system

Abstract

We provide the system. [Solution] Means of receiving information from users, A means of analyzing received information using natural language processing to identify the user's intent, A means for searching a specified database and extracting relevant information based on the identified intent, A means of generating natural language sentences based on extracted information, A system including means for sending generated natural language sentences to a user.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, 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] There is a problem that a lot of time is spent on searching for information regarding employee regulations and procedures within a company, resulting in a decrease in productivity. Also, since the information is divided complexly, it is difficult to quickly access the necessary procedures and regulations. Such a situation has led to an increase in costs in the personnel department and a decrease in the work efficiency of employees. Furthermore, when immediate responses to complex questions or specific situations are required, additional burdens arise.

Means for Solving the Problems

[0005] This invention provides a system that analyzes user inquiries using natural language processing to identify their intent, thereby enabling rapid and accurate searching of the company's internal database. Based on the analysis results, it extracts relevant information and converts that information into natural language sentences using a generation AI, enabling the immediate delivery of appropriate answers to users. Furthermore, it includes a function to automatically notify the human resources department under certain conditions and escalate inquiries as needed, achieving sophisticated problem-solving while minimizing human intervention. It also incorporates means to improve the accuracy of the generated answers using machine learning algorithms, thereby enhancing the reliability of the information provided.

[0006] A "user" is someone who uses a system to obtain information or make inquiries.

[0007] "Information" refers to data such as questions and keywords that users input into the system.

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

[0009] "Intention" refers to the purpose or desired outcome of an action, which is analyzed from the information entered by the user.

[0010] A "regulations database" is a system that stores data related to a company's employment regulations and personnel policies.

[0011] "Extracting information" is the operation of retrieving relevant information from a database.

[0012] "Generative AI" is a system that uses artificial intelligence technology to generate natural-sounding text from data.

[0013] "Natural language sentences" are sentences written using expressions that humans use in everyday life.

[0014] "Transmission" refers to the operation of transferring data for the system to provide information to the user.

[0015] "Escalation" refers to the process of passing on a problem to a more specialized responder under specific conditions.

[0016] "Machine learning algorithm" refers to a technology for learning patterns from data and making future predictions and classifications.

Brief Description of Drawings

[0017] [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] [[ID=3l]]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 multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple 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 Embodiment 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Mode for Carrying Out the Invention

[0018] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0021] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0022] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0023] 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).

[0024] 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."

[0025] [First Embodiment]

[0026] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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".

[0038] This invention provides a system that enables employees within a company to access information regarding regulations and procedures more quickly and easily. The system is configured to process user inquiries and provide necessary information by analyzing the user's intent using natural language processing technology.

[0039] Specifically, the system will be implemented as follows: Users will use a chatbot interface via their device to input the information they want to know. For example, if a user inputs the question, "How many days of paid leave are there?", the device will send this input to the server in real time.

[0040] The server analyzes the received user input using natural language processing. Through this analysis, the server identifies keywords such as "paid leave" and "number of days," and determines the information the user wants to know. Next, based on the identified intent, it searches the company's internal database and extracts the relevant information.

[0041] The extracted information is converted into natural language sentences that are easy for the user to understand by a generating AI. For example, it might be sent to the user's device in a format like "Your annual paid leave is 20 days" and displayed in the chatbot window.

[0042] Furthermore, if the information entered by the user does not meet certain conditions, or if a complex question arises that the AI ​​cannot resolve, the server will notify the HR department and appropriately escalate the inquiry. This process allows users to quickly obtain the correct information, and enables HR personnel to smoothly handle complex situations.

[0043] This system also utilizes machine learning algorithms, which improve the accuracy and reliability of the information it generates. For example, it improves its understanding of user intent with each use, enabling more accurate and efficient responses to similar questions. This significantly reduces the time employees spend gathering information, leading to improved operational efficiency and cost savings for the HR department.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The user uses their device to enter a question into the chatbot interface. For example, they might enter information in the form of, "Please tell me the number of paid vacation days."

[0047] Step 2:

[0048] The terminal transmits user input to the server in real time. During this process, it verifies that the data is transmitted correctly over the network.

[0049] Step 3:

[0050] The server analyzes the received input using natural language processing techniques to identify the user's intent. The analysis process utilizes algorithms for keyword extraction and contextual understanding.

[0051] Step 4:

[0052] Based on the identified intent, the server searches the company's internal regulations database. This database contains information about employment rules and personnel policies.

[0053] Step 5:

[0054] The server extracts relevant information from the database. For example, it might retrieve data containing the number of paid leave days.

[0055] Step 6:

[0056] The server uses a generative AI to generate natural language sentences that the user can understand based on the extracted information. For example, it can generate sentences such as, "Your annual paid leave is 20 days."

[0057] Step 7:

[0058] The server sends the generated response to the terminal, which then displays it to the user via a chatbot interface. The user can then view this and obtain the necessary information.

[0059] Step 8:

[0060] If a user asks further questions or makes a complex request, the server will re-analyze the content and, if necessary, escalate it to the HR department. The HR personnel will receive a notification so they can respond immediately.

[0061] (Example 1)

[0062] 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."

[0063] There is a growing need to expedite and facilitate employees' access to information regarding regulations and procedures within companies. However, traditional methods suffer from the problem of time-consuming information retrieval and difficulty in handling complex inquiries. Furthermore, there is a need for methods to improve the accuracy of the information users seek and to increase the efficiency of inquiry processing.

[0064] 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.

[0065] In this invention, the server includes means for acquiring data from a user, means for analyzing the acquired data using natural language processing technology to clarify the user's intent, and means for searching an information base and acquiring relevant data based on the clarified intent. This enables the rapid and appropriate provision of information within a company.

[0066] A "user" refers to an individual or legal entity that attempts to obtain information using the system.

[0067] "Data" refers to information about questions and requests obtained from users.

[0068] "Natural language processing technology" refers to computer technology used to analyze acquired data and identify its intent.

[0069] "Intent" refers to the purpose or necessary information that the user is seeking from the system.

[0070] An "information base" refers to a database that contains information about company regulations and procedures.

[0071] "Means of acquiring data" refers to the process of importing user data into the server.

[0072] "Relevant data" refers to the relevant information retrieved from the information base based on the user's identified intent.

[0073] "Methods for constructing natural language sentences" refers to the process of converting acquired relevant data into language that humans can understand.

[0074] A "notification" refers to a message sent to another department to inform them that a user's inquiry does not meet certain criteria.

[0075] "Machine learning technology" refers to algorithms that learn from data and apply the results to improve the performance of a system.

[0076] This system aims to quickly provide employees with information on regulations and procedures they need within a company. The system consists of the following elements:

[0077] Users log in to the chatbot interface on their device via the internet and enter the necessary information in text format. PCs and smartphones can be used as devices, and they access the system through a web browser.

[0078] The terminal sends data entered by the user to the server using the HTTPS protocol. The server is equipped with natural language processing technology for analysis, specifically using libraries such as spaCy and NLTK.

[0079] The server analyzes the received data using natural language processing to identify the user's intent. Based on this identified intent, the server issues SQL queries to the company's internal regulations database to retrieve relevant information. The database stores various regulations and procedural information set by the company.

[0080] The extracted information is converted into natural language sentences on the server using a generative AI model. For example, OpenAI's language model may be used as the generative AI. This generates easy-to-understand response sentences to questions entered by the user. A concrete example of such a response might be, "Your annual paid leave is 20 days."

[0081] The generated natural language text is sent back from the server to the user's device and displayed in the chatbot interface on the device. This interface provides information to the user in real time, improving the user experience.

[0082] Furthermore, if user input does not meet the requirements, or if a complex inquiry arises that cannot be resolved by the system, the server will automatically use its communication function to send an escalation notification to the appropriate department within the company.

[0083] A concrete example of a prompt message would be, "According to company regulations, how many paid leave days am I entitled to?" In this way, information tailored to the individual needs of the user is provided.

[0084] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0085] Step 1:

[0086] The user accesses the chatbot interface on their device and enters the information they want in text format. Specifically, this involves entering a sentence such as, "How many days of paid leave do I have?" This input becomes the data for the next process.

[0087] Step 2:

[0088] The terminal sends text data entered by the user to the server using the HTTPS protocol. Specifically, the terminal's actions include encoding the input data and sending it to the server via a secure communication channel. This prepares the server for analysis.

[0089] Step 3:

[0090] The server analyzes the received text data using natural language processing techniques. Specifically, it uses a natural language processing library to extract keywords such as "paid leave" and "number of days" to identify the user's intent. The output of this step is the analyzed intent.

[0091] Step 4:

[0092] The server searches the company's information base based on the identified intent. The server executes an SQL query to retrieve "paid leave" related information from the database. The input to this process is the previously identified intent, and the output is user-related paid leave information.

[0093] Step 5:

[0094] The server inputs the acquired data into a generative AI model to generate natural language sentences that are easy for the user to understand. For example, the generative AI model generates the response sentence, "Your annual paid leave is 20 days." The output of this step is natural language sentences.

[0095] Step 6:

[0096] The server sends the generated natural language sentence to the terminal. Specifically, the server encodes the sentence using a secure communication protocol and sends it to the terminal. This output is the natural language sentence that reaches the user's terminal.

[0097] Step 7:

[0098] The terminal displays the received natural language text in the chatbot interface. Through this interface, the user can visually confirm the information provided by the server. In this step, the input is natural language text from the server, and the output is the display on the terminal.

[0099] (Application Example 1)

[0100] 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."

[0101] Conventional home personal assistant robots have struggled to accurately process and provide individual information such as household rules and schedules. Conversational information provision requires correctly understanding the user's intentions and responding to diverse information needs. However, limitations in voice input accuracy and natural language processing often prevented appropriate responses. This resulted in limited user convenience and hindered the smooth progress of tasks and activities within the home.

[0102] 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.

[0103] In this invention, the server includes means for receiving information from a user, means for converting the received information into text data using a speech recognition processing device, and means for providing a knowledge base for providing information within the home and for quickly suggesting relevant information. This makes it possible to more accurately grasp the user's intentions and to provide relevant home information quickly and appropriately.

[0104] "Means of receiving information from users" refers to functions that acquire data input from users in the form of voice or text.

[0105] "Natural language processing" is a technology that uses computers to analyze human language and understand its meaning.

[0106] A "speech recognition processing device" is a device or software that analyzes speech input as a digital signal and converts it into text data.

[0107] "Rules and regulations" refer to aggregated data such as guidelines, schedules, and procedures that apply both inside and outside the home.

[0108] A "knowledge base" is a database where information in a specific domain is stored and can be searched as needed.

[0109] "Machine learning techniques" are technologies that allow computers to learn patterns from data and apply them to future predictions and classifications.

[0110] "Escalation" is the process of raising a problem or inquiry to a higher level of support if it cannot be resolved.

[0111] To implement this invention, a personal assistant robot for home use is required to have the following configuration: The robot is equipped with a voice recognition processing unit that receives information from the user's voice and converts it into text data. The converted text is sent to a server, where natural language processing technology is used to analyze the user's intent.

[0112] Based on the analyzed intent, the server searches its knowledge base for relevant rule information and extracts the necessary data. This allows the robot to provide the user with information about household rules and schedules. The extracted data is then converted into user-friendly natural language using a generative AI model and presented to the user in either audio or text format.

[0113] For example, if a user says, "Tell me what's on the schedule for today," the robot might respond with something like, "We have a family dinner at 7 PM." An example of a prompt for the generative AI model would be, "Based on the rules of this household, answer the following question: 'What's the task for today?'"

[0114] The hardware and software used include voice recognition devices such as Amazon Alexa and Google Home®, speech-to-text services such as Google® Cloud Speech-to-Text and Amazon Transcribe, and natural language processing and generative AI models such as Python's Natural Language Toolkit (NLTK) and OpenAI's GPT. In this way, the invention significantly improves the convenience of information access in the home environment.

[0115] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0116] Step 1:

[0117] The user inputs a question to the robot via voice. This voice data is converted into a digital signal by the robot's voice recognition processing unit. This process then converts the voice data into text data.

[0118] Step 2:

[0119] The device sends text data obtained through speech recognition to the server. The server receives this text data and analyzes the user's intent using natural language processing technology. In this process, the server extracts context and keywords to understand the user's request.

[0120] Step 3:

[0121] Based on the analyzed user intent, the server searches its internal knowledge base for relevant rule information. This process uses a search algorithm to identify information that matches the request and extracts the necessary data.

[0122] Step 4:

[0123] The server converts the extracted data into natural language sentences using a generative AI model. Here, the generative AI model processes the data and reconstructs it into sentences that are easy for the user to understand. This output is generated in text format.

[0124] Step 5:

[0125] The server sends the generated natural language text to the terminal, which then presents it to the user as either audio or text. The robot then uses the terminal to provide an appropriate response to the user's original question.

[0126] 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.

[0127] This invention provides a system that incorporates an emotion engine to recognize a user's emotions and utilize that information to provide appropriate natural language responses. This system processes user inquiries and, through emotion analysis, enables more personalized information delivery.

[0128] Specifically, users use their devices to input questions and requests through a chatbot interface. For example, they might ask, "I want to take paid leave, but the procedure seems complicated." The device then sends this input to the server.

[0129] When the server receives input information, it applies natural language processing techniques to analyze the user's intent. It also uses an emotion engine to identify the user's emotions from the input text. This emotion information can be expressed as a string, for example, "anxiety" or "frustration."

[0130] Based on the analyzed intent and emotional information, the server searches the company's internal database and extracts relevant information. During this process, consideration is given to providing the information in an appropriate tone and phrasing that reflects the user's emotions. Using generative AI, the extracted information is converted into natural language sentences, generating responses such as, "Don't worry. The procedure is simple, and you can take 20 days of paid leave per year."

[0131] The generated response is sent from the server to the terminal, and the user can view it through the chatbot interface. If the user's emotions are particularly negative, or if the AI ​​determines that the issue is too complex for it to handle, the server automatically notifies the HR department to prompt a quick response.

[0132] This system also leverages machine learning algorithms to accumulate and analyze users' emotional history, further improving the accuracy and personalization of responses in future interactions. This approach makes it possible to provide more empathetic and accurate support for employees' questions and concerns.

[0133] The following describes the processing flow.

[0134] Step 1:

[0135] The user uses their device to enter a question into the chatbot interface. For example, they might send a message like, "I'm worried because the paid leave application process is complicated."

[0136] Step 2:

[0137] The terminal sends the entered message to the server. This transmission takes place over the network.

[0138] Step 3:

[0139] The server analyzes received messages using natural language processing technology to identify the user's intentions and requests.

[0140] Step 4:

[0141] The server uses an emotion engine to recognize emotions from the user's text. For example, it can identify the emotion "anxiety" from a message.

[0142] Step 5:

[0143] The server searches the company's internal database based on intent and sentiment information, extracting information relevant to the user's inquiry.

[0144] Step 6:

[0145] The server uses a generative AI to convert the extracted information into natural language sentences. Taking emotional information into consideration, it generates sentences in a tone such as, "Please rest assured. The paid leave process is simple, and we will support you if needed."

[0146] Step 7:

[0147] The server sends the generated natural language response to the terminal.

[0148] Step 8:

[0149] The device displays the received response to the user through a chatbot interface. The user can then view this information and resolve any questions or concerns they may have.

[0150] Step 9:

[0151] The server automatically notifies the HR department if the user's emotions are particularly negative, and escalates the inquiry as needed. This allows the HR department to respond quickly.

[0152] Step 10:

[0153] The server stores user interaction history and sentiment information, which is then analyzed using machine learning algorithms. This improves the accuracy of future user responses and enhances personalized service.

[0154] (Example 2)

[0155] 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."

[0156] Conventional dialogue systems have faced challenges in generating responses that take user emotions into account, as they only analyze the user's intent. Furthermore, they lacked the ability to quickly and appropriately escalate issues when user emotions worsened or when inquiries were complex.

[0157] 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.

[0158] In this invention, the server includes a device for identifying the user's intent, an emotion analysis device for identifying the user's emotions from input information, and means for using a generative artificial intelligence model that searches for predetermined data based on the identified emotions and generates a response. This enables the generation of personalized responses and rapid escalation in accordance with the user's emotions.

[0159] A "device that receives information from a user" is a communication device that acquires text data entered by a user and sends that information to a server.

[0160] Natural language processing is a set of techniques and processes that enable computers to understand, analyze, and generate human language.

[0161] A "sentiment analysis device" is a system that identifies a user's emotional state from input text data and expresses it with an appropriate label.

[0162] "Regulated data" refers to data that includes past cases, internal organizational rules, guidelines, etc., and is referenced to provide information in response to user inquiries.

[0163] A "generative artificial intelligence model" is an algorithm that generates new text based on input data, and is a model that has the ability to produce natural-sounding sentences like a human.

[0164] A "device for notifying specialized departments" is a communication system that notifies the appropriate department within an organization of the situation when the AI ​​is unable to handle it, thereby encouraging a swift response.

[0165] A "machine learning algorithm" is a method that learns patterns from data and uses those learned results to make predictions and classifications.

[0166] The system of the present invention aims to return a personalized response to the user by having the user input inquiries and requests using a terminal, and processing them on a server. Specific embodiments of this system will be described below.

[0167] Users make text-based inquiries through a chatbot interface installed on their devices. For example, a user might ask, "I want to take paid leave, but the procedure seems complicated." This input is sent from the device to the server via a communication protocol.

[0168] The server first analyzes the received text data using natural language processing (NLP) techniques. Commonly used NLP technologies include SpaCy and BERT. This allows the server to identify the user's intent.

[0169] Next, the server uses an emotion analysis device to identify the user's emotional state from their text. This analysis could utilize emotion analysis tools such as TextBlob or Sentiment Analysis.

[0170] Based on the analyzed user intent and sentiment information, the server searches existing default data and extracts relevant data. SQL is the common database query language used.

[0171] Next, the server uses a generative AI model (e.g., an appropriate AI language model) to generate natural language responses based on the extracted data. This model can take the user's emotions into consideration and provide information in an appropriate tone.

[0172] The generated natural language sentences are sent from the server to the terminal, where the user reviews them through an interface. If the user's emotions do not meet certain criteria or if the AI ​​is unable to handle the situation, the server notifies a specialized department.

[0173] Furthermore, the server uses machine learning algorithms to analyze past user sentiment and interaction history, and utilizes this information to improve the system and enhance the accuracy of future responses.

[0174] An example of a prompt might be, "How should support be provided if an employee is experiencing work-related stress?" Using this prompt, the system will appropriately provide user support.

[0175] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0176] Step 1:

[0177] The user uses their device to enter inquiries or requests into the chatbot interface. The input data is in text format. For example, "I want to take paid leave, but the procedure seems complicated." The device then prepares to send this text to the server.

[0178] Step 2:

[0179] The terminal sends the user's input text to the server. HTTP or WebSocket is used as the communication protocol. At this stage, the output indicates that the user's text has been transferred to the server.

[0180] Step 3:

[0181] The server analyzes the received text using natural language processing (NLP) techniques. The input data is raw text, which is tokenized, POS tagged, and intent identified through NLP processing to determine the user's intent. Specifically, SpaCy and BERT support this throwing intelligence processing. The output after processing is structured data that indicates the user's intent.

[0182] Step 4:

[0183] The server identifies the user's emotions from the text received through the emotion analysis device. This process uses TextBlob and Sentiment Analysis to extract emotions contained in the input data. The emotion data is output as contextual information such as "anxiety" or "irritation."

[0184] Step 5:

[0185] The server searches internal company data based on the analyzed intent and sentiment information. It extracts relevant information from the database using SQL. The input is intent and sentiment data, and the output is the content of the related information.

[0186] Step 6:

[0187] The server generates a response using a generative AI model based on the extracted information. By inputting information into the generative AI model (e.g., an appropriate AI language model), a natural and appropriate response is output. At this stage, a personalized response that takes the user's emotions into account is obtained.

[0188] Step 7:

[0189] The server sends the generated response to the terminal. The terminal displays the received response to the user. The user confirms this response on the chatbot interface. This step involves the sending and receiving of response data.

[0190] Step 8:

[0191] If the server determines that a user's emotions are extremely negative, or if there is a complex problem that the AI ​​cannot handle, the server automatically notifies a specialized department. This prompts a real-time human response. This information transmission is achieved by constructing and sending notification messages.

[0192] (Application Example 2)

[0193] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0194] In caregiving settings, it is crucial to appropriately recognize the emotions of the elderly and their families and provide natural responses accordingly. However, with existing technologies, while it was possible to analyze user intentions, it was difficult to accurately recognize emotions, making personalized responses based on those emotions challenging. As a result, communication was insufficient, potentially undermining the user's sense of security.

[0195] 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.

[0196] In this invention, the server includes means for receiving information from a user, means for analyzing the received information using natural language processing to identify the user's intentions and emotions, and means for searching a set of reference information and extracting relevant information based on the identified intentions and emotions. This makes it possible to quickly and accurately recognize the emotions of the elderly and their families and provide a sense of security through appropriate responses.

[0197] "Means of receiving information from the user" refers to an interface that acquires voice or text data provided by the user.

[0198] "Natural language processing" is a technology that enables computers to understand, analyze, and generate responses to human language.

[0199] "Means for identifying user intent and emotions" refers to the process of analyzing received information to identify what the user wants and what their emotional state is.

[0200] "Means of searching a collection of reference information and extracting relevant information" refers to the process of searching for relevant information from databases and knowledge bases based on identified intentions and emotions, and retrieving the necessary information.

[0201] "Means for sending generated natural language sentences to the user" refers to a function that transmits responses generated based on analysis to the user via a device.

[0202] "A means of notifying the management department and escalating user inquiries" refers to a function that issues a warning to the management department and prompts appropriate action when the identified emotions exceed the system's capabilities.

[0203] A "machine learning algorithm" is a technology that allows computer systems to learn from experience and data to improve their performance.

[0204] The system for carrying out the present invention analyzes information provided through interaction with the user and generates an appropriate response based on the user's intentions and emotions. This system runs via a terminal such as a smartphone or smart glasses and a server in the cloud.

[0205] First, the user inputs information in voice or text format, which the device receives. This data is then transmitted to a server via a communication network. The server analyzes the user's intent using natural language processing libraries such as the Google Cloud Natural Language API. It also utilizes sentiment analysis engines such as IBM Watson® Tone Analyzer to identify emotions from the user's text.

[0206] Once the analysis is complete, the server uses a generative AI model, such as OpenAI's GPT-4®, to generate natural language responses based on the identified intent and sentiment information. During this process, machine learning algorithms are executed, resulting in improved scope and accuracy of the responses.

[0207] The generated response is sent from a server in the cloud to the user's terminal, allowing the user to review it immediately. Furthermore, if the user's emotions are particularly negative, or if the system cannot process the situation automatically, the server has a function to automatically notify the management department so they can respond quickly.

[0208] As a concrete example, suppose an elderly person says aloud, "Lately, I haven't been able to sleep at night." If the system receives this statement and the emotion engine detects "anxiety," the server will generate a response such as, "Don't worry, it's okay. Let's try to make today even more relaxing than usual," and send it to the terminal to provide reassurance.

[0209] Examples of prompts for a generative AI model include:

[0210] User input: "I haven't been able to sleep at night lately."

[0211] User's emotion: "Anxiety"

[0212] Please generate a response.

[0213] This system enables support that is sensitive to the emotions of users in care settings, thereby improving the quality of communication.

[0214] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0215] Step 1:

[0216] The device receives voice or text input from the user. Information spoken or typed by the user is captured through the device's microphone or keyboard. This input is stored as digital data for later processing.

[0217] Step 2:

[0218] The device converts the received audio data into text data. This is done using speech recognition technology. The converted text data becomes input for natural language processing. In this process, a language recognition library is used to convert speech to text.

[0219] Step 3:

[0220] The server uses a natural language processing library to receive text data as input and analyze the user's intent. This analysis includes grammatical and semantic analysis to identify what the user is asking for. The output is information that indicates the user's intent.

[0221] Step 4:

[0222] The server uses a sentiment analysis engine to identify the user's emotions from text data as input. In this step, specific keywords and phrases are analyzed, and the user's emotional state (e.g., "anxious" or "reassured") is obtained as output.

[0223] Step 5:

[0224] The server takes the identified intentions and emotions as input, searches a set of reference information, and extracts relevant information. Here, it selects relevant information from the database and obtains the information that should be provided to the user as output.

[0225] Step 6:

[0226] The server uses a generative AI model to generate natural language sentences from the extracted information as input. In this process, the generative AI model uses prompt sentences to output appropriate and emotionally sensitive response sentences.

[0227] Step 7:

[0228] The server sends the generated natural language text as input to the terminal. The terminal displays this output to the user. The user can view the response through a smartphone or smart glasses interface.

[0229] Step 8:

[0230] The server automatically notifies the management department if the user's emotions meet certain conditions. This notification allows the management department to take prompt action as needed.

[0231] 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.

[0232] 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.

[0233] 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.

[0234] [Second Embodiment]

[0235] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0236] 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.

[0237] 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).

[0238] 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.

[0239] 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.

[0240] 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).

[0241] 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.

[0242] 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.

[0243] 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.

[0244] 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.

[0245] 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.

[0246] 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".

[0247] This invention provides a system that enables employees within a company to access information regarding regulations and procedures more quickly and easily. The system is configured to process user inquiries and provide necessary information by analyzing the user's intent using natural language processing technology.

[0248] Specifically, the system will be implemented as follows: Users will use a chatbot interface via their device to input the information they want to know. For example, if a user inputs the question, "How many days of paid leave are there?", the device will send this input to the server in real time.

[0249] The server analyzes the received user input using natural language processing. Through this analysis, the server identifies keywords such as "paid leave" and "number of days," and determines the information the user wants to know. Next, based on the identified intent, it searches the company's internal database and extracts the relevant information.

[0250] The extracted information is converted into natural language sentences that are easy for the user to understand by a generating AI. For example, it might be sent to the user's device in a format like "Your annual paid leave is 20 days" and displayed in the chatbot window.

[0251] Furthermore, if the information entered by the user does not meet certain conditions, or if a complex question arises that the AI ​​cannot resolve, the server will notify the HR department and appropriately escalate the inquiry. This process allows users to quickly obtain the correct information, and enables HR personnel to smoothly handle complex situations.

[0252] This system also utilizes machine learning algorithms, which improve the accuracy and reliability of the information it generates. For example, it improves its understanding of user intent with each use, enabling more accurate and efficient responses to similar questions. This significantly reduces the time employees spend gathering information, leading to improved operational efficiency and cost savings for the HR department.

[0253] The following describes the processing flow.

[0254] Step 1:

[0255] The user uses their device to enter a question into the chatbot interface. For example, they might enter information in the form of, "Please tell me the number of paid vacation days."

[0256] Step 2:

[0257] The terminal transmits user input to the server in real time. During this process, it verifies that the data is transmitted correctly over the network.

[0258] Step 3:

[0259] The server analyzes the received input using natural language processing techniques to identify the user's intent. The analysis process utilizes algorithms for keyword extraction and contextual understanding.

[0260] Step 4:

[0261] Based on the identified intent, the server searches the company's internal regulations database. This database contains information about employment rules and personnel policies.

[0262] Step 5:

[0263] The server extracts relevant information from the database. For example, it might retrieve data containing the number of paid leave days.

[0264] Step 6:

[0265] The server uses a generative AI to generate natural language sentences that the user can understand based on the extracted information. For example, it can generate sentences such as, "Your annual paid leave is 20 days."

[0266] Step 7:

[0267] The server sends the generated response to the terminal, which then displays it to the user via a chatbot interface. The user can then view this and obtain the necessary information.

[0268] Step 8:

[0269] If a user asks further questions or makes a complex request, the server will re-analyze the content and, if necessary, escalate it to the HR department. The HR personnel will receive a notification so they can respond immediately.

[0270] (Example 1)

[0271] 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."

[0272] There is a growing need to expedite and facilitate employees' access to information regarding regulations and procedures within companies. However, traditional methods suffer from the problem of time-consuming information retrieval and difficulty in handling complex inquiries. Furthermore, there is a need for methods to improve the accuracy of the information users seek and to increase the efficiency of inquiry processing.

[0273] 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.

[0274] In this invention, the server includes means for acquiring data from a user, means for analyzing the acquired data using natural language processing technology to clarify the user's intent, and means for searching an information base and acquiring relevant data based on the clarified intent. This enables the rapid and appropriate provision of information within a company.

[0275] A "user" refers to an individual or legal entity that attempts to obtain information using the system.

[0276] "Data" refers to information about questions and requests obtained from users.

[0277] "Natural language processing technology" refers to computer technology used to analyze acquired data and identify its intent.

[0278] "Intention" refers to the purpose or necessary information that the user demands from the system.

[0279] "Information base" refers to a database in which information on company regulations and procedures is recorded.

[0280] "Means of acquiring data" refers to the process of importing data from the user into the server.

[0281] "Relevant data" refers to the corresponding information obtained from the information base based on the identified intention of the user.

[0282] "Means of constructing natural language sentences" refers to the process of converting the acquired relevant data into words that humans can understand.

[0283] "Notification" refers to the message sent to inform another department when the user's inquiry does not meet specific criteria.

[0284] "Machine learning technology" refers to an algorithm that learns from data and applies the results to improve the performance of the system.

[0285] This system aims to quickly provide employees within the company with information on regulations and procedures they need. The system consists of the following elements.

[0286] The user uses the Internet to log in to the chatbot interface on the terminal and enters the necessary information in text format. As terminals, PCs and smartphones can be used, and they access the system through a browser.

[0287] The terminal sends the data input by the user to the server using the HTTPS protocol. The server is equipped with natural language processing technology for analysis, and specifically, libraries such as spaCy and NLTK are used.

[0288] The server analyzes the received data using natural language processing to identify the user's intent. Based on this identified intent, the server issues SQL queries to the company's internal regulations database to retrieve relevant information. The database stores various regulations and procedural information set by the company.

[0289] The extracted information is converted into natural language sentences on the server using a generative AI model. For example, OpenAI's language model may be used as the generative AI. This generates easy-to-understand response sentences to questions entered by the user. A concrete example of such a response might be, "Your annual paid leave is 20 days."

[0290] The generated natural language text is sent back from the server to the user's device and displayed in the chatbot interface on the device. This interface provides information to the user in real time, improving the user experience.

[0291] Furthermore, if user input does not meet the requirements, or if a complex inquiry arises that cannot be resolved by the system, the server will automatically use its communication function to send an escalation notification to the appropriate department within the company.

[0292] A concrete example of a prompt message would be, "According to company regulations, how many paid leave days am I entitled to?" In this way, information tailored to the individual needs of the user is provided.

[0293] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0294] Step 1:

[0295] The user accesses the chatbot interface on their device and enters the information they want in text format. Specifically, this involves entering a sentence such as, "How many days of paid leave do I have?" This input becomes the data for the next process.

[0296] Step 2:

[0297] The terminal sends text data entered by the user to the server using the HTTPS protocol. Specifically, the terminal's actions include encoding the input data and sending it to the server via a secure communication channel. This prepares the server for analysis.

[0298] Step 3:

[0299] The server analyzes the received text data using natural language processing techniques. Specifically, it uses a natural language processing library to extract keywords such as "paid leave" and "number of days" to identify the user's intent. The output of this step is the analyzed intent.

[0300] Step 4:

[0301] The server searches the company's information base based on the identified intent. The server executes an SQL query to retrieve "paid leave" related information from the database. The input to this process is the previously identified intent, and the output is user-related paid leave information.

[0302] Step 5:

[0303] The server inputs the acquired data into a generative AI model to generate natural language sentences that are easy for the user to understand. For example, the generative AI model generates the response sentence, "Your annual paid leave is 20 days." The output of this step is natural language sentences.

[0304] Step 6:

[0305] The server sends the generated natural language sentence to the terminal. Specifically, the server encodes the sentence using a secure communication protocol and sends it to the terminal. This output is the natural language sentence that reaches the user's terminal.

[0306] Step 7:

[0307] The terminal displays the received natural language sentence on the chatbot interface. Through this interface, the user can visually confirm the information provided by the server. The input in this step is the natural language sentence from the server, and the output is the display on the terminal.

[0308] (Application Example 1)

[0309] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0310] Conventional household personal assistant robots have difficulty accurately processing and providing individual information such as household rules and schedules. In providing information in an interactive format, it is required to correctly understand the user's intention and respond to various information needs. However, due to the accuracy of voice input and the limitations of natural language processing, appropriate responses could not be made in many cases. As a result, there was a problem that the convenience for the user was limited and the smooth progress of tasks and activities within the home was hindered.

[0311] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0312] In this invention, the server includes means for receiving information from the user, means for converting the received information into text data by a voice recognition processing device, and a knowledge base for providing household information and means for quickly proposing relevant information. Thereby, it becomes possible to more accurately grasp the user's intention and quickly and appropriately provide relevant household information.

[0313] The "means for receiving information from the user" is a function for acquiring data input by voice or text from the user. <00憨00987>

[0314] "Natural language processing" is a technology that uses computers to analyze human language and understand its meaning.

[0315] A "speech recognition processing device" is a device or software that analyzes speech input as a digital signal and converts it into text data.

[0316] "Rules and regulations" refer to aggregated data such as guidelines, schedules, and procedures that apply both inside and outside the home.

[0317] A "knowledge base" is a database where information in a specific domain is stored and can be searched as needed.

[0318] "Machine learning techniques" are technologies that allow computers to learn patterns from data and apply them to future predictions and classifications.

[0319] "Escalation" is the process of raising a problem or inquiry to a higher level of support if it cannot be resolved.

[0320] To implement this invention, a personal assistant robot for home use is required to have the following configuration: The robot is equipped with a voice recognition processing unit that receives information from the user's voice and converts it into text data. The converted text is sent to a server, where natural language processing technology is used to analyze the user's intent.

[0321] Based on the analyzed intent, the server searches its knowledge base for relevant rule information and extracts the necessary data. This allows the robot to provide the user with information about household rules and schedules. The extracted data is then converted into user-friendly natural language using a generative AI model and presented to the user in either audio or text format.

[0322] For example, if a user says, "Tell me what's on the schedule for today," the robot might respond with something like, "We have a family dinner at 7 PM." An example of a prompt for the generative AI model would be, "Based on the rules of this household, answer the following question: 'What's the task for today?'"

[0323] The hardware and software used include voice recognition devices such as Amazon Alexa and Google Home, speech-to-text services such as Google Cloud Speech-to-Text and Amazon Transcribe, and natural language processing and generative AI models such as Python's Natural Language Toolkit (NLTK) and OpenAI's GPT. In this way, the invention significantly improves the convenience of information access in the home environment.

[0324] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0325] Step 1:

[0326] The user inputs a question to the robot via voice. This voice data is converted into a digital signal by the robot's voice recognition processing unit. This process then converts the voice data into text data.

[0327] Step 2:

[0328] The device sends text data obtained through speech recognition to the server. The server receives this text data and analyzes the user's intent using natural language processing technology. In this process, the server extracts context and keywords to understand the user's request.

[0329] Step 3:

[0330] Based on the analyzed user intent, the server searches its internal knowledge base for relevant rule information. This process uses a search algorithm to identify information that matches the request and extracts the necessary data.

[0331] Step 4:

[0332] The server converts the extracted data into natural language sentences using a generative AI model. Here, the generative AI model processes the data and reconstructs it into sentences that are easy for the user to understand. This output is generated in text format.

[0333] Step 5:

[0334] The server sends the generated natural language text to the terminal, which then presents it to the user as either audio or text. The robot then uses the terminal to provide an appropriate response to the user's original question.

[0335] 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.

[0336] This invention provides a system that incorporates an emotion engine to recognize a user's emotions and utilize that information to provide appropriate natural language responses. This system processes user inquiries and, through emotion analysis, enables more personalized information delivery.

[0337] Specifically, users use their devices to input questions and requests through a chatbot interface. For example, they might ask, "I want to take paid leave, but the procedure seems complicated." The device then sends this input to the server.

[0338] When the server receives input information, it applies natural language processing techniques to analyze the user's intent. It also uses an emotion engine to identify the user's emotions from the input text. This emotion information can be expressed as a string, for example, "anxiety" or "frustration."

[0339] Based on the analyzed intent and emotional information, the server searches the company's internal database and extracts relevant information. During this process, consideration is given to providing the information in an appropriate tone and phrasing that reflects the user's emotions. Using generative AI, the extracted information is converted into natural language sentences, generating responses such as, "Don't worry. The procedure is simple, and you can take 20 days of paid leave per year."

[0340] The generated response is sent from the server to the terminal, and the user can view it through the chatbot interface. If the user's emotions are particularly negative, or if the AI ​​determines that the issue is too complex for it to handle, the server automatically notifies the HR department to prompt a quick response.

[0341] This system also leverages machine learning algorithms to accumulate and analyze users' emotional history, further improving the accuracy and personalization of responses in future interactions. This approach makes it possible to provide more empathetic and accurate support for employees' questions and concerns.

[0342] The following describes the processing flow.

[0343] Step 1:

[0344] The user uses their device to enter a question into the chatbot interface. For example, they might send a message like, "I'm worried because the paid leave application process is complicated."

[0345] Step 2:

[0346] The terminal sends the entered message to the server. This transmission takes place over the network.

[0347] Step 3:

[0348] The server analyzes received messages using natural language processing technology to identify the user's intentions and requests.

[0349] Step 4:

[0350] The server uses an emotion engine to recognize emotions from the user's text. For example, it can identify the emotion "anxiety" from a message.

[0351] Step 5:

[0352] The server searches the company's internal database based on intent and sentiment information, extracting information relevant to the user's inquiry.

[0353] Step 6:

[0354] The server uses a generative AI to convert the extracted information into natural language sentences. Taking emotional information into consideration, it generates sentences in a tone such as, "Please rest assured. The paid leave process is simple, and we will support you if needed."

[0355] Step 7:

[0356] The server sends the generated natural language response to the terminal.

[0357] Step 8:

[0358] The device displays the received response to the user through a chatbot interface. The user can then view this information and resolve any questions or concerns they may have.

[0359] Step 9:

[0360] The server automatically notifies the HR department if the user's emotions are particularly negative, and escalates the inquiry as needed. This allows the HR department to respond quickly.

[0361] Step 10:

[0362] The server stores user interaction history and sentiment information, which is then analyzed using machine learning algorithms. This improves the accuracy of future user responses and enhances personalized service.

[0363] (Example 2)

[0364] 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".

[0365] Conventional dialogue systems have faced challenges in generating responses that take user emotions into account, as they only analyze the user's intent. Furthermore, they lacked the ability to quickly and appropriately escalate issues when user emotions worsened or when inquiries were complex.

[0366] 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.

[0367] In this invention, the server includes a device for identifying the user's intent, an emotion analysis device for identifying the user's emotions from input information, and means for using a generative artificial intelligence model that searches for predetermined data based on the identified emotions and generates a response. This enables the generation of personalized responses and rapid escalation in accordance with the user's emotions.

[0368] A "device that receives information from a user" is a communication device that acquires text data entered by a user and sends that information to a server.

[0369] Natural language processing is a set of techniques and processes that enable computers to understand, analyze, and generate human language.

[0370] A "sentiment analysis device" is a system that identifies a user's emotional state from input text data and expresses it with an appropriate label.

[0371] "Regulated data" refers to data that includes past cases, internal organizational rules, guidelines, etc., and is referenced to provide information in response to user inquiries.

[0372] A "generative artificial intelligence model" is an algorithm that generates new text based on input data, and is a model that has the ability to produce natural-sounding sentences like a human.

[0373] A "device for notifying specialized departments" is a communication system that notifies the appropriate department within an organization of the situation when the AI ​​is unable to handle it, thereby encouraging a swift response.

[0374] A "machine learning algorithm" is a method that learns patterns from data and uses those learned results to make predictions and classifications.

[0375] The system of the present invention aims to return a personalized response to the user by having the user input inquiries and requests using a terminal, and processing them on a server. Specific embodiments of this system will be described below.

[0376] Users make text-based inquiries through a chatbot interface installed on their devices. For example, a user might ask, "I want to take paid leave, but the procedure seems complicated." This input is sent from the device to the server via a communication protocol.

[0377] The server first analyzes the received text data using natural language processing (NLP) techniques. Commonly used NLP technologies include SpaCy and BERT. This allows the server to identify the user's intent.

[0378] Next, the server uses an emotion analysis device to identify the user's emotional state from their text. This analysis could utilize emotion analysis tools such as TextBlob or Sentiment Analysis.

[0379] Based on the analyzed user intent and sentiment information, the server searches existing default data and extracts relevant data. SQL is the common database query language used.

[0380] Next, the server uses a generative AI model (e.g., an appropriate AI language model) to generate natural language responses based on the extracted data. This model can take the user's emotions into consideration and provide information in an appropriate tone.

[0381] The generated natural language sentences are sent from the server to the terminal, where the user reviews them through an interface. If the user's emotions do not meet certain criteria or if the AI ​​is unable to handle the situation, the server notifies a specialized department.

[0382] Furthermore, the server uses machine learning algorithms to analyze past user sentiment and interaction history, and utilizes this information to improve the system and enhance the accuracy of future responses.

[0383] An example of a prompt might be, "How should support be provided if an employee is experiencing work-related stress?" Using this prompt, the system will appropriately provide user support.

[0384] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0385] Step 1:

[0386] The user uses their device to enter inquiries or requests into the chatbot interface. The input data is in text format. For example, "I want to take paid leave, but the procedure seems complicated." The device then prepares to send this text to the server.

[0387] Step 2:

[0388] The terminal sends the user's input text to the server. HTTP or WebSocket is used as the communication protocol. At this stage, the output indicates that the user's text has been transferred to the server.

[0389] Step 3:

[0390] The server analyzes the received text using natural language processing (NLP) techniques. The input data is raw text, which is tokenized, POS tagged, and intent identified through NLP processing to determine the user's intent. Specifically, SpaCy and BERT support this throwing intelligence processing. The output after processing is structured data that indicates the user's intent.

[0391] Step 4:

[0392] The server identifies the user's emotions from the text received through the emotion analysis device. This process uses TextBlob and Sentiment Analysis to extract emotions contained in the input data. The emotion data is output as contextual information such as "anxiety" or "irritation."

[0393] Step 5:

[0394] The server searches internal company data based on the analyzed intent and sentiment information. It extracts relevant information from the database using SQL. The input is intent and sentiment data, and the output is the content of the related information.

[0395] Step 6:

[0396] The server generates a response using a generative AI model based on the extracted information. By inputting information into the generative AI model (e.g., an appropriate AI language model), a natural and appropriate response is output. At this stage, a personalized response that takes the user's emotions into account is obtained.

[0397] Step 7:

[0398] The server sends the generated response to the terminal. The terminal displays the received response to the user. The user confirms this response on the chatbot interface. This step involves the sending and receiving of response data.

[0399] Step 8:

[0400] If the server determines that a user's emotions are extremely negative, or if there is a complex problem that the AI ​​cannot handle, the server automatically notifies a specialized department. This prompts a real-time human response. This information transmission is achieved by constructing and sending notification messages.

[0401] (Application Example 2)

[0402] 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."

[0403] In caregiving settings, it is crucial to appropriately recognize the emotions of the elderly and their families and provide natural responses accordingly. However, with existing technologies, while it was possible to analyze user intentions, it was difficult to accurately recognize emotions, making personalized responses based on those emotions challenging. As a result, communication was insufficient, potentially undermining the user's sense of security.

[0404] 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.

[0405] In this invention, the server includes means for receiving information from a user, means for analyzing the received information using natural language processing to identify the user's intentions and emotions, and means for searching a set of reference information and extracting relevant information based on the identified intentions and emotions. This makes it possible to quickly and accurately recognize the emotions of the elderly and their families and provide a sense of security through appropriate responses.

[0406] "Means of receiving information from the user" refers to an interface that acquires voice or text data provided by the user.

[0407] "Natural language processing" is a technology that enables computers to understand, analyze, and generate responses to human language.

[0408] "Means for identifying user intent and emotions" refers to the process of analyzing received information to identify what the user wants and what their emotional state is.

[0409] "Means of searching a collection of reference information and extracting relevant information" refers to the process of searching for relevant information from databases and knowledge bases based on identified intentions and emotions, and retrieving the necessary information.

[0410] "Means for sending generated natural language sentences to the user" refers to a function that transmits responses generated based on analysis to the user via a device.

[0411] "A means of notifying the management department and escalating user inquiries" refers to a function that issues a warning to the management department and prompts appropriate action when the identified emotions exceed the system's capabilities.

[0412] A "machine learning algorithm" is a technology that allows computer systems to learn from experience and data to improve their performance.

[0413] The system for carrying out the present invention analyzes information provided through interaction with the user and generates an appropriate response based on the user's intentions and emotions. This system runs via a terminal such as a smartphone or smart glasses and a server in the cloud.

[0414] First, the user inputs information in voice or text format, which the device receives. This data is then transmitted to a server via a communication network. The server analyzes the user's intent using natural language processing libraries such as the Google Cloud Natural Language API. It also leverages sentiment analysis engines like IBM Watson Tone Analyzer to identify emotions from the user's text.

[0415] Once the analysis is complete, the server uses a generative AI model, such as OpenAI's GPT-4, to generate natural language responses based on the identified intent and sentiment information. During this process, machine learning algorithms are executed, resulting in improved scope and accuracy of the responses.

[0416] The generated response is sent from a server in the cloud to the user's terminal, allowing the user to review it immediately. Furthermore, if the user's emotions are particularly negative, or if the system cannot process the situation automatically, the server has a function to automatically notify the management department so they can respond quickly.

[0417] As a concrete example, suppose an elderly person says aloud, "Lately, I haven't been able to sleep at night." If the system receives this statement and the emotion engine detects "anxiety," the server will generate a response such as, "Don't worry, it's okay. Let's try to make today even more relaxing than usual," and send it to the terminal to provide reassurance.

[0418] Examples of prompts for a generative AI model include:

[0419] User input: "I haven't been able to sleep at night lately."

[0420] User's emotion: "Anxiety"

[0421] Please generate a response.

[0422] This system enables support that is sensitive to the emotions of users in care settings, thereby improving the quality of communication.

[0423] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0424] Step 1:

[0425] The device receives voice or text input from the user. Information spoken or typed by the user is captured through the device's microphone or keyboard. This input is stored as digital data for later processing.

[0426] Step 2:

[0427] The device converts the received audio data into text data. This is done using speech recognition technology. The converted text data becomes input for natural language processing. In this process, a language recognition library is used to convert speech to text.

[0428] Step 3:

[0429] The server uses a natural language processing library to receive text data as input and analyze the user's intent. This analysis includes grammatical and semantic analysis to identify what the user is asking for. The output is information that indicates the user's intent.

[0430] Step 4:

[0431] The server uses a sentiment analysis engine to identify the user's emotions from text data as input. In this step, specific keywords and phrases are analyzed, and the user's emotional state (e.g., "anxious" or "reassured") is obtained as output.

[0432] Step 5:

[0433] The server takes the identified intentions and emotions as input, searches a set of reference information, and extracts relevant information. Here, it selects relevant information from the database and obtains the information that should be provided to the user as output.

[0434] Step 6:

[0435] The server uses a generative AI model to generate natural language sentences from the extracted information as input. In this process, the generative AI model uses prompt sentences to output appropriate and emotionally sensitive response sentences.

[0436] Step 7:

[0437] The server sends the generated natural language text as input to the terminal. The terminal displays this output to the user. The user can view the response through a smartphone or smart glasses interface.

[0438] Step 8:

[0439] The server automatically notifies the management department if the user's emotions meet certain conditions. This notification allows the management department to take prompt action as needed.

[0440] 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.

[0441] 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.

[0442] 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.

[0443] [Third Embodiment]

[0444] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0445] 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.

[0446] 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).

[0447] 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.

[0448] 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.

[0449] 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).

[0450] 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.

[0451] 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.

[0452] 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.

[0453] 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.

[0454] 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.

[0455] 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".

[0456] This invention provides a system that enables employees within a company to access information regarding regulations and procedures more quickly and easily. The system is configured to process user inquiries and provide necessary information by analyzing the user's intent using natural language processing technology.

[0457] Specifically, the system will be implemented as follows: Users will use a chatbot interface via their device to input the information they want to know. For example, if a user inputs the question, "How many days of paid leave are there?", the device will send this input to the server in real time.

[0458] The server analyzes the received user input using natural language processing. Through this analysis, the server identifies keywords such as "paid leave" and "number of days," and determines the information the user wants to know. Next, based on the identified intent, it searches the company's internal database and extracts the relevant information.

[0459] The extracted information is converted into natural language sentences that are easy for the user to understand by a generating AI. For example, it might be sent to the user's device in a format like "Your annual paid leave is 20 days" and displayed in the chatbot window.

[0460] Furthermore, if the information entered by the user does not meet certain conditions, or if a complex question arises that the AI ​​cannot resolve, the server will notify the HR department and appropriately escalate the inquiry. This process allows users to quickly obtain the correct information, and enables HR personnel to smoothly handle complex situations.

[0461] This system also utilizes machine learning algorithms, which improve the accuracy and reliability of the information it generates. For example, it improves its understanding of user intent with each use, enabling more accurate and efficient responses to similar questions. This significantly reduces the time employees spend gathering information, leading to improved operational efficiency and cost savings for the HR department.

[0462] The following describes the processing flow.

[0463] Step 1:

[0464] The user uses their device to enter a question into the chatbot interface. For example, they might enter information in the form of, "Please tell me the number of paid vacation days."

[0465] Step 2:

[0466] The terminal transmits user input to the server in real time. During this process, it verifies that the data is transmitted correctly over the network.

[0467] Step 3:

[0468] The server analyzes the received input using natural language processing techniques to identify the user's intent. The analysis process utilizes algorithms for keyword extraction and contextual understanding.

[0469] Step 4:

[0470] Based on the identified intent, the server searches the company's internal regulations database. This database contains information about employment rules and personnel policies.

[0471] Step 5:

[0472] The server extracts relevant information from the database. For example, it might retrieve data containing the number of paid leave days.

[0473] Step 6:

[0474] The server uses a generative AI to generate natural language sentences that the user can understand based on the extracted information. For example, it can generate sentences such as, "Your annual paid leave is 20 days."

[0475] Step 7:

[0476] The server sends the generated response to the terminal, which then displays it to the user via a chatbot interface. The user can then view this and obtain the necessary information.

[0477] Step 8:

[0478] If a user asks further questions or makes a complex request, the server will re-analyze the content and, if necessary, escalate it to the HR department. The HR personnel will receive a notification so they can respond immediately.

[0479] (Example 1)

[0480] 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."

[0481] There is a growing need to expedite and facilitate employees' access to information regarding regulations and procedures within companies. However, traditional methods suffer from the problem of time-consuming information retrieval and difficulty in handling complex inquiries. Furthermore, there is a need for methods to improve the accuracy of the information users seek and to increase the efficiency of inquiry processing.

[0482] 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.

[0483] In this invention, the server includes means for acquiring data from a user, means for analyzing the acquired data using natural language processing technology to clarify the user's intent, and means for searching an information base and acquiring relevant data based on the clarified intent. This enables the rapid and appropriate provision of information within a company.

[0484] A "user" refers to an individual or legal entity that attempts to obtain information using the system.

[0485] "Data" refers to information about questions and requests obtained from users.

[0486] "Natural language processing technology" refers to computer technology used to analyze acquired data and identify its intent.

[0487] "Intent" refers to the purpose or necessary information that the user is seeking from the system.

[0488] An "information base" refers to a database that contains information about company regulations and procedures.

[0489] "Means of acquiring data" refers to the process of importing user data into the server.

[0490] "Relevant data" refers to the relevant information retrieved from the information base based on the user's identified intent.

[0491] "Methods for constructing natural language sentences" refers to the process of converting acquired relevant data into language that humans can understand.

[0492] A "notification" refers to a message sent to another department to inform them that a user's inquiry does not meet certain criteria.

[0493] "Machine learning technology" refers to algorithms that learn from data and apply the results to improve the performance of a system.

[0494] This system aims to quickly provide employees with information on regulations and procedures they need within a company. The system consists of the following elements:

[0495] Users log in to the chatbot interface on their device via the internet and enter the necessary information in text format. PCs and smartphones can be used as devices, and they access the system through a web browser.

[0496] The terminal sends data entered by the user to the server using the HTTPS protocol. The server is equipped with natural language processing technology for analysis, specifically using libraries such as spaCy and NLTK.

[0497] The server analyzes the received data using natural language processing to identify the user's intent. Based on this identified intent, the server issues SQL queries to the company's internal regulations database to retrieve relevant information. The database stores various regulations and procedural information set by the company.

[0498] The extracted information is converted into natural language sentences on the server using a generative AI model. For example, OpenAI's language model may be used as the generative AI. This generates easy-to-understand response sentences to questions entered by the user. A concrete example of such a response might be, "Your annual paid leave is 20 days."

[0499] The generated natural language text is sent back from the server to the user's device and displayed in the chatbot interface on the device. This interface provides information to the user in real time, improving the user experience.

[0500] Furthermore, if user input does not meet the requirements, or if a complex inquiry arises that cannot be resolved by the system, the server will automatically use its communication function to send an escalation notification to the appropriate department within the company.

[0501] A concrete example of a prompt message would be, "According to company regulations, how many paid leave days am I entitled to?" In this way, information tailored to the individual needs of the user is provided.

[0502] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0503] Step 1:

[0504] The user accesses the chatbot interface on their device and enters the information they want in text format. Specifically, this involves entering a sentence such as, "How many days of paid leave do I have?" This input becomes the data for the next process.

[0505] Step 2:

[0506] The terminal sends text data entered by the user to the server using the HTTPS protocol. Specifically, the terminal's actions include encoding the input data and sending it to the server via a secure communication channel. This prepares the server for analysis.

[0507] Step 3:

[0508] The server analyzes the received text data using natural language processing techniques. Specifically, it uses a natural language processing library to extract keywords such as "paid leave" and "number of days" to identify the user's intent. The output of this step is the analyzed intent.

[0509] Step 4:

[0510] The server searches the company's information base based on the identified intent. The server executes an SQL query to retrieve "paid leave" related information from the database. The input to this process is the previously identified intent, and the output is user-related paid leave information.

[0511] Step 5:

[0512] The server inputs the acquired data into a generative AI model to generate natural language sentences that are easy for the user to understand. For example, the generative AI model generates the response sentence, "Your annual paid leave is 20 days." The output of this step is natural language sentences.

[0513] Step 6:

[0514] The server sends the generated natural language sentence to the terminal. Specifically, the server encodes the sentence using a secure communication protocol and sends it to the terminal. This output is the natural language sentence that reaches the user's terminal.

[0515] Step 7:

[0516] The terminal displays the received natural language text in the chatbot interface. Through this interface, the user can visually confirm the information provided by the server. In this step, the input is natural language text from the server, and the output is the display on the terminal.

[0517] (Application Example 1)

[0518] 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."

[0519] Conventional home personal assistant robots have struggled to accurately process and provide individual information such as household rules and schedules. Conversational information provision requires correctly understanding the user's intentions and responding to diverse information needs. However, limitations in voice input accuracy and natural language processing often prevented appropriate responses. This resulted in limited user convenience and hindered the smooth progress of tasks and activities within the home.

[0520] 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.

[0521] In this invention, the server includes means for receiving information from a user, means for converting the received information into text data using a speech recognition processing device, and means for providing a knowledge base for providing information within the home and for quickly suggesting relevant information. This makes it possible to more accurately grasp the user's intentions and to provide relevant home information quickly and appropriately.

[0522] "Means of receiving information from users" refers to functions that acquire data input from users in the form of voice or text.

[0523] "Natural language processing" is a technology that uses computers to analyze human language and understand its meaning.

[0524] A "speech recognition processing device" is a device or software that analyzes speech input as a digital signal and converts it into text data.

[0525] "Rules and regulations" refer to aggregated data such as guidelines, schedules, and procedures that apply both inside and outside the home.

[0526] A "knowledge base" is a database where information in a specific domain is stored and can be searched as needed.

[0527] "Machine learning techniques" are technologies that allow computers to learn patterns from data and apply them to future predictions and classifications.

[0528] "Escalation" is the process of raising a problem or inquiry to a higher level of support if it cannot be resolved.

[0529] To implement this invention, a personal assistant robot for home use is required to have the following configuration: The robot is equipped with a voice recognition processing unit that receives information from the user's voice and converts it into text data. The converted text is sent to a server, where natural language processing technology is used to analyze the user's intent.

[0530] Based on the analyzed intent, the server searches its knowledge base for relevant rule information and extracts the necessary data. This allows the robot to provide the user with information about household rules and schedules. The extracted data is then converted into user-friendly natural language using a generative AI model and presented to the user in either audio or text format.

[0531] For example, if a user says, "Tell me what's on the schedule for today," the robot might respond with something like, "We have a family dinner at 7 PM." An example of a prompt for the generative AI model would be, "Based on the rules of this household, answer the following question: 'What's the task for today?'"

[0532] The hardware and software used include voice recognition devices such as Amazon Alexa and Google Home, speech-to-text services such as Google Cloud Speech-to-Text and Amazon Transcribe, and natural language processing and generative AI models such as Python's Natural Language Toolkit (NLTK) and OpenAI's GPT. In this way, the invention significantly improves the convenience of information access in the home environment.

[0533] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0534] Step 1:

[0535] The user inputs a question to the robot via voice. This voice data is converted into a digital signal by the robot's voice recognition processing unit. This process then converts the voice data into text data.

[0536] Step 2:

[0537] The device sends text data obtained through speech recognition to the server. The server receives this text data and analyzes the user's intent using natural language processing technology. In this process, the server extracts context and keywords to understand the user's request.

[0538] Step 3:

[0539] Based on the analyzed user intent, the server searches its internal knowledge base for relevant rule information. This process uses a search algorithm to identify information that matches the request and extracts the necessary data.

[0540] Step 4:

[0541] The server converts the extracted data into natural language sentences using a generative AI model. Here, the generative AI model processes the data and reconstructs it into sentences that are easy for the user to understand. This output is generated in text format.

[0542] Step 5:

[0543] The server sends the generated natural language text to the terminal, which then presents it to the user as either audio or text. The robot then uses the terminal to provide an appropriate response to the user's original question.

[0544] 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.

[0545] This invention provides a system that incorporates an emotion engine to recognize a user's emotions and utilize that information to provide appropriate natural language responses. This system processes user inquiries and, through emotion analysis, enables more personalized information delivery.

[0546] Specifically, users use their devices to input questions and requests through a chatbot interface. For example, they might ask, "I want to take paid leave, but the procedure seems complicated." The device then sends this input to the server.

[0547] When the server receives input information, it applies natural language processing techniques to analyze the user's intent. It also uses an emotion engine to identify the user's emotions from the input text. This emotion information can be expressed as a string, for example, "anxiety" or "frustration."

[0548] Based on the analyzed intent and emotional information, the server searches the company's internal database and extracts relevant information. During this process, consideration is given to providing the information in an appropriate tone and phrasing that reflects the user's emotions. Using generative AI, the extracted information is converted into natural language sentences, generating responses such as, "Don't worry. The procedure is simple, and you can take 20 days of paid leave per year."

[0549] The generated response is sent from the server to the terminal, and the user can view it through the chatbot interface. If the user's emotions are particularly negative, or if the AI ​​determines that the issue is too complex for it to handle, the server automatically notifies the HR department to prompt a quick response.

[0550] This system also leverages machine learning algorithms to accumulate and analyze users' emotional history, further improving the accuracy and personalization of responses in future interactions. This approach makes it possible to provide more empathetic and accurate support for employees' questions and concerns.

[0551] The following describes the processing flow.

[0552] Step 1:

[0553] The user uses their device to enter a question into the chatbot interface. For example, they might send a message like, "I'm worried because the paid leave application process is complicated."

[0554] Step 2:

[0555] The terminal sends the entered message to the server. This transmission takes place over the network.

[0556] Step 3:

[0557] The server analyzes received messages using natural language processing technology to identify the user's intentions and requests.

[0558] Step 4:

[0559] The server uses an emotion engine to recognize emotions from the user's text. For example, it can identify the emotion "anxiety" from a message.

[0560] Step 5:

[0561] The server searches the company's internal database based on intent and sentiment information, extracting information relevant to the user's inquiry.

[0562] Step 6:

[0563] The server uses a generative AI to convert the extracted information into natural language sentences. Taking emotional information into consideration, it generates sentences in a tone such as, "Please rest assured. The paid leave process is simple, and we will support you if needed."

[0564] Step 7:

[0565] The server sends the generated natural language response to the terminal.

[0566] Step 8:

[0567] The device displays the received response to the user through a chatbot interface. The user can then view this information and resolve any questions or concerns they may have.

[0568] Step 9:

[0569] The server automatically notifies the HR department if the user's emotions are particularly negative, and escalates the inquiry as needed. This allows the HR department to respond quickly.

[0570] Step 10:

[0571] The server stores user interaction history and sentiment information, which is then analyzed using machine learning algorithms. This improves the accuracy of future user responses and enhances personalized service.

[0572] (Example 2)

[0573] 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."

[0574] Conventional dialogue systems have faced challenges in generating responses that take user emotions into account, as they only analyze the user's intent. Furthermore, they lacked the ability to quickly and appropriately escalate issues when user emotions worsened or when inquiries were complex.

[0575] 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.

[0576] In this invention, the server includes a device for identifying the user's intent, an emotion analysis device for identifying the user's emotions from input information, and means for using a generative artificial intelligence model that searches for predetermined data based on the identified emotions and generates a response. This enables the generation of personalized responses and rapid escalation in accordance with the user's emotions.

[0577] A "device that receives information from a user" is a communication device that acquires text data entered by a user and sends that information to a server.

[0578] Natural language processing is a set of techniques and processes that enable computers to understand, analyze, and generate human language.

[0579] A "sentiment analysis device" is a system that identifies a user's emotional state from input text data and expresses it with an appropriate label.

[0580] "Regulated data" refers to data that includes past cases, internal organizational rules, guidelines, etc., and is referenced to provide information in response to user inquiries.

[0581] A "generative artificial intelligence model" is an algorithm that generates new text based on input data, and is a model that has the ability to produce natural-sounding sentences like a human.

[0582] A "device for notifying specialized departments" is a communication system that notifies the appropriate department within an organization of the situation when the AI ​​is unable to handle it, thereby encouraging a swift response.

[0583] A "machine learning algorithm" is a method that learns patterns from data and uses those learned results to make predictions and classifications.

[0584] The system of the present invention aims to return a personalized response to the user by having the user input inquiries and requests using a terminal, and processing them on a server. Specific embodiments of this system will be described below.

[0585] Users make text-based inquiries through a chatbot interface installed on their devices. For example, a user might ask, "I want to take paid leave, but the procedure seems complicated." This input is sent from the device to the server via a communication protocol.

[0586] The server first analyzes the received text data using natural language processing (NLP) techniques. Commonly used NLP technologies include SpaCy and BERT. This allows the server to identify the user's intent.

[0587] Next, the server uses an emotion analysis device to identify the user's emotional state from their text. This analysis could utilize emotion analysis tools such as TextBlob or Sentiment Analysis.

[0588] Based on the analyzed user intent and sentiment information, the server searches existing default data and extracts relevant data. SQL is the common database query language used.

[0589] Next, the server uses a generative AI model (e.g., an appropriate AI language model) to generate natural language responses based on the extracted data. This model can take the user's emotions into consideration and provide information in an appropriate tone.

[0590] The generated natural language sentences are sent from the server to the terminal, where the user reviews them through an interface. If the user's emotions do not meet certain criteria or if the AI ​​is unable to handle the situation, the server notifies a specialized department.

[0591] Furthermore, the server uses machine learning algorithms to analyze past user sentiment and interaction history, and utilizes this information to improve the system and enhance the accuracy of future responses.

[0592] An example of a prompt might be, "How should support be provided if an employee is experiencing work-related stress?" Using this prompt, the system will appropriately provide user support.

[0593] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0594] Step 1:

[0595] The user uses their device to enter inquiries or requests into the chatbot interface. The input data is in text format. For example, "I want to take paid leave, but the procedure seems complicated." The device then prepares to send this text to the server.

[0596] Step 2:

[0597] The terminal sends the user's input text to the server. HTTP or WebSocket is used as the communication protocol. At this stage, the output indicates that the user's text has been transferred to the server.

[0598] Step 3:

[0599] The server analyzes the received text using natural language processing (NLP) techniques. The input data is raw text, which is tokenized, POS tagged, and intent identified through NLP processing to determine the user's intent. Specifically, SpaCy and BERT support this throwing intelligence processing. The output after processing is structured data that indicates the user's intent.

[0600] Step 4:

[0601] The server identifies the user's emotions from the text received through the emotion analysis device. This process uses TextBlob and Sentiment Analysis to extract emotions contained in the input data. The emotion data is output as contextual information such as "anxiety" or "irritation."

[0602] Step 5:

[0603] The server searches internal company data based on the analyzed intent and sentiment information. It extracts relevant information from the database using SQL. The input is intent and sentiment data, and the output is the content of the related information.

[0604] Step 6:

[0605] The server generates a response using a generative AI model based on the extracted information. By inputting information into the generative AI model (e.g., an appropriate AI language model), a natural and appropriate response is output. At this stage, a personalized response that takes the user's emotions into account is obtained.

[0606] Step 7:

[0607] The server sends the generated response to the terminal. The terminal displays the received response to the user. The user confirms this response on the chatbot interface. This step involves the sending and receiving of response data.

[0608] Step 8:

[0609] If the server determines that a user's emotions are extremely negative, or if there is a complex problem that the AI ​​cannot handle, the server automatically notifies a specialized department. This prompts a real-time human response. This information transmission is achieved by constructing and sending notification messages.

[0610] (Application Example 2)

[0611] 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."

[0612] In caregiving settings, it is crucial to appropriately recognize the emotions of the elderly and their families and provide natural responses accordingly. However, with existing technologies, while it was possible to analyze user intentions, it was difficult to accurately recognize emotions, making personalized responses based on those emotions challenging. As a result, communication was insufficient, potentially undermining the user's sense of security.

[0613] 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.

[0614] In this invention, the server includes means for receiving information from a user, means for analyzing the received information using natural language processing to identify the user's intentions and emotions, and means for searching a set of reference information and extracting relevant information based on the identified intentions and emotions. This makes it possible to quickly and accurately recognize the emotions of the elderly and their families and provide a sense of security through appropriate responses.

[0615] "Means of receiving information from the user" refers to an interface that acquires voice or text data provided by the user.

[0616] "Natural language processing" is a technology that enables computers to understand, analyze, and generate responses to human language.

[0617] "Means for identifying user intent and emotions" refers to the process of analyzing received information to identify what the user wants and what their emotional state is.

[0618] "Means of searching a collection of reference information and extracting relevant information" refers to the process of searching for relevant information from databases and knowledge bases based on identified intentions and emotions, and retrieving the necessary information.

[0619] "Means for sending generated natural language sentences to the user" refers to a function that transmits responses generated based on analysis to the user via a device.

[0620] "A means of notifying the management department and escalating user inquiries" refers to a function that issues a warning to the management department and prompts appropriate action when the identified emotions exceed the system's capabilities.

[0621] A "machine learning algorithm" is a technology that allows computer systems to learn from experience and data to improve their performance.

[0622] The system for carrying out the present invention analyzes information provided through interaction with the user and generates an appropriate response based on the user's intentions and emotions. This system runs via a terminal such as a smartphone or smart glasses and a server in the cloud.

[0623] First, the user inputs information in voice or text format, which the device receives. This data is then transmitted to a server via a communication network. The server analyzes the user's intent using natural language processing libraries such as the Google Cloud Natural Language API. It also leverages sentiment analysis engines like IBM Watson Tone Analyzer to identify emotions from the user's text.

[0624] Once the analysis is complete, the server uses a generative AI model, such as OpenAI's GPT-4, to generate natural language responses based on the identified intent and sentiment information. During this process, machine learning algorithms are executed, resulting in improved scope and accuracy of the responses.

[0625] The generated response is sent from a server in the cloud to the user's terminal, allowing the user to review it immediately. Furthermore, if the user's emotions are particularly negative, or if the system cannot process the situation automatically, the server has a function to automatically notify the management department so they can respond quickly.

[0626] As a concrete example, suppose an elderly person says aloud, "Lately, I haven't been able to sleep at night." If the system receives this statement and the emotion engine detects "anxiety," the server will generate a response such as, "Don't worry, it's okay. Let's try to make today even more relaxing than usual," and send it to the terminal to provide reassurance.

[0627] Examples of prompts for a generative AI model include:

[0628] User input: "I haven't been able to sleep at night lately."

[0629] User's emotion: "Anxiety"

[0630] Please generate a response.

[0631] This system enables support that is sensitive to the emotions of users in care settings, thereby improving the quality of communication.

[0632] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0633] Step 1:

[0634] The device receives voice or text input from the user. Information spoken or typed by the user is captured through the device's microphone or keyboard. This input is stored as digital data for later processing.

[0635] Step 2:

[0636] The device converts the received audio data into text data. This is done using speech recognition technology. The converted text data becomes input for natural language processing. In this process, a language recognition library is used to convert speech to text.

[0637] Step 3:

[0638] The server uses a natural language processing library to receive text data as input and analyze the user's intent. This analysis includes grammatical and semantic analysis to identify what the user is asking for. The output is information that indicates the user's intent.

[0639] Step 4:

[0640] The server uses a sentiment analysis engine to identify the user's emotions from text data as input. In this step, specific keywords and phrases are analyzed, and the user's emotional state (e.g., "anxious" or "reassured") is obtained as output.

[0641] Step 5:

[0642] The server takes the identified intentions and emotions as input, searches a set of reference information, and extracts relevant information. Here, it selects relevant information from the database and obtains the information that should be provided to the user as output.

[0643] Step 6:

[0644] The server uses a generative AI model to generate natural language sentences from the extracted information as input. In this process, the generative AI model uses prompt sentences to output appropriate and emotionally sensitive response sentences.

[0645] Step 7:

[0646] The server sends the generated natural language text as input to the terminal. The terminal displays this output to the user. The user can view the response through a smartphone or smart glasses interface.

[0647] Step 8:

[0648] The server automatically notifies the management department if the user's emotions meet certain conditions. This notification allows the management department to take prompt action as needed.

[0649] 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.

[0650] 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.

[0651] 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.

[0652] [Fourth Embodiment]

[0653] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0654] 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.

[0655] 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).

[0656] 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.

[0657] 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.

[0658] 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).

[0659] 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.

[0660] 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.

[0661] 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.

[0662] 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.

[0663] 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.

[0664] 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.

[0665] 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".

[0666] This invention provides a system that enables employees within a company to access information regarding regulations and procedures more quickly and easily. The system is configured to process user inquiries and provide necessary information by analyzing the user's intent using natural language processing technology.

[0667] Specifically, the system will be implemented as follows: Users will use a chatbot interface via their device to input the information they want to know. For example, if a user inputs the question, "How many days of paid leave are there?", the device will send this input to the server in real time.

[0668] The server analyzes the received user input using natural language processing. Through this analysis, the server identifies keywords such as "paid leave" and "number of days," and determines the information the user wants to know. Next, based on the identified intent, it searches the company's internal database and extracts the relevant information.

[0669] The extracted information is converted into natural language sentences that are easy for the user to understand by a generating AI. For example, it might be sent to the user's device in a format like "Your annual paid leave is 20 days" and displayed in the chatbot window.

[0670] Furthermore, if the information entered by the user does not meet certain conditions, or if a complex question arises that the AI ​​cannot resolve, the server will notify the HR department and appropriately escalate the inquiry. This process allows users to quickly obtain the correct information, and enables HR personnel to smoothly handle complex situations.

[0671] This system also utilizes machine learning algorithms, which improve the accuracy and reliability of the information it generates. For example, it improves its understanding of user intent with each use, enabling more accurate and efficient responses to similar questions. This significantly reduces the time employees spend gathering information, leading to improved operational efficiency and cost savings for the HR department.

[0672] The following describes the processing flow.

[0673] Step 1:

[0674] The user uses their device to enter a question into the chatbot interface. For example, they might enter information in the form of, "Please tell me the number of paid vacation days."

[0675] Step 2:

[0676] The terminal transmits user input to the server in real time. During this process, it verifies that the data is transmitted correctly over the network.

[0677] Step 3:

[0678] The server analyzes the received input using natural language processing techniques to identify the user's intent. The analysis process utilizes algorithms for keyword extraction and contextual understanding.

[0679] Step 4:

[0680] Based on the identified intent, the server searches the company's internal regulations database. This database contains information about employment rules and personnel policies.

[0681] Step 5:

[0682] The server extracts relevant information from the database. For example, it might retrieve data containing the number of paid leave days.

[0683] Step 6:

[0684] The server uses a generative AI to generate natural language sentences that the user can understand based on the extracted information. For example, it can generate sentences such as, "Your annual paid leave is 20 days."

[0685] Step 7:

[0686] The server sends the generated response to the terminal, which then displays it to the user via a chatbot interface. The user can then view this and obtain the necessary information.

[0687] Step 8:

[0688] If a user asks further questions or makes a complex request, the server will re-analyze the content and, if necessary, escalate it to the HR department. The HR personnel will receive a notification so they can respond immediately.

[0689] (Example 1)

[0690] 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".

[0691] There is a growing need to expedite and facilitate employees' access to information regarding regulations and procedures within companies. However, traditional methods suffer from the problem of time-consuming information retrieval and difficulty in handling complex inquiries. Furthermore, there is a need for methods to improve the accuracy of the information users seek and to increase the efficiency of inquiry processing.

[0692] 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.

[0693] In this invention, the server includes means for acquiring data from a user, means for analyzing the acquired data using natural language processing technology to clarify the user's intent, and means for searching an information base and acquiring relevant data based on the clarified intent. This enables the rapid and appropriate provision of information within a company.

[0694] A "user" refers to an individual or legal entity that attempts to obtain information using the system.

[0695] "Data" refers to information about questions and requests obtained from users.

[0696] "Natural language processing technology" refers to computer technology used to analyze acquired data and identify its intent.

[0697] "Intent" refers to the purpose or necessary information that the user is seeking from the system.

[0698] An "information base" refers to a database that contains information about company regulations and procedures.

[0699] "Means of acquiring data" refers to the process of importing user data into the server.

[0700] "Relevant data" refers to the relevant information retrieved from the information base based on the user's identified intent.

[0701] "Methods for constructing natural language sentences" refers to the process of converting acquired relevant data into language that humans can understand.

[0702] A "notification" refers to a message sent to another department to inform them that a user's inquiry does not meet certain criteria.

[0703] "Machine learning technology" refers to algorithms that learn from data and apply the results to improve the performance of a system.

[0704] This system aims to quickly provide employees with information on regulations and procedures they need within a company. The system consists of the following elements:

[0705] Users log in to the chatbot interface on their device via the internet and enter the necessary information in text format. PCs and smartphones can be used as devices, and they access the system through a web browser.

[0706] The terminal sends data entered by the user to the server using the HTTPS protocol. The server is equipped with natural language processing technology for analysis, specifically using libraries such as spaCy and NLTK.

[0707] The server analyzes the received data using natural language processing to identify the user's intent. Based on this identified intent, the server issues SQL queries to the company's internal regulations database to retrieve relevant information. The database stores various regulations and procedural information set by the company.

[0708] The extracted information is converted into natural language sentences on the server using a generative AI model. For example, OpenAI's language model may be used as the generative AI. This generates easy-to-understand response sentences to questions entered by the user. A concrete example of such a response might be, "Your annual paid leave is 20 days."

[0709] The generated natural language text is sent back from the server to the user's device and displayed in the chatbot interface on the device. This interface provides information to the user in real time, improving the user experience.

[0710] Furthermore, if user input does not meet the requirements, or if a complex inquiry arises that cannot be resolved by the system, the server will automatically use its communication function to send an escalation notification to the appropriate department within the company.

[0711] A concrete example of a prompt message would be, "According to company regulations, how many paid leave days am I entitled to?" In this way, information tailored to the individual needs of the user is provided.

[0712] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0713] Step 1:

[0714] The user accesses the chatbot interface on their device and enters the information they want in text format. Specifically, this involves entering a sentence such as, "How many days of paid leave do I have?" This input becomes the data for the next process.

[0715] Step 2:

[0716] The terminal sends text data entered by the user to the server using the HTTPS protocol. Specifically, the terminal's actions include encoding the input data and sending it to the server via a secure communication channel. This prepares the server for analysis.

[0717] Step 3:

[0718] The server analyzes the received text data using natural language processing techniques. Specifically, it uses a natural language processing library to extract keywords such as "paid leave" and "number of days" to identify the user's intent. The output of this step is the analyzed intent.

[0719] Step 4:

[0720] The server searches the company's information base based on the identified intent. The server executes an SQL query to retrieve "paid leave" related information from the database. The input to this process is the previously identified intent, and the output is user-related paid leave information.

[0721] Step 5:

[0722] The server inputs the acquired data into a generative AI model to generate natural language sentences that are easy for the user to understand. For example, the generative AI model generates the response sentence, "Your annual paid leave is 20 days." The output of this step is natural language sentences.

[0723] Step 6:

[0724] The server sends the generated natural language sentence to the terminal. Specifically, the server encodes the sentence using a secure communication protocol and sends it to the terminal. This output is the natural language sentence that reaches the user's terminal.

[0725] Step 7:

[0726] The terminal displays the received natural language text in the chatbot interface. Through this interface, the user can visually confirm the information provided by the server. In this step, the input is natural language text from the server, and the output is the display on the terminal.

[0727] (Application Example 1)

[0728] 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".

[0729] Conventional home personal assistant robots have struggled to accurately process and provide individual information such as household rules and schedules. Conversational information provision requires correctly understanding the user's intentions and responding to diverse information needs. However, limitations in voice input accuracy and natural language processing often prevented appropriate responses. This resulted in limited user convenience and hindered the smooth progress of tasks and activities within the home.

[0730] 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.

[0731] In this invention, the server includes means for receiving information from a user, means for converting the received information into text data using a speech recognition processing device, and means for providing a knowledge base for providing information within the home and for quickly suggesting relevant information. This makes it possible to more accurately grasp the user's intentions and to provide relevant home information quickly and appropriately.

[0732] "Means of receiving information from users" refers to functions that acquire data input from users in the form of voice or text.

[0733] "Natural language processing" is a technology that uses computers to analyze human language and understand its meaning.

[0734] A "speech recognition processing device" is a device or software that analyzes speech input as a digital signal and converts it into text data.

[0735] "Rules and regulations" refer to aggregated data such as guidelines, schedules, and procedures that apply both inside and outside the home.

[0736] A "knowledge base" is a database where information in a specific domain is stored and can be searched as needed.

[0737] "Machine learning techniques" are technologies that allow computers to learn patterns from data and apply them to future predictions and classifications.

[0738] "Escalation" is the process of raising a problem or inquiry to a higher level of support if it cannot be resolved.

[0739] To implement this invention, a personal assistant robot for home use is required to have the following configuration: The robot is equipped with a voice recognition processing unit that receives information from the user's voice and converts it into text data. The converted text is sent to a server, where natural language processing technology is used to analyze the user's intent.

[0740] Based on the analyzed intent, the server searches its knowledge base for relevant rule information and extracts the necessary data. This allows the robot to provide the user with information about household rules and schedules. The extracted data is then converted into user-friendly natural language using a generative AI model and presented to the user in either audio or text format.

[0741] For example, if a user says, "Tell me what's on the schedule for today," the robot might respond with something like, "We have a family dinner at 7 PM." An example of a prompt for the generative AI model would be, "Based on the rules of this household, answer the following question: 'What's the task for today?'"

[0742] The hardware and software used include voice recognition devices such as Amazon Alexa and Google Home, speech-to-text services such as Google Cloud Speech-to-Text and Amazon Transcribe, and natural language processing and generative AI models such as Python's Natural Language Toolkit (NLTK) and OpenAI's GPT. In this way, the invention significantly improves the convenience of information access in the home environment.

[0743] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0744] Step 1:

[0745] The user inputs a question to the robot via voice. This voice data is converted into a digital signal by the robot's voice recognition processing unit. This process then converts the voice data into text data.

[0746] Step 2:

[0747] The device sends text data obtained through speech recognition to the server. The server receives this text data and analyzes the user's intent using natural language processing technology. In this process, the server extracts context and keywords to understand the user's request.

[0748] Step 3:

[0749] Based on the analyzed user intent, the server searches its internal knowledge base for relevant rule information. This process uses a search algorithm to identify information that matches the request and extracts the necessary data.

[0750] Step 4:

[0751] The server converts the extracted data into natural language sentences using a generative AI model. Here, the generative AI model processes the data and reconstructs it into sentences that are easy for the user to understand. This output is generated in text format.

[0752] Step 5:

[0753] The server sends the generated natural language text to the terminal, which then presents it to the user as either audio or text. The robot then uses the terminal to provide an appropriate response to the user's original question.

[0754] 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.

[0755] This invention provides a system that incorporates an emotion engine to recognize a user's emotions and utilize that information to provide appropriate natural language responses. This system processes user inquiries and, through emotion analysis, enables more personalized information delivery.

[0756] Specifically, users use their devices to input questions and requests through a chatbot interface. For example, they might ask, "I want to take paid leave, but the procedure seems complicated." The device then sends this input to the server.

[0757] When the server receives input information, it applies natural language processing techniques to analyze the user's intent. It also uses an emotion engine to identify the user's emotions from the input text. This emotion information can be expressed as a string, for example, "anxiety" or "frustration."

[0758] Based on the analyzed intent and emotional information, the server searches the company's internal database and extracts relevant information. During this process, consideration is given to providing the information in an appropriate tone and phrasing that reflects the user's emotions. Using generative AI, the extracted information is converted into natural language sentences, generating responses such as, "Don't worry. The procedure is simple, and you can take 20 days of paid leave per year."

[0759] The generated response is sent from the server to the terminal, and the user can view it through the chatbot interface. If the user's emotions are particularly negative, or if the AI ​​determines that the issue is too complex for it to handle, the server automatically notifies the HR department to prompt a quick response.

[0760] This system also leverages machine learning algorithms to accumulate and analyze users' emotional history, further improving the accuracy and personalization of responses in future interactions. This approach makes it possible to provide more empathetic and accurate support for employees' questions and concerns.

[0761] The following describes the processing flow.

[0762] Step 1:

[0763] The user uses their device to enter a question into the chatbot interface. For example, they might send a message like, "I'm worried because the paid leave application process is complicated."

[0764] Step 2:

[0765] The terminal sends the entered message to the server. This transmission takes place over the network.

[0766] Step 3:

[0767] The server analyzes received messages using natural language processing technology to identify the user's intentions and requests.

[0768] Step 4:

[0769] The server uses an emotion engine to recognize emotions from the user's text. For example, it can identify the emotion "anxiety" from a message.

[0770] Step 5:

[0771] The server searches the company's internal database based on intent and sentiment information, extracting information relevant to the user's inquiry.

[0772] Step 6:

[0773] The server uses a generative AI to convert the extracted information into natural language sentences. Taking emotional information into consideration, it generates sentences in a tone such as, "Please rest assured. The paid leave process is simple, and we will support you if needed."

[0774] Step 7:

[0775] The server sends the generated natural language response to the terminal.

[0776] Step 8:

[0777] The device displays the received response to the user through a chatbot interface. The user can then view this information and resolve any questions or concerns they may have.

[0778] Step 9:

[0779] The server automatically notifies the HR department if the user's emotions are particularly negative, and escalates the inquiry as needed. This allows the HR department to respond quickly.

[0780] Step 10:

[0781] The server stores user interaction history and sentiment information, which is then analyzed using machine learning algorithms. This improves the accuracy of future user responses and enhances personalized service.

[0782] (Example 2)

[0783] 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".

[0784] Conventional dialogue systems have faced challenges in generating responses that take user emotions into account, as they only analyze the user's intent. Furthermore, they lacked the ability to quickly and appropriately escalate issues when user emotions worsened or when inquiries were complex.

[0785] 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.

[0786] In this invention, the server includes a device for identifying the user's intent, an emotion analysis device for identifying the user's emotions from input information, and means for using a generative artificial intelligence model that searches for predetermined data based on the identified emotions and generates a response. This enables the generation of personalized responses and rapid escalation in accordance with the user's emotions.

[0787] A "device that receives information from a user" is a communication device that acquires text data entered by a user and sends that information to a server.

[0788] Natural language processing is a set of techniques and processes that enable computers to understand, analyze, and generate human language.

[0789] A "sentiment analysis device" is a system that identifies a user's emotional state from input text data and expresses it with an appropriate label.

[0790] "Regulated data" refers to data that includes past cases, internal organizational rules, guidelines, etc., and is referenced to provide information in response to user inquiries.

[0791] A "generative artificial intelligence model" is an algorithm that generates new text based on input data, and is a model that has the ability to produce natural-sounding sentences like a human.

[0792] A "device for notifying specialized departments" is a communication system that notifies the appropriate department within an organization of the situation when the AI ​​is unable to handle it, thereby encouraging a swift response.

[0793] A "machine learning algorithm" is a method that learns patterns from data and uses those learned results to make predictions and classifications.

[0794] The system of the present invention aims to return a personalized response to the user by having the user input inquiries and requests using a terminal, and processing them on a server. Specific embodiments of this system will be described below.

[0795] Users make text-based inquiries through a chatbot interface installed on their devices. For example, a user might ask, "I want to take paid leave, but the procedure seems complicated." This input is sent from the device to the server via a communication protocol.

[0796] The server first analyzes the received text data using natural language processing (NLP) techniques. Commonly used NLP technologies include SpaCy and BERT. This allows the server to identify the user's intent.

[0797] Next, the server uses an emotion analysis device to identify the user's emotional state from their text. This analysis could utilize emotion analysis tools such as TextBlob or Sentiment Analysis.

[0798] Based on the analyzed user intent and sentiment information, the server searches existing default data and extracts relevant data. SQL is the common database query language used.

[0799] Next, the server uses a generative AI model (e.g., an appropriate AI language model) to generate natural language responses based on the extracted data. This model can take the user's emotions into consideration and provide information in an appropriate tone.

[0800] The generated natural language sentences are sent from the server to the terminal, where the user reviews them through an interface. If the user's emotions do not meet certain criteria or if the AI ​​is unable to handle the situation, the server notifies a specialized department.

[0801] Furthermore, the server uses machine learning algorithms to analyze past user sentiment and interaction history, and utilizes this information to improve the system and enhance the accuracy of future responses.

[0802] An example of a prompt might be, "How should support be provided if an employee is experiencing work-related stress?" Using this prompt, the system will appropriately provide user support.

[0803] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0804] Step 1:

[0805] The user uses their device to enter inquiries or requests into the chatbot interface. The input data is in text format. For example, "I want to take paid leave, but the procedure seems complicated." The device then prepares to send this text to the server.

[0806] Step 2:

[0807] The terminal sends the user's input text to the server. HTTP or WebSocket is used as the communication protocol. At this stage, the output indicates that the user's text has been transferred to the server.

[0808] Step 3:

[0809] The server analyzes the received text using natural language processing (NLP) techniques. The input data is raw text, which is tokenized, POS tagged, and intent identified through NLP processing to determine the user's intent. Specifically, SpaCy and BERT support this throwing intelligence processing. The output after processing is structured data that indicates the user's intent.

[0810] Step 4:

[0811] The server identifies the user's emotions from the text received through the emotion analysis device. This process uses TextBlob and Sentiment Analysis to extract emotions contained in the input data. The emotion data is output as contextual information such as "anxiety" or "irritation."

[0812] Step 5:

[0813] The server searches internal company data based on the analyzed intent and sentiment information. It extracts relevant information from the database using SQL. The input is intent and sentiment data, and the output is the content of the related information.

[0814] Step 6:

[0815] The server generates a response using a generative AI model based on the extracted information. By inputting information into the generative AI model (e.g., an appropriate AI language model), a natural and appropriate response is output. At this stage, a personalized response that takes the user's emotions into account is obtained.

[0816] Step 7:

[0817] The server sends the generated response to the terminal. The terminal displays the received response to the user. The user confirms this response on the chatbot interface. This step involves the sending and receiving of response data.

[0818] Step 8:

[0819] If the server determines that a user's emotions are extremely negative, or if there is a complex problem that the AI ​​cannot handle, the server automatically notifies a specialized department. This prompts a real-time human response. This information transmission is achieved by constructing and sending notification messages.

[0820] (Application Example 2)

[0821] 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".

[0822] In caregiving settings, it is crucial to appropriately recognize the emotions of the elderly and their families and provide natural responses accordingly. However, with existing technologies, while it was possible to analyze user intentions, it was difficult to accurately recognize emotions, making personalized responses based on those emotions challenging. As a result, communication was insufficient, potentially undermining the user's sense of security.

[0823] 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.

[0824] In this invention, the server includes means for receiving information from a user, means for analyzing the received information using natural language processing to identify the user's intentions and emotions, and means for searching a set of reference information and extracting relevant information based on the identified intentions and emotions. This makes it possible to quickly and accurately recognize the emotions of the elderly and their families and provide a sense of security through appropriate responses.

[0825] "Means of receiving information from the user" refers to an interface that acquires voice or text data provided by the user.

[0826] "Natural language processing" is a technology that enables computers to understand, analyze, and generate responses to human language.

[0827] "Means for identifying user intent and emotions" refers to the process of analyzing received information to identify what the user wants and what their emotional state is.

[0828] "Means of searching a collection of reference information and extracting relevant information" refers to the process of searching for relevant information from databases and knowledge bases based on identified intentions and emotions, and retrieving the necessary information.

[0829] "Means for sending generated natural language sentences to the user" refers to a function that transmits responses generated based on analysis to the user via a device.

[0830] "A means of notifying the management department and escalating user inquiries" refers to a function that issues a warning to the management department and prompts appropriate action when the identified emotions exceed the system's capabilities.

[0831] A "machine learning algorithm" is a technology that allows computer systems to learn from experience and data to improve their performance.

[0832] The system for carrying out the present invention analyzes information provided through interaction with the user and generates an appropriate response based on the user's intentions and emotions. This system runs via a terminal such as a smartphone or smart glasses and a server in the cloud.

[0833] First, the user inputs information in voice or text format, which the device receives. This data is then transmitted to a server via a communication network. The server analyzes the user's intent using natural language processing libraries such as the Google Cloud Natural Language API. It also leverages sentiment analysis engines like IBM Watson Tone Analyzer to identify emotions from the user's text.

[0834] Once the analysis is complete, the server uses a generative AI model, such as OpenAI's GPT-4, to generate natural language responses based on the identified intent and sentiment information. During this process, machine learning algorithms are executed, resulting in improved scope and accuracy of the responses.

[0835] The generated response is sent from a server in the cloud to the user's terminal, allowing the user to review it immediately. Furthermore, if the user's emotions are particularly negative, or if the system cannot process the situation automatically, the server has a function to automatically notify the management department so they can respond quickly.

[0836] As a concrete example, suppose an elderly person says aloud, "Lately, I haven't been able to sleep at night." If the system receives this statement and the emotion engine detects "anxiety," the server will generate a response such as, "Don't worry, it's okay. Let's try to make today even more relaxing than usual," and send it to the terminal to provide reassurance.

[0837] Examples of prompts for a generative AI model include:

[0838] User input: "I haven't been able to sleep at night lately."

[0839] User's emotion: "Anxiety"

[0840] Please generate a response.

[0841] This system enables support that is sensitive to the emotions of users in care settings, thereby improving the quality of communication.

[0842] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0843] Step 1:

[0844] The device receives voice or text input from the user. Information spoken or typed by the user is captured through the device's microphone or keyboard. This input is stored as digital data for later processing.

[0845] Step 2:

[0846] The device converts the received audio data into text data. This is done using speech recognition technology. The converted text data becomes input for natural language processing. In this process, a language recognition library is used to convert speech to text.

[0847] Step 3:

[0848] The server uses a natural language processing library to receive text data as input and analyze the user's intent. This analysis includes grammatical and semantic analysis to identify what the user is asking for. The output is information that indicates the user's intent.

[0849] Step 4:

[0850] The server uses a sentiment analysis engine to identify the user's emotions from text data as input. In this step, specific keywords and phrases are analyzed, and the user's emotional state (e.g., "anxious" or "reassured") is obtained as output.

[0851] Step 5:

[0852] The server takes the identified intentions and emotions as input, searches a set of reference information, and extracts relevant information. Here, it selects relevant information from the database and obtains the information that should be provided to the user as output.

[0853] Step 6:

[0854] The server uses a generative AI model to generate natural language sentences from the extracted information as input. In this process, the generative AI model uses prompt sentences to output appropriate and emotionally sensitive response sentences.

[0855] Step 7:

[0856] The server sends the generated natural language text as input to the terminal. The terminal displays this output to the user. The user can view the response through a smartphone or smart glasses interface.

[0857] Step 8:

[0858] The server automatically notifies the management department if the user's emotions meet certain conditions. This notification allows the management department to take prompt action as needed.

[0859] 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.

[0860] 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.

[0861] 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.

[0862] 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.

[0863] 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.

[0864] 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.

[0865] 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.

[0866] 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.

[0867] 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."

[0868] 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.

[0869] 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.

[0870] 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.

[0871] 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.

[0872] 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.

[0873] 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.

[0874] 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.

[0875] 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.

[0876] 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.

[0877] 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.

[0878] 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.

[0879] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0880] The following is further disclosed regarding the embodiments described above.

[0881] (Claim 1)

[0882] Means of receiving information from users,

[0883] A means of analyzing received information using natural language processing to identify the user's intent,

[0884] A means for searching a specified database and extracting relevant information based on the identified intent,

[0885] A means of generating natural language sentences based on extracted information,

[0886] A system including means for sending generated natural language sentences to a user.

[0887] (Claim 2)

[0888] The system according to claim 1, further comprising means for notifying the human resources department and escalating the user's inquiry if the information from the user does not meet certain conditions.

[0889] (Claim 3)

[0890] The system according to claim 1, comprising means of using a machine learning algorithm to adjust the scope of application of extracted information and improve the accuracy of the generated natural language sentences.

[0891] "Example 1"

[0892] (Claim 1)

[0893] Means of obtaining data from users,

[0894] The acquired data is analyzed using natural language processing technology to clarify the user's intent,

[0895] With a clearly defined intent, the means of searching the information base and obtaining relevant data,

[0896] A means of constructing natural language sentences based on acquired data,

[0897] A system including means for sending a constructed natural language sentence to a user.

[0898] (Claim 2)

[0899] The system according to claim 1, further comprising means for notifying a department and raising the processing stage of a user inquiry if data from a user does not meet certain criteria.

[0900] (Claim 3)

[0901] The system according to claim 1, comprising means of using machine learning techniques to adjust the scope of application of acquired data and improve the accuracy of constructed natural language sentences.

[0902] "Application Example 1"

[0903] (Claim 1)

[0904] Means of receiving information from users,

[0905] A means of analyzing received information using natural language processing to identify the user's intent,

[0906] A means of searching for rule information and extracting relevant knowledge based on a specified intent,

[0907] A means of generating natural language sentences based on extracted knowledge,

[0908] A means for sending the generated natural language sentence to the user,

[0909] A means for analyzing a user's voice input using a speech recognition processing device and converting it into text data,

[0910] A system that includes a knowledge base for providing information within the home and means for quickly suggesting relevant information.

[0911] (Claim 2)

[0912] The system according to claim 1, further comprising means for notifying the service department and escalating the user's inquiry if the information from the user does not meet certain conditions.

[0913] (Claim 3)

[0914] The system according to claim 1, comprising means of using machine learning techniques to adjust the scope of application of extracted knowledge and improve the accuracy of generated natural language sentences.

[0915] "Example 2 of combining an emotion engine"

[0916] (Claim 1)

[0917] A device that receives information from a user,

[0918] A device that analyzes received information using natural language processing to identify the user's intent,

[0919] An emotion analysis device that identifies the user's emotions from input information,

[0920] A device that searches for specified data and extracts relevant information based on identified intentions and identified emotions,

[0921] A device that generates natural language sentences using a generative artificial intelligence model based on extracted information,

[0922] A device that sends generated natural language sentences to the user,

[0923] A system that includes this.

[0924] (Claim 2)

[0925] The system according to claim 1, further comprising a device for notifying a specialized department and escalating a user's inquiry if the user's emotions do not meet certain criteria or if the artificial intelligence model is unable to address the issue.

[0926] (Claim 3)

[0927] The system according to claim 1, comprising a machine learning algorithm used to adjust the scope of application of extracted information and improve the accuracy of the generated natural language sentences.

[0928] "Application example 2 when combining with an emotional engine"

[0929] (Claim 1)

[0930] Means of receiving information from users,

[0931] A means of analyzing received information using natural language processing to identify the user's intentions and emotions,

[0932] A means for searching a set of reference information and extracting relevant information based on identified intentions and emotions,

[0933] A means of generating natural language sentences based on extracted information,

[0934] A system including means for sending generated natural language sentences to a user.

[0935] (Claim 2)

[0936] The system according to claim 1, further comprising means for notifying the management department and escalating the user's inquiry if the identified emotion does not meet certain conditions.

[0937] (Claim 3)

[0938] The system according to claim 1, comprising means of using a machine learning algorithm to adjust the scope of application of the extracted information and to improve the accuracy and familiarity of the generated natural language sentences. [Explanation of symbols]

[0939] 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. Means of receiving information from users, A means of analyzing received information using natural language processing to identify the user's intent, A means for searching a specified database and extracting relevant information based on the identified intent, A means of generating natural language sentences based on extracted information, A system including means for sending generated natural language sentences to a user.

2. The system according to claim 1, further comprising means for notifying the human resources department and escalating the user's inquiry if the information from the user does not meet certain conditions.

3. The system according to claim 1, comprising means of using a machine learning algorithm to adjust the scope of application of extracted information and improve the accuracy of the generated natural language sentences.

Images