system

Abstract

We provide the system. [Solution] A means of understanding questions received from users using natural language processing technology, A means for searching a knowledge database based on the aforementioned analysis results and obtaining relevant answers, A means for translating the aforementioned answer into multiple languages ​​and sending it to the user, A means to automatically update the knowledge database when a new question is detected, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a conventional FAQ system, there is a problem that a user cannot identify an appropriate question and cannot reach the required answer. Also, while accurate and prompt responses are required for various questions, information updates are often performed manually, lacking efficiency. Furthermore, it has been difficult to provide consistent multilingual support for global users.

Means for Solving the Problems

[0005] This invention provides a system that understands user-submitted questions using natural language processing technology and retrieves relevant answers from a knowledge database based on the analysis results. This system has the functionality to translate answers into multiple languages ​​and send them to the user, and can automatically update the knowledge database when a new question is detected. Furthermore, by engaging in continuous dialogue with the user, it dynamically generates answers and provides accurate information tailored to the user's needs.

[0006] A "user" is someone who uses the system to input questions and receive answers.

[0007] "Natural language processing technology" is a technology that analyzes text data entered by users to understand its meaning and intent.

[0008] A "knowledge database" is a collection of data that stores answers and information to various questions, and relevant information can be retrieved through searching.

[0009] An "answer" is information retrieved from a knowledge database in response to a user's question, and formatted as needed.

[0010] "Multilingual translation" is the process of accurately converting an answer expressed in one language into another language.

[0011] A "new question" refers to a question for which there are no existing answers in the knowledge database, or for which only a partial answer can be provided.

[0012] "Automatic updates" is the process by which a system updates its knowledge database to the latest information and questions without manual intervention.

[0013] "Continuous dialogue" is a process of maintaining interaction with the user while flexibly providing information in response to additional questions. [Brief explanation of the drawing]

[0014] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0017] In the following embodiments, a processor with a reference number (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, a RAM (Random Access Memory) with a reference number is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a storage with a reference number is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like. [[ID=十七]]

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

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

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0031] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] This invention is implemented as an FAQ search system that provides efficient and accurate answers to user inquiries. This system consists of a server, a terminal, and a user, and operates as follows.

[0036] First, the user enters a question through the terminal's interface. The terminal sends this question to the server. The server analyzes the received question using natural language processing technology to gain a deep understanding of the user's intent.

[0037] Once the analysis is complete, the server searches the knowledge database to retrieve relevant information. This database contains a well-organized collection of pre-answered questions. After retrieving the appropriate answer, the server formats it in a way that is easy for the user to understand. The server also translates the answer using a multilingual translation function based on the user's settings and geographical language settings.

[0038] After formatting the answer, the server sends it to the terminal, which then displays the answer to the user. The user can review this information and repeat the same process if they have further questions.

[0039] Furthermore, when the server detects a new question from a user, it automatically updates the knowledge database accordingly. This ensures that the entire system is always up-to-date and improves its ability to respond to similar questions in the future.

[0040] For example, if a user asks, "How do I apply for a new passport?", the server can instantly provide an answer including relevant laws and procedural information, translate that information into English if necessary, and display it to the user. This allows users to obtain the necessary information efficiently and quickly.

[0041] Thus, the system of the present invention, by incorporating natural language processing, knowledge database search, multilingual support, and automatic update functions, is capable of providing users with advanced information.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The user accesses the terminal interface, enters a question, and presses submit. This question is sent from the terminal to the server as text data.

[0045] Step 2:

[0046] The server receives question data from the terminal and performs analysis using natural language processing technology. This analysis helps understand the intent of the question and extract important keywords and context.

[0047] Step 3:

[0048] The server searches the knowledge database based on the information obtained from the analysis. It queries for relevant answers and extracts information with a high degree of match.

[0049] Step 4:

[0050] The server formats the retrieved answers into a format that is easy for the user to understand. This is done using generative AI technology to improve the naturalness and appropriateness of the answers.

[0051] Step 5:

[0052] The server checks the user's language settings and translates the answers using its multilingual translation function as needed. This ensures that answers are available in the language specified by the user.

[0053] Step 6:

[0054] The server sends the final answer to the terminal. The terminal displays this information in the user interface.

[0055] Step 7:

[0056] The user reviews the answer displayed on their device and determines whether the solution to their question is appropriate. If necessary, they can enter additional questions and process the question again.

[0057] Step 8:

[0058] The server continues to interact with users in response to new questions and automatically updates its knowledge database. This ensures that it can stay up-to-date with the latest information.

[0059] (Example 1)

[0060] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0061] With the advancement of information technology in the modern era, there is a growing need for systems that can provide quick and accurate answers to a wide range of questions. However, existing FAQ systems suffer from issues such as insufficient accuracy in natural language processing, limitations in multilingual support, and delays in responding to new questions. As a result, users are unable to efficiently obtain the information they need, reducing the value of the system.

[0062] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0063] In this invention, the server includes means for understanding questions obtained from users using natural language processing technology, means for searching an information base and obtaining relevant information, means for translating and communicating in multiple languages ​​to the user, means for automatically updating the information base, and means for formatting answers based on the user's settings. As a result, users can quickly obtain the latest and most relevant information through continuous dialogue in multiple languages.

[0064] "User" refers to an individual or organization that attempts to obtain information using the system.

[0065] A "question" refers to a sentence or phrase that a user enters into the system via their device to inquire about knowledge or information.

[0066] "Natural language processing technology" refers to technologies that enable computers to understand and analyze human language, and includes morphological analysis and semantic analysis.

[0067] An "information base" refers to a collection of data containing numerous questions and their answers, which is managed as a database.

[0068] "Multilingual conversion" refers to the process of converting answers or information into multiple different languages.

[0069] "Automatically updating the information base" refers to the process of automatically adding or modifying the content of the information base based on newly detected questions and information.

[0070] "Formatting answers" refers to the process of arranging and organizing information in a way that is easy for users to understand and view.

[0071] "Continuous dialogue" refers to the process of providing step-by-step and sequential answers to the user's questions and maintaining the dialogue.

[0072] This invention is an FAQ search system that enables users to efficiently obtain the information they want. This system consists of three components: the user, the terminal, and the server.

[0073] The user enters their question via a terminal. A terminal refers to a device such as a smartphone or personal computer, which functions as a means of inputting and obtaining information through an interface. For example, the user might enter a question such as, "Please tell me how to apply for a new passport."

[0074] The terminal's role is to receive input from the user and send that data to the server. The terminal communicates with the server using the Internet Protocol and sends the user's input to the server.

[0075] After receiving a question from a user, the server performs analysis using natural language processing (NLP) techniques. Natural language processing models such as BERT and spaCy may be used for NLP. Through this analysis, the server understands the user's intent and then searches an information base. This information base contains a large number of pre-registered questions and their answers, and database management systems such as MySQL® or PostgreSQL may be used.

[0076] The answers retrieved from the information base are formatted by the server into a user-friendly format. This formatting is performed using a template engine such as Jinja2. Furthermore, multilingual support is provided using the Google Translate API or similar multilingual translation software, depending on user settings and requirements.

[0077] Prepared answers are sent from the server to the terminal, which then displays the answers to the user. This allows the user to quickly obtain the desired information. Furthermore, if a question is not yet registered in the information base, the server detects this and automatically updates it as new knowledge.

[0078] As a concrete example, an example prompt would be: "Please search for the information needed to answer the following question and prepare to answer the user in multiple languages: 'Please tell me how to apply for a new passport.'" This input is given to the generating AI model. Based on this prompt, the system provides information efficiently.

[0079] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0080] Step 1:

[0081] The user enters questions to obtain information using the terminal's interface. This input is passed to the terminal as natural language text data.

[0082] Step 2:

[0083] The terminal receives text input from the user and prepares to send it to the server. The text data is sent to the server via the Internet Protocol.

[0084] Step 3:

[0085] The server receives text data from the terminal and begins analysis using natural language processing technology. This analysis uses a generative AI model to understand the user's intent from the text data. Specifically, it performs morphological and semantic analysis and generates metadata of the intent as a result of the analysis.

[0086] Step 4:

[0087] The server searches the information base based on the analysis results. The information base stores relevant past questions and answers. The server uses a database management system to execute queries and extract highly relevant answer data.

[0088] Step 5:

[0089] The server formats the acquired answer data into a form suitable for the user's understanding. Specifically, it uses a template engine to generate dynamic HTML and performs multilingual translation as needed, according to the user's language settings. A translation API is used for this purpose.

[0090] Step 6:

[0091] The server sends the formatted answer to the terminal as a data packet. Asynchronous communication is used in this process, and the answer is encoded in a standard format such as JSON.

[0092] Step 7:

[0093] The terminal receives the answer data from the server and displays it to the user. It renders the answers through a user interface so that the user can easily read them.

[0094] Step 8:

[0095] The user checks the answer displayed on the device. If further information is needed, they can enter a new question and repeat the process. This cycle allows the user to obtain information dynamically and continuously.

[0096] (Application Example 1)

[0097] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0098] In modern e-commerce platforms, there is a lack of efficient and accurate means for users to obtain product information. Furthermore, appropriate product recommendations based on user purchasing behavior are insufficient, highlighting the need for improved user experience.

[0099] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0100] In this invention, the server includes means for understanding questions received from the user using natural language processing technology, means for searching a knowledge database based on the analysis results to obtain relevant answers, and means for analyzing the user's purchase information to suggest relevant products. This enables the user to quickly obtain the necessary information and receive personalized product suggestions based on their purchasing behavior.

[0101] "Natural language processing technology" is a technology that analyzes questions from users in natural language and understands their intent and meaning.

[0102] A "knowledge database" is a collection of information that has accumulated prior answers to various questions, and is used to provide relevant information to users' questions.

[0103] "Multilingual translation" is a technology that converts acquired answers into different languages ​​and provides them according to the user's language settings.

[0104] "Automatic updates" is a function that keeps the system continuously up-to-date by adding information to the knowledge database whenever a new question is detected.

[0105] "Purchase information analysis" is a technology that analyzes a user's past purchase history and behavioral patterns, and then suggests highly relevant products based on that analysis.

[0106] The invention will now be described in terms of its embodiments. This system consists of a user, a terminal, and a server.

[0107] First, the user enters a question through their device. The device then sends this question to the server via the internet. The server uses Google Cloud's Natural Language API to perform natural language analysis on the received question and understand the user's intent.

[0108] Once the analysis is complete, the server accesses a knowledge database stored in Google Cloud Firestore to search for relevant answers based on the analysis results. Simultaneously, it references a database containing the user's past purchase information to generate highly relevant product suggestions. This includes, in particular, pattern recognition based on the user's purchase history and interests.

[0109] The answers and product suggestions obtained are translated into multiple languages ​​based on the user's language settings using the Google Cloud Translation API. The server then sends the translated answers and related product information to the device. The device displays this information to the user and can accept further questions as needed.

[0110] For example, if a user asks for advice on purchasing a new smartphone, the server will suggest the latest model information and popular accessories, and also provide relevant reviews and usage guidelines.

[0111] An example of an input prompt for a generative AI model is, "Please recommend products for a specific event."

[0112] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0113] Step 1:

[0114] The user enters a question through the terminal. The terminal receives this input and sends its contents to the server. The input is text data from the user, and the output is data sent to the server.

[0115] Step 2:

[0116] The server analyzes received questions using Google Cloud's Natural Language API. The input is text data received from the user, and the output is information about the user's intent after analysis. In this process, natural language processing techniques are used to identify keywords and phrases within the text, and the data is processed to understand the user's intent.

[0117] Step 3:

[0118] Based on the analysis results, the server searches a knowledge database stored in Google Cloud Firestore to retrieve relevant answers. The input is a query based on the analysis results, and the output is text data containing the answer to the user. At this stage, data calculations are performed to select the appropriate answer using a database search algorithm.

[0119] Step 4:

[0120] The server analyzes the user's purchase history to suggest related products. The input is the user's past purchase data, and the output is information about recommended products. This process analyzes patterns based on past purchasing behavior and performs data analysis to select appropriate products.

[0121] Step 5:

[0122] The server translates the retrieved answers and product suggestions into multiple languages ​​based on the user's language settings. The input is the answers and suggested product information, and the output is the information translated into the user's display language. This process utilizes the Google Cloud Translation API to convert the data into the appropriate language.

[0123] Step 6:

[0124] The server sends the translated information to the terminal, which then displays it to the user. The input is translated text data, and the output is the display on the user's screen. This process involves receiving information via data communication and presenting it appropriately to the display device.

[0125] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0126] This invention is an FAQ search system that takes user emotions into consideration, providing more appropriate and personalized answers to user questions. This system is composed of three main components: a server, a terminal, and the user.

[0127] First, the user inputs a question through the terminal's interface and sends it. The terminal sends this question data to the server. The server analyzes the received question using natural language processing technology and an emotion engine. Natural language processing technology understands the intent of the question, and the emotion engine identifies the user's emotions expressed in the text.

[0128] The server searches a knowledge database based on the analysis results and sentiment data to retrieve relevant answers. At this time, the emotions identified by the sentiment engine are taken into consideration, and the tone and content of the answers are adjusted accordingly. For example, if the user is expressing frustration, a more empathetic and polite answer will be selected.

[0129] The answers are formatted using generational AI technology and adjusted to be easily understood by the user. The server then translates the answers according to the user's language settings and sends the final answers to the device. The device then displays these answers to the user.

[0130] The user can review the answer displayed on their device and, if necessary, enter additional questions to continue the conversation. The server quickly provides appropriate answers to the user's new questions and automatically updates its knowledge database.

[0131] For example, if a user asks, "I'm frustrated because my product hasn't arrived," the server recognizes this emotion and provides an empathetic and understanding response such as, "We apologize. Please wait a moment while we check the current delivery status." In this way, information provided to the user can be optimized, ensuring a better experience.

[0132] This system integrates natural language processing, an emotion engine, knowledge database search, multilingual support, and automatic update functions to provide users with appropriate and human-centered information.

[0133] The following describes the processing flow.

[0134] Step 1:

[0135] The user enters a question through the terminal's interface and presses the "Send" button. This question data is then sent from the terminal to the server.

[0136] Step 2:

[0137] The server receives question data from the terminal and analyzes the text using natural language processing technology. It extracts important keywords and context to understand the user's intent and the content of the question.

[0138] Step 3:

[0139] The server uses extracted keywords and contextual information to activate an emotion engine that identifies the user's emotions. This engine detects emotions such as joy, anger, and sadness, and also measures their intensity.

[0140] Step 4:

[0141] The server uses the analysis results and sentiment data to search the knowledge database. It retrieves relevant answers and formats them accordingly. In this process, it adjusts the tone and expression of the answers according to the emotions. For example, if anger is detected in the user's question, the answer will be adjusted to be more empathetic and polite.

[0142] Step 5:

[0143] The server checks the user's language settings and translates the formatted answers as needed. Multilingual support is used to translate the answers into the user's native language.

[0144] Step 6:

[0145] The server sends the final answer to the terminal, which then displays it on the user's screen. The user can then verify this answer.

[0146] Step 7:

[0147] The user can check the answer displayed on their device and enter additional questions if the question is not sufficiently resolved. As long as the interaction continues, the server will receive new questions and repeat the same analysis process.

[0148] Step 8:

[0149] The server records new user inquiries in the system and automatically updates the knowledge database, preparing for future use. This ensures that the system always provides the most up-to-date information.

[0150] (Example 2)

[0151] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0152] Modern interactive systems are required not only to provide factual information in response to user questions, but also to offer personalized answers that take user emotions into consideration. However, conventional systems only understand the intent of the inquiry and lack responses based on user emotions, resulting in a decline in user satisfaction.

[0153] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0154] In this invention, the server includes means for understanding a question received from a user using a natural language processing method, means for sentiment analysis to identify the emotions contained in the question, and means for searching a knowledge data store and obtaining relevant answers based on the analysis results and sentiment data. This makes it possible to provide personalized answers in an appropriate tone according to the user's emotions.

[0155] A "user" is the entity that accesses an information system and enters a question.

[0156] A "terminal" is a device used by users to input questions and is responsible for sending and receiving data with a server via communication means.

[0157] A "server" is a central processing unit that analyzes questions received from users, generates appropriate answers, and sends them to terminals.

[0158] "Natural language processing techniques" are technologies that convert text data received from users into a format that computers can understand, and then analyze its intent and context.

[0159] "Sentiment analysis" is a technique for identifying emotions from text data and processing information based on those emotions.

[0160] A "knowledge data store" is a repository of information resources that holds answers to user questions and retrieves and provides information as needed.

[0161] "Multilingual translation" is a technology that converts information expressed in one language into another language, providing answers that are tailored to the user's language settings.

[0162] A "generative model" is a computational model that generates new information or text based on machine learning.

[0163] This invention is implemented as an FAQ search system that takes user sentiment into consideration. When a user enters a question through the terminal interface, the terminal sends this question to the server. The server analyzes the intent of the question using natural language processing techniques. General natural language processing software is used for this analysis, and specific examples include open-source natural language processing libraries and cloud-based language services.

[0164] The server further utilizes a sentiment engine to perform sentiment analysis. This identifies the emotions contained in the user's question and processes them appropriately. The sentiment engine employs an algorithm that evaluates the sentiment of text based on machine learning.

[0165] Subsequently, the server searches the knowledge data store based on the analysis results and sentiment data to retrieve relevant answers. During this process, the tone of the answers is adjusted, taking sentiment data into consideration. A generative AI model is used to generate the answers, dynamically changing the tone and expression of the text. For example, a prompt such as, "The user is expressing dissatisfaction. Please generate an empathetic and polite response," can be used.

[0166] Furthermore, the server translates the answers using a multilingual translation service according to the user's language settings. Google Translate and other translation APIs are available here. The translated answers are sent to the device and displayed to the user.

[0167] In this way, users can receive more personalized answers tailored to their own situation. Because the system's responses address the user's emotions and specific needs, an improved user experience is expected.

[0168] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0169] Step 1:

[0170] The user enters and submits a question using the device's interface. This action generates the input question text data. The output is the submitted question data. Specifically, the user enters content such as "I am dissatisfied because the product has not arrived" using the keyboard or voice input function.

[0171] Step 2:

[0172] The terminal sends the user's question data to the server. This process involves data transfer from the terminal to the server. Specifically, the text data of the question is sent to the server as packets via the HTTP protocol. The input is the user's question data, and the output is the question data received by the server.

[0173] Step 3:

[0174] The server analyzes received question data using natural language processing techniques. The input is the question text data received by the server, and the output is the analyzed intent and main topic of the question. Specifically, a natural language processing engine is used to identify topics and extract keywords. For example, open-source libraries are used for the analysis.

[0175] Step 4:

[0176] The server uses an emotion engine to identify the emotions contained in a question. In this process, the question text to be analyzed is used as input, and user emotion data is generated as output. Specifically, a machine learning model identifies the emotions in the text, such as positive, negative, or neutral.

[0177] Step 5:

[0178] The server searches the knowledge data store based on the analysis results and sentiment data to retrieve relevant answers. The input is the analysis results and sentiment data, and the output is the relevant answers. Specifically, it uses SQL queries to access the data store and quickly retrieve matching FAQs.

[0179] Step 6:

[0180] The server considers sentiment data and adjusts the tone of the response. The input here is the initial response and sentiment data, and the output is the adjusted response. A generative AI model is used to change the tone of the sentence using prompt sentences, for example, instructions such as "Make it more empathetic."

[0181] Step 7:

[0182] The server translates the answer according to the user's language settings. The input is the adjusted answer, and the output is the answer in a language the user understands. A translation API is called to convert the answer to a specific language.

[0183] Step 8:

[0184] The server sends the final answer to the terminal. The input is the translated answer, and the output is the message sent to the terminal. In this process, the server sends the answer to the terminal as an HTTP response.

[0185] Step 9:

[0186] The terminal displays the received answer to the user. The input is the answer data received by the terminal, and the output is the answer displayed on the screen. The answer is clearly displayed in the user interface, and the user can confirm it.

[0187] (Application Example 2)

[0188] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0189] There is a growing need to provide prompt and appropriate answers to user questions and problems that arise when using a service, taking their emotions into consideration. However, conventional FAQ systems do not consider user emotions and generate non-personalized answers, which can lead to decreased customer satisfaction. This invention aims to improve the user experience when resolving problems by analyzing user emotions and providing personalized answers accordingly.

[0190] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0191] In this invention, the server includes means for understanding a question received from a user using natural language processing technology, means for searching a knowledge base based on the analysis results and sentiment data associated with the user to obtain relevant answers, and means for formatting the answers using a generation engine and providing them to the user in a tone adjusted according to their emotions. This makes it possible to quickly provide personalized answers that take into account the user's emotions.

[0192] "Natural language processing technology" is a technology that enables computers to understand and interpret questions and texts from users.

[0193] "Emotional data" refers to information data related to emotions, extracted from text and questions entered by users.

[0194] A "knowledge base" is a collection of information that stores answers to questions, and it is a database that is referenced to obtain appropriate answers.

[0195] A "generative engine" is a technology used to format acquired answers and express them in an appropriate tone, generating answers in a way that is easy for users to understand.

[0196] "Continuous dialogue" is a process in which the user and the system engage in a two-way conversation, dynamically generating answers and improving user satisfaction.

[0197] To implement the present invention, it is necessary to construct a system in which users, servers, and terminals work together. This system includes terminals equipped with a user interface, servers for data processing, and communication technology to coordinate them.

[0198] First, the user inputs a question containing emotions using a device such as a smartphone. This question is sent from the device to the server. The server uses natural language processing technology built with Python to analyze the content of the user's question, and then an emotion analysis engine retrieves the user's emotional data. This analysis reveals the user's specific intentions and emotional state. Next, the server retrieves relevant answers by referring to a knowledge base based on the analysis results. This knowledge base is a database that stores a wide range of information to address all possibilities.

[0199] The acquired answers are further refined using a generative AI model, shaping them into natural language and adjusting their tone and content according to the user's emotions. For example, if the system detects that the user is anxious, the answer is adjusted to a kind and empathetic tone. The final answers are translated into a language the user understands using a multilingual engine, enabling the system to serve a global user base. The device receives answers from the server and displays them to the user. The user can review the displayed answers and enter new questions. The server automatically updates its knowledge base upon receiving new questions, improving the system's response accuracy.

[0200] For example, if a user expresses anxiety about why their electronic payment isn't working, the server will sense their concern and generate a response such as, "Please rest assured. We will analyze the problem immediately and provide a solution." The AI ​​is then instructed with a prompt message such as, "Generate a response that will alleviate the user's anxiety regarding the electronic payment problem."

[0201] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0202] Step 1:

[0203] The user enters a question on the terminal interface and presses the submit button. This information is sent from the terminal to the server. The input consists of the user's question and its language information, and the output is the query data sent to the server.

[0204] Step 2:

[0205] When the server receives query data, it first uses natural language processing (NLP) techniques to analyze the intent of the question. The input is the text data of the question sent by the user, and the output is the analyzed intent data. The server then runs a text analysis tool to understand the meaning of the question.

[0206] Step 3:

[0207] The server uses an emotion analysis engine to detect the user's emotions from the query data. The input is the text data analyzed in step 2, and the output is the user's emotion data. In this step, the server runs an emotion classification model to identify the emotional state from the text.

[0208] Step 4:

[0209] The server searches a knowledge base based on intent and sentiment data to retrieve relevant answers. The input is the parsed intent and sentiment data, and the output is the relevant answer data. In this operation, the server executes database queries and selects the appropriate answer.

[0210] Step 5:

[0211] The server uses a generative AI model to format the answer data and adjust it appropriately to match the user's emotions. The input is the answer data and emotion data, and the output is the formatted answer text. In this step, the server operates the generative model to form natural and empathetic responses.

[0212] Step 6:

[0213] The server translates the formatted answer into the user's language using a multilingual engine. The input is the formatted answer text, and the output is the translated answer text. Here, the server applies the multilingual translation function to convert the answer into the specified language.

[0214] Step 7:

[0215] The server sends the translated final answer to the terminal. The terminal displays this answer to the user. The input is the translated answer text, and the output is the answer displayed on the user's terminal screen. In this final step, the terminal runs the answer display module and provides information to the user.

[0216] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0217] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0218] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0219] [Second Embodiment]

[0220] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0221] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0222] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0223] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0224] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0225] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0226] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0227] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0228] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0229] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0230] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0231] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0232] This invention is implemented as an FAQ search system that provides efficient and accurate answers to user inquiries. This system consists of a server, a terminal, and a user, and operates as follows.

[0233] First, the user enters a question through the terminal's interface. The terminal sends this question to the server. The server analyzes the received question using natural language processing technology to gain a deep understanding of the user's intent.

[0234] Once the analysis is complete, the server searches the knowledge database to retrieve relevant information. This database contains a well-organized collection of pre-answered questions. After retrieving the appropriate answer, the server formats it in a way that is easy for the user to understand. The server also translates the answer using a multilingual translation function based on the user's settings and geographical language settings.

[0235] After formatting the answer, the server sends it to the terminal, which then displays the answer to the user. The user can review this information and repeat the same process if they have further questions.

[0236] Furthermore, when the server detects a new question from a user, it automatically updates the knowledge database accordingly. This ensures that the entire system is always up-to-date and improves its ability to respond to similar questions in the future.

[0237] For example, if a user asks, "How do I apply for a new passport?", the server can instantly provide an answer including relevant laws and procedural information, translate that information into English if necessary, and display it to the user. This allows users to obtain the necessary information efficiently and quickly.

[0238] Thus, the system of the present invention, by incorporating natural language processing, knowledge database search, multilingual support, and automatic update functions, is capable of providing users with advanced information.

[0239] The following describes the processing flow.

[0240] Step 1:

[0241] The user accesses the terminal interface, enters a question, and presses submit. This question is sent from the terminal to the server as text data.

[0242] Step 2:

[0243] The server receives question data from the terminal and performs analysis using natural language processing technology. This analysis helps understand the intent of the question and extract important keywords and context.

[0244] Step 3:

[0245] The server searches the knowledge database based on the information obtained from the analysis. It queries for relevant answers and extracts information with a high degree of match.

[0246] Step 4:

[0247] The server formats the retrieved answers into a format that is easy for the user to understand. This is done using generative AI technology to improve the naturalness and appropriateness of the answers.

[0248] Step 5:

[0249] The server checks the user's language settings and translates the answers using its multilingual translation function as needed. This ensures that answers are available in the language specified by the user.

[0250] Step 6:

[0251] The server sends the final answer to the terminal. The terminal displays this information in the user interface.

[0252] Step 7:

[0253] The user reviews the answer displayed on their device and determines whether the solution to their question is appropriate. If necessary, they can enter additional questions and process the question again.

[0254] Step 8:

[0255] The server continues to interact with users in response to new questions and automatically updates its knowledge database. This ensures that it can stay up-to-date with the latest information.

[0256] (Example 1)

[0257] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0258] With the advancement of information technology in the modern era, there is a growing need for systems that can provide quick and accurate answers to a wide range of questions. However, existing FAQ systems suffer from issues such as insufficient accuracy in natural language processing, limitations in multilingual support, and delays in responding to new questions. As a result, users are unable to efficiently obtain the information they need, reducing the value of the system.

[0259] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0260] In this invention, the server includes means for understanding questions obtained from users using natural language processing technology, means for searching an information base and obtaining relevant information, means for translating and communicating in multiple languages ​​to the user, means for automatically updating the information base, and means for formatting answers based on the user's settings. As a result, users can quickly obtain the latest and most relevant information through continuous dialogue in multiple languages.

[0261] "User" refers to an individual or organization that attempts to obtain information using the system.

[0262] A "question" refers to a sentence or phrase that a user enters into the system via their device to inquire about knowledge or information.

[0263] "Natural language processing technology" refers to technologies that enable computers to understand and analyze human language, and includes morphological analysis and semantic analysis.

[0264] An "information base" refers to a collection of data containing numerous questions and their answers, which is managed as a database.

[0265] "Multilingual conversion" refers to the process of converting answers or information into multiple different languages.

[0266] "Automatically updating the information base" refers to the process of automatically adding or modifying the content of the information base based on newly detected questions and information.

[0267] "Formatting answers" refers to the process of arranging and organizing information in a way that is easy for users to understand and view.

[0268] "Continuous dialogue" refers to the process of providing step-by-step and sequential answers to the user's questions and maintaining the dialogue.

[0269] This invention is an FAQ search system that enables users to efficiently obtain the information they want. This system consists of three components: the user, the terminal, and the server.

[0270] The user enters their question via a terminal. A terminal refers to a device such as a smartphone or personal computer, which functions as a means of inputting and obtaining information through an interface. For example, the user might enter a question such as, "Please tell me how to apply for a new passport."

[0271] The terminal's role is to receive input from the user and send that data to the server. The terminal communicates with the server using the Internet Protocol and sends the user's input to the server.

[0272] After receiving a question from a user, the server performs analysis using natural language processing (NLP) techniques. Natural language processing models such as BERT and spaCy may be used for this analysis. Through this analysis, the server understands the user's intent and then searches an information base. This information base contains a large number of pre-registered questions and their answers, and database management systems such as MySQL and PostgreSQL are sometimes used.

[0273] The answers retrieved from the information base are formatted by the server into a user-friendly format. This formatting is done using a template engine such as Jinja2. Furthermore, depending on user settings and requirements, multilingual support is provided using the Google Translate API or similar multilingual translation software.

[0274] Prepared answers are sent from the server to the terminal, which then displays the answers to the user. This allows the user to quickly obtain the desired information. Furthermore, if a question is not yet registered in the information base, the server detects this and automatically updates it as new knowledge.

[0275] As a concrete example, an example prompt would be: "Please search for the information needed to answer the following question and prepare to answer the user in multiple languages: 'Please tell me how to apply for a new passport.'" This input is given to the generating AI model. Based on this prompt, the system provides information efficiently.

[0276] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0277] Step 1:

[0278] The user enters questions to obtain information using the terminal's interface. This input is passed to the terminal as natural language text data.

[0279] Step 2:

[0280] The terminal receives the input text from the user and prepares to send it to the server. Through the Internet protocol, the text data is sent to the server.

[0281] Step 3:

[0282] The server obtains the text data received from the terminal and begins analysis using natural language analysis technology. A generative AI model is used for this analysis to grasp the user's intention from the text data. Specifically, morphological analysis and semantic analysis are performed, and metadata of the intention is generated as the analysis result.

[0283] Step 4:

[0284] Based on the analysis result, the server searches the information base. In the information base, related past questions and answers are accumulated. The server uses a database management system to execute a query and extracts highly relevant answer data.

[0285] Step 5:

[0286] The server formats the obtained answer data into a form suitable for the user's understanding. Specifically, dynamic HTML is generated using a template engine, and multilingual translation is performed as needed according to the user's set language. This utilizes a translation API.

[0287] Step 6:

[0288] The server sends the formatted answer to the terminal as a data packet. Asynchronous communication is used in this process, and the answer is encoded in a standard format such as JSON.

[0289] Step 7:

[0290] The terminal receives the answer data received from the server and displays it to the user. Rendering is performed through the user interface so that the user can easily read the answer.

[0291] Step 8:

[0292] The user checks the answer displayed on the device. If further information is needed, they can enter a new question and repeat the process. This cycle allows the user to obtain information dynamically and continuously.

[0293] (Application Example 1)

[0294] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0295] In modern e-commerce platforms, there is a lack of efficient and accurate means for users to obtain product information. Furthermore, appropriate product recommendations based on user purchasing behavior are insufficient, highlighting the need for improved user experience.

[0296] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0297] In this invention, the server includes means for understanding questions received from the user using natural language processing technology, means for searching a knowledge database based on the analysis results to obtain relevant answers, and means for analyzing the user's purchase information to suggest relevant products. This enables the user to quickly obtain the necessary information and receive personalized product suggestions based on their purchasing behavior.

[0298] "Natural language processing technology" is a technology that analyzes questions from users in natural language and understands their intent and meaning.

[0299] A "knowledge database" is a collection of information that has accumulated prior answers to various questions, and is used to provide relevant information to users' questions.

[0300] "Multilingual translation" is a technology that converts acquired answers into different languages ​​and provides them according to the user's language settings.

[0301] "Automatic updates" is a function that keeps the system continuously up-to-date by adding information to the knowledge database whenever a new question is detected.

[0302] "Purchase information analysis" is a technology that analyzes a user's past purchase history and behavioral patterns, and then suggests highly relevant products based on that analysis.

[0303] The invention will now be described in terms of its embodiments. This system consists of a user, a terminal, and a server.

[0304] First, the process begins with the user entering a question through their device. The device then sends this question to a server via the internet. The server uses Google Cloud's Natural Language API to perform natural language analysis on the received question and understand the user's intent.

[0305] Once the analysis is complete, the server accesses a knowledge database stored in Google Cloud Firestore to search for relevant answers based on the analysis results. Simultaneously, it references a database containing the user's past purchase information to generate highly relevant product suggestions. This includes, in particular, pattern recognition based on the user's purchase history and interests.

[0306] The answers and product suggestions obtained are translated into multiple languages ​​based on the user's language settings using the Google Cloud Translation API. The server then sends the translated answers and related product information to the device. The device displays this information to the user and can accept further questions as needed.

[0307] As a specific example, when a user asks "I want advice on buying a new smartphone", the server proposes the latest model information and popular accessories, and also provides relevant reviews and usage guidelines.

[0308] An example of an input prompt sentence for the generative AI model is "Please tell me the recommended products for a specific event."

[0309] The flow of the specific process in Application Example 1 will be described using Figure 12.

[0310] Step 1:

[0311] The user inputs a question through the terminal. The terminal receives this input and transmits its content to the server. The input is text data from the user, and the output is data transmission to the server.

[0312] Step 2:

[0313] The server analyzes the received question using Google Cloud's Natural Language API. The input is the text data received from the user, and the output is information regarding the analyzed user intention. In this process, natural language analysis technology is used to identify keywords and phrases within the text, and data processing is performed to understand the user's intention.

[0314] Step 3:

[0315] Based on the analysis result, the server searches the knowledge database stored in Google Cloud Firestore and obtains relevant answers. The input is an inquiry based on the analysis result, and the output is text data including the answer to the user. At this stage, data calculation is performed using a database search algorithm to select an appropriate answer.

[0316] Step 4:

[0317] The server analyzes the user's purchase history to suggest related products. The input is the user's past purchase data, and the output is information about recommended products. This process analyzes patterns based on past purchasing behavior and performs data analysis to select appropriate products.

[0318] Step 5:

[0319] The server translates the retrieved answers and product suggestions into multiple languages ​​based on the user's language settings. The input is the answers and suggested product information, and the output is the information translated into the user's display language. This process utilizes the Google Cloud Translation API to convert the data into the appropriate language.

[0320] Step 6:

[0321] The server sends the translated information to the terminal, which then displays it to the user. The input is translated text data, and the output is the display on the user's screen. This process involves receiving information via data communication and presenting it appropriately to the display device.

[0322] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0323] This invention is an FAQ search system that takes user emotions into consideration, providing more appropriate and personalized answers to user questions. This system is composed of three main components: a server, a terminal, and the user.

[0324] First, the user inputs a question through the terminal's interface and sends it. The terminal sends this question data to the server. The server analyzes the received question using natural language processing technology and an emotion engine. Natural language processing technology understands the intent of the question, and the emotion engine identifies the user's emotions expressed in the text.

[0325] The server searches a knowledge database based on the analysis results and sentiment data to retrieve relevant answers. At this time, the emotions identified by the sentiment engine are taken into consideration, and the tone and content of the answers are adjusted accordingly. For example, if the user is expressing frustration, a more empathetic and polite answer will be selected.

[0326] The answers are formatted using generational AI technology and adjusted to be easily understood by the user. The server then translates the answers according to the user's language settings and sends the final answers to the device. The device then displays these answers to the user.

[0327] The user can review the answer displayed on their device and, if necessary, enter additional questions to continue the conversation. The server quickly provides appropriate answers to the user's new questions and automatically updates its knowledge database.

[0328] For example, if a user asks, "I'm frustrated because my product hasn't arrived," the server recognizes this emotion and provides an empathetic and understanding response such as, "We apologize. Please wait a moment while we check the current delivery status." In this way, information provided to the user can be optimized, ensuring a better experience.

[0329] This system integrates natural language processing, an emotion engine, knowledge database search, multilingual support, and automatic update functions to provide users with appropriate and human-centered information.

[0330] The following describes the processing flow.

[0331] Step 1:

[0332] The user enters a question through the terminal's interface and presses the "Send" button. This question data is then sent from the terminal to the server.

[0333] Step 2:

[0334] The server receives question data from the terminal and analyzes the text using natural language processing technology. It extracts important keywords and context to understand the user's intent and the content of the question.

[0335] Step 3:

[0336] The server uses extracted keywords and contextual information to activate an emotion engine that identifies the user's emotions. This engine detects emotions such as joy, anger, and sadness, and also measures their intensity.

[0337] Step 4:

[0338] The server uses the analysis results and sentiment data to search the knowledge database. It retrieves relevant answers and formats them accordingly. In this process, it adjusts the tone and expression of the answers according to the emotions. For example, if anger is detected in the user's question, the answer will be adjusted to be more empathetic and polite.

[0339] Step 5:

[0340] The server checks the user's language settings and translates the formatted answers as needed. Multilingual support is used to translate the answers into the user's native language.

[0341] Step 6:

[0342] The server sends the final answer to the terminal, which then displays it on the user's screen. The user can then verify this answer.

[0343] Step 7:

[0344] The user can check the answer displayed on their device and enter additional questions if the question is not sufficiently resolved. As long as the interaction continues, the server will receive new questions and repeat the same analysis process.

[0345] Step 8:

[0346] The server records new user inquiries in the system and automatically updates the knowledge database, preparing for future use. This ensures that the system always provides the most up-to-date information.

[0347] (Example 2)

[0348] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0349] Modern interactive systems are required not only to provide factual information in response to user questions, but also to offer personalized answers that take user emotions into consideration. However, conventional systems only understand the intent of the inquiry and lack responses based on user emotions, resulting in a decline in user satisfaction.

[0350] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0351] In this invention, the server includes means for understanding a question received from a user using a natural language processing method, means for sentiment analysis to identify the emotions contained in the question, and means for searching a knowledge data store and obtaining relevant answers based on the analysis results and sentiment data. This makes it possible to provide personalized answers in an appropriate tone according to the user's emotions.

[0352] A "user" is the entity that accesses an information system and enters a question.

[0353] A "terminal" is a device used by users to input questions and is responsible for sending and receiving data with a server via communication means.

[0354] A "server" is a central processing unit that analyzes questions received from users, generates appropriate answers, and sends them to terminals.

[0355] "Natural language processing techniques" are technologies that convert text data received from users into a format that computers can understand, and then analyze its intent and context.

[0356] "Sentiment analysis" is a technique for identifying emotions from text data and processing information based on those emotions.

[0357] A "knowledge data store" is a repository of information resources that holds answers to user questions and retrieves and provides information as needed.

[0358] "Multilingual translation" is a technology that converts information expressed in one language into another language, providing answers that are tailored to the user's language settings.

[0359] A "generative model" is a computational model that generates new information or text based on machine learning.

[0360] This invention is implemented as an FAQ search system that takes user sentiment into consideration. When a user enters a question through the terminal interface, the terminal sends this question to the server. The server analyzes the intent of the question using natural language processing techniques. General natural language processing software is used for this analysis, and specific examples include open-source natural language processing libraries and cloud-based language services.

[0361] The server further utilizes a sentiment engine to perform sentiment analysis. This identifies the emotions contained in the user's question and processes them appropriately. The sentiment engine employs an algorithm that evaluates the sentiment of text based on machine learning.

[0362] Subsequently, the server searches the knowledge data store based on the analysis results and sentiment data to retrieve relevant answers. During this process, the tone of the answers is adjusted, taking sentiment data into consideration. A generative AI model is used to generate the answers, dynamically changing the tone and expression of the text. For example, a prompt such as, "The user is expressing dissatisfaction. Please generate an empathetic and polite response," can be used.

[0363] Furthermore, the server translates the answers using a multilingual translation service according to the user's language settings. Google Translate and other translation APIs are available here. The translated answers are sent to the device and displayed to the user.

[0364] In this way, users can receive more personalized answers tailored to their own situation. Because the system's responses address the user's emotions and specific needs, an improved user experience is expected.

[0365] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0366] Step 1:

[0367] The user enters and submits a question using the device's interface. This action generates the input question text data. The output is the submitted question data. Specifically, the user enters content such as "I am dissatisfied because the product has not arrived" using the keyboard or voice input function.

[0368] Step 2:

[0369] The terminal sends the user's question data to the server. This process involves data transfer from the terminal to the server. Specifically, the text data of the question is sent to the server as packets via the HTTP protocol. The input is the user's question data, and the output is the question data received by the server.

[0370] Step 3:

[0371] The server analyzes received question data using natural language processing techniques. The input is the question text data received by the server, and the output is the analyzed intent and main topic of the question. Specifically, a natural language processing engine is used to identify topics and extract keywords. For example, open-source libraries are used for the analysis.

[0372] Step 4:

[0373] The server uses an emotion engine to identify the emotions contained in a question. In this process, the question text to be analyzed is used as input, and user emotion data is generated as output. Specifically, a machine learning model identifies the emotions in the text, such as positive, negative, or neutral.

[0374] Step 5:

[0375] The server searches the knowledge data store based on the analysis results and sentiment data to retrieve relevant answers. The input is the analysis results and sentiment data, and the output is the relevant answers. Specifically, it uses SQL queries to access the data store and quickly retrieve matching FAQs.

[0376] Step 6:

[0377] The server considers sentiment data and adjusts the tone of the response. The input here is the initial response and sentiment data, and the output is the adjusted response. A generative AI model is used to change the tone of the sentence using prompt sentences, for example, instructions such as "Make it more empathetic."

[0378] Step 7:

[0379] The server translates the answer according to the user's language settings. The input is the adjusted answer, and the output is the answer in a language the user understands. A translation API is called to convert the answer to a specific language.

[0380] Step 8:

[0381] The server sends the final answer to the terminal. The input is the translated answer, and the output is the message sent to the terminal. In this process, the server sends the answer to the terminal as an HTTP response.

[0382] Step 9:

[0383] The terminal displays the received answer to the user. The input is the answer data received by the terminal, and the output is the answer displayed on the screen. The answer is clearly displayed in the user interface, and the user can confirm it.

[0384] (Application Example 2)

[0385] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0386] There is a growing need to provide prompt and appropriate answers to user questions and problems that arise when using a service, taking their emotions into consideration. However, conventional FAQ systems do not consider user emotions and generate non-personalized answers, which can lead to decreased customer satisfaction. This invention aims to improve the user experience when resolving problems by analyzing user emotions and providing personalized answers accordingly.

[0387] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0388] In this invention, the server includes means for understanding a question received from a user using natural language processing technology, means for searching a knowledge base based on the analysis results and sentiment data associated with the user to obtain relevant answers, and means for formatting the answers using a generation engine and providing them to the user in a tone adjusted according to their emotions. This makes it possible to quickly provide personalized answers that take into account the user's emotions.

[0389] "Natural language processing technology" is a technology that enables computers to understand and interpret questions and texts from users.

[0390] "Emotional data" refers to information data related to emotions, extracted from text and questions entered by users.

[0391] A "knowledge base" is a collection of information that stores answers to questions, and it is a database that is referenced to obtain appropriate answers.

[0392] A "generative engine" is a technology used to format acquired answers and express them in an appropriate tone, generating answers in a way that is easy for users to understand.

[0393] "Continuous dialogue" is a process in which the user and the system engage in a two-way conversation, dynamically generating answers and improving user satisfaction.

[0394] To implement the present invention, it is necessary to construct a system in which users, servers, and terminals work together. This system includes terminals equipped with a user interface, servers for data processing, and communication technology to coordinate them.

[0395] First, the user inputs a question containing emotions using a device such as a smartphone. This question is sent from the device to the server. The server uses natural language processing technology built with Python to analyze the content of the user's question, and then an emotion analysis engine retrieves the user's emotional data. This analysis reveals the user's specific intentions and emotional state. Next, the server retrieves relevant answers by referring to a knowledge base based on the analysis results. This knowledge base is a database that stores a wide range of information to address all possibilities.

[0396] The acquired answers are further refined using a generative AI model, shaping them into natural language and adjusting their tone and content according to the user's emotions. For example, if the system detects that the user is anxious, the answer is adjusted to a kind and empathetic tone. The final answers are translated into a language the user understands using a multilingual engine, enabling the system to serve a global user base. The device receives answers from the server and displays them to the user. The user can review the displayed answers and enter new questions. The server automatically updates its knowledge base upon receiving new questions, improving the system's response accuracy.

[0397] For example, if a user expresses anxiety about why their electronic payment isn't working, the server will sense their concern and generate a response such as, "Please rest assured. We will analyze the problem immediately and provide a solution." The AI ​​is then instructed with a prompt message such as, "Generate a response that will alleviate the user's anxiety regarding the electronic payment problem."

[0398] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0399] Step 1:

[0400] The user enters a question on the terminal interface and presses the submit button. This information is sent from the terminal to the server. The input consists of the user's question and its language information, and the output is the query data sent to the server.

[0401] Step 2:

[0402] When the server receives query data, it first uses natural language processing (NLP) techniques to analyze the intent of the question. The input is the text data of the question sent by the user, and the output is the analyzed intent data. The server then runs a text analysis tool to understand the meaning of the question.

[0403] Step 3:

[0404] The server uses an emotion analysis engine to detect the user's emotions from the query data. The input is the text data analyzed in step 2, and the output is the user's emotion data. In this step, the server runs an emotion classification model to identify the emotional state from the text.

[0405] Step 4:

[0406] The server searches a knowledge base based on intent and sentiment data to retrieve relevant answers. The input is the parsed intent and sentiment data, and the output is the relevant answer data. In this operation, the server executes database queries and selects the appropriate answer.

[0407] Step 5:

[0408] The server uses a generative AI model to format the answer data and adjust it appropriately to match the user's emotions. The input is the answer data and emotion data, and the output is the formatted answer text. In this step, the server operates the generative model to form natural and empathetic responses.

[0409] Step 6:

[0410] The server translates the formatted answer into the user's language using a multilingual engine. The input is the formatted answer text, and the output is the translated answer text. Here, the server applies the multilingual translation function to convert the answer into the specified language.

[0411] Step 7:

[0412] The server sends the translated final answer to the terminal. The terminal displays this answer to the user. The input is the translated answer text, and the output is the answer displayed on the user's terminal screen. In this final step, the terminal runs the answer display module and provides information to the user.

[0413] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0414] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0415] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0416] [Third Embodiment]

[0417] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0418] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0419] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0420] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0421] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0422] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0423] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0424] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0425] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0426] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0427] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0428] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0429] This invention is implemented as an FAQ search system that provides efficient and accurate answers to user inquiries. This system consists of a server, a terminal, and a user, and operates as follows.

[0430] First, the user enters a question through the terminal's interface. The terminal sends this question to the server. The server analyzes the received question using natural language processing technology to gain a deep understanding of the user's intent.

[0431] Once the analysis is complete, the server searches the knowledge database to retrieve relevant information. This database contains a well-organized collection of pre-answered questions. After retrieving the appropriate answer, the server formats it in a way that is easy for the user to understand. The server also translates the answer using a multilingual translation function based on the user's settings and geographical language settings.

[0432] After formatting the answer, the server sends it to the terminal, which then displays the answer to the user. The user can review this information and repeat the same process if they have further questions.

[0433] Furthermore, when the server detects a new question from a user, it automatically updates the knowledge database accordingly. This ensures that the entire system is always up-to-date and improves its ability to respond to similar questions in the future.

[0434] For example, if a user asks, "How do I apply for a new passport?", the server can instantly provide an answer including relevant laws and procedural information, translate that information into English if necessary, and display it to the user. This allows users to obtain the necessary information efficiently and quickly.

[0435] Thus, the system of the present invention, by incorporating natural language processing, knowledge database search, multilingual support, and automatic update functions, is capable of providing users with advanced information.

[0436] The following describes the processing flow.

[0437] Step 1:

[0438] The user accesses the terminal interface, enters a question, and presses submit. This question is sent from the terminal to the server as text data.

[0439] Step 2:

[0440] The server receives question data from the terminal and performs analysis using natural language processing technology. This analysis helps understand the intent of the question and extract important keywords and context.

[0441] Step 3:

[0442] The server searches the knowledge database based on the information obtained from the analysis. It queries for relevant answers and extracts information with a high degree of match.

[0443] Step 4:

[0444] The server formats the retrieved answers into a format that is easy for the user to understand. This is done using generative AI technology to improve the naturalness and appropriateness of the answers.

[0445] Step 5:

[0446] The server checks the user's language settings and translates the answers using its multilingual translation function as needed. This ensures that answers are available in the language specified by the user.

[0447] Step 6:

[0448] The server sends the final answer to the terminal. The terminal displays this information in the user interface.

[0449] Step 7:

[0450] The user reviews the answer displayed on their device and determines whether the solution to their question is appropriate. If necessary, they can enter additional questions and process the question again.

[0451] Step 8:

[0452] The server continues to interact with users in response to new questions and automatically updates its knowledge database. This ensures that it can stay up-to-date with the latest information.

[0453] (Example 1)

[0454] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0455] With the advancement of information technology in the modern era, there is a growing need for systems that can provide quick and accurate answers to a wide range of questions. However, existing FAQ systems suffer from issues such as insufficient accuracy in natural language processing, limitations in multilingual support, and delays in responding to new questions. As a result, users are unable to efficiently obtain the information they need, reducing the value of the system.

[0456] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0457] In this invention, the server includes means for understanding questions obtained from users using natural language processing technology, means for searching an information base and obtaining relevant information, means for translating and communicating in multiple languages ​​to the user, means for automatically updating the information base, and means for formatting answers based on the user's settings. As a result, users can quickly obtain the latest and most relevant information through continuous dialogue in multiple languages.

[0458] "User" refers to an individual or organization that attempts to obtain information using the system.

[0459] A "question" refers to a sentence or phrase that a user enters into the system via their device to inquire about knowledge or information.

[0460] "Natural language processing technology" refers to technologies that enable computers to understand and analyze human language, and includes morphological analysis and semantic analysis.

[0461] An "information base" refers to a collection of data containing numerous questions and their answers, which is managed as a database.

[0462] "Multilingual conversion" refers to the process of converting answers or information into multiple different languages.

[0463] "Automatically updating the information base" refers to the process of automatically adding or modifying the content of the information base based on newly detected questions and information.

[0464] "Formatting answers" refers to the process of arranging and organizing information in a way that is easy for users to understand and view.

[0465] "Continuous dialogue" refers to the process of providing step-by-step and sequential answers to the user's questions and maintaining the dialogue.

[0466] This invention is an FAQ search system that enables users to efficiently obtain the information they want. This system consists of three components: the user, the terminal, and the server.

[0467] The user enters their question via a terminal. A terminal refers to a device such as a smartphone or personal computer, which functions as a means of inputting and obtaining information through an interface. For example, the user might enter a question such as, "Please tell me how to apply for a new passport."

[0468] The terminal's role is to receive input from the user and send that data to the server. The terminal communicates with the server using the Internet Protocol and sends the user's input to the server.

[0469] After receiving a question from a user, the server performs analysis using natural language processing (NLP) techniques. Natural language processing models such as BERT and spaCy may be used for this analysis. Through this analysis, the server understands the user's intent and then searches an information base. This information base contains a large number of pre-registered questions and their answers, and database management systems such as MySQL and PostgreSQL are sometimes used.

[0470] The answers retrieved from the information base are formatted by the server into a user-friendly format. This formatting is done using a template engine such as Jinja2. Furthermore, depending on user settings and requirements, multilingual support is provided using the Google Translate API or similar multilingual translation software.

[0471] Prepared answers are sent from the server to the terminal, which then displays the answers to the user. This allows the user to quickly obtain the desired information. Furthermore, if a question is not yet registered in the information base, the server detects this and automatically updates it as new knowledge.

[0472] As a concrete example, an example prompt would be: "Please search for the information needed to answer the following question and prepare to answer the user in multiple languages: 'Please tell me how to apply for a new passport.'" This input is given to the generating AI model. Based on this prompt, the system provides information efficiently.

[0473] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0474] Step 1:

[0475] The user enters questions to obtain information using the terminal's interface. This input is passed to the terminal as natural language text data.

[0476] Step 2:

[0477] The terminal receives text input from the user and prepares to send it to the server. The text data is sent to the server via the Internet Protocol.

[0478] Step 3:

[0479] The server receives text data from the terminal and begins analysis using natural language processing technology. This analysis uses a generative AI model to understand the user's intent from the text data. Specifically, it performs morphological and semantic analysis and generates metadata of the intent as a result of the analysis.

[0480] Step 4:

[0481] Based on the analysis results, the server searches the information base. The information base stores relevant past questions and answers. The server uses a database management system to execute queries and extract highly relevant answer data.

[0482] Step 5:

[0483] The server formats the acquired answer data into a format suitable for user understanding. Specifically, it uses a template engine to generate dynamic HTML and performs multilingual translation as needed, depending on the user's language settings. A translation API is used for this purpose.

[0484] Step 6:

[0485] The server sends the formatted answer to the terminal as a data packet. Asynchronous communication is used in this process, and the answer is encoded in a standard format such as JSON.

[0486] Step 7:

[0487] The terminal receives the answer data from the server and displays it to the user. It renders the answers through a user interface so that the user can easily read them.

[0488] Step 8:

[0489] The user checks the answer displayed on the device. If further information is needed, they can enter a new question and repeat the process. This cycle allows the user to obtain information dynamically and continuously.

[0490] (Application Example 1)

[0491] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0492] In modern e-commerce platforms, there is a lack of efficient and accurate means for users to obtain product information. Furthermore, appropriate product recommendations based on user purchasing behavior are insufficient, highlighting the need for improved user experience.

[0493] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0494] In this invention, the server includes means for understanding questions received from the user using natural language processing technology, means for searching a knowledge database based on the analysis results to obtain relevant answers, and means for analyzing the user's purchase information to suggest relevant products. This enables the user to quickly obtain the necessary information and receive personalized product suggestions based on their purchasing behavior.

[0495] "Natural language processing technology" is a technology that analyzes questions from users in natural language and understands their intent and meaning.

[0496] A "knowledge database" is a collection of information that has accumulated prior answers to various questions, and is used to provide relevant information to users' questions.

[0497] "Multilingual translation" is a technology that converts acquired answers into different languages ​​and provides them according to the user's language settings.

[0498] "Automatic updates" is a function that keeps the system continuously up-to-date by adding information to the knowledge database whenever a new question is detected.

[0499] "Purchase information analysis" is a technology that analyzes a user's past purchase history and behavioral patterns, and then suggests highly relevant products based on that analysis.

[0500] The invention will now be described in terms of its embodiments. This system consists of a user, a terminal, and a server.

[0501] First, the process begins with the user entering a question through their device. The device then sends this question to a server via the internet. The server uses Google Cloud's Natural Language API to perform natural language analysis on the received question and understand the user's intent.

[0502] Once the analysis is complete, the server accesses a knowledge database stored in Google Cloud Firestore to search for relevant answers based on the analysis results. Simultaneously, it references a database containing the user's past purchase information to generate highly relevant product suggestions. This includes, in particular, pattern recognition based on the user's purchase history and interests.

[0503] The answers and product suggestions obtained are translated into multiple languages ​​based on the user's language settings using the Google Cloud Translation API. The server then sends the translated answers and related product information to the device. The device displays this information to the user and can accept further questions as needed.

[0504] For example, if a user asks for advice on purchasing a new smartphone, the server will suggest the latest model information and popular accessories, and also provide relevant reviews and usage guidelines.

[0505] An example of an input prompt for a generative AI model is, "Please recommend products for a specific event."

[0506] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0507] Step 1:

[0508] The user enters a question through the terminal. The terminal receives this input and sends its contents to the server. The input is text data from the user, and the output is data sent to the server.

[0509] Step 2:

[0510] The server analyzes received questions using Google Cloud's Natural Language API. The input is text data received from the user, and the output is information about the user's intent after analysis. In this process, natural language processing techniques are used to identify keywords and phrases within the text, and the data is processed to understand the user's intent.

[0511] Step 3:

[0512] Based on the analysis results, the server searches a knowledge database stored in Google Cloud Firestore to retrieve relevant answers. The input is a query based on the analysis results, and the output is text data containing the answer to the user. At this stage, data calculations are performed to select the appropriate answer using a database search algorithm.

[0513] Step 4:

[0514] The server analyzes the user's purchase history to suggest related products. The input is the user's past purchase data, and the output is information about recommended products. This process analyzes patterns based on past purchasing behavior and performs data analysis to select appropriate products.

[0515] Step 5:

[0516] The server translates the retrieved answers and product suggestions into multiple languages ​​based on the user's language settings. The input is the answers and suggested product information, and the output is the information translated into the user's display language. This process utilizes the Google Cloud Translation API to convert the data into the appropriate language.

[0517] Step 6:

[0518] The server sends the translated information to the terminal, which then displays it to the user. The input is translated text data, and the output is the display on the user's screen. This process involves receiving information via data communication and presenting it appropriately to the display device.

[0519] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0520] This invention is an FAQ search system that takes user emotions into consideration, providing more appropriate and personalized answers to user questions. This system is composed of three main components: a server, a terminal, and the user.

[0521] First, the user inputs a question through the terminal's interface and sends it. The terminal sends this question data to the server. The server analyzes the received question using natural language processing technology and an emotion engine. Natural language processing technology understands the intent of the question, and the emotion engine identifies the user's emotions expressed in the text.

[0522] The server searches a knowledge database based on the analysis results and sentiment data to retrieve relevant answers. At this time, the emotions identified by the sentiment engine are taken into consideration, and the tone and content of the answers are adjusted accordingly. For example, if the user is expressing frustration, a more empathetic and polite answer will be selected.

[0523] The answers are formatted using generational AI technology and adjusted to be easily understood by the user. The server then translates the answers according to the user's language settings and sends the final answers to the device. The device then displays these answers to the user.

[0524] The user can review the answer displayed on their device and, if necessary, enter additional questions to continue the conversation. The server quickly provides appropriate answers to the user's new questions and automatically updates its knowledge database.

[0525] For example, if a user asks, "I'm frustrated because my product hasn't arrived," the server recognizes this emotion and provides an empathetic and understanding response such as, "We apologize. Please wait a moment while we check the current delivery status." In this way, information provided to the user can be optimized, ensuring a better experience.

[0526] This system integrates natural language processing, an emotion engine, knowledge database search, multilingual support, and automatic update functions to provide users with appropriate and human-centered information.

[0527] The following describes the processing flow.

[0528] Step 1:

[0529] The user enters a question through the terminal's interface and presses the "Send" button. This question data is then sent from the terminal to the server.

[0530] Step 2:

[0531] The server receives question data from the terminal and analyzes the text using natural language processing technology. It extracts important keywords and context to understand the user's intent and the content of the question.

[0532] Step 3:

[0533] The server uses extracted keywords and contextual information to activate an emotion engine that identifies the user's emotions. This engine detects emotions such as joy, anger, and sadness, and also measures their intensity.

[0534] Step 4:

[0535] The server uses the analysis results and sentiment data to search the knowledge database. It retrieves relevant answers and formats them accordingly. In this process, it adjusts the tone and expression of the answers according to the emotions. For example, if anger is detected in the user's question, the answer will be adjusted to be more empathetic and polite.

[0536] Step 5:

[0537] The server checks the user's language settings and translates the formatted answers as needed. Multilingual support is used to translate the answers into the user's native language.

[0538] Step 6:

[0539] The server sends the final answer to the terminal, which then displays it on the user's screen. The user can then verify this answer.

[0540] Step 7:

[0541] The user can review the answer displayed on their device and enter additional questions if the question is not sufficiently resolved. As long as the interaction continues, the server will receive new questions and repeat the same analysis process.

[0542] Step 8:

[0543] The server records new user inquiries in the system and automatically updates the knowledge database, preparing for future use. This ensures that the system always provides the most up-to-date information.

[0544] (Example 2)

[0545] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0546] Modern interactive systems are required not only to provide factual information in response to user questions, but also to offer personalized answers that take user emotions into consideration. However, conventional systems only understand the intent of the inquiry and lack responses based on user emotions, resulting in a decline in user satisfaction.

[0547] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0548] In this invention, the server includes means for understanding a question received from a user using a natural language processing method, means for sentiment analysis to identify the emotions contained in the question, and means for searching a knowledge data store and obtaining relevant answers based on the analysis results and sentiment data. This makes it possible to provide personalized answers in an appropriate tone according to the user's emotions.

[0549] A "user" is the entity that accesses an information system and enters a question.

[0550] A "terminal" is a device used by a user to input questions and is responsible for sending and receiving data with a server via communication means.

[0551] A "server" is a central processing unit that analyzes questions received from users, generates appropriate answers, and sends them to terminals.

[0552] "Natural language processing techniques" are technologies that convert text data received from users into a format that computers can understand, and then analyze its intent and context.

[0553] "Sentiment analysis" is a technique for identifying emotions from text data and processing information based on those emotions.

[0554] A "knowledge data store" is a repository of information resources that holds answers to user questions and retrieves and provides information as needed.

[0555] "Multilingual translation" is a technology that converts information expressed in one language into another language, providing answers that are tailored to the user's language settings.

[0556] A "generative model" is a computational model that generates new information or text based on machine learning.

[0557] This invention is implemented as an FAQ search system that takes user sentiment into consideration. When a user enters a question through the terminal interface, the terminal sends this question to the server. The server analyzes the intent of the question using natural language processing techniques. General natural language processing software is used for this analysis, and specific examples include open-source natural language processing libraries and cloud-based language services.

[0558] The server further utilizes a sentiment engine to perform sentiment analysis. This identifies the emotions contained in the user's question and processes them appropriately. The sentiment engine employs an algorithm that evaluates the sentiment of text based on machine learning.

[0559] Subsequently, the server searches the knowledge data store based on the analysis results and sentiment data to retrieve relevant answers. During this process, the tone of the answers is adjusted, taking sentiment data into consideration. A generative AI model is used to generate the answers, dynamically changing the tone and expression of the text. For example, a prompt such as, "The user is expressing dissatisfaction. Please generate an empathetic and polite response," can be used.

[0560] Furthermore, the server translates the answers using a multilingual translation service according to the user's language settings. Google Translate and other translation APIs are available here. The translated answers are sent to the device and displayed to the user.

[0561] In this way, users can receive more personalized answers tailored to their own situation. Because the system's responses address the user's emotions and specific needs, an improved user experience is expected.

[0562] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0563] Step 1:

[0564] The user enters and submits a question using the device's interface. This action generates the input question text data. The output is the submitted question data. Specifically, the user enters content such as "I am dissatisfied because the product has not arrived" using the keyboard or voice input function.

[0565] Step 2:

[0566] The terminal sends the user's question data to the server. This process involves data transfer from the terminal to the server. Specifically, the text data of the question is sent to the server as packets via the HTTP protocol. The input is the user's question data, and the output is the question data received by the server.

[0567] Step 3:

[0568] The server analyzes received question data using natural language processing techniques. The input is the question text data received by the server, and the output is the analyzed intent and main topic of the question. Specifically, a natural language processing engine is used to identify topics and extract keywords. For example, open-source libraries are used for the analysis.

[0569] Step 4:

[0570] The server uses an emotion engine to identify the emotions contained in a question. In this process, the question text to be analyzed is used as input, and user emotion data is generated as output. Specifically, a machine learning model identifies the emotions in the text, such as positive, negative, or neutral.

[0571] Step 5:

[0572] The server searches the knowledge data store based on the analysis results and sentiment data to retrieve relevant answers. The input is the analysis results and sentiment data, and the output is the relevant answers. Specifically, it uses SQL queries to access the data store and quickly retrieve matching FAQs.

[0573] Step 6:

[0574] The server considers sentiment data and adjusts the tone of the response. The input here is the initial response and sentiment data, and the output is the adjusted response. A generative AI model is used to change the tone of the sentence using prompt sentences, for example, instructions such as "Make it more empathetic."

[0575] Step 7:

[0576] The server translates the answer according to the user's language settings. The input is the adjusted answer, and the output is the answer in a language the user understands. A translation API is called to convert the answer to a specific language.

[0577] Step 8:

[0578] The server sends the final answer to the terminal. The input is the translated answer, and the output is the message sent to the terminal. In this process, the server sends the answer to the terminal as an HTTP response.

[0579] Step 9:

[0580] The terminal displays the received answer to the user. The input is the answer data received by the terminal, and the output is the answer displayed on the screen. The answer is clearly displayed in the user interface, and the user can confirm it.

[0581] (Application Example 2)

[0582] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0583] There is a growing need to provide prompt and appropriate answers to user questions and problems that arise when using a service, taking their emotions into consideration. However, conventional FAQ systems do not consider user emotions and generate non-personalized answers, which can lead to decreased customer satisfaction. This invention aims to improve the user experience when resolving problems by analyzing user emotions and providing personalized answers accordingly.

[0584] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0585] In this invention, the server includes means for understanding a question received from a user using natural language processing technology, means for searching a knowledge base based on the analysis results and sentiment data associated with the user to obtain relevant answers, and means for formatting the answers using a generation engine and providing them to the user in a tone adjusted according to their emotions. This makes it possible to quickly provide personalized answers that take into account the user's emotions.

[0586] "Natural language processing technology" is a technology that enables computers to understand and interpret questions and texts from users.

[0587] "Emotional data" refers to information data related to emotions, extracted from text and questions entered by users.

[0588] A "knowledge base" is a collection of information that stores answers to questions, and it is a database that is referenced to obtain appropriate answers.

[0589] A "generative engine" is a technology used to format acquired answers and express them in an appropriate tone, generating answers in a way that is easy for users to understand.

[0590] "Continuous dialogue" is a process in which the user and the system engage in a two-way conversation, dynamically generating answers and improving user satisfaction.

[0591] To implement the present invention, it is necessary to construct a system in which users, servers, and terminals work together. This system includes terminals equipped with a user interface, servers for data processing, and communication technology to coordinate them.

[0592] First, the user inputs a question containing emotions using a device such as a smartphone. This question is sent from the device to the server. The server uses natural language processing technology built with Python to analyze the content of the user's question, and then an emotion analysis engine retrieves the user's emotional data. This analysis reveals the user's specific intentions and emotional state. Next, the server retrieves relevant answers by referring to a knowledge base based on the analysis results. This knowledge base is a database that stores a wide range of information to address all possibilities.

[0593] The acquired answers are further refined using a generative AI model, shaping them into natural language and adjusting their tone and content according to the user's emotions. For example, if the system detects that the user is anxious, the answer is adjusted to a kind and empathetic tone. The final answers are translated into a language the user understands using a multilingual engine, enabling the system to serve a global user base. The device receives answers from the server and displays them to the user. The user can review the displayed answers and enter new questions. The server automatically updates its knowledge base upon receiving new questions, improving the system's response accuracy.

[0594] For example, if a user expresses anxiety about why their electronic payment isn't working, the server will sense their concern and generate a response such as, "Please rest assured. We will analyze the problem immediately and provide a solution." The AI ​​is then instructed with a prompt message such as, "Generate a response that will alleviate the user's anxiety regarding the electronic payment problem."

[0595] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0596] Step 1:

[0597] The user enters a question on the terminal interface and presses the submit button. This information is sent from the terminal to the server. The input consists of the user's question and its language information, and the output is the query data sent to the server.

[0598] Step 2:

[0599] When the server receives query data, it first uses natural language processing (NLP) techniques to analyze the intent of the question. The input is the text data of the question sent by the user, and the output is the analyzed intent data. The server then runs a text analysis tool to understand the meaning of the question.

[0600] Step 3:

[0601] The server uses an emotion analysis engine to detect the user's emotions from the query data. The input is the text data analyzed in step 2, and the output is the user's emotion data. In this step, the server runs an emotion classification model to identify the emotional state from the text.

[0602] Step 4:

[0603] The server searches a knowledge base based on intent and sentiment data to retrieve relevant answers. The input is the parsed intent and sentiment data, and the output is the relevant answer data. In this operation, the server executes database queries and selects the appropriate answer.

[0604] Step 5:

[0605] The server uses a generative AI model to format the answer data and adjust it appropriately to match the user's emotions. The input is the answer data and emotion data, and the output is the formatted answer text. In this step, the server operates the generative model to form natural and empathetic responses.

[0606] Step 6:

[0607] The server translates the formatted answer into the user's language using a multilingual engine. The input is the formatted answer text, and the output is the translated answer text. Here, the server applies the multilingual translation function to convert the answer into the specified language.

[0608] Step 7:

[0609] The server sends the translated final answer to the terminal. The terminal displays this answer to the user. The input is the translated answer text, and the output is the answer displayed on the user's terminal screen. In this final step, the terminal runs the answer display module and provides information to the user.

[0610] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0611] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0612] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0613] [Fourth Embodiment]

[0614] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0615] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0616] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0617] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0618] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0619] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0620] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0621] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0622] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0623] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0624] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0625] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0626] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0627] This invention is implemented as an FAQ search system that provides efficient and accurate answers to user inquiries. This system consists of a server, a terminal, and a user, and operates as follows.

[0628] First, the user enters a question through the terminal's interface. The terminal sends this question to the server. The server analyzes the received question using natural language processing technology to gain a deep understanding of the user's intent.

[0629] Once the analysis is complete, the server searches the knowledge database to retrieve relevant information. This database contains a well-organized collection of pre-answered questions. After retrieving the appropriate answer, the server formats it in a way that is easy for the user to understand. The server also translates the answer using a multilingual translation function based on the user's settings and geographical language settings.

[0630] After formatting the answer, the server sends it to the terminal, which then displays the answer to the user. The user can review this information and repeat the same process if they have further questions.

[0631] Furthermore, when the server detects a new question from a user, it automatically updates the knowledge database accordingly. This ensures that the entire system is always up-to-date and improves its ability to respond to similar questions in the future.

[0632] For example, if a user asks, "How do I apply for a new passport?", the server can instantly provide an answer including relevant laws and procedural information, translate that information into English if necessary, and display it to the user. This allows users to obtain the necessary information efficiently and quickly.

[0633] Thus, the system of the present invention, by incorporating natural language processing, knowledge database search, multilingual support, and automatic update functions, is capable of providing users with advanced information.

[0634] The following describes the processing flow.

[0635] Step 1:

[0636] The user accesses the terminal interface, enters a question, and presses submit. This question is sent from the terminal to the server as text data.

[0637] Step 2:

[0638] The server receives question data from the terminal and performs analysis using natural language processing technology. This analysis helps understand the intent of the question and extract important keywords and context.

[0639] Step 3:

[0640] The server searches the knowledge database based on the information obtained from the analysis. It queries for relevant answers and extracts information with a high degree of match.

[0641] Step 4:

[0642] The server formats the retrieved answers into a format that is easy for the user to understand. This is done using generative AI technology to improve the naturalness and appropriateness of the answers.

[0643] Step 5:

[0644] The server checks the user's language settings and translates the answers using its multilingual translation function as needed. This ensures that answers are available in the language specified by the user.

[0645] Step 6:

[0646] The server sends the final answer to the terminal. The terminal displays this information in the user interface.

[0647] Step 7:

[0648] The user reviews the answer displayed on their device and determines whether the solution to their question is appropriate. If necessary, they can enter additional questions and process the question again.

[0649] Step 8:

[0650] The server continues to interact with users in response to new questions and automatically updates its knowledge database. This ensures that it can stay up-to-date with the latest information.

[0651] (Example 1)

[0652] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0653] With the advancement of information technology in the modern era, there is a growing need for systems that can provide quick and accurate answers to a wide range of questions. However, existing FAQ systems suffer from issues such as insufficient accuracy in natural language processing, limitations in multilingual support, and delays in responding to new questions. As a result, users are unable to efficiently obtain the information they need, reducing the value of the system.

[0654] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0655] In this invention, the server includes means for understanding questions obtained from users using natural language processing technology, means for searching an information base and obtaining relevant information, means for translating and communicating in multiple languages ​​to the user, means for automatically updating the information base, and means for formatting answers based on the user's settings. As a result, users can quickly obtain the latest and most relevant information through continuous dialogue in multiple languages.

[0656] "User" refers to an individual or organization that attempts to obtain information using the system.

[0657] A "question" refers to a sentence or phrase that a user enters into the system via their device to inquire about knowledge or information.

[0658] "Natural language processing technology" refers to technologies that enable computers to understand and analyze human language, and includes morphological analysis and semantic analysis.

[0659] An "information base" refers to a collection of data containing numerous questions and their answers, which is managed as a database.

[0660] "Multilingual conversion" refers to the process of converting answers or information into multiple different languages.

[0661] "Automatically updating the information base" refers to the process of automatically adding or modifying the content of the information base based on newly detected questions and information.

[0662] "Formatting answers" refers to the process of arranging and organizing information in a way that is easy for users to understand and view.

[0663] "Continuous dialogue" refers to the process of providing step-by-step and sequential answers to the user's questions and maintaining the dialogue.

[0664] This invention is an FAQ search system that enables users to efficiently obtain the information they want. This system consists of three components: the user, the terminal, and the server.

[0665] The user enters their question via a terminal. A terminal refers to a device such as a smartphone or personal computer, which functions as a means of inputting and obtaining information through an interface. For example, the user might enter a question such as, "Please tell me how to apply for a new passport."

[0666] The terminal's role is to receive input from the user and send that data to the server. The terminal communicates with the server using the Internet Protocol and sends the user's input to the server.

[0667] After receiving a question from a user, the server performs analysis using natural language processing (NLP) techniques. Natural language processing models such as BERT and spaCy may be used for this analysis. Through this analysis, the server understands the user's intent and then searches an information base. This information base contains a large number of pre-registered questions and their answers, and database management systems such as MySQL and PostgreSQL are sometimes used.

[0668] The answers retrieved from the information base are formatted by the server into a user-friendly format. This formatting is done using a template engine such as Jinja2. Furthermore, depending on user settings and requirements, multilingual support is provided using the Google Translate API or similar multilingual translation software.

[0669] Prepared answers are sent from the server to the terminal, which then displays the answers to the user. This allows the user to quickly obtain the desired information. Furthermore, if a question is not yet registered in the information base, the server detects this and automatically updates it as new knowledge.

[0670] As a concrete example, an example prompt would be: "Please search for the information needed to answer the following question and prepare to answer the user in multiple languages: 'Please tell me how to apply for a new passport.'" This input is given to the generating AI model. Based on this prompt, the system provides information efficiently.

[0671] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0672] Step 1:

[0673] The user enters questions to obtain information using the terminal's interface. This input is passed to the terminal as natural language text data.

[0674] Step 2:

[0675] The terminal receives text input from the user and prepares to send it to the server. The text data is sent to the server via the Internet Protocol.

[0676] Step 3:

[0677] The server receives text data from the terminal and begins analysis using natural language processing technology. This analysis uses a generative AI model to understand the user's intent from the text data. Specifically, it performs morphological and semantic analysis and generates metadata of the intent as a result of the analysis.

[0678] Step 4:

[0679] Based on the analysis results, the server searches the information base. The information base stores relevant past questions and answers. The server uses a database management system to execute queries and extract highly relevant answer data.

[0680] Step 5:

[0681] The server formats the acquired answer data into a format suitable for user understanding. Specifically, it uses a template engine to generate dynamic HTML and performs multilingual translation as needed, depending on the user's language settings. A translation API is used for this purpose.

[0682] Step 6:

[0683] The server sends the formatted answer to the terminal as a data packet. Asynchronous communication is used in this process, and the answer is encoded in a standard format such as JSON.

[0684] Step 7:

[0685] The terminal receives the answer data from the server and displays it to the user. It renders the answers through a user interface so that the user can easily read them.

[0686] Step 8:

[0687] The user checks the answer displayed on the device. If further information is needed, they can enter a new question and repeat the process. This cycle allows the user to obtain information dynamically and continuously.

[0688] (Application Example 1)

[0689] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0690] In modern e-commerce platforms, there is a lack of efficient and accurate means for users to obtain product information. Furthermore, appropriate product recommendations based on user purchasing behavior are insufficient, highlighting the need for improved user experience.

[0691] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0692] In this invention, the server includes means for understanding questions received from the user using natural language processing technology, means for searching a knowledge database based on the analysis results to obtain relevant answers, and means for analyzing the user's purchase information to suggest relevant products. This enables the user to quickly obtain the necessary information and receive personalized product suggestions based on their purchasing behavior.

[0693] "Natural language processing technology" is a technology that analyzes questions from users in natural language and understands their intent and meaning.

[0694] A "knowledge database" is a collection of information that has accumulated prior answers to various questions, and is used to provide relevant information to users' questions.

[0695] "Multilingual translation" is a technology that converts acquired answers into different languages ​​and provides them according to the user's language settings.

[0696] "Automatic updates" is a function that keeps the system continuously up-to-date by adding information to the knowledge database whenever a new question is detected.

[0697] "Purchase information analysis" is a technology that analyzes a user's past purchase history and behavioral patterns, and then suggests highly relevant products based on that analysis.

[0698] The invention will now be described in terms of its embodiments. This system consists of a user, a terminal, and a server.

[0699] First, the process begins with the user entering a question through their device. The device then sends this question to a server via the internet. The server uses Google Cloud's Natural Language API to perform natural language analysis on the received question and understand the user's intent.

[0700] Once the analysis is complete, the server accesses a knowledge database stored in Google Cloud Firestore to search for relevant answers based on the analysis results. Simultaneously, it references a database containing the user's past purchase information to generate highly relevant product suggestions. This includes, in particular, pattern recognition based on the user's purchase history and interests.

[0701] The answers and product suggestions obtained are translated into multiple languages ​​based on the user's language settings using the Google Cloud Translation API. The server then sends the translated answers and related product information to the device. The device displays this information to the user and can accept further questions as needed.

[0702] For example, if a user asks for advice on purchasing a new smartphone, the server will suggest the latest model information and popular accessories, and also provide relevant reviews and usage guidelines.

[0703] An example of an input prompt for a generative AI model is, "Please recommend products for a specific event."

[0704] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0705] Step 1:

[0706] The user enters a question through the terminal. The terminal receives this input and sends its contents to the server. The input is text data from the user, and the output is data sent to the server.

[0707] Step 2:

[0708] The server analyzes received questions using Google Cloud's Natural Language API. The input is text data received from the user, and the output is information about the user's intent after analysis. In this process, natural language processing techniques are used to identify keywords and phrases within the text, and the data is processed to understand the user's intent.

[0709] Step 3:

[0710] Based on the analysis results, the server searches a knowledge database stored in Google Cloud Firestore to retrieve relevant answers. The input is a query based on the analysis results, and the output is text data containing the answer to the user. At this stage, data calculations are performed to select the appropriate answer using a database search algorithm.

[0711] Step 4:

[0712] The server analyzes the user's purchase history to suggest related products. The input is the user's past purchase data, and the output is information about recommended products. This process analyzes patterns based on past purchasing behavior and performs data analysis to select appropriate products.

[0713] Step 5:

[0714] The server translates the retrieved answers and product suggestions into multiple languages ​​based on the user's language settings. The input is the answers and suggested product information, and the output is the information translated into the user's display language. This process utilizes the Google Cloud Translation API to convert the data into the appropriate language.

[0715] Step 6:

[0716] The server sends the translated information to the terminal, which then displays it to the user. The input is translated text data, and the output is the display on the user's screen. This process involves receiving information via data communication and presenting it appropriately to the display device.

[0717] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0718] This invention is an FAQ search system that takes user emotions into consideration, providing more appropriate and personalized answers to user questions. This system is composed of three main components: a server, a terminal, and the user.

[0719] First, the user inputs a question through the terminal's interface and sends it. The terminal sends this question data to the server. The server analyzes the received question using natural language processing technology and an emotion engine. Natural language processing technology understands the intent of the question, and the emotion engine identifies the user's emotions expressed in the text.

[0720] The server searches a knowledge database based on the analysis results and sentiment data to retrieve relevant answers. At this time, the emotions identified by the sentiment engine are taken into consideration, and the tone and content of the answers are adjusted accordingly. For example, if the user is expressing frustration, a more empathetic and polite answer will be selected.

[0721] The answers are formatted using generational AI technology and adjusted to be easily understood by the user. The server then translates the answers according to the user's language settings and sends the final answers to the device. The device then displays these answers to the user.

[0722] The user can review the answer displayed on their device and, if necessary, enter additional questions to continue the conversation. The server quickly provides appropriate answers to the user's new questions and automatically updates its knowledge database.

[0723] For example, if a user asks, "I'm frustrated because my product hasn't arrived," the server recognizes this emotion and provides an empathetic and understanding response such as, "We apologize. Please wait a moment while we check the current delivery status." In this way, information provided to the user can be optimized, ensuring a better experience.

[0724] This system integrates natural language processing, an emotion engine, knowledge database search, multilingual support, and automatic update functions to provide users with appropriate and human-centered information.

[0725] The following describes the processing flow.

[0726] Step 1:

[0727] The user enters a question through the terminal's interface and presses the "Send" button. This question data is then sent from the terminal to the server.

[0728] Step 2:

[0729] The server receives question data from the terminal and analyzes the text using natural language processing technology. It extracts important keywords and context to understand the user's intent and the content of the question.

[0730] Step 3:

[0731] The server uses extracted keywords and contextual information to activate an emotion engine that identifies the user's emotions. This engine detects emotions such as joy, anger, and sadness, and also measures their intensity.

[0732] Step 4:

[0733] The server uses the analysis results and sentiment data to search the knowledge database. It retrieves relevant answers and formats them accordingly. In this process, it adjusts the tone and expression of the answers according to the emotions. For example, if anger is detected in the user's question, the answer will be adjusted to be more empathetic and polite.

[0734] Step 5:

[0735] The server checks the user's language settings and translates the formatted answers as needed. Multilingual support is used to translate the answers into the user's native language.

[0736] Step 6:

[0737] The server sends the final answer to the terminal, which then displays it on the user's screen. The user can then verify this answer.

[0738] Step 7:

[0739] The user can review the answer displayed on their device and enter additional questions if the question is not sufficiently resolved. As long as the interaction continues, the server will receive new questions and repeat the same analysis process.

[0740] Step 8:

[0741] The server records new user inquiries in the system and automatically updates the knowledge database, preparing for future use. This ensures that the system always provides the most up-to-date information.

[0742] (Example 2)

[0743] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0744] Modern interactive systems are required not only to provide factual information in response to user questions, but also to offer personalized answers that take user emotions into consideration. However, conventional systems only understand the intent of the inquiry and lack responses based on user emotions, resulting in a decline in user satisfaction.

[0745] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0746] In this invention, the server includes means for understanding a question received from a user using a natural language processing method, means for sentiment analysis to identify the emotions contained in the question, and means for searching a knowledge data store and obtaining relevant answers based on the analysis results and sentiment data. This makes it possible to provide personalized answers in an appropriate tone according to the user's emotions.

[0747] A "user" is the entity that accesses an information system and enters a question.

[0748] A "terminal" is a device used by a user to input questions and is responsible for sending and receiving data with a server via communication means.

[0749] A "server" is a central processing unit that analyzes questions received from users, generates appropriate answers, and sends them to terminals.

[0750] "Natural language processing techniques" are technologies that convert text data received from users into a format that computers can understand, and then analyze its intent and context.

[0751] "Sentiment analysis" is a technique for identifying emotions from text data and processing information based on those emotions.

[0752] A "knowledge data store" is a repository of information resources that holds answers to user questions and retrieves and provides information as needed.

[0753] "Multilingual translation" is a technology that converts information expressed in one language into another language, providing answers that are tailored to the user's language settings.

[0754] A "generative model" is a computational model that generates new information or text based on machine learning.

[0755] This invention is implemented as an FAQ search system that takes user sentiment into consideration. When a user enters a question through the terminal interface, the terminal sends this question to the server. The server analyzes the intent of the question using natural language processing techniques. General natural language processing software is used for this analysis, and specific examples include open-source natural language processing libraries and cloud-based language services.

[0756] The server further utilizes a sentiment engine to perform sentiment analysis. This identifies the emotions contained in the user's question and processes them appropriately. The sentiment engine employs an algorithm that evaluates the sentiment of text based on machine learning.

[0757] Subsequently, the server searches the knowledge data store based on the analysis results and sentiment data to retrieve relevant answers. During this process, the tone of the answers is adjusted, taking sentiment data into consideration. A generative AI model is used to generate the answers, dynamically changing the tone and expression of the text. For example, a prompt such as, "The user is expressing dissatisfaction. Please generate an empathetic and polite response," can be used.

[0758] Furthermore, the server translates the answers using a multilingual translation service according to the user's language settings. Google Translate and other translation APIs are available here. The translated answers are sent to the device and displayed to the user.

[0759] In this way, users can receive more personalized answers tailored to their own situation. Because the system's responses address the user's emotions and specific needs, an improved user experience is expected.

[0760] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0761] Step 1:

[0762] The user enters and submits a question using the device's interface. This action generates the input question text data. The output is the submitted question data. Specifically, the user enters content such as "I am dissatisfied because the product has not arrived" using the keyboard or voice input function.

[0763] Step 2:

[0764] The terminal sends the user's question data to the server. This process involves data transfer from the terminal to the server. Specifically, the text data of the question is sent to the server as packets via the HTTP protocol. The input is the user's question data, and the output is the question data received by the server.

[0765] Step 3:

[0766] The server analyzes received question data using natural language processing techniques. The input is the question text data received by the server, and the output is the analyzed intent and main topic of the question. Specifically, a natural language processing engine is used to identify topics and extract keywords. For example, open-source libraries are used for the analysis.

[0767] Step 4:

[0768] The server uses an emotion engine to identify the emotions contained in a question. In this process, the question text to be analyzed is used as input, and user emotion data is generated as output. Specifically, a machine learning model identifies the emotions in the text, such as positive, negative, or neutral.

[0769] Step 5:

[0770] The server searches the knowledge data store based on the analysis results and sentiment data to retrieve relevant answers. The input is the analysis results and sentiment data, and the output is the relevant answers. Specifically, it uses SQL queries to access the data store and quickly retrieve matching FAQs.

[0771] Step 6:

[0772] The server considers sentiment data and adjusts the tone of the response. The input here is the initial response and sentiment data, and the output is the adjusted response. A generative AI model is used to change the tone of the sentence using prompt sentences, for example, instructions such as "Make it more empathetic."

[0773] Step 7:

[0774] The server translates the answer according to the user's language settings. The input is the adjusted answer, and the output is the answer in a language the user understands. A translation API is called to convert the answer to a specific language.

[0775] Step 8:

[0776] The server sends the final answer to the terminal. The input is the translated answer, and the output is the message sent to the terminal. In this process, the server sends the answer to the terminal as an HTTP response.

[0777] Step 9:

[0778] The terminal displays the received answer to the user. The input is the answer data received by the terminal, and the output is the answer displayed on the screen. The answer is clearly displayed in the user interface, and the user can confirm it.

[0779] (Application Example 2)

[0780] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0781] There is a growing need to provide prompt and appropriate answers to user questions and problems that arise when using a service, taking their emotions into consideration. However, conventional FAQ systems do not consider user emotions and generate non-personalized answers, which can lead to decreased customer satisfaction. This invention aims to improve the user experience when resolving problems by analyzing user emotions and providing personalized answers accordingly.

[0782] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0783] In this invention, the server includes means for understanding a question received from a user using natural language processing technology, means for searching a knowledge base based on the analysis results and sentiment data associated with the user to obtain relevant answers, and means for formatting the answers using a generation engine and providing them to the user in a tone adjusted according to their emotions. This makes it possible to quickly provide personalized answers that take into account the user's emotions.

[0784] "Natural language processing technology" is a technology that enables computers to understand and interpret questions and texts from users.

[0785] "Emotional data" refers to information data related to emotions, extracted from text and questions entered by users.

[0786] A "knowledge base" is a collection of information that stores answers to questions, and it is a database that is referenced to obtain appropriate answers.

[0787] A "generative engine" is a technology used to format acquired answers and express them in an appropriate tone, generating answers in a way that is easy for users to understand.

[0788] "Continuous dialogue" is a process in which the user and the system engage in a two-way conversation, dynamically generating answers and improving user satisfaction.

[0789] To implement the present invention, it is necessary to construct a system in which users, servers, and terminals work together. This system includes terminals equipped with a user interface, servers for data processing, and communication technology to coordinate them.

[0790] First, the user inputs a question containing emotions using a device such as a smartphone. This question is sent from the device to the server. The server uses natural language processing technology built with Python to analyze the content of the user's question, and then an emotion analysis engine retrieves the user's emotional data. This analysis reveals the user's specific intentions and emotional state. Next, the server retrieves relevant answers by referring to a knowledge base based on the analysis results. This knowledge base is a database that stores a wide range of information to address all possibilities.

[0791] The acquired answers are further refined using a generative AI model, shaping them into natural language and adjusting their tone and content according to the user's emotions. For example, if the system detects that the user is anxious, the answer is adjusted to a kind and empathetic tone. The final answers are translated into a language the user understands using a multilingual engine, enabling the system to serve a global user base. The device receives answers from the server and displays them to the user. The user can review the displayed answers and enter new questions. The server automatically updates its knowledge base upon receiving new questions, improving the system's response accuracy.

[0792] For example, if a user expresses anxiety about why their electronic payment isn't working, the server will sense their concern and generate a response such as, "Please rest assured. We will analyze the problem immediately and provide a solution." The AI ​​is then instructed with a prompt message such as, "Generate a response that will alleviate the user's anxiety regarding the electronic payment problem."

[0793] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0794] Step 1:

[0795] The user enters a question on the terminal interface and presses the submit button. This information is sent from the terminal to the server. The input consists of the user's question and its language information, and the output is the query data sent to the server.

[0796] Step 2:

[0797] When the server receives query data, it first uses natural language processing (NLP) techniques to analyze the intent of the question. The input is the text data of the question sent by the user, and the output is the analyzed intent data. The server then runs a text analysis tool to understand the meaning of the question.

[0798] Step 3:

[0799] The server uses an emotion analysis engine to detect the user's emotions from the query data. The input is the text data analyzed in step 2, and the output is the user's emotion data. In this step, the server runs an emotion classification model to identify the emotional state from the text.

[0800] Step 4:

[0801] The server searches a knowledge base based on intent and sentiment data to retrieve relevant answers. The input is the parsed intent and sentiment data, and the output is the relevant answer data. In this operation, the server executes database queries and selects the appropriate answer.

[0802] Step 5:

[0803] The server uses a generative AI model to format the answer data and adjust it appropriately to match the user's emotions. The input is the answer data and emotion data, and the output is the formatted answer text. In this step, the server operates the generative model to form natural and empathetic responses.

[0804] Step 6:

[0805] The server translates the formatted answer into the user's language using a multilingual engine. The input is the formatted answer text, and the output is the translated answer text. Here, the server applies the multilingual translation function to convert the answer into the specified language.

[0806] Step 7:

[0807] The server sends the translated final answer to the terminal. The terminal displays this answer to the user. The input is the translated answer text, and the output is the answer displayed on the user's terminal screen. In this final step, the terminal runs the answer display module and provides information to the user.

[0808] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0809] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0810] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0811] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0812] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0813] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0814] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0815] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0816] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0817] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0818] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0819] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0820] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0821] 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.

[0822] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0823] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0824] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0825] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0826] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0827] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0828] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0829] The following is further disclosed regarding the embodiments described above.

[0830] (Claim 1)

[0831] A means of understanding questions received from users using natural language processing technology,

[0832] A means for searching a knowledge database based on the aforementioned analysis results and obtaining relevant answers,

[0833] A means for translating the aforementioned answer into multiple languages ​​and sending it to the user,

[0834] A means to automatically update the knowledge database when a new question is detected,

[0835] A system that includes this.

[0836] (Claim 2)

[0837] The system according to claim 1, characterized in that the natural language processing technique utilizes a generative model.

[0838] (Claim 3)

[0839] The system according to claim 1, further comprising means for performing a continuous dialogue with user input and dynamically generating an answer.

[0840] "Example 1"

[0841] (Claim 1)

[0842] A means of understanding questions obtained from users using natural language processing technology,

[0843] A means for searching an information base and obtaining related information based on the aforementioned analysis results,

[0844] A means for converting the aforementioned information into multiple languages ​​and transmitting it to the user,

[0845] A means to automatically update the information base when a new question is detected,

[0846] A means of formatting the answer based on the user's settings,

[0847] A means of receiving input from users and conducting continuous dialogue,

[0848] A system that includes this.

[0849] (Claim 2)

[0850] The system according to claim 1, characterized in that the natural language processing technique uses a generative model.

[0851] (Claim 3)

[0852] The system according to claim 1, further comprising means for dynamically generating information based on user input.

[0853] "Application Example 1"

[0854] (Claim 1)

[0855] A means of understanding questions received from users using natural language processing technology,

[0856] A means for searching a knowledge database based on the aforementioned analysis results and obtaining relevant answers,

[0857] A means for translating the aforementioned answer into multiple languages ​​and sending it to the user,

[0858] A means to automatically update the knowledge database when a new question is detected,

[0859] A method for analyzing user purchase information and suggesting related products,

[0860] A system that includes this.

[0861] (Claim 2)

[0862] The system according to claim 1, characterized in that the natural language processing technique utilizes a generative model.

[0863] (Claim 3)

[0864] The system according to claim 1, further comprising means for performing a continuous dialogue with user input and dynamically generating an answer.

[0865] "Example 2 of combining an emotion engine"

[0866] (Claim 1)

[0867] A means of understanding questions received from users using natural language processing techniques,

[0868] A means of emotional analysis to identify the emotions included in the aforementioned question,

[0869] A means for searching a knowledge data store based on the aforementioned analysis results and sentiment data to obtain relevant answers,

[0870] A means for adjusting the tone of the response in consideration of the aforementioned emotional data,

[0871] A means for translating the aforementioned answer into multiple languages ​​and sending it to the user,

[0872] A means to automatically update the knowledge data store when a new question is detected,

[0873] A system that includes this.

[0874] (Claim 2)

[0875] The system according to claim 1, characterized in that the natural language processing method utilizes a generative model and performs response adjustments based on sentiment analysis.

[0876] (Claim 3)

[0877] The system according to claim 1, further comprising means for performing continuous dialogue in response to user input, dynamically generating answers, and providing emotion-based responses.

[0878] "Application example 2 when combining with an emotional engine"

[0879] (Claim 1)

[0880] A means of understanding questions received from users using natural language processing technology,

[0881] A means for searching a knowledge base based on the aforementioned analysis results and sentiment data associated with the user, and obtaining relevant answers,

[0882] A means of formatting the aforementioned answer using a generation engine and providing it to the user in a tone adjusted according to emotion,

[0883] A means for translating the aforementioned answer into multiple languages ​​and sending it to the user,

[0884] A means to automatically update the knowledge base when a new question is detected,

[0885] A system that includes this.

[0886] (Claim 2)

[0887] The system according to claim 1, characterized in that the natural language processing technology and the emotion data processing technology utilize generative models.

[0888] (Claim 3)

[0889] The system according to claim 1, further comprising means for performing a continuous dialogue based on sentiment analysis in response to user input and dynamically generating an answer. [Explanation of Symbols]

[0890] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of understanding questions received from users using natural language processing technology, A means for searching a knowledge database based on the aforementioned analysis results and obtaining relevant answers, A means for translating the aforementioned answer into multiple languages ​​and sending it to the user, A means to automatically update the knowledge database when a new question is detected, A system that includes this.

2. The system according to claim 1, characterized in that the natural language processing technique utilizes a generative model.

3. The system according to claim 1, further comprising means for performing a continuous dialogue with user input and dynamically generating an answer.

Images