system

Abstract

We provide the system. [Solution] A means of analyzing user inquiries using a natural language processing engine and identifying the intent behind those inquiries, A means for acquiring relevant information from an information acquisition device based on the analyzed intent, A means of generating a response to the user in natural language format based on the acquired information, A means for transmitting and presenting the generated response to the user interface, A method for recommending products based on past purchase data, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In conventional customer service, there are problems that a large amount of manpower and time are required for inquiry response, resulting in a loss of customer satisfaction. Also, responding in a 24-hour system is costly and difficult to achieve for small and medium-sized enterprises. Furthermore, even when the inquiry contents are similar, there are variations in the judgments and responses of individual operators, making it difficult to provide a consistent service.

Means for Solving the Problems

[0005] This invention provides a means for accurately obtaining relevant information by rapidly analyzing user inquiries using a natural language processing engine and identifying their intent. Furthermore, it constructs a system that enables consistent 24 / 7 support by generating responses in natural language format from the acquired information and presenting them through a user interface. This system incorporates a means for continuously improving response accuracy through machine learning based on user inquiry history, thereby achieving improved customer satisfaction and reduced operating costs for businesses.

[0006] A "natural language processing engine" is a technical means of analyzing natural language input provided by a user and understanding its meaning.

[0007] A "user" refers to an individual or legal entity that uses the system to ask questions or make requests.

[0008] "Inquiry" refers to a request for information or a problem presented by a user to the system.

[0009] An "information acquisition device" refers to a database or external system that stores or makes accessible the necessary information.

[0010] "Means of generating responses" refers to technologies that construct appropriate answers to queries and output them in natural language format.

[0011] A "user interface" refers to the means of input and output that enable interaction between the user and the system.

[0012] A "machine learning algorithm" refers to a process that uses data to continuously improve the performance and accuracy of a system's responses. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2]It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which 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 Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

MODE FOR CARRYING OUT THE INVENTION

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described according to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, a 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.

[0017] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0019] In the following embodiments, a numbered communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

[0020] 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."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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".

[0034] This invention relates to a system for efficiently automating customer service. The system includes a series of processes that receive inquiries from users via a user interface, analyze the content of those inquiries on a server, and generate appropriate responses.

[0035] Users input questions or problems via text or voice using their device. A dedicated chatbot or voice bot runs on the device, receiving the user's input in real time. The input data is then sent from the device to the server.

[0036] The server analyzes the received data using a natural language processing engine to accurately understand the user's intent. For example, if a user inquires, "I want to know the status of my order," the server identifies this intent as "checking the order status." This process uses machine learning algorithms and existing dictionary databases to enable highly accurate analysis.

[0037] Based on the analysis results, the server accesses the information acquisition device and collects relevant data. For example, it retrieves the current status of orders associated with a specific customer ID from the database. This information serves as the raw material for generating answers to user inquiries.

[0038] The server generates the optimal response for the user based on the acquired data. This response is then formatted back into natural language and sent to the terminal. The terminal presents this response to the user on its user interface, either displaying it on the chat screen or outputting it as audio.

[0039] For example, if a user inquires about tracking an order, the system will check the delivery status based on the order number. The server will generate a response such as, "Order number 12345 is currently in transit and is expected to arrive tomorrow," and the user can confirm this information on their device's display screen or via audio output.

[0040] Furthermore, the user interface stores a log of the user's past inquiries, and this data is used to improve follow-up inquiries and provide personalized customer service. In this way, the system can continue to be refined and provide a more accurate service through continuous use.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The user enters their inquiry via text or voice through the terminal. The terminal receives this input and, if necessary, converts the voice input to text.

[0044] Step 2:

[0045] The terminal sends the user's inquiry to the server. The server passes the received message to a natural language processing engine, which analyzes the user's intent and interests. Specifically, it breaks down the inquiry content and extracts its categories and keywords.

[0046] Step 3:

[0047] The server then refers to the database based on the analysis results and retrieves the necessary information. For example, if it's to check the order status, it retrieves the relevant order data from the database.

[0048] Step 4:

[0049] The server generates a response to the user based on the acquired data. The response is written in natural language and formatted in a way that is easy for the user to understand.

[0050] Step 5:

[0051] The server sends the generated response to the terminal. The terminal then displays this response on its screen or communicates it to the user via voice.

[0052] Step 6:

[0053] The user reviews the response and makes additional inquiries if necessary. The terminal sends this additional information back to the server and continues processing.

[0054] Step 7:

[0055] After processing is complete, the server records the query logs and response history, and uses this data to improve the service using machine learning algorithms.

[0056] (Example 1)

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

[0058] In today's world, responding quickly and accurately to user inquiries is crucial. However, conventional systems have struggled to accurately grasp user intent and automatically generate appropriate responses based on that intent. Furthermore, they have been insufficient in continuously improving response quality through the effective use of history. Moreover, there is a growing need to support diverse user input formats, including voice and text.

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

[0060] In this invention, the server includes means for analyzing queries and identifying intent using a natural language processing engine, means for acquiring relevant information from an information acquisition device, means for generating a response in natural language format based on the acquired information, means for converting user input into text using speech recognition software, and means for saving past query history and improving the quality of responses. This makes it possible to accurately grasp the user's intent and generate high-quality responses based on relevant information.

[0061] A "natural language processing engine" is a technology that allows computers to understand and analyze human language, and is used to identify the meaning and intent of text.

[0062] "User" refers to an individual or legal entity that makes an inquiry using the system.

[0063] An "inquiry" refers to a question or request for information that a user submits to the system.

[0064] "Analysis" refers to the process of processing received information and interpreting its content and meaning.

[0065] "Intention" refers to the information or purpose that the user making the inquiry is seeking.

[0066] An "information acquisition device" refers to a device or function used to acquire necessary information from a database or external data source.

[0067] "Response" refers to the answer or information provided by a system in response to a user's inquiry.

[0068] "Speech recognition software" refers to the technology and programs that convert speech input into text information.

[0069] "User interface" refers to the screen display and means of operation that allow users to interact with the system.

[0070] "Inquiry history" refers to a record of inquiries made by users in the past and the responses to those inquiries.

[0071] A "machine learning algorithm" refers to a computational method that learns a model based on data and automatically discovers patterns and rules.

[0072] This invention is an automated system for generating efficient and accurate responses to user inquiries. Specifically, it involves receiving text or voice input via a user interface, which is then analyzed by a server to generate an appropriate response.

[0073] The terminal is equipped with speech recognition software, which has the ability to convert voice input into text with high accuracy. For example, if a user voice-inputs "I want to know the status of my order," the speech recognition software converts this into text data. The converted text is then sent from the terminal to the server.

[0074] The server has a built-in natural language processing engine that analyzes the received text data. This analysis specifically identifies the user's intent and collects appropriate information based on that intent. Generative AI models are used for the analysis, such as BERT or GPT. As a result, the user's intent, "I want to know the status of my order," is identified in the form of "check order status."

[0075] When retrieving information, the server accesses relevant databases to collect the necessary information. This includes retrieving the current order status based on the customer ID and order number. Based on this information, the server generates a natural language response to the user. This response is then sent back to the terminal and either displayed on the user interface or presented via an audio output device.

[0076] For example, when a user tracks their order using the order number, the system can automatically retrieve shipping information and generate a response such as, "Order number 12345 is currently in transit and is expected to arrive tomorrow." The user can then confirm this information on their device screen or via voice.

[0077] An example of a prompt message would be, "A user has inquired about order tracking. Please generate an appropriate response," which would be input to the generation AI model. This prompt would then prepare the model to efficiently provide a response to the user.

[0078] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0079] Step 1:

[0080] The user enters their inquiry using the terminal in either voice or text format. In the case of voice input, the terminal's voice recognition software converts the voice into text. For example, the user might ask, "I want to know the status of my order." The entered voice is output as text data and sent to the next processing step.

[0081] Step 2:

[0082] The terminal sends the converted text data to the server. The communication protocol used here is HTTP or HTTPS. Specifically, the terminal converts the data into a JSON formatted request and transfers the data to the server via a secure connection. The input is text data, and the output is sent to the server.

[0083] Step 3:

[0084] The server inputs the received text data into a generative AI model, which then analyzes it using a natural language processing engine. At this stage, the server uses the generative AI model's prompts to identify the user's intent. For example, it identifies the intent "I want to know the status of my order" as "check the order status" and performs advanced language analysis and contextual understanding. As a result, the data is transformed into an intent.

[0085] Step 4:

[0086] Based on the identified intent, the server collects relevant information from the database through an information retrieval device. Specifically, the server uses the customer ID and order number to search for the current delivery status and extract the necessary information. The input is an intent-based query, and the output is information such as order status retrieved from the database.

[0087] Step 5:

[0088] The server generates a response to the user in natural language format based on the acquired information. This response constructs sentences based on the data collected in the previous step. For example, it might generate a response such as, "Order number 12345 is currently being shipped and is expected to arrive tomorrow." The input is the collected data, and the output is a response in natural language format.

[0089] Step 6:

[0090] The server sends the generated response to the terminal, which receives it. The terminal then either displays the received response on the user interface or outputs it as audio using a speech synthesizer. Specifically, it displays the response on the chat screen or plays it back through the speaker. The input is the generated response, and the output is either a display or audio output.

[0091] This series of processes allows users to quickly obtain accurate answers to their inquiries.

[0092] (Application Example 1)

[0093] 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."

[0094] E-commerce sites are required to respond quickly and accurately to a wide range of user inquiries, as well as to recommend products based on past purchase data. However, traditional systems have struggled to integrate and effectively implement these responses and recommendations. As a result, improvements in the user experience have been hindered, and the need for efficient customer service is increasing.

[0095] 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.

[0096] In this invention, the server includes means for analyzing user inquiries and identifying their intent using a natural language processing engine, means for acquiring relevant information from an information acquisition device, and means for generating a response in natural language format based on the acquired information. This enables rapid responses to user inquiries and effective product recommendations utilizing past purchase data.

[0097] A "natural language processing engine" is a software technology that analyzes text or voice input from a user to understand its meaning and intent.

[0098] An "information acquisition device" is a device or program used to extract necessary information from a database or similar source based on an analyzed intent.

[0099] A "user interface" is an interface that allows users to interact with a system, enabling input and output via text or voice.

[0100] A "machine learning algorithm" is an algorithm that uses past data to improve the accuracy of responses, and it improves the system based on experience.

[0101] "Purchase data" refers to the history of products a user has purchased so far, and it is an important indicator when making product recommendations.

[0102] "Product recommendation" is the process of suggesting highly relevant products based on the user's interests and purchase history.

[0103] The embodiment of this invention is based on a system that enables automated customer support on an e-commerce site. Primarily, three parties—a server, a terminal, and a user—each play their respective roles.

[0104] The server utilizes a natural language processing engine to analyze text or voice inquiries sent from the user via their device. During the analysis process, the server leverages the Google® Cloud Natural Language API to understand the meaning of the input and identify the intent of the inquiry. As a result, it uses Firebase Realtime Database as a database to retrieve relevant information and extracts the necessary data. This integration of analysis and data retrieval establishes a process for generating optimized responses for the user in natural language format.

[0105] Furthermore, the server provides a product recommendation function using machine learning algorithms. For this purpose, a model using TENSORFLOW® enables the recommendation of highly relevant products based on past purchase data. This entire system is designed to be accessible to users via smartphones and other devices, and is built to be easily accessible through its interface.

[0106] When a user asks, "What are the latest recommended products?", the server analyzes their purchase history, selects appropriate products, and generates a response such as, "Based on your recent purchases, we recommend this new ebook." An example of this prompt would be, "Based on the data of books the user has purchased, please suggest 5 books that they are likely to purchase next."

[0107] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0108] Step 1:

[0109] The user enters their inquiry via text or voice using a device. The entered data is sent to the server via an interface running on the device. The user's input (e.g., "What are the latest recommended products?") is sent to the system.

[0110] Step 2:

[0111] The server uses the Google Cloud Natural Language API to analyze the received text or audio data. Natural language processing is performed here to determine the intent of the user's question. The input data is semantically analyzed to identify the intent of the inquiry (e.g., "request for product recommendations").

[0112] Step 3:

[0113] The server accesses the Firebase Realtime Database and retrieves relevant information based on the query intent. Purchase history data and other information are extracted, and the information necessary for product recommendations is collected.

[0114] Step 4:

[0115] Based on the collected information, the server runs a machine learning model using TensorFlow. It analyzes past purchase data and recommends highly relevant products. The input data is analyzed and a list of recommended products is generated (e.g., "Select the 5 best ebooks").

[0116] Step 5:

[0117] The generated recommendation results are formatted in natural language so that the user can understand them, and then sent from the server to the terminal. The generated text (e.g., "Based on your recent purchases, we recommend this new ebook.") is output.

[0118] Step 6:

[0119] The user's device displays the received response. The user can review the results and browse the recommended products or make a purchase decision. The generated recommendation text is displayed on the interface, prompting the user to take actual action.

[0120] 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.

[0121] This invention relates to a system that automates customer service through a user interface and has the ability to recognize user emotions. By combining natural language processing and emotion recognition functions, the system can provide more accurate and emotionally sensitive responses to user inquiries.

[0122] The user enters questions or problems in text or voice format using a terminal. The terminal receives this input and converts voice input to text as needed. The entered data is then sent to the server for further processing.

[0123] The server passes the received data to a natural language processing engine, which analyzes the user's intent. In this process, the query is understood based on the context of the words, and appropriate categories and keywords are extracted.

[0124] Next, the server uses an emotion engine to analyze the emotional nuances and states contained in the user's input. This analysis allows the server to understand the user's feelings, such as whether they are dissatisfied or in a state of urgency.

[0125] Based on the analysis results, the server retrieves necessary information from the database and adjusts the content and tone of its response according to the user's emotional state. As a result, a more appropriate and receptive response becomes possible.

[0126] For example, if a user complains that their order hasn't arrived, the server will first check the delivery status and then generate a response that includes an apology and a solution, such as, "We apologize for the inconvenience. Order ID 12345 is currently in transit and is expected to arrive tomorrow. We ask for your patience."

[0127] The generated response is sent back to the terminal, which then displays or audibly presents this response through the user interface. Furthermore, the user's interaction history and emotional data are recorded as logs and used as data to continuously improve the service using machine learning algorithms. By implementing the invention in this way, improved customer satisfaction and efficient service operation are achieved.

[0128] The following describes the processing flow.

[0129] Step 1:

[0130] The user enters their inquiry via text or voice through the terminal. If voice input is received, the terminal converts it to text and prepares to send the input to the server.

[0131] Step 2:

[0132] The terminal sends the user's query data to the server. The server analyzes the received data using a natural language processing engine to understand the intent of the query. Specifically, it analyzes the sentence structure and identifies the main content of the query.

[0133] Step 3:

[0134] The server uses an emotion engine to extract emotional information from the text entered by the user. For example, it determines the user's emotional state from keywords and context and evaluates it as positive, negative, or neutral.

[0135] Step 4:

[0136] Based on the analyzed intent and sentiment data, the server retrieves relevant information by referring to the database. For example, if a user asks a question related to an order, the server collects the status information for that order at this stage.

[0137] Step 5:

[0138] The server generates responses based on the user's emotional state. If the user expresses dissatisfaction, the response will be adjusted to use more polite and considerate language. A specific example of a response would be: "We apologize for the inconvenience. We are currently reviewing the status of your order."

[0139] Step 6:

[0140] The server sends the generated response to the terminal. The terminal then presents the received response to the user either by displaying it on the screen or by outputting it as speech using speech synthesis.

[0141] Step 7:

[0142] The user can review the provided response and inquire again if they have any further questions or feedback. The terminal receives new input and prepares to send it back to the server for further processing.

[0143] Step 8:

[0144] The server logs conversation history and sentiment data, and uses machine learning algorithms to continuously improve the accuracy of the model. This allows the system to periodically improve the quality of its responses to match user tendencies.

[0145] (Example 2)

[0146] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0147] Modern information processing systems are required to accurately understand the intent behind user inquiries and provide responses that are sensitive to their emotional needs. However, conventional systems have not been able to adequately achieve this, resulting in lower user satisfaction. Furthermore, there is a need for more effective technologies to improve response accuracy by learning from inquiry history.

[0148] 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.

[0149] In this invention, the server includes means for analyzing user inquiries and identifying their intent using natural language processing technology, means for obtaining relevant information from information sources, means for generating responses to the user in natural language format based on the obtained information, and means for analyzing the user's emotional nuances using sentiment analysis technology and adjusting the response accordingly. This makes it possible to provide highly accurate responses that take into account the user's intent and emotions.

[0150] "Natural language processing technology" refers to computational techniques that enable computers to understand, generate, and analyze human language.

[0151] "User" refers to an individual or organization that uses the system to make an inquiry.

[0152] "Intention" refers to the purpose or goal that the user is seeking through their inquiry.

[0153] "Information source" refers to the databases or storage media that the server accesses to retrieve relevant information.

[0154] "Natural language forms" refer to expressions using the linguistic forms that humans use on a daily basis.

[0155] A "user display device" refers to a device that includes an interface for displaying responses and information to the user.

[0156] "Emotional analysis technology" is a computational technique for analyzing the nuances of emotions from user input.

[0157] "Machine learning technology" refers to algorithms that allow computers to learn from past data and improve the accuracy of future predictions and responses.

[0158] "Inquiry history" refers to records of inquiries made by users in the past.

[0159] This invention provides a technology that utilizes a computer system to generate responses in natural language to user inquiries. The system consists of a terminal and a server, and automatically generates appropriate responses when the user inputs information in natural language.

[0160] A terminal is a device used by users to input inquiries. The terminal has a user interface that accepts text and voice input. In the case of voice input, the terminal uses speech recognition software (e.g., a speech recognition API) to convert the speech into text. The converted text data is then sent to a server for information processing.

[0161] The server analyzes the received text data and performs information processing to understand the user's intent and emotions. Using natural language processing techniques, the server analyzes the intent contained in the user's question and extracts relevant keywords and categories. Furthermore, using sentiment analysis techniques, it analyzes the emotional nuances contained in the inquiry and adjusts the response accordingly.

[0162] This analysis allows the server to retrieve relevant information from the database and generate a natural language response that takes into account the user's intent and feelings. For example, if a user inquires, "I'm having trouble because my order hasn't arrived," the server will check the delivery status and generate a response that includes an appropriate apology and solution. A specific example of such a response would be, "We apologize for the inconvenience. Order ID 12345 is currently in transit and is expected to arrive tomorrow. We ask for your patience."

[0163] The generated response is sent back to the terminal, which then presents this response to the user via the user interface. The user interaction history and sentiment data are logged on the server and used by machine learning algorithms to improve the service later.

[0164] The system provides information to the generating AI model using prompts such as: "The user has the following inquiry: 'I'm having trouble because my order hasn't arrived.' Generate an appropriate response to this inquiry, expressing it in language that takes the user's feelings into consideration."

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

[0166] Step 1:

[0167] The user uses the terminal to input their inquiry as text or voice. In the case of voice input, the terminal uses speech recognition software to convert the voice into text. This process prepares the user's natural language input as text data.

[0168] Step 2:

[0169] The device sends the text data converted by speech recognition or the original text input to the server. The text data becomes the input at this point.

[0170] Step 3:

[0171] The server passes the received text data to a natural language processing engine. The server uses this engine to analyze the user's intent from the text data and extract relevant categories and keywords. The analysis results are then output.

[0172] Step 4:

[0173] The server passes the analysis results to the sentiment analysis engine. The server uses this engine to understand the user's emotional nuances from the input data. For example, emotional information such as dissatisfaction or urgency is output.

[0174] Step 5:

[0175] The server retrieves relevant information from the database based on the analysis results of intentions and emotions. The server integrates the retrieved information with the analysis results and generates an appropriate response in natural language. The generated response becomes the output data.

[0176] Step 6:

[0177] The server sends the generated response to the terminal. The terminal presents the received response to the user via a display device or audio output. This allows the user to receive a response from the system.

[0178] Step 7:

[0179] The server logs user interaction history and sentiment data. This data is then used to apply machine learning and improve the accuracy of the service.

[0180] (Application Example 2)

[0181] 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".

[0182] Existing customer service systems often fail to adequately adjust responses to user inquiries based on the situation, leading to decreased user satisfaction. Furthermore, a lack of consideration for user emotions results in service quality not meeting expectations.

[0183] 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.

[0184] In this invention, the server includes means for analyzing user inquiries using a natural language processing engine and identifying the user's intent, means for acquiring relevant information from an information acquisition device based on the analyzed intent, and means for determining the user's emotions based on the analysis results and adjusting the response content according to the emotional state. This makes it possible to provide appropriate and individualized responses that take the user's emotions into consideration.

[0185] A "natural language processing engine" is software or a system that enables computers to understand and analyze human language.

[0186] "Users" refers to people who operate or use the system, including customers and end users.

[0187] "Inquiry" refers to the act of asking questions about information that a user wants to know or a problem they want to solve.

[0188] "Intention" refers to the purpose or request that the user hopes to achieve through their inquiry.

[0189] An "information acquisition device" is a device or system for storing necessary materials and data and providing information related to an inquiry.

[0190] A "response" refers to the answer or reply that a system generates based on a user's inquiry.

[0191] "Emotion" refers to a person's psychological state, including states such as joy and dissatisfaction.

[0192] A "user interface" is a means for a user and a computer system to communicate with each other, and includes screen display and audio output.

[0193] A "machine learning algorithm" is a method of computer programming that automatically learns by identifying patterns from data and improves performance.

[0194] To implement this invention, a series of systems for processing user inquiries is required. These systems primarily consist of terminals, servers, and databases.

[0195] The terminal is a device equipped with a user interface similar to a smartphone or smart glasses, and accepts user inquiries in the form of voice or text. Voice input is converted to text using speech recognition software on the terminal (e.g., Google Speech-to-Text API). The converted text information is then sent to the server.

[0196] The server uses a natural language processing engine (e.g., BERT model) to analyze the user's inquiry text and identify its intent. Then, it uses an emotion recognition engine (e.g., OpenAI® Sentiment Analysis API) to determine the user's emotions and generate an appropriate response based on the context. For example, if the user expresses dissatisfaction with the delivery status, the server will provide a polite apology along with updated delivery information.

[0197] Based on the analysis results, relevant information is retrieved from the database, a response tailored to the user's emotions is constructed, and the response is generated in natural language. The generated response is sent to the device and presented to the user in text or audio format.

[0198] Furthermore, user interaction history and sentiment data are recorded in a database and used by machine learning algorithms to continuously improve the accuracy of the service. This allows the system to respond more accurately to the individual needs of users.

[0199] For example, when a user inquires that "the item I recently ordered has not yet arrived," the server uses a prompt message such as, "Please understand the user's intent, check the current delivery status of order ID 12345, and consider the best response to resolve the user's dissatisfaction." This prompt is then used to generate an appropriate response and resolve the user's complaint.

[0200] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0201] Step 1:

[0202] The terminal receives inquiries from the user in either voice or text format. In the case of voice inquiries, the terminal uses speech recognition software to convert the speech to text. The input in this process is the user's inquiry, and the output is text data.

[0203] Step 2:

[0204] The terminal sends the converted text data to the server. The transmitted data corresponds to the user's inquiry.

[0205] Step 3:

[0206] The server uses a natural language processing engine to analyze the received text data. The input is text data, and the output is an analysis result that includes the user's intent. This intent analysis determines the meaning and purpose of the inquiry.

[0207] Step 4:

[0208] The server uses an emotion recognition engine to determine the emotions contained in the user's input. This process generates emotion labels based on the analysis results, and the user's emotional state is obtained as output. For example, information such as whether the user is dissatisfied may be obtained.

[0209] Step 5:

[0210] The server retrieves relevant information from the database based on the analysis results and emotional state. The input is the user's intent and emotional state, and the output is data for the response. Specific information such as order status and product information is extracted here.

[0211] Step 6:

[0212] The server generates a response in natural language format based on the relevant information and emotional state it has acquired. For example, it might generate a response such as, "We apologize for the inconvenience. Order ID 12345 is currently being shipped and is expected to arrive tomorrow."

[0213] Step 7:

[0214] The server sends the generated response to the terminal, which then presents it to the user via text or audio through its user interface. The input here is the response data, and the output is the display or audio presentation to the user.

[0215] Step 8:

[0216] The server records user interaction history and sentiment data in a database, which is then used by machine learning algorithms to improve the accuracy of future responses. In this process, the content of the interaction is utilized as data for future accuracy improvements.

[0217] 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.

[0218] 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.

[0219] 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.

[0220] [Second Embodiment]

[0221] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0222] 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.

[0223] 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).

[0224] 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.

[0225] 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.

[0226] 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).

[0227] 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.

[0228] 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.

[0229] 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.

[0230] 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.

[0231] 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.

[0232] 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".

[0233] This invention relates to a system for efficiently automating customer service. The system includes a series of processes that receive inquiries from users via a user interface, analyze the content of those inquiries on a server, and generate appropriate responses.

[0234] Users input questions or problems via text or voice using their device. A dedicated chatbot or voice bot runs on the device, receiving the user's input in real time. The input data is then sent from the device to the server.

[0235] The server analyzes the received data using a natural language processing engine to accurately understand the user's intent. For example, if a user inquires, "I want to know the status of my order," the server identifies this intent as "checking the order status." This process uses machine learning algorithms and existing dictionary databases to enable highly accurate analysis.

[0236] Based on the analysis results, the server accesses the information acquisition device and collects relevant data. For example, it retrieves the current status of orders associated with a specific customer ID from the database. This information serves as the raw material for generating answers to user inquiries.

[0237] The server generates the optimal response for the user based on the acquired data. This response is then formatted back into natural language and sent to the terminal. The terminal presents this response to the user on its user interface, either displaying it on the chat screen or outputting it as audio.

[0238] For example, if a user inquires about tracking an order, the system will check the delivery status based on the order number. The server will generate a response such as, "Order number 12345 is currently in transit and is expected to arrive tomorrow," and the user can confirm this information on their device's display screen or via audio output.

[0239] Furthermore, the user interface stores a log of the user's past inquiries, and this data is used to improve follow-up inquiries and provide personalized customer service. In this way, the system can continue to be refined and provide a more accurate service through continuous use.

[0240] The following describes the processing flow.

[0241] Step 1:

[0242] The user enters their inquiry via text or voice through the terminal. The terminal receives this input and, if necessary, converts the voice input to text.

[0243] Step 2:

[0244] The terminal sends the user's inquiry to the server. The server passes the received message to a natural language processing engine, which analyzes the user's intent and interests. Specifically, it breaks down the inquiry content and extracts its categories and keywords.

[0245] Step 3:

[0246] The server then refers to the database based on the analysis results and retrieves the necessary information. For example, if it's to check the order status, it retrieves the relevant order data from the database.

[0247] Step 4:

[0248] The server generates a response to the user based on the acquired data. The response is written in natural language and formatted in a way that is easy for the user to understand.

[0249] Step 5:

[0250] The server sends the generated response to the terminal. The terminal then displays this response on its screen or communicates it to the user via voice.

[0251] Step 6:

[0252] The user reviews the response and makes additional inquiries if necessary. The terminal sends this additional information back to the server and continues processing.

[0253] Step 7:

[0254] After processing is complete, the server records the query logs and response history, and uses this data to improve the service using machine learning algorithms.

[0255] (Example 1)

[0256] 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."

[0257] In today's world, responding quickly and accurately to user inquiries is crucial. However, conventional systems have struggled to accurately grasp user intent and automatically generate appropriate responses based on that intent. Furthermore, they have been insufficient in continuously improving response quality through the effective use of history. Moreover, there is a growing need to support diverse user input formats, including voice and text.

[0258] 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.

[0259] In this invention, the server includes means for analyzing queries and identifying intent using a natural language processing engine, means for acquiring relevant information from an information acquisition device, means for generating a response in natural language format based on the acquired information, means for converting user input into text using speech recognition software, and means for saving past query history and improving the quality of responses. This makes it possible to accurately grasp the user's intent and generate high-quality responses based on relevant information.

[0260] A "natural language processing engine" is a technology that allows computers to understand and analyze human language, and is used to identify the meaning and intent of text.

[0261] "User" refers to an individual or legal entity that makes an inquiry using the system.

[0262] An "inquiry" refers to a question or request for information that a user submits to the system.

[0263] "Analysis" refers to the process of processing received information and interpreting its content and meaning.

[0264] "Intention" refers to the information or purpose that the user making the inquiry is seeking.

[0265] An "information acquisition device" refers to a device or function used to acquire necessary information from a database or external data source.

[0266] "Response" refers to the answer or information provided by a system in response to a user's inquiry.

[0267] "Speech recognition software" refers to the technology and programs that convert speech input into text information.

[0268] "User interface" refers to the screen display and means of operation that allow users to interact with the system.

[0269] "Inquiry history" refers to a record of inquiries made by users in the past and the responses to those inquiries.

[0270] A "machine learning algorithm" refers to a computational method that learns a model based on data and automatically discovers patterns and rules.

[0271] This invention is an automated system for generating efficient and accurate responses to user inquiries. Specifically, it involves receiving text or voice input via a user interface, which is then analyzed by a server to generate an appropriate response.

[0272] The terminal is equipped with speech recognition software, which has the ability to convert voice input into text with high accuracy. For example, if a user voice-inputs "I want to know the status of my order," the speech recognition software converts this into text data. The converted text is then sent from the terminal to the server.

[0273] The server has a built-in natural language processing engine that analyzes the received text data. This analysis specifically identifies the user's intent and collects appropriate information based on that intent. Generative AI models are used for the analysis, such as BERT or GPT. As a result, the user's intent, "I want to know the status of my order," is identified in the form of "check order status."

[0274] When retrieving information, the server accesses relevant databases to collect the necessary information. This includes retrieving the current order status based on the customer ID and order number. Based on this information, the server generates a natural language response to the user. This response is then sent back to the terminal and either displayed on the user interface or presented via an audio output device.

[0275] For example, when a user tracks their order using the order number, the system can automatically retrieve shipping information and generate a response such as, "Order number 12345 is currently in transit and is expected to arrive tomorrow." The user can then confirm this information on their device screen or via voice.

[0276] An example of a prompt message would be, "A user has inquired about order tracking. Please generate an appropriate response," which would be input to the generation AI model. This prompt would then prepare the model to efficiently provide a response to the user.

[0277] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0278] Step 1:

[0279] The user enters their inquiry using the terminal in either voice or text format. In the case of voice input, the terminal's voice recognition software converts the voice into text. For example, the user might ask, "I want to know the status of my order." The entered voice is output as text data and sent to the next processing step.

[0280] Step 2:

[0281] The terminal sends the converted text data to the server. The communication protocol used here is HTTP or HTTPS. Specifically, it converts the request into a JSON format generated by the terminal and transfers the data to the server via a secure connection. The input is text data, and the output is the transmission to the server.

[0282] Step 3:

[0283] The server inputs the received text data into the generative AI model and analyzes it using a natural language processing engine. At this stage, the server uses the prompt text of the generative AI model to identify the user's intention. For example, from the input "I want to know the order status", it identifies the intention of "checking the order status" and performs advanced language analysis and context understanding. As a result, the data is converted into an intention.

[0284] Step 4:

[0285] Based on the identified intention, the server collects relevant information from the database through an information acquisition device. Specifically, the server uses the customer ID and order number to search for the current delivery status and extracts the necessary information. The input is a query based on the intention, and the output is information such as the order status obtained from the database.

[0286] Step 5:

[0287] Based on the information obtained, the server generates a response to the user in natural language form. This response constructs a sentence based on the data collected in the previous step. For example, it generates a response such as "Order number 12345 is currently in transit, and the expected arrival date is tomorrow". The input is the collected data, and the output is a response in natural language form.

[0288] Step 6:

[0289] The server sends the generated response to the terminal, which receives it. The terminal then either displays the received response on the user interface or outputs it as audio using a speech synthesizer. Specifically, it displays the response on the chat screen or plays it back through the speaker. The input is the generated response, and the output is either a display or audio output.

[0290] This series of processes allows users to quickly obtain accurate answers to their inquiries.

[0291] (Application Example 1)

[0292] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0293] E-commerce sites are required to respond quickly and accurately to a wide range of user inquiries, as well as to recommend products based on past purchase data. However, traditional systems have struggled to integrate and effectively implement these responses and recommendations. As a result, improvements in the user experience have been hindered, and the need for efficient customer service is increasing.

[0294] 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.

[0295] In this invention, the server includes means for analyzing user inquiries and identifying their intent using a natural language processing engine, means for acquiring relevant information from an information acquisition device, and means for generating a response in natural language format based on the acquired information. This enables rapid responses to user inquiries and effective product recommendations utilizing past purchase data.

[0296] A "natural language processing engine" is a software technology that analyzes text or voice input from a user to understand its meaning and intent.

[0297] An "information acquisition device" is a device or program used to extract necessary information from a database or similar source based on an analyzed intent.

[0298] A "user interface" is an interface that allows users to interact with a system, enabling input and output via text or voice.

[0299] A "machine learning algorithm" is an algorithm that uses past data to improve the accuracy of responses, and it improves the system based on experience.

[0300] "Purchase data" refers to the history of products a user has purchased so far, and it is an important indicator when making product recommendations.

[0301] "Product recommendation" is the process of suggesting highly relevant products based on the user's interests and purchase history.

[0302] The embodiment of this invention is based on a system that enables automated customer support on an e-commerce site. Primarily, three parties—a server, a terminal, and a user—each play their respective roles.

[0303] The server utilizes a natural language processing engine to analyze text or voice queries sent from the user via their device. During the analysis process, the server leverages the Google Cloud Natural Language API to understand the meaning of the input and identify the intent of the query. As a result, it uses Firebase Realtime Database as a database to retrieve relevant information and extracts the necessary data. This integration of analysis and data retrieval establishes a process for generating user-optimized responses in natural language.

[0304] Furthermore, the server provides a product recommendation function using machine learning algorithms. For this purpose, it is possible to recommend highly relevant products based on past purchase data using a model based on TensorFlow. This series of systems is constructed so that users can use it on smartphones and other terminals and can easily access it through an interface.

[0305] When the user asks "What are the latest recommended products?", the server analyzes the purchase history, selects appropriate products, and generates a response such as "Based on the recently purchased products, we recommend this new e-book". Examples of this prompt text include "Propose five books that are likely to be purchased next based on the data of the books purchased by the user."

[0306] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0307] Step 1:

[0308] The user uses the terminal to input an inquiry in text or voice. The input data is sent to the server via an interface operating on the terminal. The user's input (e.g., "What are the latest recommended products?") is sent to the system.

[0309] Step 2:

[0310] The server uses the Google Cloud Natural Language API to analyze the received text or voice data. Here, natural language processing is performed to identify the intention of the user's question. The input data is semantically analyzed, and the intention of the inquiry (e.g., "Request for product recommendation") is identified.

[0311] Step 3:

[0312] The server accesses the Firebase Realtime Database and retrieves relevant information based on the query intent. Purchase history data and other information are extracted, and the information necessary for product recommendations is collected.

[0313] Step 4:

[0314] Based on the collected information, the server runs a machine learning model using TensorFlow. It analyzes past purchase data and recommends highly relevant products. The input data is analyzed and a list of recommended products is generated (e.g., "Select the 5 best ebooks").

[0315] Step 5:

[0316] The generated recommendation results are formatted in natural language so that the user can understand them, and then sent from the server to the terminal. The generated text (e.g., "Based on your recent purchases, we recommend this new ebook.") is output.

[0317] Step 6:

[0318] The user's device displays the received response. The user can review the results and browse the recommended products or make a purchase decision. The generated recommendation text is displayed on the interface, prompting the user to take actual action.

[0319] 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.

[0320] This invention relates to a system that automates customer service through a user interface and has the ability to recognize user emotions. By combining natural language processing and emotion recognition functions, the system can provide more accurate and emotionally sensitive responses to user inquiries.

[0321] The user enters questions or problems in text or voice format using a terminal. The terminal receives this input and converts voice input to text as needed. The entered data is then sent to the server for further processing.

[0322] The server passes the received data to a natural language processing engine, which analyzes the user's intent. In this process, the query is understood based on the context of the words, and appropriate categories and keywords are extracted.

[0323] Next, the server uses an emotion engine to analyze the emotional nuances and states contained in the user's input. This analysis allows the server to understand the user's feelings, such as whether they are dissatisfied or in a state of urgency.

[0324] Based on the analysis results, the server retrieves necessary information from the database and adjusts the content and tone of its response according to the user's emotional state. As a result, a more appropriate and receptive response becomes possible.

[0325] For example, if a user complains that their order hasn't arrived, the server will first check the delivery status and then generate a response that includes an apology and a solution, such as, "We apologize for the inconvenience. Order ID 12345 is currently in transit and is expected to arrive tomorrow. We ask for your patience."

[0326] The generated response is sent back to the terminal, which then displays or audibly presents this response through the user interface. Furthermore, the user's interaction history and emotional data are recorded as logs and used as data to continuously improve the service using machine learning algorithms. By implementing the invention in this way, improved customer satisfaction and efficient service operation are achieved.

[0327] The following describes the processing flow.

[0328] Step 1:

[0329] The user enters their inquiry via text or voice through the terminal. If voice input is received, the terminal converts it to text and prepares to send the input to the server.

[0330] Step 2:

[0331] The terminal sends the user's query data to the server. The server analyzes the received data using a natural language processing engine to understand the intent of the query. Specifically, it analyzes the sentence structure and identifies the main content of the query.

[0332] Step 3:

[0333] The server uses an emotion engine to extract emotional information from the text entered by the user. For example, it determines the user's emotional state from keywords and context and evaluates it as positive, negative, or neutral.

[0334] Step 4:

[0335] Based on the analyzed intent and sentiment data, the server retrieves relevant information by referring to the database. For example, if a user asks a question related to an order, the server collects the status information for that order at this stage.

[0336] Step 5:

[0337] The server generates responses based on the user's emotional state. If the user expresses dissatisfaction, the response will be adjusted to use more polite and considerate language. A specific example of a response would be: "We apologize for the inconvenience. We are currently reviewing the status of your order."

[0338] Step 6:

[0339] The server sends the generated response to the terminal. The terminal then presents the received response to the user either by displaying it on the screen or by outputting it as speech using speech synthesis.

[0340] Step 7:

[0341] The user can review the provided response and inquire again if they have any further questions or feedback. The terminal receives new input and prepares to send it back to the server for further processing.

[0342] Step 8:

[0343] The server logs conversation history and sentiment data, and uses machine learning algorithms to continuously improve the accuracy of the model. This allows the system to periodically improve the quality of its responses to match user tendencies.

[0344] (Example 2)

[0345] 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".

[0346] Modern information processing systems are required to accurately understand the intent behind user inquiries and provide responses that are sensitive to their emotional needs. However, conventional systems have not been able to adequately achieve this, resulting in lower user satisfaction. Furthermore, there is a need for more effective technologies to improve response accuracy by learning from inquiry history.

[0347] 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.

[0348] In this invention, the server includes means for analyzing user inquiries and identifying their intent using natural language processing technology, means for obtaining relevant information from information sources, means for generating responses to the user in natural language format based on the obtained information, and means for analyzing the user's emotional nuances using sentiment analysis technology and adjusting the response accordingly. This makes it possible to provide highly accurate responses that take into account the user's intent and emotions.

[0349] "Natural language processing technology" refers to computational techniques that enable computers to understand, generate, and analyze human language.

[0350] "User" refers to an individual or organization that uses the system to make an inquiry.

[0351] "Intention" refers to the purpose or goal that the user is seeking through their inquiry.

[0352] "Information source" refers to the databases or storage media that the server accesses to retrieve relevant information.

[0353] "Natural language forms" refer to expressions using the linguistic forms that humans use on a daily basis.

[0354] A "user display device" refers to a device that includes an interface for displaying responses and information to the user.

[0355] "Emotional analysis technology" is a computational technique for analyzing the nuances of emotions from user input.

[0356] "Machine learning technology" refers to algorithms that allow computers to learn from past data and improve the accuracy of future predictions and responses.

[0357] "Inquiry history" refers to records of inquiries made by users in the past.

[0358] This invention provides a technology that utilizes a computer system to generate responses in natural language to user inquiries. The system consists of a terminal and a server, and automatically generates appropriate responses when the user inputs information in natural language.

[0359] A terminal is a device used by users to input inquiries. The terminal has a user interface that accepts text and voice input. In the case of voice input, the terminal uses speech recognition software (e.g., a speech recognition API) to convert the speech into text. The converted text data is then sent to a server for information processing.

[0360] The server analyzes the received text data and performs information processing to understand the user's intent and emotions. Using natural language processing techniques, the server analyzes the intent contained in the user's question and extracts relevant keywords and categories. Furthermore, using sentiment analysis techniques, it analyzes the emotional nuances contained in the inquiry and adjusts the response accordingly.

[0361] This analysis allows the server to retrieve relevant information from the database and generate a natural language response that takes into account the user's intent and feelings. For example, if a user inquires, "I'm having trouble because my order hasn't arrived," the server will check the delivery status and generate a response that includes an appropriate apology and solution. A specific example of such a response would be, "We apologize for the inconvenience. Order ID 12345 is currently in transit and is expected to arrive tomorrow. We ask for your patience."

[0362] The generated response is sent back to the terminal, which then presents this response to the user via the user interface. The user interaction history and sentiment data are logged on the server and used by machine learning algorithms to improve the service later.

[0363] The system provides information to the generating AI model using prompts such as: "The user has the following inquiry: 'I'm having trouble because my order hasn't arrived.' Generate an appropriate response to this inquiry, expressing it in language that takes the user's feelings into consideration."

[0364] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0365] Step 1:

[0366] The user uses the terminal to input their inquiry as text or voice. In the case of voice input, the terminal uses speech recognition software to convert the voice into text. This process prepares the user's natural language input as text data.

[0367] Step 2:

[0368] The device sends the text data converted by speech recognition or the original text input to the server. The text data becomes the input at this point.

[0369] Step 3:

[0370] The server passes the received text data to a natural language processing engine. The server uses this engine to analyze the user's intent from the text data and extract relevant categories and keywords. The analysis results are then output.

[0371] Step 4:

[0372] The server passes the analysis results to the sentiment analysis engine. The server uses this engine to understand the user's emotional nuances from the input data. For example, emotional information such as dissatisfaction or urgency is output.

[0373] Step 5:

[0374] The server retrieves relevant information from the database based on the analysis results of intentions and emotions. The server integrates the retrieved information with the analysis results and generates an appropriate response in natural language. The generated response becomes the output data.

[0375] Step 6:

[0376] The server sends the generated response to the terminal. The terminal presents the received response to the user via a display device or audio output. This allows the user to receive a response from the system.

[0377] Step 7:

[0378] The server logs user interaction history and sentiment data. This data is then used to apply machine learning and improve the accuracy of the service.

[0379] (Application Example 2)

[0380] 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."

[0381] Existing customer service systems often fail to adequately adjust responses to user inquiries based on the situation, leading to decreased user satisfaction. Furthermore, a lack of consideration for user emotions results in service quality not meeting expectations.

[0382] 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.

[0383] In this invention, the server includes means for analyzing user inquiries using a natural language processing engine and identifying the user's intent, means for acquiring relevant information from an information acquisition device based on the analyzed intent, and means for determining the user's emotions based on the analysis results and adjusting the response content according to the emotional state. This makes it possible to provide appropriate and individualized responses that take the user's emotions into consideration.

[0384] A "natural language processing engine" is software or a system that enables computers to understand and analyze human language.

[0385] "Users" refers to people who operate or use the system, including customers and end users.

[0386] "Inquiry" refers to the act of asking questions about information that a user wants to know or a problem they want to solve.

[0387] "Intention" refers to the purpose or request that the user hopes to achieve through their inquiry.

[0388] An "information acquisition device" is a device or system for storing necessary materials and data and providing information related to an inquiry.

[0389] A "response" refers to the answer or reply that a system generates based on a user's inquiry.

[0390] "Emotion" refers to a person's psychological state, including states such as joy and dissatisfaction.

[0391] A "user interface" is a means for a user and a computer system to communicate with each other, and includes screen display and audio output.

[0392] A "machine learning algorithm" is a method of computer programming that automatically learns by identifying patterns from data and improves performance.

[0393] To implement this invention, a series of systems for processing user inquiries is required. These systems primarily consist of terminals, servers, and databases.

[0394] The terminal is a device equipped with a user interface similar to a smartphone or smart glasses, and accepts user inquiries in the form of voice or text. Voice input is converted to text using speech recognition software on the terminal (e.g., Google Speech-to-Text API). The converted text information is then sent to the server.

[0395] The server uses a natural language processing engine (e.g., BERT model) to analyze the user's inquiry text and identify its intent. Then, it uses an emotion recognition engine (e.g., OpenAI Sentiment Analysis API) to determine the user's emotions and generate an appropriate response based on the context. For example, if the user expresses dissatisfaction with the delivery status, the server will provide a polite apology along with updated delivery information.

[0396] Based on the analysis results, relevant information is retrieved from the database, a response tailored to the user's emotions is constructed, and the response is generated in natural language. The generated response is sent to the device and presented to the user in text or audio format.

[0397] Furthermore, user interaction history and sentiment data are recorded in a database and used by machine learning algorithms to continuously improve the accuracy of the service. This allows the system to respond more accurately to the individual needs of users.

[0398] For example, when a user inquires that "the item I recently ordered has not yet arrived," the server uses a prompt message such as, "Please understand the user's intent, check the current delivery status of order ID 12345, and consider the best response to resolve the user's dissatisfaction." This prompt is then used to generate an appropriate response and resolve the user's complaint.

[0399] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0400] Step 1:

[0401] The terminal receives inquiries from the user in either voice or text format. In the case of voice inquiries, the terminal uses speech recognition software to convert the speech to text. The input in this process is the user's inquiry, and the output is text data.

[0402] Step 2:

[0403] The terminal sends the converted text data to the server. The transmitted data corresponds to the user's inquiry.

[0404] Step 3:

[0405] The server uses a natural language processing engine to analyze the received text data. The input is text data, and the output is an analysis result that includes the user's intent. This intent analysis determines the meaning and purpose of the inquiry.

[0406] Step 4:

[0407] The server uses an emotion recognition engine to determine the emotions contained in the user's input. This process generates emotion labels based on the analysis results, and the user's emotional state is obtained as output. For example, information such as whether the user is dissatisfied may be obtained.

[0408] Step 5:

[0409] The server retrieves relevant information from the database based on the analysis results and emotional state. The input is the user's intent and emotional state, and the output is data for the response. Specific information such as order status and product information is extracted here.

[0410] Step 6:

[0411] The server generates a response in natural language format based on the relevant information and emotional state it has acquired. For example, it might generate a response such as, "We apologize for the inconvenience. Order ID 12345 is currently being shipped and is expected to arrive tomorrow."

[0412] Step 7:

[0413] The server sends the generated response to the terminal, which then presents it to the user via text or audio through its user interface. The input here is the response data, and the output is the display or audio presentation to the user.

[0414] Step 8:

[0415] The server records user interaction history and sentiment data in a database, which is then used by machine learning algorithms to improve the accuracy of future responses. In this process, the content of the interaction is utilized as data for future accuracy improvements.

[0416] 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.

[0417] 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.

[0418] 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.

[0419] [Third Embodiment]

[0420] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0421] 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.

[0422] 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).

[0423] 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.

[0424] 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.

[0425] 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).

[0426] 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.

[0427] 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.

[0428] 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.

[0429] 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.

[0430] 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.

[0431] 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".

[0432] This invention relates to a system for efficiently automating customer service. The system includes a series of processes that receive inquiries from users via a user interface, analyze the content of those inquiries on a server, and generate appropriate responses.

[0433] Users input questions or problems via text or voice using their device. A dedicated chatbot or voice bot runs on the device, receiving the user's input in real time. The input data is then sent from the device to the server.

[0434] The server analyzes the received data using a natural language processing engine to accurately understand the user's intent. For example, if a user inquires, "I want to know the status of my order," the server identifies this intent as "checking the order status." This process uses machine learning algorithms and existing dictionary databases to enable highly accurate analysis.

[0435] Based on the analysis results, the server accesses the information acquisition device and collects relevant data. For example, it retrieves the current status of orders associated with a specific customer ID from the database. This information serves as the raw material for generating answers to user inquiries.

[0436] The server generates the optimal response for the user based on the acquired data. This response is then formatted back into natural language and sent to the terminal. The terminal presents this response to the user on its user interface, either displaying it on the chat screen or outputting it as audio.

[0437] For example, if a user inquires about tracking an order, the system will check the delivery status based on the order number. The server will generate a response such as, "Order number 12345 is currently in transit and is expected to arrive tomorrow," and the user can confirm this information on their device's display screen or via audio output.

[0438] Furthermore, the user interface stores a log of the user's past inquiries, and this data is used to improve follow-up inquiries and provide personalized customer service. In this way, the system can continue to be refined and provide a more accurate service through continuous use.

[0439] The following describes the processing flow.

[0440] Step 1:

[0441] The user enters their inquiry via text or voice through the terminal. The terminal receives this input and, if necessary, converts the voice input to text.

[0442] Step 2:

[0443] The terminal sends the user's inquiry to the server. The server passes the received message to a natural language processing engine, which analyzes the user's intent and interests. Specifically, it breaks down the inquiry content and extracts its categories and keywords.

[0444] Step 3:

[0445] The server then refers to the database based on the analysis results and retrieves the necessary information. For example, if it's to check the order status, it retrieves the relevant order data from the database.

[0446] Step 4:

[0447] The server generates a response to the user based on the acquired data. The response is written in natural language and formatted in a way that is easy for the user to understand.

[0448] Step 5:

[0449] The server sends the generated response to the terminal. The terminal then displays this response on its screen or communicates it to the user via voice.

[0450] Step 6:

[0451] The user reviews the response and makes additional inquiries if necessary. The terminal sends this additional information back to the server and continues processing.

[0452] Step 7:

[0453] After processing is complete, the server records the query logs and response history, and uses this data to improve the service using machine learning algorithms.

[0454] (Example 1)

[0455] 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."

[0456] In today's world, responding quickly and accurately to user inquiries is crucial. However, conventional systems have struggled to accurately grasp user intent and automatically generate appropriate responses based on that intent. Furthermore, they have been insufficient in continuously improving response quality through the effective use of history. Moreover, there is a growing need to support diverse user input formats, including voice and text.

[0457] 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.

[0458] In this invention, the server includes means for analyzing queries and identifying intent using a natural language processing engine, means for acquiring relevant information from an information acquisition device, means for generating a response in natural language format based on the acquired information, means for converting user input into text using speech recognition software, and means for saving past query history and improving the quality of responses. This makes it possible to accurately grasp the user's intent and generate high-quality responses based on relevant information.

[0459] A "natural language processing engine" is a technology that allows computers to understand and analyze human language, and is used to identify the meaning and intent of text.

[0460] "User" refers to an individual or legal entity that makes an inquiry using the system.

[0461] An "inquiry" refers to a question or request for information that a user submits to the system.

[0462] "Analysis" refers to the process of processing received information and interpreting its content and meaning.

[0463] "Intention" refers to the information or purpose that the user making the inquiry is seeking.

[0464] An "information acquisition device" refers to a device or function used to acquire necessary information from a database or external data source.

[0465] "Response" refers to the answer or information provided by a system in response to a user's inquiry.

[0466] "Speech recognition software" refers to the technology and programs that convert speech input into text information.

[0467] "User interface" refers to the screen display and means of operation that allow users to interact with the system.

[0468] "Inquiry history" refers to a record of inquiries made by users in the past and the responses to those inquiries.

[0469] A "machine learning algorithm" refers to a computational method that learns a model based on data and automatically discovers patterns and rules.

[0470] This invention is an automated system for generating efficient and accurate responses to user inquiries. Specifically, it involves receiving text or voice input via a user interface, which is then analyzed by a server to generate an appropriate response.

[0471] The terminal is equipped with speech recognition software, which has the ability to convert voice input into text with high accuracy. For example, if a user voice-inputs "I want to know the status of my order," the speech recognition software converts this into text data. The converted text is then sent from the terminal to the server.

[0472] The server has a built-in natural language processing engine that analyzes the received text data. This analysis specifically identifies the user's intent and collects appropriate information based on that intent. Generative AI models are used for the analysis, such as BERT or GPT. As a result, the user's intent, "I want to know the status of my order," is identified in the form of "check order status."

[0473] When retrieving information, the server accesses relevant databases to collect the necessary information. This includes retrieving the current order status based on the customer ID and order number. Based on this information, the server generates a natural language response to the user. This response is then sent back to the terminal and either displayed on the user interface or presented via an audio output device.

[0474] For example, when a user tracks their order using the order number, the system can automatically retrieve shipping information and generate a response such as, "Order number 12345 is currently in transit and is expected to arrive tomorrow." The user can then confirm this information on their device screen or via voice.

[0475] An example of a prompt message would be, "A user has inquired about order tracking. Please generate an appropriate response," which would be input to the generation AI model. This prompt would then prepare the model to efficiently provide a response to the user.

[0476] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0477] Step 1:

[0478] The user enters their inquiry using the terminal in either voice or text format. In the case of voice input, the terminal's voice recognition software converts the voice into text. For example, the user might ask, "I want to know the status of my order." The entered voice is output as text data and sent to the next processing step.

[0479] Step 2:

[0480] The terminal sends the converted text data to the server. The communication protocol used here is HTTP or HTTPS. Specifically, the terminal converts the data into a JSON formatted request and transfers the data to the server via a secure connection. The input is text data, and the output is sent to the server.

[0481] Step 3:

[0482] The server inputs the received text data into a generative AI model, which then analyzes it using a natural language processing engine. At this stage, the server uses the generative AI model's prompts to identify the user's intent. For example, it identifies the intent "I want to know the status of my order" as "check the order status" and performs advanced language analysis and contextual understanding. As a result, the data is transformed into an intent.

[0483] Step 4:

[0484] Based on the identified intent, the server collects relevant information from the database through an information retrieval device. Specifically, the server uses the customer ID and order number to search for the current delivery status and extract the necessary information. The input is an intent-based query, and the output is information such as order status retrieved from the database.

[0485] Step 5:

[0486] The server generates a response to the user in natural language format based on the acquired information. This response constructs sentences based on the data collected in the previous step. For example, it might generate a response such as, "Order number 12345 is currently being shipped and is expected to arrive tomorrow." The input is the collected data, and the output is a response in natural language format.

[0487] Step 6:

[0488] The server sends the generated response to the terminal, which receives it. The terminal then either displays the received response on the user interface or outputs it as audio using a speech synthesizer. Specifically, it displays the response on the chat screen or plays it back through the speaker. The input is the generated response, and the output is either a display or audio output.

[0489] This series of processes allows users to quickly obtain accurate answers to their inquiries.

[0490] (Application Example 1)

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

[0492] E-commerce sites are required to respond quickly and accurately to a wide range of user inquiries, as well as to recommend products based on past purchase data. However, traditional systems have struggled to integrate and effectively implement these responses and recommendations. As a result, improvements in the user experience have been hindered, and the need for efficient customer service is increasing.

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

[0494] In this invention, the server includes means for analyzing user inquiries and identifying their intent using a natural language processing engine, means for acquiring relevant information from an information acquisition device, and means for generating a response in natural language format based on the acquired information. This enables rapid responses to user inquiries and effective product recommendations utilizing past purchase data.

[0495] A "natural language processing engine" is a software technology that analyzes text or voice input from a user to understand its meaning and intent.

[0496] An "information acquisition device" is a device or program used to extract necessary information from a database or similar source based on an analyzed intent.

[0497] A "user interface" is an interface that allows users to interact with a system, enabling input and output via text or voice.

[0498] A "machine learning algorithm" is an algorithm that uses past data to improve the accuracy of responses, and it improves the system based on experience.

[0499] "Purchase data" refers to the history of products a user has purchased so far, and it is an important indicator when making product recommendations.

[0500] "Product recommendation" is the process of suggesting highly relevant products based on the user's interests and purchase history.

[0501] The embodiment of this invention is based on a system that enables automated customer support on an e-commerce site. Primarily, three parties—a server, a terminal, and a user—each play their respective roles.

[0502] The server utilizes a natural language processing engine to analyze text or voice queries sent from the user via their device. During the analysis process, the server leverages the Google Cloud Natural Language API to understand the meaning of the input and identify the intent of the query. As a result, it uses Firebase Realtime Database as a database to retrieve relevant information and extracts the necessary data. This integration of analysis and data retrieval establishes a process for generating user-optimized responses in natural language.

[0503] Furthermore, the server provides a product recommendation function using machine learning algorithms. For this purpose, a model using TensorFlow enables the recommendation of highly relevant products based on past purchase data. This entire system is designed to be accessible to users via smartphones and other devices, and is built to be easily accessible through an interface.

[0504] When a user asks, "What are the latest recommended products?", the server analyzes their purchase history, selects appropriate products, and generates a response such as, "Based on your recent purchases, we recommend this new ebook." An example of this prompt would be, "Based on the data of books the user has purchased, please suggest 5 books that they are likely to purchase next."

[0505] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0506] Step 1:

[0507] The user enters their inquiry via text or voice using a device. The entered data is sent to the server via an interface running on the device. The user's input (e.g., "What are the latest recommended products?") is sent to the system.

[0508] Step 2:

[0509] The server uses the Google Cloud Natural Language API to analyze the received text or audio data. Natural language processing is performed here to determine the intent of the user's question. The input data is semantically analyzed to identify the intent of the inquiry (e.g., "request for product recommendations").

[0510] Step 3:

[0511] The server accesses the Firebase Realtime Database and retrieves relevant information based on the query intent. Purchase history data and other information are extracted, and the information necessary for product recommendations is collected.

[0512] Step 4:

[0513] Based on the collected information, the server runs a machine learning model using TensorFlow. It analyzes past purchase data and recommends highly relevant products. The input data is analyzed and a list of recommended products is generated (e.g., "Select the 5 best ebooks").

[0514] Step 5:

[0515] The generated recommendation results are formatted in natural language so that the user can understand them, and then sent from the server to the terminal. The generated text (e.g., "Based on your recent purchases, we recommend this new ebook.") is output.

[0516] Step 6:

[0517] The user's device displays the received response. The user can review the results and browse the recommended products or make a purchase decision. The generated recommendation text is displayed on the interface, prompting the user to take actual action.

[0518] 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.

[0519] This invention relates to a system that automates customer service through a user interface and has the ability to recognize user emotions. By combining natural language processing and emotion recognition functions, the system can provide more accurate and emotionally sensitive responses to user inquiries.

[0520] The user enters questions or problems in text or voice format using a terminal. The terminal receives this input and converts voice input to text as needed. The entered data is then sent to the server for further processing.

[0521] The server passes the received data to a natural language processing engine, which analyzes the user's intent. In this process, the query is understood based on the context of the words, and appropriate categories and keywords are extracted.

[0522] Next, the server uses an emotion engine to analyze the emotional nuances and states contained in the user's input. This analysis allows the server to understand the user's feelings, such as whether they are dissatisfied or in a state of urgency.

[0523] Based on the analysis results, the server retrieves necessary information from the database and adjusts the content and tone of its response according to the user's emotional state. As a result, a more appropriate and receptive response becomes possible.

[0524] For example, if a user complains that their order hasn't arrived, the server will first check the delivery status and then generate a response that includes an apology and a solution, such as, "We apologize for the inconvenience. Order ID 12345 is currently in transit and is expected to arrive tomorrow. We ask for your patience."

[0525] The generated response is sent back to the terminal, which then displays or audibly presents this response through the user interface. Furthermore, the user's interaction history and emotional data are recorded as logs and used as data to continuously improve the service using machine learning algorithms. By implementing the invention in this way, improved customer satisfaction and efficient service operation are achieved.

[0526] The following describes the processing flow.

[0527] Step 1:

[0528] The user enters their inquiry via text or voice through the terminal. If voice input is received, the terminal converts it to text and prepares to send the input to the server.

[0529] Step 2:

[0530] The terminal sends the user's query data to the server. The server analyzes the received data using a natural language processing engine to understand the intent of the query. Specifically, it analyzes the sentence structure and identifies the main content of the query.

[0531] Step 3:

[0532] The server uses an emotion engine to extract emotional information from the text entered by the user. For example, it determines the user's emotional state from keywords and context and evaluates it as positive, negative, or neutral.

[0533] Step 4:

[0534] Based on the analyzed intent and sentiment data, the server retrieves relevant information by referring to the database. For example, if a user asks a question related to an order, the server collects the status information for that order at this stage.

[0535] Step 5:

[0536] The server generates responses based on the user's emotional state. If the user expresses dissatisfaction, the response will be adjusted to use more polite and considerate language. A specific example of a response would be: "We apologize for the inconvenience. We are currently reviewing the status of your order."

[0537] Step 6:

[0538] The server sends the generated response to the terminal. The terminal then presents the received response to the user either by displaying it on the screen or by outputting it as speech using speech synthesis.

[0539] Step 7:

[0540] The user can review the provided response and inquire again if they have any further questions or feedback. The terminal receives new input and prepares to send it back to the server for further processing.

[0541] Step 8:

[0542] The server logs conversation history and sentiment data, and uses machine learning algorithms to continuously improve the accuracy of the model. This allows the system to periodically improve the quality of its responses to match user tendencies.

[0543] (Example 2)

[0544] 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."

[0545] Modern information processing systems are required to accurately understand the intent behind user inquiries and provide responses that are sensitive to their emotional needs. However, conventional systems have not been able to adequately achieve this, resulting in lower user satisfaction. Furthermore, there is a need for more effective technologies to improve response accuracy by learning from inquiry history.

[0546] 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.

[0547] In this invention, the server includes means for analyzing user inquiries and identifying their intent using natural language processing technology, means for obtaining relevant information from information sources, means for generating responses to the user in natural language format based on the obtained information, and means for analyzing the user's emotional nuances using sentiment analysis technology and adjusting the response accordingly. This makes it possible to provide highly accurate responses that take into account the user's intent and emotions.

[0548] "Natural language processing technology" refers to computational techniques that enable computers to understand, generate, and analyze human language.

[0549] "User" refers to an individual or organization that uses the system to make an inquiry.

[0550] "Intention" refers to the purpose or goal that the user is seeking through their inquiry.

[0551] "Information source" refers to the databases or storage media that the server accesses to retrieve relevant information.

[0552] "Natural language forms" refer to expressions using the linguistic forms that humans use on a daily basis.

[0553] A "user display device" refers to a device that includes an interface for displaying responses and information to the user.

[0554] "Emotional analysis technology" is a computational technique for analyzing the nuances of emotions from user input.

[0555] "Machine learning technology" refers to algorithms that allow computers to learn from past data and improve the accuracy of future predictions and responses.

[0556] "Inquiry history" refers to records of inquiries made by users in the past.

[0557] This invention provides a technology that utilizes a computer system to generate responses in natural language to user inquiries. The system consists of a terminal and a server, and automatically generates appropriate responses when the user inputs information in natural language.

[0558] A terminal is a device used by users to input inquiries. The terminal has a user interface that accepts text and voice input. In the case of voice input, the terminal uses speech recognition software (e.g., a speech recognition API) to convert the speech into text. The converted text data is then sent to a server for information processing.

[0559] The server analyzes the received text data and performs information processing to understand the user's intent and emotions. Using natural language processing techniques, the server analyzes the intent contained in the user's question and extracts relevant keywords and categories. Furthermore, using sentiment analysis techniques, it analyzes the emotional nuances contained in the inquiry and adjusts the response accordingly.

[0560] This analysis allows the server to retrieve relevant information from the database and generate a natural language response that takes into account the user's intent and feelings. For example, if a user inquires, "I'm having trouble because my order hasn't arrived," the server will check the delivery status and generate a response that includes an appropriate apology and solution. A specific example of such a response would be, "We apologize for the inconvenience. Order ID 12345 is currently in transit and is expected to arrive tomorrow. We ask for your patience."

[0561] The generated response is sent back to the terminal, which then presents this response to the user via the user interface. The user interaction history and sentiment data are logged on the server and used by machine learning algorithms to improve the service later.

[0562] The system provides information to the generating AI model using prompts such as: "The user has the following inquiry: 'I'm having trouble because my order hasn't arrived.' Generate an appropriate response to this inquiry, expressing it in language that takes the user's feelings into consideration."

[0563] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0564] Step 1:

[0565] The user uses the terminal to input their inquiry as text or voice. In the case of voice input, the terminal uses speech recognition software to convert the voice into text. This process prepares the user's natural language input as text data.

[0566] Step 2:

[0567] The device sends the text data converted by speech recognition or the original text input to the server. The text data becomes the input at this point.

[0568] Step 3:

[0569] The server passes the received text data to a natural language processing engine. The server uses this engine to analyze the user's intent from the text data and extract relevant categories and keywords. The analysis results are then output.

[0570] Step 4:

[0571] The server passes the analysis results to the sentiment analysis engine. The server uses this engine to understand the user's emotional nuances from the input data. For example, emotional information such as dissatisfaction or urgency is output.

[0572] Step 5:

[0573] The server retrieves relevant information from the database based on the analysis results of intentions and emotions. The server integrates the retrieved information with the analysis results and generates an appropriate response in natural language. The generated response becomes the output data.

[0574] Step 6:

[0575] The server sends the generated response to the terminal. The terminal presents the received response to the user via a display device or audio output. This allows the user to receive a response from the system.

[0576] Step 7:

[0577] The server logs user interaction history and sentiment data. This data is then used to apply machine learning and improve the accuracy of the service.

[0578] (Application Example 2)

[0579] 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."

[0580] Existing customer service systems often fail to adequately adjust responses to user inquiries based on the situation, leading to decreased user satisfaction. Furthermore, a lack of consideration for user emotions results in service quality not meeting expectations.

[0581] 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.

[0582] In this invention, the server includes means for analyzing user inquiries using a natural language processing engine and identifying the user's intent, means for acquiring relevant information from an information acquisition device based on the analyzed intent, and means for determining the user's emotions based on the analysis results and adjusting the response content according to the emotional state. This makes it possible to provide appropriate and individualized responses that take the user's emotions into consideration.

[0583] A "natural language processing engine" is software or a system that enables computers to understand and analyze human language.

[0584] "Users" refers to people who operate or use the system, including customers and end users.

[0585] "Inquiry" refers to the act of asking questions about information that a user wants to know or a problem they want to solve.

[0586] "Intention" refers to the purpose or request that the user hopes to achieve through their inquiry.

[0587] An "information acquisition device" is a device or system for storing necessary materials and data and providing information related to an inquiry.

[0588] A "response" refers to the answer or reply that a system generates based on a user's inquiry.

[0589] "Emotion" refers to a person's psychological state, including states such as joy and dissatisfaction.

[0590] A "user interface" is a means for a user and a computer system to communicate with each other, and includes screen display and audio output.

[0591] A "machine learning algorithm" is a method of computer programming that automatically learns by identifying patterns from data and improves performance.

[0592] To implement this invention, a series of systems for processing user inquiries is required. These systems primarily consist of terminals, servers, and databases.

[0593] The terminal is a device equipped with a user interface similar to a smartphone or smart glasses, and accepts user inquiries in the form of voice or text. Voice input is converted to text using speech recognition software on the terminal (e.g., Google Speech-to-Text API). The converted text information is then sent to the server.

[0594] The server uses a natural language processing engine (e.g., BERT model) to analyze the user's inquiry text and identify its intent. Then, it uses an emotion recognition engine (e.g., OpenAI Sentiment Analysis API) to determine the user's emotions and generate an appropriate response based on the context. For example, if the user expresses dissatisfaction with the delivery status, the server will provide a polite apology along with updated delivery information.

[0595] Based on the analysis results, relevant information is retrieved from the database, a response tailored to the user's emotions is constructed, and the response is generated in natural language. The generated response is sent to the device and presented to the user in text or audio format.

[0596] Furthermore, user interaction history and sentiment data are recorded in a database and used by machine learning algorithms to continuously improve the accuracy of the service. This allows the system to respond more accurately to the individual needs of users.

[0597] For example, when a user inquires that "the item I recently ordered has not yet arrived," the server uses a prompt message such as, "Please understand the user's intent, check the current delivery status of order ID 12345, and consider the best response to resolve the user's dissatisfaction." This prompt is then used to generate an appropriate response and resolve the user's complaint.

[0598] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0599] Step 1:

[0600] The terminal receives inquiries from the user in either voice or text format. In the case of voice inquiries, the terminal uses speech recognition software to convert the speech to text. The input in this process is the user's inquiry, and the output is text data.

[0601] Step 2:

[0602] The terminal sends the converted text data to the server. The transmitted data corresponds to the user's inquiry.

[0603] Step 3:

[0604] The server uses a natural language processing engine to analyze the received text data. The input is text data, and the output is an analysis result that includes the user's intent. This intent analysis determines the meaning and purpose of the inquiry.

[0605] Step 4:

[0606] The server uses an emotion recognition engine to determine the emotions contained in the user's input. This process generates emotion labels based on the analysis results, and the user's emotional state is obtained as output. For example, information such as whether the user is dissatisfied may be obtained.

[0607] Step 5:

[0608] The server retrieves relevant information from the database based on the analysis results and emotional state. The input is the user's intent and emotional state, and the output is data for the response. Specific information such as order status and product information is extracted here.

[0609] Step 6:

[0610] The server generates a response in natural language format based on the relevant information and emotional state it has acquired. For example, it might generate a response such as, "We apologize for the inconvenience. Order ID 12345 is currently being shipped and is expected to arrive tomorrow."

[0611] Step 7:

[0612] The server sends the generated response to the terminal, which then presents it to the user via text or audio through its user interface. The input here is the response data, and the output is the display or audio presentation to the user.

[0613] Step 8:

[0614] The server records user interaction history and sentiment data in a database, which is then used by machine learning algorithms to improve the accuracy of future responses. In this process, the content of the interaction is utilized as data for future accuracy improvements.

[0615] 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.

[0616] 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.

[0617] 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.

[0618] [Fourth Embodiment]

[0619] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0620] 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.

[0621] 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).

[0622] 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.

[0623] 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.

[0624] 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).

[0625] 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.

[0626] 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.

[0627] 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.

[0628] 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.

[0629] 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.

[0630] 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.

[0631] 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".

[0632] This invention relates to a system for efficiently automating customer service. The system includes a series of processes that receive inquiries from users via a user interface, analyze the content of those inquiries on a server, and generate appropriate responses.

[0633] Users input questions or problems via text or voice using their device. A dedicated chatbot or voice bot runs on the device, receiving the user's input in real time. The input data is then sent from the device to the server.

[0634] The server analyzes the received data using a natural language processing engine to accurately understand the user's intent. For example, if a user inquires, "I want to know the status of my order," the server identifies this intent as "checking the order status." This process uses machine learning algorithms and existing dictionary databases to enable highly accurate analysis.

[0635] Based on the analysis results, the server accesses the information acquisition device and collects relevant data. For example, it retrieves the current status of orders associated with a specific customer ID from the database. This information serves as the raw material for generating answers to user inquiries.

[0636] The server generates the optimal response for the user based on the acquired data. This response is then formatted back into natural language and sent to the terminal. The terminal presents this response to the user on its user interface, either displaying it on the chat screen or outputting it as audio.

[0637] For example, if a user inquires about tracking an order, the system will check the delivery status based on the order number. The server will generate a response such as, "Order number 12345 is currently in transit and is expected to arrive tomorrow," and the user can confirm this information on their device's display screen or via audio output.

[0638] Furthermore, the user interface stores a log of the user's past inquiries, and this data is used to improve follow-up inquiries and provide personalized customer service. In this way, the system can continue to be refined and provide a more accurate service through continuous use.

[0639] The following describes the processing flow.

[0640] Step 1:

[0641] The user enters their inquiry via text or voice through the terminal. The terminal receives this input and, if necessary, converts the voice input to text.

[0642] Step 2:

[0643] The terminal sends the user's inquiry to the server. The server passes the received message to a natural language processing engine, which analyzes the user's intent and interests. Specifically, it breaks down the inquiry content and extracts its categories and keywords.

[0644] Step 3:

[0645] The server then refers to the database based on the analysis results and retrieves the necessary information. For example, if it's to check the order status, it retrieves the relevant order data from the database.

[0646] Step 4:

[0647] The server generates a response to the user based on the acquired data. The response is written in natural language and formatted in a way that is easy for the user to understand.

[0648] Step 5:

[0649] The server sends the generated response to the terminal. The terminal then displays this response on its screen or communicates it to the user via voice.

[0650] Step 6:

[0651] The user reviews the response and makes additional inquiries if necessary. The terminal sends this additional information back to the server and continues processing.

[0652] Step 7:

[0653] After processing is complete, the server records the query logs and response history, and uses this data to improve the service using machine learning algorithms.

[0654] (Example 1)

[0655] 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".

[0656] In today's world, responding quickly and accurately to user inquiries is crucial. However, conventional systems have struggled to accurately grasp user intent and automatically generate appropriate responses based on that intent. Furthermore, they have been insufficient in continuously improving response quality through the effective use of history. Moreover, there is a growing need to support diverse user input formats, including voice and text.

[0657] 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.

[0658] In this invention, the server includes means for analyzing queries and identifying intent using a natural language processing engine, means for acquiring relevant information from an information acquisition device, means for generating a response in natural language format based on the acquired information, means for converting user input into text using speech recognition software, and means for saving past query history and improving the quality of responses. This makes it possible to accurately grasp the user's intent and generate high-quality responses based on relevant information.

[0659] A "natural language processing engine" is a technology that allows computers to understand and analyze human language, and is used to identify the meaning and intent of text.

[0660] "User" refers to an individual or legal entity that makes an inquiry using the system.

[0661] An "inquiry" refers to a question or request for information that a user submits to the system.

[0662] "Analysis" refers to the process of processing received information and interpreting its content and meaning.

[0663] "Intention" refers to the information or purpose that the user making the inquiry is seeking.

[0664] An "information acquisition device" refers to a device or function used to acquire necessary information from a database or external data source.

[0665] "Response" refers to the answer or information provided by a system in response to a user's inquiry.

[0666] "Speech recognition software" refers to the technology and programs that convert speech input into text information.

[0667] "User interface" refers to the screen display and means of operation that allow users to interact with the system.

[0668] "Inquiry history" refers to a record of inquiries made by users in the past and the responses to those inquiries.

[0669] A "machine learning algorithm" refers to a computational method that learns a model based on data and automatically discovers patterns and rules.

[0670] This invention is an automated system for generating efficient and accurate responses to user inquiries. Specifically, it involves receiving text or voice input via a user interface, which is then analyzed by a server to generate an appropriate response.

[0671] The terminal is equipped with speech recognition software, which has the ability to convert voice input into text with high accuracy. For example, if a user voice-inputs "I want to know the status of my order," the speech recognition software converts this into text data. The converted text is then sent from the terminal to the server.

[0672] The server has a built-in natural language processing engine that analyzes the received text data. This analysis specifically identifies the user's intent and collects appropriate information based on that intent. Generative AI models are used for the analysis, such as BERT or GPT. As a result, the user's intent, "I want to know the status of my order," is identified in the form of "check order status."

[0673] When retrieving information, the server accesses relevant databases to collect the necessary information. This includes retrieving the current order status based on the customer ID and order number. Based on this information, the server generates a natural language response to the user. This response is then sent back to the terminal and either displayed on the user interface or presented via an audio output device.

[0674] For example, when a user tracks their order using the order number, the system can automatically retrieve shipping information and generate a response such as, "Order number 12345 is currently in transit and is expected to arrive tomorrow." The user can then confirm this information on their device screen or via voice.

[0675] An example of a prompt message would be, "A user has inquired about order tracking. Please generate an appropriate response," which would be input to the generation AI model. This prompt would then prepare the model to efficiently provide a response to the user.

[0676] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0677] Step 1:

[0678] The user enters their inquiry using the terminal in either voice or text format. In the case of voice input, the terminal's voice recognition software converts the voice into text. For example, the user might ask, "I want to know the status of my order." The entered voice is output as text data and sent to the next processing step.

[0679] Step 2:

[0680] The terminal sends the converted text data to the server. The communication protocol used here is HTTP or HTTPS. Specifically, the terminal converts the data into a JSON formatted request and transfers the data to the server via a secure connection. The input is text data, and the output is sent to the server.

[0681] Step 3:

[0682] The server inputs the received text data into a generative AI model, which then analyzes it using a natural language processing engine. At this stage, the server uses the generative AI model's prompts to identify the user's intent. For example, it identifies the intent "I want to know the status of my order" as "check the order status" and performs advanced language analysis and contextual understanding. As a result, the data is transformed into an intent.

[0683] Step 4:

[0684] Based on the identified intent, the server collects relevant information from the database through an information retrieval device. Specifically, the server uses the customer ID and order number to search for the current delivery status and extract the necessary information. The input is an intent-based query, and the output is information such as order status retrieved from the database.

[0685] Step 5:

[0686] The server generates a response to the user in natural language format based on the acquired information. This response constructs sentences based on the data collected in the previous step. For example, it might generate a response such as, "Order number 12345 is currently being shipped and is expected to arrive tomorrow." The input is the collected data, and the output is a response in natural language format.

[0687] Step 6:

[0688] The server sends the generated response to the terminal, which receives it. The terminal then either displays the received response on the user interface or outputs it as audio using a speech synthesizer. Specifically, it displays the response on the chat screen or plays it back through the speaker. The input is the generated response, and the output is either a display or audio output.

[0689] This series of processes allows users to quickly obtain accurate answers to their inquiries.

[0690] (Application Example 1)

[0691] 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".

[0692] E-commerce sites are required to respond quickly and accurately to a wide range of user inquiries, as well as to recommend products based on past purchase data. However, traditional systems have struggled to integrate and effectively implement these responses and recommendations. As a result, improvements in the user experience have been hindered, and the need for efficient customer service is increasing.

[0693] 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.

[0694] In this invention, the server includes means for analyzing user inquiries and identifying their intent using a natural language processing engine, means for acquiring relevant information from an information acquisition device, and means for generating a response in natural language format based on the acquired information. This enables rapid responses to user inquiries and effective product recommendations utilizing past purchase data.

[0695] A "natural language processing engine" is a software technology that analyzes text or voice input from a user to understand its meaning and intent.

[0696] An "information acquisition device" is a device or program used to extract necessary information from a database or similar source based on an analyzed intent.

[0697] A "user interface" is an interface that allows users to interact with a system, enabling input and output via text or voice.

[0698] A "machine learning algorithm" is an algorithm that uses past data to improve the accuracy of responses, and it improves the system based on experience.

[0699] "Purchase data" refers to the history of products a user has purchased so far, and it is an important indicator when making product recommendations.

[0700] "Product recommendation" is the process of suggesting highly relevant products based on the user's interests and purchase history.

[0701] The embodiment of this invention is based on a system that enables automated customer support on an e-commerce site. Primarily, three parties—a server, a terminal, and a user—each play their respective roles.

[0702] The server utilizes a natural language processing engine to analyze text or voice queries sent from the user via their device. During the analysis process, the server leverages the Google Cloud Natural Language API to understand the meaning of the input and identify the intent of the query. As a result, it uses Firebase Realtime Database as a database to retrieve relevant information and extracts the necessary data. This integration of analysis and data retrieval establishes a process for generating user-optimized responses in natural language.

[0703] Furthermore, the server provides a product recommendation function using machine learning algorithms. For this purpose, a model using TensorFlow enables the recommendation of highly relevant products based on past purchase data. This entire system is designed to be accessible to users via smartphones and other devices, and is built to be easily accessible through an interface.

[0704] When a user asks, "What are the latest recommended products?", the server analyzes their purchase history, selects appropriate products, and generates a response such as, "Based on your recent purchases, we recommend this new ebook." An example of this prompt would be, "Based on the data of books the user has purchased, please suggest 5 books that they are likely to purchase next."

[0705] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0706] Step 1:

[0707] The user enters their inquiry via text or voice using a device. The entered data is sent to the server via an interface running on the device. The user's input (e.g., "What are the latest recommended products?") is sent to the system.

[0708] Step 2:

[0709] The server uses the Google Cloud Natural Language API to analyze the received text or audio data. Natural language processing is performed here to determine the intent of the user's question. The input data is semantically analyzed to identify the intent of the inquiry (e.g., "request for product recommendations").

[0710] Step 3:

[0711] The server accesses the Firebase Realtime Database and retrieves relevant information based on the query intent. Purchase history data and other information are extracted, and the information necessary for product recommendations is collected.

[0712] Step 4:

[0713] Based on the collected information, the server runs a machine learning model using TensorFlow. It analyzes past purchase data and recommends highly relevant products. The input data is analyzed and a list of recommended products is generated (e.g., "Select the 5 best ebooks").

[0714] Step 5:

[0715] The generated recommendation results are formatted in natural language so that the user can understand them, and then sent from the server to the terminal. The generated text (e.g., "Based on your recent purchases, we recommend this new ebook.") is output.

[0716] Step 6:

[0717] The user's device displays the received response. The user can review the results and browse the recommended products or make a purchase decision. The generated recommendation text is displayed on the interface, prompting the user to take actual action.

[0718] 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.

[0719] This invention relates to a system that automates customer service through a user interface and has the ability to recognize user emotions. By combining natural language processing and emotion recognition functions, the system can provide more accurate and emotionally sensitive responses to user inquiries.

[0720] The user enters questions or problems in text or voice format using a terminal. The terminal receives this input and converts voice input to text as needed. The entered data is then sent to the server for further processing.

[0721] The server passes the received data to a natural language processing engine, which analyzes the user's intent. In this process, the query is understood based on the context of the words, and appropriate categories and keywords are extracted.

[0722] Next, the server uses an emotion engine to analyze the emotional nuances and states contained in the user's input. This analysis allows the server to understand the user's feelings, such as whether they are dissatisfied or in a state of urgency.

[0723] Based on the analysis results, the server retrieves necessary information from the database and adjusts the content and tone of its response according to the user's emotional state. As a result, a more appropriate and receptive response becomes possible.

[0724] For example, if a user complains that their order hasn't arrived, the server will first check the delivery status and then generate a response that includes an apology and a solution, such as, "We apologize for the inconvenience. Order ID 12345 is currently in transit and is expected to arrive tomorrow. We ask for your patience."

[0725] The generated response is sent back to the terminal, which then displays or audibly presents this response through the user interface. Furthermore, the user's interaction history and emotional data are recorded as logs and used as data to continuously improve the service using machine learning algorithms. By implementing the invention in this way, improved customer satisfaction and efficient service operation are achieved.

[0726] The following describes the processing flow.

[0727] Step 1:

[0728] The user enters their inquiry via text or voice through the terminal. If voice input is received, the terminal converts it to text and prepares to send the input to the server.

[0729] Step 2:

[0730] The terminal sends the user's query data to the server. The server analyzes the received data using a natural language processing engine to understand the intent of the query. Specifically, it analyzes the sentence structure and identifies the main content of the query.

[0731] Step 3:

[0732] The server uses an emotion engine to extract emotional information from the text entered by the user. For example, it determines the user's emotional state from keywords and context and evaluates it as positive, negative, or neutral.

[0733] Step 4:

[0734] Based on the analyzed intent and sentiment data, the server retrieves relevant information by referring to the database. For example, if a user asks a question related to an order, the server collects the status information for that order at this stage.

[0735] Step 5:

[0736] The server generates responses based on the user's emotional state. If the user expresses dissatisfaction, the response will be adjusted to use more polite and considerate language. A specific example of a response would be: "We apologize for the inconvenience. We are currently reviewing the status of your order."

[0737] Step 6:

[0738] The server sends the generated response to the terminal. The terminal then presents the received response to the user either by displaying it on the screen or by outputting it as speech using speech synthesis.

[0739] Step 7:

[0740] The user can review the provided response and inquire again if they have any further questions or feedback. The terminal receives new input and prepares to send it back to the server for further processing.

[0741] Step 8:

[0742] The server logs conversation history and sentiment data, and uses machine learning algorithms to continuously improve the accuracy of the model. This allows the system to periodically improve the quality of its responses to match user tendencies.

[0743] (Example 2)

[0744] 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".

[0745] Modern information processing systems are required to accurately understand the intent behind user inquiries and provide responses that are sensitive to their emotional needs. However, conventional systems have not been able to adequately achieve this, resulting in lower user satisfaction. Furthermore, there is a need for more effective technologies to improve response accuracy by learning from inquiry history.

[0746] 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.

[0747] In this invention, the server includes means for analyzing user inquiries and identifying their intent using natural language processing technology, means for obtaining relevant information from information sources, means for generating responses to the user in natural language format based on the obtained information, and means for analyzing the user's emotional nuances using sentiment analysis technology and adjusting the response accordingly. This makes it possible to provide highly accurate responses that take into account the user's intent and emotions.

[0748] "Natural language processing technology" refers to computational techniques that enable computers to understand, generate, and analyze human language.

[0749] "User" refers to an individual or organization that uses the system to make an inquiry.

[0750] "Intention" refers to the purpose or goal that the user is seeking through their inquiry.

[0751] "Information source" refers to the databases or storage media that the server accesses to retrieve relevant information.

[0752] "Natural language forms" refer to expressions using the linguistic forms that humans use on a daily basis.

[0753] A "user display device" refers to a device that includes an interface for displaying responses and information to the user.

[0754] "Emotional analysis technology" is a computational technique for analyzing the nuances of emotions from user input.

[0755] "Machine learning technology" refers to algorithms that allow computers to learn from past data and improve the accuracy of future predictions and responses.

[0756] "Inquiry history" refers to records of inquiries made by users in the past.

[0757] This invention provides a technology that utilizes a computer system to generate responses in natural language to user inquiries. The system consists of a terminal and a server, and automatically generates appropriate responses when the user inputs information in natural language.

[0758] A terminal is a device used by users to input inquiries. The terminal has a user interface that accepts text and voice input. In the case of voice input, the terminal uses speech recognition software (e.g., a speech recognition API) to convert the speech into text. The converted text data is then sent to a server for information processing.

[0759] The server analyzes the received text data and performs information processing to understand the user's intent and emotions. Using natural language processing techniques, the server analyzes the intent contained in the user's question and extracts relevant keywords and categories. Furthermore, using sentiment analysis techniques, it analyzes the emotional nuances contained in the inquiry and adjusts the response accordingly.

[0760] This analysis allows the server to retrieve relevant information from the database and generate a natural language response that takes into account the user's intent and feelings. For example, if a user inquires, "I'm having trouble because my order hasn't arrived," the server will check the delivery status and generate a response that includes an appropriate apology and solution. A specific example of such a response would be, "We apologize for the inconvenience. Order ID 12345 is currently in transit and is expected to arrive tomorrow. We ask for your patience."

[0761] The generated response is sent back to the terminal, which then presents this response to the user via the user interface. The user interaction history and sentiment data are logged on the server and used by machine learning algorithms to improve the service later.

[0762] The system provides information to the generating AI model using prompts such as: "The user has the following inquiry: 'I'm having trouble because my order hasn't arrived.' Generate an appropriate response to this inquiry, expressing it in language that takes the user's feelings into consideration."

[0763] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0764] Step 1:

[0765] The user uses the terminal to input their inquiry as text or voice. In the case of voice input, the terminal uses speech recognition software to convert the voice into text. This process prepares the user's natural language input as text data.

[0766] Step 2:

[0767] The device sends the text data converted by speech recognition or the original text input to the server. The text data becomes the input at this point.

[0768] Step 3:

[0769] The server passes the received text data to a natural language processing engine. The server uses this engine to analyze the user's intent from the text data and extract relevant categories and keywords. The analysis results are then output.

[0770] Step 4:

[0771] The server passes the analysis results to the sentiment analysis engine. The server uses this engine to understand the user's emotional nuances from the input data. For example, emotional information such as dissatisfaction or urgency is output.

[0772] Step 5:

[0773] The server retrieves relevant information from the database based on the analysis results of intentions and emotions. The server integrates the retrieved information with the analysis results and generates an appropriate response in natural language. The generated response becomes the output data.

[0774] Step 6:

[0775] The server sends the generated response to the terminal. The terminal presents the received response to the user via a display device or audio output. This allows the user to receive a response from the system.

[0776] Step 7:

[0777] The server logs user interaction history and sentiment data. This data is then used to apply machine learning and improve the accuracy of the service.

[0778] (Application Example 2)

[0779] 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".

[0780] Existing customer service systems often fail to adequately adjust responses to user inquiries based on the situation, leading to decreased user satisfaction. Furthermore, a lack of consideration for user emotions results in service quality not meeting expectations.

[0781] 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.

[0782] In this invention, the server includes means for analyzing user inquiries using a natural language processing engine and identifying the user's intent, means for acquiring relevant information from an information acquisition device based on the analyzed intent, and means for determining the user's emotions based on the analysis results and adjusting the response content according to the emotional state. This makes it possible to provide appropriate and individualized responses that take the user's emotions into consideration.

[0783] A "natural language processing engine" is software or a system that enables computers to understand and analyze human language.

[0784] "Users" refers to people who operate or use the system, including customers and end users.

[0785] "Inquiry" refers to the act of asking questions about information that a user wants to know or a problem they want to solve.

[0786] "Intention" refers to the purpose or request that the user hopes to achieve through their inquiry.

[0787] An "information acquisition device" is a device or system for storing necessary materials and data and providing information related to an inquiry.

[0788] A "response" refers to the answer or reply that a system generates based on a user's inquiry.

[0789] "Emotion" refers to a person's psychological state, including states such as joy and dissatisfaction.

[0790] A "user interface" is a means for a user and a computer system to communicate with each other, and includes screen display and audio output.

[0791] A "machine learning algorithm" is a method of computer programming that automatically learns by identifying patterns from data and improves performance.

[0792] To implement this invention, a series of systems for processing user inquiries is required. These systems primarily consist of terminals, servers, and databases.

[0793] The terminal is a device equipped with a user interface similar to a smartphone or smart glasses, and accepts user inquiries in the form of voice or text. Voice input is converted to text using speech recognition software on the terminal (e.g., Google Speech-to-Text API). The converted text information is then sent to the server.

[0794] The server uses a natural language processing engine (e.g., BERT model) to analyze the user's inquiry text and identify its intent. Then, it uses an emotion recognition engine (e.g., OpenAI Sentiment Analysis API) to determine the user's emotions and generate an appropriate response based on the context. For example, if the user expresses dissatisfaction with the delivery status, the server will provide a polite apology along with updated delivery information.

[0795] Based on the analysis results, relevant information is retrieved from the database, a response tailored to the user's emotions is constructed, and the response is generated in natural language. The generated response is sent to the device and presented to the user in text or audio format.

[0796] Furthermore, user interaction history and sentiment data are recorded in a database and used by machine learning algorithms to continuously improve the accuracy of the service. This allows the system to respond more accurately to the individual needs of users.

[0797] For example, when a user inquires that "the item I recently ordered has not yet arrived," the server uses a prompt message such as, "Please understand the user's intent, check the current delivery status of order ID 12345, and consider the best response to resolve the user's dissatisfaction." This prompt is then used to generate an appropriate response and resolve the user's complaint.

[0798] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0799] Step 1:

[0800] The terminal receives inquiries from the user in either voice or text format. In the case of voice inquiries, the terminal uses speech recognition software to convert the speech to text. The input in this process is the user's inquiry, and the output is text data.

[0801] Step 2:

[0802] The terminal sends the converted text data to the server. The transmitted data corresponds to the user's inquiry.

[0803] Step 3:

[0804] The server uses a natural language processing engine to analyze the received text data. The input is text data, and the output is an analysis result that includes the user's intent. This intent analysis determines the meaning and purpose of the inquiry.

[0805] Step 4:

[0806] The server uses an emotion recognition engine to determine the emotions contained in the user's input. This process generates emotion labels based on the analysis results, and the user's emotional state is obtained as output. For example, information such as whether the user is dissatisfied may be obtained.

[0807] Step 5:

[0808] The server retrieves relevant information from the database based on the analysis results and emotional state. The input is the user's intent and emotional state, and the output is data for the response. Specific information such as order status and product information is extracted here.

[0809] Step 6:

[0810] The server generates a response in natural language format based on the relevant information and emotional state it has acquired. For example, it might generate a response such as, "We apologize for the inconvenience. Order ID 12345 is currently being shipped and is expected to arrive tomorrow."

[0811] Step 7:

[0812] The server sends the generated response to the terminal, which then presents it to the user via text or audio through its user interface. The input here is the response data, and the output is the display or audio presentation to the user.

[0813] Step 8:

[0814] The server records user interaction history and sentiment data in a database, which is then used by machine learning algorithms to improve the accuracy of future responses. In this process, the content of the interaction is utilized as data for future accuracy improvements.

[0815] 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.

[0816] 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.

[0817] 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.

[0818] 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.

[0819] 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.

[0820] 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.

[0821] 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.

[0822] 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.

[0823] 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."

[0824] 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.

[0825] 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.

[0826] 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.

[0827] 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.

[0828] 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.

[0829] 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.

[0830] 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.

[0831] 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.

[0832] 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.

[0833] 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.

[0834] 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.

[0835] 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.

[0836] The following is further disclosed regarding the embodiments described above.

[0837] (Claim 1)

[0838] A means of analyzing user inquiries using a natural language processing engine and identifying the intent behind those inquiries,

[0839] A means for acquiring relevant information from an information acquisition device based on the analyzed intent,

[0840] A means of generating a response to the user in natural language format based on the acquired information,

[0841] A means for sending and presenting the generated response to the user interface,

[0842] A system that includes this.

[0843] (Claim 2)

[0844] The system according to claim 1, comprising means for recording the user's inquiry history and improving the accuracy of responses using a machine learning algorithm.

[0845] (Claim 3)

[0846] The system according to claim 1, comprising an interface means for receiving user input in the form of text or voice through a user interface.

[0847] "Example 1"

[0848] (Claim 1)

[0849] A device that uses a natural language processing engine to analyze user inquiries and identify the intent behind those inquiries,

[0850] Based on the analyzed intent, a device acquires relevant information from an information acquisition device,

[0851] A device that generates a response to the user in natural language format based on acquired information,

[0852] A device that transmits and presents the generated response to the user interface,

[0853] A device that converts user input into text using speech recognition software,

[0854] A device that presents responses via a user interface, either by voice or on a display screen,

[0855] A device that saves past inquiry history and improves the quality of responses in response to future inquiries,

[0856] A system that includes this.

[0857] (Claim 2)

[0858] The system according to claim 1, comprising a device that records the user's inquiry history and improves the accuracy of responses using a machine learning algorithm.

[0859] (Claim 3)

[0860] The system according to claim 1, comprising a device that accepts user input using text or voice through a user interface.

[0861] "Application Example 1"

[0862] (Claim 1)

[0863] A means of analyzing user inquiries using a natural language processing engine and identifying the intent behind those inquiries,

[0864] A means for acquiring relevant information from an information acquisition device based on the analyzed intent,

[0865] A means of generating a response to the user in natural language format based on the acquired information,

[0866] A means for transmitting and presenting the generated response to the user interface,

[0867] A method for recommending products based on past purchase data,

[0868] A system that includes this.

[0869] (Claim 2)

[0870] The system according to claim 1, comprising means for recording the user's inquiry history and improving the accuracy of responses using a machine learning algorithm.

[0871] (Claim 3)

[0872] The system according to claim 1, comprising a interface means for receiving user input in the form of text or voice through a user interface.

[0873] "Example 2 of combining an emotion engine"

[0874] (Claim 1)

[0875] A means of analyzing user inquiries and identifying their intent using natural language processing technology,

[0876] Based on the analyzed intent, means of obtaining relevant information from the information source,

[0877] A means of generating a response to the user in natural language format based on the acquired information,

[0878] A means for transmitting and displaying the generated response on a user display device,

[0879] A means of analyzing the emotional nuances of a user using emotion analysis technology and adjusting the response accordingly,

[0880] A system that includes this.

[0881] (Claim 2)

[0882] The system according to claim 1, comprising means for recording the user's inquiry history and improving the accuracy of responses using machine learning technology.

[0883] (Claim 3)

[0884] The system according to claim 1, comprising means for receiving user input in text or voice format through a user display device.

[0885] "Application example 2 when combining with an emotional engine"

[0886] (Claim 1)

[0887] A means of analyzing user inquiries using a natural language processing engine and identifying the intent behind those inquiries,

[0888] A means for acquiring relevant information from an information acquisition device based on the analyzed intent,

[0889] A means of generating a response to the user in natural language format based on the acquired information,

[0890] A means to determine the user's emotions based on the analysis results and adjust the response content according to the emotional state,

[0891] A means for sending and presenting the generated response to the user interface,

[0892] A system that includes this.

[0893] (Claim 2)

[0894] The system according to claim 1, comprising means for recording user inquiry history and sentiment data, and for improving response accuracy and sentiment consideration capabilities using machine learning algorithms.

[0895] (Claim 3)

[0896] The system according to claim 1, comprising an interface means for receiving user input using text information or voice through a user interface. [Explanation of Symbols]

[0897] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of analyzing user inquiries using a natural language processing engine and identifying the intent behind those inquiries, A means for acquiring relevant information from an information acquisition device based on the analyzed intent, A means of generating a response to the user in natural language format based on the acquired information, A means for transmitting and presenting the generated response to the user interface, A method for recommending products based on past purchase data, A system that includes this.

2. The system according to claim 1, further comprising means for recording the user's inquiry history and improving the accuracy of responses using a machine learning algorithm.

3. The system according to claim 1, comprising interface means for receiving user input in the form of text or voice through a user interface.

Images