a result, it is difficult for users to create satisfying travel plans. Furthermore, when a large number of search results are returned, it is difficult for users to narrow down the specific information they need, which requires time and effort.

[0489] 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.

[0490] In this invention, the server includes a means for analyzing the user's emotional state along with the user's question, a means for searching for related information based on the user's question and emotional state, and a means for generating and providing filtered information using a generative AI model. This makes it possible to provide customized information based on the user's emotional state and past preferences, allowing the user to make more satisfying travel plans.

[0491] "Means for accepting user questions" refers to a function for receiving travel-related questions that users input into the system.

[0492] "Means for analyzing the user's emotional state" refers to a function for analyzing the user's emotional state (for example, excitement, confusion, etc.) from questions or voice data entered by the user.

[0493] "Means for searching related information" refers to the function of searching for related information from databases or the Internet based on the user's question and emotional state.

[0494] "Filtering means" refers to the function of narrowing down searched information based on the user's past data and preference information, and selecting the most appropriate information.

[0495] "Means of providing information using a generative AI model" refers to the function of using AI technology to generate specific, customized information desired by the user and provide it to the user.

[0496] "Natural language processing means" refers to technology that analyzes questions entered by users and extracts important keywords.

[0497] "Means for generating prompt sentences" refers to the function of creating appropriate input sentences for the generative AI model.

[0498] This invention relates to a system for improving the efficiency of travel planning and providing a fulfilling travel experience to users. This system not only analyzes questions entered by users and provides relevant information based on the analysis results, but also recognizes the user's emotions and customizes the content and presentation of information based on those emotions to provide a more personalized travel guide.

[0499] First, the user inputs a travel-related question into the device. For example, if the user inputs a question such as "What are the recommended tourist spots in Kyoto?", the device receives the question and then an emotion engine analyzes the user's emotional state from the input text and voice.

[0500] The device sends the user's question along with emotion data to the server. The server then uses natural language processing to analyze the question. Specifically, it tokenizes the question and extracts keywords. In this case, the keywords extracted are "Kyoto," "recommended," and "tourist spot." The server then uses a generative AI model to understand the user's intent and identify relevant information.

[0501] The server then queries the database to find tourist spot information related to the user's question. The search results include famous tourist spots in Kyoto, such as Kinkaku-ji Temple, Kiyomizu-dera Temple, and Fushimi Inari Taisha Shrine. The server then references the user's past data, preference information, and emotional data, and filters this information to narrow down the recommendations that are most suitable for the user.

[0502] After filtering, the server uses a generative AI model to generate detailed descriptions of each tourist spot and the reasons for its recommendation. For example, if the user is surprised or excited, the server generates more positive and emotional content, such as "Kinkaku-ji Temple is a particularly beautiful piece of architecture, and you can feel the history of Japan."

[0503] Finally, the server converts the generated information into a data structure such as JSON and sends it to the device as an HTTP response. The device then analyzes the received information, updates the GUI components, and displays them to the user. For example, a user who is surprised or excited could be shown a visually appealing image or video.

[0504] For example, if a user asks, "How do I get around Kyoto City?" and the emotion engine recognizes that the user is confused, the server will go through a similar process to provide information on appropriate transportation options. For example, it will provide detailed information on the convenience of city buses, how to use one-day passes, the convenience of JR and subways, and even how to rent a bicycle. Confused users will be provided with particularly clear and specific guidance.

[0505] In this way, the system of the present invention, which combines an emotion engine, analyzes the content of the user's question, searches, filters, and generates related information, and ultimately provides information customized according to the user's emotions, thereby realizing a more personalized travel guide.

[0506] Examples of prompts might include: "The user asked about tourist attractions in Kyoto. The user seems excited. How would you respond?" or "The user asked about transportation options within Kyoto. The user seems confused. Please provide a clear answer."

[0507] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0508] Step 1:

[0509] The user inputs a travel question into the terminal.

[0510] Specific operation: The user enters "What are the recommended tourist spots in Kyoto?" into the input field on the device.

[0511] Input: User question text

[0512] Output: The question text is typed into the terminal.

[0513] Step 2:

[0514] The terminal analyzes the input question text and uses an emotion engine to analyze the user's emotional state.

[0515] Specific operation: The device's emotion engine analyzes the text and extracts emotional states such as "excitement" or "confusion."

[0516] Input: Question text

[0517] Output: Emotion data (e.g. excited)

[0518] Step 3:

[0519] The device sends the question text and emotion data to the server.

[0520] Specific operation: The device uses an HTTP request to send the user's question, "What are the recommended tourist spots in Kyoto?" and emotion data to the server.

[0521] Input: Question text, emotion data

[0522] Output: HTTP request to the server

[0523] Step 4:

[0524] The server analyzes the received question text and extracts keywords using natural language processing means.

[0525] Specific operation: The server uses an NLP library (e.g., NLTK or SpaCy) to tokenize the question and extract keywords. The keywords obtained are "Kyoto," "recommended," and "tourist spot."

[0526] Input: Question text

[0527] Output: Extracted keywords

[0528] Step 5:

[0529] The server inputs prompts into the generative AI model to understand the user's intent and identify relevant information.

[0530] Specific operation: The server inputs a prompt to the generative AI model (e.g., GPT-3): "The user asked about recommended tourist spots in Kyoto. The user is excited. How would you respond?" The generative AI model generates related information such as "Kinkaku-ji Temple," "Kiyomizu-dera Temple," and "Fushimi Inari Taisha Shrine."

[0531] Input: Extracted keywords, prompt sentence

[0532] Output: Related information generated

[0533] Step 6:

[0534] The server queries the database to find the relevant information.

[0535] Specific operation: The server executes a database query to retrieve tourist spot information that matches the keywords: "Kinkaku-ji Temple," "Kiyomizu-dera Temple," and "Fushimi Inari Taisha Shrine."

[0536] Input: Generated related information

[0537] Output: Tourist spot information retrieved from the database

[0538] Step 7:

[0539] The server filters information based on the user's past data, preference information, and emotional data.

[0540] Specific operation: The server compares the user's past search history and preferences to select the most suitable tourist spot. For example, it determines that Kinkaku-ji Temple is the most suitable for the user's preferences.

[0541] Input: Tourist spot information obtained from the database, user's past data, preference information, emotional data

[0542] Output: Filtered tourist spot information

[0543] Step 8:

[0544] The server uses a generative AI model to generate detailed explanations and recommendations based on the filtered information.

[0545] Specific behavior: The generative AI model generates a detailed description that reads, "Kinkaku-ji is a particularly beautiful piece of architecture, and you can feel the history of Japan."

[0546] Input: Filtered tourist spot information

[0547] Output: Detailed description generated

[0548] Step 9:

[0549] The server converts the generated information into a data structure such as JSON format and sends it to the terminal as an HTTP response.

[0550] Specific operation: The information generated by the server is converted into JSON data and sent to the terminal via an HTTP response.

[0551] Input: Generated detailed description

[0552] Output: HTTP response to the device

[0553] Step 10:

[0554] The terminal analyzes the received information, updates the GUI components, and displays them to the user.

[0555] What it does: The device parses the JSON data and displays the information in a GUI with visually appealing images and videos, using particularly positive language for excited users.

[0556] Input: HTTP response to the terminal

[0557] Output: Updated GUI display

[0558] (Application example 2)

[0559] 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."

[0560] While conventional travel guide systems can provide general information in response to user questions, they have difficulty providing personalized information based on the user's emotional state or individual preferences. Furthermore, there is a lack of interactive methods for obtaining necessary information in real time during travel, which has resulted in a lack of sufficient improvement in the user experience.

[0561] 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 accepting a user's question, means for analyzing the content of the question, means for searching for related information based on the analysis result, means for filtering the search results based on the user's preferences, means for generating and providing the filtered information, means for displaying the provided information to the user, and means for analyzing emotions. This makes it possible to provide a personalized travel guide in real time according to the user's emotional state.

[0562] The "means for accepting user questions" is an interface through which users input questions about travel, and is a device or software that accepts questions by text or voice.

[0563] The "means for analyzing the question content" is a device or software that analyzes the question entered by the user and extracts the intent of the question and key keywords.

[0564] The "means for searching for related information" is a device or software that searches for related information from a database or the Internet based on the analyzed question content.

[0565] A "means for filtering based on user preferences" is a device or software that selects the most appropriate information from search results based on the user's past behavior and preference data.

[0566] The "means for generating and providing filtered information" refers to a device or software that automatically generates text such as an explanation or a reason for recommendation in order to provide the filtered information to the user.

[0567] The "means for displaying the provided information to the user" is a device or software for visually displaying the generated information on the user's terminal.

[0568] The "emotion analysis means" is a device or software that analyzes the user's emotional state based on the content of the user's questions and past behavioral data, and customizes the information provided based on the results.

[0569] This invention is a system that allows users to input travel-related questions and provides personalized information based on the content of the question and the user's emotional state. The system aims to improve the user experience by providing an efficient means for users to obtain necessary information in real time while traveling.

[0570] 1. Hardware and Software Used

[0571] The main hardware required to implement this system includes the device used by the user (e.g., smartphone, head-mounted display, etc.) and the server. The main software used includes a natural language processing engine (e.g., spaCy), a sentiment analysis engine (e.g., AWS Comprehend, Hugging Face Transformers), and a Web API server (e.g., Flask, Django). Information is also generated using a generative AI model.

[0572] 2. System Operation Overview

[0573] A user inputs a travel-related question into a terminal. For example, if a question is input such as "What are the recommended tourist spots in Kyoto?", the terminal receives this question. The emotion analysis means analyzes the user's emotional state from the input text and sends the obtained emotion data to the server. The server performs processing in the following steps based on the received question content and emotion data.

[0574] Question analysis: The question is tokenized and keywords are extracted. For example, keywords such as "Kyoto," "recommended," and "tourist spots" are extracted.

[0575] Information retrieval: The server uses a generative AI model to understand the user's intent and identify relevant information, then queries the database to retrieve tourist spot information.

[0576] Information filtering: Search results are filtered to provide the most relevant recommendations to the user based on their past data, preferences, and emotional data.

[0577] Information generation and display: The filtered information is generated as text using a generative AI model. This information is converted into a data structure such as JSON and sent to the device as an HTTP response. The device analyzes the received information, updates the GUI components, and displays it to the user.

[0578] 3. Examples and prompts

[0579] For example, if a user asks, "How do I get around Kyoto City?" and the sentiment analysis tool detects that the user is confused, the server will go through a similar process to provide information on appropriate transportation options. For example, detailed explanations on the convenience of city buses, how to use one-day passes, the convenience of JR and subways, and even how to rent a bicycle are provided. Confused users will be provided with particularly clear and specific guidance.

[0580] Prompt Sentence Examples

[0581] "Please tell me about some beautiful gardens in Kyoto. I am always amazed when I see my favorite scenery."

[0582] This system provides users with real-time travel guides tailored to their emotional state, making the virtual travel experience more personalized.

[0583] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0584] Step 1:

[0585] The user inputs a question into the terminal. For example, the user inputs "What are the recommended tourist spots in Kyoto?" The terminal receives this question and sends it to the sentiment analysis means. The input is the user's question, and the output is text data that is passed to the sentiment analysis.

[0586] Step 2:

[0587] An emotion analysis means installed on the device analyzes the user's emotional state from the input text data. An emotion analysis engine (e.g., AWS Comprehend) analyzes the text and detects emotional states such as "surprise" or "excitement." The input is the user's question, and the output is the detected emotional data. The device then sends this emotional data to a server.

[0588] Step 3:

[0589] The server receives the emotion data and the question. It then uses a natural language processing engine (e.g., spaCy) to analyze the question. It tokenizes the question and extracts key keywords. For example, it extracts keywords such as "Kyoto," "recommended," and "tourist spots." The input is the question and emotion data, and the output is the extracted keywords.

[0590] Step 4:

[0591] The server uses a generative AI model to understand the user's intent and identify relevant information. Based on the extracted keywords, the generative AI model infers the user's intent. The input is the extracted keywords, and the output is the inferred result of the user's intent.

[0592] Step 5:

[0593] The server queries the database to retrieve information about related tourist spots. For example, it retrieves information about "Kinkaku-ji Temple," "Kiyomizu-dera Temple," and "Fushimi Inari Taisha Shrine." The input is the result of inferring the user's intention, and the output is the retrieved tourist spot information.

[0594] Step 6:

[0595] The server filters the search results based on the user's preferences. This filtering refers to the user's past data and preference information to select the most suitable spots. For example, it may select based on places and activities that the user has shown interest in in the past. The input is the search results, and the output is the filtered tourist spot information.

[0596] Step 7:

[0597] The server uses a generative AI model to generate explanatory text based on the filtered information. It also takes into account the user's emotional data to generate text that appeals to the user's emotions. For example, it generates the sentence, "Kinkaku-ji Temple is a particularly beautiful piece of architecture, and you can feel the history of Japan." The input is the filtered information and emotional data, and the output is the generated explanatory text.

[0598] Step 8:

[0599] The server converts the generated information into a data structure such as JSON and sends it to the terminal as an HTTP response. The input is the generated description, and the output is the data sent as the HTTP response.

[0600] Step 9:

[0601] The device analyzes the information it receives and updates GUI components to visually display it to the user, for example displaying generated explanatory text along with attractive images or videos. The input is the data received as an HTTP response, and the output is the visual information displayed to the user.

[0602] Through this step, users can get real-time travel guide information that is personalized according to their emotional state.

[0603] 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.

[0604] 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.

[0605] 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.

[0606] [Third embodiment]

[0607] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0608] 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.

[0609] 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).

[0610] 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.

[0611] 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.

[0612] 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).

[0613] 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.

[0614] 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.

[0615] 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.

[0616] 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.

[0617] 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.

[0618] 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."

[0619] The present invention relates to a system for streamlining travel planning and providing a fulfilling travel experience to users. This system analyzes questions entered by users and provides relevant information based on the analysis results to generate a travel guide customized to the user's needs.

[0620] First, the user inputs a travel-related question into the terminal. For example, if the user inputs a question such as "What are the recommended tourist spots in Kyoto?", the terminal receives the question and sends it to the server.

[0621] The server analyzes the question using natural language processing. Specifically, it tokenizes the question and extracts keywords. In this example, the keywords extracted are "Kyoto," "recommended," and "tourist spots." The server then uses a generative AI model to understand the user's intent and identify relevant information.

[0622] The server then queries the database to find tourist spot information related to the user's question. The search results include famous tourist spots in Kyoto, such as Kinkaku-ji Temple, Kiyomizu-dera Temple, and Fushimi Inari Taisha Shrine. The server then references the user's past data and preference information, filtering this information to narrow down the recommendations that are most suitable for the user.

[0623] After filtering, the server uses a generative AI model to generate detailed descriptions of each tourist spot and the reasons for its recommendation. For example, it generates information like, "Kinkaku-ji Temple is an especially beautiful piece of architecture, and you can really feel the history of Japan. Visiting early in the morning will help you avoid the crowds."

[0624] Finally, the server converts the generated information into a data structure such as JSON format and sends it to the device as an HTTP response. The device analyzes the received information, updates the GUI components, and displays them to the user. The user can then use the provided information to plan their trip.

[0625] For example, if a user asks, "How can I get around Kyoto city?", the server will go through a similar process to provide information on appropriate transportation options, such as the convenience of city buses, how to use one-day passes, the convenience of JR and subways, and even bicycle rentals.

[0626] In this way, the system of the present invention provides an efficient and accurate travel guide by including a series of processes that analyze the content of the user's question, search, filter, and generate relevant information, and finally provide it to the user.

[0627] The processing flow will be explained below.

[0628] Step 1:

[0629] The user inputs a travel-related question into the terminal. Specifically, for example, the text "What are the recommended tourist spots in Kyoto?" is input.

[0630] Step 2:

[0631] The device receives the input question and prepares an HTTP request to send to the server, converting the question content into a data structure such as JSON.

[0632] Step 3:

[0633] The server receives the HTTP request sent from the terminal and begins the process of analyzing the question.

[0634] Step 4:

[0635] The server uses natural language processing to tokenize the question and extract keywords, such as "Kyoto," "recommended," and "tourist spots."

[0636] Step 5:

[0637] The server inputs the analyzed keywords and question content into a generative AI model to understand the user's intent. This generative AI model then identifies the type of information desired from the user's question.

[0638] Step 6:

[0639] The server generates a query in the database to search for tourist spot information related to the query. The search query includes the extracted keywords.

[0640] Step 7:

[0641] The server receives the search results retrieved from the database and uses a generative AI model to filter them based on the user's preferences and past tastes, for example, by looking at past search history and user profiles.

[0642] Step 8:

[0643] The server generates detailed explanations and reasons for recommendations based on the filtered information. The generative AI model converts this into text. For example, it generates information such as, "Kinkaku-ji Temple is a particularly beautiful piece of architecture, and you can feel the history of Japan."

[0644] Step 9:

[0645] The server converts the generated information into a data structure such as JSON format and sends it to the terminal as an HTTP response.

[0646] Step 10:

[0647] The terminal analyzes the HTTP response received from the server and performs processing to display it on the user interface.

[0648] Step 11:

[0649] The terminal displays the generated information to the user, for example, detailed information about Kinkaku-ji Temple, Kiyomizu-dera Temple, and Fushimi Inari Taisha Shrine.

[0650] Step 12:

[0651] The user consults the provided information and plans their trip, entering further questions as needed and returning to step 1.

[0652] Example 1

[0653] 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."

[0654] Conventional travel guide systems have the problem that when users input travel-related questions, the information provided is general, making it difficult to respond to individual user needs and preferences.In addition, the information is not sufficiently filtered or customized, making it difficult to provide the information users truly want.

[0655] 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.

[0656] In this invention, the server includes means for accepting a user's question, means for performing natural language processing to analyze the content of the question, means for identifying related information using a generative AI model based on the analysis results, means for searching a database for the identified related information, means for filtering search results based on the user's preferences, means for generating and providing the filtered information, and means for displaying the provided information to the user, thereby enabling the provision of information that meets the individual needs and preferences of the user.

[0657] A "user question" is text data that a user inputs into a terminal to obtain information about a trip in which the user is interested.

[0658] "Natural language processing" is a technology that analyzes text data entered by a user and performs keyword extraction and grammatical analysis.

[0659] A "generative AI model" is an algorithm that uses artificial intelligence to understand a user's intent and generate appropriate answers to questions.

[0660] A "database" is a storage device that stores information on tourist spots, transportation options, and the like.

[0661] "Filtering" is the process of selecting information from search results that matches the user's preferences.

[0662] "Information generation" is the process of creating specific answers to provide to users based on the filtered data.

[0663] "Providing information" is the process of presenting the generated answers to the user in an easy-to-understand format.

[0664] "Display" refers to the act of visually showing the generated answer on the user's terminal screen.

[0665] "Past user data" refers to records relating to questions and preferences previously entered by a user, information that is used to generate customized answers.

[0666] MODE FOR CARRYING OUT THE INVENTION

[0667] The present invention relates to a system for improving the efficiency of users' travel planning and providing a fulfilling travel experience, which accepts and analyzes user questions, searches, filters, generates related information, and provides it to users. Specific embodiments of the system are described below.

[0668] Hardware and Software Configuration

[0669] This system consists of a terminal where users can input travel-related questions, a server for analyzing the questions and generating information, and a database.

[0670] Terminal: Users access the system using a terminal such as a smartphone, tablet, or PC. The terminal is equipped with an input interface (e.g., touchscreen, keyboard).

[0671] Server: The server contains a natural language processing (NLP) module, a generative AI model, and a database access module to analyze user questions, identify relevant information, and generate it.

[0672] Database: Contains information on tourist attractions, transportation options, etc.

[0673] Program processing

[0674] A user inputs a travel-related question into a device. For example, if a question is input such as "What are the recommended tourist spots in Kyoto?", the device receives the question and sends it to the server as an HTTP POST request. The server receives the question and analyzes it using a natural language processing module. During the analysis, the question is tokenized and keywords are extracted. For example, the keywords "Kyoto," "recommended," and "tourist spots" are extracted.

[0675] The server then uses a generative AI model to understand the user's intent and identify relevant information. An example prompt might be, "The user is asking about recommended tourist spots in Kyoto." The server then queries the database to search for tourist spot information related to the user's question. For example, the search results might include information about Kyoto's most famous tourist spots, such as Kinkaku-ji Temple, Kiyomizu-dera Temple, and Fushimi Inari Taisha Shrine.

[0676] The server then references the user's past data and preferences, filtering this information to narrow down the recommendations to the most appropriate ones. After filtering, the server uses a generative AI model to generate detailed descriptions of each tourist spot and the reasons for the recommendation. For example, the server generates information such as, "Kinkaku-ji Temple has particularly beautiful architecture and allows you to feel the history of Japan. Visiting early in the morning will help you avoid the crowds."

[0677] Finally, the server converts the generated information into JSON format and sends it to the device as an HTTP response. The device parses the received JSON data, updates the appropriate GUI components, and displays them to the user. The user can then use the provided information to plan their trip.

[0678] Specific examples

[0679] For example, if a user asks, "How can I get around Kyoto city?", the server will go through a similar process to provide information on appropriate transportation options. This includes information on the convenience of city buses, how to use one-day passes, the convenience of trains and subways, and even bicycle rentals. An example prompt would be, "The user is asking about effective transportation options within Kyoto city."

[0680] In this way, the system of the present invention can provide information that meets the individual needs and preferences of each user.

[0681] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0682] Step 1:

[0683] The user inputs a travel-related question into the terminal. For example, "What are the recommended tourist spots in Kyoto?" The text is entered into the input field, and this text data is used as input for subsequent processing.

[0684] Step 2:

[0685] The terminal receives a question from the user and sends it to the server as an HTTP POST request. The input is the user's question text, and the output is the HTTP request.

[0686] Step 3:

[0687] The server analyzes the received question. This question text is passed to a natural language processing (NLP) module. The input is the user's question text, and the output is the analyzed keywords. Specifically, the question text is tokenized to extract keywords. Keywords such as "Kyoto," "recommended," and "tourist spots" are extracted.

[0688] Step 4:

[0689] The server sends a prompt to the generative AI model based on the extracted keywords. The input is the extracted keywords, and the output is related information that understands the user's intent. An example of a prompt is, "The user is asking about recommended tourist spots in Kyoto."

[0690] Step 5:

[0691] The server issues a query to the database to search for relevant tourist spot information. The input is a prompt statement and a query to the database, and the output is tourist spot information as a search result. An example is "SELECT FROM tourist spot WHERE location = 'Kyoto' AND recommended = 1".

[0692] Step 6:

[0693] The server filters the search results, narrowing down the optimal results based on the user's past data and preferences. The input is the search results and the user's past data, and the output is the filtered tourist spot information.

[0694] Step 7:

[0695] The server uses a generative AI model to generate detailed descriptions based on the filtered tourist spot information. The input is the filtered tourist spot information, and the output is the generated detailed description. The generated sentence might be something like, "Kinkaku-ji Temple is a particularly beautiful piece of architecture, and you can really feel the history of Japan. If you visit early in the morning, you can avoid the crowds."

[0696] Step 8:

[0697] The server converts the generated information into JSON format and sends it to the terminal as an HTTP response. The input is the generated description, and the output is JSON format data.

[0698] Step 9:

[0699] The device parses the received JSON data, updates the GUI components, and displays them to the user. The input is JSON data, and the output is the information displayed on the user's screen. The user uses the provided information to plan their trip.

[0700] In this way, specific data processing and data calculations are performed at each step, and the input for the next step is generated based on the results.

[0701] (Application example 1)

[0702] 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."

[0703] Conventional travel guide systems were unable to meet the diverse needs of users and had difficulty providing information in real time. This made it difficult for tourists to efficiently obtain information while traveling and plan trips that suited their preferences. Furthermore, there was a lack of systems that utilized voice input or smart devices, making them less convenient.

[0704] 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.

[0705] In this invention, the server includes means for accepting a user's question, means for analyzing the question, means for searching for related information based on the analysis result, means for filtering the search results based on the user's preferences, means for generating and providing the filtered information, means for displaying the provided information to the user, means for accepting a voice input, means for recognizing the voice input and converting it into text data, and means for displaying or outputting the text on the smart device. This allows the user to input a question using voice, and the answer to the question can be displayed or output as text on the smart device in real time.

[0706] The "means for accepting user questions" is an interface that allows the user to input questions about travel in voice or text format.

[0707] The "means for analyzing the question content" is a system that uses natural language processing technology to analyze the question entered by the user and extract key keywords and intent.

[0708] The "means for searching for related information based on the analysis results" is a system that searches databases and external information sources to obtain related information based on the analyzed question content.

[0709] "Means for filtering search results based on user preferences" refers to a system that scrutinizes acquired information based on the user's past preferences and behavioral data, and selects the information that is deemed most appropriate.

[0710] The "means for generating and providing filtered information" is a system for converting selected information into a form that is easy for users to understand and providing it in text or audio.

[0711] The "means for displaying the provided information to the user" is a system that displays the generated information visually or audibly on the user's terminal.

[0712] The "means for accepting voice input" is an interface that receives questions input by voice from the user through a device such as a microphone.

[0713] "Means for recognizing voice input and converting it into text data" refers to a system that uses voice recognition technology to analyze the voice input by the user and convert it into text data.

[0714] "Means for displaying or outputting audio on a smart device" refers to a system for displaying the generated information on a device such as a smartphone or smart glasses, or outputting it as audio.

[0715] To implement this invention, several steps are required. First, a smart device (e.g., smart glasses) is used as a means for accepting user questions. The user inputs questions by voice through this device. For example, a question such as "What are the recommended tourist spots in Kyoto?" can be input by voice.

[0716] Smart devices have a means of recognizing voice input and converting it into text data. This is done using the speech_recognition library. This recognized text data is sent directly to the server, where it is analyzed.

[0717] The server has the means to analyze the question, using natural language processing techniques (e.g., the "question answering" model from the transformers library). After analyzing the question, the server searches for relevant information based on the analysis results from a database, which is pre-populated with travel information.

[0718] The searched information is filtered using the user's past data (preferences and behavioral history). This filtering selects the information most appropriate for the user. The server then uses a generative AI model to generate detailed explanatory text from the filtered information to provide to the user. For example, information such as "Kinkaku-ji Temple is a particularly beautiful piece of architecture, and is a place where you can feel the history of Japan. Visiting early in the morning will help you avoid the crowds."

[0719] The generated information is displayed on the smart device or output as audio, utilizing the device's standard interface, allowing users to obtain the tourist information they need in real time, facilitating decision-making during their trip.

[0720] For example, if a user asks, "How can I get around Kyoto?", the server might provide information like this: "City buses are very convenient, and you can save money by using a one-day pass. JR and subways are also efficient ways to get around. We also recommend renting a bicycle to tour around Kyoto's tourist attractions."

[0721] Examples of prompts are:

[0722] User dictates: "What are some recommended places to eat in Kyoto?"

[0723] The system responds: "We particularly recommend Japanese restaurants such as Gion Sasagi in Gion and Arashiyama Yoshimura in Arashiyama. Each offers distinctive cuisine and stunning views."

[0724] In this way, the system of the present invention can provide real-time travel guide information that meets the diverse needs of users.

[0725] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0726] Step 1:

[0727] The user starts voice input. The user speaks a question into the smart device (e.g., smart glasses) (e.g., "What are the recommended tourist spots in Kyoto?"). This voice data is input.

[0728] Step 2:

[0729] The device receives the voice data and performs speech recognition. Specifically, it converts the voice data into text data using the speech_recognition library. The converted text data is generated (e.g., "What are the recommended tourist spots in Kyoto?").

[0730] Step 3:

[0731] The terminal transmits the generated text data to the server, which receives the text data.

[0732] Step 4:

[0733] The server analyzes the question, performs natural language processing using the transformers library, and extracts key keywords (e.g., "Kyoto," "recommended," "tourist spots") as the analysis results.

[0734] Step 5:

[0735] The server searches for relevant information based on the analysis results. It obtains data on "Kyoto tourist spots" from internal databases and external information sources. The obtained data is generated (e.g., "Kinkaku-ji Temple," "Kiyomizu-dera Temple," "Fushimi Inari Taisha Shrine").

[0736] Step 6:

[0737] The server filters the search results based on the user's preferences, referencing the user's past preferences and behavioral history to select the most relevant information, and the filtered data is generated.

[0738] Step 7:

[0739] The server uses a generative AI model to generate detailed explanatory text based on the filtered information, using prompts (e.g., "Kinkaku-ji Temple is a particularly beautiful building, and you can feel the history of Japan. Visiting it early in the morning will help you avoid the crowds.").

[0740] Step 8:

[0741] The terminal displays or outputs the provided information as audio, and displays the generated text on the smart device's display or outputs it as audio through the speaker.

[0742] This series of processes allows the user to perform voice input and obtain customized travel guide information in real time as a result.

[0743] 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.

[0744] This invention relates to a system for improving the efficiency of travel planning and providing a fulfilling travel experience to users. This system not only analyzes questions entered by users and provides relevant information based on the analysis results, but also recognizes the user's emotions and customizes the content and presentation of information based on those emotions to provide a more personalized travel guide.

[0745] First, the user inputs a travel-related question into the device. For example, if the user inputs a question such as "What are the recommended tourist spots in Kyoto?", the device receives the question and then an emotion engine analyzes the user's emotional state from the input text and voice.

[0746] The device sends the user's question along with emotion data to the server. The server then uses natural language processing to analyze the question. Specifically, it tokenizes the question and extracts keywords. In this case, the keywords extracted are "Kyoto," "recommended," and "tourist spot." The server then uses a generative AI model to understand the user's intent and identify relevant information.

[0747] The server then queries the database to find tourist spot information related to the user's question. The search results include famous tourist spots in Kyoto, such as Kinkaku-ji Temple, Kiyomizu-dera Temple, and Fushimi Inari Taisha Shrine. The server then references the user's past data, preference information, and emotional data, and filters this information to narrow down the recommendations that are most suitable for the user.

[0748] After filtering, the server uses a generative AI model to generate detailed descriptions of each tourist spot and the reasons for its recommendation. For example, if the user is surprised or excited, the server generates more positive and emotional content, such as "Kinkaku-ji Temple is a particularly beautiful piece of architecture, and you can feel the history of Japan."

[0749] Finally, the server converts the generated information into a data structure such as JSON and sends it to the device as an HTTP response. The device then analyzes the received information, updates the GUI components, and displays them to the user. For example, a user who is surprised or excited could be shown a visually appealing image or video.

[0750] For example, if a user asks, "How do I get around Kyoto City?" and the emotion engine recognizes that the user is confused, the server will go through a similar process to provide information on appropriate transportation options. For example, it will provide detailed information on the convenience of city buses, how to use one-day passes, the convenience of JR and subways, and even how to rent a bicycle. Confused users will be provided with particularly clear and specific guidance.

[0751] In this way, the system of the present invention, which combines an emotion engine, analyzes the content of the user's question, searches, filters, and generates related information, and ultimately provides information customized according to the user's emotions, thereby realizing a more personalized travel guide.

[0752] The processing flow will be explained below.

[0753] Step 1:

[0754] The user inputs a travel-related question into the terminal. Specifically, the user inputs the text "What are the recommended tourist spots in Kyoto?"

[0755] Step 2:

[0756] The device receives the input question, and an emotion engine analyzes the text to determine the user's emotions, such as whether the user is surprised or happy.

[0757] Step 3:

[0758] The device sends the question and the recognized emotion data to the server, which converts the data into a data structure such as JSON.

[0759] Step 4:

[0760] The server receives the question content and emotion data sent from the terminal and starts the process of analyzing the question content.

[0761] Step 5:

[0762] The server uses natural language processing to tokenize the question and extract keywords, such as "Kyoto," "recommended," and "tourist spots."

[0763] Step 6:

[0764] The server uses a generative AI model to identify the type of information sought from the user's question based on the extracted keywords and understand the intent.

[0765] Step 7:

[0766] The server queries the database to find tourist spots related to the user's question, and the search results include "Kinkaku-ji Temple," "Kiyomizu-dera Temple," and "Fushimi Inari Taisha Shrine."

[0767] Step 8:

[0768] The server uses a generative AI model to filter the acquired tourist spot information based on the user's past preference data and recognized emotional data, thereby providing more optimistic content to users in a positive emotional state, for example.

[0769] Step 9:

[0770] Based on the filtered information, the server uses a generative AI model to generate detailed explanations and reasons for the recommendation in text format. For example, if the emotion engine recognizes the user's emotion of surprise, it will generate content that touches on the user's emotion, such as "Kinkaku-ji Temple is a particularly beautiful piece of architecture, and you can feel the history of Japan."

[0771] Step 10:

[0772] The server converts the generated information into a data structure such as JSON format and sends it to the terminal as an HTTP response.

[0773] Step 11:

[0774] The device analyzes the HTTP response received from the server, updates the GUI components, and displays them to the user. For example, it may also display emotive images or videos.

[0775] Step 12:

[0776] The user refers to the provided information and makes travel plans. If the user has further questions, they return to step 1 and enter new questions.

[0777] For example, if a user asks, "How do I get around Kyoto City?" and the emotion engine recognizes the user's confusion, the server will provide detailed information on appropriate transportation methods, such as how to use city buses, how to purchase one-day passes, and the convenience of JR and subways, providing easy-to-understand visual guidance.

[0778] Example 2

[0779] 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."

[0780] Conventional travel guide systems simply provide information in response to user questions, and are insufficient in providing personalized information that reflects the user's emotional state or individual preferences. As a result, it is difficult for users to create satisfying travel plans. Furthermore, when a large number of search results are returned, it is difficult for users to narrow down the specific information they need, which requires time and effort.

[0781] 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.

[0782] In this invention, the server includes a means for analyzing the user's emotional state along with the user's question, a means for searching for related information based on the user's question and emotional state, and a means for generating and providing filtered information using a generative AI model. This makes it possible to provide customized information based on the user's emotional state and past preferences, allowing the user to make more satisfying travel plans.

[0783] "Means for accepting user questions" refers to a function for receiving travel-related questions that users input into the system.

[0784] "Means for analyzing the user's emotional state" refers to a function for analyzing the user's emotional state (for example, excitement, confusion, etc.) from questions or voice data entered by the user.

[0785] "Means for searching related information" refers to the function of searching for related information from databases or the Internet based on the user's question and emotional state.

[0786] "Filtering means" refers to the function of narrowing down searched information based on the user's past data and preference information, and selecting the most appropriate information.

[0787] "Means of providing information using a generative AI model" refers to the function of using AI technology to generate specific, customized information desired by the user and provide it to the user.

[0788] "Natural language processing means" refers to technology that analyzes questions entered by users and extracts important keywords.

[0789] "Means for generating prompt sentences" refers to the function of creating appropriate input sentences for the generative AI model.

[0790] This invention relates to a system for improving the efficiency of travel planning and providing a fulfilling travel experience to users. This system not only analyzes questions entered by users and provides relevant information based on the analysis results, but also recognizes the user's emotions and customizes the content and presentation of information based on those emotions to provide a more personalized travel guide.

[0791] First, the user inputs a travel-related question into the device. For example, if the user inputs a question such as "What are the recommended tourist spots in Kyoto?", the device receives the question and then an emotion engine analyzes the user's emotional state from the input text and voice.

[0792] The device sends the user's question along with emotion data to the server. The server then uses natural language processing to analyze the question. Specifically, it tokenizes the question and extracts keywords. In this case, the keywords extracted are "Kyoto," "recommended," and "tourist spot." The server then uses a generative AI model to understand the user's intent and identify relevant information.

[0793] The server then queries the database to find tourist spot information related to the user's question. The search results include famous tourist spots in Kyoto, such as Kinkaku-ji Temple, Kiyomizu-dera Temple, and Fushimi Inari Taisha Shrine. The server then references the user's past data, preference information, and emotional data, and filters this information to narrow down the recommendations that are most suitable for the user.

[0794] After filtering, the server uses a generative AI model to generate detailed descriptions of each tourist spot and the reasons for its recommendation. For example, if the user is surprised or excited, the server generates more positive and emotional content, such as "Kinkaku-ji Temple is a particularly beautiful piece of architecture, and you can feel the history of Japan."

[0795] Finally, the server converts the generated information into a data structure such as JSON and sends it to the device as an HTTP response. The device then analyzes the received information, updates the GUI components, and displays them to the user. For example, a user who is surprised or excited could be shown a visually appealing image or video.

[0796] For example, if a user asks, "How do I get around Kyoto City?" and the emotion engine recognizes that the user is confused, the server will go through a similar process to provide information on appropriate transportation options. For example, it will provide detailed information on the convenience of city buses, how to use one-day passes, the convenience of JR and subways, and even how to rent a bicycle. Confused users will be provided with particularly clear and specific guidance.

[0797] In this way, the system of the present invention, which combines an emotion engine, analyzes the content of the user's question, searches, filters, and generates related information, and ultimately provides information customized according to the user's emotions, thereby realizing a more personalized travel guide.

[0798] Examples of prompts might include: "The user asked about tourist attractions in Kyoto. The user seems excited. How would you respond?" or "The user asked about transportation options within Kyoto. The user seems confused. Please provide a clear answer."

[0799] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0800] Step 1:

[0801] The user inputs a travel question into the terminal.

[0802] Specific operation: The user enters "What are the recommended tourist spots in Kyoto?" into the input field on the device.

[0803] Input: User question text

[0804] Output: The question text is typed into the terminal.

[0805] Step 2:

[0806] The terminal analyzes the input question text and uses an emotion engine to analyze the user's emotional state.

[0807] Specific operation: The device's emotion engine analyzes the text and extracts emotional states such as "excitement" or "confusion."

[0808] Input: Question text

[0809] Output: Emotion data (e.g. excited)

[0810] Step 3:

[0811] The device sends the question text and emotion data to the server.

[0812] Specific operation: The device uses an HTTP request to send the user's question, "What are the recommended tourist spots in Kyoto?" and emotion data to the server.

[0813] Input: Question text, emotion data

[0814] Output: HTTP request to the server

[0815] Step 4:

[0816] The server analyzes the received question text and extracts keywords using natural language processing means.

[0817] Specific operation: The server uses an NLP library (e.g., NLTK or SpaCy) to tokenize the question and extract keywords. The keywords obtained are "Kyoto," "recommended," and "tourist spot."

[0818] Input: Question text

[0819] Output: Extracted keywords

[0820] Step 5:

[0821] The server inputs prompts into the generative AI model to understand the user's intent and identify relevant information.

[0822] Specific operation: The server inputs a prompt to the generative AI model (e.g., GPT-3): "The user asked about recommended tourist spots in Kyoto. The user is excited. How would you respond?" The generative AI model generates related information such as "Kinkaku-ji Temple," "Kiyomizu-dera Temple," and "Fushimi Inari Taisha Shrine."

[0823] Input: Extracted keywords, prompt sentence

[0824] Output: Related information generated

[0825] Step 6:

[0826] The server queries the database to find the relevant information.

[0827] Specific operation: The server executes a database query to retrieve tourist spot information that matches the keywords: "Kinkaku-ji Temple," "Kiyomizu-dera Temple," and "Fushimi Inari Taisha Shrine."

[0828] Input: Generated related information

[0829] Output: Tourist spot information retrieved from the database

[0830] Step 7:

[0831] The server filters information based on the user's past data, preference information, and emotional data.

[0832] Specific operation: The server compares the user's past search history and preferences to select the most suitable tourist spot. For example, it determines that Kinkaku-ji Temple is the most suitable for the user's preferences.

[0833] Input: Tourist spot information obtained from the database, user's past data, preference information, emotional data

[0834] Output: Filtered tourist spot information

[0835] Step 8:

[0836] The server uses a generative AI model to generate detailed explanations and recommendations based on the filtered information.

[0837] Specific behavior: The generative AI model generates a detailed description that reads, "Kinkaku-ji is a particularly beautiful piece of architecture, and you can feel the history of Japan."

[0838] Input: Filtered tourist spot information

[0839] Output: Detailed description generated

[0840] Step 9:

[0841] The server converts the generated information into a data structure such as JSON format and sends it to the terminal as an HTTP response.

[0842] Specific operation: The information generated by the server is converted into JSON data and sent to the terminal via an HTTP response.

[0843] Input: Generated detailed description

[0844] Output: HTTP response to the device

[0845] Step 10:

[0846] The terminal analyzes the received information, updates the GUI components, and displays them to the user.

[0847] What it does: The device parses the JSON data and displays the information in a GUI with visually appealing images and videos, using particularly positive language for excited users.

[0848] Input: HTTP response to the terminal

[0849] Output: Updated GUI display

[0850] (Application example 2)

[0851] 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."

[0852] While conventional travel guide systems can provide general information in response to user questions, they have difficulty providing personalized information based on the user's emotional state or individual preferences. Furthermore, there is a lack of interactive methods for obtaining necessary information in real time during travel, which has resulted in a lack of sufficient improvement in the user experience.

[0853] 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 accepting a user's question, means for analyzing the content of the question, means for searching for related information based on the analysis result, means for filtering the search results based on the user's preferences, means for generating and providing the filtered information, means for displaying the provided information to the user, and means for analyzing emotions. This makes it possible to provide a personalized travel guide in real time according to the user's emotional state.

[0854] The "means for accepting user questions" is an interface through which users input questions about travel, and is a device or software that accepts questions by text or voice.

[0855] The "means for analyzing the question content" is a device or software that analyzes the question entered by the user and extracts the intent of the question and key keywords.

[0856] The "means for searching for related information" is a device or software that searches for related information from a database or the Internet based on the analyzed question content.

[0857] A "means for filtering based on user preferences" is a device or software that selects the most appropriate information from search results based on the user's past behavior and preference data.

[0858] The "means for generating and providing filtered information" refers to a device or software that automatically generates text such as an explanation or a reason for recommendation in order to provide the filtered information to the user.

[0859] The "means for displaying the provided information to the user" is a device or software for visually displaying the generated information on the user's terminal.

[0860] The "emotion analysis means" is a device or software that analyzes the user's emotional state based on the content of the user's questions and past behavioral data, and customizes the information provided based on the results.

[0861] This invention is a system that allows users to input travel-related questions and provides personalized information based on the content of the question and the user's emotional state. The system aims to improve the user experience by providing an efficient means for users to obtain necessary information in real time while traveling.

[0862] 1. Hardware and Software Used

[0863] The main hardware required to implement this system includes the device used by the user (e.g., smartphone, head-mounted display, etc.) and the server. The main software used includes a natural language processing engine (e.g., spaCy), a sentiment analysis engine (e.g., AWS Comprehend, Hugging Face Transformers), and a Web API server (e.g., Flask, Django). Information is also generated using a generative AI model.

[0864] 2. System Operation Overview

[0865] A user inputs a travel-related question into a terminal. For example, if a question is input such as "What are the recommended tourist spots in Kyoto?", the terminal receives this question. The emotion analysis means analyzes the user's emotional state from the input text and sends the obtained emotion data to the server. The server performs processing in the following steps based on the received question content and emotion data.

[0866] Question analysis: The question is tokenized and keywords are extracted. For example, keywords such as "Kyoto," "recommended," and "tourist spots" are extracted.

[0867] Information retrieval: The server uses a generative AI model to understand the user's intent and identify relevant information, then queries the database to retrieve tourist spot information.

[0868] Information filtering: Search results are filtered to provide the most relevant recommendations to the user based on their past data, preferences, and emotional data.

[0869] Information generation and display: The filtered information is generated as text using a generative AI model. This information is converted into a data structure such as JSON and sent to the device as an HTTP response. The device analyzes the received information, updates the GUI components, and displays it to the user.

[0870] 3. Examples and prompts

[0871] For example, if a user asks, "How do I get around Kyoto City?" and the sentiment analysis tool detects that the user is confused, the server will go through a similar process to provide information on appropriate transportation options. For example, detailed explanations on the convenience of city buses, how to use one-day passes, the convenience of JR and subways, and even how to rent a bicycle are provided. Confused users will be provided with particularly clear and specific guidance.

[0872] Prompt Sentence Examples

[0873] "Please tell me about some beautiful gardens in Kyoto. I am always amazed when I see my favorite scenery."

[0874] This system provides users with real-time travel guides tailored to their emotional state, making the virtual travel experience more personalized.

[0875] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0876] Step 1:

[0877] The user inputs a question into the terminal. For example, the user inputs "What are the recommended tourist spots in Kyoto?" The terminal receives this question and sends it to the sentiment analysis means. The input is the user's question, and the output is text data that is passed to the sentiment analysis.

[0878] Step 2:

[0879] An emotion analysis means installed on the device analyzes the user's emotional state from the input text data. An emotion analysis engine (e.g., AWS Comprehend) analyzes the text and detects emotional states such as "surprise" or "excitement." The input is the user's question, and the output is the detected emotional data. The device then sends this emotional data to a server.

[0880] Step 3:

[0881] The server receives the emotion data and the question. It then uses a natural language processing engine (e.g., spaCy) to analyze the question. It tokenizes the question and extracts key keywords. For example, it extracts keywords such as "Kyoto," "recommended," and "tourist spots." The input is the question and emotion data, and the output is the extracted keywords.

[0882] Step 4:

[0883] The server uses a generative AI model to understand the user's intent and identify relevant information. Based on the extracted keywords, the generative AI model infers the user's intent. The input is the extracted keywords, and the output is the inferred result of the user's intent.

[0884] Step 5:

[0885] The server queries the database to retrieve information about related tourist spots. For example, it retrieves information about "Kinkaku-ji Temple," "Kiyomizu-dera Temple," and "Fushimi Inari Taisha Shrine." The input is the result of inferring the user's intention, and the output is the retrieved tourist spot information.

[0886] Step 6:

[0887] The server filters the search results based on the user's preferences. This filtering refers to the user's past data and preference information to select the most suitable spots. For example, it may select based on places and activities that the user has shown interest in in the past. The input is the search results, and the output is the filtered tourist spot information.

[0888] Step 7:

[0889] The server uses a generative AI model to generate explanatory text based on the filtered information. It also takes into account the user's emotional data to generate text that appeals to the user's emotions. For example, it generates the sentence, "Kinkaku-ji Temple is a particularly beautiful piece of architecture, and you can feel the history of Japan." The input is the filtered information and emotional data, and the output is the generated explanatory text.

[0890] Step 8:

[0891] The server converts the generated information into a data structure such as JSON and sends it to the terminal as an HTTP response. The input is the generated description, and the output is the data sent as the HTTP response.

[0892] Step 9:

[0893] The device analyzes the information it receives and updates GUI components to visually display it to the user, for example displaying generated explanatory text along with attractive images or videos. The input is the data received as an HTTP response, and the output is the visual information displayed to the user.

[0894] Through this step, users can get real-time travel guide information that is personalized according to their emotional state.

[0895] 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.

[0896] 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.

[0897] 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.

[0898] [Fourth embodiment]

[0899] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0900] 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.

[0901] 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).

[0902] 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.

[0903] 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.

[0904] 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).

[0905] 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.

[0906] 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.

[0907] 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.

[0908] 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.

[0909] 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.

[0910] 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.

[0911] 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."

[0912] The present invention relates to a system for streamlining travel planning and providing a fulfilling travel experience to users. This system analyzes questions entered by users and provides relevant information based on the analysis results to generate a travel guide customized to the user's needs.

[0913] First, the user inputs a travel-related question into the terminal. For example, if the user inputs a question such as "What are the recommended tourist spots in Kyoto?", the terminal receives the question and sends it to the server.

[0914] The server analyzes the question using natural language processing. Specifically, it tokenizes the question and extracts keywords. In this example, the keywords extracted are "Kyoto," "recommended," and "tourist spots." The server then uses a generative AI model to understand the user's intent and identify relevant information.

[0915] The server then queries the database to find tourist spot information related to the user's question. The search results include famous tourist spots in Kyoto, such as Kinkaku-ji Temple, Kiyomizu-dera Temple, and Fushimi Inari Taisha Shrine. The server then references the user's past data and preference information, filtering this information to narrow down the recommendations that are most suitable for the user.

[0916] After filtering, the server uses a generative AI model to generate detailed descriptions of each tourist spot and the reasons for its recommendation. For example, it generates information like, "Kinkaku-ji Temple is an especially beautiful piece of architecture, and you can really feel the history of Japan. Visiting early in the morning will help you avoid the crowds."

[0917] Finally, the server converts the generated information into a data structure such as JSON format and sends it to the device as an HTTP response. The device analyzes the received information, updates the GUI components, and displays them to the user. The user can then use the provided information to plan their trip.

[0918] For example, if a user asks, "How can I get around Kyoto city?", the server will go through a similar process to provide information on appropriate transportation options, such as the convenience of city buses, how to use one-day passes, the convenience of JR and subways, and even bicycle rentals.

[0919] In this way, the system of the present invention provides an efficient and accurate travel guide by including a series of processes that analyze the content of the user's question, search, filter, and generate relevant information, and finally provide it to the user.

[0920] The processing flow will be explained below.

[0921] Step 1:

[0922] The user inputs a travel-related question into the terminal. Specifically, for example, the text "What are the recommended tourist spots in Kyoto?" is input.

[0923] Step 2:

[0924] The device receives the input question and prepares an HTTP request to send to the server, converting the question content into a data structure such as JSON.

[0925] Step 3:

[0926] The server receives the HTTP request sent from the terminal and begins the process of analyzing the question.

[0927] Step 4:

[0928] The server uses natural language processing to tokenize the question and extract keywords, such as "Kyoto," "recommended," and "tourist spots."

[0929] Step 5:

[0930] The server inputs the analyzed keywords and question content into a generative AI model to understand the user's intent. This generative AI model then identifies the type of information desired from the user's question.

[0931] Step 6:

[0932] The server generates a query in the database to search for tourist spot information related to the query. The search query includes the extracted keywords.

[0933] Step 7:

[0934] The server receives the search results retrieved from the database and uses a generative AI model to filter them based on the user's preferences and past tastes, for example, by looking at past search history and user profiles.

[0935] Step 8:

[0936] The server generates detailed explanations and reasons for recommendations based on the filtered information. The generative AI model converts this into text. For example, it generates information such as, "Kinkaku-ji Temple is a particularly beautiful piece of architecture, and you can feel the history of Japan."

[0937] Step 9:

[0938] The server converts the generated information into a data structure such as JSON format and sends it to the terminal as an HTTP response.

[0939] Step 10:

[0940] The terminal analyzes the HTTP response received from the server and performs processing to display it on the user interface.

[0941] Step 11:

[0942] The terminal displays the generated information to the user, for example, detailed information about Kinkaku-ji Temple, Kiyomizu-dera Temple, and Fushimi Inari Taisha Shrine.

[0943] Step 12:

[0944] The user consults the provided information and plans their trip, entering further questions as needed and returning to step 1.

[0945] Example 1

[0946] 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."

[0947] Conventional travel guide systems have the problem that when users input travel-related questions, the information provided is general, making it difficult to respond to individual user needs and preferences.In addition, the information is not sufficiently filtered or customized, making it difficult to provide the information users truly want.

[0948] 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.

[0949] In this invention, the server includes means for accepting a user's question, means for performing natural language processing to analyze the content of the question, means for identifying related information using a generative AI model based on the analysis results, means for searching a database for the identified related information, means for filtering search results based on the user's preferences, means for generating and providing the filtered information, and means for displaying the provided information to the user, thereby enabling the provision of information that meets the individual needs and preferences of the user.

[0950] A "user question" is text data that a user inputs into a terminal to obtain information about a trip in which the user is interested.

[0951] "Natural language processing" is a technology that analyzes text data entered by a user and performs keyword extraction and grammatical analysis.

[0952] A "generative AI model" is an algorithm that uses artificial intelligence to understand a user's intent and generate appropriate answers to questions.

[0953] A "database" is a storage device that stores information on tourist spots, transportation options, and the like.

[0954] "Filtering" is the process of selecting information from search results that matches the user's preferences.

[0955] "Information generation" is the process of creating specific answers to provide to users based on the filtered data.

[0956] "Providing information" is the process of presenting the generated answers to the user in an easy-to-understand format.

[0957] "Display" refers to the act of visually showing the generated answer on the user's terminal screen.

[0958] "Past user data" refers to records relating to questions and preferences previously entered by a user, information that is used to generate customized answers.

[0959] MODE FOR CARRYING OUT THE INVENTION

[0960] The present invention relates to a system for improving the efficiency of users' travel planning and providing a fulfilling travel experience, which accepts and analyzes user questions, searches, filters, generates related information, and provides it to users. Specific embodiments of the system are described below.

[0961] Hardware and Software Configuration

[0962] This system consists of a terminal where users can input travel-related questions, a server for analyzing the questions and generating information, and a database.

[0963] Terminal: Users access the system using a terminal such as a smartphone, tablet, or PC. The terminal is equipped with an input interface (e.g., touchscreen, keyboard).

[0964] Server: The server contains a natural language processing (NLP) module, a generative AI model, and a database access module to analyze user questions, identify relevant information, and generate it.

[0965] Database: Contains information on tourist attractions, transportation options, etc.

[0966] Program processing

[0967] A user inputs a travel-related question into a device. For example, if a question is input such as "What are the recommended tourist spots in Kyoto?", the device receives the question and sends it to the server as an HTTP POST request. The server receives the question and analyzes it using a natural language processing module. During the analysis, the question is tokenized and keywords are extracted. For example, the keywords "Kyoto," "recommended," and "tourist spots" are extracted.

[0968] The server then uses a generative AI model to understand the user's intent and identify relevant information. An example prompt might be, "The user is asking about recommended tourist spots in Kyoto." The server then queries the database to search for tourist spot information related to the user's question. For example, the search results might include information about Kyoto's most famous tourist spots, such as Kinkaku-ji Temple, Kiyomizu-dera Temple, and Fushimi Inari Taisha Shrine.

[0969] The server then references the user's past data and preferences, filtering this information to narrow down the recommendations to the most appropriate ones. After filtering, the server uses a generative AI model to generate detailed descriptions of each tourist spot and the reasons for the recommendation. For example, the server generates information such as, "Kinkaku-ji Temple has particularly beautiful architecture and allows you to feel the history of Japan. Visiting early in the morning will help you avoid the crowds."

[0970] Finally, the server converts the generated information into JSON format and sends it to the device as an HTTP response. The device parses the received JSON data, updates the appropriate GUI components, and displays them to the user. The user can then use the provided information to plan their trip.

[0971] Specific examples

[0972] For example, if a user asks, "How can I get around Kyoto city?", the server will go through a similar process to provide information on appropriate transportation options. This includes information on the convenience of city buses, how to use one-day passes, the convenience of trains and subways, and even bicycle rentals. An example prompt would be, "The user is asking about effective transportation options within Kyoto city."

[0973] In this way, the system of the present invention can provide information that meets the individual needs and preferences of each user.

[0974] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0975] Step 1:

[0976] The user inputs a travel-related question into the terminal. For example, "What are the recommended tourist spots in Kyoto?" The text is entered into the input field, and this text data is used as input for subsequent processing.

[0977] Step 2:

[0978] The terminal receives a question from the user and sends it to the server as an HTTP POST request. The input is the user's question text, and the output is the HTTP request.

[0979] Step 3:

[0980] The server analyzes the received question. This question text is passed to a natural language processing (NLP) module. The input is the user's question text, and the output is the analyzed keywords. Specifically, the question text is tokenized to extract keywords. Keywords such as "Kyoto," "recommended," and "tourist spots" are extracted.

[0981] Step 4:

[0982] The server sends a prompt to the generative AI model based on the extracted keywords. The input is the extracted keywords, and the output is related information that understands the user's intent. An example of a prompt is, "The user is asking about recommended tourist spots in Kyoto."

[0983] Step 5:

[0984] The server issues a query to the database to search for relevant tourist spot information. The input is a prompt statement and a query to the database, and the output is tourist spot information as a search result. An example is "SELECT FROM tourist spot WHERE location = 'Kyoto' AND recommended = 1".

[0985] Step 6:

[0986] The server filters the search results, narrowing down the optimal results based on the user's past data and preferences. The input is the search results and the user's past data, and the output is the filtered tourist spot information.

[0987] Step 7:

[0988] The server uses a generative AI model to generate detailed descriptions based on the filtered tourist spot information. The input is the filtered tourist spot information, and the output is the generated detailed description. The generated sentence might be something like, "Kinkaku-ji Temple is a particularly beautiful piece of architecture, and you can really feel the history of Japan. If you visit early in the morning, you can avoid the crowds."

[0989] Step 8:

[0990] The server converts the generated information into JSON format and sends it to the terminal as an HTTP response. The input is the generated description, and the output is JSON format data.

[0991] Step 9:

[0992] The device parses the received JSON data, updates the GUI components, and displays them to the user. The input is JSON data, and the output is the information displayed on the user's screen. The user uses the provided information to plan their trip.

[0993] In this way, specific data processing and data calculations are performed at each step, and the input for the next step is generated based on the results.

[0994] (Application example 1)

[0995] 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."

[0996] Conventional travel guide systems were unable to meet the diverse needs of users and had difficulty providing information in real time. This made it difficult for tourists to efficiently obtain information while traveling and plan trips that suited their preferences. Furthermore, there was a lack of systems that utilized voice input or smart devices, making them less convenient.

[0997] 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.

[0998] In this invention, the server includes means for accepting a user's question, means for analyzing the question, means for searching for related information based on the analysis result, means for filtering the search results based on the user's preferences, means for generating and providing the filtered information, means for displaying the provided information to the user, means for accepting a voice input, means for recognizing the voice input and converting it into text data, and means for displaying or outputting the text on the smart device. This allows the user to input a question using voice, and the answer to the question can be displayed or output as text on the smart device in real time.

[0999] The "means for accepting user questions" is an interface that allows the user to input questions about travel in voice or text format.

[1000] The "means for analyzing the question content" is a system that uses natural language processing technology to analyze the question entered by the user and extract key keywords and intent.

[1001] The "means for searching for related information based on the analysis results" is a system that searches databases and external information sources to obtain related information based on the analyzed question content.

[1002] "Means for filtering search results based on user preferences" refers to a system that scrutinizes acquired information based on the user's past preferences and behavioral data, and selects the information that is deemed most appropriate.

[1003] The "means for generating and providing filtered information" is a system for converting selected information into a form that is easy for users to understand and providing it in text or audio.

[1004] The "means for displaying the provided information to the user" is a system that displays the generated information visually or audibly on the user's terminal.

[1005] The "means for accepting voice input" is an interface that receives questions input by voice from the user through a device such as a microphone.

[1006] "Means for recognizing voice input and converting it into text data" refers to a system that uses voice recognition technology to analyze the voice input by the user and convert it into text data.

[1007] "Means for displaying or outputting audio on a smart device" refers to a system for displaying the generated information on a device such as a smartphone or smart glasses, or outputting it as audio.

[1008] To implement this invention, several steps are required. First, a smart device (e.g., smart glasses) is used as a means for accepting user questions. The user inputs questions by voice through this device. For example, a question such as "What are the recommended tourist spots in Kyoto?" can be input by voice.

[1009] Smart devices have a means of recognizing voice input and converting it into text data. This is done using the speech_recognition library. This recognized text data is sent directly to the server, where it is analyzed.

[1010] The server has the means to analyze the question, using natural language processing techniques (e.g., the "question answering" model from the transformers library). After analyzing the question, the server searches for relevant information based on the analysis results from a database, which is pre-populated with travel information.

[1011] The searched information is filtered using the user's past data (preferences and behavioral history). This filtering selects the information most appropriate for the user. The server then uses a generative AI model to generate detailed explanatory text from the filtered information to provide to the user. For example, information such as "Kinkaku-ji Temple is a particularly beautiful piece of architecture, and is a place where you can feel the history of Japan. Visiting early in the morning will help you avoid the crowds."

[1012] The generated information is displayed on the smart device or output as audio, utilizing the device's standard interface, allowing users to obtain the tourist information they need in real time, facilitating decision-making during their trip.

[1013] For example, if a user asks, "How can I get around Kyoto?", the server might provide information like this: "City buses are very convenient, and you can save money by using a one-day pass. JR and subways are also efficient ways to get around. We also recommend renting a bicycle to tour around Kyoto's tourist attractions."

[1014] Examples of prompts are:

[1015] User dictates: "What are some recommended places to eat in Kyoto?"

[1016] The system responds: "We particularly recommend Japanese restaurants such as Gion Sasagi in Gion and Arashiyama Yoshimura in Arashiyama. Each offers distinctive cuisine and stunning views."

[1017] In this way, the system of the present invention can provide real-time travel guide information that meets the diverse needs of users.

[1018] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1019] Step 1:

[1020] The user starts voice input. The user speaks a question into the smart device (e.g., smart glasses) (e.g., "What are the recommended tourist spots in Kyoto?"). This voice data is input.

[1021] Step 2:

[1022] The device receives the voice data and performs speech recognition. Specifically, it converts the voice data into text data using the speech_recognition library. The converted text data is generated (e.g., "What are the recommended tourist spots in Kyoto?").

[1023] Step 3:

[1024] The terminal transmits the generated text data to the server, which receives the text data.

[1025] Step 4:

[1026] The server analyzes the question, performs natural language processing using the transformers library, and extracts key keywords (e.g., "Kyoto," "recommended," "tourist spots") as the analysis results.

[1027] Step 5:

[1028] The server searches for relevant information based on the analysis results. It obtains data on "Kyoto tourist spots" from internal databases and external information sources. The obtained data is generated (e.g., "Kinkaku-ji Temple," "Kiyomizu-dera Temple," "Fushimi Inari Taisha Shrine").

[1029] Step 6:

[1030] The server filters the search results based on the user's preferences, referencing the user's past preferences and behavioral history to select the most relevant information, and the filtered data is generated.

[1031] Step 7:

[1032] The server uses a generative AI model to generate detailed explanatory text based on the filtered information, using prompts (e.g., "Kinkaku-ji Temple is a particularly beautiful building, and you can feel the history of Japan. Visiting it early in the morning will help you avoid the crowds.").

[1033] Step 8:

[1034] The terminal displays or outputs the provided information as audio, and displays the generated text on the smart device's display or outputs it as audio through the speaker.

[1035] This series of processes allows the user to perform voice input and obtain customized travel guide information in real time as a result.

[1036] 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.

[1037] This invention relates to a system for improving the efficiency of travel planning and providing a fulfilling travel experience to users. This system not only analyzes questions entered by users and provides relevant information based on the analysis results, but also recognizes the user's emotions and customizes the content and presentation of information based on those emotions to provide a more personalized travel guide.

[1038] First, the user inputs a travel-related question into the device. For example, if the user inputs a question such as "What are the recommended tourist spots in Kyoto?", the device receives the question and then an emotion engine analyzes the user's emotional state from the input text and voice.

[1039] The device sends the user's question along with emotion data to the server. The server then uses natural language processing to analyze the question. Specifically, it tokenizes the question and extracts keywords. In this case, the keywords extracted are "Kyoto," "recommended," and "tourist spot." The server then uses a generative AI model to understand the user's intent and identify relevant information.

[1040] The server then queries the database to find tourist spot information related to the user's question. The search results include famous tourist spots in Kyoto, such as Kinkaku-ji Temple, Kiyomizu-dera Temple, and Fushimi Inari Taisha Shrine. The server then references the user's past data, preference information, and emotional data, and filters this information to narrow down the recommendations that are most suitable for the user.

[1041] After filtering, the server uses a generative AI model to generate detailed descriptions of each tourist spot and the reasons for its recommendation. For example, if the user is surprised or excited, the server generates more positive and emotional content, such as "Kinkaku-ji Temple is a particularly beautiful piece of architecture, and you can feel the history of Japan."

[1042] Finally, the server converts the generated information into a data structure such as JSON and sends it to the device as an HTTP response. The device then analyzes the received information, updates the GUI components, and displays them to the user. For example, a user who is surprised or excited could be shown a visually appealing image or video.

[1043] For example, if a user asks, "How do I get around Kyoto City?" and the emotion engine recognizes that the user is confused, the server will go through a similar process to provide information on appropriate transportation options. For example, it will provide detailed information on the convenience of city buses, how to use one-day passes, the convenience of JR and subways, and even how to rent a bicycle. Confused users will be provided with particularly clear and specific guidance.

[1044] In this way, the system of the present invention, which combines an emotion engine, analyzes the content of the user's question, searches, filters, and generates related information, and ultimately provides information customized according to the user's emotions, thereby realizing a more personalized travel guide.

[1045] The processing flow will be explained below.

[1046] Step 1:

[1047] The user inputs a travel-related question into the terminal. Specifically, the user inputs the text "What are the recommended tourist spots in Kyoto?"

[1048] Step 2:

[1049] The device receives the input question, and an emotion engine analyzes the text to determine the user's emotions, such as whether the user is surprised or happy.

[1050] Step 3:

[1051] The device sends the question and the recognized emotion data to the server, which converts the data into a data structure such as JSON.

[1052] Step 4:

[1053] The server receives the question content and emotion data sent from the terminal and starts the process of analyzing the question content.

[1054] Step 5:

[1055] The server uses natural language processing to tokenize the question and extract keywords, such as "Kyoto," "recommended," and "tourist spots."

[1056] Step 6:

[1057] The server uses a generative AI model to identify the type of information sought from the user's question based on the extracted keywords and understand the intent.

[1058] Step 7:

[1059] The server queries the database to find tourist spots related to the user's question, and the search results include "Kinkaku-ji Temple," "Kiyomizu-dera Temple," and "Fushimi Inari Taisha Shrine."

[1060] Step 8:

[1061] The server uses a generative AI model to filter the acquired tourist spot information based on the user's past preference data and recognized emotional data, thereby providing more optimistic content to users in a positive emotional state, for example.

[1062] Step 9:

[1063] Based on the filtered information, the server uses a generative AI model to generate detailed explanations and reasons for the recommendation in text format. For example, if the emotion engine recognizes the user's emotion of surprise, it will generate content that touches on the user's emotion, such as "Kinkaku-ji Temple is a particularly beautiful piece of architecture, and you can feel the history of Japan."

[1064] Step 10:

[1065] The server converts the generated information into a data structure such as JSON format and sends it to the terminal as an HTTP response.

[1066] Step 11:

[1067] The device analyzes the HTTP response received from the server, updates the GUI components, and displays them to the user. For example, it may also display emotive images or videos.

[1068] Step 12:

[1069] The user refers to the provided information and makes travel plans. If the user has further questions, they return to step 1 and enter new questions.

[1070] For example, if a user asks, "How do I get around Kyoto City?" and the emotion engine recognizes the user's confusion, the server will provide detailed information on appropriate transportation methods, such as how to use city buses, how to purchase one-day passes, and the convenience of JR and subways, providing easy-to-understand visual guidance.

[1071] Example 2

[1072] 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."

[1073] Conventional travel guide systems simply provide information in response to user questions, and are insufficient in providing personalized information that reflects the user's emotional state or individual preferences. As a result, it is difficult for users to create satisfying travel plans. Furthermore, when a large number of search results are returned, it is difficult for users to narrow down the specific information they need, which requires time and effort.

[1074] 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.

[1075] In this invention, the server includes a means for analyzing the user's emotional state along with the user's question, a means for searching for related information based on the user's question and emotional state, and a means for generating and providing filtered information using a generative AI model. This makes it possible to provide customized information based on the user's emotional state and past preferences, allowing the user to make more satisfying travel plans.

[1076] "Means for accepting user questions" refers to a function for receiving travel-related questions that users input into the system.

[1077] "Means for analyzing the user's emotional state" refers to a function for analyzing the user's emotional state (for example, excitement, confusion, etc.) from questions or voice data entered by the user.

[1078] "Means for searching related information" refers to the function of searching for related information from databases or the Internet based on the user's question and emotional state.

[1079] "Filtering means" refers to the function of narrowing down searched information based on the user's past data and preference information, and selecting the most appropriate information.

[1080] "Means of providing information using a generative AI model" refers to the function of using AI technology to generate specific, customized information desired by the user and provide it to the user.

[1081] "Natural language processing means" refers to technology that analyzes questions entered by users and extracts important keywords.

[1082] "Means for generating prompt sentences" refers to the function of creating appropriate input sentences for the generative AI model.

[1083] This invention relates to a system for improving the efficiency of travel planning and providing a fulfilling travel experience to users. This system not only analyzes questions entered by users and provides relevant information based on the analysis results, but also recognizes the user's emotions and customizes the content and presentation of information based on those emotions to provide a more personalized travel guide.

[1084] First, the user inputs a travel-related question into the device. For example, if the user inputs a question such as "What are the recommended tourist spots in Kyoto?", the device receives the question and then an emotion engine analyzes the user's emotional state from the input text and voice.

[1085] The device sends the user's question along with emotion data to the server. The server then uses natural language processing to analyze the question. Specifically, it tokenizes the question and extracts keywords. In this case, the keywords extracted are "Kyoto," "recommended," and "tourist spot." The server then uses a generative AI model to understand the user's intent and identify relevant information.

[1086] The server then queries the database to find tourist spot information related to the user's question. The search results include famous tourist spots in Kyoto, such as Kinkaku-ji Temple, Kiyomizu-dera Temple, and Fushimi Inari Taisha Shrine. The server then references the user's past data, preference information, and emotional data, and filters this information to narrow down the recommendations that are most suitable for the user.

[1087] After filtering, the server uses a generative AI model to generate detailed descriptions of each tourist spot and the reasons for its recommendation. For example, if the user is surprised or excited, the server generates more positive and emotional content, such as "Kinkaku-ji Temple is a particularly beautiful piece of architecture, and you can feel the history of Japan."

[1088] Finally, the server converts the generated information into a data structure such as JSON and sends it to the device as an HTTP response. The device then analyzes the received information, updates the GUI components, and displays them to the user. For example, a user who is surprised or excited could be shown a visually appealing image or video.

[1089] For example, if a user asks, "How do I get around Kyoto City?" and the emotion engine recognizes that the user is confused, the server will go through a similar process to provide information on appropriate transportation options. For example, it will provide detailed information on the convenience of city buses, how to use one-day passes, the convenience of JR and subways, and even how to rent a bicycle. Confused users will be provided with particularly clear and specific guidance.

[1090] In this way, the system of the present invention, which combines an emotion engine, analyzes the content of the user's question, searches, filters, and generates related information, and ultimately provides information customized according to the user's emotions, thereby realizing a more personalized travel guide.

[1091] Examples of prompts might include: "The user asked about tourist attractions in Kyoto. The user seems excited. How would you respond?" or "The user asked about transportation options within Kyoto. The user seems confused. Please provide a clear answer."

[1092] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1093] Step 1:

[1094] The user inputs a travel question into the terminal.

[1095] Specific operation: The user enters "What are the recommended tourist spots in Kyoto?" into the input field on the device.

[1096] Input: User question text

[1097] Output: The question text is typed into the terminal.

[1098] Step 2:

[1099] The terminal analyzes the input question text and uses an emotion engine to analyze the user's emotional state.

[1100] Specific operation: The device's emotion engine analyzes the text and extracts emotional states such as "excitement" or "confusion."

[1101] Input: Question text

[1102] Output: Emotion data (e.g. excited)

[1103] Step 3:

[1104] The device sends the question text and emotion data to the server.

[1105] Specific operation: The device uses an HTTP request to send the user's question, "What are the recommended tourist spots in Kyoto?" and emotion data to the server.

[1106] Input: Question text, emotion data

[1107] Output: HTTP request to the server

[1108] Step 4:

[1109] The server analyzes the received question text and extracts keywords using natural language processing means.

[1110] Specific operation: The server uses an NLP library (e.g., NLTK or SpaCy) to tokenize the question and extract keywords. The keywords obtained are "Kyoto," "recommended," and "tourist spot."

[1111] Input: Question text

[1112] Output: Extracted keywords

[1113] Step 5:

[1114] The server inputs prompts into the generative AI model to understand the user's intent and identify relevant information.

[1115] Specific operation: The server inputs a prompt to the generative AI model (e.g., GPT-3): "The user asked about recommended tourist spots in Kyoto. The user is excited. How would you respond?" The generative AI model generates related information such as "Kinkaku-ji Temple," "Kiyomizu-dera Temple," and "Fushimi Inari Taisha Shrine."

[1116] Input: Extracted keywords, prompt sentence

[1117] Output: Related information generated

[1118] Step 6:

[1119] The server queries the database to find the relevant information.

[1120] Specific operation: The server executes a database query to retrieve tourist spot information that matches the keywords: "Kinkaku-ji Temple," "Kiyomizu-dera Temple," and "Fushimi Inari Taisha Shrine."

[1121] Input: Generated related information

[1122] Output: Tourist spot information retrieved from the database

[1123] Step 7:

[1124] The server filters information based on the user's past data, preference information, and emotional data.

[1125] Specific operation: The server compares the user's past search history and preferences to select the most suitable tourist spot. For example, it determines that Kinkaku-ji Temple is the most suitable for the user's preferences.

[1126] Input: Tourist spot information obtained from the database, user's past data, preference information, emotional data

[1127] Output: Filtered tourist spot information

[1128] Step 8:

[1129] The server uses a generative AI model to generate detailed explanations and recommendations based on the filtered information.

[1130] Specific behavior: The generative AI model generates a detailed description that reads, "Kinkaku-ji is a particularly beautiful piece of architecture, and you can feel the history of Japan."

[1131] Input: Filtered tourist spot information

[1132] Output: Detailed description generated

[1133] Step 9:

[1134] The server converts the generated information into a data structure such as JSON format and sends it to the terminal as an HTTP response.

[1135] Specific operation: The information generated by the server is converted into JSON data and sent to the terminal via an HTTP response.

[1136] Input: Generated detailed description

[1137] Output: HTTP response to the device

[1138] Step 10:

[1139] The terminal analyzes the received information, updates the GUI components, and displays them to the user.

[1140] What it does: The device parses the JSON data and displays the information in a GUI with visually appealing images and videos, using particularly positive language for excited users.

[1141] Input: HTTP response to the terminal

[1142] Output: Updated GUI display

[1143] (Application example 2)

[1144] 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."

[1145] While conventional travel guide systems can provide general information in response to user questions, they have difficulty providing personalized information based on the user's emotional state or individual preferences. Furthermore, there is a lack of interactive methods for obtaining necessary information in real time during travel, which has resulted in a lack of sufficient improvement in the user experience.

[1146] 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 accepting a user's question, means for analyzing the content of the question, means for searching for related information based on the analysis result, means for filtering the search results based on the user's preferences, means for generating and providing the filtered information, means for displaying the provided information to the user, and means for analyzing emotions. This makes it possible to provide a personalized travel guide in real time according to the user's emotional state.

[1147] The "means for accepting user questions" is an interface through which users input questions about travel, and is a device or software that accepts questions by text or voice.

[1148] The "means for analyzing the question content" is a device or software that analyzes the question entered by the user and extracts the intent of the question and key keywords.

[1149] The "means for searching for related information" is a device or software that searches for related information from a database or the Internet based on the analyzed question content.

[1150] A "means for filtering based on user preferences" is a device or software that selects the most appropriate information from search results based on the user's past behavior and preference data.

[1151] The "means for generating and providing filtered information" refers to a device or software that automatically generates text such as an explanation or a reason for recommendation in order to provide the filtered information to the user.

[1152] The "means for displaying the provided information to the user" is a device or software for visually displaying the generated information on the user's terminal.

[1153] The "emotion analysis means" is a device or software that analyzes the user's emotional state based on the content of the user's questions and past behavioral data, and customizes the information provided based on the results.

[1154] This invention is a system that allows users to input travel-related questions and provides personalized information based on the content of the question and the user's emotional state. The system aims to improve the user experience by providing an efficient means for users to obtain necessary information in real time while traveling.

[1155] 1. Hardware and Software Used

[1156] The main hardware required to implement this system includes the device used by the user (e.g., smartphone, head-mounted display, etc.) and the server. The main software used includes a natural language processing engine (e.g., spaCy), a sentiment analysis engine (e.g., AWS Comprehend, Hugging Face Transformers), and a Web API server (e.g., Flask, Django). Information is also generated using a generative AI model.

[1157] 2. System Operation Overview

[1158] A user inputs a travel-related question into a terminal. For example, if a question is input such as "What are the recommended tourist spots in Kyoto?", the terminal receives this question. The emotion analysis means analyzes the user's emotional state from the input text and sends the obtained emotion data to the server. The server performs processing in the following steps based on the received question content and emotion data.

[1159] Question analysis: The question is tokenized and keywords are extracted. For example, keywords such as "Kyoto," "recommended," and "tourist spots" are extracted.

[1160] Information retrieval: The server uses a generative AI model to understand the user's intent and identify relevant information, then queries the database to retrieve tourist spot information.

[1161] Information filtering: Search results are filtered to provide the most relevant recommendations to the user based on their past data, preferences, and emotional data.

[1162] Information generation and display: The filtered information is generated as text using a generative AI model. This information is converted into a data structure such as JSON and sent to the device as an HTTP response. The device analyzes the received information, updates the GUI components, and displays it to the user.

[1163] 3. Examples and prompts

[1164] For example, if a user asks, "How do I get around Kyoto City?" and the sentiment analysis tool detects that the user is confused, the server will go through a similar process to provide information on appropriate transportation options. For example, detailed explanations on the convenience of city buses, how to use one-day passes, the convenience of JR and subways, and even how to rent a bicycle are provided. Confused users will be provided with particularly clear and specific guidance.

[1165] Prompt Sentence Examples

[1166] "Please tell me about some beautiful gardens in Kyoto. I am always amazed when I see my favorite scenery."

[1167] This system provides users with real-time travel guides tailored to their emotional state, making the virtual travel experience more personalized.

[1168] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1169] Step 1:

[1170] The user inputs a question into the terminal. For example, the user inputs "What are the recommended tourist spots in Kyoto?" The terminal receives this question and sends it to the sentiment analysis means. The input is the user's question, and the output is text data that is passed to the sentiment analysis.

[1171] Step 2:

[1172] An emotion analysis means installed on the device analyzes the user's emotional state from the input text data. An emotion analysis engine (e.g., AWS Comprehend) analyzes the text and detects emotional states such as "surprise" or "excitement." The input is the user's question, and the output is the detected emotional data. The device then sends this emotional data to a server.

[1173] Step 3:

[1174] The server receives the emotion data and the question. It then uses a natural language processing engine (e.g., spaCy) to analyze the question. It tokenizes the question and extracts key keywords. For example, it extracts keywords such as "Kyoto," "recommended," and "tourist spots." The input is the question and emotion data, and the output is the extracted keywords.

[1175] Step 4:

[1176] The server uses a generative AI model to understand the user's intent and identify relevant information. Based on the extracted keywords, the generative AI model infers the user's intent. The input is the extracted keywords, and the output is the inferred result of the user's intent.

[1177] Step 5:

[1178] The server queries the database to retrieve information about related tourist spots. For example, it retrieves information about "Kinkaku-ji Temple," "Kiyomizu-dera Temple," and "Fushimi Inari Taisha Shrine." The input is the result of inferring the user's intention, and the output is the retrieved tourist spot information.

[1179] Step 6:

[1180] The server filters the search results based on the user's preferences. This filtering refers to the user's past data and preference information to select the most suitable spots. For example, it may select based on places and activities that the user has shown interest in in the past. The input is the search results, and the output is the filtered tourist spot information.

[1181] Step 7:

[1182] The server uses a generative AI model to generate explanatory text based on the filtered information. It also takes into account the user's emotional data to generate text that appeals to the user's emotions. For example, it generates the sentence, "Kinkaku-ji Temple is a particularly beautiful piece of architecture, and you can feel the history of Japan." The input is the filtered information and emotional data, and the output is the generated explanatory text.

[1183] Step 8:

[1184] The server converts the generated information into a data structure such as JSON and sends it to the terminal as an HTTP response. The input is the generated description, and the output is the data sent as the HTTP response.

[1185] Step 9:

[1186] The device analyzes the information it receives and updates GUI components to visually display it to the user, for example displaying generated explanatory text along with attractive images or videos. The input is the data received as an HTTP response, and the output is the visual information displayed to the user.

[1187] Through this step, users can get real-time travel guide information that is personalized according to their emotional state.

[1188] 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.

[1189] 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.

[1190] 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.

[1191] 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.

[1192] 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.

[1193] 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.

[1194] 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).

[1195] 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.

[1196] 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."

[1197] 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.

[1198] 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).

[1199] 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.

[1200] 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.

[1201] 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.

[1202] 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.

[1203] 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.

[1204] 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.

[1205] 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.

[1206] 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.

[1207] 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.

[1208] 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.

[1209] The following is further disclosed regarding the above embodiment.

[1210] (Claim 1)

[1211] means for accepting user questions;

[1212] means for analyzing the content of the question;

[1213] A means for searching for related information based on the analysis results;

[1214] means for filtering the search results based on user preferences;

[1215] means for generating and providing filtered information;

[1216] The system includes means for displaying said provided information to a user.

[1217] (Claim 2)

[1218] 10. The system of claim 1, further comprising means for utilizing past user data to customize the generated information.

[1219] (Claim 3)

[1220] 2. The system according to claim 1, further comprising natural language processing means for analyzing the content of the question and extracting keywords.

[1221] "Example 1"

[1222] (Claim 1)

[1223] means for accepting user questions;

[1224] means for performing natural language processing to analyze the content of the question;

[1225] A means for identifying relevant information using a generative AI model based on the analysis results;

[1226] means for searching a database for the identified related information;

[1227] means for filtering the search results based on user preferences;

[1228] means for generating and providing filtered information;

[1229] The system includes means for displaying said provided information to a user.

[1230] (Claim 2)

[1231] 10. The system of claim 1, further comprising means for utilizing past user data to customize the generated information.

[1232] (Claim 3)

[1233] 2. The system according to claim 1, further comprising natural language processing means for analyzing the content of the question and extracting keywords.

[1234] "Application Example 1"

[1235] (Claim 1)

[1236] means for accepting user questions;

[1237] means for analyzing the content of the question;

[1238] A means for searching for related information based on the analysis results;

[1239] means for filtering the search results based on user preferences;

[1240] means for generating and providing filtered information;

[1241] means for displaying the provided information to a user;

[1242] means for accepting voice input;

[1243] means for recognizing the voice input and converting it into text data;

[1244] A means for displaying or outputting the information to a smart device;

[1245] A system including:

[1246] (Claim 2)

[1247] 10. The system of claim 1, further comprising means for utilizing past user data to customize the generated information.

[1248] (Claim 3)

[1249] 2. The system according to claim 1, further comprising natural language processing means for analyzing the content of the question and extracting keywords.

[1250] "Example 2: Combining Emotion Engines"

[1251] (Claim 1)

[1252] means for accepting user questions;

[1253] means for analyzing the emotional state of the user in conjunction with said question;

[1254] A means for searching for related information based on the question content and emotional state;

[1255] means for filtering the search results based on the user's past data and preference information;

[1256] means for generating and providing filtered information using a generative AI model;

[1257] means for displaying said provided information in response to a user's emotional state.

[1258] (Claim 2)

[1259] 10. The system of claim 1, further comprising means for generating a prompt sentence for input to the generative AI model.

[1260] (Claim 3)

[1261] 2. The system according to claim 1, further comprising natural language processing means for analyzing the question content and the user's emotional state and extracting keywords.

[1262] "Application example 2 when combining emotion engines"

[1263] (Claim 1)

[1264] means for accepting user questions;

[1265] means for analyzing the content of the question;

[1266] A means for searching for related information based on the analysis results;

[1267] means for filtering the search results based on user preferences;

[1268] means for generating and providing filtered information;

[1269] means for displaying the provided information to a user;

[1270] including sentiment analysis means;

[1271] the emotion analysis means analyzes the user's emotional state;

[1272] The system includes a means for customizing the content and presentation of information based on the analyzed emotional data.

[1273] (Claim 2)

[1274] 10. The system of claim 1, further comprising means for utilizing past user data to customize the generated information.

[1275] (Claim 3)

[1276] 2. The system according to claim 1, further comprising natural language processing means for analyzing the content of the question and extracting keywords. [Explanation of symbols]

[1277] 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 accepting user questions; means for analyzing the content of the question; A means for searching for related information based on the analysis results; means for filtering the search results based on user preferences; means for generating and providing filtered information; The system includes means for displaying said provided information to a user.

2. 10. The system of claim 1, further comprising means for utilizing past user data to customize the generated information.

3. 2. The system according to claim 1, further comprising natural language processing means for analyzing the content of the question and extracting keywords.

Images