system

Abstract

We provide the system. [Solution] A means of analyzing text data obtained from users using natural language processing technology to identify the user's intent, Means for retrieving relevant information from a database based on identified intent, A means of formatting and presenting acquired information in a way suitable for the user, A means of personalizing information by taking into account the user's past behavior patterns and preferences, A means of updating information in real time by linking with external data sources, 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 chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In urban areas, quickly and accurately providing information needed by residents and visitors is a common problem faced by many cities. Also, it is very difficult to select and provide information suitable for individual users from a huge amount of information, and as a result, the practical value possessed by users cannot be maximally exerted.Furthermore, the construction of a system for real-time information update and response to individual needs of users also poses a technical hurdle. It is necessary to develop an innovative information provision system to solve these problems and support a more convenient and comfortable urban life.

Means for Solving the Problems

[0005] This invention includes means for analyzing text data from users using natural language processing technology to identify user intent. This makes it possible to accurately grasp user requests and retrieve relevant information from a database. It also includes means for formatting and presenting the retrieved information in a way that is suitable for the user, and can personalize the information by considering the user's past behavior patterns and preferences. Furthermore, the system has means for updating information in real time by linking with external data sources, enabling it to continuously provide users with the latest and most accurate information. In this way, this invention provides a system that realizes optimal information provision for residents and visitors, making their urban life more convenient and comfortable.

[0006] "Natural language processing technology" is a technology that allows computers to understand and analyze human language, and has the ability to extract meaning and intent from text and audio data.

[0007] A "user" refers to a resident or visitor who uses an information system, and is an individual entity that seeks specific information or services.

[0008] A "database" is an information system designed to systematically store large amounts of information and to allow for efficient searching, retrieval, and management.

[0009] "Formatting" refers to the operations and procedures for rearranging acquired information into a format that is easy for users to understand.

[0010] "Behavioral patterns" refer to the actions and choices a user has made in the past, and the tendencies that result from them, and are used in user profiling.

[0011] An "external data source" refers to an external information provider that does not exist within the system but is linked to in order to obtain necessary information. [Brief explanation of the drawing]

[0012] [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]

[0013] 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.

[0014] First, the terms used in the following description will be explained.

[0015] 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.

[0016] 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.

[0017] 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, and the like.

[0018] 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).

[0019] 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."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] 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.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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".

[0033] The system of this invention efficiently acquires information that residents and visitors need within a city, thereby supporting a comfortable urban life. Based on user input, the system uses natural language processing technology to analyze the data and retrieves and presents relevant information from a database.

[0034] Users can send questions to the device via voice or text input. For example, if a user asks, "Where are the nearby restaurants?", the device formats the question into text and sends it to the server. The server then uses natural language processing technology to analyze this text and determine the user's intent.

[0035] Based on the analysis results, the server generates queries to retrieve relevant information from the database. These queries target relevant information such as restaurant location, opening hours, and ratings. The retrieved information is then reorganized into a personalized format, taking into account the user's past behavior patterns and preferences.

[0036] For example, the server can prioritize displaying restaurant information best suited to the user based on the types of restaurants the user has previously searched for and their visit history. Ultimately, the information provided to the user can be in text format as well as audio format, and the device will present the information in the most appropriate way depending on the situation.

[0037] Furthermore, the system integrates with external data sources, updating information in real time. This ensures that users are always provided with the latest information. This feature is particularly useful for responding to sudden changes in event information or emergencies.

[0038] In this way, the present invention can provide users with the information they need in a rapid and personalized manner, significantly improving the quality of life in smart cities.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] Users input questions or requests into the device via voice or text. For example, they might type, "Tell me about nearby restaurants."

[0042] Step 2:

[0043] The device converts voice input into text, organizes the text data, and sends it to the server. Speech recognition technology is used to format the user's words into text.

[0044] Step 3:

[0045] The server analyzes the received text data using natural language processing techniques to recognize the user's intent. This analysis involves intent classification and entity extraction. For example, it might identify the category "restaurant."

[0046] Step 4:

[0047] The server generates queries to query the database based on the analysis results. These queries include conditions for searching for information related to the identified entities and intentions.

[0048] Step 5:

[0049] The server executes the generated query and retrieves the relevant information from the database, such as a list of nearby restaurants.

[0050] Step 6:

[0051] The server reformats the retrieved information into a user-friendly format. If necessary, it personalizes the information by considering the user's past behavior patterns.

[0052] Step 7:

[0053] The server sends formatted information to the terminal. The information is in a format that can be handled in either text or audio format.

[0054] Step 8:

[0055] The device presents the received information to the user. Depending on the user's preferences, it may display the information on the screen or provide an audio response.

[0056] Step 9:

[0057] Based on the information presented, users can decide on their next action and, if necessary, ask additional questions or provide feedback to the device.

[0058] (Example 1)

[0059] 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."

[0060] In modern urban life, it is crucial to quickly and individually obtain the information that residents and visitors need. However, conventional information acquisition systems have struggled to accurately analyze user intent and provide personalized information that takes past behavioral patterns into account. Furthermore, real-time information updates have been insufficient, making it impossible to always provide the latest information. In addition, the convenience of information acquisition using voice input has not been adequate.

[0061] 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.

[0062] In this invention, the server includes means for analyzing data obtained from the user using natural language processing technology to identify the user's intent, means for obtaining relevant information from a data storage device based on the identified intent, and means for structuring and presenting the obtained information in a way that is suitable for the user. This enables the user to quickly obtain personalized information that takes into account past behavioral patterns and preferences. Furthermore, by converting voice input into text data and presenting information in both voice and text formats, user convenience can be improved. In addition, by synchronizing with external information sources in real time, the latest information can always be provided to support rapid decision-making.

[0063] "Natural language processing technology" is a technology that enables computers to understand, interpret, and generate human language, and to analyze data obtained from users to identify their intentions.

[0064] A "data storage device" is a device or system that stores information and keeps it accessible as needed, and is used to retrieve relevant information based on the user's intent.

[0065] "Past behavioral patterns" refer to the history of choices and actions a user has made in the past, and this data is used to personalize information.

[0066] An "external information source" refers to a source of data or information that exists outside the system, and is the destination to which the system connects in order to enable real-time information updates.

[0067] "Personalization" refers to the process of adjusting and presenting acquired information in a way that is optimal for the user, based on the user's past behavioral patterns and preferences.

[0068] "Voice input" refers to a method of sending data to a system using the voice spoken by the user, and includes the technology to convert this voice into text data.

[0069] "Real-time updates" refers to a function that synchronizes with external information sources to keep information up-to-date and reflects changes immediately.

[0070] This system begins with the user querying the terminal for information via voice or text. For example, the user might ask the terminal, "Where's the nearest cafe?" If the input is voice, the terminal uses speech recognition software to convert it into text. For speech recognition, common speech recognition technologies are used, and Google® Cloud Speech-to-Text API or other solutions available on the market can be utilized.

[0071] The terminal then sends the converted text data to the server. The server uses natural language processing (NLP) techniques to analyze the text and identify the user's intent. At this stage, natural language processing libraries such as spaCy or BERT are used.

[0072] Based on the user's intent revealed through analysis, the server generates and executes queries to retrieve the necessary relevant information from the data storage device. These queries target information such as the location, opening hours, and ratings of nearby cafes.

[0073] The information obtained is personalized, taking into account the user's past behavioral patterns. The server uses this profile data to prioritize providing the type of information the user prefers.

[0074] Finally, the device presents the personalized information received from the server to the user in either audio or text format. The information is provided in the most effective way for the user, but this will vary depending on the device's characteristics, the user's environment, and settings.

[0075] For example, if a user speaks into their smartphone and asks, "Which cafes are open now?", the device converts the speech into text, the server analyzes the intent of the text to generate a query, and retrieves cafe information from its data storage. Then, after personalizing that information, it provides voice guidance such as, "There are two cafes open near your current location: Cafe A and Cafe B."

[0076] An example of a prompt to the generative AI model would be: "What nearby French restaurants would the user like to visit? Please provide priority results considering past visit history."

[0077] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0078] Step 1:

[0079] Users query the device for information via voice or text. For example, they might ask, "Where's the nearest cafe?" This input is received by the device. In the case of voice input, the device first uses speech recognition technology to convert the voice into text data. As a result, the voice input is output as text data.

[0080] Step 2:

[0081] The terminal sends the converted text data to the server. The server receives this text data as input and performs analysis using natural language processing. Specifically, BERT and spaCy can be used as natural language processing technologies. Through this analysis, the user's intent is identified, and the result is output.

[0082] Step 3:

[0083] The server generates a query to access data storage based on the identified user's intent. This query might retrieve information such as the location, opening hours, and reviews of nearby cafes. The server executes this query against the data storage and retrieves the relevant data. As a result, information matching the user's intent is retrieved and output.

[0084] Step 4:

[0085] The acquired information is personalized by the server, taking into account the user's past behavior patterns and preferences. Specifically, it analyzes data on places the user has visited in the past and their preferences, and selects information to display preferentially. The output of this process is personalized information.

[0086] Step 5:

[0087] The server sends personalized information to the terminal, which then presents it to the user. The terminal outputs the information in either voice or text format, the method of which is selected according to the user's device settings and environment. For example, as voice output, it might announce, "The cafes open near your current location are Cafe A and Cafe B."

[0088] (Application Example 1)

[0089] 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."

[0090] In modern urban life, individuals are required to obtain appropriate and useful information quickly and efficiently. However, the sheer volume of information makes it difficult to provide information tailored to individual needs. Furthermore, if information is not updated in real time, it becomes difficult to cope with constantly changing circumstances. Users need to be able to quickly obtain the information they seek, and that information needs to be personalized and up-to-date.

[0091] 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.

[0092] In this invention, the server includes means for analyzing information obtained from the user using natural language processing technology to identify the user's purpose, means for obtaining relevant information from information sources based on the identified purpose, and means for presenting the information as physical visual information via a user interface using a wearable information display device. This enables the user to obtain the latest and personalized information visually and intuitively through a wearable device.

[0093] "Natural language processing technology" is a technology that analyzes text and audio data obtained from users to enable computers to understand and process human language.

[0094] "Means for identifying user objectives" refers to methods for determining what a user wants based on the analyzed information.

[0095] "Means of obtaining relevant information from information sources" refers to methods for collecting necessary data from information sources such as the internet or local databases, in accordance with user requests.

[0096] A "wearable information display device" is a hardware device that a user can wear to provide visual information.

[0097] "Means of presenting information as visual information via a user interface" refers to methods of visually displaying acquired information in a way that is easy for the user to understand, and of manipulating it through an interface.

[0098] "A means of updating information in real time in conjunction with external information sources" refers to a method of continuously communicating with external information sources to update data in order to always maintain the latest information.

[0099] "Personalized information" refers to information that has been tailored to be optimal for a specific user based on their past behavior and preferences.

[0100] The system implementing this invention enables a user wearing smart glasses to obtain and display necessary information in real time within a city by making questions and requests in natural language. By using smart glasses as a wearable information display device, information is provided to the user visually and intuitively. The terminal and server cooperate and process information in the following manner.

[0101] The server has the capability to convert speech input from users into text using natural language processing technology. Specifically, it uses software such as the Google Cloud Natural Language API to analyze and convert the speech. This text data is then analyzed in detail to identify the user's intent.

[0102] Next, the server retrieves relevant information from databases and internet sources based on the identified purpose. By utilizing the Google Maps API, for example, it is possible to obtain location information and real-time event information.

[0103] The server further personalizes the acquired information based on the user's past behavior history and preferences. At this stage, machine learning algorithms can also be used, so that information relevant to the user is prioritized according to their browsing history and past choices.

[0104] The collected information is presented as visual information through the smart glasses' display via a user interface. This allows users to receive information in real time and in a personalized format as needed. For example, if a user asks, "What live events are I able to go to this evening?", the server analyzes the question and displays relevant event information on the glasses' display in real time.

[0105] An example of a prompt for a generative AI model would be: "The user asked about live events they can attend this evening. Considering their current location, suggest the three closest and highest-rated events."

[0106] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0107] Step 1:

[0108] The device acquires the user's voice input. The user's voice is captured through the smart glasses' microphone. This input voice data is acquired as a digital audio file.

[0109] Step 2:

[0110] The terminal sends the acquired audio data to the server. The terminal transfers the audio data to the server via the network and prepares it for processing. The output here is the server receiving the audio data.

[0111] Step 3:

[0112] The server converts the audio data to text. The Google Cloud Natural Language API is used to convert the audio data to text data. The input to this process is audio data, and the output is text data for analysis.

[0113] Step 4:

[0114] The server analyzes text data to identify the user's intent. It utilizes natural language processing techniques to refine the text and understand the user's questions and requests. The input is text data, and the output is information about the user's intent. Specific operations include keyword extraction and contextual analysis.

[0115] Step 5:

[0116] The server retrieves relevant information based on the user's intent. Using the Google Maps API, it retrieves necessary information, such as nearby event information, from a database. The input is information about the user's intent, and the output is a dataset of relevant information.

[0117] Step 6:

[0118] The server personalizes the information it acquires. Using machine learning algorithms, it optimizes the information by considering the user's past behavior and preferences. The input is a dataset of related information, and the output is a personalized set of information.

[0119] Step 7:

[0120] The device presents personalized information to the user. The information is displayed visually and intuitively through the smart glasses' display. The input is a personalized set of information, and the output is information that the user can visually confirm.

[0121] 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.

[0122] The system of this invention provides more personalized urban information by taking into account the user's emotional state. This system combines natural language processing technology and an emotion engine, dynamically adjusting the content and method of information presentation based on the user's emotion analysis.

[0123] The user inputs information into the device via voice or text. This input data is sent by the device to the emotion engine, which analyzes the tone of voice and linguistic features of the text to recognize the user's emotional state (e.g., joy, anger, sadness, etc.).

[0124] Based on the sentiment analysis results received from the sentiment engine, the server further analyzes the user's intentions using natural language processing technology. This process evaluates how the user's emotional state affects the way and content of information provided. For example, if it is determined that the user is stressed, the server will take measures such as recommending a relaxing place in a calm tone.

[0125] Furthermore, the server generates queries to the database based on the analysis results and retrieves relevant information. In doing so, it takes into account past sentiment data and reactions, prioritizing the retrieval of information most relevant to the user.

[0126] For example, if a user asks, "I'm tired, is there anywhere I can rest?", the server will analyze the emotion engine to determine that the user is feeling tired and adjust its information accordingly, providing details about nearby cafes and parks. This information will include details about relaxing places and how crowded they are.

[0127] Ultimately, the device provides the user with the acquired information in text or audio format. The information is delivered in a tone and content that is sensitive to the user's emotions. This results in a more intuitive and satisfying user experience.

[0128] In this way, the system of the present invention can sense the user's emotions and provide more appropriate and user-friendly information, thereby further improving the quality of life in smart cities.

[0129] The following describes the processing flow.

[0130] Step 1:

[0131] The user enters questions or requests into the device via voice or text. For example, they might type, "I'm tired today."

[0132] Step 2:

[0133] The device converts input data into text using speech recognition technology and sends it to the emotion engine. Here, tones are extracted from the speech, and keywords are extracted from the text.

[0134] Step 3:

[0135] The server uses an emotion engine to analyze the user's input data and estimate the user's emotional state. For example, if the user uses a word indicating fatigue, the server will determine the emotional state to be "tired."

[0136] Step 4:

[0137] The server then uses natural language processing techniques to analyze the user's intent. It takes the user's emotional state into consideration and prepares to determine what information is most appropriate.

[0138] Step 5:

[0139] The server generates queries to the database based on the analysis results and retrieves relevant information. For example, it might search for nearby cafes or parks for a user who is feeling tired.

[0140] Step 6:

[0141] The server formats the information retrieved from the database, taking into account the user's emotional state. When listing appropriate options, it prioritizes elements such as a "relaxing space" and a "calm atmosphere."

[0142] Step 7:

[0143] The server sends the formatted information to the terminal. The information is prepared in a format that is easy for the user to receive (text or audio).

[0144] Step 8:

[0145] The device displays the acquired information to the user. For example, it might say in a calm voice, "There's a quiet and relaxing cafe nearby."

[0146] Step 9:

[0147] Users use the presented information to make decisions about their actions. They can also ask additional questions or provide feedback if necessary.

[0148] (Example 2)

[0149] 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".

[0150] In modern information delivery systems, there is a problem in that information suggestions to users are uniform or non-individualized, and do not adequately consider users' feelings and emotional needs. As a result, the user experience is not sufficiently satisfying, and efficient information acquisition becomes difficult.

[0151] 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.

[0152] In this invention, the server includes means for identifying the user's intentions and emotional state, means for acquiring relevant information from information resources based on the identified intentions and emotions and adjusting the content and method of information provision, and means for formatting and presenting the acquired information in a manner that takes into account the user's emotional state. This enables the provision of appropriate and personalized information that responds to the user's emotions.

[0153] "Natural language data" refers to information composed of language that humans use on a daily basis, and is data that is input as audio or text.

[0154] "User intent" refers to the specific requests and desires that users have for an information system, and is revealed by analyzing the input natural language data.

[0155] "Emotional state" refers to the emotional reactions and feelings a user exhibits when entering information, and includes states such as "joy," "anger," and "sadness."

[0156] "Information resources" refer to databases and external information sources accessed to obtain the information to be provided, and are capable of efficiently collecting the necessary information.

[0157] "Formatting" refers to the process or method of organizing acquired information into a specific format, transforming it into a visually appealing and easily understandable form.

[0158] "External information sources" refer to additional information sources that are not stored within the system but are accessible via the internet or other means, and are intended to update information in real time.

[0159] This system analyzes the user's emotional state in real time and provides personalized information tailored to their specific needs. Natural language processing technology and an emotion analysis engine play a crucial role in the system's implementation.

[0160] The user inputs natural language data via a device. This input can be in the form of speech or text, and the device sends it to an emotion analysis engine. This engine uses speech recognition software and natural language processing tools to analyze the tone of the speech and the linguistic features of the text to identify the user's emotional state.

[0161] The server generates queries against information resources based on the results obtained from the sentiment analysis engine. This uses natural language processing techniques to search for and retrieve information that is relevant to the user's intent and emotions. The retrieved information is formatted in a way that is sensitive to the user's emotions and presented through the terminal.

[0162] For example, if a user asks, "I'm tired, is there anywhere I can rest?", the sentiment analysis engine will determine that the user is feeling tired. Based on this analysis, the server will search for information on nearby cafes, parks, and other places where the user can relax and provide this information to the user. This information will also include additional data such as crowd levels.

[0163] This system enhances the user experience by providing appropriate information tailored to their emotions. Furthermore, by integrating with external information sources in real time, it can always provide the most up-to-date information.

[0164] An example of a prompt for a generative AI model might be, "When a user is feeling relaxed, how should you provide them with city information that meets their needs?" Through this prompt, the model is expected to learn how to provide information based on emotions.

[0165] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0166] Step 1:

[0167] The user inputs information into the device via voice or text. The input natural language data is sent to the sentiment analysis engine. In this process, data is acquired using the device's microphone and keyboard, and if it is voice data, it is converted into text data through speech recognition.

[0168] Step 2:

[0169] The device sends input data to an emotion analysis engine. The emotion analysis engine analyzes the tone of voice and the linguistic features of the text to identify the user's emotional state. Here, speech recognition software and natural language processing techniques are used to extract the emotional data and map it to specific emotion labels such as joy and anger.

[0170] Step 3:

[0171] The server clarifies the user's intentions based on the results from the sentiment analysis engine. The server uses natural language processing techniques to determine how emotional states influence information delivery. As a result, it analyzes in detail what the user wants and clarifies their intentions.

[0172] Step 4:

[0173] The server generates queries to information resources based on the analyzed intent and emotional state, and retrieves relevant information. This process involves making appropriate queries to the database and prioritizing the retrieval of information relevant to the user's situation. By also considering past user data, optimal information provision becomes possible.

[0174] Step 5:

[0175] The server formats the acquired information with consideration for the user's emotions and sends it to the terminal. The terminal presents the acquired information to the user in either audio or text. The output information is presented in a way that is adjusted according to the user's emotional state, optimizing the user experience. This process utilizes speech synthesis and display technologies.

[0176] (Application Example 2)

[0177] 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".

[0178] In modern society, people living in cities need a diverse range of information. However, the information provided often fails to take into account the individual user's feelings and circumstances, resulting in inadequate information delivery. In particular, the lack of information tailored to the user's mental state is a significant challenge, leading to decreased user satisfaction.

[0179] 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.

[0180] In this invention, the server includes means for analyzing text data obtained from the user using natural language processing technology to identify the user's emotional state, means for obtaining relevant information from a database based on the identified emotional state, and means for formatting and presenting the obtained information in a tone and style corresponding to the user's emotions. This enables the provision of personalized information according to the user's emotional state.

[0181] "Natural language processing technology" is a technology that analyzes voice and text data obtained from users to mechanically understand their intentions and emotions.

[0182] "Text data" refers to information expressed in characters, which is analyzed using natural language processing techniques.

[0183] "Emotional state" refers to the user's emotional response and mental state, and serves as the basis for adjusting the content of the information provided accordingly.

[0184] A "database" is an electronic recording device that systematically stores and retrieves related information, and is used to obtain information as needed.

[0185] "Format" refers to a method or form for arranging information in an appropriate and easy-to-understand way and presenting it to the user.

[0186] "Tone of voice" refers to the vocal or expressive characteristics used when conveying information, and is adjusted according to the user's emotional state.

[0187] "Real-time" is a term that indicates that processing or reactions are performed immediately within the current time frame.

[0188] One embodiment of this invention is a system that provides personalized information according to the user's emotional state. The system mainly consists of a user terminal, a server, and a database.

[0189] The user's device is a device that accepts voice or text input and sends the input information to a server for sentiment analysis. In this process, the device uses speech recognition software (e.g., Speech-to-Text API) to convert speech to text.

[0190] The server receives user input data and analyzes the text data using natural language processing technology (e.g., IBM Watson® Natural Language Understanding). The purpose of the analysis is to identify not only the user's intent but also their emotional state. Based on the identified emotional state, the server communicates with the database to retrieve the most relevant information for the user.

[0191] Based on the acquired information, the server generates output in a format appropriate to the emotional state. This output is provided with a tone and style that takes the user's emotions into consideration, utilizing a generative AI model (e.g., OpenAI's GPT series). The server then sends this to the terminal and presents it to the user.

[0192] For example, if a user types "I'm tired, where can I relax?" into their device, the server analyzes this input to determine that the user is feeling tired. It then retrieves information about quiet, easily accessible cafes and parks from its database and presents this information to the user in a calming tone.

[0193] An example of a prompt to input into the generating AI model would be, "Based on the user's current emotional state (fatigue), please recommend a quiet and relaxing cafe." Through this prompt, it becomes easy to provide information that is tailored to the user's emotions.

[0194] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0195] Step 1:

[0196] The user's device accepts input in voice or text format. When the user enters a question or request and sends it, the device uses speech recognition software (e.g., Speech-to-Text API) to convert the voice data into text. The converted text data is retrieved and sent to the server.

[0197] Step 2:

[0198] The server receives text data sent from the terminal. The received data is analyzed using natural language processing technology (e.g., IBM Watson Natural Language Understanding). Through this analysis, the server identifies the user's intent and emotional state from the text data. The emotional state obtained through the analysis is output as base data for use in the next step.

[0199] Step 3:

[0200] The server queries the database based on the identified emotional state. It retrieves the most relevant information from the database corresponding to the user's emotional state (e.g., fatigue, stress, joy). This process also takes into account the user's past behavioral patterns and preferences. The output is a list of information to be presented to the user.

[0201] Step 4:

[0202] Based on the acquired information, the server uses a generative AI model (e.g., OpenAI's GPT series) to generate output in a manner appropriate to the user's emotional state. The generated output consists of text or audio that includes a tone and manner of speaking that takes the user's emotions into consideration.

[0203] Step 5:

[0204] Finally, the server sends the generated output to the terminal. The terminal then presents the received information to the user. This information is displayed as text on the smartphone's screen or played back as audio. This allows the user to receive information that is relevant to their own emotional state.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] [Second Embodiment]

[0209] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0210] 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.

[0211] 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).

[0212] 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.

[0213] 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.

[0214] 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).

[0215] 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.

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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.

[0220] 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".

[0221] The system of this invention efficiently acquires information that residents and visitors need within a city, thereby supporting a comfortable urban life. Based on user input, the system uses natural language processing technology to analyze the data and retrieves and presents relevant information from a database.

[0222] Users can send questions to the device via voice or text input. For example, if a user asks, "Where are the nearby restaurants?", the device formats the question into text and sends it to the server. The server then uses natural language processing technology to analyze this text and determine the user's intent.

[0223] Based on the analysis results, the server generates queries to retrieve relevant information from the database. These queries target relevant information such as restaurant location, opening hours, and ratings. The retrieved information is then reorganized into a personalized format, taking into account the user's past behavior patterns and preferences.

[0224] For example, the server can prioritize displaying restaurant information best suited to the user based on the types of restaurants the user has previously searched for and their visit history. Ultimately, the information provided to the user can be in text format as well as audio format, and the device will present the information in the most appropriate way depending on the situation.

[0225] Furthermore, the system integrates with external data sources, updating information in real time. This ensures that users are always provided with the latest information. This feature is particularly useful for responding to sudden changes in event information or emergencies.

[0226] In this way, the present invention can provide users with the information they need in a rapid and personalized manner, significantly improving the quality of life in smart cities.

[0227] The following describes the processing flow.

[0228] Step 1:

[0229] Users input questions or requests into the device via voice or text. For example, they might type, "Tell me about nearby restaurants."

[0230] Step 2:

[0231] The device converts voice input into text, organizes the text data, and sends it to the server. Speech recognition technology is used to format the user's words into text.

[0232] Step 3:

[0233] The server analyzes the received text data using natural language processing techniques to recognize the user's intent. This analysis involves intent classification and entity extraction. For example, it might identify the category "restaurant."

[0234] Step 4:

[0235] The server generates queries to query the database based on the analysis results. These queries include conditions for searching for information related to the identified entities and intentions.

[0236] Step 5:

[0237] The server executes the generated query and retrieves the relevant information from the database, such as a list of nearby restaurants.

[0238] Step 6:

[0239] The server reformats the retrieved information into a user-friendly format. If necessary, it personalizes the information by considering the user's past behavior patterns.

[0240] Step 7:

[0241] The server sends formatted information to the terminal. The information is in a format that can be handled in either text or audio format.

[0242] Step 8:

[0243] The device presents the received information to the user. Depending on the user's preferences, it may display the information on the screen or provide an audio response.

[0244] Step 9:

[0245] Based on the information presented, users can decide on their next action and, if necessary, ask additional questions or provide feedback to the device.

[0246] (Example 1)

[0247] 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."

[0248] In modern urban life, it is crucial to quickly and individually obtain the information that residents and visitors need. However, conventional information acquisition systems have struggled to accurately analyze user intent and provide personalized information that takes past behavioral patterns into account. Furthermore, real-time information updates have been insufficient, making it impossible to always provide the latest information. In addition, the convenience of information acquisition using voice input has not been adequate.

[0249] 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.

[0250] In this invention, the server includes means for analyzing data obtained from the user using natural language processing technology to identify the user's intent, means for obtaining relevant information from a data storage device based on the identified intent, and means for structuring and presenting the obtained information in a way that is suitable for the user. This enables the user to quickly obtain personalized information that takes into account past behavioral patterns and preferences. Furthermore, by converting voice input into text data and presenting information in both voice and text formats, user convenience can be improved. In addition, by synchronizing with external information sources in real time, the latest information can always be provided to support rapid decision-making.

[0251] "Natural language processing technology" is a technology that enables computers to understand, interpret, and generate human language, and to analyze data obtained from users to identify their intentions.

[0252] A "data storage device" is a device or system that stores information and keeps it accessible as needed, and is used to retrieve relevant information based on the user's intent.

[0253] "Past behavioral patterns" refer to the history of choices and actions a user has made in the past, and this data is used to personalize information.

[0254] An "external information source" refers to a source of data or information that exists outside the system, and is the destination to which the system connects in order to enable real-time information updates.

[0255] "Personalization" refers to the process of adjusting and presenting acquired information in a way that is optimal for the user, based on the user's past behavioral patterns and preferences.

[0256] "Voice input" refers to a method of sending data to a system using the voice spoken by the user, and includes the technology to convert this voice into text data.

[0257] "Real-time updates" refers to a function that synchronizes with external information sources to keep information up-to-date and reflects changes immediately.

[0258] This system begins with the user querying the device for information via voice or text. For example, the user might ask, "Where's the nearest cafe?" If the input is voice, the device converts it to text using speech recognition software. For speech recognition, common speech recognition technologies are used, and Google Cloud Speech-to-Text API or other solutions available on the market can be utilized.

[0259] The terminal then sends the converted text data to the server. The server uses natural language processing (NLP) techniques to analyze the text and identify the user's intent. At this stage, natural language processing libraries such as spaCy or BERT are used.

[0260] Based on the user's intent revealed through analysis, the server generates and executes queries to retrieve the necessary relevant information from the data storage device. These queries target information such as the location, opening hours, and ratings of nearby cafes.

[0261] The information obtained is personalized, taking into account the user's past behavioral patterns. The server uses this profile data to prioritize providing the type of information the user prefers.

[0262] Finally, the device presents the personalized information received from the server to the user in either audio or text format. The information is provided in the most effective way for the user, but this will vary depending on the device's characteristics, the user's environment, and settings.

[0263] For example, if a user speaks into their smartphone and asks, "Which cafes are open now?", the device converts the speech into text, the server analyzes the intent of the text to generate a query, and retrieves cafe information from its data storage. Then, after personalizing that information, it provides voice guidance such as, "There are two cafes open near your current location: Cafe A and Cafe B."

[0264] An example of a prompt to the generative AI model would be: "What nearby French restaurants would the user like to visit? Please provide priority results considering past visit history."

[0265] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0266] Step 1:

[0267] Users query the device for information via voice or text. For example, they might ask, "Where's the nearest cafe?" This input is received by the device. In the case of voice input, the device first uses speech recognition technology to convert the voice into text data. As a result, the voice input is output as text data.

[0268] Step 2:

[0269] The terminal sends the converted text data to the server. The server receives this text data as input and performs analysis using natural language processing. Specifically, BERT and spaCy can be used as natural language processing technologies. Through this analysis, the user's intent is identified, and the result is output.

[0270] Step 3:

[0271] The server generates a query to access data storage based on the identified user's intent. This query might retrieve information such as the location, opening hours, and reviews of nearby cafes. The server executes this query against the data storage and retrieves the relevant data. As a result, information matching the user's intent is retrieved and output.

[0272] Step 4:

[0273] The acquired information is personalized by the server, taking into account the user's past behavior patterns and preferences. Specifically, it analyzes data on places the user has visited in the past and their preferences, and selects information to display preferentially. The output of this process is personalized information.

[0274] Step 5:

[0275] The server sends personalized information to the terminal, which then presents it to the user. The terminal outputs the information in either voice or text format, the method of which is selected according to the user's device settings and environment. For example, as voice output, it might announce, "The cafes open near your current location are Cafe A and Cafe B."

[0276] (Application Example 1)

[0277] 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 glasses 214 will be referred to as the "terminal."

[0278] In modern urban life, individuals are required to obtain appropriate and useful information quickly and efficiently. However, the sheer volume of information makes it difficult to provide information tailored to individual needs. Furthermore, if information is not updated in real time, it becomes difficult to cope with constantly changing circumstances. Users need to be able to quickly obtain the information they seek, and that information needs to be personalized and up-to-date.

[0279] 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.

[0280] In this invention, the server includes means for analyzing information obtained from the user using natural language processing technology to identify the user's purpose, means for obtaining relevant information from information sources based on the identified purpose, and means for presenting the information as physical visual information via a user interface using a wearable information display device. This enables the user to obtain the latest and personalized information visually and intuitively through a wearable device.

[0281] "Natural language processing technology" is a technology that analyzes text and audio data obtained from users to enable computers to understand and process human language.

[0282] The "means for identifying the user's purpose" is a method for determining what the user is seeking from the analyzed information.

[0283] The "means for obtaining relevant information from information sources" is a method for collecting necessary data from information sources such as the Internet or local databases according to the user's requests.

[0284] The "wearable information display device" is a hardware device that a user can wear and is a technology for providing visual information.

[0285] The "means for presenting information visually via a user interface" is a method for visually displaying the acquired information in a form easy for the user to understand and operating it through the interface.

[0286] The "means for updating information in real-time in cooperation with an external information source" is a method for continuously communicating with an external information source to update data in order to always hold the latest information.

[0287] "Individualized information" is information adjusted to an optimal form for a specific user based on the user's past behaviors and preferences.

[0288] The system for implementing this invention enables a user wearing smart glasses to obtain and display necessary information in the city in real-time by making natural language questions and requests. By using smart glasses as the wearable information display device, information is provided to the user visually and intuitively. The terminal and the server cooperate to perform information processing in the following ways.

[0289] When receiving voice input from the user, the server has a function of converting voice to text using natural language processing technology. Specifically, software such as the Google Cloud Natural Language API is used to analyze and convert the voice. These text data are analyzed in detail to identify the user's intention.

[0290] Next, the server retrieves relevant information from databases and internet sources based on the identified purpose. By utilizing the Google Maps API, for example, it is possible to obtain location information and real-time event information.

[0291] The server further personalizes the acquired information based on the user's past behavior history and preferences. At this stage, machine learning algorithms can also be used, so that information relevant to the user is prioritized according to their browsing history and past choices.

[0292] The collected information is presented as visual information through the smart glasses' display via a user interface. This allows users to receive information in real time and in a personalized format as needed. For example, if a user asks, "What live events are I able to go to this evening?", the server analyzes the question and displays relevant event information on the glasses' display in real time.

[0293] An example of a prompt for a generative AI model would be: "The user asked about live events they can attend this evening. Considering their current location, suggest the three closest and highest-rated events."

[0294] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0295] Step 1:

[0296] The device acquires the user's voice input. The user's voice is captured through the smart glasses' microphone. This input voice data is acquired as a digital audio file.

[0297] Step 2:

[0298] The terminal transmits the acquired voice data to the server. The terminal transfers the voice data to the server via the network and prepares for processing. The output here is for the server to receive the voice data.

[0299] Step 3:

[0300] The server converts the voice data into text. Using the Google Cloud Natural Language API, the voice data is converted into text data. The input of this process is voice data, and the output is text data for analysis.

[0301] Step 4:

[0302] The server analyzes the text data to identify the user's intention. Utilizing natural language processing techniques, the text is scrutinized to understand the user's question or request. The input is text data, and the output is information regarding the user's intention. Specific operations include keyword extraction and context analysis.

[0303] Step 5:

[0304] The server retrieves relevant information based on the user's intention. Using the Google Maps API, necessary information, such as nearby event information, is retrieved from the database. The input is information regarding the user's intention, and the output is a dataset of relevant information.

[0305] Step 6:

[0306] The server personalizes the acquired information. Using machine learning algorithms, considering the user's past behavior and preferences, the information is optimized. The input is a dataset of relevant information, and the output is a personalized information set.

[0307] Step 7:

[0308] The device presents personalized information to the user. The information is displayed visually and intuitively through the smart glasses' display. The input is a personalized set of information, and the output is information that the user can visually confirm.

[0309] 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.

[0310] The system of this invention provides more personalized urban information by taking into account the user's emotional state. This system combines natural language processing technology and an emotion engine, dynamically adjusting the content and method of information presentation based on the user's emotion analysis.

[0311] The user inputs information into the device via voice or text. This input data is sent by the device to the emotion engine, which analyzes the tone of voice and linguistic features of the text to recognize the user's emotional state (e.g., joy, anger, sadness, etc.).

[0312] Based on the sentiment analysis results received from the sentiment engine, the server further analyzes the user's intentions using natural language processing technology. This process evaluates how the user's emotional state affects the way and content of information provided. For example, if it is determined that the user is stressed, the server will take measures such as recommending a relaxing place in a calm tone.

[0313] Furthermore, the server generates queries to the database based on the analysis results and retrieves relevant information. In doing so, it takes into account past sentiment data and reactions, prioritizing the retrieval of information most relevant to the user.

[0314] For example, if a user asks, "I'm tired, is there anywhere I can rest?", the server will analyze the emotion engine to determine that the user is feeling tired and adjust its information accordingly, providing details about nearby cafes and parks. This information will include details about relaxing places and how crowded they are.

[0315] Ultimately, the device provides the user with the acquired information in text or audio format. The information is delivered in a tone and content that is sensitive to the user's emotions. This results in a more intuitive and satisfying user experience.

[0316] In this way, the system of the present invention can sense the user's emotions and provide more appropriate and user-friendly information, thereby further improving the quality of life in smart cities.

[0317] The following describes the processing flow.

[0318] Step 1:

[0319] The user enters questions or requests into the device via voice or text. For example, they might type, "I'm tired today."

[0320] Step 2:

[0321] The device converts input data into text using speech recognition technology and sends it to the emotion engine. Here, tones are extracted from the speech, and keywords are extracted from the text.

[0322] Step 3:

[0323] The server uses an emotion engine to analyze the user's input data and estimate the user's emotional state. For example, if the user uses a word indicating fatigue, the server will determine the emotional state to be "tired."

[0324] Step 4:

[0325] The server then uses natural language processing techniques to analyze the user's intent. It takes the user's emotional state into consideration and prepares to determine what information is most appropriate.

[0326] Step 5:

[0327] The server generates queries to the database based on the analysis results and retrieves relevant information. For example, it might search for nearby cafes or parks for a user who is feeling tired.

[0328] Step 6:

[0329] The server formats the information retrieved from the database, taking into account the user's emotional state. When listing appropriate options, it prioritizes elements such as a "relaxing space" and a "calm atmosphere."

[0330] Step 7:

[0331] The server sends the formatted information to the terminal. The information is prepared in a format that is easy for the user to receive (text or audio).

[0332] Step 8:

[0333] The device displays the acquired information to the user. For example, it might say in a calm voice, "There's a quiet and relaxing cafe nearby."

[0334] Step 9:

[0335] Users use the presented information to make decisions about their actions. They can also ask additional questions or provide feedback if necessary.

[0336] (Example 2)

[0337] 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".

[0338] In modern information delivery systems, there is a problem in that information suggestions to users are uniform or non-individualized, and do not adequately consider users' feelings and emotional needs. As a result, the user experience is not sufficiently satisfying, and efficient information acquisition becomes difficult.

[0339] 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.

[0340] In this invention, the server includes means for identifying the user's intentions and emotional state, means for acquiring relevant information from information resources based on the identified intentions and emotions and adjusting the content and method of information provision, and means for formatting and presenting the acquired information in a manner that takes into account the user's emotional state. This enables the provision of appropriate and personalized information that responds to the user's emotions.

[0341] "Natural language data" refers to information composed of language that humans use on a daily basis, and is data that is input as audio or text.

[0342] "User intent" refers to the specific requests and desires that users have for an information system, and is revealed by analyzing the input natural language data.

[0343] "Emotional state" refers to the emotional reactions and feelings a user exhibits when entering information, and includes states such as "joy," "anger," and "sadness."

[0344] "Information resources" refer to databases and external information sources accessed to obtain the information to be provided, and are capable of efficiently collecting the necessary information.

[0345] "Formatting" refers to the process or method of organizing acquired information into a specific format, transforming it into a visually appealing and easily understandable form.

[0346] "External information sources" refer to additional information sources that are not stored within the system but are accessible via the internet or other means, and are intended to update information in real time.

[0347] This system analyzes the user's emotional state in real time and provides personalized information tailored to their specific needs. Natural language processing technology and an emotion analysis engine play a crucial role in the system's implementation.

[0348] The user inputs natural language data via a device. This input can be in the form of speech or text, and the device sends it to an emotion analysis engine. This engine uses speech recognition software and natural language processing tools to analyze the tone of the speech and the linguistic features of the text to identify the user's emotional state.

[0349] The server generates queries against information resources based on the results obtained from the sentiment analysis engine. This uses natural language processing techniques to search for and retrieve information that is relevant to the user's intent and emotions. The retrieved information is formatted in a way that is sensitive to the user's emotions and presented through the terminal.

[0350] For example, if a user asks, "I'm tired, is there anywhere I can rest?", the sentiment analysis engine will determine that the user is feeling tired. Based on this analysis, the server will search for information on nearby cafes, parks, and other places where the user can relax and provide this information to the user. This information will also include additional data such as crowd levels.

[0351] This system enhances the user experience by providing appropriate information tailored to their emotions. Furthermore, by integrating with external information sources in real time, it can always provide the most up-to-date information.

[0352] An example of a prompt for a generative AI model might be, "When a user is feeling relaxed, how should you provide them with city information that meets their needs?" Through this prompt, the model is expected to learn how to provide information based on emotions.

[0353] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0354] Step 1:

[0355] The user inputs information into the device via voice or text. The input natural language data is sent to the sentiment analysis engine. In this process, data is acquired using the device's microphone and keyboard, and if it is voice data, it is converted into text data through speech recognition.

[0356] Step 2:

[0357] The device sends input data to an emotion analysis engine. The emotion analysis engine analyzes the tone of voice and the linguistic features of the text to identify the user's emotional state. Here, speech recognition software and natural language processing techniques are used to extract the emotional data and map it to specific emotion labels such as joy and anger.

[0358] Step 3:

[0359] The server clarifies the user's intentions based on the results from the sentiment analysis engine. The server uses natural language processing techniques to determine how emotional states influence information delivery. As a result, it analyzes in detail what the user wants and clarifies their intentions.

[0360] Step 4:

[0361] The server generates queries to information resources based on the analyzed intent and emotional state, and retrieves relevant information. This process involves making appropriate queries to the database and prioritizing the retrieval of information relevant to the user's situation. By also considering past user data, optimal information provision becomes possible.

[0362] Step 5:

[0363] The server formats the acquired information with consideration for the user's emotions and sends it to the terminal. The terminal presents the acquired information to the user in either audio or text. The output information is presented in a way that is adjusted according to the user's emotional state, optimizing the user experience. This process utilizes speech synthesis and display technologies.

[0364] (Application Example 2)

[0365] 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."

[0366] In modern society, people living in cities need a diverse range of information. However, the information provided often fails to take into account the individual user's feelings and circumstances, resulting in inadequate information delivery. In particular, the lack of information tailored to the user's mental state is a significant challenge, leading to decreased user satisfaction.

[0367] 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.

[0368] In this invention, the server includes means for analyzing text data obtained from the user using natural language processing technology to identify the user's emotional state, means for obtaining relevant information from a database based on the identified emotional state, and means for formatting and presenting the obtained information in a tone and style corresponding to the user's emotions. This enables the provision of personalized information according to the user's emotional state.

[0369] "Natural language processing technology" is a technology that analyzes voice and text data obtained from users to mechanically understand their intentions and emotions.

[0370] "Text data" refers to information expressed in characters, which is analyzed using natural language processing techniques.

[0371] "Emotional state" refers to the user's emotional response and mental state, and serves as the basis for adjusting the content of the information provided accordingly.

[0372] A "database" is an electronic recording device that systematically stores and retrieves related information, and is used to obtain information as needed.

[0373] "Format" refers to a method or form for arranging information in an appropriate and easy-to-understand way and presenting it to the user.

[0374] "Tone of voice" refers to the vocal or expressive characteristics used when conveying information, and is adjusted according to the user's emotional state.

[0375] "Real-time" is a term that indicates that processing or reactions are performed immediately within the current time frame.

[0376] One embodiment of this invention is a system that provides personalized information according to the user's emotional state. The system mainly consists of a user terminal, a server, and a database.

[0377] The user's device is a device that accepts voice or text input and sends the input information to a server for sentiment analysis. In this process, the device uses speech recognition software (e.g., Speech-to-Text API) to convert speech to text.

[0378] The server receives user input data and analyzes the text data using natural language processing technology (e.g., IBM Watson Natural Language Understanding). The purpose of the analysis is to identify not only the user's intent but also their emotional state. Based on the identified emotional state, the server communicates with a database to retrieve the most relevant information for the user.

[0379] Based on the acquired information, the server generates output in a format appropriate to the emotional state. This output is provided with a tone and style that takes the user's emotions into consideration, utilizing a generative AI model (e.g., OpenAI's GPT series). The server then sends this to the terminal and presents it to the user.

[0380] For example, if a user types "I'm tired, where can I relax?" into their device, the server analyzes this input to determine that the user is feeling tired. It then retrieves information about quiet, easily accessible cafes and parks from its database and presents this information to the user in a calming tone.

[0381] An example of a prompt to input into the generating AI model would be, "Based on the user's current emotional state (fatigue), please recommend a quiet and relaxing cafe." Through this prompt, it becomes easy to provide information that is tailored to the user's emotions.

[0382] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0383] Step 1:

[0384] The user's device accepts input in voice or text format. When the user enters a question or request and sends it, the device uses speech recognition software (e.g., Speech-to-Text API) to convert the voice data into text. The converted text data is retrieved and sent to the server.

[0385] Step 2:

[0386] The server receives text data sent from the terminal. The received data is analyzed using natural language processing technology (e.g., IBM Watson Natural Language Understanding). Through this analysis, the server identifies the user's intent and emotional state from the text data. The emotional state obtained through the analysis is output as base data for use in the next step.

[0387] Step 3:

[0388] The server queries the database based on the identified emotional state. It retrieves the most relevant information from the database corresponding to the user's emotional state (e.g., fatigue, stress, joy). This process also takes into account the user's past behavioral patterns and preferences. The output is a list of information to be presented to the user.

[0389] Step 4:

[0390] Based on the acquired information, the server uses a generative AI model (e.g., OpenAI's GPT series) to generate output in a manner appropriate to the user's emotional state. The generated output consists of text or audio that includes a tone and manner of speaking that takes the user's emotions into consideration.

[0391] Step 5:

[0392] Finally, the server sends the generated output to the terminal. The terminal then presents the received information to the user. This information is displayed as text on the smartphone's screen or played back as audio. This allows the user to receive information that is relevant to their own emotional state.

[0393] 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.

[0394] 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.

[0395] 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.

[0396] [Third Embodiment]

[0397] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0398] 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.

[0399] 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).

[0400] 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.

[0401] 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.

[0402] 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).

[0403] 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.

[0404] 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.

[0405] 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.

[0406] 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.

[0407] 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.

[0408] 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".

[0409] The system of this invention efficiently acquires information that residents and visitors need within a city, thereby supporting a comfortable urban life. Based on user input, the system uses natural language processing technology to analyze the data and retrieves and presents relevant information from a database.

[0410] Users can send questions to the device via voice or text input. For example, if a user asks, "Where are the nearby restaurants?", the device formats the question into text and sends it to the server. The server then uses natural language processing technology to analyze this text and determine the user's intent.

[0411] Based on the analysis results, the server generates queries to retrieve relevant information from the database. These queries target relevant information such as restaurant location, opening hours, and ratings. The retrieved information is then reorganized into a personalized format, taking into account the user's past behavior patterns and preferences.

[0412] For example, the server can prioritize displaying restaurant information best suited to the user based on the types of restaurants the user has previously searched for and their visit history. Ultimately, the information provided to the user can be in text format as well as audio format, and the device will present the information in the most appropriate way depending on the situation.

[0413] Furthermore, the system integrates with external data sources, updating information in real time. This ensures that users are always provided with the latest information. This feature is particularly useful for responding to sudden changes in event information or emergencies.

[0414] In this way, the present invention can provide users with the information they need in a rapid and personalized manner, significantly improving the quality of life in smart cities.

[0415] The following describes the processing flow.

[0416] Step 1:

[0417] Users input questions or requests into the device via voice or text. For example, they might type, "Tell me about nearby restaurants."

[0418] Step 2:

[0419] The device converts voice input into text, organizes the text data, and sends it to the server. Speech recognition technology is used to format the user's words into text.

[0420] Step 3:

[0421] The server analyzes the received text data using natural language processing techniques to recognize the user's intent. This analysis involves intent classification and entity extraction. For example, it might identify the category "restaurant."

[0422] Step 4:

[0423] The server generates queries to query the database based on the analysis results. These queries include conditions for searching for information related to the identified entities and intentions.

[0424] Step 5:

[0425] The server executes the generated query and retrieves the relevant information from the database, such as a list of nearby restaurants.

[0426] Step 6:

[0427] The server reformats the retrieved information into a user-friendly format. If necessary, it personalizes the information by considering the user's past behavior patterns.

[0428] Step 7:

[0429] The server sends formatted information to the terminal. The information is in a format that can be handled in either text or audio format.

[0430] Step 8:

[0431] The device presents the received information to the user. Depending on the user's preferences, it may display the information on the screen or provide an audio response.

[0432] Step 9:

[0433] Based on the information presented, users can decide on their next action and, if necessary, ask additional questions or provide feedback to the device.

[0434] (Example 1)

[0435] 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."

[0436] In modern urban life, it is crucial to quickly and individually obtain the information that residents and visitors need. However, conventional information acquisition systems have struggled to accurately analyze user intent and provide personalized information that takes past behavioral patterns into account. Furthermore, real-time information updates have been insufficient, making it impossible to always provide the latest information. In addition, the convenience of information acquisition using voice input has not been adequate.

[0437] 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.

[0438] In this invention, the server includes means for analyzing data obtained from the user using natural language processing technology to identify the user's intent, means for obtaining relevant information from a data storage device based on the identified intent, and means for structuring and presenting the obtained information in a way that is suitable for the user. This enables the user to quickly obtain personalized information that takes into account past behavioral patterns and preferences. Furthermore, by converting voice input into text data and presenting information in both voice and text formats, user convenience can be improved. In addition, by synchronizing with external information sources in real time, the latest information can always be provided to support rapid decision-making.

[0439] "Natural language processing technology" is a technology that enables computers to understand, interpret, and generate human language, and to analyze data obtained from users to identify their intentions.

[0440] A "data storage device" is a device or system that stores information and keeps it accessible as needed, and is used to retrieve relevant information based on the user's intent.

[0441] "Past behavioral patterns" refer to the history of choices and actions a user has made in the past, and this data is used to personalize information.

[0442] An "external information source" refers to a source of data or information that exists outside the system, and is the destination to which the system connects in order to enable real-time information updates.

[0443] "Personalization" refers to the process of adjusting and presenting acquired information in a way that is optimal for the user, based on the user's past behavioral patterns and preferences.

[0444] "Voice input" refers to a method of sending data to a system using the voice spoken by the user, and includes the technology to convert this voice into text data.

[0445] "Real-time updates" refers to a function that synchronizes with external information sources to keep information up-to-date and reflects changes immediately.

[0446] This system begins with the user querying the device for information via voice or text. For example, the user might ask, "Where's the nearest cafe?" If the input is voice, the device converts it to text using speech recognition software. For speech recognition, common speech recognition technologies are used, and Google Cloud Speech-to-Text API or other solutions available on the market can be utilized.

[0447] The terminal then sends the converted text data to the server. The server uses natural language processing (NLP) techniques to analyze the text and identify the user's intent. At this stage, natural language processing libraries such as spaCy or BERT are used.

[0448] Based on the user's intent revealed through analysis, the server generates and executes queries to retrieve the necessary relevant information from the data storage device. These queries target information such as the location, opening hours, and ratings of nearby cafes.

[0449] The information obtained is personalized, taking into account the user's past behavioral patterns. The server uses this profile data to prioritize providing the type of information the user prefers.

[0450] Finally, the device presents the personalized information received from the server to the user in either audio or text format. The information is provided in the most effective way for the user, but this will vary depending on the device's characteristics, the user's environment, and settings.

[0451] For example, if a user speaks into their smartphone and asks, "Which cafes are open now?", the device converts the speech into text, the server analyzes the intent of the text to generate a query, and retrieves cafe information from its data storage. Then, after personalizing that information, it provides voice guidance such as, "There are two cafes open near your current location: Cafe A and Cafe B."

[0452] An example of a prompt to the generative AI model would be: "What nearby French restaurants would the user like to visit? Please provide priority results considering past visit history."

[0453] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0454] Step 1:

[0455] Users query the device for information via voice or text. For example, they might ask, "Where's the nearest cafe?" This input is received by the device. In the case of voice input, the device first uses speech recognition technology to convert the voice into text data. As a result, the voice input is output as text data.

[0456] Step 2:

[0457] The terminal sends the converted text data to the server. The server receives this text data as input and performs analysis using natural language processing. Specifically, BERT and spaCy can be used as natural language processing technologies. Through this analysis, the user's intent is identified, and the result is output.

[0458] Step 3:

[0459] The server generates a query to access data storage based on the identified user's intent. This query might retrieve information such as the location, opening hours, and reviews of nearby cafes. The server executes this query against the data storage and retrieves the relevant data. As a result, information matching the user's intent is retrieved and output.

[0460] Step 4:

[0461] The acquired information is personalized by the server, taking into account the user's past behavior patterns and preferences. Specifically, it analyzes data on places the user has visited in the past and their preferences, and selects information to display preferentially. The output of this process is personalized information.

[0462] Step 5:

[0463] The server sends personalized information to the terminal, which then presents it to the user. The terminal outputs the information in either voice or text format, the method of which is selected according to the user's device settings and environment. For example, as voice output, it might announce, "The cafes open near your current location are Cafe A and Cafe B."

[0464] (Application Example 1)

[0465] 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."

[0466] In modern urban life, individuals are required to obtain appropriate and useful information quickly and efficiently. However, the sheer volume of information makes it difficult to provide information tailored to individual needs. Furthermore, if information is not updated in real time, it becomes difficult to cope with constantly changing circumstances. Users need to be able to quickly obtain the information they seek, and that information needs to be personalized and up-to-date.

[0467] 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.

[0468] In this invention, the server includes means for analyzing information obtained from the user using natural language processing technology to identify the user's purpose, means for obtaining relevant information from information sources based on the identified purpose, and means for presenting the information as physical visual information via a user interface using a wearable information display device. This enables the user to obtain the latest and personalized information visually and intuitively through a wearable device.

[0469] "Natural language processing technology" is a technology that analyzes text and audio data obtained from users to enable computers to understand and process human language.

[0470] "Means for identifying user objectives" refers to methods for determining what a user wants based on the analyzed information.

[0471] "Means of obtaining relevant information from information sources" refers to methods for collecting necessary data from information sources such as the internet or local databases, in accordance with user requests.

[0472] A "wearable information display device" is a hardware device that a user can wear to provide visual information.

[0473] "Means of presenting information as visual information via a user interface" refers to methods of visually displaying acquired information in a way that is easy for the user to understand, and of manipulating it through an interface.

[0474] "A means of updating information in real time in conjunction with external information sources" refers to a method of continuously communicating with external information sources to update data in order to always maintain the latest information.

[0475] "Personalized information" refers to information that has been tailored to be optimal for a specific user based on their past behavior and preferences.

[0476] The system implementing this invention enables a user wearing smart glasses to obtain and display necessary information in real time within a city by making questions and requests in natural language. By using smart glasses as a wearable information display device, information is provided to the user visually and intuitively. The terminal and server cooperate and process information in the following manner.

[0477] The server has the capability to convert speech input from users into text using natural language processing technology. Specifically, it uses software such as the Google Cloud Natural Language API to analyze and convert the speech. This text data is then analyzed in detail to identify the user's intent.

[0478] Next, the server retrieves relevant information from databases and internet sources based on the identified purpose. By utilizing the Google Maps API, for example, it is possible to obtain location information and real-time event information.

[0479] The server further personalizes the acquired information based on the user's past behavior history and preferences. At this stage, machine learning algorithms can also be used, so that information relevant to the user is prioritized according to their browsing history and past choices.

[0480] The collected information is presented as visual information through the smart glasses' display via a user interface. This allows users to receive information in real time and in a personalized format as needed. For example, if a user asks, "What live events are I able to go to this evening?", the server analyzes the question and displays relevant event information on the glasses' display in real time.

[0481] An example of a prompt for a generative AI model would be: "The user asked about live events they can attend this evening. Considering their current location, suggest the three closest and highest-rated events."

[0482] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0483] Step 1:

[0484] The device acquires the user's voice input. The user's voice is captured through the smart glasses' microphone. This input voice data is acquired as a digital audio file.

[0485] Step 2:

[0486] The terminal sends the acquired audio data to the server. The terminal transfers the audio data to the server via the network and prepares it for processing. The output here is the server receiving the audio data.

[0487] Step 3:

[0488] The server converts the audio data to text. The Google Cloud Natural Language API is used to convert the audio data to text data. The input to this process is audio data, and the output is text data for analysis.

[0489] Step 4:

[0490] The server analyzes text data to identify the user's intent. It utilizes natural language processing techniques to refine the text and understand the user's questions and requests. The input is text data, and the output is information about the user's intent. Specific operations include keyword extraction and contextual analysis.

[0491] Step 5:

[0492] The server retrieves relevant information based on the user's intent. Using the Google Maps API, it retrieves necessary information, such as nearby event information, from a database. The input is information about the user's intent, and the output is a dataset of relevant information.

[0493] Step 6:

[0494] The server personalizes the information it acquires. Using machine learning algorithms, it optimizes the information by considering the user's past behavior and preferences. The input is a dataset of related information, and the output is a personalized set of information.

[0495] Step 7:

[0496] The device presents personalized information to the user. The information is displayed visually and intuitively through the smart glasses' display. The input is a personalized set of information, and the output is information that the user can visually confirm.

[0497] 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.

[0498] The system of this invention provides more personalized urban information by taking into account the user's emotional state. This system combines natural language processing technology and an emotion engine, dynamically adjusting the content and method of information presentation based on the user's emotion analysis.

[0499] The user inputs information into the device via voice or text. This input data is sent by the device to the emotion engine, which analyzes the tone of voice and linguistic features of the text to recognize the user's emotional state (e.g., joy, anger, sadness, etc.).

[0500] Based on the sentiment analysis results received from the sentiment engine, the server further analyzes the user's intentions using natural language processing technology. This process evaluates how the user's emotional state affects the way and content of information provided. For example, if it is determined that the user is stressed, the server will take measures such as recommending a relaxing place in a calm tone.

[0501] Furthermore, the server generates queries to the database based on the analysis results and retrieves relevant information. In doing so, it takes into account past sentiment data and reactions, prioritizing the retrieval of information most relevant to the user.

[0502] For example, if a user asks, "I'm tired, is there anywhere I can rest?", the server will analyze the emotion engine to determine that the user is feeling tired and adjust its information accordingly, providing details about nearby cafes and parks. This information will include details about relaxing places and how crowded they are.

[0503] Ultimately, the device provides the user with the acquired information in text or audio format. The information is delivered in a tone and content that is sensitive to the user's emotions. This results in a more intuitive and satisfying user experience.

[0504] In this way, the system of the present invention can sense the user's emotions and provide more appropriate and user-friendly information, thereby further improving the quality of life in smart cities.

[0505] The following describes the processing flow.

[0506] Step 1:

[0507] The user enters questions or requests into the device via voice or text. For example, they might type, "I'm tired today."

[0508] Step 2:

[0509] The device converts input data into text using speech recognition technology and sends it to the emotion engine. Here, tones are extracted from the speech, and keywords are extracted from the text.

[0510] Step 3:

[0511] The server uses an emotion engine to analyze the user's input data and estimate the user's emotional state. For example, if the user uses a word indicating fatigue, the server will determine the emotional state to be "tired."

[0512] Step 4:

[0513] The server then uses natural language processing techniques to analyze the user's intent. It takes the user's emotional state into consideration and prepares to determine what information is most appropriate.

[0514] Step 5:

[0515] The server generates queries to the database based on the analysis results and retrieves relevant information. For example, it might search for nearby cafes or parks for a user who is feeling tired.

[0516] Step 6:

[0517] The server formats the information retrieved from the database, taking into account the user's emotional state. When listing appropriate options, it prioritizes elements such as a "relaxing space" and a "calm atmosphere."

[0518] Step 7:

[0519] The server sends the formatted information to the terminal. The information is prepared in a format that is easy for the user to receive (text or audio).

[0520] Step 8:

[0521] The device displays the acquired information to the user. For example, it might say in a calm voice, "There's a quiet and relaxing cafe nearby."

[0522] Step 9:

[0523] Users use the presented information to make decisions about their actions. They can also ask additional questions or provide feedback if necessary.

[0524] (Example 2)

[0525] 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."

[0526] In modern information delivery systems, there is a problem in that information suggestions to users are uniform or non-individualized, and do not adequately consider users' feelings and emotional needs. As a result, the user experience is not sufficiently satisfying, and efficient information acquisition becomes difficult.

[0527] 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.

[0528] In this invention, the server includes means for identifying the user's intentions and emotional state, means for acquiring relevant information from information resources based on the identified intentions and emotions and adjusting the content and method of information provision, and means for formatting and presenting the acquired information in a manner that takes into account the user's emotional state. This enables the provision of appropriate and personalized information that responds to the user's emotions.

[0529] "Natural language data" refers to information composed of language that humans use on a daily basis, and is data that is input as audio or text.

[0530] "User intent" refers to the specific requests and desires that users have for an information system, and is revealed by analyzing the input natural language data.

[0531] "Emotional state" refers to the emotional reactions and feelings a user exhibits when entering information, and includes states such as "joy," "anger," and "sadness."

[0532] "Information resources" refer to databases and external information sources accessed to obtain the information to be provided, and are capable of efficiently collecting the necessary information.

[0533] "Formatting" refers to the process or method of organizing acquired information into a specific format, transforming it into a visually appealing and easily understandable form.

[0534] "External information sources" refer to additional information sources that are not stored within the system but are accessible via the internet or other means, and are intended to update information in real time.

[0535] This system analyzes the user's emotional state in real time and provides personalized information tailored to their specific needs. Natural language processing technology and an emotion analysis engine play a crucial role in the system's implementation.

[0536] The user inputs natural language data via a device. This input can be in the form of speech or text, and the device sends it to an emotion analysis engine. This engine uses speech recognition software and natural language processing tools to analyze the tone of the speech and the linguistic features of the text to identify the user's emotional state.

[0537] The server generates queries against information resources based on the results obtained from the sentiment analysis engine. This uses natural language processing techniques to search for and retrieve information that is relevant to the user's intent and emotions. The retrieved information is formatted in a way that is sensitive to the user's emotions and presented through the terminal.

[0538] For example, if a user asks, "I'm tired, is there anywhere I can rest?", the sentiment analysis engine will determine that the user is feeling tired. Based on this analysis, the server will search for information on nearby cafes, parks, and other places where the user can relax and provide this information to the user. This information will also include additional data such as crowd levels.

[0539] This system enhances the user experience by providing appropriate information tailored to their emotions. Furthermore, by integrating with external information sources in real time, it can always provide the most up-to-date information.

[0540] An example of a prompt for a generative AI model might be, "When a user is feeling relaxed, how should you provide them with city information that meets their needs?" Through this prompt, the model is expected to learn how to provide information based on emotions.

[0541] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0542] Step 1:

[0543] The user inputs information into the device via voice or text. The input natural language data is sent to the sentiment analysis engine. In this process, data is acquired using the device's microphone and keyboard, and if it is voice data, it is converted into text data through speech recognition.

[0544] Step 2:

[0545] The device sends input data to an emotion analysis engine. The emotion analysis engine analyzes the tone of voice and the linguistic features of the text to identify the user's emotional state. Here, speech recognition software and natural language processing techniques are used to extract the emotional data and map it to specific emotion labels such as joy and anger.

[0546] Step 3:

[0547] The server clarifies the user's intentions based on the results from the sentiment analysis engine. The server uses natural language processing techniques to determine how emotional states influence information delivery. As a result, it analyzes in detail what the user wants and clarifies their intentions.

[0548] Step 4:

[0549] The server generates queries to information resources based on the analyzed intent and emotional state, and retrieves relevant information. This process involves making appropriate queries to the database and prioritizing the retrieval of information relevant to the user's situation. By also considering past user data, optimal information provision becomes possible.

[0550] Step 5:

[0551] The server formats the acquired information with consideration for the user's emotions and sends it to the terminal. The terminal presents the acquired information to the user in either audio or text. The output information is presented in a way that is adjusted according to the user's emotional state, optimizing the user experience. This process utilizes speech synthesis and display technologies.

[0552] (Application Example 2)

[0553] 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."

[0554] In modern society, people living in cities need a diverse range of information. However, the information provided often fails to take into account the individual user's feelings and circumstances, resulting in inadequate information delivery. In particular, the lack of information tailored to the user's mental state is a significant challenge, leading to decreased user satisfaction.

[0555] 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.

[0556] In this invention, the server includes means for analyzing text data obtained from the user using natural language processing technology to identify the user's emotional state, means for obtaining relevant information from a database based on the identified emotional state, and means for formatting and presenting the obtained information in a tone and style corresponding to the user's emotions. This enables the provision of personalized information according to the user's emotional state.

[0557] "Natural language processing technology" is a technology that analyzes voice and text data obtained from users to mechanically understand their intentions and emotions.

[0558] "Text data" refers to information expressed in characters, which is analyzed using natural language processing techniques.

[0559] "Emotional state" refers to the user's emotional response and mental state, and serves as the basis for adjusting the content of the information provided accordingly.

[0560] A "database" is an electronic recording device that systematically stores and retrieves related information, and is used to obtain information as needed.

[0561] "Format" refers to a method or form for arranging information in an appropriate and easy-to-understand way and presenting it to the user.

[0562] "Tone of voice" refers to the vocal or expressive characteristics used when conveying information, and is adjusted according to the user's emotional state.

[0563] "Real-time" is a term that indicates that processing or reactions are performed immediately within the current time frame.

[0564] One embodiment of this invention is a system that provides personalized information according to the user's emotional state. The system mainly consists of a user terminal, a server, and a database.

[0565] The user's device is a device that accepts voice or text input and sends the input information to a server for sentiment analysis. In this process, the device uses speech recognition software (e.g., Speech-to-Text API) to convert speech to text.

[0566] The server receives user input data and analyzes the text data using natural language processing technology (e.g., IBM Watson Natural Language Understanding). The purpose of the analysis is to identify not only the user's intent but also their emotional state. Based on the identified emotional state, the server communicates with a database to retrieve the most relevant information for the user.

[0567] Based on the acquired information, the server generates output in a format appropriate to the emotional state. This output is provided with a tone and style that takes the user's emotions into consideration, utilizing a generative AI model (e.g., OpenAI's GPT series). The server then sends this to the terminal and presents it to the user.

[0568] For example, if a user types "I'm tired, where can I relax?" into their device, the server analyzes this input to determine that the user is feeling tired. It then retrieves information about quiet, easily accessible cafes and parks from its database and presents this information to the user in a calming tone.

[0569] An example of a prompt to input into the generating AI model would be, "Based on the user's current emotional state (fatigue), please recommend a quiet and relaxing cafe." Through this prompt, it becomes easy to provide information that is tailored to the user's emotions.

[0570] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0571] Step 1:

[0572] The user's device accepts input in voice or text format. When the user enters a question or request and sends it, the device uses speech recognition software (e.g., Speech-to-Text API) to convert the voice data into text. The converted text data is retrieved and sent to the server.

[0573] Step 2:

[0574] The server receives text data sent from the terminal. The received data is analyzed using natural language processing technology (e.g., IBM Watson Natural Language Understanding). Through this analysis, the server identifies the user's intent and emotional state from the text data. The emotional state obtained through the analysis is output as base data for use in the next step.

[0575] Step 3:

[0576] The server queries the database based on the identified emotional state. It retrieves the most relevant information from the database corresponding to the user's emotional state (e.g., fatigue, stress, joy). This process also takes into account the user's past behavioral patterns and preferences. The output is a list of information to be presented to the user.

[0577] Step 4:

[0578] Based on the acquired information, the server uses a generative AI model (e.g., OpenAI's GPT series) to generate output in a manner appropriate to the user's emotional state. The generated output consists of text or audio that includes a tone and manner of speaking that takes the user's emotions into consideration.

[0579] Step 5:

[0580] Finally, the server sends the generated output to the terminal. The terminal then presents the received information to the user. This information is displayed as text on the smartphone's screen or played back as audio. This allows the user to receive information that is relevant to their own emotional state.

[0581] 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.

[0582] 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.

[0583] 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.

[0584] [Fourth Embodiment]

[0585] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0586] 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.

[0587] 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).

[0588] 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.

[0589] 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.

[0590] 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).

[0591] 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.

[0592] 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.

[0593] 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.

[0594] 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.

[0595] 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.

[0596] 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.

[0597] 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".

[0598] The system of this invention efficiently acquires information that residents and visitors need within a city, thereby supporting a comfortable urban life. Based on user input, the system uses natural language processing technology to analyze the data and retrieves and presents relevant information from a database.

[0599] Users can send questions to the device via voice or text input. For example, if a user asks, "Where are the nearby restaurants?", the device formats the question into text and sends it to the server. The server then uses natural language processing technology to analyze this text and determine the user's intent.

[0600] Based on the analysis results, the server generates queries to retrieve relevant information from the database. These queries target relevant information such as restaurant location, opening hours, and ratings. The retrieved information is then reorganized into a personalized format, taking into account the user's past behavior patterns and preferences.

[0601] For example, the server can prioritize displaying restaurant information best suited to the user based on the types of restaurants the user has previously searched for and their visit history. Ultimately, the information provided to the user can be in text format as well as audio format, and the device will present the information in the most appropriate way depending on the situation.

[0602] Furthermore, the system integrates with external data sources, updating information in real time. This ensures that users are always provided with the latest information. This feature is particularly useful for responding to sudden changes in event information or emergencies.

[0603] In this way, the present invention can provide users with the information they need in a rapid and personalized manner, significantly improving the quality of life in smart cities.

[0604] The following describes the processing flow.

[0605] Step 1:

[0606] Users input questions or requests into the device via voice or text. For example, they might type, "Tell me about nearby restaurants."

[0607] Step 2:

[0608] The device converts voice input into text, organizes the text data, and sends it to the server. Speech recognition technology is used to format the user's words into text.

[0609] Step 3:

[0610] The server analyzes the received text data using natural language processing techniques to recognize the user's intent. This analysis involves intent classification and entity extraction. For example, it might identify the category "restaurant."

[0611] Step 4:

[0612] The server generates queries to query the database based on the analysis results. These queries include conditions for searching for information related to the identified entities and intentions.

[0613] Step 5:

[0614] The server executes the generated query and retrieves the relevant information from the database, such as a list of nearby restaurants.

[0615] Step 6:

[0616] The server reformats the retrieved information into a user-friendly format. If necessary, it personalizes the information by considering the user's past behavior patterns.

[0617] Step 7:

[0618] The server sends formatted information to the terminal. The information is in a format that can be handled in either text or audio format.

[0619] Step 8:

[0620] The device presents the received information to the user. Depending on the user's preferences, it may display the information on the screen or provide an audio response.

[0621] Step 9:

[0622] Based on the information presented, users can decide on their next action and, if necessary, ask additional questions or provide feedback to the device.

[0623] (Example 1)

[0624] 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".

[0625] In modern urban life, it is crucial to quickly and individually obtain the information that residents and visitors need. However, conventional information acquisition systems have struggled to accurately analyze user intent and provide personalized information that takes past behavioral patterns into account. Furthermore, real-time information updates have been insufficient, making it impossible to always provide the latest information. In addition, the convenience of information acquisition using voice input has not been adequate.

[0626] 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.

[0627] In this invention, the server includes means for analyzing data obtained from the user using natural language processing technology to identify the user's intent, means for obtaining relevant information from a data storage device based on the identified intent, and means for structuring and presenting the obtained information in a way that is suitable for the user. This enables the user to quickly obtain personalized information that takes into account past behavioral patterns and preferences. Furthermore, by converting voice input into text data and presenting information in both voice and text formats, user convenience can be improved. In addition, by synchronizing with external information sources in real time, the latest information can always be provided to support rapid decision-making.

[0628] "Natural language processing technology" is a technology that enables computers to understand, interpret, and generate human language, and to analyze data obtained from users to identify their intentions.

[0629] A "data storage device" is a device or system that stores information and keeps it accessible as needed, and is used to retrieve relevant information based on the user's intent.

[0630] "Past behavioral patterns" refer to the history of choices and actions a user has made in the past, and this data is used to personalize information.

[0631] An "external information source" refers to a source of data or information that exists outside the system, and is the destination to which the system connects in order to enable real-time information updates.

[0632] "Personalization" refers to the process of adjusting and presenting acquired information in a way that is optimal for the user, based on the user's past behavioral patterns and preferences.

[0633] "Voice input" refers to a method of sending data to a system using the voice spoken by the user, and includes the technology to convert this voice into text data.

[0634] "Real-time updates" refers to a function that synchronizes with external information sources to keep information up-to-date and reflects changes immediately.

[0635] This system begins with the user querying the device for information via voice or text. For example, the user might ask, "Where's the nearest cafe?" If the input is voice, the device converts it to text using speech recognition software. For speech recognition, common speech recognition technologies are used, and Google Cloud Speech-to-Text API or other solutions available on the market can be utilized.

[0636] The terminal then sends the converted text data to the server. The server uses natural language processing (NLP) techniques to analyze the text and identify the user's intent. At this stage, natural language processing libraries such as spaCy or BERT are used.

[0637] Based on the user's intent revealed through analysis, the server generates and executes queries to retrieve the necessary relevant information from the data storage device. These queries target information such as the location, opening hours, and ratings of nearby cafes.

[0638] The information obtained is personalized, taking into account the user's past behavioral patterns. The server uses this profile data to prioritize providing the type of information the user prefers.

[0639] Finally, the device presents the personalized information received from the server to the user in either audio or text format. The information is provided in the most effective way for the user, but this will vary depending on the device's characteristics, the user's environment, and settings.

[0640] For example, if a user speaks into their smartphone and asks, "Which cafes are open now?", the device converts the speech into text, the server analyzes the intent of the text to generate a query, and retrieves cafe information from its data storage. Then, after personalizing that information, it provides voice guidance such as, "There are two cafes open near your current location: Cafe A and Cafe B."

[0641] An example of a prompt to the generative AI model would be: "What nearby French restaurants would the user like to visit? Please provide priority results considering past visit history."

[0642] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0643] Step 1:

[0644] Users query the device for information via voice or text. For example, they might ask, "Where's the nearest cafe?" This input is received by the device. In the case of voice input, the device first uses speech recognition technology to convert the voice into text data. As a result, the voice input is output as text data.

[0645] Step 2:

[0646] The terminal sends the converted text data to the server. The server receives this text data as input and performs analysis using natural language processing. Specifically, BERT and spaCy can be used as natural language processing technologies. Through this analysis, the user's intent is identified, and the result is output.

[0647] Step 3:

[0648] The server generates a query to access data storage based on the identified user's intent. This query might retrieve information such as the location, opening hours, and reviews of nearby cafes. The server executes this query against the data storage and retrieves the relevant data. As a result, information matching the user's intent is retrieved and output.

[0649] Step 4:

[0650] The acquired information is personalized by the server, taking into account the user's past behavior patterns and preferences. Specifically, it analyzes data on places the user has visited in the past and their preferences, and selects information to display preferentially. The output of this process is personalized information.

[0651] Step 5:

[0652] The server sends personalized information to the terminal, which then presents it to the user. The terminal outputs the information in either voice or text format, the method of which is selected according to the user's device settings and environment. For example, as voice output, it might announce, "The cafes open near your current location are Cafe A and Cafe B."

[0653] (Application Example 1)

[0654] 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".

[0655] In modern urban life, individuals are required to obtain appropriate and useful information quickly and efficiently. However, the sheer volume of information makes it difficult to provide information tailored to individual needs. Furthermore, if information is not updated in real time, it becomes difficult to cope with constantly changing circumstances. Users need to be able to quickly obtain the information they seek, and that information needs to be personalized and up-to-date.

[0656] 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.

[0657] In this invention, the server includes means for analyzing information obtained from the user using natural language processing technology to identify the user's purpose, means for obtaining relevant information from information sources based on the identified purpose, and means for presenting the information as physical visual information via a user interface using a wearable information display device. This enables the user to obtain the latest and personalized information visually and intuitively through a wearable device.

[0658] "Natural language processing technology" is a technology that analyzes text and audio data obtained from users to enable computers to understand and process human language.

[0659] "Means for identifying user objectives" refers to methods for determining what a user wants based on the analyzed information.

[0660] "Means of obtaining relevant information from information sources" refers to methods for collecting necessary data from information sources such as the internet or local databases, in accordance with user requests.

[0661] A "wearable information display device" is a hardware device that a user can wear to provide visual information.

[0662] "Means of presenting information as visual information via a user interface" refers to methods of visually displaying acquired information in a way that is easy for the user to understand, and of manipulating it through an interface.

[0663] "A means of updating information in real time in conjunction with external information sources" refers to a method of continuously communicating with external information sources to update data in order to always maintain the latest information.

[0664] "Personalized information" refers to information that has been tailored to be optimal for a specific user based on their past behavior and preferences.

[0665] The system implementing this invention enables a user wearing smart glasses to obtain and display necessary information in real time within a city by making questions and requests in natural language. By using smart glasses as a wearable information display device, information is provided to the user visually and intuitively. The terminal and server cooperate and process information in the following manner.

[0666] The server has the capability to convert speech input from users into text using natural language processing technology. Specifically, it uses software such as the Google Cloud Natural Language API to analyze and convert the speech. This text data is then analyzed in detail to identify the user's intent.

[0667] Next, the server retrieves relevant information from databases and internet sources based on the identified purpose. By utilizing the Google Maps API, for example, it is possible to obtain location information and real-time event information.

[0668] The server further personalizes the acquired information based on the user's past behavior history and preferences. At this stage, machine learning algorithms can also be used, so that information relevant to the user is prioritized according to their browsing history and past choices.

[0669] The collected information is presented as visual information through the smart glasses' display via a user interface. This allows users to receive information in real time and in a personalized format as needed. For example, if a user asks, "What live events are I able to go to this evening?", the server analyzes the question and displays relevant event information on the glasses' display in real time.

[0670] An example of a prompt for a generative AI model would be: "The user asked about live events they can attend this evening. Considering their current location, suggest the three closest and highest-rated events."

[0671] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0672] Step 1:

[0673] The device acquires the user's voice input. The user's voice is captured through the smart glasses' microphone. This input voice data is acquired as a digital audio file.

[0674] Step 2:

[0675] The terminal sends the acquired audio data to the server. The terminal transfers the audio data to the server via the network and prepares it for processing. The output here is the server receiving the audio data.

[0676] Step 3:

[0677] The server converts the audio data to text. The Google Cloud Natural Language API is used to convert the audio data to text data. The input to this process is audio data, and the output is text data for analysis.

[0678] Step 4:

[0679] The server analyzes text data to identify the user's intent. It utilizes natural language processing techniques to refine the text and understand the user's questions and requests. The input is text data, and the output is information about the user's intent. Specific operations include keyword extraction and contextual analysis.

[0680] Step 5:

[0681] The server retrieves relevant information based on the user's intent. Using the Google Maps API, it retrieves necessary information, such as nearby event information, from a database. The input is information about the user's intent, and the output is a dataset of relevant information.

[0682] Step 6:

[0683] The server personalizes the information it acquires. Using machine learning algorithms, it optimizes the information by considering the user's past behavior and preferences. The input is a dataset of related information, and the output is a personalized set of information.

[0684] Step 7:

[0685] The device presents personalized information to the user. The information is displayed visually and intuitively through the smart glasses' display. The input is a personalized set of information, and the output is information that the user can visually confirm.

[0686] 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.

[0687] The system of this invention provides more personalized urban information by taking into account the user's emotional state. This system combines natural language processing technology and an emotion engine, dynamically adjusting the content and method of information presentation based on the user's emotion analysis.

[0688] The user inputs information into the device via voice or text. This input data is sent by the device to the emotion engine, which analyzes the tone of voice and linguistic features of the text to recognize the user's emotional state (e.g., joy, anger, sadness, etc.).

[0689] Based on the sentiment analysis results received from the sentiment engine, the server further analyzes the user's intentions using natural language processing technology. This process evaluates how the user's emotional state affects the way and content of information provided. For example, if it is determined that the user is stressed, the server will take measures such as recommending a relaxing place in a calm tone.

[0690] Furthermore, the server generates queries to the database based on the analysis results and retrieves relevant information. In doing so, it takes into account past sentiment data and reactions, prioritizing the retrieval of information most relevant to the user.

[0691] For example, if a user asks, "I'm tired, is there anywhere I can rest?", the server will analyze the emotion engine to determine that the user is feeling tired and adjust its information accordingly, providing details about nearby cafes and parks. This information will include details about relaxing places and how crowded they are.

[0692] Ultimately, the device provides the user with the acquired information in text or audio format. The information is delivered in a tone and content that is sensitive to the user's emotions. This results in a more intuitive and satisfying user experience.

[0693] In this way, the system of the present invention can sense the user's emotions and provide more appropriate and user-friendly information, thereby further improving the quality of life in smart cities.

[0694] The following describes the processing flow.

[0695] Step 1:

[0696] The user enters questions or requests into the device via voice or text. For example, they might type, "I'm tired today."

[0697] Step 2:

[0698] The device converts input data into text using speech recognition technology and sends it to the emotion engine. Here, tones are extracted from the speech, and keywords are extracted from the text.

[0699] Step 3:

[0700] The server uses an emotion engine to analyze the user's input data and estimate the user's emotional state. For example, if the user uses a word indicating fatigue, the server will determine the emotional state to be "tired."

[0701] Step 4:

[0702] The server then uses natural language processing techniques to analyze the user's intent. It takes the user's emotional state into consideration and prepares to determine what information is most appropriate.

[0703] Step 5:

[0704] The server generates queries to the database based on the analysis results and retrieves relevant information. For example, it might search for nearby cafes or parks for a user who is feeling tired.

[0705] Step 6:

[0706] The server formats the information retrieved from the database, taking into account the user's emotional state. When listing appropriate options, it prioritizes elements such as a "relaxing space" and a "calm atmosphere."

[0707] Step 7:

[0708] The server sends the formatted information to the terminal. The information is prepared in a format that is easy for the user to receive (text or audio).

[0709] Step 8:

[0710] The device displays the acquired information to the user. For example, it might say in a calm voice, "There's a quiet and relaxing cafe nearby."

[0711] Step 9:

[0712] Users use the presented information to make decisions about their actions. They can also ask additional questions or provide feedback if necessary.

[0713] (Example 2)

[0714] 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".

[0715] In modern information delivery systems, there is a problem in that information suggestions to users are uniform or non-individualized, and do not adequately consider users' feelings and emotional needs. As a result, the user experience is not sufficiently satisfying, and efficient information acquisition becomes difficult.

[0716] 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.

[0717] In this invention, the server includes means for identifying the user's intentions and emotional state, means for acquiring relevant information from information resources based on the identified intentions and emotions and adjusting the content and method of information provision, and means for formatting and presenting the acquired information in a manner that takes into account the user's emotional state. This enables the provision of appropriate and personalized information that responds to the user's emotions.

[0718] "Natural language data" refers to information composed of language that humans use on a daily basis, and is data that is input as audio or text.

[0719] "User intent" refers to the specific requests and desires that users have for an information system, and is revealed by analyzing the input natural language data.

[0720] "Emotional state" refers to the emotional reactions and feelings a user exhibits when entering information, and includes states such as "joy," "anger," and "sadness."

[0721] "Information resources" refer to databases and external information sources accessed to obtain the information to be provided, and are capable of efficiently collecting the necessary information.

[0722] "Formatting" refers to the process or method of organizing acquired information into a specific format, transforming it into a visually appealing and easily understandable form.

[0723] "External information sources" refer to additional information sources that are not stored within the system but are accessible via the internet or other means, and are intended to update information in real time.

[0724] This system analyzes the user's emotional state in real time and provides personalized information tailored to their specific needs. Natural language processing technology and an emotion analysis engine play a crucial role in the system's implementation.

[0725] The user inputs natural language data via a device. This input can be in the form of speech or text, and the device sends it to an emotion analysis engine. This engine uses speech recognition software and natural language processing tools to analyze the tone of the speech and the linguistic features of the text to identify the user's emotional state.

[0726] The server generates queries against information resources based on the results obtained from the sentiment analysis engine. This uses natural language processing techniques to search for and retrieve information that is relevant to the user's intent and emotions. The retrieved information is formatted in a way that is sensitive to the user's emotions and presented through the terminal.

[0727] For example, if a user asks, "I'm tired, is there anywhere I can rest?", the sentiment analysis engine will determine that the user is feeling tired. Based on this analysis, the server will search for information on nearby cafes, parks, and other places where the user can relax and provide this information to the user. This information will also include additional data such as crowd levels.

[0728] This system enhances the user experience by providing appropriate information tailored to their emotions. Furthermore, by integrating with external information sources in real time, it can always provide the most up-to-date information.

[0729] An example of a prompt for a generative AI model might be, "When a user is feeling relaxed, how should you provide them with city information that meets their needs?" Through this prompt, the model is expected to learn how to provide information based on emotions.

[0730] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0731] Step 1:

[0732] The user inputs information into the device via voice or text. The input natural language data is sent to the sentiment analysis engine. In this process, data is acquired using the device's microphone and keyboard, and if it is voice data, it is converted into text data through speech recognition.

[0733] Step 2:

[0734] The device sends input data to an emotion analysis engine. The emotion analysis engine analyzes the tone of voice and the linguistic features of the text to identify the user's emotional state. Here, speech recognition software and natural language processing techniques are used to extract the emotional data and map it to specific emotion labels such as joy and anger.

[0735] Step 3:

[0736] The server clarifies the user's intentions based on the results from the sentiment analysis engine. The server uses natural language processing techniques to determine how emotional states influence information delivery. As a result, it analyzes in detail what the user wants and clarifies their intentions.

[0737] Step 4:

[0738] The server generates queries to information resources based on the analyzed intent and emotional state, and retrieves relevant information. This process involves making appropriate queries to the database and prioritizing the retrieval of information relevant to the user's situation. By also considering past user data, optimal information provision becomes possible.

[0739] Step 5:

[0740] The server formats the acquired information with consideration for the user's emotions and sends it to the terminal. The terminal presents the acquired information to the user in either audio or text. The output information is presented in a way that is adjusted according to the user's emotional state, optimizing the user experience. This process utilizes speech synthesis and display technologies.

[0741] (Application Example 2)

[0742] 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".

[0743] In modern society, people living in cities need a diverse range of information. However, the information provided often fails to take into account the individual user's feelings and circumstances, resulting in inadequate information delivery. In particular, the lack of information tailored to the user's mental state is a significant challenge, leading to decreased user satisfaction.

[0744] 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.

[0745] In this invention, the server includes means for analyzing text data obtained from the user using natural language processing technology to identify the user's emotional state, means for obtaining relevant information from a database based on the identified emotional state, and means for formatting and presenting the obtained information in a tone and style corresponding to the user's emotions. This enables the provision of personalized information according to the user's emotional state.

[0746] "Natural language processing technology" is a technology that analyzes voice and text data obtained from users to mechanically understand their intentions and emotions.

[0747] "Text data" refers to information expressed in characters, which is analyzed using natural language processing techniques.

[0748] "Emotional state" refers to the user's emotional response and mental state, and serves as the basis for adjusting the content of the information provided accordingly.

[0749] A "database" is an electronic recording device that systematically stores and retrieves related information, and is used to obtain information as needed.

[0750] "Format" refers to a method or form for arranging information in an appropriate and easy-to-understand way and presenting it to the user.

[0751] "Tone of voice" refers to the vocal or expressive characteristics used when conveying information, and is adjusted according to the user's emotional state.

[0752] "Real-time" is a term that indicates that processing or reactions are performed immediately within the current time frame.

[0753] One embodiment of this invention is a system that provides personalized information according to the user's emotional state. The system mainly consists of a user terminal, a server, and a database.

[0754] The user's device is a device that accepts voice or text input and sends the input information to a server for sentiment analysis. In this process, the device uses speech recognition software (e.g., Speech-to-Text API) to convert speech to text.

[0755] The server receives user input data and analyzes the text data using natural language processing technology (e.g., IBM Watson Natural Language Understanding). The purpose of the analysis is to identify not only the user's intent but also their emotional state. Based on the identified emotional state, the server communicates with a database to retrieve the most relevant information for the user.

[0756] Based on the acquired information, the server generates output in a format appropriate to the emotional state. This output is provided with a tone and style that takes the user's emotions into consideration, utilizing a generative AI model (e.g., OpenAI's GPT series). The server then sends this to the terminal and presents it to the user.

[0757] For example, if a user types "I'm tired, where can I relax?" into their device, the server analyzes this input to determine that the user is feeling tired. It then retrieves information about quiet, easily accessible cafes and parks from its database and presents this information to the user in a calming tone.

[0758] An example of a prompt to input into the generating AI model would be, "Based on the user's current emotional state (fatigue), please recommend a quiet and relaxing cafe." Through this prompt, it becomes easy to provide information that is tailored to the user's emotions.

[0759] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0760] Step 1:

[0761] The user's device accepts input in voice or text format. When the user enters a question or request and sends it, the device uses speech recognition software (e.g., Speech-to-Text API) to convert the voice data into text. The converted text data is retrieved and sent to the server.

[0762] Step 2:

[0763] The server receives text data sent from the terminal. The received data is analyzed using natural language processing technology (e.g., IBM Watson Natural Language Understanding). Through this analysis, the server identifies the user's intent and emotional state from the text data. The emotional state obtained through the analysis is output as base data for use in the next step.

[0764] Step 3:

[0765] The server queries the database based on the identified emotional state. It retrieves the most relevant information from the database corresponding to the user's emotional state (e.g., fatigue, stress, joy). This process also takes into account the user's past behavioral patterns and preferences. The output is a list of information to be presented to the user.

[0766] Step 4:

[0767] Based on the acquired information, the server uses a generative AI model (e.g., OpenAI's GPT series) to generate output in a manner appropriate to the user's emotional state. The generated output consists of text or audio that includes a tone and manner of speaking that takes the user's emotions into consideration.

[0768] Step 5:

[0769] Finally, the server sends the generated output to the terminal. The terminal then presents the received information to the user. This information is displayed as text on the smartphone's screen or played back as audio. This allows the user to receive information that is relevant to their own emotional state.

[0770] 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.

[0771] 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.

[0772] 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.

[0773] 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.

[0774] 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.

[0775] 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.

[0776] 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.

[0777] 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.

[0778] 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."

[0779] 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.

[0780] 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.

[0781] 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.

[0782] 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.

[0783] 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.

[0784] 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.

[0785] 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.

[0786] 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.

[0787] 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.

[0788] 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.

[0789] 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.

[0790] 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.

[0791] The following is further disclosed regarding the embodiments described above.

[0792] (Claim 1)

[0793] A means of analyzing text data obtained from users using natural language processing technology to identify the user's intent,

[0794] Means for retrieving relevant information from a database based on identified intent,

[0795] A means of formatting and presenting acquired information in a way suitable for the user,

[0796] A means of personalizing information by taking into account the user's past behavior patterns and preferences,

[0797] A means of updating information in real time by linking with external data sources,

[0798] A system that includes this.

[0799] (Claim 2)

[0800] The system according to claim 1, further comprising means for converting voice input from a user into text using natural language processing technology.

[0801] (Claim 3)

[0802] The system according to claim 1, further comprising means for presenting acquired information to the user in either audio or text format.

[0803] "Example 1"

[0804] (Claim 1)

[0805] A means of analyzing data obtained from users using natural language processing technology to identify the user's intent,

[0806] Means for obtaining relevant information from a data storage device based on an identified intent,

[0807] A means of structuring and presenting acquired information in a way that is suitable for the user,

[0808] A means of personalizing information by taking into account the user's past behavioral patterns and preferences,

[0809] A means of synchronizing with external information sources in real time and updating information,

[0810] A means of converting voice input into text data,

[0811] A means of presenting acquired information to the user in either audio or text format,

[0812] A system that includes this.

[0813] (Claim 2)

[0814] The system according to claim 1, further comprising means for querying a terminal for information using voice input.

[0815] (Claim 3)

[0816] The system according to claim 1, further comprising means for determining the priority of information based on the user's past search history.

[0817] "Application Example 1"

[0818] (Claim 1)

[0819] A means of analyzing information obtained from users using natural language processing technology to identify the user's purpose,

[0820] Means for obtaining relevant information from sources based on a specified purpose,

[0821] A means of presenting acquired information in a format suitable for the user,

[0822] A means of personalizing information by considering the user's past behavioral characteristics and preferences,

[0823] A means of updating information in real time in conjunction with external information sources,

[0824] A means of presenting information as physical visual information via a user interface using a wearable information display device,

[0825] A system that includes this.

[0826] (Claim 2)

[0827] The system according to claim 1, further comprising means for converting voice input from a user into text using natural language processing technology.

[0828] (Claim 3)

[0829] The system according to claim 1, further comprising means for presenting acquired information to the user in the form of audio and text.

[0830] "Example 2 of combining an emotion engine"

[0831] (Claim 1)

[0832] A means for analyzing natural language data obtained from users to identify the user's intentions and emotional state,

[0833] Means for obtaining relevant information from information resources based on identified intentions and emotions, and for adjusting the content and method of information provision,

[0834] A means of formatting and presenting acquired information in a way that takes into account the user's emotional state,

[0835] A means of personalizing information by taking into account the user's past emotional data and reactions,

[0836] A means of instantly linking with external information sources and updating information,

[0837] A system that includes this.

[0838] (Claim 2)

[0839] The system according to claim 1, further comprising means for converting acoustic input from a user into textual information and recognizing the user's emotional state using natural language processing technology.

[0840] (Claim 3)

[0841] The system according to claim 1, further comprising means for presenting acquired information to the user in both audio and text format, and for conveying it in a manner and tone that corresponds to the user's emotions.

[0842] "Application example 2 when combining with an emotional engine"

[0843] (Claim 1)

[0844] A method for analyzing text data obtained from users using natural language processing technology to identify the user's emotional state,

[0845] A means of obtaining relevant information from a database based on an identified emotional state,

[0846] A means of formatting and presenting acquired information in a tone and style that corresponds to the user's emotions,

[0847] A means of personalizing information by taking into account the user's past emotional data and preferences,

[0848] A means of updating information in real time by linking with external data sources,

[0849] A system that includes this.

[0850] (Claim 2)

[0851] The system according to claim 1, further comprising means for analyzing the user's emotions from voice input using natural language processing technology.

[0852] (Claim 3)

[0853] The system according to claim 1, further comprising means for presenting acquired information in both audio and text that correspond to the user's emotions. [Explanation of symbols]

[0854] 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 of analyzing text data obtained from users using natural language processing technology to identify the user's intent, Means for retrieving relevant information from a database based on identified intent, A means of formatting and presenting acquired information in a way suitable for the user, A means of personalizing information by taking into account the user's past behavior patterns and preferences, A means of updating information in real time by linking with external data sources, A system that includes this.

2. The system according to claim 1, further comprising means for converting voice input from a user into text using natural language processing technology.

3. The system according to claim 1, further comprising means for presenting acquired information to the user in either audio or text format.

Images