system

Abstract

We provide the system. [Solution] A means for receiving information entered in natural language from a user terminal, The means for analyzing the aforementioned information using natural language processing technology, A means of searching a database based on the analyzed information and obtaining facility information that matches the criteria, A means of transmitting acquired facility information to the user terminal, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern society, selecting an optimal food and beverage facility to be used in various situations such as meals with friends, dates, business dinners, and travel is a complex and time-consuming task for many people. In conventional search sites, only limited search conditions can be set, and it is difficult to quickly find a facility that exactly matches the specific conditions desired by the user. In addition, there is also a problem that multiple searches need to be performed for different conditions, which is time-consuming and laborious.

Means for Solving the Problems

[0005] The system receives information entered in natural language from the user's terminal and analyzes this information using natural language processing technology. Based on the analyzed information, it searches a database for facilities that match the conditions specified by the user and provides the retrieved facility information to the user's terminal, thereby quickly and efficiently presenting the most suitable dining establishment. Furthermore, it aims to improve user convenience by providing features such as the ability for users to share facility information between different communication terminals and additional information such as available reservation times.

[0006] A "user terminal" is a general term for electronic devices that allow users to input and receive information.

[0007] "Natural language" refers to the form of language that humans use on a daily basis, before it is converted into a form that computers can understand.

[0008] "Natural language processing technology" is the technology that enables computers to understand, analyze, and process human language.

[0009] A "database" is a collection of information that efficiently stores organized information and allows it to be searched and retrieved as needed.

[0010] "Facility information" refers to detailed data about a specific facility, such as its name, address, and available hours. [Brief explanation of the drawing]

[0011] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5]This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0012] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0013] First, let's explain the terminology used in the following explanation.

[0014] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0015] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0016] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0017] In the following embodiments, the numbered communication I / F (Interface) is an interface that includes a communication processor, an antenna, and the like. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0018] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0019] [First Embodiment]

[0020] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0021] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0022] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0023] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0024] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0025] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0026] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0027] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0029] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0030] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0031] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0032] The system of this invention comprises a user terminal, a server, a natural language processing engine, and a database. This system is used when a user searches for a restaurant.

[0033] First, the user enters the conditions in natural language via a messaging app. For example, they can set the condition "Chinese restaurants within a 10-minute walk from a subway station." The user's device receives this information and sends it to the server.

[0034] The server passes the received user message to a natural language processing engine for analysis. This engine analyzes the user's request and extracts specific search criteria. Using the analyzed results, the server accesses a facility information database and searches for restaurants that match the criteria.

[0035] The searched restaurant information, such as name, address, available hours, and reservation status, is formatted on the server and sent to the user's terminal.

[0036] The user terminal presents the user with information received from the server. This allows the user to quickly find the optimal restaurant that meets their criteria. Furthermore, the user can make a reservation based on the presented information if necessary. This enables the user to find a restaurant that meets their desired conditions in a short amount of time without hassle, making efficient facility selection possible through the system of this invention.

[0037] The following describes the processing flow.

[0038] Step 1:

[0039] Users input natural language text into messaging apps to recommend restaurants that meet specific criteria. For example, they might say, "I'm looking for a quiet cafe near the train station."

[0040] Step 2:

[0041] The terminal receives a message entered by the user and prepares to send that data to the server. During this process, it constructs a packet to ensure that the input content and user ID are reliably transmitted.

[0042] Step 3:

[0043] The server receives user messages sent from the terminal and passes them to the natural language processing engine. The messages are then placed in a queue for analysis.

[0044] Step 4:

[0045] The server's natural language processing engine analyzes the received text data and extracts key conditions (e.g., location, restaurant style, and other specific requests). The extracted results are stored as structured data.

[0046] Step 5:

[0047] The server queries the facility information database based on conditions obtained through natural language processing and retrieves a list of relevant restaurant information. In this process, location information is cross-referenced to narrow down the list of candidate restaurants.

[0048] Step 6:

[0049] The server converts the retrieved restaurant information into a user-friendly format. For example, it formats and lists the restaurant name, address, available reservation times, and any special notes.

[0050] Step 7:

[0051] The server sends the formatted restaurant information to the terminal. The response data is formatted with display on the user's terminal in mind.

[0052] Step 8:

[0053] The device receives restaurant information retrieved from the server and presents it to the user via the messaging app. The presented information may include links to view details and options for making reservations.

[0054] Step 9:

[0055] Users can review the presented restaurant information and, if they find a restaurant they like, take the next step, such as making a reservation.

[0056] (Example 1)

[0057] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0058] Currently, many location search systems struggle to efficiently process complex natural language conditions and provide users with relevant information quickly. Furthermore, they lack features for sharing search results across various communication devices and for presenting additional information of value to users. As a result, users inevitably spend considerable time and effort obtaining the information they need.

[0059] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0060] In this invention, the server includes means for receiving information entered in natural language from a user input device, means for analyzing the information using natural language processing technology to extract specific keywords and conditions, and means for querying an information database based on the extracted search conditions to obtain facility information that matches the conditions. This allows users to easily input even complex conditions and quickly and efficiently obtain information that matches those conditions. Furthermore, it is possible to enhance the value to the user by making it easier to share search results between different communication devices and visually presenting available time slots and additional information.

[0061] A "user input device" is a device that allows a user to input information in natural language and transmit it to a system.

[0062] "Natural language processing technology" is a technique that interprets text written in natural language and converts it into a format that machines can understand.

[0063] An "information database" is a data storage system in which specific information is structured and stored, and can be searched by queries as needed.

[0064] A "query" is a command or request used to retrieve specific information from a database.

[0065] "Facility information" refers to detailed data about a specific facility, including information such as its name, location, operating hours, and reservation status.

[0066] "To present visually" means to display information to the user using a graphical interface or other visual means.

[0067] A "communication device" is a device that enables the transmission and reception of data over a network.

[0068] The present invention is configured as a system including a user input device, a server, a natural language processing engine, and an information database. This system is designed to allow users to quickly and efficiently obtain desired facility information by inputting conditions in natural language.

[0069] The user accesses the messaging app using a user input device and enters their desired conditions in natural language. This user input device could be a smartphone or tablet, for example. The entered information is sent to the server via the network.

[0070] The server is equipped with a natural language processing engine, which uses natural language processing libraries such as SpaCy and NLTK. This engine analyzes the received natural language information and extracts specific keywords and conditions. Based on these analysis results, the server queries the information database to find facility information that matches the conditions.

[0071] The information database stores detailed information about numerous facilities, and the desired data can be quickly retrieved using query languages ​​such as SQL. The retrieved facility information is formatted by the server and sent to the user input device.

[0072] Users can view the presented facility information on the user input device and make reservations as needed. This entire process makes it easy for users to find facilities that meet their desired criteria.

[0073] For example, if a user enters "I want to find a quiet cafe within a 5-minute walk," the natural language processing engine extracts keywords such as "5-minute walk" and "quiet cafe" and queries the database. As a result, cafes that match the criteria are searched for, and that information is provided to the user. This mechanism enhances user convenience by combining it with the use of prompt sentences in the generative AI model.

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

[0075] Step 1:

[0076] The user opens a messaging app on their user input device and enters their desired conditions in natural language. Specifically, this step involves the user entering conditions into a text input box and pressing the send button. The input is natural language text, such as "I'm looking for a quiet cafe within a 5-minute walk." The output is this information, encoded as data, stored on the user's device.

[0077] Step 2:

[0078] The user terminal sends user input information to the server using a network protocol (e.g., HTTP / HTTPS). During this process, user input data is packetized and prepared for transmission. The input is the user's natural language message, and the output is the request data sent to the server.

[0079] Step 3:

[0080] The server passes the received data to a natural language processing engine for analysis. Specifically, it uses tools such as SpaCy or NLTK to tokenize the text data, perform semantic analysis, and extract keywords that can be used as search criteria (e.g., "5 minutes on foot," "quiet cafe"). The input is natural language text received from the user, and the output is a search query with specified criteria.

[0081] Step 4:

[0082] The server queries the information database using the parsed search query and retrieves data that matches the criteria. Specifically, an SQL query is generated and executed by the database management system. The input is the search query expanded by the server, and the output is a list of facility information retrieved from the database.

[0083] Step 5:

[0084] The server formats the facility information retrieved from the database into a user-friendly format. Here, the response data is structured in JSON format. The input is the raw data of the retrieved facility information, and the output is the formatted JSON data.

[0085] Step 6:

[0086] The server sends formatted data to the user terminal. The server transmits this data using network protocols and performs the transformation until the data reaches the user terminal. The input is formatted information data, and the output is the data displayed on the user terminal.

[0087] Step 7:

[0088] The user terminal displays the received data in a graphical user interface (GUI), presenting facility information to the user. Specifically, a display engine (e.g., React or Vue.js) performs the rendering process, visually outputting the information. The input is JSON data received from the server, and the output is a visual display of facility information presented to the user.

[0089] Step 8:

[0090] The user reviews the presented information and makes a reservation or selection as needed. Specifically, the user completes the action by clicking a reservation button or link. This input is the user's choice and actions on their device, and the output is the reservation or acquisition of detailed information based on the user's actions.

[0091] (Application Example 1)

[0092] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0093] The current facility search system requires users to input criteria as text, and voice support is insufficient. Furthermore, even when facility information matching the criteria is retrieved, the visual presentation of the information and the booking process are complex, resulting in usability issues.

[0094] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0095] In this invention, the server includes means for receiving natural language information input by voice from a user terminal, means for analyzing the information using natural language processing technology and converting it into text data using speech recognition technology, and means for searching a database based on the analyzed information and obtaining facility information that matches the specified conditions. This enables intuitive and rapid acquisition of facility information using voice input, as well as the accompanying visual information presentation and reservation operation.

[0096] "Voice input" is a method of inputting information by having the user speak into the device.

[0097] "Natural language processing technology" is a technology that enables computers to understand and analyze human language.

[0098] "Speech recognition technology" is a technology in which a computer analyzes input speech and converts it into digital text.

[0099] "Text data" refers to digital character information converted using speech recognition technology.

[0100] A "database" is a collection of information that is systematically stored and can be searched and retrieved.

[0101] "Visual presentation" refers to a method of providing information to users in a visible form through displays or monitors.

[0102] "Reservation operation" refers to the act of specifying the desired date and time for a selected facility or service and completing the procedure in advance.

[0103] This system is implemented using user terminals, servers, a natural language processing engine including speech recognition technology, and a database containing facility information.

[0104] The user enters the conditions by voice using a user device such as a smartphone. This voice data is converted into text data by speech recognition software built into the device. Google's Speech-to-Text API may be used for this conversion. Subsequently, a natural language processing engine analyzes this text data and extracts the information necessary for database searches that match the conditions. IBM Watson or Google Dialogflow can be used for this analysis.

[0105] The server receives the analyzed information, searches the database, and retrieves facility information that matches the criteria. This database includes basic facility information and available reservation times.

[0106] The acquired information is transmitted to the user's terminal and visually displayed on the terminal's screen. Based on the displayed information, the user can, for example, make a restaurant reservation.

[0107] For example, if a user voice-inputs "Tell me some recommended ramen restaurants in Ikebukuro," the system will search for ramen restaurants around Ikebukuro and display a list of restaurants that meet the criteria. The restaurant information also displays available reservation times, allowing users to make reservations on the spot.

[0108] An example of a prompt to input into the generating AI model is, "Based on the restaurant criteria requested by the user, list French restaurants near Tokyo Tower and present them to the user."

[0109] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0110] Step 1:

[0111] The user provides voice input to the device. This input is captured by the device as voice data.

[0112] Step 2:

[0113] The terminal uses speech recognition software to convert speech data into text data. Here, the software analyzes the speech waveform and uses a language model to generate the corresponding string. The input is speech data, and the output is a text-based instruction.

[0114] Step 3:

[0115] The terminal sends text data to the server. The server receives this text data and prepares it for the next step.

[0116] Step 4:

[0117] The server analyzes the received text data using a natural language processing engine. This analysis extracts the intent from the text and the information necessary for the search criteria. The input is the received text data, and the output is structured conditional information.

[0118] Step 5:

[0119] The server converts structured conditional information into a database search query and searches the database. This search operation retrieves facility information that matches the criteria. The input is conditional information, and the output is a list of facility information.

[0120] Step 6:

[0121] The server organizes the acquired facility information and formats it into a visually presentable format. This formatting makes the information easier for users to understand. The input is a list of facility information, and the output is the formatted information.

[0122] Step 7:

[0123] The server sends the formatted information to the terminal. The terminal receives this information and displays it on its screen. The user can then select a facility.

[0124] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0125] This invention relates to a system that combines a user terminal, a server, a natural language processing engine, an emotion engine, and a facility information database. This system not only presents recommended facilities based on messages entered by the user in natural language, but also recognizes the user's emotions and enables flexible responses in accordance with those emotions.

[0126] Users use messaging apps to input and send specific conditions or requests in natural language. For example, they might send a request like, "I'm feeling a bit down today, so could you recommend a cafe where I can relax?" The user's device receives this message and forwards it to the server.

[0127] The server passes the received message to a natural language processing engine, which analyzes its content. This analysis extracts specific conditions and desires. Furthermore, the emotion engine detects emotions from the user's message and determines the user's psychological state. For example, the message might detect the emotion of "feeling depressed."

[0128] The server searches a facility information database based on the results of natural language processing and emotion engine analysis. This selects restaurants, cafes, and other facilities that are suitable for the user's state. If the user's emotions are positive, it can prioritize suggesting lively places; if negative, it can prioritize suggesting relaxing places.

[0129] The acquired information is formatted for user clarity and sent from the server to the user's terminal. The user's terminal displays the received information, allowing users to easily select and book facilities. This system enables users to quickly find places that match their current emotional state, resulting in a more personalized experience.

[0130] The following describes the processing flow.

[0131] Step 1:

[0132] Users describe the conditions of the facility they are looking for and their own emotional state in natural language using a messaging app and send the message. For example, they might type a message like, "I'm a little tired, so I'd like a quiet cafe."

[0133] Step 2:

[0134] The terminal receives a message entered by the user and prepares to send that data to the server. Here, the data is formatted so that the message content and user ID, etc., are transmitted accurately.

[0135] Step 3:

[0136] The server receives user messages sent from the terminal and passes the data to a natural language processing engine for analysis. This includes recognizing the input conditions and preferences and extracting important elements.

[0137] Step 4:

[0138] The server's natural language processing engine analyzes the results, which are then passed through an emotion engine to identify emotions from user messages. In this process, the emotion engine analyzes the input content from an emotional perspective, identifying states such as "tired" or "stressed."

[0139] Step 5:

[0140] The server queries the facility information database based on the extracted conditions and emotional information to find facilities that meet the criteria. Recommendations are taken into consideration based on emotional factors; for example, places that provide a sense of calm are prioritized.

[0141] Step 6:

[0142] The server formats the acquired facility information and lists it in a user-friendly format. This includes details such as the facility name, address, business hours, and whether reservations are accepted.

[0143] Step 7:

[0144] The server sends the formatted facility information to the terminal. The response sent is formatted to be easily understood by the user.

[0145] Step 8:

[0146] The device analyzes facility information received from the server and displays it to the user via the messaging app. This display may include links to view details and options for direct booking.

[0147] Step 9:

[0148] Based on the displayed information, users can select a facility that suits their needs and, if necessary, proceed to the next step, such as making a reservation or making an inquiry.

[0149] (Example 2)

[0150] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0151] In society, users face the challenge of quickly selecting an appropriate environment that suits their emotional state. In particular, accurately finding a suitable facility when experiencing negative emotions is difficult, preventing users from having a more personalized experience.

[0152] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0153] In this invention, the server includes means for receiving information input in natural language from a user terminal, means for analyzing the received information to recognize the user's emotional state, and means for searching a database based on the analyzed information and emotional state to obtain facility information corresponding to the user's emotions. This makes it possible to quickly and accurately provide appropriate facilities according to the user's emotional state.

[0154] A "user terminal" is an electronic information device used by users to input or receive information, and includes smartphones and personal computers.

[0155] "Natural language" refers to the language that humans use on a daily basis. Unlike programming languages, it is a language intended for communication between people.

[0156] "Means of receiving" refers to a technical device or mechanism for receiving data or information transmitted from an external source.

[0157] "Means of analysis" refers to technical devices or algorithms used to analyze received information, understand its structure and content, and extract specific data.

[0158] "Means for recognizing emotional states" refers to a technical device or process for determining a user's psychological or emotional state based on information from the user.

[0159] A "database" is a system for systematically organizing and managing large amounts of data, and it is a structured collection of information that can be easily searched and accessed.

[0160] "Facility information" refers to detailed data about a specific location, including information such as name, address, business hours, and characteristics.

[0161] "Formatting methods" refer to technologies or functions used to convert acquired data or information into a format that is easy for users to understand.

[0162] This invention relates to a system combining a user terminal, a server, a natural language processing engine, an emotion recognition engine, and a database. The user terminal is an electronic information device such as a smartphone or personal computer, and provides a means for the user to input information in natural language and transmit it to the server. The purpose of this system is to quickly provide facility information that corresponds to the user's emotional state.

[0163] The user might input a message such as, "I want to relax today, so please tell me a quiet place." This message is received by the user's device and sent to the server. The server uses natural language processing libraries like spacy or nltk to analyze the received message and extract the user's wishes and conditions. Simultaneously, an emotion recognition engine uses the Google Cloud Natural Language API to analyze the user's emotional state and recognize that it is the emotion of wanting to relax.

[0164] Furthermore, the server searches the database for appropriate facility information based on the extracted conditions, preferences, and emotional state. This database includes facility names, locations, business hours, and features. The information obtained through the search is formatted in a user-friendly format and sent to the user's terminal.

[0165] As a concrete example, if a user inputs "I'm looking for a lively place to unwind," the server recognizes this positive emotional state and presents lively restaurants and cafes from its database. This allows the user to efficiently select the most suitable establishment based on their emotional state. Another possible prompt for the generating AI model would be "Please recommend a place that would be good for a user who wants to feel more energetic."

[0166] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0167] Step 1:

[0168] The user uses a messaging app to type a natural language message about their wishes and feelings. This message might include something like, "I want to relax today, so I'd like to know about quiet places." The entered information is prepared as text data on the device. The device then prepares this text data to be sent to a server over the internet.

[0169] Step 2:

[0170] The server retrieves natural language messages received from the user's terminal. The received text data is passed to a natural language processing engine. Here, the server uses libraries such as spaCy or NLTK to tokenize the message and parse its keywords and structure. The input is a text message from the user, and the output is information about the user's wishes and conditions.

[0171] Step 3:

[0172] The server passes the analyzed message data through an emotion recognition engine. This process analyzes the user's emotional state using tools such as the Google Cloud Natural Language API. Specific words and phrases are scored to quantify emotions, such as positive or negative. The input is the analyzed message data, and the output is the user's emotion score.

[0173] Step 4:

[0174] The server searches the facility information database based on the results of natural language processing and sentiment analysis. It uses SQL queries to retrieve facility information that matches the user's preferences and emotional state. The input is the user's preferences and emotional state, and the output is a list of matching facility information.

[0175] Step 5:

[0176] The server formats the acquired facility information into a format suitable for the user's terminal. Filtering and format conversion are performed to transform the information into something easily understandable to the user. The input is a list of facility information, and the output is the formatted facility information.

[0177] Step 6:

[0178] The server sends formatted facility information to the user's terminal. The terminal displays the received information on its screen, allowing the user to view and select details for each facility. The input is formatted facility information, and the output is visual information provided to the user.

[0179] (Application Example 2)

[0180] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0181] Conventional facility search systems lacked the flexibility to respond based on user emotions, resulting in users only being able to find the optimal facility by simply entering facility criteria. There is a need for a system that can make choices while taking the user's psychological state into consideration.

[0182] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0183] In this invention, the server includes means for receiving information input in natural language from a user terminal, means for analyzing the information using natural language processing technology, and means for detecting emotions from the analyzed information and determining the user's psychological state. This enables flexible facility suggestions tailored to the user's emotional state.

[0184] A "user terminal" is a communication device used by users to input information and receive results.

[0185] "Natural language processing technology" is a technology that enables computers to understand and analyze the language that humans use on a daily basis.

[0186] "Means for detecting emotions and determining psychological state" refers to technology that identifies a user's emotions and evaluates their psychological state based on text received from a communication device.

[0187] A "database" is a collection of information that is organized and managed in a way that allows for efficient searching.

[0188] "Facility information" refers to data about a specific location or service, and is used to select a facility that meets the user's requirements.

[0189] "Flexible response" refers to the ability to appropriately adjust to the situation and provide services tailored to the individual needs of the users.

[0190] To realize this invention, the user first inputs information in natural language using a communication terminal. The communication terminal receives the user's input and transmits the data to a server. The server analyzes the received natural language data using natural language processing technology. Through this process, specific conditions and requests are extracted from the input text.

[0191] Next, the server employs technology to detect emotions and determine the user's psychological state. As part of this technology, an emotion engine is used, which identifies the user's emotions from received messages and evaluates their psychological state. Based on this information, the server searches a database to retrieve facility information that best suits the user's conditions and psychological state.

[0192] Afterward, the acquired facility information is transmitted back to the communication terminal and presented to the user. The presented information includes customized information based on the user's emotional state, allowing the user to make flexible facility selections that take their current psychological condition into account.

[0193] For example, if a user enters "I'd like a quiet cafe today," the server can consider that preference and emotion and suggest cafes with a quiet atmosphere. It is expected that Python and natural language processing libraries would be used in the process supporting this entire operation.

[0194] Examples of prompts include "Where are some relaxing cafes?" or "I want to unwind, so I'd like to know about some quiet places." In response to such prompts, the system provides appropriate facility information.

[0195] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0196] Step 1:

[0197] The user inputs their wishes and feelings in natural language into the communication terminal. This input is text data, such as "Today I'd like to go to a relaxing cafe." The input data is retrieved by the terminal and sent to the server.

[0198] Step 2:

[0199] The server analyzes natural language input data received from the terminal. Natural language processing techniques are used to analyze the input text and extract specific desires or conditions. Keywords such as "relax" and "cafe" are identified in the input text, and these keywords are output as a result of the analysis.

[0200] Step 3:

[0201] The server uses an emotion engine to detect the user's emotions from the received text and determine their psychological state. The input to this process is the linguistic data of the user's text, and the output is an emotional state such as "I want to relax."

[0202] Step 4:

[0203] The server searches the database based on the analysis results and sentiment data. Specifically, it retrieves facility information from the database that matches the conditions and sentiments extracted in the analysis. In this step, the conditions and sentiment data are used as input, and a list of matching facilities is obtained as output.

[0204] Step 5:

[0205] The acquired facility information is transmitted from the server to the terminal. The terminal receives the information and displays it to the user. The input is facility information data, and the output is a user-friendly format that suggests the facilities.

[0206] Step 6:

[0207] The user views facility information presented on the device and selects a facility that suits their situation. The selected facility is the most suitable place based on the user's psychological state.

[0208] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0209] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0210] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0211] [Second Embodiment]

[0212] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0213] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0214] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0215] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0216] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0217] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0218] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0219] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0220] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0221] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0222] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0223] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0224] The system of this invention comprises a user terminal, a server, a natural language processing engine, and a database. This system is used when a user searches for a restaurant.

[0225] First, the user enters the conditions in natural language via a messaging app. For example, they can set the condition "Chinese restaurants within a 10-minute walk from a subway station." The user's device receives this information and sends it to the server.

[0226] The server passes the received user message to a natural language processing engine for analysis. This engine analyzes the user's request and extracts specific search criteria. Using the analyzed results, the server accesses a facility information database and searches for restaurants that match the criteria.

[0227] The searched restaurant information, such as name, address, available hours, and reservation status, is formatted on the server and sent to the user's terminal.

[0228] The user terminal presents the user with information received from the server. This allows the user to quickly find the optimal restaurant that meets their criteria. Furthermore, the user can make a reservation based on the presented information if necessary. This enables the user to find a restaurant that meets their desired conditions in a short amount of time without hassle, making efficient facility selection possible through the system of this invention.

[0229] The following describes the processing flow.

[0230] Step 1:

[0231] Users input natural language text into messaging apps to recommend restaurants that meet specific criteria. For example, they might say, "I'm looking for a quiet cafe near the train station."

[0232] Step 2:

[0233] The terminal receives a message entered by the user and prepares to send that data to the server. During this process, it constructs a packet to ensure that the input content and user ID are reliably transmitted.

[0234] Step 3:

[0235] The server receives user messages sent from the terminal and passes them to the natural language processing engine. The messages are then placed in a queue for analysis.

[0236] Step 4:

[0237] The server's natural language processing engine analyzes the received text data and extracts key conditions (e.g., location, restaurant style, and other specific requests). The extracted results are stored as structured data.

[0238] Step 5:

[0239] The server queries the facility information database based on conditions obtained through natural language processing and retrieves a list of relevant restaurant information. In this process, location information is cross-referenced to narrow down the list of candidate restaurants.

[0240] Step 6:

[0241] The server converts the retrieved restaurant information into a user-friendly format. For example, it formats and lists the restaurant name, address, available reservation times, and any special notes.

[0242] Step 7:

[0243] The server sends the formatted restaurant information to the terminal. The response data is formatted with display on the user's terminal in mind.

[0244] Step 8:

[0245] The device receives restaurant information retrieved from the server and presents it to the user via the messaging app. The presented information may include links to view details and options for making reservations.

[0246] Step 9:

[0247] Users can review the presented restaurant information and, if they find a restaurant they like, take the next step, such as making a reservation.

[0248] (Example 1)

[0249] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0250] Currently, many location search systems struggle to efficiently process complex natural language conditions and provide users with relevant information quickly. Furthermore, they lack features for sharing search results across various communication devices and for presenting additional information of value to users. As a result, users inevitably spend considerable time and effort obtaining the information they need.

[0251] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0252] In this invention, the server includes means for receiving information entered in natural language from a user input device, means for analyzing the information using natural language processing technology to extract specific keywords and conditions, and means for querying an information database based on the extracted search conditions to obtain facility information that matches the conditions. This allows users to easily input even complex conditions and quickly and efficiently obtain information that matches those conditions. Furthermore, it is possible to enhance the value to the user by making it easier to share search results between different communication devices and visually presenting available time slots and additional information.

[0253] A "user input device" is a device that allows a user to input information in natural language and transmit it to a system.

[0254] "Natural language processing technology" is a technique that interprets text written in natural language and converts it into a format that machines can understand.

[0255] An "information database" is a data storage system in which specific information is structured and stored, and can be searched by queries as needed.

[0256] A "query" is a command or request used to retrieve specific information from a database.

[0257] "Facility information" refers to detailed data about a specific facility, including information such as its name, location, operating hours, and reservation status.

[0258] "To present visually" means to display information to the user using a graphical interface or other visual means.

[0259] A "communication device" is a device that enables the transmission and reception of data over a network.

[0260] The present invention is configured as a system including a user input device, a server, a natural language processing engine, and an information database. This system is designed to allow users to quickly and efficiently obtain desired facility information by inputting conditions in natural language.

[0261] The user accesses the messaging app using a user input device and enters their desired conditions in natural language. This user input device could be a smartphone or tablet, for example. The entered information is sent to the server via the network.

[0262] The server is equipped with a natural language processing engine, which uses natural language processing libraries such as SpaCy and NLTK. This engine analyzes the received natural language information and extracts specific keywords and conditions. Based on these analysis results, the server queries the information database to find facility information that matches the conditions.

[0263] The information database stores detailed information about numerous facilities, and the desired data can be quickly retrieved using query languages ​​such as SQL. The retrieved facility information is formatted by the server and sent to the user input device.

[0264] Users can view the presented facility information on the user input device and make reservations as needed. This entire process makes it easy for users to find facilities that meet their desired criteria.

[0265] For example, if a user enters "I want to find a quiet cafe within a 5-minute walk," the natural language processing engine extracts keywords such as "5-minute walk" and "quiet cafe" and queries the database. As a result, cafes that match the criteria are searched for, and that information is provided to the user. This mechanism enhances user convenience by combining it with the use of prompt sentences in the generative AI model.

[0266] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0267] Step 1:

[0268] The user opens a messaging app on their user input device and enters their desired conditions in natural language. Specifically, this step involves the user entering conditions into a text input box and pressing the send button. The input is natural language text, such as "I'm looking for a quiet cafe within a 5-minute walk." The output is this information, encoded as data, stored on the user's device.

[0269] Step 2:

[0270] The user terminal sends user input information to the server using a network protocol (e.g., HTTP / HTTPS). During this process, user input data is packetized and prepared for transmission. The input is the user's natural language message, and the output is the request data sent to the server.

[0271] Step 3:

[0272] The server passes the received data to a natural language processing engine for analysis. Specifically, it uses tools such as SpaCy or NLTK to tokenize the text data, perform semantic analysis, and extract keywords that can be used as search criteria (e.g., "5 minutes on foot," "quiet cafe"). The input is natural language text received from the user, and the output is a search query with specified criteria.

[0273] Step 4:

[0274] The server queries the information database using the parsed search query and retrieves data that matches the criteria. Specifically, an SQL query is generated and executed by the database management system. The input is the search query expanded by the server, and the output is a list of facility information retrieved from the database.

[0275] Step 5:

[0276] The server formats the facility information retrieved from the database into a user-friendly format. Here, the response data is structured in JSON format. The input is the raw data of the retrieved facility information, and the output is the formatted JSON data.

[0277] Step 6:

[0278] The server sends formatted data to the user terminal. The server transmits this data using network protocols and performs the transformation until the data reaches the user terminal. The input is formatted information data, and the output is the data displayed on the user terminal.

[0279] Step 7:

[0280] The user terminal displays the received data on a graphical user interface (GUI) to present facility information to the user. Specifically here, a display engine (e.g., React or Vue.js) performs rendering processing and the information is visually output. The input is JSON data received from the server, and the output is a visual display of the facility information presented to the user.

[0281] Step 8:

[0282] The user examines the presented information and makes a reservation or selection according to the requirements. Specifically, the user clicks a reservation button or link to complete the action. This input is the selection of the user acting on the user terminal, and the output is the acquisition of a reservation or detailed information based on the user operation.

[0283] (Application Example 1)

[0284] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0285] In the current facility search system, the user needs to input conditions in text, and voice utilization is insufficient. Also, even if facility information that meets the conditions is obtained, the visual presentation of the information and its reservation operation are complex and there are problems in usability.

[0286] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0287] In this invention, the server includes means for receiving natural language information input by voice from the user terminal, means for analyzing the information using natural language processing technology and converting it into text data using voice recognition technology, and means for searching a database based on the analyzed information and obtaining facility information that meets the conditions. Thereby, intuitive and rapid acquisition of facility information using voice input, and accompanying visual information presentation and reservation operation become possible.

[0288] "Voice input" is a method of inputting information by having the user speak into the device.

[0289] "Natural language processing technology" is a technology that enables computers to understand and analyze human language.

[0290] "Speech recognition technology" is a technology in which a computer analyzes input speech and converts it into digital text.

[0291] "Text data" refers to digital character information converted using speech recognition technology.

[0292] A "database" is a collection of information that is systematically stored and can be searched and retrieved.

[0293] "Visual presentation" refers to a method of providing information to users in a visible form through displays or monitors.

[0294] "Reservation operation" refers to the act of specifying the desired date and time for a selected facility or service and completing the procedure in advance.

[0295] This system is implemented using user terminals, servers, a natural language processing engine including speech recognition technology, and a database containing facility information.

[0296] The user uses a user device such as a smartphone to input conditions by voice. This voice data is converted into text data by speech recognition software built into the device. Google's Speech-to-Text API may be used for this conversion. Subsequently, a natural language processing engine analyzes this text data and extracts the information necessary for database searches that match the conditions. IBM Watson or Google Dialogflow can be used for this analysis.

[0297] The server receives the analyzed information, searches the database, and retrieves facility information that matches the criteria. This database includes basic facility information and available reservation times.

[0298] The acquired information is transmitted to the user's terminal and visually displayed on the terminal's screen. Based on the displayed information, the user can, for example, make a restaurant reservation.

[0299] For example, if a user voice-inputs "Tell me some recommended ramen restaurants in Ikebukuro," the system will search for ramen restaurants around Ikebukuro and display a list of restaurants that meet the criteria. The restaurant information also displays available reservation times, allowing users to make reservations on the spot.

[0300] An example of a prompt to input into the generating AI model is, "Based on the restaurant criteria requested by the user, list French restaurants near Tokyo Tower and present them to the user."

[0301] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0302] Step 1:

[0303] The user provides voice input to the device. This input is captured by the device as voice data.

[0304] Step 2:

[0305] The terminal uses speech recognition software to convert speech data into text data. Here, the software analyzes the speech waveform and uses a language model to generate the corresponding string. The input is speech data, and the output is a text-based instruction.

[0306] Step 3:

[0307] The terminal sends text data to the server. The server receives this text data and prepares it for the next step.

[0308] Step 4:

[0309] The server analyzes the received text data using a natural language processing engine. In this analysis, the intention is read from the text and the information necessary for the search conditions is extracted. The input is the received text data, and the output is structured condition information.

[0310] Step 5:

[0311] The server converts the structured condition information into a query for database search and searches the database. In this search operation, facility information that meets the conditions is obtained. The input is the condition information, and the output is a list of facility information.

[0312] Step 6:

[0313] The server organizes the obtained facility information and formats it into a visually presentable form. This formatting makes the information easier for the user to understand. The input is a list of facility information, and the output is the formatted information.

[0314] Step 7:

[0315] The server sends the formatted information to the terminal. The terminal receives this information and displays it on the display. The user can thereby select a facility.

[0316] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform specific processing using the user's emotion.

[0317] This invention relates to a system that combines a user terminal, a server, a natural language processing engine, an emotion engine, and a facility information database. This system not only presents recommended facilities based on messages entered by the user in natural language, but also recognizes the user's emotions and enables flexible responses in accordance with those emotions.

[0318] Users use messaging apps to input and send specific conditions or requests in natural language. For example, they might send a request like, "I'm feeling a bit down today, so could you recommend a cafe where I can relax?" The user's device receives this message and forwards it to the server.

[0319] The server passes the received message to a natural language processing engine, which analyzes its content. This analysis extracts specific conditions and desires. Furthermore, the emotion engine detects emotions from the user's message and determines the user's psychological state. For example, the message might detect the emotion of "feeling depressed."

[0320] The server searches a facility information database based on the results of natural language processing and emotion engine analysis. This selects restaurants, cafes, and other facilities that are suitable for the user's state. If the user's emotions are positive, it can prioritize suggesting lively places; if negative, it can prioritize suggesting relaxing places.

[0321] The acquired information is formatted for user clarity and sent from the server to the user's terminal. The user's terminal displays the received information, allowing users to easily select and book facilities. This system enables users to quickly find places that match their current emotional state, resulting in a more personalized experience.

[0322] The following describes the processing flow.

[0323] Step 1:

[0324] Users describe the conditions of the facility they are looking for and their own emotional state in natural language using a messaging app and send the message. For example, they might type a message like, "I'm a little tired, so I'd like a quiet cafe."

[0325] Step 2:

[0326] The terminal receives a message entered by the user and prepares to send that data to the server. Here, the data is formatted so that the message content and user ID, etc., are transmitted accurately.

[0327] Step 3:

[0328] The server receives user messages sent from the terminal and passes the data to a natural language processing engine for analysis. This includes recognizing the input conditions and preferences and extracting important elements.

[0329] Step 4:

[0330] The server's natural language processing engine analyzes the results, which are then passed through an emotion engine to identify emotions from user messages. In this process, the emotion engine analyzes the input content from an emotional perspective, identifying states such as "tired" or "stressed."

[0331] Step 5:

[0332] The server queries the facility information database based on the extracted conditions and emotional information to find facilities that meet the criteria. Recommendations are taken into consideration based on emotional factors; for example, places that provide a sense of calm are prioritized.

[0333] Step 6:

[0334] The server formats the acquired facility information and lists it in a user-friendly format. This includes details such as the facility name, address, business hours, and whether reservations are accepted.

[0335] Step 7:

[0336] The server sends the formatted facility information to the terminal. The response sent is formatted to be easily understood by the user.

[0337] Step 8:

[0338] The device analyzes facility information received from the server and displays it to the user via the messaging app. This display may include links to view details and options for direct booking.

[0339] Step 9:

[0340] Based on the displayed information, users can select a facility that suits their needs and, if necessary, proceed to the next step, such as making a reservation or making an inquiry.

[0341] (Example 2)

[0342] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0343] In society, users face the challenge of quickly selecting an appropriate environment that suits their emotional state. In particular, accurately finding a suitable facility when experiencing negative emotions is difficult, preventing users from having a more personalized experience.

[0344] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0345] In this invention, the server includes means for receiving information input in natural language from a user terminal, means for analyzing the received information to recognize the user's emotional state, and means for searching a database based on the analyzed information and emotional state to obtain facility information corresponding to the user's emotions. This makes it possible to quickly and accurately provide appropriate facilities according to the user's emotional state.

[0346] A "user terminal" is an electronic information device used by users to input or receive information, and includes smartphones and personal computers.

[0347] "Natural language" refers to the language that humans use on a daily basis. Unlike programming languages, it is a language intended for communication between people.

[0348] "Means of receiving" refers to a technical device or mechanism for receiving data or information transmitted from an external source.

[0349] "Means of analysis" refers to technical devices or algorithms used to analyze received information, understand its structure and content, and extract specific data.

[0350] "Means for recognizing emotional states" refers to a technical device or process for determining a user's psychological or emotional state based on information from the user.

[0351] A "database" is a system for systematically organizing and managing large amounts of data, and it is a structured collection of information that can be easily searched and accessed.

[0352] "Facility information" refers to detailed data about a specific location, including information such as name, address, business hours, and characteristics.

[0353] "Formatting methods" refer to technologies or functions used to convert acquired data or information into a format that is easy for users to understand.

[0354] This invention relates to a system combining a user terminal, a server, a natural language processing engine, an emotion recognition engine, and a database. The user terminal is an electronic information device such as a smartphone or personal computer, and provides a means for the user to input information in natural language and transmit it to the server. The purpose of this system is to quickly provide facility information that corresponds to the user's emotional state.

[0355] The user might input a message such as, "I want to relax today, so please tell me a quiet place." This message is received by the user's device and sent to the server. The server uses natural language processing libraries like spacy or nltk to analyze the received message and extract the user's wishes and conditions. Simultaneously, an emotion recognition engine uses the Google Cloud Natural Language API to analyze the user's emotional state and recognize that it is the emotion of wanting to relax.

[0356] Furthermore, the server searches the database for appropriate facility information based on the extracted conditions, preferences, and emotional state. This database includes facility names, locations, business hours, and features. The information obtained through the search is formatted in a user-friendly format and sent to the user's terminal.

[0357] As a concrete example, if a user inputs "I'm looking for a lively place to unwind," the server recognizes this positive emotional state and presents lively restaurants and cafes from its database. This allows the user to efficiently select the most suitable establishment based on their emotional state. Another possible prompt for the generating AI model would be "Please recommend a place that would be good for a user who wants to feel more energetic."

[0358] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0359] Step 1:

[0360] The user uses a messaging app to type a natural language message about their wishes and feelings. This message might include something like, "I want to relax today, so I'd like to know about quiet places." The entered information is prepared as text data on the device. The device then prepares this text data to be sent to a server over the internet.

[0361] Step 2:

[0362] The server retrieves natural language messages received from the user's terminal. The received text data is passed to a natural language processing engine. Here, the server uses libraries such as spaCy or NLTK to tokenize the message and parse its keywords and structure. The input is a text message from the user, and the output is information about the user's wishes and conditions.

[0363] Step 3:

[0364] The server passes the analyzed message data through an emotion recognition engine. This process analyzes the user's emotional state using tools such as the Google Cloud Natural Language API. Specific words and phrases are scored to quantify emotions, such as positive or negative. The input is the analyzed message data, and the output is the user's emotion score.

[0365] Step 4:

[0366] The server searches the facility information database based on the results of natural language processing and sentiment analysis. It uses SQL queries to retrieve facility information that matches the user's preferences and emotional state. The input is the user's preferences and emotional state, and the output is a list of matching facility information.

[0367] Step 5:

[0368] The server formats the acquired facility information into a format suitable for the user's terminal. Filtering and format conversion are performed to transform the information into something easily understandable to the user. The input is a list of facility information, and the output is the formatted facility information.

[0369] Step 6:

[0370] The server sends formatted facility information to the user's terminal. The terminal displays the received information on its screen, allowing the user to view and select details for each facility. The input is formatted facility information, and the output is visual information provided to the user.

[0371] (Application Example 2)

[0372] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0373] Conventional facility search systems lacked the flexibility to respond based on user emotions, resulting in users only being able to find the optimal facility by simply entering facility criteria. There is a need for a system that can make choices while taking the user's psychological state into consideration.

[0374] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0375] In this invention, the server includes means for receiving information input in natural language from a user terminal, means for analyzing the information using natural language processing technology, and means for detecting emotions from the analyzed information and determining the user's psychological state. This enables flexible facility suggestions tailored to the user's emotional state.

[0376] A "user terminal" is a communication device used by users to input information and receive results.

[0377] "Natural language processing technology" is a technology that enables computers to understand and analyze the language that humans use on a daily basis.

[0378] "Means for detecting emotions and determining psychological state" refers to technology that identifies a user's emotions and evaluates their psychological state based on text received from a communication device.

[0379] A "database" is a collection of information that is organized and managed in a way that allows for efficient searching.

[0380] "Facility information" refers to data about a specific location or service, and is used to select a facility that meets the user's requirements.

[0381] "Flexible response" refers to the ability to appropriately adjust to the situation and provide services tailored to the individual needs of the users.

[0382] To realize this invention, the user first inputs information in natural language using a communication terminal. The communication terminal receives the user's input and transmits the data to a server. The server analyzes the received natural language data using natural language processing technology. Through this process, specific conditions and requests are extracted from the input text.

[0383] Next, the server employs technology to detect emotions and determine the user's psychological state. As part of this technology, an emotion engine is used, which identifies the user's emotions from received messages and evaluates their psychological state. Based on this information, the server searches a database to retrieve facility information that best suits the user's conditions and psychological state.

[0384] Afterward, the acquired facility information is transmitted back to the communication terminal and presented to the user. The presented information includes customized information based on the user's emotional state, allowing the user to make flexible facility selections that take their current psychological condition into account.

[0385] For example, if a user enters "I'd like a quiet cafe today," the server can consider that preference and emotion and suggest cafes with a quiet atmosphere. It is expected that Python and natural language processing libraries would be used in the process supporting this entire operation.

[0386] Examples of prompts include "Where are some relaxing cafes?" or "I want to unwind, so I'd like to know about some quiet places." In response to such prompts, the system provides appropriate facility information.

[0387] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0388] Step 1:

[0389] The user inputs their wishes and feelings in natural language into the communication terminal. This input is text data, such as "Today I'd like to go to a relaxing cafe." The input data is retrieved by the terminal and sent to the server.

[0390] Step 2:

[0391] The server analyzes natural language input data received from the terminal. Natural language processing techniques are used to analyze the input text and extract specific desires or conditions. Keywords such as "relax" and "cafe" are identified in the input text, and these keywords are output as a result of the analysis.

[0392] Step 3:

[0393] The server uses an emotion engine to detect the user's emotions from the received text and determine their psychological state. The input to this process is the linguistic data of the user's text, and the output is an emotional state such as "I want to relax."

[0394] Step 4:

[0395] The server searches the database based on the analysis results and sentiment data. Specifically, it retrieves facility information from the database that matches the conditions and sentiments extracted in the analysis. In this step, the conditions and sentiment data are used as input, and a list of matching facilities is obtained as output.

[0396] Step 5:

[0397] The acquired facility information is transmitted from the server to the terminal. The terminal receives the information and displays it to the user. The input is facility information data, and the output is a user-friendly format that suggests the facilities.

[0398] Step 6:

[0399] The user views facility information presented on the device and selects a facility that suits their situation. The selected facility is the most suitable place based on the user's psychological state.

[0400] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0401] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0402] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0403] [Third Embodiment]

[0404] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0405] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0406] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0407] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0408] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0409] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0410] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0411] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0412] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0413] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0414] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0415] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0416] The system of this invention comprises a user terminal, a server, a natural language processing engine, and a database. This system is used when a user searches for a restaurant.

[0417] First, the user enters the conditions in natural language via a messaging app. For example, they can set the condition "Chinese restaurants within a 10-minute walk from a subway station." The user's device receives this information and sends it to the server.

[0418] The server passes the received user message to a natural language processing engine for analysis. This engine analyzes the user's request and extracts specific search criteria. Using the analyzed results, the server accesses a facility information database and searches for restaurants that match the criteria.

[0419] The searched restaurant information, such as name, address, available hours, and reservation status, is formatted on the server and sent to the user's terminal.

[0420] The user terminal presents the user with information received from the server. This allows the user to quickly find the optimal restaurant that meets their criteria. Furthermore, the user can make a reservation based on the presented information if necessary. This enables the user to find a restaurant that meets their desired conditions in a short amount of time without hassle, making efficient facility selection possible through the system of this invention.

[0421] The following describes the processing flow.

[0422] Step 1:

[0423] Users input natural language text into messaging apps to recommend restaurants that meet specific criteria. For example, they might say, "I'm looking for a quiet cafe near the train station."

[0424] Step 2:

[0425] The terminal receives a message entered by the user and prepares to send that data to the server. During this process, it constructs a packet to ensure that the input content and user ID are reliably transmitted.

[0426] Step 3:

[0427] The server receives user messages sent from the terminal and passes them to the natural language processing engine. The messages are then placed in a queue for analysis.

[0428] Step 4:

[0429] The server's natural language processing engine analyzes the received text data and extracts key conditions (e.g., location, restaurant style, and other specific requests). The extracted results are stored as structured data.

[0430] Step 5:

[0431] The server queries the facility information database based on conditions obtained through natural language processing and retrieves a list of relevant restaurant information. In this process, location information is cross-referenced to narrow down the list of candidate restaurants.

[0432] Step 6:

[0433] The server converts the retrieved restaurant information into a user-friendly format. For example, it formats and lists the restaurant name, address, available reservation times, and any special notes.

[0434] Step 7:

[0435] The server sends the formatted restaurant information to the terminal. The response data is formatted with display on the user's terminal in mind.

[0436] Step 8:

[0437] The device receives restaurant information retrieved from the server and presents it to the user via the messaging app. The presented information may include links to view details and options for making reservations.

[0438] Step 9:

[0439] Users can review the presented restaurant information and, if they find a restaurant they like, take the next step, such as making a reservation.

[0440] (Example 1)

[0441] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0442] Currently, many location search systems struggle to efficiently process complex natural language conditions and provide users with relevant information quickly. Furthermore, they lack features for sharing search results across various communication devices and for presenting additional information of value to users. As a result, users inevitably spend considerable time and effort obtaining the information they need.

[0443] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0444] In this invention, the server includes means for receiving information entered in natural language from a user input device, means for analyzing the information using natural language processing technology to extract specific keywords and conditions, and means for querying an information database based on the extracted search conditions to obtain facility information that matches the conditions. This allows users to easily input even complex conditions and quickly and efficiently obtain information that matches those conditions. Furthermore, it is possible to enhance the value to the user by making it easier to share search results between different communication devices and visually presenting available time slots and additional information.

[0445] A "user input device" is a device that allows a user to input information in natural language and transmit it to a system.

[0446] "Natural language processing technology" is a technique that interprets text written in natural language and converts it into a format that machines can understand.

[0447] An "information database" is a data storage system in which specific information is structured and stored, and can be searched by queries as needed.

[0448] A "query" is a command or request used to retrieve specific information from a database.

[0449] "Facility information" refers to detailed data about a specific facility, including information such as its name, location, operating hours, and reservation status.

[0450] "To present visually" means to display information to the user using a graphical interface or other visual means.

[0451] A "communication device" is a device that enables the transmission and reception of data over a network.

[0452] The present invention is configured as a system including a user input device, a server, a natural language processing engine, and an information database. This system is designed to allow users to quickly and efficiently obtain desired facility information by inputting conditions in natural language.

[0453] The user accesses the messaging app using a user input device and enters their desired conditions in natural language. This user input device could be a smartphone or tablet, for example. The entered information is sent to the server via the network.

[0454] The server is equipped with a natural language processing engine, which uses natural language processing libraries such as SpaCy and NLTK. This engine analyzes the received natural language information and extracts specific keywords and conditions. Based on these analysis results, the server queries the information database to find facility information that matches the conditions.

[0455] The information database stores detailed information about numerous facilities, and the desired data can be quickly retrieved using query languages ​​such as SQL. The retrieved facility information is formatted by the server and sent to the user input device.

[0456] Users can view the presented facility information on the user input device and make reservations as needed. This entire process makes it easy for users to find facilities that meet their desired criteria.

[0457] For example, if a user enters "I want to find a quiet cafe within a 5-minute walk," the natural language processing engine extracts keywords such as "5-minute walk" and "quiet cafe" and queries the database. As a result, cafes that match the criteria are searched for, and that information is provided to the user. This mechanism enhances user convenience by combining it with the use of prompt sentences in the generative AI model.

[0458] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0459] Step 1:

[0460] The user opens a messaging app on their user input device and enters their desired conditions in natural language. Specifically, this step involves the user entering conditions into a text input box and pressing the send button. The input is natural language text, such as "I'm looking for a quiet cafe within a 5-minute walk." The output is this information, encoded as data, stored on the user's device.

[0461] Step 2:

[0462] The user terminal sends user input information to the server using a network protocol (e.g., HTTP / HTTPS). During this process, user input data is packetized and prepared for transmission. The input is the user's natural language message, and the output is the request data sent to the server.

[0463] Step 3:

[0464] The server passes the received data to a natural language processing engine for analysis. Specifically, it uses tools such as SpaCy or NLTK to tokenize the text data, perform semantic analysis, and extract keywords that can be used as search criteria (e.g., "5 minutes on foot," "quiet cafe"). The input is natural language text received from the user, and the output is a search query with specified criteria.

[0465] Step 4:

[0466] The server queries the information database using the parsed search query and retrieves data that matches the criteria. Specifically, an SQL query is generated and executed by the database management system. The input is the search query expanded by the server, and the output is a list of facility information retrieved from the database.

[0467] Step 5:

[0468] The server formats the facility information retrieved from the database into a user-friendly format. Here, the response data is structured in JSON format. The input is the raw data of the retrieved facility information, and the output is the formatted JSON data.

[0469] Step 6:

[0470] The server sends formatted data to the user terminal. The server transmits this data using network protocols and performs the transformation until the data reaches the user terminal. The input is formatted information data, and the output is the data displayed on the user terminal.

[0471] Step 7:

[0472] The user terminal displays the received data in a graphical user interface (GUI), presenting facility information to the user. Specifically, a display engine (e.g., React or Vue.js) performs the rendering process, visually outputting the information. The input is JSON data received from the server, and the output is a visual display of facility information presented to the user.

[0473] Step 8:

[0474] The user reviews the presented information and makes a reservation or selection as needed. Specifically, the user completes the action by clicking a reservation button or link. This input is the user's choice and actions on their device, and the output is the reservation or acquisition of detailed information based on the user's actions.

[0475] (Application Example 1)

[0476] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0477] The current facility search system requires users to input criteria as text, and voice support is insufficient. Furthermore, even when facility information matching the criteria is retrieved, the visual presentation of the information and the booking process are complex, resulting in usability issues.

[0478] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0479] In this invention, the server includes means for receiving natural language information input by voice from a user terminal, means for analyzing the information using natural language processing technology and converting it into text data using speech recognition technology, and means for searching a database based on the analyzed information and obtaining facility information that matches the specified conditions. This enables intuitive and rapid acquisition of facility information using voice input, as well as the accompanying visual information presentation and reservation operation.

[0480] "Voice input" is a method of inputting information by having the user speak into the device.

[0481] "Natural language processing technology" is a technology that enables computers to understand and analyze human language.

[0482] "Speech recognition technology" is a technology in which a computer analyzes input speech and converts it into digital text.

[0483] "Text data" refers to digital character information converted using speech recognition technology.

[0484] A "database" is a collection of information that is systematically stored and can be searched and retrieved.

[0485] "Visual presentation" refers to a method of providing information to users in a visible form through displays or monitors.

[0486] "Reservation operation" refers to the act of specifying the desired date and time for a selected facility or service and completing the procedure in advance.

[0487] This system is implemented using user terminals, servers, a natural language processing engine including speech recognition technology, and a database containing facility information.

[0488] The user uses a user device such as a smartphone to input conditions by voice. This voice data is converted into text data by speech recognition software built into the device. Google's Speech-to-Text API may be used for this conversion. Subsequently, a natural language processing engine analyzes this text data and extracts the information necessary for database searches that match the conditions. IBM Watson or Google Dialogflow can be used for this analysis.

[0489] The server receives the analyzed information, searches the database, and retrieves facility information that matches the criteria. This database includes basic facility information and available reservation times.

[0490] The acquired information is transmitted to the user's terminal and visually displayed on the terminal's screen. Based on the displayed information, the user can, for example, make a restaurant reservation.

[0491] For example, if a user voice-inputs "Tell me some recommended ramen restaurants in Ikebukuro," the system will search for ramen restaurants around Ikebukuro and display a list of restaurants that meet the criteria. The restaurant information also displays available reservation times, allowing users to make reservations on the spot.

[0492] An example of a prompt to input into the generating AI model is, "Based on the restaurant criteria requested by the user, list French restaurants near Tokyo Tower and present them to the user."

[0493] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0494] Step 1:

[0495] The user provides voice input to the device. This input is captured by the device as voice data.

[0496] Step 2:

[0497] The terminal uses speech recognition software to convert speech data into text data. Here, the software analyzes the speech waveform and uses a language model to generate the corresponding string. The input is speech data, and the output is a text-based instruction.

[0498] Step 3:

[0499] The terminal sends text data to the server. The server receives this text data and prepares it for the next step.

[0500] Step 4:

[0501] The server analyzes the received text data using a natural language processing engine. This analysis extracts the intent from the text and the information necessary for the search criteria. The input is the received text data, and the output is structured conditional information.

[0502] Step 5:

[0503] The server converts structured conditional information into a database search query and searches the database. This search operation retrieves facility information that matches the criteria. The input is conditional information, and the output is a list of facility information.

[0504] Step 6:

[0505] The server organizes the acquired facility information and formats it into a visually presentable format. This formatting makes the information easier for users to understand. The input is a list of facility information, and the output is the formatted information.

[0506] Step 7:

[0507] The server sends the formatted information to the terminal. The terminal receives this information and displays it on its screen. The user can then select a facility.

[0508] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0509] This invention relates to a system that combines a user terminal, a server, a natural language processing engine, an emotion engine, and a facility information database. This system not only presents recommended facilities based on messages entered by the user in natural language, but also recognizes the user's emotions and enables flexible responses in accordance with those emotions.

[0510] Users use messaging apps to input and send specific conditions or requests in natural language. For example, they might send a request like, "I'm feeling a bit down today, so could you recommend a cafe where I can relax?" The user's device receives this message and forwards it to the server.

[0511] The server passes the received message to a natural language processing engine, which analyzes its content. This analysis extracts specific conditions and desires. Furthermore, the emotion engine detects emotions from the user's message and determines the user's psychological state. For example, the message might detect the emotion of "feeling depressed."

[0512] The server searches a facility information database based on the results of natural language processing and emotion engine analysis. This selects restaurants, cafes, and other facilities that are suitable for the user's state. If the user's emotions are positive, it can prioritize suggesting lively places; if negative, it can prioritize suggesting relaxing places.

[0513] The acquired information is formatted for user clarity and sent from the server to the user's terminal. The user's terminal displays the received information, allowing users to easily select and book facilities. This system enables users to quickly find places that match their current emotional state, resulting in a more personalized experience.

[0514] The following describes the processing flow.

[0515] Step 1:

[0516] Users describe the conditions of the facility they are looking for and their own emotional state in natural language using a messaging app and send the message. For example, they might type a message like, "I'm a little tired, so I'd like a quiet cafe."

[0517] Step 2:

[0518] The terminal receives a message entered by the user and prepares to send that data to the server. Here, the data is formatted so that the message content and user ID, etc., are transmitted accurately.

[0519] Step 3:

[0520] The server receives user messages sent from the terminal and passes the data to a natural language processing engine for analysis. This includes recognizing the input conditions and preferences and extracting important elements.

[0521] Step 4:

[0522] The server's natural language processing engine analyzes the results, which are then passed through an emotion engine to identify emotions from user messages. In this process, the emotion engine analyzes the input content from an emotional perspective, identifying states such as "tired" or "stressed."

[0523] Step 5:

[0524] The server queries the facility information database based on the extracted conditions and emotional information to find facilities that meet the criteria. Emotional recommendations are taken into consideration, for example, places that provide a sense of calm are prioritized.

[0525] Step 6:

[0526] The server formats the retrieved facility information and lists it in a user-friendly format. This includes details such as the facility name, address, business hours, and whether reservations are accepted.

[0527] Step 7:

[0528] The server sends the formatted facility information to the terminal. The response sent is formatted to be easily understood by the user.

[0529] Step 8:

[0530] The device analyzes facility information received from the server and displays it to the user via the messaging app. This display may include links to view details and options for direct booking.

[0531] Step 9:

[0532] Based on the displayed information, users can select a facility that suits their needs and, if necessary, proceed to the next step, such as making a reservation or making an inquiry.

[0533] (Example 2)

[0534] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0535] In society, users face the challenge of quickly selecting an appropriate environment that suits their emotional state. In particular, accurately finding a suitable facility when experiencing negative emotions is difficult, preventing users from having a more personalized experience.

[0536] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0537] In this invention, the server includes means for receiving information input in natural language from a user terminal, means for analyzing the received information to recognize the user's emotional state, and means for searching a database based on the analyzed information and emotional state to obtain facility information corresponding to the user's emotions. This makes it possible to quickly and accurately provide appropriate facilities according to the user's emotional state.

[0538] A "user terminal" is an electronic information device used by users to input or receive information, and includes smartphones and personal computers.

[0539] "Natural language" refers to the language that humans use on a daily basis. Unlike programming languages, it is a language intended for communication between people.

[0540] "Means of receiving" refers to a technical device or mechanism for receiving data or information transmitted from an external source.

[0541] "Means of analysis" refers to technical devices or algorithms used to analyze received information, understand its structure and content, and extract specific data.

[0542] "Means for recognizing emotional states" refers to a technical device or process for determining a user's psychological or emotional state based on information from the user.

[0543] A "database" is a system for systematically organizing and managing large amounts of data, and it is a structured collection of information that can be easily searched and accessed.

[0544] "Facility information" refers to detailed data about a specific location, including information such as name, address, business hours, and characteristics.

[0545] "Formatting methods" refer to technologies or functions used to convert acquired data or information into a format that is easy for users to understand.

[0546] This invention relates to a system combining a user terminal, a server, a natural language processing engine, an emotion recognition engine, and a database. The user terminal is an electronic information device such as a smartphone or personal computer, and provides a means for the user to input information in natural language and transmit it to the server. The purpose of this system is to quickly provide facility information that corresponds to the user's emotional state.

[0547] The user might input a message such as, "I want to relax today, so please tell me a quiet place." This message is received by the user's device and sent to the server. The server uses natural language processing libraries like spacy or nltk to analyze the received message and extract the user's wishes and conditions. Simultaneously, an emotion recognition engine uses the Google Cloud Natural Language API to analyze the user's emotional state and recognize that it is the emotion of wanting to relax.

[0548] Furthermore, the server searches the database for appropriate facility information based on the extracted conditions, preferences, and emotional state. This database includes facility names, locations, business hours, and features. The information obtained through the search is formatted in a user-friendly format and sent to the user's terminal.

[0549] As a concrete example, if a user inputs "I'm looking for a lively place to unwind," the server recognizes this positive emotional state and presents lively restaurants and cafes from its database. This allows the user to efficiently select the most suitable establishment based on their emotional state. Another possible prompt for the generating AI model would be "Please recommend a place that would be good for a user who wants to feel more energetic."

[0550] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0551] Step 1:

[0552] The user uses a messaging app to type a natural language message about their wishes and feelings. This message might include something like, "I want to relax today, so I'd like to know about quiet places." The entered information is prepared as text data on the device. The device then prepares this text data to be sent to a server over the internet.

[0553] Step 2:

[0554] The server retrieves natural language messages received from the user's terminal. The received text data is passed to a natural language processing engine. Here, the server uses libraries such as spaCy or NLTK to tokenize the message and parse its keywords and structure. The input is a text message from the user, and the output is information about the user's wishes and conditions.

[0555] Step 3:

[0556] The server passes the analyzed message data through an emotion recognition engine. This process analyzes the user's emotional state using tools such as the Google Cloud Natural Language API. Specific words and phrases are scored to quantify emotions, such as positive or negative. The input is the analyzed message data, and the output is the user's emotion score.

[0557] Step 4:

[0558] The server searches the facility information database based on the results of natural language processing and sentiment analysis. It uses SQL queries to retrieve facility information that matches the user's preferences and emotional state. The input is the user's preferences and emotional state, and the output is a list of matching facility information.

[0559] Step 5:

[0560] The server formats the acquired facility information into a format suitable for the user's terminal. Filtering and format conversion are performed to transform the information into something easily understandable to the user. The input is a list of facility information, and the output is the formatted facility information.

[0561] Step 6:

[0562] The server sends formatted facility information to the user's terminal. The terminal displays the received information on its screen, allowing the user to view and select details for each facility. The input is formatted facility information, and the output is visual information provided to the user.

[0563] (Application Example 2)

[0564] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0565] Conventional facility search systems lacked the flexibility to respond based on user emotions, resulting in users only being able to find the optimal facility by simply entering facility criteria. There is a need for a system that can make choices while taking the user's psychological state into consideration.

[0566] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0567] In this invention, the server includes means for receiving information input in natural language from a user terminal, means for analyzing the information using natural language processing technology, and means for detecting emotions from the analyzed information and determining the user's psychological state. This enables flexible facility suggestions tailored to the user's emotional state.

[0568] A "user terminal" is a communication device used by users to input information and receive results.

[0569] "Natural language processing technology" is a technology that enables computers to understand and analyze the language that humans use on a daily basis.

[0570] "Means for detecting emotions and determining psychological state" refers to technology that identifies a user's emotions and evaluates their psychological state based on text received from a communication device.

[0571] A "database" is a collection of information that is organized and managed in a way that allows for efficient searching.

[0572] "Facility information" refers to data about a specific location or service, and is used to select a facility that meets the user's requirements.

[0573] "Flexible response" refers to the ability to appropriately adjust to the situation and provide services tailored to the individual needs of the users.

[0574] To realize this invention, the user first inputs information in natural language using a communication terminal. The communication terminal receives the user's input and transmits the data to a server. The server analyzes the received natural language data using natural language processing technology. Through this process, specific conditions and requests are extracted from the input text.

[0575] Next, the server employs technology to detect emotions and determine the user's psychological state. As part of this technology, an emotion engine is used, which identifies the user's emotions from received messages and evaluates their psychological state. Based on this information, the server searches a database to retrieve facility information that best suits the user's conditions and psychological state.

[0576] Afterward, the acquired facility information is transmitted back to the communication terminal and presented to the user. The presented information includes customized information based on the user's emotional state, allowing the user to make flexible facility selections that take their current psychological condition into account.

[0577] For example, if a user enters "I'd like a quiet cafe today," the server can consider that preference and emotion and suggest cafes with a quiet atmosphere. It is expected that Python and natural language processing libraries would be used in the process supporting this entire operation.

[0578] Examples of prompts include "Where are some relaxing cafes?" or "I want to unwind, so I'd like to know about some quiet places." In response to such prompts, the system provides appropriate facility information.

[0579] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0580] Step 1:

[0581] The user inputs their wishes and feelings in natural language into the communication terminal. This input is text data, such as "Today I'd like to go to a relaxing cafe." The input data is retrieved by the terminal and sent to the server.

[0582] Step 2:

[0583] The server analyzes natural language input data received from the terminal. Natural language processing techniques are used to analyze the input text and extract specific desires or conditions. Keywords such as "relax" and "cafe" are identified in the input text, and these keywords are output as a result of the analysis.

[0584] Step 3:

[0585] The server uses an emotion engine to detect the user's emotions from the received text and determine their psychological state. The input to this process is the linguistic data of the user's text, and the output is an emotional state such as "I want to relax."

[0586] Step 4:

[0587] The server searches the database based on the analysis results and sentiment data. Specifically, it retrieves facility information from the database that matches the conditions and sentiments extracted in the analysis. In this step, the conditions and sentiment data are used as input, and a list of matching facilities is obtained as output.

[0588] Step 5:

[0589] The acquired facility information is transmitted from the server to the terminal. The terminal receives the information and displays it to the user. The input is facility information data, and the output is a user-friendly format that suggests the facilities.

[0590] Step 6:

[0591] The user views facility information presented on the device and selects a facility that suits their situation. The selected facility is the most suitable place based on the user's psychological state.

[0592] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0593] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0594] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0595] [Fourth Embodiment]

[0596] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0597] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0598] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0599] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0600] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0601] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0602] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0603] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0604] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0605] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0606] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0607] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0608] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0609] The system of this invention comprises a user terminal, a server, a natural language processing engine, and a database. This system is used when a user searches for a restaurant.

[0610] First, the user enters the conditions in natural language via a messaging app. For example, they can set the condition "Chinese restaurants within a 10-minute walk from a subway station." The user's device receives this information and sends it to the server.

[0611] The server passes the received user message to a natural language processing engine for analysis. This engine analyzes the user's request and extracts specific search criteria. Using the analyzed results, the server accesses a facility information database and searches for restaurants that match the criteria.

[0612] The searched restaurant information, such as name, address, available hours, and reservation status, is formatted on the server and sent to the user's terminal.

[0613] The user terminal presents the user with information received from the server. This allows the user to quickly find the optimal restaurant that meets their criteria. Furthermore, the user can make a reservation based on the presented information if necessary. This enables the user to find a restaurant that meets their desired conditions in a short amount of time without hassle, making efficient facility selection possible through the system of this invention.

[0614] The following describes the processing flow.

[0615] Step 1:

[0616] Users input natural language text into messaging apps to recommend restaurants that meet specific criteria. For example, they might say, "I'm looking for a quiet cafe near the train station."

[0617] Step 2:

[0618] The terminal receives a message entered by the user and prepares to send that data to the server. During this process, it constructs a packet to ensure that the input content and user ID are reliably transmitted.

[0619] Step 3:

[0620] The server receives user messages sent from the terminal and passes them to the natural language processing engine. The messages are then placed in a queue for analysis.

[0621] Step 4:

[0622] The server's natural language processing engine analyzes the received text data and extracts key conditions (e.g., location, restaurant style, and other specific requests). The extracted results are stored as structured data.

[0623] Step 5:

[0624] The server queries the facility information database based on conditions obtained through natural language processing and retrieves a list of relevant restaurant information. In this process, location information is cross-referenced to narrow down the list of candidate restaurants.

[0625] Step 6:

[0626] The server converts the retrieved restaurant information into a user-friendly format. For example, it formats and lists the restaurant name, address, available reservation times, and any special notes.

[0627] Step 7:

[0628] The server sends the formatted restaurant information to the terminal. The response data is formatted with display on the user's terminal in mind.

[0629] Step 8:

[0630] The device receives restaurant information retrieved from the server and presents it to the user via the messaging app. The presented information may include links to view details and options for making reservations.

[0631] Step 9:

[0632] Users can review the presented restaurant information and, if they find a restaurant they like, take the next step, such as making a reservation.

[0633] (Example 1)

[0634] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0635] Currently, many location search systems struggle to efficiently process complex natural language conditions and provide users with relevant information quickly. Furthermore, they lack features for sharing search results across various communication devices and for presenting additional information of value to users. As a result, users inevitably spend considerable time and effort obtaining the information they need.

[0636] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0637] In this invention, the server includes means for receiving information entered in natural language from a user input device, means for analyzing the information using natural language processing technology to extract specific keywords and conditions, and means for querying an information database based on the extracted search conditions to obtain facility information that matches the conditions. This allows users to easily input even complex conditions and quickly and efficiently obtain information that matches those conditions. Furthermore, it is possible to enhance the value to the user by making it easier to share search results between different communication devices and visually presenting available time slots and additional information.

[0638] A "user input device" is a device that allows a user to input information in natural language and transmit it to a system.

[0639] "Natural language processing technology" is a technique that interprets text written in natural language and converts it into a format that machines can understand.

[0640] An "information database" is a data storage system in which specific information is structured and stored, and can be searched by queries as needed.

[0641] A "query" is a command or request used to retrieve specific information from a database.

[0642] "Facility information" refers to detailed data about a specific facility, including information such as its name, location, operating hours, and reservation status.

[0643] "To present visually" means to display information to the user using a graphical interface or other visual means.

[0644] A "communication device" is a device that enables the transmission and reception of data over a network.

[0645] The present invention is configured as a system including a user input device, a server, a natural language processing engine, and an information database. This system is designed to allow users to quickly and efficiently obtain desired facility information by inputting conditions in natural language.

[0646] The user accesses the messaging app using a user input device and enters their desired conditions in natural language. This user input device could be a smartphone or tablet, for example. The entered information is sent to the server via the network.

[0647] The server is equipped with a natural language processing engine, which uses natural language processing libraries such as SpaCy and NLTK. This engine analyzes the received natural language information and extracts specific keywords and conditions. Based on these analysis results, the server queries the information database to find facility information that matches the conditions.

[0648] The information database stores detailed information about numerous facilities, and the desired data can be quickly retrieved using query languages ​​such as SQL. The retrieved facility information is formatted by the server and sent to the user input device.

[0649] Users can view the presented facility information on the user input device and make reservations as needed. This entire process makes it easy for users to find facilities that meet their desired criteria.

[0650] For example, if a user enters "I want to find a quiet cafe within a 5-minute walk," the natural language processing engine extracts keywords such as "5-minute walk" and "quiet cafe" and queries the database. As a result, cafes that match the criteria are searched for, and that information is provided to the user. This mechanism enhances user convenience by combining it with the use of prompt sentences in the generative AI model.

[0651] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0652] Step 1:

[0653] The user opens a messaging app on their user input device and enters their desired conditions in natural language. Specifically, this step involves the user entering conditions into a text input box and pressing the send button. The input is natural language text, such as "I'm looking for a quiet cafe within a 5-minute walk." The output is this information, encoded as data, stored on the user's device.

[0654] Step 2:

[0655] The user terminal sends user input information to the server using a network protocol (e.g., HTTP / HTTPS). During this process, user input data is packetized and prepared for transmission. The input is the user's natural language message, and the output is the request data sent to the server.

[0656] Step 3:

[0657] The server passes the received data to a natural language processing engine for analysis. Specifically, it uses tools such as SpaCy or NLTK to tokenize the text data, perform semantic analysis, and extract keywords that can be used as search criteria (e.g., "5 minutes on foot," "quiet cafe"). The input is natural language text received from the user, and the output is a search query with specified criteria.

[0658] Step 4:

[0659] The server queries the information database using the parsed search query and retrieves data that matches the criteria. Specifically, an SQL query is generated and executed by the database management system. The input is the search query expanded by the server, and the output is a list of facility information retrieved from the database.

[0660] Step 5:

[0661] The server formats the facility information retrieved from the database into a user-friendly format. Here, the response data is structured in JSON format. The input is the raw data of the retrieved facility information, and the output is the formatted JSON data.

[0662] Step 6:

[0663] The server sends formatted data to the user terminal. The server transmits this data using network protocols and performs the transformation until the data reaches the user terminal. The input is formatted information data, and the output is the data displayed on the user terminal.

[0664] Step 7:

[0665] The user terminal displays the received data in a graphical user interface (GUI), presenting facility information to the user. Specifically, a display engine (e.g., React or Vue.js) performs the rendering process, visually outputting the information. The input is JSON data received from the server, and the output is a visual display of facility information presented to the user.

[0666] Step 8:

[0667] The user reviews the presented information and makes a reservation or selection as needed. Specifically, the user completes the action by clicking a reservation button or link. This input is the user's choice and actions on their device, and the output is the reservation or acquisition of detailed information based on the user's actions.

[0668] (Application Example 1)

[0669] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0670] The current facility search system requires users to input criteria as text, and voice support is insufficient. Furthermore, even when facility information matching the criteria is retrieved, the visual presentation of the information and the booking process are complex, resulting in usability issues.

[0671] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0672] In this invention, the server includes means for receiving natural language information input by voice from a user terminal, means for analyzing the information using natural language processing technology and converting it into text data using speech recognition technology, and means for searching a database based on the analyzed information and obtaining facility information that matches the specified conditions. This enables intuitive and rapid acquisition of facility information using voice input, as well as the accompanying visual information presentation and reservation operation.

[0673] "Voice input" is a method of inputting information by having the user speak into the device.

[0674] "Natural language processing technology" is a technology that enables computers to understand and analyze human language.

[0675] "Speech recognition technology" is a technology in which a computer analyzes input speech and converts it into digital text.

[0676] "Text data" refers to digital character information converted using speech recognition technology.

[0677] A "database" is a collection of information that is systematically stored and can be searched and retrieved.

[0678] "Visual presentation" refers to a method of providing information to users in a visible form through displays or monitors.

[0679] "Reservation operation" refers to the act of specifying the desired date and time for a selected facility or service and completing the procedure in advance.

[0680] This system is implemented using user terminals, servers, a natural language processing engine including speech recognition technology, and a database containing facility information.

[0681] The user uses a user device such as a smartphone to input conditions by voice. This voice data is converted into text data by speech recognition software built into the device. Google's Speech-to-Text API may be used for this conversion. Subsequently, a natural language processing engine analyzes this text data and extracts the information necessary for database searches that match the conditions. IBM Watson or Google Dialogflow can be used for this analysis.

[0682] The server receives the analyzed information, searches the database, and retrieves facility information that matches the criteria. This database includes basic facility information and available reservation times.

[0683] The acquired information is transmitted to the user's terminal and visually displayed on the terminal's screen. Based on the displayed information, the user can, for example, make a restaurant reservation.

[0684] For example, if a user voice-inputs "Tell me some recommended ramen restaurants in Ikebukuro," the system will search for ramen restaurants around Ikebukuro and display a list of restaurants that meet the criteria. The restaurant information also displays available reservation times, allowing users to make reservations on the spot.

[0685] An example of a prompt to input into the generating AI model is, "Based on the restaurant criteria requested by the user, list French restaurants near Tokyo Tower and present them to the user."

[0686] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0687] Step 1:

[0688] The user provides voice input to the device. This input is captured by the device as voice data.

[0689] Step 2:

[0690] The terminal uses speech recognition software to convert speech data into text data. Here, the software analyzes the speech waveform and uses a language model to generate the corresponding string. The input is speech data, and the output is a text-based instruction.

[0691] Step 3:

[0692] The terminal sends text data to the server. The server receives this text data and prepares it for the next step.

[0693] Step 4:

[0694] The server analyzes the received text data using a natural language processing engine. This analysis extracts the intent from the text and the information necessary for the search criteria. The input is the received text data, and the output is structured conditional information.

[0695] Step 5:

[0696] The server converts structured conditional information into a database search query and searches the database. This search operation retrieves facility information that matches the criteria. The input is conditional information, and the output is a list of facility information.

[0697] Step 6:

[0698] The server organizes the acquired facility information and formats it into a visually presentable format. This formatting makes the information easier for users to understand. The input is a list of facility information, and the output is the formatted information.

[0699] Step 7:

[0700] The server sends the formatted information to the terminal. The terminal receives this information and displays it on its screen. The user can then select a facility.

[0701] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0702] This invention relates to a system that combines a user terminal, a server, a natural language processing engine, an emotion engine, and a facility information database. This system not only presents recommended facilities based on messages entered by the user in natural language, but also recognizes the user's emotions and enables flexible responses in accordance with those emotions.

[0703] Users use messaging apps to input and send specific conditions or requests in natural language. For example, they might send a request like, "I'm feeling a bit down today, so could you recommend a cafe where I can relax?" The user's device receives this message and forwards it to the server.

[0704] The server passes the received message to a natural language processing engine, which analyzes its content. This analysis extracts specific conditions and desires. Furthermore, the emotion engine detects emotions from the user's message and determines the user's psychological state. For example, the message might detect the emotion of "feeling depressed."

[0705] The server searches a facility information database based on the results of natural language processing and emotion engine analysis. This selects restaurants, cafes, and other facilities that are suitable for the user's state. If the user's emotions are positive, it can prioritize suggesting lively places; if negative, it can prioritize suggesting relaxing places.

[0706] The acquired information is formatted for user clarity and sent from the server to the user's terminal. The user's terminal displays the received information, allowing users to easily select and book facilities. This system enables users to quickly find places that match their current emotional state, resulting in a more personalized experience.

[0707] The following describes the processing flow.

[0708] Step 1:

[0709] Users describe the conditions of the facility they are looking for and their own emotional state in natural language using a messaging app and send the message. For example, they might type a message like, "I'm a little tired, so I'd like a quiet cafe."

[0710] Step 2:

[0711] The terminal receives a message entered by the user and prepares to send that data to the server. Here, the data is formatted so that the message content and user ID, etc., are transmitted accurately.

[0712] Step 3:

[0713] The server receives user messages sent from the terminal and passes the data to a natural language processing engine for analysis. This includes recognizing the input conditions and preferences and extracting important elements.

[0714] Step 4:

[0715] The server's natural language processing engine analyzes the results, which are then passed through an emotion engine to identify emotions from user messages. In this process, the emotion engine analyzes the input content from an emotional perspective, identifying states such as "tired" or "stressed."

[0716] Step 5:

[0717] The server queries the facility information database based on the extracted conditions and emotional information to find facilities that meet the criteria. Recommendations are taken into consideration based on emotional factors; for example, places that provide a sense of calm are prioritized.

[0718] Step 6:

[0719] The server formats the acquired facility information and lists it in a user-friendly format. This includes details such as the facility name, address, business hours, and whether reservations are accepted.

[0720] Step 7:

[0721] The server sends the formatted facility information to the terminal. The response sent is formatted to be easily understood by the user.

[0722] Step 8:

[0723] The device analyzes facility information received from the server and displays it to the user via the messaging app. This display may include links to view details and options for direct booking.

[0724] Step 9:

[0725] Based on the displayed information, users can select a facility that suits their needs and, if necessary, proceed to the next step, such as making a reservation or making an inquiry.

[0726] (Example 2)

[0727] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0728] In society, users face the challenge of quickly selecting an appropriate environment that suits their emotional state. In particular, accurately finding a suitable facility when experiencing negative emotions is difficult, preventing users from having experiences that are more tailored to their needs.

[0729] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0730] In this invention, the server includes means for receiving information input in natural language from a user terminal, means for analyzing the received information to recognize the user's emotional state, and means for searching a database based on the analyzed information and emotional state to obtain facility information corresponding to the user's emotions. This makes it possible to quickly and accurately provide appropriate facilities according to the user's emotional state.

[0731] A "user terminal" is an electronic information device used by users to input or receive information, and includes smartphones and personal computers.

[0732] "Natural language" refers to the language that humans use on a daily basis. Unlike programming languages, it is a language intended for communication between people.

[0733] "Means of receiving" refers to a technical device or mechanism for receiving data or information transmitted from an external source.

[0734] "Means of analysis" refers to technical devices or algorithms used to analyze received information, understand its structure and content, and extract specific data.

[0735] "Means for recognizing emotional states" refers to a technical device or process for determining a user's psychological or emotional state based on information from the user.

[0736] A "database" is a system for systematically organizing and managing large amounts of data, and it is a structured collection of information that can be easily searched and accessed.

[0737] "Facility information" refers to detailed data about a specific location, including information such as name, address, business hours, and characteristics.

[0738] "Formatting methods" refer to technologies or functions used to convert acquired data or information into a format that is easy for users to understand.

[0739] This invention relates to a system combining a user terminal, a server, a natural language processing engine, an emotion recognition engine, and a database. The user terminal is an electronic information device such as a smartphone or personal computer, and provides a means for the user to input information in natural language and transmit it to the server. The purpose of this system is to quickly provide facility information that corresponds to the user's emotional state.

[0740] The user might input a message such as, "I want to relax today, so please tell me a quiet place." This message is received by the user's device and sent to the server. The server uses natural language processing libraries like spacy or nltk to analyze the received message and extract the user's wishes and conditions. Simultaneously, an emotion recognition engine uses the Google Cloud Natural Language API to analyze the user's emotional state and recognize that it is the emotion of wanting to relax.

[0741] Furthermore, the server searches the database for appropriate facility information based on the extracted conditions, preferences, and emotional state. This database includes facility names, locations, business hours, and features. The information obtained through the search is formatted in a user-friendly format and sent to the user's terminal.

[0742] As a concrete example, if a user inputs "I'm looking for a lively place to unwind," the server recognizes this positive emotional state and presents lively restaurants and cafes from its database. This allows the user to efficiently select the most suitable establishment based on their emotional state. Another possible prompt for the generating AI model would be "Please recommend a place that would be good for a user who wants to feel more energetic."

[0743] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0744] Step 1:

[0745] The user uses a messaging app to type a natural language message about their wishes and feelings. This message might include something like, "I want to relax today, so I'd like to know about quiet places." The entered information is prepared as text data on the device. The device then prepares this text data to be sent to a server over the internet.

[0746] Step 2:

[0747] The server retrieves natural language messages received from the user's terminal. The received text data is passed to a natural language processing engine. Here, the server uses libraries such as spaCy or NLTK to tokenize the message and parse its keywords and structure. The input is a text message from the user, and the output is information about the user's wishes and conditions.

[0748] Step 3:

[0749] The server passes the analyzed message data through an emotion recognition engine. This process analyzes the user's emotional state using tools such as the Google Cloud Natural Language API. Specific words and phrases are scored to quantify emotions, such as positive or negative. The input is the analyzed message data, and the output is the user's emotion score.

[0750] Step 4:

[0751] The server searches the facility information database based on the results of natural language processing and sentiment analysis. It uses SQL queries to retrieve facility information that matches the user's preferences and emotional state. The input is the user's preferences and emotional state, and the output is a list of matching facility information.

[0752] Step 5:

[0753] The server formats the acquired facility information into a format suitable for the user's terminal. Filtering and format conversion are performed to transform the information into something easily understandable to the user. The input is a list of facility information, and the output is the formatted facility information.

[0754] Step 6:

[0755] The server sends formatted facility information to the user's terminal. The terminal displays the received information on its screen, allowing the user to view and select details for each facility. The input is formatted facility information, and the output is visual information provided to the user.

[0756] (Application Example 2)

[0757] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0758] Conventional facility search systems lacked the flexibility to respond based on user emotions, resulting in users only being able to find the optimal facility by simply entering facility criteria. There is a need for a system that can make choices while taking the user's psychological state into consideration.

[0759] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0760] In this invention, the server includes means for receiving information input in natural language from a user terminal, means for analyzing the information using natural language processing technology, and means for detecting emotions from the analyzed information and determining the user's psychological state. This enables flexible facility suggestions tailored to the user's emotional state.

[0761] A "user terminal" is a communication device used by users to input information and receive results.

[0762] "Natural language processing technology" is a technology that enables computers to understand and analyze the language that humans use on a daily basis.

[0763] "Means for detecting emotions and determining psychological state" refers to technology that identifies a user's emotions and evaluates their psychological state based on text received from a communication device.

[0764] A "database" is a collection of information that is organized and managed in a way that allows for efficient searching.

[0765] "Facility information" refers to data about a specific location or service, and is used to select a facility that meets the user's requirements.

[0766] "Flexible response" refers to the ability to appropriately adjust to the situation and provide services tailored to the individual needs of the users.

[0767] To realize this invention, the user first inputs information in natural language using a communication terminal. The communication terminal receives the user's input and transmits the data to a server. The server analyzes the received natural language data using natural language processing technology. Through this process, specific conditions and requests are extracted from the input text.

[0768] Next, the server employs technology to detect emotions and determine the user's psychological state. As part of this technology, an emotion engine is used, which identifies the user's emotions from received messages and evaluates their psychological state. Based on this information, the server searches a database to retrieve facility information that best suits the user's conditions and psychological state.

[0769] Afterward, the acquired facility information is transmitted back to the communication terminal and presented to the user. The presented information includes customized information based on the user's emotional state, allowing the user to make flexible facility selections that take their current psychological condition into account.

[0770] For example, if a user enters "I'd like a quiet cafe today," the server can consider that preference and emotion and suggest cafes with a quiet atmosphere. It is expected that Python and natural language processing libraries would be used in the process supporting this entire operation.

[0771] Examples of prompts include "Where are some relaxing cafes?" or "I want to unwind, so I'd like to know about some quiet places." In response to such prompts, the system provides appropriate facility information.

[0772] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0773] Step 1:

[0774] The user inputs their wishes and feelings in natural language into the communication terminal. This input is text data, such as "Today I'd like to go to a relaxing cafe." The input data is retrieved by the terminal and sent to the server.

[0775] Step 2:

[0776] The server analyzes natural language input data received from the terminal. Natural language processing techniques are used to analyze the input text and extract specific desires or conditions. Keywords such as "relax" and "cafe" are identified in the input text, and these keywords are output as a result of the analysis.

[0777] Step 3:

[0778] The server uses an emotion engine to detect the user's emotions from the received text and determine their psychological state. The input to this process is the linguistic data of the user's text, and the output is an emotional state such as "I want to relax."

[0779] Step 4:

[0780] The server searches the database based on the analysis results and sentiment data. Specifically, it retrieves facility information from the database that matches the conditions and sentiments extracted in the analysis. In this step, the conditions and sentiment data are used as input, and a list of matching facilities is obtained as output.

[0781] Step 5:

[0782] The acquired facility information is transmitted from the server to the terminal. The terminal receives the information and displays it to the user. The input is facility information data, and the output is a user-friendly format that suggests the facilities.

[0783] Step 6:

[0784] The user views facility information presented on the device and selects a facility that suits their situation. The selected facility is the most suitable place based on the user's psychological state.

[0785] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0786] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0787] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0788] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0789] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0790] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0791] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0792] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0793] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0794] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0795] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0796] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0797] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0798] 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.

[0799] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0800] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0801] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0802] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0803] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0804] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0805] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0806] The following is further disclosed regarding the embodiments described above.

[0807] (Claim 1)

[0808] A means for receiving information entered in natural language from a user terminal,

[0809] The means for analyzing the aforementioned information using natural language processing technology,

[0810] A means of searching a database based on the analyzed information and obtaining facility information that matches the criteria,

[0811] A means of transmitting acquired facility information to the user terminal,

[0812] A system that includes this.

[0813] (Claim 2)

[0814] The system according to claim 1, characterized by comprising means for enabling the sharing of facility information between different communication terminals based on conditions entered by the user.

[0815] (Claim 3)

[0816] The system according to claim 1, characterized in that it includes means for presenting the user terminal with available reservation time slots and additional information.

[0817] "Example 1"

[0818] (Claim 1)

[0819] A means for receiving information entered in natural language from a user input device,

[0820] A means for analyzing the aforementioned information using natural language processing technology and extracting specific keywords and conditions,

[0821] A means of querying an information database based on extracted search criteria to obtain facility information that matches the criteria,

[0822] A means for formatting the acquired facility information and transmitting it to a user input device,

[0823] An information retrieval system that includes this.

[0824] (Claim 2)

[0825] The information retrieval system according to claim 1, characterized by comprising means that enable sharing and displaying facility information among multiple communication devices based on conditions entered by a user.

[0826] (Claim 3)

[0827] The information retrieval system according to claim 1, characterized in that it includes means for visually presenting available time slots and additional information to a user input device.

[0828] "Application Example 1"

[0829] (Claim 1)

[0830] A means for receiving natural language information input by voice from a user terminal,

[0831] The means for analyzing the aforementioned information using natural language processing technology and converting it into text data using speech recognition technology,

[0832] A means of searching a database based on the analyzed information and obtaining facility information that matches the criteria,

[0833] A means of visually displaying acquired facility information on the user's terminal and enabling reservation operations,

[0834] A system that includes this.

[0835] (Claim 2)

[0836] The system according to claim 1, comprising means for enabling the sharing of facility information between different communication terminals via a voice interface based on conditions entered by the user.

[0837] (Claim 3)

[0838] The system according to claim 1, further comprising means for visually presenting facility information, available time slots, and additional information to a user terminal.

[0839] "Example 2 of combining an emotion engine"

[0840] (Claim 1)

[0841] A means for receiving information entered in natural language from a user terminal,

[0842] A means of analyzing received information to recognize the user's emotional state,

[0843] A means for searching a database based on analyzed information and emotional state to obtain facility information corresponding to the user's emotions,

[0844] A means of formatting acquired facility information in an easy-to-understand manner for the user and sending it to the user's terminal,

[0845] A system that includes this.

[0846] (Claim 2)

[0847] The system according to claim 1, characterized in that it prioritizes and presents facility information according to the user's emotional state.

[0848] (Claim 3)

[0849] The system according to claim 1, characterized in that it includes means for presenting additional facility information, including available reservation times and map information, to the user terminal.

[0850] "Application example 2 when combining with an emotional engine"

[0851] (Claim 1)

[0852] A means for receiving information entered in natural language from a user terminal,

[0853] The means for analyzing the aforementioned information using natural language processing technology,

[0854] A means of detecting emotions from analyzed information and determining psychological state,

[0855] Based on the aforementioned psychological state, a means for searching a database and obtaining facility information that matches the conditions,

[0856] A means of transmitting acquired facility information to the user's terminal, enabling flexible responses according to the user's emotional state,

[0857] A system that includes this.

[0858] (Claim 2)

[0859] The system according to claim 1, characterized in that it includes means for sharing facility information between different communication terminals and for selecting facilities based on emotions, based on the psychological state entered by the user.

[0860] (Claim 3)

[0861] The system according to claim 1, characterized in that it includes means for presenting the user terminal with available reservation times for the facility and additional information that corresponds to the user's emotions. [Explanation of Symbols]

[0862] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for receiving information entered in natural language from a user terminal, The means for analyzing the aforementioned information using natural language processing technology, A means of searching a database based on the analyzed information and obtaining facility information that matches the criteria, A means of transmitting acquired facility information to the user terminal, A system that includes this.

2. The system according to claim 1, characterized by comprising means for enabling the sharing of facility information between different communication terminals based on conditions entered by the user.

3. The system according to claim 1, characterized in that it includes means for presenting the user terminal with available reservation time slots and additional information.

Images