system

Abstract

Provide a system. An interface means for a user to input a question; a means for the server to receive a question sent by the user; means for parsing the question using a natural language processing engine; means for generating an answer based on the question using a trained artificial intelligence model; means for transmitting the generated answer to the user's terminal; A system including:

Description

[Technical Field]

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

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

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

[0004] The present invention aims to solve the problem of the difficulty that foreigners in Japan have in efficiently obtaining information regarding their residence status in Japan. Specifically, when foreigners in Japan access information regarding the renewal or acquisition of residence status, they face the problem that the legal system is complex and difficult to understand, and the immigration bureau counters are always busy, making it difficult for them to receive adequate assistance. This results in the problem that users cannot quickly and accurately obtain the information they need. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides the following means: a system including an interface means for a user to input a question; a server means for receiving the question sent from the user; a means for analyzing the question using a natural language processing engine; a means for generating an answer based on the question using a trained artificial intelligence model; and a means for transmitting the generated answer to the user's terminal. The natural language processing engine performs processes including tokenization, part-of-speech tagging, and dependency structure analysis, thereby accurately analyzing the meaning of the question. Furthermore, the trained artificial intelligence model accesses a database containing legal systems and procedures related to immigration status, thereby providing an appropriate answer to the user's question. This allows the user to efficiently obtain the information they need.

[0006] "User" refers to a person who accesses the system and enters a question.

[0007] The term "interface means" refers to a mechanism including an input means for a user to input a question and a transmission means.

[0008] "Server" refers to a computer system that receives questions sent by users, analyzes them, and generates answers.

[0009] "Natural language processing engine" refers to algorithms and programs, including tokenization, part-of-speech tagging, and dependency structure analysis, for parsing questions.

[0010] "Tokenization" refers to the process of dividing input text into units of words or phrases.

[0011] "Part-of-speech tagging" refers to the process of assigning the part of speech (noun, verb, adjective, etc.) to each word or phrase in a text.

[0012] "Dependency structure analysis" refers to the process of analyzing the dependencies between words in a sentence.

[0013] An "artificial intelligence model" refers to a machine learning model that generates appropriate output for input based on training data.

[0014] "Database" refers to a collection of information that stores data on legal systems and procedures related to immigration status.

[0015] "Answer generation means" refers to a mechanism that includes a process for creating an appropriate answer based on a user's question.

[0016] "Terminal" refers to the device (smartphone, PC, tablet, etc.) through which a user accesses the system and receives responses.

[0017] "Question analysis" refers to the process of converting a question entered by a user into an easy-to-understand form using a natural language processing engine.

[0018] "Answer sending means" refers to a mechanism for sending the generated answer to the user's terminal. [Brief explanation of the drawings]

[0019] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0020] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0021] First, the terms used in the following description will be explained.

[0022] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0023] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0024] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0025] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0026] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0030] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0031] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0032] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0033] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0034] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0037] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0038] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0039] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0040] This invention is a system for foreigners in Japan to efficiently obtain information regarding their residence status in Japan. This system is implemented by having a user input a question, a server analyze the question, generate an appropriate answer, and return it to the user.

[0041] System configuration

[0042] The system includes the following major components:

[0043] 1. User device: A device on which a user enters questions and checks answers. This includes smartphones, PCs, tablets, etc.

[0044] 2. Server: The central part of the system, which receives questions, analyzes them, generates answers, and sends them.

[0045] 3. Interface means: Provides a GUI (graphical user interface) and text boxes for users to enter questions.

[0046] 4. Natural language processing engine: Runs on the server and analyzes questions sent by users, performing processes such as tokenization, part-of-speech tagging, and dependency structure analysis.

[0047] 5. Trained AI model: This model is created using historical data and specific training to generate appropriate answers based on the question.

[0048] 6. Database: Data on immigration-related legal systems and procedures is stored. Access to this database allows the model to provide accurate information.

[0049] System Operation

[0050] First, a user accesses the system using a terminal and inputs a question using the interface means, for example, "How do I extend my visa?"

[0051] The server then receives the user-submitted question, which is then analyzed by a natural language processing engine, including tokenization, part-of-speech tagging, and dependency structure analysis.

[0052] Once the analysis is complete, the server uses a trained artificial intelligence model to generate an answer based on the user's question, which then uses the analysis results to pull the necessary information from a database to create the appropriate answer.

[0053] Finally, the server sends the generated answer to the user's device, where the user can confirm the answer displayed on the device and obtain the necessary procedures or information.

[0054] Specific examples

[0055] Example 1: When a user enters "How do I extend my visa?"

[0056] 1. The user enters a question into the terminal and presses the send button.

[0057] 2. The server receives the question and analyzes it using a natural language processing engine.

[0058] 3. The server uses a trained artificial intelligence model to retrieve the necessary documents and procedures for visa extension from the database.

[0059] 4. The server generates a response saying, "To extend your visa, you need to prepare application documents and submit them to the Immigration Bureau. For detailed procedures, please refer to the official website of the Immigration Bureau."

[0060] 5. The server sends the generated response to the user's device.

[0061] 6. The user checks the answers on the device and understands the necessary procedures.

[0062] In this way, the present invention is designed to enable foreigners in Japan to efficiently obtain information regarding the complicated procedures for obtaining residence status.

[0063] The processing flow will be explained below.

[0064] Step 1:

[0065] A user accesses the system using a terminal. The user opens a dedicated application or website.

[0066] Step 2:

[0067] The user uses the interface means to input a question, for example, "How do I extend my visa?" into the text box.

[0068] Step 3:

[0069] The user presses the send button to send the entered question to the server.

[0070] Step 4:

[0071] The server receives questions sent by users and saves them in text format.

[0072] Step 5:

[0073] The server uses a natural language processing engine to parse the received question, which includes tokenization, part-of-speech tagging, and dependency structure analysis.

[0074] Step 6:

[0075] The server uses a trained artificial intelligence model to generate appropriate answers to questions based on the analysis, which pulls the necessary information from a database.

[0076] Step 7:

[0077] The server uses a response sending means to send the generated response back to the user.

[0078] Step 8:

[0079] The user's terminal receives the response sent from the server and displays the received response on the screen.

[0080] Step 9:

[0081] The user checks the answers displayed on the device screen and understands the appropriate procedures and information.

[0082] These are the processing steps for the entire system.

[0083] Example 1

[0084] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0085] Foreigners living in Japan face the challenge of efficiently obtaining information about their residence status. In particular, there are limited ways to quickly obtain accurate information about the complex legal system and procedures, which can easily lead to misunderstandings and delays in procedures.

[0086] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0087] In this invention, the server includes an interface means for a user to input a question, a means for the server to receive the question sent from the user, a means for analyzing the question using a natural language processing engine, a means for generating an answer based on the question using a trained artificial intelligence model, a means for transmitting the generated answer to the user's terminal, and a means for the user to confirm the generated answer, thereby enabling the user to efficiently and accurately obtain information regarding residence status.

[0088] "User" refers to a person who uses the system to enter questions and receive answers.

[0089] "Interface means" refers to means that provides a graphical user interface and text boxes for a user to enter a question.

[0090] "Server" refers to a central computer system that receives questions from users, analyzes and generates answers, and sends the answers to users.

[0091] A "natural language processing engine" is software that analyzes questions submitted by users, performing functions such as tokenization, part-of-speech tagging, and dependency structure analysis.

[0092] "Tokenization" refers to the process of breaking down text into basic units such as words and phrases.

[0093] "Part-of-speech tagging" refers to the process of assigning each token its part of speech (noun, verb, adjective, etc.).

[0094] "Dependency analysis" refers to the process of analyzing the grammatical relationships between words in a sentence.

[0095] An "artificial intelligence model" refers to a model that learns from past data and specific training and generates appropriate answers to user questions.

[0096] "Answer generation means" refers to a means for generating answers based on a user's question using a trained artificial intelligence model.

[0097] "Database" refers to a data resource that stores data on immigration-related legal systems and procedures.

[0098] The "answer sending means" refers to a means for sending the generated answer to the user's terminal.

[0099] A "user's terminal" is a device on which a user inputs questions and checks answers, and includes smartphones, PCs, tablets, etc.

[0100] The present invention is a system that allows foreign residents in Japan to efficiently obtain information regarding their residence status in Japan. This system is implemented by having a user input a question, a server analyze the question, generate an appropriate answer, and return it to the user. How this system is implemented will be described in detail below.

[0101] System configuration

[0102] 1. User Device:

[0103] A user terminal is a device that allows a user to enter questions and check answers, and includes smartphones, PCs, tablets, etc.

[0104] Specific examples include smartphones (e.g., iPhone (registered trademark), Samsung Galaxy), PCs (e.g., Dell XPS, MacBook Pro), and tablets (e.g., iPad (registered trademark), MICROSOFT (registered trademark) SURFACE (registered trademark)).

[0105] 2. Server:

[0106] The server is the center of the system, receiving questions, analyzing them, generating answers, and sending them out.

[0107] The server may use a cloud-based system (e.g., Amazon Web Services, Google® Cloud Platform).

[0108] 3. Interface means:

[0109] The interface means provides a GUI (Graphical User Interface) and a text box for the user to input a question.

[0110] For example, this includes forms and chatbot interfaces that run on a web browser.

[0111] 4. Natural Language Processing Engine:

[0112] The natural language processing engine runs on the server and analyzes questions submitted by users. The main processes include tokenization, part-of-speech tagging, and dependency structure analysis.

[0113] The software used includes natural language processing libraries such as NLTK and SpaCy.

[0114] 5. Trained artificial intelligence models:

[0115] The model is built using historical data and specific training to generate appropriate answers based on the question.

[0116] As specific examples, models such as GPT-3 (registered trademark) and BERT are used.

[0117] 6. Database:

[0118] The database stores data on legal systems and procedures related to immigration status.

[0119] The databases used include relational database management systems (RDBMS) such as MySQL (registered trademark) and PostgreSQL.

[0120] System operation example

[0121] For example, if a user types "How do I extend my visa?" the process is as follows:

[0122] 1. Users enter their questions using their smartphones, PCs, or tablets.

[0123] 2. The server receives the question and parses it using a natural language processing engine, which splits the question into tokens, tags it with parts of speech, and analyzes grammatical dependencies.

[0124] 3. The trained AI model retrieves the necessary information from the database based on the analysis results and generates an appropriate answer.

[0125] 4. The server generates a response and sends it to the user's device.

[0126] 5. The user checks the answers on the device and understands the necessary procedures.

[0127] In this way, the present invention is designed to enable foreign residents to efficiently obtain information regarding the complicated procedures for obtaining residence status, allowing users to quickly and accurately obtain the information they need.

[0128] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0129] Step 1:

[0130] The server receives the user's question through the interface means. The user accesses the interface using a terminal, inputs the question "How do I extend my visa?", and presses the send button. This input data is sent to the server by the interface means. The server receives this data and passes it on to the next processing step.

[0131] Step 2:

[0132] The server passes the question to the natural language processing engine for analysis. The input question is divided into tokens such as "visa," "extension," "how," "teach," and "please." Next, each token is tagged with a part of speech, and finally, grammatical dependencies are analyzed. This generates an analysis result, which is passed to the next step.

[0133] Step 3:

[0134] The server passes the analysis results to a trained AI model, which generates an answer based on the question. The analysis results, which are input data, are processed to generate a specific answer. Specifically, the analysis results act as a trigger, and the AI ​​model (e.g., GPT-3) generates an answer such as, "To apply for a visa extension, you must prepare application documents and submit them to the Immigration Bureau." This generated answer is passed to the next step.

[0135] Step 4:

[0136] The server sends the generated answer to the user's terminal. The answer, which is output data from the trained artificial intelligence model, is sent to the user's terminal as an HTTP response. The server converts the answer data into an appropriate format and sends it to the user's terminal via a transmission means.

[0137] Step 5:

[0138] The user checks the answer on their device. The user's device displays the received answer data, and the user checks it. Specifically, the answer is displayed on a web browser or application, and the user receives information such as, "To apply for a visa extension, you will need to prepare application documents and submit them to the Immigration Bureau."

[0139] This series of processing steps enables the user to efficiently and accurately obtain information regarding residence status.

[0140] (Application example 1)

[0141] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0142] Currently, it is difficult for foreigners living in Japan to efficiently obtain information regarding their Japanese residence status. Furthermore, there is no system that can respond to questions in real time when using autonomous vehicles. Furthermore, there is no established method for improving convenience using voice input and output. A new system is needed to solve these issues.

[0143] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0144] In this invention, the server includes an interface means for a user to input a question or command, a means for the server to receive the question or command sent from the user, a means for analyzing the question or command using a natural language processing engine, a means for generating a response based on the question or command using a trained artificial intelligence model, a means for transmitting the generated response to a display device in the user's terminal or in the vehicle, and a voice generation means for providing the generated response to the user through a voice output device. This enables foreigners residing in Japan to efficiently obtain information on their status of residence in real time even while riding in an autonomous vehicle.

[0145] An "interface means" is a device or software through which a user inputs questions or commands.

[0146] A "server" is a central processing unit that receives questions or commands sent by users, analyzes them, and generates responses.

[0147] A "natural language processing engine" is software that analyzes questions and commands from users and understands their intentions.

[0148] A "trained artificial intelligence model" is an algorithm that learns from large amounts of data to generate appropriate responses based on questions or commands.

[0149] A "user's terminal" is a device used by a user, such as a smartphone, tablet, or PC.

[0150] A "display device" is a screen device for visually displaying the generated responses.

[0151] A "voice generating means" is a device and software for providing the generated response to the user as voice.

[0152] "Database" means a system for storing information on legal systems and procedures related to immigration status.

[0153] This invention is a system that allows a user to input questions or commands related to Japanese residence status and obtain answers in real time within an autonomous vehicle. The system includes a server, a user terminal, a natural language processing engine, a trained artificial intelligence model, a display device, a voice generation means, and a database.

[0154] System configuration

[0155] 1. User Interface Means:

[0156] Users input questions using devices such as smartphones, tablets, and in-car displays.

[0157] Specifically, voice input can be used, for example, by using prompt sentences such as "Please tell me how to extend my visa."

[0158] 2. Server:

[0159] Use a cloud-based server, such as Amazon Web Services (AWS®) or Microsoft Azure®.

[0160] The server receives questions or commands from users and uses a natural language processing engine and generative AI models to analyze and generate answers.

[0161] 3. Natural Language Processing Engine:

[0162] The natural language processing engine uses Google Cloud Natural Language API and IBM Watson(registered trademark) Natural Language Understanding.

[0163] The system processes user questions through tokenization, part-of-speech tagging, dependency structure analysis, and other processes to accurately analyze their intent.

[0164] 4. Trained artificial intelligence model:

[0165] AI models such as OpenAI's (registered trademark) GPT-4 (registered trademark) can be used.

[0166] Based on the analyzed questions, the necessary information is extracted from a database related to residence status and an appropriate answer is generated.

[0167] 5. Display devices and sound generating means:

[0168] The display device uses the screen on the user's terminal or in the car.

[0169] Voice generation uses the gTTS (Google Text-to-Speech) library and the voice output device installed in the vehicle.

[0170] The generated answers are converted into audio files and provided to the user.

[0171] 6. Database:

[0172] A database will be used to store information on immigration-related legal systems and procedures.

[0173] For example, this includes data provided by the Japanese Immigration Bureau and the Ministry of Justice.

[0174] Specific examples

[0175] Specifically, when a user uses the in-car display or voice input to type "How do I extend my visa?", the following happens:

[0176] 1. The user types or speaks a question using the in-car interface.

[0177] 2. The question is sent to the server and analyzed by a natural language processing engine.

[0178] 3. Based on the parsed question, a trained artificial intelligence model generates a response.

[0179] 4. The response is displayed on the user's terminal or on a display device in the vehicle.

[0180] 5. At the same time, the voice generating means converts the response into a voice file and provides it to the user audibly.

[0181] This system will enable foreigners in Japan to receive real-time answers to questions about their residence status while riding in an autonomous vehicle, and voice input and output functions will greatly improve convenience.

[0182] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0183] Step 1:

[0184] The user uses the in-car interface means to input or speak a question. The user may say a prompt, for example, "How do I extend my visa?" The input here is text or voice data. The output is the question data received by the interface means. The interface uses speech recognition software to convert the user's speech into text.

[0185] Step 2:

[0186] The terminal transmits the user's query data to the server, where the input is the query data received by the interface means and the output is the query data sent to the server. The network module of the terminal is responsible for this transfer.

[0187] Step 3:

[0188] The server receives the question data and analyzes it using a natural language processing engine. The natural language processing engine uses Google Cloud Natural Language API or IBM Watson. The input is the received question data, and the output is the analyzed data. This analysis includes tokenization, part-of-speech tagging, and dependency structure analysis.

[0189] Step 4:

[0190] The server passes the analyzed data to a trained artificial intelligence model to generate an appropriate response. The AI ​​model used here is OpenAI's GPT-4, etc. The input is the analyzed data, and the output is the generated response. The AI ​​model uses the analysis results to extract the necessary information from a database and generate a response.

[0191] Step 5:

[0192] The server sends the generated response to the user's terminal or to a display device in the car. The input is the generated response, and the output is the response displayed on the user's terminal. The communication protocol and interface used here use standard web server technology.

[0193] Step 6:

[0194] The server converts the generated response into an audio file using a speech generator, such as the gTTS (Google Text-to-Speech) library, or the car's audio output device. The input is the text data of the generated response, and the output is an audio file. This audio file is played through the car's speakers.

[0195] Step 7:

[0196] The user can see the response displayed on the terminal or hear the audio response from the car's speakers. This step effectively communicates the information provided to the user in real time. The input is the displayed or played response, and the output is the user's understanding and action.

[0197] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0198] This invention is a system that enables foreigners residing in Japan to efficiently obtain information regarding their Japanese residence status, and it also combines an emotion engine that recognizes the user's emotions and adjusts the quality and format of the answer. This system is realized by having the user input a question, and the server analyzes the question, generates an appropriate answer, and returns it to the user. Another objective is to improve the user experience by recognizing the user's emotions.

[0199] System configuration

[0200] The system includes the following major components:

[0201] 1. User device: A device on which a user enters questions and checks answers. This includes smartphones, PCs, tablets, etc.

[0202] 2. Server: The central part of the system, which receives questions, analyzes them, generates answers, and sends them. It also adjusts the answers based on the results of sentiment analysis by the sentiment engine.

[0203] 3. Interface: Provides a GUI (Graphical User Interface) and text boxes for users to enter questions. This interface incorporates an emotion engine to recognize the user's emotions.

[0204] 4. Natural language processing engine: Runs on the server and analyzes questions sent by users, performing processes such as tokenization, part-of-speech tagging, and dependency structure analysis.

[0205] 5. Trained AI model: This model is created using historical data and specific training to generate appropriate answers based on the question.

[0206] 6. Database: Data on immigration-related legal systems and procedures is stored. Access to this database allows the model to provide accurate information.

[0207] 7. Emotion Engine: An engine for recognizing emotions from user input. It can analyze emotions not only through text input, but also through voice input and facial recognition.

[0208] System Operation

[0209] First, a user accesses the system using a terminal and inputs a question using the interface means. For example, the user inputs, "Please tell me how to extend my visa." At this time, an emotion engine built into the interface means recognizes emotions from the user's text input.

[0210] Next, the server receives the question sent by the user. The received question is analyzed by a natural language processing engine. This analysis includes tokenization, part-of-speech tagging, and dependency structure analysis. At the same time, emotional information analyzed by an emotion engine is also sent to the server.

[0211] Once the analysis is complete, the server uses a trained artificial intelligence model to generate an answer based on the user's question. The model uses the analysis results to pull necessary information from a database to create an appropriate answer. Furthermore, based on the analysis results of the emotion engine, the format and content of the answer can be adjusted depending on the user's emotional state.

[0212] Finally, the server sends the generated answer to the user's device, where the user can confirm the answer displayed on the device and obtain the necessary procedures or information.

[0213] Specific examples

[0214] Example 1: When a user enters "How do I extend my visa?"

[0215] 1. The user enters a question on the device and presses the send button. At this time, the emotion engine recognizes emotions such as "impatience" or "anxiety" from the user's text.

[0216] 2. The server receives the question and analyzes it using the natural language processing engine. At the same time, it also receives the results of the emotion engine.

[0217] 3. The server uses a trained AI model to retrieve the necessary documents and procedures for visa extension from the database. Based on the results of the emotion engine, it adjusts the tone of the message to a calm and reassuring one: "Please stay calm. To extend your visa, you will need to prepare the application documents and submit them to the Immigration Bureau. For detailed procedures, please refer to the Immigration Bureau's official website."

[0218] 4. The server sends the generated response to the user's device.

[0219] 5. The user checks the answers on the device and understands the necessary procedures.

[0220] In this way, the present invention is designed to enable foreigners in Japan to efficiently obtain information on the complicated procedures for obtaining residence status. Furthermore, the emotion engine recognizes the user's emotions and provides information in an appropriate format, improving the user experience.

[0221] The processing flow will be explained below.

[0222] Step 1:

[0223] A user accesses the system using a terminal. The user opens a dedicated application or website.

[0224] Step 2:

[0225] The user uses the interface means to input a question, for example, "How do I extend my visa?" into the text box.

[0226] Step 3:

[0227] The user presses the send button to send the entered question to the server, at which point an emotion engine built into the interface means recognizes emotions from the user's text input.

[0228] Step 4:

[0229] The server receives questions sent by users and saves them in text format.

[0230] Step 5:

[0231] The server parses the received question using a natural language processing engine, which performs tokenization, part-of-speech tagging, and dependency structure analysis.

[0232] Step 6:

[0233] At the same time, the server receives emotion information analyzed by the emotion engine, which determines the user's emotion from the text content and expressions.

[0234] Step 7:

[0235] The server uses a trained artificial intelligence model to generate appropriate answers to questions based on the analysis, which pulls the necessary information from a database.

[0236] Step 8:

[0237] The server uses the emotion information from the emotion engine to adjust the format and content of the response depending on the user's emotional state. For example, if emotions such as "impatience" or "anxiety" are recognized, the response will be modified to a calmer, more reassuring tone.

[0238] Step 9:

[0239] The server then sends the generated answer to the user's device, which includes an expression that corresponds to the user's emotional state.

[0240] Step 10:

[0241] The user's terminal receives the response sent from the server and displays the received response on the screen.

[0242] Step 11:

[0243] The user checks the answers displayed on the device screen and understands the appropriate procedures and information. The answers include expressions that correspond to the user's emotional state, allowing the user to take the next action with greater confidence.

[0244] Examples:

[0245] 1. The user enters a question on the device and presses the send button. At this time, the emotion engine recognizes emotions such as "impatience" or "anxiety" from the user's text.

[0246] 2. The server receives the question and analyzes it using the natural language processing engine. At the same time, it also receives the results of the emotion engine.

[0247] 3. The server uses a trained AI model to retrieve the necessary documents and procedures for visa extension from the database. Based on the results of the emotion engine, it adjusts the tone of the message to a calm and reassuring one: "Please stay calm. To extend your visa, you will need to prepare the application documents and submit them to the Immigration Bureau. For detailed procedures, please refer to the Immigration Bureau's official website."

[0248] 4. The server sends the generated response to the user's device.

[0249] 5. The user checks the answers on the device and understands the necessary procedures.

[0250] Example 2

[0251] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0252] Conventional information acquisition systems made it difficult for foreigners in Japan to efficiently acquire information related to their Japanese residence status, and were also unable to respond in a way that took user feelings into consideration. As a result, the user experience did not improve and user satisfaction was low.

[0253] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an interface means for a user to input a question, a means for the server to receive the question sent from the user, a means for analyzing the question using a natural language processing engine, a means for generating an answer based on the question using a trained artificial intelligence model, a means for transmitting the generated answer to the user's terminal, a means for recognizing and analyzing the user's emotions using an emotion engine, and a means for adjusting the format and content of the answer based on the analysis result of the emotion engine. This not only enables foreigners residing in Japan to efficiently obtain information about their residence status, but also enables answers that take the user's emotions into consideration, improving the user experience.

[0254] A "user" is someone who uses this system to enter questions and receive answers.

[0255] "Terminal" refers to a device on which a user enters questions and checks answers, and specifically includes smartphones, PCs, tablets, etc.

[0256] An "interface means" is a means for providing a graphical user interface and a text box for a user to input a question.

[0257] The "server" is a central computer system that receives questions, analyzes them, generates answers, sends answers, recognizes and analyzes user emotions, and so on.

[0258] A "natural language processing engine" is an engine that analyzes questions sent by users, and performs tokenization, part-of-speech tagging, dependency structure analysis, etc.

[0259] A "trained artificial intelligence model" is an artificial intelligence model that is trained using historical data or specific training data to generate appropriate answers based on questions.

[0260] "Database" refers to a data store that stores data on legal systems and procedures related to immigration status, and which AI models access to extract the necessary information.

[0261] An "emotion engine" is an engine that recognizes and analyzes emotions from user input, and is capable of analyzing emotions not only through text input but also through voice input and facial recognition.

[0262] "Tokenization" is the process by which a natural language processing engine breaks text into basic units such as words and phrases.

[0263] "Part-of-speech tagging" is the process by which a natural language processing engine adds part-of-speech information (noun, verb, adjective, etc.) to each token.

[0264] "Dependency structure analysis" is a process in which a natural language processing engine analyzes the structure of a sentence and identifies the dependencies between words.

[0265] To implement this invention, the following elements are required: a user, a terminal, and a server. This system is realized by having the user input a question, and the server analyze the question, generate an answer, and send it back to the user's terminal. Furthermore, it combines an emotion engine that recognizes the user's emotions and adjusts the quality and format of the answer.

[0266] The devices used by users are smartphones, PCs, tablets, etc., and they access the system through these devices. As an interface, a GUI and text boxes are provided for users to enter questions.

[0267] The server is the central component of the system and performs the following functions:

[0268] 1. Receiving a question: Receives the question data sent by the user.

[0269] 2. Natural Language Processing: A natural language processing engine analyzes the question, including tokenization, part-of-speech tagging, and dependency structure analysis.

[0270] 3. Emotion recognition: The emotion engine recognizes emotions from the user's input and sends the analysis results to the server.

[0271] 4. Answer generation: A trained AI model generates answers based on the analyzed questions. This model accesses a database containing data on immigration-related legal systems and procedures.

[0272] 5. Response Adjustment: Adjust the quality and format of responses based on the sentiment engine analysis results.

[0273] 6. Sending the answer: Send the generated answer to the user's device.

[0274] The specific operation of this system will be explained below as an example.

[0275] Examples:

[0276] If the user types "How do I extend my visa?"

[0277] 1. The user enters a question using a terminal and presses the send button. At this time, the emotion engine recognizes emotions such as "impatience" or "anxiety" from the user's text.

[0278] 2. The server receives the question and begins analyzing it with the natural language processing engine. At the same time, it also receives the results of the emotion engine.

[0279] 3. The server uses a trained AI model to retrieve the necessary information for visa extension from the database. Based on the results of the emotion engine, it adjusts the tone of the message to a calm and reassuring one: "Please stay calm. To apply for a visa extension, you need to prepare the application documents and submit them to the Immigration Bureau. For detailed procedures, please refer to the Immigration Bureau's official website."

[0280] 4. The server sends the generated response to the user's device.

[0281] 5. The user checks the answers on the device and understands the necessary procedures.

[0282] This system not only enables foreigners living in Japan to efficiently obtain information about their residence status, but also uses an emotion engine to respond in a way that takes the user's emotions into consideration.

[0283] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0284] Step 1:

[0285] The user types a question into the terminal.

[0286] A user accesses the system using a terminal. They input a question through the interface means (GUI or text box) on the terminal. For example, the user inputs "How do I extend my visa?" In this step, the user's question text is obtained as input.

[0287] Step 2:

[0288] The emotion engine recognizes the user's emotions.

[0289] The question text entered on the device is immediately sent to the emotion engine. The emotion engine performs text analysis to recognize the user's emotions. In this process, the user's question text is used as input, and emotion data such as "impatience" or "anxiety" is obtained as output. For example, the emotion engine analyzes the emotion of "anxiety" from the user's text.

[0290] Step 3:

[0291] The server receives the query.

[0292] The user's question text is sent to the server along with the emotion data. The server prepares to process the received question text and emotion data. In this step, the question text and emotion data are obtained as input.

[0293] Step 4:

[0294] A natural language processing engine analyzes the question.

[0295] The server's natural language processing engine analyzes the question text. This analysis includes tokenization, part-of-speech tagging, and dependency structure analysis. The analysis results in structured text data. For example, the text is categorized by words such as "visa," "extension," and "method," and the context and dependencies are analyzed.

[0296] Step 5:

[0297] The server receives the analysis results of the emotion engine.

[0298] The server receives the emotion data sent from the emotion engine. The server then prepares a dataset containing the user's emotion information. The emotion data is input, and the emotion information is added to the dataset in the server as output.

[0299] Step 6:

[0300] A trained artificial intelligence model generates the answer.

[0301] The server inputs the analysis results of the natural language processing engine and sentiment data into a trained artificial intelligence model. The model then uses the analysis results of the question to retrieve appropriate information from a database and generate an answer. For example, this could include information about the specific procedures and necessary documents for visa extension. The generated answer text is then provided as output.

[0302] Step 7:

[0303] Tailor your answers based on the results of the sentiment engine.

[0304] The generated answer is adjusted based on the analysis results of the emotion engine. The server takes into account the user's emotions and changes the tone to be calm and reassuring. For example, it adds words like "please stay calm" based on the emotional information. The adjusted answer text is obtained as the output.

[0305] Step 8:

[0306] The server sends the response to the user's terminal.

[0307] The adjusted answer text is sent from the server to the user's terminal. The user's terminal receives and displays the answer. In this step, the adjusted answer text is the input, and the answer displayed on the terminal is the output.

[0308] Step 9:

[0309] The user checks the answer.

[0310] The user checks the answers displayed on the device, which helps them understand the necessary procedures and decide on their next course of action. Through the device interface, the user can view the answers and obtain the necessary information.

[0311] (Application example 2)

[0312] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0313] In modern society, when users access various information online, it is important to quickly obtain appropriate answers. Furthermore, when users are from different countries, differences in language and culture can make understanding and communication difficult. Food delivery services, in particular, are required to alleviate anxiety and impatience during the ordering process and provide smooth support. However, conventional information provision systems are unable to respond in a way that takes user emotions into consideration, which leaves the user experience unsatisfactory.

[0314] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0315] In this invention, the server includes an interface means for a user to input a question, a means for the server to receive the question sent from the user, a means for analyzing the question using a natural language processing engine, a means for generating an answer based on the question using a trained artificial intelligence model, a means for transmitting the generated answer to the user's terminal, and a means for recognizing the user's emotion using an emotion engine and adjusting the quality and format of the answer. This makes it possible to provide an appropriate answer according to the user's emotional state, thereby improving the user experience in food delivery services.

[0316] A "user" is an individual or entity that utilizes the system to enter questions and receive answers.

[0317] A "question" is a written or spoken input that a user makes through the interface to obtain the information or support they are seeking.

[0318] An "interface means" is a part of the system that allows a user to input a question, and includes a graphical user interface (GUI), a text box, a voice input device, and the like.

[0319] A "server" is a computer or network service that serves as the core of a system that receives questions, analyzes them, generates answers, and sends them.

[0320] A "natural language processing engine" is a collection of software that analyzes and understands the meaning of questions submitted by users.

[0321] A "trained artificial intelligence model" is a collection of algorithms that have been trained using past data and specific training to automatically perform specific tasks.

[0322] An "answer" is a written or spoken message such as information, instructions, or explanations that the system generates in response to a user's question.

[0323] An "emotion engine" is a set of software that recognizes and analyzes emotions from user input. It performs emotion analysis through text input, voice input, and facial recognition.

[0324] A "terminal" is a device that a user uses to access the system, enter questions, and check answers. This includes smartphones, PCs, tablets, etc.

[0325] "Tokenization" is the process of breaking down text into the smallest meaningful units, such as words or phrases.

[0326] "Part-of-speech tagging" is the process of identifying for each word in a text its part of speech (noun, verb, adjective, etc.).

[0327] Dependency analysis is the process of analyzing the relationships between words in a sentence to help understand its meaning.

[0328] This invention is a system that enables foreigners residing in Japan to efficiently obtain information regarding their Japanese residence status, and further combines it with an emotion engine that recognizes the user's emotions and adjusts the quality and format of responses. This system is particularly effective for services targeting multinational users, such as food delivery. The specific system configuration and operation are described below.

[0329] System configuration

[0330] The system includes the following major components:

[0331] 1. User Device:

[0332] A device that allows users to access the system, input questions using interface means, and check answers. This includes smartphones, PCs, tablets, etc.

[0333] 2. Server:

[0334] It is the central computer in the system that receives questions, analyzes them, generates answers, and sends the answers.

[0335] 3. Interface means:

[0336] It is the part of the system where users can enter questions, providing a graphical user interface (GUI) and text boxes, and also incorporating an emotion engine to recognize the user's emotions.

[0337] 4. Natural Language Processing Engine:

[0338] This software analyzes questions sent by users, performing processes such as tokenization, part-of-speech tagging, and dependency structure analysis.

[0339] 5. Trained artificial intelligence models:

[0340] It is a collection of algorithms that are created using historical data and specific training to generate appropriate answers based on questions.

[0341] 6. Database:

[0342] It stores data on immigration-related legal systems and procedures. Access to this database allows the model to provide accurate information.

[0343] 7. Emotion Engine:

[0344] This software recognizes and analyzes emotions from user input. It performs emotion analysis through text input, voice input, and facial recognition.

[0345] System Operation

[0346] First, a user accesses the system using a terminal and inputs a question using the interface means. For example, the user inputs, "Please tell me how to extend my visa." At this time, an emotion engine built into the interface means recognizes emotions from the user's text input.

[0347] Next, the server receives the question sent by the user. The received question is analyzed by a natural language processing engine. This analysis includes tokenization, part-of-speech tagging, and dependency structure analysis. At the same time, emotional information analyzed by an emotion engine is also sent to the server.

[0348] Once the analysis is complete, the server uses a trained artificial intelligence model to generate an answer based on the user's question. The model uses the analysis results to pull necessary information from a database to create an appropriate answer. Furthermore, based on the analysis results of the emotion engine, the format and content of the answer can be adjusted depending on the user's emotional state.

[0349] Finally, the server sends the generated answer to the user's device, where the user can confirm the answer displayed on the device and obtain the necessary procedures or information.

[0350] Usage example

[0351] If a user types "How do I extend my visa?", the system will act as follows:

[0352] 1. The user enters a question on the device and presses the send button. At this time, the emotion engine recognizes emotions such as "impatience" or "anxiety" from the user's text.

[0353] 2. The server receives the question and analyzes it using the natural language processing engine. At the same time, it also receives the results of the emotion engine.

[0354] 3. The server uses a trained AI model to retrieve the necessary documents and procedures for visa extension from the database. Based on the results of the emotion engine, it adjusts the tone of the message to a calm and reassuring one: "Please stay calm. To extend your visa, you will need to prepare the application documents and submit them to the Immigration Bureau. For detailed procedures, please refer to the Immigration Bureau's official website."

[0355] 4. The server sends the generated response to the user's device.

[0356] 5. The user can check the answers on the device and understand the necessary procedures.

[0357] An example of a prompt sentence is, "Please tell me how to extend my visa."

[0358] The system as a whole is designed to enable users to efficiently obtain information about complex immigration procedures. The emotion engine also recognizes the user's emotions and provides information in an appropriate format, improving the user experience.

[0359] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0360] Step 1:

[0361] A user accesses the system using a terminal and inputs a question using the interface means.

[0362] Input: The user enters the text "How do I extend my visa?" into the interface means.

[0363] Output: Text data is sent from the user's terminal to the system.

[0364] Specific operation: The user enters a question in the text box of the terminal and clicks the send button. At this time, the emotion engine built into the interface means analyzes the emotion from the user's text input.

[0365] Step 2:

[0366] The server receives a question sent by a user.

[0367] Input: Text data sent from the user's terminal.

[0368] Output: Text data received in the server.

[0369] Specific operation: The server receives the text data sent from the user's terminal, along with the analysis results of the emotion engine.

[0370] Step 3:

[0371] The server uses a natural language processing engine to parse the question.

[0372] Input: Text data stored on the server.

[0373] Output: Parsed question tokens, parts of speech, and dependency structure data.

[0374] Specific operation: The natural language processing engine performs tokenization, part-of-speech tagging, and dependency structure analysis on the text data to generate analysis results.

[0375] Step 4:

[0376] The server uses a trained artificial intelligence model to generate answers based on the questions.

[0377] Input: Parsed question data and sentiment engine results.

[0378] Output: The generated answer text.

[0379] How it works: The AI ​​model retrieves the necessary information from the database based on the analysis results and generates an appropriate answer. The quality and format of the answer are adjusted based on the results of the emotion engine.

[0380] Step 5:

[0381] The server sends the generated answer to the user's terminal.

[0382] Input: The generated answer text.

[0383] Output: The answer text that is displayed on the user's terminal.

[0384] Specific operation: The server sends the generated answer text to the user's terminal, where the user can check the answer and understand the necessary procedures.

[0385] Step 6:

[0386] The user checks the answer on the device.

[0387] Input: The answer text sent by the server.

[0388] Output: User understanding and next actions.

[0389] Specific operation: The user checks the answers displayed on the device screen and understands the necessary information and procedures. If the information is insufficient, the user can enter a new question.

[0390] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0391] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0392] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0393] [Second embodiment]

[0394] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0395] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0396] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0397] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0398] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0399] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0400] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0401] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0402] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0403] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0404] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0405] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0406] This invention is a system for foreigners in Japan to efficiently obtain information regarding their residence status in Japan. This system is implemented by having a user input a question, a server analyze the question, generate an appropriate answer, and return it to the user.

[0407] System configuration

[0408] The system includes the following major components:

[0409] 1. User device: A device on which a user enters questions and checks answers. This includes smartphones, PCs, tablets, etc.

[0410] 2. Server: The central part of the system, which receives questions, analyzes them, generates answers, and sends them.

[0411] 3. Interface means: Provides a GUI (graphical user interface) and text boxes for users to enter questions.

[0412] 4. Natural language processing engine: Runs on the server and analyzes questions sent by users, performing processes such as tokenization, part-of-speech tagging, and dependency structure analysis.

[0413] 5. Trained AI model: This model is created using historical data and specific training to generate appropriate answers based on the question.

[0414] 6. Database: Data on immigration-related legal systems and procedures is stored. Access to this database allows the model to provide accurate information.

[0415] System Operation

[0416] First, a user accesses the system using a terminal and inputs a question using the interface means, for example, "How do I extend my visa?"

[0417] The server then receives the user-submitted question, which is then analyzed by a natural language processing engine, including tokenization, part-of-speech tagging, and dependency structure analysis.

[0418] Once the analysis is complete, the server uses a trained artificial intelligence model to generate an answer based on the user's question, which then uses the analysis results to pull the necessary information from a database to create the appropriate answer.

[0419] Finally, the server sends the generated answer to the user's device, where the user can confirm the answer displayed on the device and obtain the necessary procedures or information.

[0420] Specific examples

[0421] Example 1: When a user enters "How do I extend my visa?"

[0422] 1. The user enters a question into the terminal and presses the send button.

[0423] 2. The server receives the question and analyzes it using a natural language processing engine.

[0424] 3. The server uses a trained artificial intelligence model to retrieve the necessary documents and procedures for visa extension from the database.

[0425] 4. The server generates a response saying, "To extend your visa, you need to prepare application documents and submit them to the Immigration Bureau. For detailed procedures, please refer to the official website of the Immigration Bureau."

[0426] 5. The server sends the generated response to the user's device.

[0427] 6. The user checks the answers on the device and understands the necessary procedures.

[0428] In this way, the present invention is designed to enable foreigners in Japan to efficiently obtain information regarding the complicated procedures for obtaining residence status.

[0429] The processing flow will be explained below.

[0430] Step 1:

[0431] A user accesses the system using a terminal. The user opens a dedicated application or website.

[0432] Step 2:

[0433] The user uses the interface means to input a question, for example, "How do I extend my visa?" into the text box.

[0434] Step 3:

[0435] The user presses the send button to send the entered question to the server.

[0436] Step 4:

[0437] The server receives questions sent by users and saves them in text format.

[0438] Step 5:

[0439] The server uses a natural language processing engine to parse the received question, which includes tokenization, part-of-speech tagging, and dependency structure analysis.

[0440] Step 6:

[0441] The server uses a trained artificial intelligence model to generate appropriate answers to questions based on the analysis, which pulls the necessary information from a database.

[0442] Step 7:

[0443] The server uses a response sending means to send the generated response back to the user.

[0444] Step 8:

[0445] The user's terminal receives the response sent from the server and displays the received response on the screen.

[0446] Step 9:

[0447] The user checks the answers displayed on the device screen and understands the appropriate procedures and information.

[0448] These are the processing steps for the entire system.

[0449] Example 1

[0450] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0451] Foreigners living in Japan face the challenge of efficiently obtaining information about their residence status. In particular, there are limited ways to quickly obtain accurate information about the complex legal system and procedures, which can easily lead to misunderstandings and delays in procedures.

[0452] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0453] In this invention, the server includes an interface means for a user to input a question, a means for the server to receive the question sent from the user, a means for analyzing the question using a natural language processing engine, a means for generating an answer based on the question using a trained artificial intelligence model, a means for transmitting the generated answer to the user's terminal, and a means for the user to confirm the generated answer, thereby enabling the user to efficiently and accurately obtain information regarding residence status.

[0454] "User" refers to a person who uses the system to enter questions and receive answers.

[0455] "Interface means" refers to means that provides a graphical user interface and text boxes for a user to enter a question.

[0456] "Server" refers to a central computer system that receives questions from users, analyzes and generates answers, and sends the answers to users.

[0457] A "natural language processing engine" is software that analyzes questions submitted by users, performing functions such as tokenization, part-of-speech tagging, and dependency structure analysis.

[0458] "Tokenization" refers to the process of breaking down text into basic units such as words and phrases.

[0459] "Part-of-speech tagging" refers to the process of assigning each token its part of speech (noun, verb, adjective, etc.).

[0460] "Dependency analysis" refers to the process of analyzing the grammatical relationships between words in a sentence.

[0461] An "artificial intelligence model" refers to a model that learns from past data and specific training and generates appropriate answers to user questions.

[0462] "Answer generation means" refers to a means for generating answers based on a user's question using a trained artificial intelligence model.

[0463] "Database" refers to a data resource that stores data on immigration-related legal systems and procedures.

[0464] The "answer sending means" refers to a means for sending the generated answer to the user's terminal.

[0465] A "user's terminal" is a device on which a user inputs questions and checks answers, and includes smartphones, PCs, tablets, etc.

[0466] The present invention is a system that allows foreign residents in Japan to efficiently obtain information regarding their residence status in Japan. This system is implemented by having a user input a question, a server analyze the question, generate an appropriate answer, and return it to the user. How this system is implemented will be described in detail below.

[0467] System configuration

[0468] 1. User Device:

[0469] A user terminal is a device that allows a user to enter questions and check answers, and includes smartphones, PCs, tablets, etc.

[0470] Examples include smartphones (e.g., iPhone, Samsung Galaxy), PCs (e.g., Dell XPS, MacBook Pro), and tablets (e.g., iPad, Microsoft Surface).

[0471] 2. Server:

[0472] The server is the center of the system, receiving questions, analyzing them, generating answers, and sending them out.

[0473] The server can use a cloud-based system (e.g., Amazon Web Services, Google Cloud Platform).

[0474] 3. Interface means:

[0475] The interface means provides a GUI (Graphical User Interface) and a text box for the user to input a question.

[0476] For example, this includes forms and chatbot interfaces that run on a web browser.

[0477] 4. Natural Language Processing Engine:

[0478] The natural language processing engine runs on the server and analyzes questions submitted by users. The main processes include tokenization, part-of-speech tagging, and dependency structure analysis.

[0479] The software used includes natural language processing libraries such as NLTK and SpaCy.

[0480] 5. Trained artificial intelligence models:

[0481] The model is built using historical data and specific training to generate appropriate answers based on the question.

[0482] Specific examples include models such as GPT-3 and BERT.

[0483] 6. Database:

[0484] The database stores data on legal systems and procedures related to immigration status.

[0485] The databases used include relational database management systems (RDBMS) such as MySQL and PostgreSQL.

[0486] System operation example

[0487] For example, if a user types "How do I extend my visa?" the process is as follows:

[0488] 1. Users enter their questions using their smartphones, PCs, or tablets.

[0489] 2. The server receives the question and parses it using a natural language processing engine, which splits the question into tokens, tags it with parts of speech, and analyzes grammatical dependencies.

[0490] 3. The trained AI model retrieves the necessary information from the database based on the analysis results and generates an appropriate answer.

[0491] 4. The server generates a response and sends it to the user's device.

[0492] 5. The user checks the answers on the device and understands the necessary procedures.

[0493] In this way, the present invention is designed to enable foreign residents to efficiently obtain information regarding the complicated procedures for obtaining residence status, allowing users to quickly and accurately obtain the information they need.

[0494] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0495] Step 1:

[0496] The server receives the user's question through the interface means. The user accesses the interface using a terminal, inputs the question "How do I extend my visa?", and presses the send button. This input data is sent to the server by the interface means. The server receives this data and passes it on to the next processing step.

[0497] Step 2:

[0498] The server passes the question to the natural language processing engine for analysis. The input question is divided into tokens such as "visa," "extension," "how," "teach," and "please." Next, each token is tagged with a part of speech, and finally, grammatical dependencies are analyzed. This generates an analysis result, which is passed to the next step.

[0499] Step 3:

[0500] The server passes the analysis results to a trained AI model, which generates an answer based on the question. The analysis results, which are input data, are processed to generate a specific answer. Specifically, the analysis results act as a trigger, and the AI ​​model (e.g., GPT-3) generates an answer such as, "To apply for a visa extension, you must prepare application documents and submit them to the Immigration Bureau." This generated answer is passed to the next step.

[0501] Step 4:

[0502] The server sends the generated answer to the user's terminal. The answer, which is output data from the trained artificial intelligence model, is sent to the user's terminal as an HTTP response. The server converts the answer data into an appropriate format and sends it to the user's terminal via a transmission means.

[0503] Step 5:

[0504] The user checks the answer on their device. The user's device displays the received answer data, and the user checks it. Specifically, the answer is displayed on a web browser or application, and the user receives information such as, "To apply for a visa extension, you will need to prepare application documents and submit them to the Immigration Bureau."

[0505] This series of processing steps enables the user to efficiently and accurately obtain information regarding residence status.

[0506] (Application example 1)

[0507] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0508] Currently, it is difficult for foreigners living in Japan to efficiently obtain information regarding their Japanese residence status. Furthermore, there is no system that can respond to questions in real time when using autonomous vehicles. Furthermore, there is no established method for improving convenience using voice input and output. A new system is needed to solve these issues.

[0509] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0510] In this invention, the server includes an interface means for a user to input a question or command, a means for the server to receive the question or command sent from the user, a means for analyzing the question or command using a natural language processing engine, a means for generating a response based on the question or command using a trained artificial intelligence model, a means for transmitting the generated response to a display device in the user's terminal or in the vehicle, and a voice generation means for providing the generated response to the user through a voice output device. This enables foreigners residing in Japan to efficiently obtain information on their status of residence in real time even while riding in an autonomous vehicle.

[0511] An "interface means" is a device or software through which a user inputs questions or commands.

[0512] A "server" is a central processing unit that receives questions or commands sent by users, analyzes them, and generates responses.

[0513] A "natural language processing engine" is software that analyzes questions and commands from users and understands their intentions.

[0514] A "trained artificial intelligence model" is an algorithm that learns from large amounts of data to generate appropriate responses based on questions or commands.

[0515] A "user's terminal" is a device used by a user, such as a smartphone, tablet, or PC.

[0516] A "display device" is a screen device for visually displaying the generated responses.

[0517] A "voice generating means" is a device and software for providing the generated response to the user as voice.

[0518] "Database" means a system for storing information on legal systems and procedures related to immigration status.

[0519] This invention is a system that allows a user to input questions or commands related to Japanese residence status and obtain answers in real time within an autonomous vehicle. The system includes a server, a user terminal, a natural language processing engine, a trained artificial intelligence model, a display device, a voice generation means, and a database.

[0520] System configuration

[0521] 1. User Interface Means:

[0522] Users input questions using devices such as smartphones, tablets, and in-car displays.

[0523] Specifically, voice input can be used, for example, by using prompt sentences such as "Please tell me how to extend my visa."

[0524] 2. Server:

[0525] Use a cloud-based server, such as Amazon Web Services (AWS) or Microsoft Azure.

[0526] The server receives questions or commands from users and uses a natural language processing engine and generative AI models to analyze and generate answers.

[0527] 3. Natural Language Processing Engine:

[0528] The natural language processing engine uses Google Cloud Natural Language API and IBM Watson Natural Language Understanding.

[0529] The system processes user questions through tokenization, part-of-speech tagging, dependency structure analysis, and other processes to accurately analyze their intent.

[0530] 4. Trained artificial intelligence model:

[0531] AI models such as OpenAI's GPT-4 can be used.

[0532] Based on the analyzed questions, the necessary information is extracted from a database related to residence status and an appropriate answer is generated.

[0533] 5. Display devices and sound generating means:

[0534] The display device uses the screen on the user's terminal or in the car.

[0535] Voice generation uses the gTTS (Google Text-to-Speech) library and the voice output device installed in the vehicle.

[0536] The generated answers are converted into audio files and provided to the user.

[0537] 6. Database:

[0538] A database will be used to store information on immigration-related legal systems and procedures.

[0539] For example, this includes data provided by the Japanese Immigration Bureau and the Ministry of Justice.

[0540] Specific examples

[0541] Specifically, when a user uses the in-car display or voice input to type "How do I extend my visa?", the following happens:

[0542] 1. The user types or speaks a question using the in-car interface.

[0543] 2. The question is sent to the server and analyzed by a natural language processing engine.

[0544] 3. Based on the parsed question, a trained artificial intelligence model generates a response.

[0545] 4. The response is displayed on the user's terminal or on a display device in the vehicle.

[0546] 5. At the same time, the voice generating means converts the response into a voice file and provides it to the user audibly.

[0547] This system will enable foreigners in Japan to receive real-time answers to questions about their residence status while riding in an autonomous vehicle, and voice input and output functions will greatly improve convenience.

[0548] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0549] Step 1:

[0550] The user uses the in-car interface means to input or speak a question. The user may say a prompt, for example, "How do I extend my visa?" The input here is text or voice data. The output is the question data received by the interface means. The interface uses speech recognition software to convert the user's speech into text.

[0551] Step 2:

[0552] The terminal transmits the user's query data to the server, where the input is the query data received by the interface means and the output is the query data sent to the server. The network module of the terminal is responsible for this transfer.

[0553] Step 3:

[0554] The server receives the question data and analyzes it using a natural language processing engine. The natural language processing engine uses Google Cloud Natural Language API or IBM Watson. The input is the received question data, and the output is the analyzed data. This analysis includes tokenization, part-of-speech tagging, and dependency structure analysis.

[0555] Step 4:

[0556] The server passes the analyzed data to a trained artificial intelligence model to generate an appropriate response. The AI ​​model used here is OpenAI's GPT-4, etc. The input is the analyzed data, and the output is the generated response. The AI ​​model uses the analysis results to extract the necessary information from a database and generate a response.

[0557] Step 5:

[0558] The server sends the generated response to the user's terminal or to a display device in the car. The input is the generated response, and the output is the response displayed on the user's terminal. The communication protocol and interface used here use standard web server technology.

[0559] Step 6:

[0560] The server converts the generated response into an audio file using a speech generator, such as the gTTS (Google Text-to-Speech) library, or the car's audio output device. The input is the text data of the generated response, and the output is an audio file. This audio file is played through the car's speakers.

[0561] Step 7:

[0562] The user can see the response displayed on the terminal or hear the audio response from the car's speakers. This step effectively communicates the information provided to the user in real time. The input is the displayed or played response, and the output is the user's understanding and action.

[0563] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0564] This invention is a system that enables foreigners residing in Japan to efficiently obtain information regarding their Japanese residence status, and it also combines an emotion engine that recognizes the user's emotions and adjusts the quality and format of the answer. This system is realized by having the user input a question, and the server analyzes the question, generates an appropriate answer, and returns it to the user. Another objective is to improve the user experience by recognizing the user's emotions.

[0565] System configuration

[0566] The system includes the following major components:

[0567] 1. User device: A device on which a user enters questions and checks answers. This includes smartphones, PCs, tablets, etc.

[0568] 2. Server: The central part of the system, which receives questions, analyzes them, generates answers, and sends them. It also adjusts the answers based on the results of sentiment analysis by the sentiment engine.

[0569] 3. Interface: Provides a GUI (Graphical User Interface) and text boxes for users to enter questions. This interface incorporates an emotion engine to recognize the user's emotions.

[0570] 4. Natural language processing engine: Runs on the server and analyzes questions sent by users, performing processes such as tokenization, part-of-speech tagging, and dependency structure analysis.

[0571] 5. Trained AI model: This model is created using historical data and specific training to generate appropriate answers based on the question.

[0572] 6. Database: Data on immigration-related legal systems and procedures is stored. Access to this database allows the model to provide accurate information.

[0573] 7. Emotion Engine: An engine for recognizing emotions from user input. It can analyze emotions not only through text input, but also through voice input and facial recognition.

[0574] System Operation

[0575] First, a user accesses the system using a terminal and inputs a question using the interface means. For example, the user inputs, "Please tell me how to extend my visa." At this time, an emotion engine built into the interface means recognizes emotions from the user's text input.

[0576] Next, the server receives the question sent by the user. The received question is analyzed by a natural language processing engine. This analysis includes tokenization, part-of-speech tagging, and dependency structure analysis. At the same time, emotional information analyzed by an emotion engine is also sent to the server.

[0577] Once the analysis is complete, the server uses a trained artificial intelligence model to generate an answer based on the user's question. The model uses the analysis results to pull necessary information from a database to create an appropriate answer. Furthermore, based on the analysis results of the emotion engine, the format and content of the answer can be adjusted depending on the user's emotional state.

[0578] Finally, the server sends the generated answer to the user's device, where the user can confirm the answer displayed on the device and obtain the necessary procedures or information.

[0579] Specific examples

[0580] Example 1: When a user enters "How do I extend my visa?"

[0581] 1. The user enters a question on the device and presses the send button. At this time, the emotion engine recognizes emotions such as "impatience" or "anxiety" from the user's text.

[0582] 2. The server receives the question and analyzes it using the natural language processing engine. At the same time, it also receives the results of the emotion engine.

[0583] 3. The server uses a trained AI model to retrieve the necessary documents and procedures for visa extension from the database. Based on the results of the emotion engine, it adjusts the tone of the message to a calm and reassuring one: "Please stay calm. To extend your visa, you will need to prepare the application documents and submit them to the Immigration Bureau. For detailed procedures, please refer to the Immigration Bureau's official website."

[0584] 4. The server sends the generated response to the user's device.

[0585] 5. The user checks the answers on the device and understands the necessary procedures.

[0586] In this way, the present invention is designed to enable foreigners in Japan to efficiently obtain information on the complicated procedures for obtaining residence status. Furthermore, the emotion engine recognizes the user's emotions and provides information in an appropriate format, improving the user experience.

[0587] The processing flow will be explained below.

[0588] Step 1:

[0589] A user accesses the system using a terminal. The user opens a dedicated application or website.

[0590] Step 2:

[0591] The user uses the interface means to input a question, for example, "How do I extend my visa?" into the text box.

[0592] Step 3:

[0593] The user presses the send button to send the entered question to the server, at which point an emotion engine built into the interface means recognizes emotions from the user's text input.

[0594] Step 4:

[0595] The server receives questions sent by users and saves them in text format.

[0596] Step 5:

[0597] The server parses the received question using a natural language processing engine, which performs tokenization, part-of-speech tagging, and dependency structure analysis.

[0598] Step 6:

[0599] At the same time, the server receives emotion information analyzed by the emotion engine, which determines the user's emotion from the text content and expressions.

[0600] Step 7:

[0601] The server uses a trained artificial intelligence model to generate appropriate answers to questions based on the analysis, which pulls the necessary information from a database.

[0602] Step 8:

[0603] The server uses the emotion information from the emotion engine to adjust the format and content of the response depending on the user's emotional state. For example, if emotions such as "impatience" or "anxiety" are recognized, the response will be modified to a calmer, more reassuring tone.

[0604] Step 9:

[0605] The server then sends the generated answer to the user's device, which includes an expression that corresponds to the user's emotional state.

[0606] Step 10:

[0607] The user's terminal receives the response sent from the server and displays the received response on the screen.

[0608] Step 11:

[0609] The user checks the answers displayed on the device screen and understands the appropriate procedures and information. The answers include expressions that correspond to the user's emotional state, allowing the user to take the next action with greater confidence.

[0610] Examples:

[0611] 1. The user enters a question on the device and presses the send button. At this time, the emotion engine recognizes emotions such as "impatience" or "anxiety" from the user's text.

[0612] 2. The server receives the question and analyzes it using the natural language processing engine. At the same time, it also receives the results of the emotion engine.

[0613] 3. The server uses a trained AI model to retrieve the necessary documents and procedures for visa extension from the database. Based on the results of the emotion engine, it adjusts the tone of the message to a calm and reassuring one: "Please stay calm. To extend your visa, you will need to prepare the application documents and submit them to the Immigration Bureau. For detailed procedures, please refer to the Immigration Bureau's official website."

[0614] 4. The server sends the generated response to the user's device.

[0615] 5. The user checks the answers on the device and understands the necessary procedures.

[0616] Example 2

[0617] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0618] Conventional information acquisition systems made it difficult for foreigners in Japan to efficiently acquire information related to their Japanese residence status, and were also unable to respond in a way that took user feelings into consideration. As a result, the user experience did not improve and user satisfaction was low.

[0619] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an interface means for a user to input a question, a means for the server to receive the question sent from the user, a means for analyzing the question using a natural language processing engine, a means for generating an answer based on the question using a trained artificial intelligence model, a means for transmitting the generated answer to the user's terminal, a means for recognizing and analyzing the user's emotions using an emotion engine, and a means for adjusting the format and content of the answer based on the analysis result of the emotion engine. This not only enables foreigners residing in Japan to efficiently obtain information about their residence status, but also enables answers that take the user's emotions into consideration, improving the user experience.

[0620] A "user" is someone who uses this system to enter questions and receive answers.

[0621] "Terminal" refers to a device on which a user enters questions and checks answers, and specifically includes smartphones, PCs, tablets, etc.

[0622] An "interface means" is a means for providing a graphical user interface and a text box for a user to input a question.

[0623] The "server" is a central computer system that receives questions, analyzes them, generates answers, sends answers, recognizes and analyzes user emotions, and so on.

[0624] A "natural language processing engine" is an engine that analyzes questions sent by users, and performs tokenization, part-of-speech tagging, dependency structure analysis, etc.

[0625] A "trained artificial intelligence model" is an artificial intelligence model that is trained using historical data or specific training data to generate appropriate answers based on questions.

[0626] "Database" refers to a data store that stores data on legal systems and procedures related to immigration status, and which AI models access to extract the necessary information.

[0627] An "emotion engine" is an engine that recognizes and analyzes emotions from user input, and is capable of analyzing emotions not only through text input but also through voice input and facial recognition.

[0628] "Tokenization" is the process by which a natural language processing engine breaks text into basic units such as words and phrases.

[0629] "Part-of-speech tagging" is the process by which a natural language processing engine adds part-of-speech information (noun, verb, adjective, etc.) to each token.

[0630] "Dependency structure analysis" is a process in which a natural language processing engine analyzes the structure of a sentence and identifies the dependencies between words.

[0631] To implement this invention, the following elements are required: a user, a terminal, and a server. This system is realized by having the user input a question, and the server analyze the question, generate an answer, and send it back to the user's terminal. Furthermore, it combines an emotion engine that recognizes the user's emotions and adjusts the quality and format of the answer.

[0632] The devices used by users are smartphones, PCs, tablets, etc., and they access the system through these devices. As an interface, a GUI and text boxes are provided for users to enter questions.

[0633] The server is the central component of the system and performs the following functions:

[0634] 1. Receiving a question: Receives the question data sent by the user.

[0635] 2. Natural Language Processing: A natural language processing engine analyzes the question, including tokenization, part-of-speech tagging, and dependency structure analysis.

[0636] 3. Emotion recognition: The emotion engine recognizes emotions from the user's input and sends the analysis results to the server.

[0637] 4. Answer generation: A trained AI model generates answers based on the analyzed questions. This model accesses a database containing data on immigration-related legal systems and procedures.

[0638] 5. Response Adjustment: Adjust the quality and format of responses based on the sentiment engine analysis results.

[0639] 6. Sending the answer: Send the generated answer to the user's device.

[0640] The specific operation of this system will be explained below as an example.

[0641] Examples:

[0642] If the user types "How do I extend my visa?"

[0643] 1. The user enters a question using a terminal and presses the send button. At this time, the emotion engine recognizes emotions such as "impatience" or "anxiety" from the user's text.

[0644] 2. The server receives the question and begins analyzing it with the natural language processing engine. At the same time, it also receives the results of the emotion engine.

[0645] 3. The server uses a trained AI model to retrieve the necessary information for visa extension from the database. Based on the results of the emotion engine, it adjusts the tone of the message to a calm and reassuring one: "Please stay calm. To apply for a visa extension, you need to prepare the application documents and submit them to the Immigration Bureau. For detailed procedures, please refer to the Immigration Bureau's official website."

[0646] 4. The server sends the generated response to the user's device.

[0647] 5. The user checks the answers on the device and understands the necessary procedures.

[0648] This system not only enables foreigners living in Japan to efficiently obtain information about their residence status, but also uses an emotion engine to respond in a way that takes the user's emotions into consideration.

[0649] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0650] Step 1:

[0651] The user types a question into the terminal.

[0652] A user accesses the system using a terminal. They input a question through the interface means (GUI or text box) on the terminal. For example, the user inputs "How do I extend my visa?" In this step, the user's question text is obtained as input.

[0653] Step 2:

[0654] The emotion engine recognizes the user's emotions.

[0655] The question text entered on the device is immediately sent to the emotion engine. The emotion engine performs text analysis to recognize the user's emotions. In this process, the user's question text is used as input, and emotion data such as "impatience" or "anxiety" is obtained as output. For example, the emotion engine analyzes the emotion of "anxiety" from the user's text.

[0656] Step 3:

[0657] The server receives the query.

[0658] The user's question text is sent to the server along with the emotion data. The server prepares to process the received question text and emotion data. In this step, the question text and emotion data are obtained as input.

[0659] Step 4:

[0660] A natural language processing engine analyzes the question.

[0661] The server's natural language processing engine analyzes the question text. This analysis includes tokenization, part-of-speech tagging, and dependency structure analysis. The analysis results in structured text data. For example, the text is categorized by words such as "visa," "extension," and "method," and the context and dependencies are analyzed.

[0662] Step 5:

[0663] The server receives the analysis results of the emotion engine.

[0664] The server receives the emotion data sent from the emotion engine. The server then prepares a dataset containing the user's emotion information. The emotion data is input, and the emotion information is added to the dataset in the server as output.

[0665] Step 6:

[0666] A trained artificial intelligence model generates the answer.

[0667] The server inputs the analysis results of the natural language processing engine and sentiment data into a trained artificial intelligence model. The model then uses the analysis results of the question to retrieve appropriate information from a database and generate an answer. For example, this could include information about the specific procedures and necessary documents for visa extension. The generated answer text is then provided as output.

[0668] Step 7:

[0669] Tailor your answers based on the results of the sentiment engine.

[0670] The generated answer is adjusted based on the analysis results of the emotion engine. The server takes into account the user's emotions and changes the tone to be calm and reassuring. For example, it adds words like "please stay calm" based on the emotional information. The adjusted answer text is obtained as the output.

[0671] Step 8:

[0672] The server sends the response to the user's terminal.

[0673] The adjusted answer text is sent from the server to the user's terminal. The user's terminal receives and displays the answer. In this step, the adjusted answer text is the input, and the answer displayed on the terminal is the output.

[0674] Step 9:

[0675] The user checks the answer.

[0676] The user checks the answers displayed on the device, which helps them understand the necessary procedures and decide on their next course of action. Through the device interface, the user can view the answers and obtain the necessary information.

[0677] (Application example 2)

[0678] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0679] In modern society, when users access various information online, it is important to quickly obtain appropriate answers. Furthermore, when users are from different countries, differences in language and culture can make understanding and communication difficult. Food delivery services, in particular, are required to alleviate anxiety and impatience during the ordering process and provide smooth support. However, conventional information provision systems are unable to respond in a way that takes user emotions into consideration, which leaves the user experience unsatisfactory.

[0680] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0681] In this invention, the server includes an interface means for a user to input a question, a means for the server to receive the question sent from the user, a means for analyzing the question using a natural language processing engine, a means for generating an answer based on the question using a trained artificial intelligence model, a means for transmitting the generated answer to the user's terminal, and a means for recognizing the user's emotion using an emotion engine and adjusting the quality and format of the answer. This makes it possible to provide an appropriate answer according to the user's emotional state, thereby improving the user experience in food delivery services.

[0682] A "user" is an individual or entity that utilizes the system to enter questions and receive answers.

[0683] A "question" is a written or spoken input that a user makes through the interface to obtain the information or support they are seeking.

[0684] An "interface means" is a part of the system that allows a user to input a question, and includes a graphical user interface (GUI), a text box, a voice input device, and the like.

[0685] A "server" is a computer or network service that serves as the core of a system that receives questions, analyzes them, generates answers, and sends them.

[0686] A "natural language processing engine" is a collection of software that analyzes and understands the meaning of questions submitted by users.

[0687] A "trained artificial intelligence model" is a collection of algorithms that have been trained using past data and specific training to automatically perform specific tasks.

[0688] An "answer" is a written or spoken message such as information, instructions, or explanations that the system generates in response to a user's question.

[0689] An "emotion engine" is a set of software that recognizes and analyzes emotions from user input. It performs emotion analysis through text input, voice input, and facial recognition.

[0690] A "terminal" is a device that a user uses to access the system, enter questions, and check answers. This includes smartphones, PCs, tablets, etc.

[0691] "Tokenization" is the process of breaking down text into the smallest meaningful units, such as words or phrases.

[0692] "Part-of-speech tagging" is the process of identifying for each word in a text its part of speech (noun, verb, adjective, etc.).

[0693] Dependency analysis is the process of analyzing the relationships between words in a sentence to help understand its meaning.

[0694] This invention is a system that enables foreigners residing in Japan to efficiently obtain information regarding their Japanese residence status, and further combines it with an emotion engine that recognizes the user's emotions and adjusts the quality and format of responses. This system is particularly effective for services targeting multinational users, such as food delivery. The specific system configuration and operation are described below.

[0695] System configuration

[0696] The system includes the following major components:

[0697] 1. User Device:

[0698] A device that allows users to access the system, input questions using interface means, and check answers. This includes smartphones, PCs, tablets, etc.

[0699] 2. Server:

[0700] It is the central computer in the system that receives questions, analyzes them, generates answers, and sends the answers.

[0701] 3. Interface means:

[0702] It is the part of the system where users can enter questions, providing a graphical user interface (GUI) and text boxes, and also incorporating an emotion engine to recognize the user's emotions.

[0703] 4. Natural Language Processing Engine:

[0704] This software analyzes questions sent by users, performing processes such as tokenization, part-of-speech tagging, and dependency structure analysis.

[0705] 5. Trained artificial intelligence models:

[0706] It is a collection of algorithms that are created using historical data and specific training to generate appropriate answers based on questions.

[0707] 6. Database:

[0708] It stores data on immigration-related legal systems and procedures. Access to this database allows the model to provide accurate information.

[0709] 7. Emotion Engine:

[0710] This software recognizes and analyzes emotions from user input. It performs emotion analysis through text input, voice input, and facial recognition.

[0711] System Operation

[0712] First, a user accesses the system using a terminal and inputs a question using the interface means. For example, the user inputs, "Please tell me how to extend my visa." At this time, an emotion engine built into the interface means recognizes emotions from the user's text input.

[0713] Next, the server receives the question sent by the user. The received question is analyzed by a natural language processing engine. This analysis includes tokenization, part-of-speech tagging, and dependency structure analysis. At the same time, emotional information analyzed by an emotion engine is also sent to the server.

[0714] Once the analysis is complete, the server uses a trained artificial intelligence model to generate an answer based on the user's question. The model uses the analysis results to pull necessary information from a database to create an appropriate answer. Furthermore, based on the analysis results of the emotion engine, the format and content of the answer can be adjusted depending on the user's emotional state.

[0715] Finally, the server sends the generated answer to the user's device, where the user can confirm the answer displayed on the device and obtain the necessary procedures or information.

[0716] Usage example

[0717] If a user types "How do I extend my visa?", the system will act as follows:

[0718] 1. The user enters a question on the device and presses the send button. At this time, the emotion engine recognizes emotions such as "impatience" or "anxiety" from the user's text.

[0719] 2. The server receives the question and analyzes it using the natural language processing engine. At the same time, it also receives the results of the emotion engine.

[0720] 3. The server uses a trained AI model to retrieve the necessary documents and procedures for visa extension from the database. Based on the results of the emotion engine, it adjusts the tone of the message to a calm and reassuring one: "Please stay calm. To extend your visa, you will need to prepare the application documents and submit them to the Immigration Bureau. For detailed procedures, please refer to the Immigration Bureau's official website."

[0721] 4. The server sends the generated response to the user's device.

[0722] 5. The user can check the answers on the device and understand the necessary procedures.

[0723] An example of a prompt sentence is, "Please tell me how to extend my visa."

[0724] The system as a whole is designed to enable users to efficiently obtain information about complex immigration procedures. The emotion engine also recognizes the user's emotions and provides information in an appropriate format, improving the user experience.

[0725] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0726] Step 1:

[0727] A user accesses the system using a terminal and inputs a question using the interface means.

[0728] Input: The user enters the text "How do I extend my visa?" into the interface means.

[0729] Output: Text data is sent from the user's terminal to the system.

[0730] Specific operation: The user enters a question in the text box of the terminal and clicks the send button. At this time, the emotion engine built into the interface means analyzes the emotion from the user's text input.

[0731] Step 2:

[0732] The server receives a question sent by a user.

[0733] Input: Text data sent from the user's terminal.

[0734] Output: Text data received in the server.

[0735] Specific operation: The server receives the text data sent from the user's terminal, along with the analysis results of the emotion engine.

[0736] Step 3:

[0737] The server uses a natural language processing engine to parse the question.

[0738] Input: Text data stored on the server.

[0739] Output: Parsed question tokens, parts of speech, and dependency structure data.

[0740] Specific operation: The natural language processing engine performs tokenization, part-of-speech tagging, and dependency structure analysis on the text data to generate analysis results.

[0741] Step 4:

[0742] The server uses a trained artificial intelligence model to generate answers based on the questions.

[0743] Input: Parsed question data and sentiment engine results.

[0744] Output: The generated answer text.

[0745] How it works: The AI ​​model retrieves the necessary information from the database based on the analysis results and generates an appropriate answer. The quality and format of the answer are adjusted based on the results of the emotion engine.

[0746] Step 5:

[0747] The server sends the generated answer to the user's terminal.

[0748] Input: The generated answer text.

[0749] Output: The answer text that is displayed on the user's terminal.

[0750] Specific operation: The server sends the generated answer text to the user's terminal, where the user can check the answer and understand the necessary procedures.

[0751] Step 6:

[0752] The user checks the answer on the device.

[0753] Input: The answer text sent by the server.

[0754] Output: User understanding and next actions.

[0755] Specific operation: The user checks the answers displayed on the device screen and understands the necessary information and procedures. If the information is insufficient, the user can enter a new question.

[0756] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0757] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0758] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0759] [Third embodiment]

[0760] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0761] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0762] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0763] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0764] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0765] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0766] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0767] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0768] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0769] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0770] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0771] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0772] This invention is a system for foreigners in Japan to efficiently obtain information regarding their residence status in Japan. This system is implemented by having a user input a question, a server analyze the question, generate an appropriate answer, and return it to the user.

[0773] System configuration

[0774] The system includes the following major components:

[0775] 1. User device: A device on which a user enters questions and checks answers. This includes smartphones, PCs, tablets, etc.

[0776] 2. Server: The central part of the system, which receives questions, analyzes them, generates answers, and sends them.

[0777] 3. Interface means: Provides a GUI (graphical user interface) and text boxes for users to enter questions.

[0778] 4. Natural language processing engine: Runs on the server and analyzes questions sent by users, performing processes such as tokenization, part-of-speech tagging, and dependency structure analysis.

[0779] 5. Trained AI model: This model is created using historical data and specific training to generate appropriate answers based on the question.

[0780] 6. Database: Data on immigration-related legal systems and procedures is stored. Access to this database allows the model to provide accurate information.

[0781] System Operation

[0782] First, a user accesses the system using a terminal and inputs a question using the interface means, for example, "How do I extend my visa?"

[0783] The server then receives the user-submitted question, which is then analyzed by a natural language processing engine, including tokenization, part-of-speech tagging, and dependency structure analysis.

[0784] Once the analysis is complete, the server uses a trained artificial intelligence model to generate an answer based on the user's question, which then uses the analysis results to pull the necessary information from a database to create the appropriate answer.

[0785] Finally, the server sends the generated answer to the user's device, where the user can confirm the answer displayed on the device and obtain the necessary procedures or information.

[0786] Specific examples

[0787] Example 1: When a user enters "How do I extend my visa?"

[0788] 1. The user enters a question into the terminal and presses the send button.

[0789] 2. The server receives the question and analyzes it using a natural language processing engine.

[0790] 3. The server uses a trained artificial intelligence model to retrieve the necessary documents and procedures for visa extension from the database.

[0791] 4. The server generates a response saying, "To extend your visa, you need to prepare application documents and submit them to the Immigration Bureau. For detailed procedures, please refer to the official website of the Immigration Bureau."

[0792] 5. The server sends the generated response to the user's device.

[0793] 6. The user checks the answers on the device and understands the necessary procedures.

[0794] In this way, the present invention is designed to enable foreigners in Japan to efficiently obtain information regarding the complicated procedures for obtaining residence status.

[0795] The processing flow will be explained below.

[0796] Step 1:

[0797] A user accesses the system using a terminal. The user opens a dedicated application or website.

[0798] Step 2:

[0799] The user uses the interface means to input a question, for example, "How do I extend my visa?" into the text box.

[0800] Step 3:

[0801] The user presses the send button to send the entered question to the server.

[0802] Step 4:

[0803] The server receives questions sent by users and saves them in text format.

[0804] Step 5:

[0805] The server uses a natural language processing engine to parse the received question, which includes tokenization, part-of-speech tagging, and dependency structure analysis.

[0806] Step 6:

[0807] The server uses a trained artificial intelligence model to generate appropriate answers to questions based on the analysis, which pulls the necessary information from a database.

[0808] Step 7:

[0809] The server uses a response sending means to send the generated response back to the user.

[0810] Step 8:

[0811] The user's terminal receives the response sent from the server and displays the received response on the screen.

[0812] Step 9:

[0813] The user checks the answers displayed on the device screen and understands the appropriate procedures and information.

[0814] These are the processing steps for the entire system.

[0815] Example 1

[0816] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0817] Foreigners living in Japan face the challenge of efficiently obtaining information about their residence status. In particular, there are limited ways to quickly obtain accurate information about the complex legal system and procedures, which can easily lead to misunderstandings and delays in procedures.

[0818] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0819] In this invention, the server includes an interface means for a user to input a question, a means for the server to receive the question sent from the user, a means for analyzing the question using a natural language processing engine, a means for generating an answer based on the question using a trained artificial intelligence model, a means for transmitting the generated answer to the user's terminal, and a means for the user to confirm the generated answer, thereby enabling the user to efficiently and accurately obtain information regarding residence status.

[0820] "User" refers to a person who uses the system to enter questions and receive answers.

[0821] "Interface means" refers to means that provides a graphical user interface and text boxes for a user to enter a question.

[0822] "Server" refers to a central computer system that receives questions from users, analyzes and generates answers, and sends the answers to users.

[0823] A "natural language processing engine" is software that analyzes questions submitted by users, performing functions such as tokenization, part-of-speech tagging, and dependency structure analysis.

[0824] "Tokenization" refers to the process of breaking down text into basic units such as words and phrases.

[0825] "Part-of-speech tagging" refers to the process of assigning each token its part of speech (noun, verb, adjective, etc.).

[0826] "Dependency analysis" refers to the process of analyzing the grammatical relationships between words in a sentence.

[0827] An "artificial intelligence model" refers to a model that learns from past data and specific training and generates appropriate answers to user questions.

[0828] "Answer generation means" refers to a means for generating answers based on a user's question using a trained artificial intelligence model.

[0829] "Database" refers to a data resource that stores data on immigration-related legal systems and procedures.

[0830] The "answer sending means" refers to a means for sending the generated answer to the user's terminal.

[0831] A "user's terminal" is a device on which a user inputs questions and checks answers, and includes smartphones, PCs, tablets, etc.

[0832] The present invention is a system that allows foreign residents in Japan to efficiently obtain information regarding their residence status in Japan. This system is implemented by having a user input a question, a server analyze the question, generate an appropriate answer, and return it to the user. How this system is implemented will be described in detail below.

[0833] System configuration

[0834] 1. User Device:

[0835] A user terminal is a device that allows a user to enter questions and check answers, and includes smartphones, PCs, tablets, etc.

[0836] Examples include smartphones (e.g., iPhone, Samsung Galaxy), PCs (e.g., Dell XPS, MacBook Pro), and tablets (e.g., iPad, Microsoft Surface).

[0837] 2. Server:

[0838] The server is the center of the system, receiving questions, analyzing them, generating answers, and sending them out.

[0839] The server can use a cloud-based system (e.g., Amazon Web Services, Google Cloud Platform).

[0840] 3. Interface means:

[0841] The interface means provides a GUI (Graphical User Interface) and a text box for the user to input a question.

[0842] For example, this includes forms and chatbot interfaces that run on a web browser.

[0843] 4. Natural Language Processing Engine:

[0844] The natural language processing engine runs on the server and analyzes questions submitted by users. The main processes include tokenization, part-of-speech tagging, and dependency structure analysis.

[0845] The software used includes natural language processing libraries such as NLTK and SpaCy.

[0846] 5. Trained artificial intelligence models:

[0847] The model is built using historical data and specific training to generate appropriate answers based on the question.

[0848] Specific examples include models such as GPT-3 and BERT.

[0849] 6. Database:

[0850] The database stores data on legal systems and procedures related to immigration status.

[0851] The databases used include relational database management systems (RDBMS) such as MySQL and PostgreSQL.

[0852] System operation example

[0853] For example, if a user types "How do I extend my visa?" the process is as follows:

[0854] 1. Users enter their questions using their smartphones, PCs, or tablets.

[0855] 2. The server receives the question and parses it using a natural language processing engine, which splits the question into tokens, tags it with parts of speech, and analyzes grammatical dependencies.

[0856] 3. The trained AI model retrieves the necessary information from the database based on the analysis results and generates an appropriate answer.

[0857] 4. The server generates a response and sends it to the user's device.

[0858] 5. The user checks the answers on the device and understands the necessary procedures.

[0859] In this way, the present invention is designed to enable foreign residents to efficiently obtain information regarding the complicated procedures for obtaining residence status, allowing users to quickly and accurately obtain the information they need.

[0860] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0861] Step 1:

[0862] The server receives the user's question through the interface means. The user accesses the interface using a terminal, inputs the question "How do I extend my visa?", and presses the send button. This input data is sent to the server by the interface means. The server receives this data and passes it on to the next processing step.

[0863] Step 2:

[0864] The server passes the question to the natural language processing engine for analysis. The input question is divided into tokens such as "visa," "extension," "how," "teach," and "please." Next, each token is tagged with a part of speech, and finally, grammatical dependencies are analyzed. This generates an analysis result, which is passed to the next step.

[0865] Step 3:

[0866] The server passes the analysis results to a trained AI model, which generates an answer based on the question. The analysis results, which are input data, are processed to generate a specific answer. Specifically, the analysis results act as a trigger, and the AI ​​model (e.g., GPT-3) generates an answer such as, "To apply for a visa extension, you must prepare application documents and submit them to the Immigration Bureau." This generated answer is passed to the next step.

[0867] Step 4:

[0868] The server sends the generated answer to the user's terminal. The answer, which is output data from the trained artificial intelligence model, is sent to the user's terminal as an HTTP response. The server converts the answer data into an appropriate format and sends it to the user's terminal via a transmission means.

[0869] Step 5:

[0870] The user checks the answer on their device. The user's device displays the received answer data, and the user checks it. Specifically, the answer is displayed on a web browser or application, and the user receives information such as, "To apply for a visa extension, you will need to prepare application documents and submit them to the Immigration Bureau."

[0871] This series of processing steps enables the user to efficiently and accurately obtain information regarding residence status.

[0872] (Application example 1)

[0873] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0874] Currently, it is difficult for foreigners living in Japan to efficiently obtain information regarding their Japanese residence status. Furthermore, there is no system that can respond to questions in real time when using autonomous vehicles. Furthermore, there is no established method for improving convenience using voice input and output. A new system is needed to solve these issues.

[0875] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0876] In this invention, the server includes an interface means for a user to input a question or command, a means for the server to receive the question or command sent from the user, a means for analyzing the question or command using a natural language processing engine, a means for generating a response based on the question or command using a trained artificial intelligence model, a means for transmitting the generated response to a display device in the user's terminal or in the vehicle, and a voice generation means for providing the generated response to the user through a voice output device. This enables foreigners residing in Japan to efficiently obtain information on their status of residence in real time even while riding in an autonomous vehicle.

[0877] An "interface means" is a device or software through which a user inputs questions or commands.

[0878] A "server" is a central processing unit that receives questions or commands sent by users, analyzes them, and generates responses.

[0879] A "natural language processing engine" is software that analyzes questions and commands from users and understands their intentions.

[0880] A "trained artificial intelligence model" is an algorithm that learns from large amounts of data to generate appropriate responses based on questions or commands.

[0881] A "user's terminal" is a device used by a user, such as a smartphone, tablet, or PC.

[0882] A "display device" is a screen device for visually displaying the generated responses.

[0883] A "voice generating means" is a device and software for providing the generated response to the user as voice.

[0884] "Database" means a system for storing information on legal systems and procedures related to immigration status.

[0885] This invention is a system that allows a user to input questions or commands related to Japanese residence status and obtain answers in real time within an autonomous vehicle. The system includes a server, a user terminal, a natural language processing engine, a trained artificial intelligence model, a display device, a voice generation means, and a database.

[0886] System configuration

[0887] 1. User Interface Means:

[0888] Users input questions using devices such as smartphones, tablets, and in-car displays.

[0889] Specifically, voice input can be used, for example, by using prompt sentences such as "Please tell me how to extend my visa."

[0890] 2. Server:

[0891] Use a cloud-based server, such as Amazon Web Services (AWS) or Microsoft Azure.

[0892] The server receives questions or commands from users and uses a natural language processing engine and generative AI models to analyze and generate answers.

[0893] 3. Natural Language Processing Engine:

[0894] The natural language processing engine uses Google Cloud Natural Language API and IBM Watson Natural Language Understanding.

[0895] The system processes user questions through tokenization, part-of-speech tagging, dependency structure analysis, and other processes to accurately analyze their intent.

[0896] 4. Trained artificial intelligence model:

[0897] AI models such as OpenAI's GPT-4 can be used.

[0898] Based on the analyzed questions, the necessary information is extracted from a database related to residence status and an appropriate answer is generated.

[0899] 5. Display devices and sound generating means:

[0900] The display device uses the screen on the user's terminal or in the car.

[0901] Voice generation uses the gTTS (Google Text-to-Speech) library and the voice output device installed in the vehicle.

[0902] The generated answers are converted into audio files and provided to the user.

[0903] 6. Database:

[0904] A database will be used to store information on immigration-related legal systems and procedures.

[0905] For example, this includes data provided by the Japanese Immigration Bureau and the Ministry of Justice.

[0906] Specific examples

[0907] Specifically, when a user uses the in-car display or voice input to type "How do I extend my visa?", the following happens:

[0908] 1. The user types or speaks a question using the in-car interface.

[0909] 2. The question is sent to the server and analyzed by a natural language processing engine.

[0910] 3. Based on the parsed question, a trained artificial intelligence model generates a response.

[0911] 4. The response is displayed on the user's terminal or on a display device in the vehicle.

[0912] 5. At the same time, the voice generating means converts the response into a voice file and provides it to the user audibly.

[0913] This system will enable foreigners in Japan to receive real-time answers to questions about their residence status while riding in an autonomous vehicle, and voice input and output functions will greatly improve convenience.

[0914] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0915] Step 1:

[0916] The user uses the in-car interface means to input or speak a question. The user may say a prompt, for example, "How do I extend my visa?" The input here is text or voice data. The output is the question data received by the interface means. The interface uses speech recognition software to convert the user's speech into text.

[0917] Step 2:

[0918] The terminal transmits the user's query data to the server, where the input is the query data received by the interface means and the output is the query data sent to the server. The network module of the terminal is responsible for this transfer.

[0919] Step 3:

[0920] The server receives the question data and analyzes it using a natural language processing engine. The natural language processing engine uses Google Cloud Natural Language API or IBM Watson. The input is the received question data, and the output is the analyzed data. This analysis includes tokenization, part-of-speech tagging, and dependency structure analysis.

[0921] Step 4:

[0922] The server passes the analyzed data to a trained artificial intelligence model to generate an appropriate response. The AI ​​model used here is OpenAI's GPT-4, etc. The input is the analyzed data, and the output is the generated response. The AI ​​model uses the analysis results to extract the necessary information from a database and generate a response.

[0923] Step 5:

[0924] The server sends the generated response to the user's terminal or to a display device in the car. The input is the generated response, and the output is the response displayed on the user's terminal. The communication protocol and interface used here use standard web server technology.

[0925] Step 6:

[0926] The server converts the generated response into an audio file using a speech generator, such as the gTTS (Google Text-to-Speech) library, or the car's audio output device. The input is the text data of the generated response, and the output is an audio file. This audio file is played through the car's speakers.

[0927] Step 7:

[0928] The user can see the response displayed on the terminal or hear the audio response from the car's speakers. This step effectively communicates the information provided to the user in real time. The input is the displayed or played response, and the output is the user's understanding and action.

[0929] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0930] This invention is a system that enables foreigners residing in Japan to efficiently obtain information regarding their Japanese residence status, and it also combines an emotion engine that recognizes the user's emotions and adjusts the quality and format of the answer. This system is realized by having the user input a question, and the server analyzes the question, generates an appropriate answer, and returns it to the user. Another objective is to improve the user experience by recognizing the user's emotions.

[0931] System configuration

[0932] The system includes the following major components:

[0933] 1. User device: A device on which a user enters questions and checks answers. This includes smartphones, PCs, tablets, etc.

[0934] 2. Server: The central part of the system, which receives questions, analyzes them, generates answers, and sends them. It also adjusts the answers based on the results of sentiment analysis by the sentiment engine.

[0935] 3. Interface: Provides a GUI (Graphical User Interface) and text boxes for users to enter questions. This interface incorporates an emotion engine to recognize the user's emotions.

[0936] 4. Natural language processing engine: Runs on the server and analyzes questions sent by users, performing processes such as tokenization, part-of-speech tagging, and dependency structure analysis.

[0937] 5. Trained AI model: This model is created using historical data and specific training to generate appropriate answers based on the question.

[0938] 6. Database: Data on immigration-related legal systems and procedures is stored. Access to this database allows the model to provide accurate information.

[0939] 7. Emotion Engine: An engine for recognizing emotions from user input. It can analyze emotions not only through text input, but also through voice input and facial recognition.

[0940] System Operation

[0941] First, a user accesses the system using a terminal and inputs a question using the interface means. For example, the user inputs, "Please tell me how to extend my visa." At this time, an emotion engine built into the interface means recognizes emotions from the user's text input.

[0942] Next, the server receives the question sent by the user. The received question is analyzed by a natural language processing engine. This analysis includes tokenization, part-of-speech tagging, and dependency structure analysis. At the same time, emotional information analyzed by an emotion engine is also sent to the server.

[0943] Once the analysis is complete, the server uses a trained artificial intelligence model to generate an answer based on the user's question. The model uses the analysis results to pull necessary information from a database to create an appropriate answer. Furthermore, based on the analysis results of the emotion engine, the format and content of the answer can be adjusted depending on the user's emotional state.

[0944] Finally, the server sends the generated answer to the user's device, where the user can confirm the answer displayed on the device and obtain the necessary procedures or information.

[0945] Specific examples

[0946] Example 1: When a user enters "How do I extend my visa?"

[0947] 1. The user enters a question on the device and presses the send button. At this time, the emotion engine recognizes emotions such as "impatience" or "anxiety" from the user's text.

[0948] 2. The server receives the question and analyzes it using the natural language processing engine. At the same time, it also receives the results of the emotion engine.

[0949] 3. The server uses a trained AI model to retrieve the necessary documents and procedures for visa extension from the database. Based on the results of the emotion engine, it adjusts the tone of the message to a calm and reassuring one: "Please stay calm. To extend your visa, you will need to prepare the application documents and submit them to the Immigration Bureau. For detailed procedures, please refer to the Immigration Bureau's official website."

[0950] 4. The server sends the generated response to the user's device.

[0951] 5. The user checks the answers on the device and understands the necessary procedures.

[0952] In this way, the present invention is designed to enable foreigners in Japan to efficiently obtain information on the complicated procedures for obtaining residence status. Furthermore, the emotion engine recognizes the user's emotions and provides information in an appropriate format, improving the user experience.

[0953] The processing flow will be explained below.

[0954] Step 1:

[0955] A user accesses the system using a terminal. The user opens a dedicated application or website.

[0956] Step 2:

[0957] The user uses the interface means to input a question, for example, "How do I extend my visa?" into the text box.

[0958] Step 3:

[0959] The user presses the send button to send the entered question to the server, at which point an emotion engine built into the interface means recognizes emotions from the user's text input.

[0960] Step 4:

[0961] The server receives questions sent by users and saves them in text format.

[0962] Step 5:

[0963] The server parses the received question using a natural language processing engine, which performs tokenization, part-of-speech tagging, and dependency structure analysis.

[0964] Step 6:

[0965] At the same time, the server receives emotion information analyzed by the emotion engine, which determines the user's emotion from the text content and expressions.

[0966] Step 7:

[0967] The server uses a trained artificial intelligence model to generate appropriate answers to questions based on the analysis, which pulls the necessary information from a database.

[0968] Step 8:

[0969] The server uses the emotion information from the emotion engine to adjust the format and content of the response depending on the user's emotional state. For example, if emotions such as "impatience" or "anxiety" are recognized, the response will be modified to a calmer, more reassuring tone.

[0970] Step 9:

[0971] The server then sends the generated answer to the user's device, which includes an expression that corresponds to the user's emotional state.

[0972] Step 10:

[0973] The user's terminal receives the response sent from the server and displays the received response on the screen.

[0974] Step 11:

[0975] The user checks the answers displayed on the device screen and understands the appropriate procedures and information. The answers include expressions that correspond to the user's emotional state, allowing the user to take the next action with greater confidence.

[0976] Examples:

[0977] 1. The user enters a question on the device and presses the send button. At this time, the emotion engine recognizes emotions such as "impatience" or "anxiety" from the user's text.

[0978] 2. The server receives the question and analyzes it using the natural language processing engine. At the same time, it also receives the results of the emotion engine.

[0979] 3. The server uses a trained AI model to retrieve the necessary documents and procedures for visa extension from the database. Based on the results of the emotion engine, it adjusts the tone of the message to a calm and reassuring one: "Please stay calm. To extend your visa, you will need to prepare the application documents and submit them to the Immigration Bureau. For detailed procedures, please refer to the Immigration Bureau's official website."

[0980] 4. The server sends the generated response to the user's device.

[0981] 5. The user checks the answers on the device and understands the necessary procedures.

[0982] Example 2

[0983] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0984] Conventional information acquisition systems made it difficult for foreigners in Japan to efficiently acquire information related to their Japanese residence status, and were also unable to respond in a way that took user feelings into consideration. As a result, the user experience did not improve and user satisfaction was low.

[0985] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an interface means for a user to input a question, a means for the server to receive the question sent from the user, a means for analyzing the question using a natural language processing engine, a means for generating an answer based on the question using a trained artificial intelligence model, a means for transmitting the generated answer to the user's terminal, a means for recognizing and analyzing the user's emotions using an emotion engine, and a means for adjusting the format and content of the answer based on the analysis result of the emotion engine. This not only enables foreigners residing in Japan to efficiently obtain information about their residence status, but also enables answers that take the user's emotions into consideration, improving the user experience.

[0986] A "user" is someone who uses this system to enter questions and receive answers.

[0987] "Terminal" refers to a device on which a user enters questions and checks answers, and specifically includes smartphones, PCs, tablets, etc.

[0988] An "interface means" is a means for providing a graphical user interface and a text box for a user to input a question.

[0989] The "server" is a central computer system that receives questions, analyzes them, generates answers, sends answers, recognizes and analyzes user emotions, and so on.

[0990] A "natural language processing engine" is an engine that analyzes questions sent by users, and performs tokenization, part-of-speech tagging, dependency structure analysis, etc.

[0991] A "trained artificial intelligence model" is an artificial intelligence model that is trained using historical data or specific training data to generate appropriate answers based on questions.

[0992] "Database" refers to a data store that stores data on legal systems and procedures related to immigration status, and which AI models access to extract the necessary information.

[0993] An "emotion engine" is an engine that recognizes and analyzes emotions from user input, and is capable of analyzing emotions not only through text input but also through voice input and facial recognition.

[0994] "Tokenization" is the process by which a natural language processing engine breaks text into basic units such as words and phrases.

[0995] "Part-of-speech tagging" is the process by which a natural language processing engine adds part-of-speech information (noun, verb, adjective, etc.) to each token.

[0996] "Dependency structure analysis" is a process in which a natural language processing engine analyzes the structure of a sentence and identifies the dependencies between words.

[0997] To implement this invention, the following elements are required: a user, a terminal, and a server. This system is realized by having the user input a question, and the server analyze the question, generate an answer, and send it back to the user's terminal. Furthermore, it combines an emotion engine that recognizes the user's emotions and adjusts the quality and format of the answer.

[0998] The devices used by users are smartphones, PCs, tablets, etc., and they access the system through these devices. As an interface, a GUI and text boxes are provided for users to enter questions.

[0999] The server is the central component of the system and performs the following functions:

[1000] 1. Receiving a question: Receives the question data sent by the user.

[1001] 2. Natural Language Processing: A natural language processing engine analyzes the question, including tokenization, part-of-speech tagging, and dependency structure analysis.

[1002] 3. Emotion recognition: The emotion engine recognizes emotions from the user's input and sends the analysis results to the server.

[1003] 4. Answer generation: A trained AI model generates answers based on the analyzed questions. This model accesses a database containing data on immigration-related legal systems and procedures.

[1004] 5. Response Adjustment: Adjust the quality and format of responses based on the sentiment engine analysis results.

[1005] 6. Sending the answer: Send the generated answer to the user's device.

[1006] The specific operation of this system will be explained below as an example.

[1007] Examples:

[1008] If the user types "How do I extend my visa?"

[1009] 1. The user enters a question using a terminal and presses the send button. At this time, the emotion engine recognizes emotions such as "impatience" or "anxiety" from the user's text.

[1010] 2. The server receives the question and begins analyzing it with the natural language processing engine. At the same time, it also receives the results of the emotion engine.

[1011] 3. The server uses a trained AI model to retrieve the necessary information for visa extension from the database. Based on the results of the emotion engine, it adjusts the tone of the message to a calm and reassuring one: "Please stay calm. To apply for a visa extension, you need to prepare the application documents and submit them to the Immigration Bureau. For detailed procedures, please refer to the Immigration Bureau's official website."

[1012] 4. The server sends the generated response to the user's device.

[1013] 5. The user checks the answers on the device and understands the necessary procedures.

[1014] This system not only enables foreigners living in Japan to efficiently obtain information about their residence status, but also uses an emotion engine to respond in a way that takes the user's emotions into consideration.

[1015] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1016] Step 1:

[1017] The user types a question into the terminal.

[1018] A user accesses the system using a terminal. They input a question through the interface means (GUI or text box) on the terminal. For example, the user inputs "How do I extend my visa?" In this step, the user's question text is obtained as input.

[1019] Step 2:

[1020] The emotion engine recognizes the user's emotions.

[1021] The question text entered on the device is immediately sent to the emotion engine. The emotion engine performs text analysis to recognize the user's emotions. In this process, the user's question text is used as input, and emotion data such as "impatience" or "anxiety" is obtained as output. For example, the emotion engine analyzes the emotion of "anxiety" from the user's text.

[1022] Step 3:

[1023] The server receives the query.

[1024] The user's question text is sent to the server along with the emotion data. The server prepares to process the received question text and emotion data. In this step, the question text and emotion data are obtained as input.

[1025] Step 4:

[1026] A natural language processing engine analyzes the question.

[1027] The server's natural language processing engine analyzes the question text. This analysis includes tokenization, part-of-speech tagging, and dependency structure analysis. The analysis results in structured text data. For example, the text is categorized by words such as "visa," "extension," and "method," and the context and dependencies are analyzed.

[1028] Step 5:

[1029] The server receives the analysis results of the emotion engine.

[1030] The server receives the emotion data sent from the emotion engine. The server then prepares a dataset containing the user's emotion information. The emotion data is input, and the emotion information is added to the dataset in the server as output.

[1031] Step 6:

[1032] A trained artificial intelligence model generates the answer.

[1033] The server inputs the analysis results of the natural language processing engine and sentiment data into a trained artificial intelligence model. The model then uses the analysis results of the question to retrieve appropriate information from a database and generate an answer. For example, this could include information about the specific procedures and necessary documents for visa extension. The generated answer text is then provided as output.

[1034] Step 7:

[1035] Tailor your answers based on the results of the sentiment engine.

[1036] The generated answer is adjusted based on the analysis results of the emotion engine. The server takes into account the user's emotions and changes the tone to be calm and reassuring. For example, it adds words like "please stay calm" based on the emotional information. The adjusted answer text is obtained as the output.

[1037] Step 8:

[1038] The server sends the response to the user's terminal.

[1039] The adjusted answer text is sent from the server to the user's terminal. The user's terminal receives and displays the answer. In this step, the adjusted answer text is the input, and the answer displayed on the terminal is the output.

[1040] Step 9:

[1041] The user checks the answer.

[1042] The user checks the answers displayed on the device, which helps them understand the necessary procedures and decide on their next course of action. Through the device interface, the user can view the answers and obtain the necessary information.

[1043] (Application example 2)

[1044] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1045] In modern society, when users access various information online, it is important to quickly obtain appropriate answers. Furthermore, when users are from different countries, differences in language and culture can make understanding and communication difficult. Food delivery services, in particular, are required to alleviate anxiety and impatience during the ordering process and provide smooth support. However, conventional information provision systems are unable to respond in a way that takes user emotions into consideration, which leaves the user experience unsatisfactory.

[1046] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1047] In this invention, the server includes an interface means for a user to input a question, a means for the server to receive the question sent from the user, a means for analyzing the question using a natural language processing engine, a means for generating an answer based on the question using a trained artificial intelligence model, a means for transmitting the generated answer to the user's terminal, and a means for recognizing the user's emotion using an emotion engine and adjusting the quality and format of the answer. This makes it possible to provide an appropriate answer according to the user's emotional state, thereby improving the user experience in food delivery services.

[1048] A "user" is an individual or entity that utilizes the system to enter questions and receive answers.

[1049] A "question" is a written or spoken input that a user makes through the interface to obtain the information or support they are seeking.

[1050] An "interface means" is a part of the system that allows a user to input a question, and includes a graphical user interface (GUI), a text box, a voice input device, and the like.

[1051] A "server" is a computer or network service that serves as the core of a system that receives questions, analyzes them, generates answers, and sends them.

[1052] A "natural language processing engine" is a collection of software that analyzes and understands the meaning of questions submitted by users.

[1053] A "trained artificial intelligence model" is a collection of algorithms that have been trained using past data and specific training to automatically perform specific tasks.

[1054] An "answer" is a written or spoken message such as information, instructions, or explanations that the system generates in response to a user's question.

[1055] An "emotion engine" is a set of software that recognizes and analyzes emotions from user input. It performs emotion analysis through text input, voice input, and facial recognition.

[1056] A "terminal" is a device that a user uses to access the system, enter questions, and check answers. This includes smartphones, PCs, tablets, etc.

[1057] "Tokenization" is the process of breaking down text into the smallest meaningful units, such as words or phrases.

[1058] "Part-of-speech tagging" is the process of identifying for each word in a text its part of speech (noun, verb, adjective, etc.).

[1059] Dependency analysis is the process of analyzing the relationships between words in a sentence to help understand its meaning.

[1060] This invention is a system that enables foreigners residing in Japan to efficiently obtain information regarding their Japanese residence status, and further combines it with an emotion engine that recognizes the user's emotions and adjusts the quality and format of responses. This system is particularly effective for services targeting multinational users, such as food delivery. The specific system configuration and operation are described below.

[1061] System configuration

[1062] The system includes the following major components:

[1063] 1. User Device:

[1064] A device that allows users to access the system, input questions using interface means, and check answers. This includes smartphones, PCs, tablets, etc.

[1065] 2. Server:

[1066] It is the central computer in the system that receives questions, analyzes them, generates answers, and sends the answers.

[1067] 3. Interface means:

[1068] It is the part of the system where users can enter questions, providing a graphical user interface (GUI) and text boxes, and also incorporating an emotion engine to recognize the user's emotions.

[1069] 4. Natural Language Processing Engine:

[1070] This software analyzes questions sent by users, performing processes such as tokenization, part-of-speech tagging, and dependency structure analysis.

[1071] 5. Trained artificial intelligence models:

[1072] It is a collection of algorithms that are created using historical data and specific training to generate appropriate answers based on questions.

[1073] 6. Database:

[1074] It stores data on immigration-related legal systems and procedures. Access to this database allows the model to provide accurate information.

[1075] 7. Emotion Engine:

[1076] This software recognizes and analyzes emotions from user input. It performs emotion analysis through text input, voice input, and facial recognition.

[1077] System Operation

[1078] First, a user accesses the system using a terminal and inputs a question using the interface means. For example, the user inputs, "Please tell me how to extend my visa." At this time, an emotion engine built into the interface means recognizes emotions from the user's text input.

[1079] Next, the server receives the question sent by the user. The received question is analyzed by a natural language processing engine. This analysis includes tokenization, part-of-speech tagging, and dependency structure analysis. At the same time, emotional information analyzed by an emotion engine is also sent to the server.

[1080] Once the analysis is complete, the server uses a trained artificial intelligence model to generate an answer based on the user's question. The model uses the analysis results to pull necessary information from a database to create an appropriate answer. Furthermore, based on the analysis results of the emotion engine, the format and content of the answer can be adjusted depending on the user's emotional state.

[1081] Finally, the server sends the generated answer to the user's device, where the user can confirm the answer displayed on the device and obtain the necessary procedures or information.

[1082] Usage example

[1083] If a user types "How do I extend my visa?", the system will act as follows:

[1084] 1. The user enters a question on the device and presses the send button. At this time, the emotion engine recognizes emotions such as "impatience" or "anxiety" from the user's text.

[1085] 2. The server receives the question and analyzes it using the natural language processing engine. At the same time, it also receives the results of the emotion engine.

[1086] 3. The server uses a trained AI model to retrieve the necessary documents and procedures for visa extension from the database. Based on the results of the emotion engine, it adjusts the tone of the message to a calm and reassuring one: "Please stay calm. To extend your visa, you will need to prepare the application documents and submit them to the Immigration Bureau. For detailed procedures, please refer to the Immigration Bureau's official website."

[1087] 4. The server sends the generated response to the user's device.

[1088] 5. The user can check the answers on the device and understand the necessary procedures.

[1089] An example of a prompt sentence is, "Please tell me how to extend my visa."

[1090] The system as a whole is designed to enable users to efficiently obtain information about complex immigration procedures. The emotion engine also recognizes the user's emotions and provides information in an appropriate format, improving the user experience.

[1091] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1092] Step 1:

[1093] A user accesses the system using a terminal and inputs a question using the interface means.

[1094] Input: The user enters the text "How do I extend my visa?" into the interface means.

[1095] Output: Text data is sent from the user's terminal to the system.

[1096] Specific operation: The user enters a question in the text box of the terminal and clicks the send button. At this time, the emotion engine built into the interface means analyzes the emotion from the user's text input.

[1097] Step 2:

[1098] The server receives a question sent by a user.

[1099] Input: Text data sent from the user's terminal.

[1100] Output: Text data received in the server.

[1101] Specific operation: The server receives the text data sent from the user's terminal, along with the analysis results of the emotion engine.

[1102] Step 3:

[1103] The server uses a natural language processing engine to parse the question.

[1104] Input: Text data stored on the server.

[1105] Output: Parsed question tokens, parts of speech, and dependency structure data.

[1106] Specific operation: The natural language processing engine performs tokenization, part-of-speech tagging, and dependency structure analysis on the text data to generate analysis results.

[1107] Step 4:

[1108] The server uses a trained artificial intelligence model to generate answers based on the questions.

[1109] Input: Parsed question data and sentiment engine results.

[1110] Output: The generated answer text.

[1111] How it works: The AI ​​model retrieves the necessary information from the database based on the analysis results and generates an appropriate answer. The quality and format of the answer are adjusted based on the results of the emotion engine.

[1112] Step 5:

[1113] The server sends the generated answer to the user's terminal.

[1114] Input: The generated answer text.

[1115] Output: The answer text that is displayed on the user's terminal.

[1116] Specific operation: The server sends the generated answer text to the user's terminal, where the user can check the answer and understand the necessary procedures.

[1117] Step 6:

[1118] The user checks the answer on the device.

[1119] Input: The answer text sent by the server.

[1120] Output: User understanding and next actions.

[1121] Specific operation: The user checks the answers displayed on the device screen and understands the necessary information and procedures. If the information is insufficient, the user can enter a new question.

[1122] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1123] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1124] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1125] [Fourth embodiment]

[1126] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1127] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1128] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1129] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1130] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1131] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1132] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1133] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1134] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1135] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1136] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1137] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1138] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1139] This invention is a system for foreigners in Japan to efficiently obtain information regarding their residence status in Japan. This system is implemented by having a user input a question, a server analyze the question, generate an appropriate answer, and return it to the user.

[1140] System configuration

[1141] The system includes the following major components:

[1142] 1. User device: A device on which a user enters questions and checks answers. This includes smartphones, PCs, tablets, etc.

[1143] 2. Server: The central part of the system, which receives questions, analyzes them, generates answers, and sends them.

[1144] 3. Interface means: Provides a GUI (graphical user interface) and text boxes for users to enter questions.

[1145] 4. Natural language processing engine: Runs on the server and analyzes questions sent by users, performing processes such as tokenization, part-of-speech tagging, and dependency structure analysis.

[1146] 5. Trained AI model: This model is created using historical data and specific training to generate appropriate answers based on the question.

[1147] 6. Database: Data on immigration-related legal systems and procedures is stored. Access to this database allows the model to provide accurate information.

[1148] System Operation

[1149] First, a user accesses the system using a terminal and inputs a question using the interface means, for example, "How do I extend my visa?"

[1150] The server then receives the user-submitted question, which is then analyzed by a natural language processing engine, including tokenization, part-of-speech tagging, and dependency structure analysis.

[1151] Once the analysis is complete, the server uses a trained artificial intelligence model to generate an answer based on the user's question, which then uses the analysis results to pull the necessary information from a database to create the appropriate answer.

[1152] Finally, the server sends the generated answer to the user's device, where the user can confirm the answer displayed on the device and obtain the necessary procedures or information.

[1153] Specific examples

[1154] Example 1: When a user enters "How do I extend my visa?"

[1155] 1. The user enters a question into the terminal and presses the send button.

[1156] 2. The server receives the question and analyzes it using a natural language processing engine.

[1157] 3. The server uses a trained artificial intelligence model to retrieve the necessary documents and procedures for visa extension from the database.

[1158] 4. The server generates a response saying, "To extend your visa, you need to prepare application documents and submit them to the Immigration Bureau. For detailed procedures, please refer to the official website of the Immigration Bureau."

[1159] 5. The server sends the generated response to the user's device.

[1160] 6. The user checks the answers on the device and understands the necessary procedures.

[1161] In this way, the present invention is designed to enable foreigners in Japan to efficiently obtain information regarding the complicated procedures for obtaining residence status.

[1162] The processing flow will be explained below.

[1163] Step 1:

[1164] A user accesses the system using a terminal. The user opens a dedicated application or website.

[1165] Step 2:

[1166] The user uses the interface means to input a question, for example, "How do I extend my visa?" into the text box.

[1167] Step 3:

[1168] The user presses the send button to send the entered question to the server.

[1169] Step 4:

[1170] The server receives questions sent by users and saves them in text format.

[1171] Step 5:

[1172] The server uses a natural language processing engine to parse the received question, which includes tokenization, part-of-speech tagging, and dependency structure analysis.

[1173] Step 6:

[1174] The server uses a trained artificial intelligence model to generate appropriate answers to questions based on the analysis, which pulls the necessary information from a database.

[1175] Step 7:

[1176] The server uses a response sending means to send the generated response back to the user.

[1177] Step 8:

[1178] The user's terminal receives the response sent from the server and displays the received response on the screen.

[1179] Step 9:

[1180] The user checks the answers displayed on the device screen and understands the appropriate procedures and information.

[1181] These are the processing steps for the entire system.

[1182] Example 1

[1183] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1184] Foreigners living in Japan face the challenge of efficiently obtaining information about their residence status. In particular, there are limited ways to quickly obtain accurate information about the complex legal system and procedures, which can easily lead to misunderstandings and delays in procedures.

[1185] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1186] In this invention, the server includes an interface means for a user to input a question, a means for the server to receive the question sent from the user, a means for analyzing the question using a natural language processing engine, a means for generating an answer based on the question using a trained artificial intelligence model, a means for transmitting the generated answer to the user's terminal, and a means for the user to confirm the generated answer, thereby enabling the user to efficiently and accurately obtain information regarding residence status.

[1187] "User" refers to a person who uses the system to enter questions and receive answers.

[1188] "Interface means" refers to means that provides a graphical user interface and text boxes for a user to input a question.

[1189] "Server" refers to a central computer system that receives questions from users, analyzes and generates answers, and sends the answers to users.

[1190] A "natural language processing engine" is software that analyzes questions submitted by users, performing functions such as tokenization, part-of-speech tagging, and dependency structure analysis.

[1191] "Tokenization" refers to the process of breaking down text into basic units such as words and phrases.

[1192] "Part-of-speech tagging" refers to the process of assigning each token its part of speech (noun, verb, adjective, etc.).

[1193] "Dependency analysis" refers to the process of analyzing the grammatical relationships between words in a sentence.

[1194] An "artificial intelligence model" refers to a model that learns from past data and specific training and generates appropriate answers to user questions.

[1195] "Answer generation means" refers to a means for generating answers based on a user's question using a trained artificial intelligence model.

[1196] "Database" refers to a data resource that stores data on immigration-related legal systems and procedures.

[1197] The "answer sending means" refers to a means for sending the generated answer to the user's terminal.

[1198] A "user's terminal" is a device on which a user inputs questions and checks answers, and includes smartphones, PCs, tablets, etc.

[1199] The present invention is a system that allows foreign residents in Japan to efficiently obtain information regarding their residence status in Japan. This system is implemented by having a user input a question, a server analyze the question, generate an appropriate answer, and return it to the user. How this system is implemented will be described in detail below.

[1200] System configuration

[1201] 1. User Device:

[1202] A user terminal is a device that allows a user to enter questions and check answers, and includes smartphones, PCs, tablets, etc.

[1203] Examples include smartphones (e.g., iPhone, Samsung Galaxy), PCs (e.g., Dell XPS, MacBook Pro), and tablets (e.g., iPad, Microsoft Surface).

[1204] 2. Server:

[1205] The server is the center of the system, receiving questions, analyzing them, generating answers, and sending them out.

[1206] The server can use a cloud-based system (e.g., Amazon Web Services, Google Cloud Platform).

[1207] 3. Interface means:

[1208] The interface means provides a GUI (Graphical User Interface) and a text box for the user to input a question.

[1209] For example, this includes forms and chatbot interfaces that run on a web browser.

[1210] 4. Natural Language Processing Engine:

[1211] The natural language processing engine runs on the server and analyzes questions submitted by users. The main processes include tokenization, part-of-speech tagging, and dependency structure analysis.

[1212] The software used includes natural language processing libraries such as NLTK and SpaCy.

[1213] 5. Trained artificial intelligence models:

[1214] The model is built using historical data and specific training to generate appropriate answers based on the question.

[1215] Specific examples include models such as GPT-3 and BERT.

[1216] 6. Database:

[1217] The database stores data on legal systems and procedures related to immigration status.

[1218] The databases used include relational database management systems (RDBMS) such as MySQL and PostgreSQL.

[1219] System operation example

[1220] For example, if a user types "How do I extend my visa?" the process is as follows:

[1221] 1. Users enter their questions using their smartphones, PCs, or tablets.

[1222] 2. The server receives the question and parses it using a natural language processing engine, which splits the question into tokens, tags it with parts of speech, and analyzes grammatical dependencies.

[1223] 3. The trained AI model retrieves the necessary information from the database based on the analysis results and generates an appropriate answer.

[1224] 4. The server generates a response and sends it to the user's device.

[1225] 5. The user checks the answers on the device and understands the necessary procedures.

[1226] In this way, the present invention is designed to enable foreign residents to efficiently obtain information regarding the complicated procedures for obtaining residence status, allowing users to quickly and accurately obtain the information they need.

[1227] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1228] Step 1:

[1229] The server receives the user's question through the interface means. The user accesses the interface using a terminal, inputs the question "How do I extend my visa?", and presses the send button. This input data is sent to the server by the interface means. The server receives this data and passes it on to the next processing step.

[1230] Step 2:

[1231] The server passes the question to the natural language processing engine for analysis. The input question is divided into tokens such as "visa," "extension," "how," "teach," and "please." Next, each token is tagged with a part of speech, and finally, grammatical dependencies are analyzed. This generates an analysis result, which is passed to the next step.

[1232] Step 3:

[1233] The server passes the analysis results to a trained AI model, which generates an answer based on the question. The analysis results, which are input data, are processed to generate a specific answer. Specifically, the analysis results act as a trigger, and the AI ​​model (e.g., GPT-3) generates an answer such as, "To apply for a visa extension, you must prepare application documents and submit them to the Immigration Bureau." This generated answer is passed to the next step.

[1234] Step 4:

[1235] The server sends the generated answer to the user's terminal. The answer, which is output data from the trained artificial intelligence model, is sent to the user's terminal as an HTTP response. The server converts the answer data into an appropriate format and sends it to the user's terminal via a transmission means.

[1236] Step 5:

[1237] The user checks the answer on their device. The user's device displays the received answer data, and the user checks it. Specifically, the answer is displayed on a web browser or application, and the user receives information such as, "To apply for a visa extension, you will need to prepare application documents and submit them to the Immigration Bureau."

[1238] This series of processing steps enables the user to efficiently and accurately obtain information regarding residence status.

[1239] (Application example 1)

[1240] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1241] Currently, it is difficult for foreigners living in Japan to efficiently obtain information regarding their Japanese residence status. Furthermore, there is no system that can respond to questions in real time when using autonomous vehicles. Furthermore, there is no established method for improving convenience using voice input and output. A new system is needed to solve these issues.

[1242] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1243] In this invention, the server includes an interface means for a user to input a question or command, a means for the server to receive the question or command sent from the user, a means for analyzing the question or command using a natural language processing engine, a means for generating a response based on the question or command using a trained artificial intelligence model, a means for transmitting the generated response to a display device in the user's terminal or in the vehicle, and a voice generation means for providing the generated response to the user through a voice output device. This enables foreigners residing in Japan to efficiently obtain information on their status of residence in real time even while riding in an autonomous vehicle.

[1244] An "interface means" is a device or software through which a user inputs questions or commands.

[1245] A "server" is a central processing unit that receives questions or commands sent by users, analyzes them, and generates responses.

[1246] A "natural language processing engine" is software that analyzes questions and commands from users and understands their intentions.

[1247] A "trained artificial intelligence model" is an algorithm that learns from large amounts of data to generate appropriate responses based on questions or commands.

[1248] A "user's terminal" is a device used by a user, such as a smartphone, tablet, or PC.

[1249] A "display device" is a screen device for visually displaying the generated responses.

[1250] A "voice generating means" is a device and software for providing the generated response to the user as voice.

[1251] "Database" means a system for storing information on legal systems and procedures related to immigration status.

[1252] This invention is a system that allows a user to input questions or commands related to Japanese residence status and obtain answers in real time within an autonomous vehicle. The system includes a server, a user terminal, a natural language processing engine, a trained artificial intelligence model, a display device, a voice generation means, and a database.

[1253] System configuration

[1254] 1. User Interface Means:

[1255] Users input questions using devices such as smartphones, tablets, and in-car displays.

[1256] Specifically, voice input can be used, for example, by using prompt sentences such as "Please tell me how to extend my visa."

[1257] 2. Server:

[1258] Use a cloud-based server, such as Amazon Web Services (AWS) or Microsoft Azure.

[1259] The server receives questions or commands from users and uses a natural language processing engine and generative AI models to analyze and generate answers.

[1260] 3. Natural Language Processing Engine:

[1261] The natural language processing engine uses Google Cloud Natural Language API and IBM Watson Natural Language Understanding.

[1262] The system processes user questions through tokenization, part-of-speech tagging, dependency structure analysis, and other processes to accurately analyze their intent.

[1263] 4. Trained artificial intelligence model:

[1264] AI models such as OpenAI's GPT-4 can be used.

[1265] Based on the analyzed questions, the necessary information is extracted from a database related to residence status and an appropriate answer is generated.

[1266] 5. Display devices and sound generating means:

[1267] The display device uses the screen on the user's terminal or in the car.

[1268] Voice generation uses the gTTS (Google Text-to-Speech) library and the voice output device installed in the vehicle.

[1269] The generated answers are converted into audio files and provided to the user.

[1270] 6. Database:

[1271] A database will be used to store information on immigration-related legal systems and procedures.

[1272] For example, this includes data provided by the Japanese Immigration Bureau and the Ministry of Justice.

[1273] Specific examples

[1274] Specifically, when a user uses the in-car display or voice input to type "How do I extend my visa?", the following happens:

[1275] 1. The user types or speaks a question using the in-car interface.

[1276] 2. The question is sent to the server and analyzed by a natural language processing engine.

[1277] 3. Based on the parsed question, a trained artificial intelligence model generates a response.

[1278] 4. The response is displayed on the user's terminal or on a display device in the vehicle.

[1279] 5. At the same time, the voice generating means converts the response into a voice file and provides it to the user audibly.

[1280] This system will enable foreigners in Japan to receive real-time answers to questions about their residence status while riding in an autonomous vehicle, and voice input and output functions will greatly improve convenience.

[1281] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1282] Step 1:

[1283] The user uses the in-car interface means to input or speak a question. The user may say a prompt, for example, "How do I extend my visa?" The input here is text or voice data. The output is the question data received by the interface means. The interface uses speech recognition software to convert the user's speech into text.

[1284] Step 2:

[1285] The terminal transmits the user's query data to the server, where the input is the query data received by the interface means and the output is the query data sent to the server. The network module of the terminal is responsible for this transfer.

[1286] Step 3:

[1287] The server receives the question data and analyzes it using a natural language processing engine. The natural language processing engine uses Google Cloud Natural Language API or IBM Watson. The input is the received question data, and the output is the analyzed data. This analysis includes tokenization, part-of-speech tagging, and dependency structure analysis.

[1288] Step 4:

[1289] The server passes the analyzed data to a trained artificial intelligence model to generate an appropriate response. The AI ​​model used here is OpenAI's GPT-4, etc. The input is the analyzed data, and the output is the generated response. The AI ​​model uses the analysis results to extract the necessary information from a database and generate a response.

[1290] Step 5:

[1291] The server sends the generated response to the user's terminal or to a display device in the car. The input is the generated response, and the output is the response displayed on the user's terminal. The communication protocol and interface used here use standard web server technology.

[1292] Step 6:

[1293] The server converts the generated response into an audio file using a speech generator, such as the gTTS (Google Text-to-Speech) library, or the car's audio output device. The input is the text data of the generated response, and the output is an audio file. This audio file is played through the car's speakers.

[1294] Step 7:

[1295] The user can see the response displayed on the terminal or hear the audio response from the car's speakers. This step effectively communicates the information provided to the user in real time. The input is the displayed or played response, and the output is the user's understanding and action.

[1296] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1297] This invention is a system that enables foreigners residing in Japan to efficiently obtain information regarding their Japanese residence status, and it also combines an emotion engine that recognizes the user's emotions and adjusts the quality and format of the answer. This system is realized by having the user input a question, and the server analyzes the question, generates an appropriate answer, and returns it to the user. Another objective is to improve the user experience by recognizing the user's emotions.

[1298] System configuration

[1299] The system includes the following major components:

[1300] 1. User device: A device on which a user enters questions and checks answers. This includes smartphones, PCs, tablets, etc.

[1301] 2. Server: The central part of the system, which receives questions, analyzes them, generates answers, and sends them. It also adjusts the answers based on the results of sentiment analysis by the sentiment engine.

[1302] 3. Interface: Provides a GUI (Graphical User Interface) and text boxes for users to enter questions. This interface incorporates an emotion engine to recognize the user's emotions.

[1303] 4. Natural language processing engine: Runs on the server and analyzes questions sent by users, performing processes such as tokenization, part-of-speech tagging, and dependency structure analysis.

[1304] 5. Trained AI model: This model is created using historical data and specific training to generate appropriate answers based on the question.

[1305] 6. Database: Data on immigration-related legal systems and procedures is stored. Access to this database allows the model to provide accurate information.

[1306] 7. Emotion Engine: An engine for recognizing emotions from user input. It can analyze emotions not only through text input, but also through voice input and facial recognition.

[1307] System Operation

[1308] First, a user accesses the system using a terminal and inputs a question using the interface means. For example, the user inputs, "Please tell me how to extend my visa." At this time, an emotion engine built into the interface means recognizes emotions from the user's text input.

[1309] Next, the server receives the question sent by the user. The received question is analyzed by a natural language processing engine. This analysis includes tokenization, part-of-speech tagging, and dependency structure analysis. At the same time, emotional information analyzed by an emotion engine is also sent to the server.

[1310] Once the analysis is complete, the server uses a trained artificial intelligence model to generate an answer based on the user's question. The model uses the analysis results to pull necessary information from a database to create an appropriate answer. Furthermore, based on the analysis results of the emotion engine, the format and content of the answer can be adjusted depending on the user's emotional state.

[1311] Finally, the server sends the generated answer to the user's device, where the user can confirm the answer displayed on the device and obtain the necessary procedures or information.

[1312] Specific examples

[1313] Example 1: When a user enters "How do I extend my visa?"

[1314] 1. The user enters a question on the device and presses the send button. At this time, the emotion engine recognizes emotions such as "impatience" or "anxiety" from the user's text.

[1315] 2. The server receives the question and analyzes it using the natural language processing engine. At the same time, it also receives the results of the emotion engine.

[1316] 3. The server uses a trained AI model to retrieve the necessary documents and procedures for visa extension from the database. Based on the results of the emotion engine, it adjusts the tone of the message to a calm and reassuring one: "Please stay calm. To extend your visa, you will need to prepare the application documents and submit them to the Immigration Bureau. For detailed procedures, please refer to the Immigration Bureau's official website."

[1317] 4. The server sends the generated response to the user's device.

[1318] 5. The user checks the answers on the device and understands the necessary procedures.

[1319] In this way, the present invention is designed to enable foreigners in Japan to efficiently obtain information on the complicated procedures for obtaining residence status. Furthermore, the emotion engine recognizes the user's emotions and provides information in an appropriate format, improving the user experience.

[1320] The processing flow will be explained below.

[1321] Step 1:

[1322] A user accesses the system using a terminal. The user opens a dedicated application or website.

[1323] Step 2:

[1324] The user uses the interface means to input a question, for example, "How do I extend my visa?" into the text box.

[1325] Step 3:

[1326] The user presses the send button to send the entered question to the server, at which point an emotion engine built into the interface means recognizes emotions from the user's text input.

[1327] Step 4:

[1328] The server receives questions sent by users and saves them in text format.

[1329] Step 5:

[1330] The server parses the received question using a natural language processing engine, which performs tokenization, part-of-speech tagging, and dependency structure analysis.

[1331] Step 6:

[1332] At the same time, the server receives emotion information analyzed by the emotion engine, which determines the user's emotion from the text content and expressions.

[1333] Step 7:

[1334] The server uses a trained artificial intelligence model to generate appropriate answers to questions based on the analysis, which pulls the necessary information from a database.

[1335] Step 8:

[1336] The server uses the emotion information from the emotion engine to adjust the format and content of the response depending on the user's emotional state. For example, if emotions such as "impatience" or "anxiety" are recognized, the response will be modified to a calmer, more reassuring tone.

[1337] Step 9:

[1338] The server then sends the generated answer to the user's device, which includes an expression that corresponds to the user's emotional state.

[1339] Step 10:

[1340] The user's terminal receives the response sent from the server and displays the received response on the screen.

[1341] Step 11:

[1342] The user checks the answers displayed on the device screen and understands the appropriate procedures and information. The answers include expressions that correspond to the user's emotional state, allowing the user to take the next action with greater confidence.

[1343] Examples:

[1344] 1. The user enters a question on the device and presses the send button. At this time, the emotion engine recognizes emotions such as "impatience" or "anxiety" from the user's text.

[1345] 2. The server receives the question and analyzes it using the natural language processing engine. At the same time, it also receives the results of the emotion engine.

[1346] 3. The server uses a trained AI model to retrieve the necessary documents and procedures for visa extension from the database. Based on the results of the emotion engine, it adjusts the tone of the message to a calm and reassuring one: "Please stay calm. To extend your visa, you will need to prepare the application documents and submit them to the Immigration Bureau. For detailed procedures, please refer to the Immigration Bureau's official website."

[1347] 4. The server sends the generated response to the user's device.

[1348] 5. The user checks the answers on the device and understands the necessary procedures.

[1349] Example 2

[1350] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1351] Conventional information acquisition systems made it difficult for foreigners in Japan to efficiently acquire information about their Japanese residence status, and were unable to respond in a way that took user feelings into consideration. As a result, the user experience did not improve and user satisfaction was low.

[1352] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an interface means for a user to input a question, a means for the server to receive the question sent from the user, a means for analyzing the question using a natural language processing engine, a means for generating an answer based on the question using a trained artificial intelligence model, a means for transmitting the generated answer to the user's terminal, a means for recognizing and analyzing the user's emotions using an emotion engine, and a means for adjusting the format and content of the answer based on the analysis result of the emotion engine. This not only enables foreigners residing in Japan to efficiently obtain information about their residence status, but also enables answers that take the user's emotions into consideration, improving the user experience.

[1353] A "user" is someone who uses this system to enter questions and receive answers.

[1354] "Terminal" refers to a device on which a user enters questions and checks answers, and specifically includes smartphones, PCs, tablets, etc.

[1355] An "interface means" is a means for providing a graphical user interface and a text box for a user to input a question.

[1356] The "server" is a central computer system that receives questions, analyzes them, generates answers, sends answers, recognizes and analyzes user emotions, and so on.

[1357] A "natural language processing engine" is an engine that analyzes questions sent by users, and performs tokenization, part-of-speech tagging, dependency structure analysis, etc.

[1358] A "trained artificial intelligence model" is an artificial intelligence model that is trained using historical data or specific training data to generate appropriate answers based on questions.

[1359] "Database" refers to a data store that stores data on legal systems and procedures related to immigration status, and which AI models access to extract the necessary information.

[1360] An "emotion engine" is an engine that recognizes and analyzes emotions from user input, and is capable of analyzing emotions not only through text input but also through voice input and facial recognition.

[1361] "Tokenization" is the process by which a natural language processing engine breaks text into basic units such as words and phrases.

[1362] "Part-of-speech tagging" is the process by which a natural language processing engine adds part-of-speech information (noun, verb, adjective, etc.) to each token.

[1363] "Dependency structure analysis" is a process in which a natural language processing engine analyzes the structure of a sentence and identifies the dependencies between words.

[1364] To implement this invention, the following elements are required: a user, a terminal, and a server. This system is realized by having the user input a question, and the server analyze the question, generate an answer, and send it back to the user's terminal. Furthermore, it combines an emotion engine that recognizes the user's emotions and adjusts the quality and format of the answer.

[1365] The devices used by users are smartphones, PCs, tablets, etc., and they access the system through these devices. As an interface, a GUI and text boxes are provided for users to enter questions.

[1366] The server is the central component of the system and performs the following functions:

[1367] 1. Receiving a question: Receives the question data sent by the user.

[1368] 2. Natural Language Processing: A natural language processing engine analyzes the question, including tokenization, part-of-speech tagging, and dependency structure analysis.

[1369] 3. Emotion recognition: The emotion engine recognizes emotions from the user's input and sends the analysis results to the server.

[1370] 4. Answer generation: A trained AI model generates answers based on the analyzed questions. This model accesses a database containing data on immigration-related legal systems and procedures.

[1371] 5. Response Adjustment: Adjust the quality and format of responses based on the sentiment engine analysis results.

[1372] 6. Sending the answer: Send the generated answer to the user's device.

[1373] The specific operation of this system will be explained below as an example.

[1374] Examples:

[1375] If the user types "How do I extend my visa?"

[1376] 1. The user enters a question using a terminal and presses the send button. At this time, the emotion engine recognizes emotions such as "impatience" or "anxiety" from the user's text.

[1377] 2. The server receives the question and begins analyzing it with the natural language processing engine. At the same time, it also receives the results of the emotion engine.

[1378] 3. The server uses a trained AI model to retrieve the necessary information for visa extension from the database. Based on the results of the emotion engine, it adjusts the tone of the message to a calm and reassuring one: "Please stay calm. To apply for a visa extension, you need to prepare the application documents and submit them to the Immigration Bureau. For detailed procedures, please refer to the Immigration Bureau's official website."

[1379] 4. The server sends the generated response to the user's device.

[1380] 5. The user checks the answers on the device and understands the necessary procedures.

[1381] This system not only enables foreigners living in Japan to efficiently obtain information about their residence status, but also uses an emotion engine to respond in a way that takes the user's emotions into consideration.

[1382] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1383] Step 1:

[1384] The user types a question into the terminal.

[1385] A user accesses the system using a terminal. They input a question through the interface means (GUI or text box) on the terminal. For example, the user inputs "How do I extend my visa?" In this step, the user's question text is obtained as input.

[1386] Step 2:

[1387] The emotion engine recognizes the user's emotions.

[1388] The question text entered on the device is immediately sent to the emotion engine. The emotion engine performs text analysis to recognize the user's emotions. In this process, the user's question text is used as input, and emotion data such as "impatience" or "anxiety" is obtained as output. For example, the emotion engine analyzes the emotion of "anxiety" from the user's text.

[1389] Step 3:

[1390] The server receives the query.

[1391] The user's question text is sent to the server along with the emotion data. The server prepares to process the received question text and emotion data. In this step, the question text and emotion data are obtained as input.

[1392] Step 4:

[1393] A natural language processing engine analyzes the question.

[1394] The server's natural language processing engine analyzes the question text. This analysis includes tokenization, part-of-speech tagging, and dependency structure analysis. The analysis results in structured text data. For example, the text is categorized by words such as "visa," "extension," and "method," and the context and dependencies are analyzed.

[1395] Step 5:

[1396] The server receives the analysis results of the emotion engine.

[1397] The server receives the emotion data sent from the emotion engine. The server then prepares a dataset containing the user's emotion information. The emotion data is input, and the emotion information is added to the dataset in the server as output.

[1398] Step 6:

[1399] A trained artificial intelligence model generates the answer.

[1400] The server inputs the analysis results of the natural language processing engine and sentiment data into a trained artificial intelligence model. The model then uses the analysis results of the question to retrieve appropriate information from a database and generate an answer. For example, this could include information about the specific procedures and necessary documents for visa extension. The generated answer text is then provided as output.

[1401] Step 7:

[1402] Tailor your answers based on the results of the sentiment engine.

[1403] The generated answer is adjusted based on the analysis results of the emotion engine. The server takes into account the user's emotions and changes the tone to be calm and reassuring. For example, it adds words like "please stay calm" based on the emotional information. The adjusted answer text is obtained as the output.

[1404] Step 8:

[1405] The server sends the response to the user's terminal.

[1406] The adjusted answer text is sent from the server to the user's terminal. The user's terminal receives and displays the answer. In this step, the adjusted answer text is the input, and the answer displayed on the terminal is the output.

[1407] Step 9:

[1408] The user checks the answer.

[1409] The user checks the answers displayed on the device, which helps them understand the necessary procedures and decide on their next course of action. Through the device interface, the user can view the answers and obtain the necessary information.

[1410] (Application example 2)

[1411] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1412] In modern society, when users access various information online, it is important to quickly obtain appropriate answers. Furthermore, when users are from different countries, differences in language and culture can make understanding and communication difficult. Food delivery services, in particular, are required to alleviate anxiety and impatience during the ordering process and provide smooth support. However, conventional information provision systems are unable to respond in a way that takes user emotions into consideration, which leaves the user experience unsatisfactory.

[1413] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1414] In this invention, the server includes an interface means for a user to input a question, a means for the server to receive the question sent from the user, a means for analyzing the question using a natural language processing engine, a means for generating an answer based on the question using a trained artificial intelligence model, a means for transmitting the generated answer to the user's terminal, and a means for recognizing the user's emotion using an emotion engine and adjusting the quality and format of the answer. This makes it possible to provide an appropriate answer according to the user's emotional state, thereby improving the user experience in food delivery services.

[1415] A "user" is an individual or entity that utilizes the system to enter questions and receive answers.

[1416] A "question" is a written or spoken input that a user makes through the interface to obtain the information or support they are seeking.

[1417] An "interface means" is a part of the system that allows a user to input a question, and includes a graphical user interface (GUI), a text box, a voice input device, and the like.

[1418] A "server" is a computer or network service that serves as the core of a system that receives questions, analyzes them, generates answers, and sends them.

[1419] A "natural language processing engine" is a collection of software that analyzes and understands the meaning of questions submitted by users.

[1420] A "trained artificial intelligence model" is a collection of algorithms that have been trained using past data and specific training to automatically perform specific tasks.

[1421] An "answer" is a written or spoken message such as information, instructions, or explanations that the system generates in response to a user's question.

[1422] An "emotion engine" is a set of software that recognizes and analyzes emotions from user input. It performs emotion analysis through text input, voice input, and facial recognition.

[1423] A "terminal" is a device that a user uses to access the system, enter questions, and check answers. This includes smartphones, PCs, tablets, etc.

[1424] "Tokenization" is the process of breaking down text into the smallest meaningful units, such as words or phrases.

[1425] "Part-of-speech tagging" is the process of identifying for each word in a text its part of speech (noun, verb, adjective, etc.).

[1426] Dependency analysis is the process of analyzing the relationships between words in a sentence to help understand its meaning.

[1427] This invention is a system that enables foreigners residing in Japan to efficiently obtain information regarding their Japanese residence status, and further combines it with an emotion engine that recognizes the user's emotions and adjusts the quality and format of responses. This system is particularly effective for services targeting multinational users, such as food delivery. The specific system configuration and operation are described below.

[1428] System configuration

[1429] The system includes the following major components:

[1430] 1. User Device:

[1431] A device that allows users to access the system, input questions using interface means, and check answers. This includes smartphones, PCs, tablets, etc.

[1432] 2. Server:

[1433] It is the central computer in the system that receives questions, analyzes them, generates answers, and sends the answers.

[1434] 3. Interface means:

[1435] It is the part of the system where users can enter questions, providing a graphical user interface (GUI) and text boxes, and also incorporating an emotion engine to recognize the user's emotions.

[1436] 4. Natural Language Processing Engine:

[1437] This software analyzes questions sent by users, performing processes such as tokenization, part-of-speech tagging, and dependency structure analysis.

[1438] 5. Trained artificial intelligence models:

[1439] It is a collection of algorithms that are created using historical data and specific training to generate appropriate answers based on questions.

[1440] 6. Database:

[1441] It stores data on immigration-related legal systems and procedures. Access to this database allows the model to provide accurate information.

[1442] 7. Emotion Engine:

[1443] This software recognizes and analyzes emotions from user input. It performs emotion analysis through text input, voice input, and facial recognition.

[1444] System Operation

[1445] First, a user accesses the system using a terminal and inputs a question using the interface means. For example, the user inputs, "Please tell me how to extend my visa." At this time, an emotion engine built into the interface means recognizes emotions from the user's text input.

[1446] Next, the server receives the question sent by the user. The received question is analyzed by a natural language processing engine. This analysis includes tokenization, part-of-speech tagging, and dependency structure analysis. At the same time, emotional information analyzed by an emotion engine is also sent to the server.

[1447] Once the analysis is complete, the server uses a trained artificial intelligence model to generate an answer based on the user's question. The model uses the analysis results to pull necessary information from a database to create an appropriate answer. Furthermore, based on the analysis results of the emotion engine, the format and content of the answer can be adjusted depending on the user's emotional state.

[1448] Finally, the server sends the generated answer to the user's device, where the user can confirm the answer displayed on the device and obtain the necessary procedures or information.

[1449] Usage example

[1450] If a user types "How do I extend my visa?", the system will act as follows:

[1451] 1. The user enters a question on the device and presses the send button. At this time, the emotion engine recognizes emotions such as "impatience" or "anxiety" from the user's text.

[1452] 2. The server receives the question and analyzes it using the natural language processing engine. At the same time, it also receives the results of the emotion engine.

[1453] 3. The server uses a trained AI model to retrieve the necessary documents and procedures for visa extension from the database. Based on the results of the emotion engine, it adjusts the tone of the message to a calm and reassuring one: "Please stay calm. To extend your visa, you will need to prepare the application documents and submit them to the Immigration Bureau. For detailed procedures, please refer to the Immigration Bureau's official website."

[1454] 4. The server sends the generated response to the user's device.

[1455] 5. The user can check the answers on the device and understand the necessary procedures.

[1456] An example of a prompt sentence is, "Please tell me how to extend my visa."

[1457] The system as a whole is designed to enable users to efficiently obtain information about complex immigration procedures. The emotion engine also recognizes the user's emotions and provides information in an appropriate format, improving the user experience.

[1458] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1459] Step 1:

[1460] A user accesses the system using a terminal and inputs a question using the interface means.

[1461] Input: The user enters the text "How do I extend my visa?" into the interface means.

[1462] Output: Text data is sent from the user's terminal to the system.

[1463] Specific operation: The user enters a question in the text box of the terminal and clicks the send button. At this time, the emotion engine built into the interface means analyzes the emotion from the user's text input.

[1464] Step 2:

[1465] The server receives a question sent by a user.

[1466] Input: Text data sent from the user's terminal.

[1467] Output: Text data received in the server.

[1468] Specific operation: The server receives the text data sent from the user's terminal, along with the analysis results of the emotion engine.

[1469] Step 3:

[1470] The server uses a natural language processing engine to parse the question.

[1471] Input: Text data stored on the server.

[1472] Output: Parsed question tokens, parts of speech, and dependency structure data.

[1473] Specific operation: The natural language processing engine performs tokenization, part-of-speech tagging, and dependency structure analysis on the text data to generate analysis results.

[1474] Step 4:

[1475] The server uses a trained artificial intelligence model to generate answers based on the questions.

[1476] Input: Parsed question data and sentiment engine results.

[1477] Output: The generated answer text.

[1478] How it works: The AI ​​model retrieves the necessary information from the database based on the analysis results and generates an appropriate answer. The quality and format of the answer are adjusted based on the results of the emotion engine.

[1479] Step 5:

[1480] The server sends the generated answer to the user's terminal.

[1481] Input: The generated answer text.

[1482] Output: The answer text that is displayed on the user's terminal.

[1483] Specific operation: The server sends the generated answer text to the user's terminal, where the user can check the answer and understand the necessary procedures.

[1484] Step 6:

[1485] The user checks the answer on the device.

[1486] Input: The answer text sent by the server.

[1487] Output: User understanding and next actions.

[1488] Specific operation: The user checks the answers displayed on the device screen and understands the necessary information and procedures. If the information is insufficient, the user can enter a new question.

[1489] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1490] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1491] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1492] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1493] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1494] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1495] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1496] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1497] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1498] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1499] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1500] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1501] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1502] 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.

[1503] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1504] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1505] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1506] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1507] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1508] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1509] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1510] The following is further disclosed regarding the above embodiment.

[1511] (Claim 1)

[1512] an interface means for a user to input a question;

[1513] a means for the server to receive a question sent by the user;

[1514] means for parsing the question using a natural language processing engine;

[1515] means for generating an answer based on the question using a trained artificial intelligence model;

[1516] means for transmitting the generated answer to the user's terminal;

[1517] A system including:

[1518] (Claim 2)

[1519] 10. The system of claim 1, wherein the natural language processing engine performs processing including tokenization, part-of-speech tagging, and dependency structure analysis.

[1520] (Claim 3)

[1521] 2. The system of claim 1, wherein the trained artificial intelligence model accesses a database containing immigration status-related legal systems and procedures.

[1522] "Example 1"

[1523] (Claim 1)

[1524] an interface means for a user to input a question;

[1525] a means for the server to receive a question sent by the user;

[1526] means for parsing the question using a natural language processing engine;

[1527] means for generating an answer based on the question using a trained artificial intelligence model;

[1528] means for transmitting the generated answer to the user's terminal;

[1529] means for a user to confirm the generated answer;

[1530] A system including:

[1531] (Claim 2)

[1532] 10. The system of claim 1, wherein the natural language processing engine performs processing including tokenization, part-of-speech tagging, and dependency structure analysis.

[1533] (Claim 3)

[1534] 2. The system of claim 1, wherein the trained artificial intelligence model accesses a database containing immigration status-related legal systems and procedures.

[1535] "Application Example 1"

[1536] (Claim 1)

[1537] interface means for a user to input questions or commands;

[1538] means for the server to receive queries or commands sent by said user;

[1539] means for parsing said question or command using a natural language processing engine;

[1540] means for generating a response based on said question or command using a trained artificial intelligence model;

[1541] means for transmitting the generated response to a user terminal or a display device in the vehicle;

[1542] a voice generating means for providing the generated response to a user through a voice output device;

[1543] A system including:

[1544] (Claim 2)

[1545] 10. The system of claim 1, wherein the natural language processing engine performs processing including tokenization, part-of-speech tagging, and dependency structure analysis.

[1546] (Claim 3)

[1547] 2. The system of claim 1, wherein the trained artificial intelligence model accesses a database containing immigration status-related legal systems and procedures.

[1548] "Example 2: Combining Emotion Engines"

[1549] (Claim 1)

[1550] an interface means for a user to input a question;

[1551] a means for the server to receive a question sent by the user;

[1552] means for parsing the question using a natural language processing engine;

[1553] means for generating an answer based on the question using a trained artificial intelligence model;

[1554] means for transmitting the generated answer to the user's terminal;

[1555] means for recognizing and analyzing emotions of said user using an emotion engine;

[1556] means for adjusting the format and content of the response based on the analysis result of the emotion engine;

[1557] A system including:

[1558] (Claim 2)

[1559] 10. The system of claim 1, wherein the natural language processing engine performs processing including tokenization, part-of-speech tagging, and dependency structure analysis.

[1560] (Claim 3)

[1561] 2. The system of claim 1, wherein the trained artificial intelligence model accesses a database containing immigration status-related legal systems and procedures.

[1562] "Application example 2 when combining emotion engines"

[1563] (Claim 1)

[1564] an interface means for a user to input a question;

[1565] a means for the server to receive a question sent by the user;

[1566] means for parsing the question using a natural language processing engine;

[1567] means for generating an answer based on the question using a trained artificial intelligence model;

[1568] means for transmitting the generated answer to the user's terminal;

[1569] means for recognizing the user's emotions using an emotion engine and adjusting the quality and format of the answer;

[1570] A system including:

[1571] (Claim 2)

[1572] 10. The system of claim 1, wherein the natural language processing engine performs processing including tokenization, part-of-speech tagging, and dependency structure analysis.

[1573] (Claim 3)

[1574] 2. The system of claim 1, wherein the trained artificial intelligence model accesses a database containing immigration status-related legal systems and procedures.

[1575] (Claim 4)

[1576] 2. The system of claim 1, wherein the emotion engine analyzes emotions based on the user's text input, voice input, or facial recognition.

[1577] (Claim 5)

[1578] 2. The system of claim 1, wherein the emotion engine adjusts the tone of the response to be "calming," "reassuring," or "encouraging" depending on the user's emotional state. [Explanation of symbols]

[1579] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. an interface means for a user to input a question; a means for the server to receive a question sent by the user; means for parsing the question using a natural language processing engine; means for generating an answer based on the question using a trained artificial intelligence model; means for transmitting the generated answer to the user's terminal; A system including:

2. 10. The system of claim 1, wherein the natural language processing engine performs processing including tokenization, part-of-speech tagging, and dependency structure analysis.

3. 2. The system of claim 1, wherein the trained artificial intelligence model accesses a database containing immigration status-related legal systems and procedures.

Images