system

Abstract

Provide a system. A means for receiving an inquiry from a user; a server having a generative model for analyzing received queries; means for the server to generate a response using the generative model and present the response to the user; A system including:

Description

[Technical Field]

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

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

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

[0004] Hotels and commercial facilities require a lot of time and manpower to handle large volumes of inquiries and provide information. Customer satisfaction, particularly due to waiting times and congestion, declines, resulting in fewer repeat customers and poor word-of-mouth reviews. Human error and variations in response quality also contribute to lower customer satisfaction, making it difficult to allocate staff to handle inquiries on holidays, at night, and during emergencies. A new customer support system is needed to solve these issues and improve customer satisfaction. [Means for solving the problem]

[0005] We provide a system that includes a means for receiving inquiries from users, a server having a generative model for analyzing the received inquiry content, and a means for presenting the response generated by the server using the generative model to the user. This system operates 24 hours a day, enabling quick and consistent responses to user inquiries. Furthermore, by using a terminal that sends the inquiry content to the server and displays the resulting response to the user, human error is reduced. Furthermore, the generative model uses natural language processing to analyze the inquiry content and generate an appropriate response. This system has a means for maintaining context based on the inquiry content and a means for retrieving information from an FAQ database, making it possible to always provide optimal responses and improve customer satisfaction.

[0006] "User" refers to a customer or user who makes an inquiry to a hotel or commercial facility.

[0007] "Inquiry" refers to a question or request made by a User to Customer Support.

[0008] A "terminal" refers to a device, such as a smartphone or computer, through which a user inputs a query and receives a response.

[0009] "Server" refers to a central computer system that receives queries from users and uses generative models to generate appropriate responses.

[0010] A "generative model" refers to an artificial intelligence model that uses natural language processing to analyze query content and generate a response.

[0011] "Context" refers to the context or background information needed to properly analyze the content of a query.

[0012] An "FAQ database" is a database that contains frequently asked questions and their answers.

[0013] "24-hour system" refers to an operational system in which the system operates continuously without interruption throughout the day. [Brief explanation of the drawings]

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

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

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

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

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

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

[0020] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0022] [First embodiment]

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

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

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

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

[0027] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

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

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

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

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

[0035] This invention describes a customer support system that uses generative models to receive inquiries from users, analyze the inquiries, and generate and present appropriate responses.

[0036] First, we will describe the terminal in this system. Users use the terminal to access the customer support page and enter their questions or requests. The terminal provides an interface to receive the user's inquiry and send it to the server for analysis and response generation. This interface may be implemented as a web form or a dedicated application.

[0037] Next, we will explain the server. The server receives the inquiry content sent by the user and analyzes that content using a generative model. Specifically, the server uses natural language processing to properly understand the user's inquiry content and generate an optimal response based on that understanding. For example, a generative AI model is used as this generative model. This generative model is trained using a pre-learned dataset and is capable of generating appropriate responses with high accuracy.

[0038] The server sends the generated response to the terminal. The terminal provides a means for presenting the response received from the server to the user. For example, the response can be displayed on a screen or read aloud. This allows users to receive real-time support 24 hours a day, 365 days a year.

[0039] Next, we will explain the operation of this system using a concrete example. When a user makes an inquiry such as "I would like to change my check-in time," the terminal receives this inquiry and sends it to the server. The server uses a generative model to analyze the inquiry and generate a response such as "To change your check-in time, please access this link." The server then sends the generated response to the terminal, which displays it to the user. In this way, the user can receive a prompt and accurate response.

[0040] The system has the ability to maintain context based on the inquiry content and retrieve necessary information from an FAQ database. The system also operates 24 hours a day, ensuring availability at all times and reducing human error. This results in improved customer satisfaction and more efficient customer support operations.

[0041] The above is a description of the mode for carrying out the invention. The present system is useful in that it has a wide range of applicability and can respond to a variety of inquiries.

[0042] The processing flow will be explained below.

[0043] Step 1:

[0044] The terminal displays a customer support page and provides a form for the user to enter their inquiry. The user enters their inquiry into the form and clicks the submit button.

[0045] Step 2:

[0046] The device receives the query entered by the user, packages it as JSON-formatted data for processing, and then sends the data to the server as an HTTP POST request.

[0047] Step 3:

[0048] The server receives an HTTP POST request sent from the device, extracts the query content from the request, and passes it to the generative model for analysis.

[0049] Step 4:

[0050] A generative model on the server analyzes the query and generates an appropriate response. This generative model is pre-trained with a large amount of data, enabling highly accurate natural language processing.

[0051] Step 5:

[0052] The server receives the response generated by the generative model, packages it again as JSON-formatted data, and sends this response data to the terminal as an HTTP response.

[0053] Step 6:

[0054] The terminal analyzes the HTTP response received from the server, extracts the response content, and provides an interface for displaying the extracted response content to the user.

[0055] Step 7:

[0056] The terminal displays the response to the user, who can then confirm the response, completing the response to the user's inquiry.

[0057] Example 1

[0058] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0059] Conventional customer support systems often had slow responses to inquiries, which led to lower user satisfaction. Furthermore, they often relied on human intervention, making it difficult to provide 24-hour support. Furthermore, it was difficult to generate appropriate responses to inquiries, which sometimes led to inefficient support.

[0060] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0061] In this invention, the server includes a means for receiving inquiries from users, a means having a generative model using natural language processing technology for analyzing the content of the received inquiry, and a terminal for generating a response using the generative model and presenting the response to the user. This enables the generation of quick and appropriate responses to inquiries, realizing efficient customer support around the clock.

[0062] A "user" is a person or organization that uses the system to make an inquiry.

[0063] An "inquiry" is information about a question or request that a user enters through the system.

[0064] A "terminal" is an electronic device used by a user to enter inquiries and receive responses, and includes personal computers, smartphones, tablets, and the like.

[0065] The "server" is a central processing unit that receives the contents of an inquiry sent by a user, analyzes it, generates a response, and sends it to the terminal.

[0066] "Natural language processing technology" is a technology for converting the content of inquiries entered by users into a format that is easy for machines to understand and analyzing it.

[0067] A "generative model" is an algorithm that uses a pre-trained dataset to generate appropriate responses to user queries.

[0068] A "response" is information or instructions that the server generates in response to a user's query using a generative model and that are presented to the user via the terminal.

[0069] "24-hour system" means that the system operates continuously 24 hours a day, seven days a week, and is able to respond to user inquiries at any time.

[0070] This invention describes a customer support system that uses a generative AI model to receive inquiries from users, analyze the inquiries, and generate and present appropriate responses.

[0071] First, we will explain the terminals in this system. Users use the terminals to access the customer support page and enter their questions or requests. The terminals provide an interface for receiving the user's inquiries and sending them to the server for analysis and response generation. This interface may be implemented as a web form or a dedicated application. For example, this could be a form on a web browser or a smartphone application.

[0072] Next, we will explain the server. The server receives the inquiry content sent by the user and analyzes that content using a generative AI model. Specifically, the server uses natural language processing technology to properly understand the user's inquiry content and generate an optimal response based on that understanding. For example, a natural language generation AI model is used as this generative model. This model is trained using a large pre-learned dataset, and is capable of generating appropriate responses with high accuracy.

[0073] The server sends the generated response to the terminal. The terminal provides a means for presenting the response received from the server to the user. For example, the response can be displayed on a screen or read aloud. This allows users to receive real-time support 24 hours a day, 365 days a year.

[0074] Next, we will explain the operation of this system using a concrete example. When a user makes an inquiry such as "I would like to change my check-in time," the terminal receives this inquiry and sends it to the server. The server uses a generative model to analyze the inquiry and generate a response such as "To change your check-in time, please access this link." The server then sends the generated response to the terminal, which displays it to the user. In this way, the user can receive a prompt and accurate response.

[0075] For example, you might send the following prompt to a generative AI model:

[0076] "The user has asked, 'I would like to change the check-in time.' Please generate an appropriate response."

[0077] The system has the ability to maintain context based on the inquiry content and retrieve necessary information from an FAQ database. The system also operates 24 hours a day, ensuring availability at all times and reducing human error. This results in improved customer satisfaction and more efficient customer support operations.

[0078] The above is an embodiment of the present invention. The system has wide applicability and can respond to a variety of inquiries.

[0079] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0080] Step 1:

[0081] User input of query

[0082] A user accesses the customer support page using a terminal and enters their question or request. Specifically, the user enters "I would like to change my check-in time" in the text box. This entered data is treated as an inquiry to be used in the next step.

[0083] Step 2:

[0084] Sending inquiries via the device

[0085] The terminal receives the inquiry entered by the user and sends that data to the server. Specifically, the terminal sends the data "I would like to change the check-in time" to the server. At this time, a highly reliable communication method (e.g. HTTPS) is used. The user's inquiry is the input, and the data sent to the server is the output.

[0086] Step 3:

[0087] Receipt and analysis of query content by the server

[0088] The server receives the inquiry sent from the device. The server receives the inquiry "I would like to change the check-in time" and analyzes it using natural language processing technology. Specifically, the generative AI model receives a prompt sentence, "The user has inquired, 'I would like to change the check-in time.' Please generate an appropriate response.", and an appropriate response is generated. In this step, the inquiry is received as input, and the response from the generative AI model is obtained as output.

[0089] Step 4:

[0090] Server response generation

[0091] The server uses the generative AI model to generate an appropriate response to the query. For example, the generative AI model might generate a response like, "To change your check-in time, please visit this link." The input in this step is the prompt for the generative AI model, and the output is the generated response.

[0092] Step 5:

[0093] Server sends response

[0094] The server sends the generated response to the terminal. Specifically, it sends the generated response "To change your check-in time, please visit this link." to the terminal. The input in this step is the generated response, and the output is the data sent to the terminal.

[0095] Step 6:

[0096] Terminal display of responses

[0097] The terminal presents the response received from the server to the user. Specifically, it displays the text "To change your check-in time, please follow this link." on the screen. If necessary, it can also be read aloud. The input in this step is the response data sent from the server, and the output is the response content displayed to the user.

[0098] Step 7:

[0099] User response confirmation

[0100] The user checks the displayed response and takes the necessary action. Specifically, the user clicks the link displayed on the screen to change the check-in time. The input in this step is the response displayed on the terminal, and the output is the user's action.

[0101] (Application example 1)

[0102] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0103] Conventional customer support systems often delayed responses to user inquiries and sometimes failed to provide appropriate support. This was especially true for content distribution services, where users often made a wide variety of inquiries, making it difficult to respond quickly and accurately. Furthermore, ongoing support based on past inquiry history was not provided adequately, leading to lower customer satisfaction and worsening operational efficiency.

[0104] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0105] In this invention, the server includes means for receiving inquiries from users, means for having a generative model for analyzing the received inquiry, means for generating a response using the generative model and presenting the response to the user, means for sending inquiries using a smartphone and receiving the response, means for generating an appropriate response based on the inquiry in a content distribution service and presenting the response to the user, means for implementing natural language processing for analyzing the inquiry using the generative model and generating an appropriate response, and means for providing continuous support based on past inquiry history. This makes it possible to respond quickly and appropriately to user inquiries, improving customer satisfaction and streamlining customer support operations.

[0106] The "means for receiving inquiries from users" is an interface that allows users to input and send their own questions or requests.

[0107] A "server having a generative model for analyzing received inquiry content" is a server device equipped with a generative AI model for understanding the inquiry content sent by a user and generating an appropriate response.

[0108] "Means for generating a response using a generative model and presenting that response to the user" refers to a mechanism that generates an appropriate response from the results of analysis using a generative AI model and notifies the user of that response visually or audibly.

[0109] The "means for sending an inquiry and receiving a response using a smartphone" is an interface that allows a user to input an inquiry using a smartphone and receive a response to the inquiry.

[0110] "Means for generating an appropriate response based on the content of an inquiry in a content distribution service and presenting it to the user" refers to a mechanism for collecting and analyzing information related to a user's inquiry within a content distribution service, and generating and providing an appropriate response based on that information.

[0111] A "server that implements natural language processing to analyze inquiries using a generative model and generate appropriate responses" is a server that can analyze inquiries from users and generate accurate responses using a generative model and natural language processing technology.

[0112] "Means having the function of providing continuous support based on past inquiry history" refers to a mechanism that has the function of retaining the user's past inquiry history and providing continuous appropriate support based on that information.

[0113] The system for realizing this invention receives a query from a user, analyzes the query, and generates and presents an appropriate response. The system is composed of the following main components:

[0114] 1. Program Generation

[0115] The smartphone application provides an interface for users to submit queries and receive responses. When a user enters a query using their smartphone, the information is immediately sent to the server.

[0116] The server analyzes the received query using a generative AI model and natural language processing technology. As a result of the analysis, it generates an appropriate response based on the generative AI model. The server performs this processing using open-source natural language processing libraries (e.g., Spacy or NLTK) and generative AI models (e.g., OpenAI's GPT-3®).

[0117] 2. Program processing explanation

[0118] Hardware and Software Use:

[0119] Hardware:

[0120] Smartphones (devices for entering and displaying user queries)

[0121] Server (a device that analyzes the query and generates a response)

[0122] software:

[0123] Smartphone application (interface for sending inquiries and displaying responses)

[0124] Generative AI model on the server (model for query analysis and response generation)

[0125] Data processing and calculation:

[0126] 1. Inquiry received:

[0127] A user uses a smartphone application to send a query and transmits the content to the server.

[0128] 2. Content analysis:

[0129] The server uses a generative AI model (such as GPT-3) to analyze the query, using natural language processing technology to understand the meaning of the query.

[0130] 3. Response generation:

[0131] Based on the analysis results, the generative AI model generates an appropriate response, taking into account past inquiry history and context.

[0132] 4. Response prompts:

[0133] The server returns the generated response to the smartphone application and presents it to the user, who can view the response on the smartphone screen.

[0134] 3. Examples of concrete examples and prompts

[0135] Examples:

[0136] When a user sends an inquiry such as "How do I use the content distribution service?", the system operates as follows.

[0137] 1. The user uses their smartphone to enter an inquiry and tap the send button.

[0138] 2. The server receives the query and the generative AI model begins analysis.

[0139] 3. The generative AI model generates a response saying, "Here's how to use our content streaming service: First, download the app and create an account. Then you can search for content that interests you and start watching."

[0140] 4. The server generates a response and sends it back to the smartphone application, which displays it to the user.

[0141] Example prompt sentence:

[0142] User Question: "How do I use the content delivery service?"

[0143] Generate an appropriate response.

[0144] In this way, the present invention realizes a system for providing quick and accurate responses to user inquiries, and provides specific means for improving user satisfaction with content distribution services.

[0145] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0146] Step 1:

[0147] The user enters a query:

[0148] The user opens the smartphone application and enters a query. For example, the input is text such as "Please tell me how to use the content distribution service." Once the input is complete, the user taps the send button. This operation sends the query from the smartphone to the server.

[0149] Step 2:

[0150] The server receives the query:

[0151] The server receives a query sent from a smartphone application. The query is received as text data. The server prepares the text data to be passed to the generative AI model for analysis.

[0152] Step 3:

[0153] Inquiry analysis:

[0154] The server inputs the received query text into a generative AI model. The generative AI model (e.g., GPT-3) uses natural language processing to analyze the query and understand its meaning. The input data is the query text, and the output data is the context and key information of the analyzed query.

[0155] Step 4:

[0156] Producing the appropriate response:

[0157] The server uses a generative AI model based on the parsed query content to generate an appropriate response. Specifically, the generative AI model generates text such as, "To use our content distribution service, first download the app and create an account. Then, you can search for content that interests you and start watching." The input data is the parsed query context, and the output data is the generated response text.

[0158] Step 5:

[0159] Sending a response:

[0160] The server sends the generated response text to the smartphone application, where the input data is the generated response text and the output data is the response text received by the smartphone application.

[0161] Step 6:

[0162] Present the response to the user:

[0163] The smartphone application visually displays the response text received from the server to the user. The user can confirm the appropriate response content on the screen. Specifically, the app screen displays the following message: "To use our content distribution service, first download the app and create an account. Then, you can search for content that interests you and start watching."

[0164] In this way, the system can provide quick and accurate responses to user inquiries.

[0165] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0166] This invention relates to a customer support system that combines a generative model and an emotion engine. This system not only generates appropriate responses to user inquiries, but also recognizes the user's emotional state and provides responses based on that, thereby realizing more personalized support.

[0167] First, a user accesses the customer support page using a device and enters their inquiry. The device receives the user's inquiry and sends it in JSON format to the server. At this time, information for analyzing the user's sentiment is also collected.

[0168] Next, we will explain the server. The server receives data sent from the terminal. The received data includes the content of the inquiry and information about the user's emotional state. The server first starts the emotion engine and analyzes the user's emotional state. The emotion engine reads the user's emotions from their vocabulary and context, and determines whether the user is angry, troubled, or happy, for example.

[0169] The server uses a generative model to analyze the query based on the emotional state obtained from the emotion engine and generate an appropriate response. The generative model uses natural language processing to provide a response with a tone and content that matches the user's emotions. For example, if the user is angry, the generative model will generate a response with a calming tone, and if the user is in trouble, it will provide a kind and easy-to-understand explanation.

[0170] The server then sends the generated response to the device, which then displays it to the user. The response can be displayed as text on the screen or read aloud, allowing the user to view it and receive help in resolving the problem.

[0171] For example, if a user inquires, "I'd like to change my check-in time," the emotion engine may recognize an irritated emotion from the user's writing style. In this case, the generative model generates a polite response such as, "We're very sorry. You can change your check-in time. Please follow this link to complete the procedure. Please let us know if you need any further assistance." The server sends this response to the device, which then displays it to the user.

[0172] This system has the ability to maintain context and quickly retrieve necessary information from an FAQ database, and operates 24 hours a day, making it available at any time. The emotion engine provides responses based on the user's emotional state, improving customer satisfaction and streamlining customer support operations. This enables the system to provide highly reliable, friendly customer support to users.

[0173] The processing flow will be explained below.

[0174] Step 1:

[0175] The terminal displays a customer support page and provides a form for the user to enter their inquiry. The user enters their inquiry into the form and clicks the submit button.

[0176] Step 2:

[0177] The device receives the user's query, packages it as JSON data, performs rudimentary sentiment analysis based on the input to interpret the user's emotional state, and then sends this data to the server as an HTTP POST request.

[0178] Step 3:

[0179] The server receives an HTTP POST request sent from the device. The request data includes the query and simple emotional information. The server then launches the emotion engine to analyze this information.

[0180] Step 4:

[0181] The server-side emotion engine analyzes the user's inquiry in detail to determine the user's emotional state, which is then classified into multiple emotion categories, such as whether the user is angry, confused, happy, etc.

[0182] Step 5:

[0183] The server then uses the generative model to analyze the query and generate an appropriate response, taking into account the emotion engine's findings and tailoring the response to the user's emotional state. For example, if the user is angry, it might use a soothing tone, or if they are confused, it might provide a friendly, easy-to-understand explanation.

[0184] Step 6:

[0185] The server packages the generated response as JSON format data and sends it to the terminal as an HTTP response.

[0186] Step 7:

[0187] The terminal analyzes the HTTP response received from the server and extracts the response content. The terminal provides an interface to display this response to the user. Specifically, the terminal displays the response content as text or reads it out loud.

[0188] Step 8:

[0189] The user can check the displayed response to get an answer to their query, and can make further queries if necessary.

[0190] Through the above processing steps, the system can provide a quick and emotional response to user inquiries, thereby improving customer satisfaction.

[0191] Example 2

[0192] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0193] Conventional customer support systems do not take the user's emotions into consideration when generating responses to user inquiries, making it difficult to provide personalized responses and improving customer satisfaction. Furthermore, there is a demand for systems that can operate 24 hours a day and respond in line with the customer's emotions.

[0194] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0195] In this invention, the server includes means for receiving a query from a user, means having an emotion engine for analyzing the emotional state of the user, means for analyzing and generating a response using a generative model based on the received query content and the emotional state, and means for presenting the generated response to the user, thereby enabling the generation of a personalized response that is in line with the user's emotions.

[0196] "User" refers to any individual or legal entity that uses the System to make an inquiry.

[0197] "Enquiry" refers to a request for information or a question that a user makes to the system for support.

[0198] "Emotion engine" refers to software or algorithms for analyzing a user's emotional state.

[0199] A "generative model" refers to an AI model that performs natural language processing based on received data and generates an appropriate response.

[0200] "Server" refers to a computing device that receives queries from users and generates responses using an emotion engine or generative model.

[0201] "Terminal" refers to a device (e.g., smartphone, PC) through which a user enters a query and receives and displays responses generated by a server.

[0202] "JSON format" is an abbreviation for JavaScript (registered trademark) Object Notation, and is a lightweight data exchange format used as a data exchange format.

[0203] "24-hour system" refers to an operational mode in which the system operates continuously without daytime restrictions.

[0204] "Personalized response" refers to a response that is customized according to the user's inquiry and emotional state.

[0205] This invention relates to a customer support system that combines a generative model and an emotion engine. This system not only generates appropriate responses to user inquiries, but also recognizes the user's emotional state and provides responses based on that, thereby realizing more personalized support.

[0206] First, a user accesses the customer support page using a device and enters their inquiry. The device receives the user's inquiry and sends it in JSON format to the server. At this time, information for analyzing the user's sentiment is also collected.

[0207] The server receives the data sent from the terminal. The received data includes the inquiry content and information about the user's emotional state. The server first activates the emotion engine to analyze the user's emotional state. The emotion engine reads the user's emotions from their vocabulary and context, and determines whether the user is angry, troubled, or happy, for example.

[0208] The server uses a generative model to analyze the query based on the emotional state obtained from the emotion engine and generate an appropriate response. The generative model uses natural language processing to provide a response with a tone and content that matches the user's emotions. For example, if the user is angry, the generative model will generate a response with a calming tone, and if the user is in trouble, it will provide a kind and easy-to-understand explanation.

[0209] The server then sends the generated response to the device, which then displays it to the user. The response can be displayed as text on the screen or read aloud, allowing the user to view it and receive help in resolving the problem.

[0210] The specific hardware and software configuration of this system is as follows:

[0211] Emotion Engine

[0212] Software used: Python-based sentiment analysis library (e.g., NLTK, TextBlob)

[0213] Hardware used: Cloud server (e.g. AWS (registered trademark) EC2)

[0214] Generative Model

[0215] Software used: Natural language processing model (e.g. GPT-3)

[0216] Hardware used: High-performance GPU servers or cloud-based AI infrastructure (e.g., Google® Cloud AI, Azure® AI)

[0217] Specific examples

[0218] If a user inquires, "I'd like to change my check-in time," the emotion engine may recognize an irritated emotion from the user's writing style. In this case, the generative model generates a polite response such as, "We're very sorry. You can change your check-in time. Please follow this link to complete the procedure. Please let us know if you need any further assistance." The server sends this response to the device, which then displays it to the user.

[0219] Prompt Sentence Examples

[0220] Type: "My flight has been delayed and I would like to change my check-in time. How do I do this?"

[0221] Prompt to generative AI model: "The user has inquired about changing their check-in time. Analysis from the emotion engine indicates that the user is frustrated by their flight delay. Please provide an appropriate response to calm the user."

[0222] The system aims to improve customer satisfaction by providing emotion-based responses, and is capable of operating 24 hours a day, enabling fast and accurate customer support.

[0223] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0224] Step 1:

[0225] The user accesses the customer support page using the device and enters the inquiry.

[0226] Input: The inquiry entered by the user (e.g., "I would like to change my check-in time").

[0227] Specific operation: The user opens the device's web browser or a dedicated application and enters a question into the inquiry form.

[0228] Step 2:

[0229] The device collects the inquiry content and information for sentiment analysis and sends it to the server in JSON format.

[0230] Input: The inquiry entered by the user, and information for sentiment analysis (e.g., keyboard input speed, past inquiry history).

[0231] Data processing: Convert the input content and information for sentiment analysis into JSON format.

[0232] Output: Sends the query data in JSON format to the server.

[0233] Specific operation: The device packages the query content and accompanying emotion analysis data into a single JSON object and sends it to the server via an HTTP request.

[0234] Step 3:

[0235] The server receives and parses the JSON data.

[0236] Input: JSON formatted inquiry data sent from the terminal.

[0237] Data processing: Parsing JSON data.

[0238] Output: Analyzed query content and information for sentiment analysis.

[0239] Specific operation: The server receives an HTTP request, analyzes the JSON format data, and extracts the inquiry content and information for sentiment analysis.

[0240] Step 4:

[0241] The server activates an emotion engine to analyze the user's emotional state.

[0242] Input: Parsed inquiry content and information for sentiment analysis.

[0243] Data computation: Emotional state analysis using an emotion engine (e.g., using a natural language processing library).

[0244] Output: The user's emotional state (e.g., annoyed, troubled).

[0245] Specific operation: The server uses an emotion analysis library to analyze the user's language, context, keyboard input speed, etc. to determine the user's emotional state.

[0246] Step 5:

[0247] The server uses a generative model based on the emotional state to generate an appropriate response.

[0248] Input: Parsed query content and user's emotional state.

[0249] Data Computing: Generating responses with generative models (e.g., natural language processing using GPT-3).

[0250] Output: The generated response (e.g., "Your check-in time can be changed. Please complete the process here.").

[0251] Specific operation: The server activates the generative model and generates a response with appropriate tone and content depending on the user's query content and emotional state.

[0252] Step 6:

[0253] The server sends the generated response to the terminal.

[0254] Input: The generated response.

[0255] Data processing: Convert the response into JSON format.

[0256] Output: Sends JSON formatted response data to the terminal.

[0257] Specific operation: The server converts the generated response into JSON format and sends it to the terminal as an HTTP response.

[0258] Step 7:

[0259] The terminal displays the generated response to the user.

[0260] Input: JSON formatted response data sent from the server.

[0261] Data processing: Parse the JSON data to extract the text response.

[0262] Output: The response text or audio that is displayed to the user.

[0263] Specific operation: The device parses the JSON format response data and displays it as text on a web page or application, or reads it aloud using speech synthesis.

[0264] (Application example 2)

[0265] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0266] Conventional customer support systems often provide uniform responses without considering the user's emotional state, which can lead to lower user satisfaction and ineffective support. It is also difficult to provide appropriate responses depending on the user's emotions, such as distress or anger, making it necessary to improve the quality of customer support.

[0267] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving an inquiry from a user, means having a generative model and an emotion engine for analyzing the content of the received inquiry and the user's emotional state, and means for the server to generate a response based on the user's emotional state using the generative model and present the response to the user. This enables a personalized response tailored to the user's emotions, making it possible to improve the quality of customer support and user satisfaction.

[0268] The "means for receiving an inquiry from a user" is a mechanism for transmitting the contents of an inquiry entered by a user using a terminal to a server.

[0269] The "server with a generative model and emotion engine for analyzing the received inquiry content and the user's emotional state" is a server that has the function of analyzing questions from users and reading emotions from wording and context.

[0270] "Means for using a generative model to generate a response based on the user's emotional state and presenting that response to the user" is a mechanism for automatically generating a response that takes the user's emotions into consideration and displaying or communicating that response to the user.

[0271] The present invention is a customer support system that analyzes the content of a user's inquiry and emotional state and generates a personalized response according to the user's emotion. This system includes a mechanism in which a user makes an inquiry using a device such as a smartphone, and the content of the inquiry is processed by a server.

[0272] Hardware and software used

[0273] Hardware

[0274] Smartphone: Devices running iOS or ANDROID (registered trademark) OS

[0275] Server: A cloud server with suitable capabilities (e.g., AWS EC2 server)

[0276] Network equipment: Infrastructure equipment for data communication from terminals to servers

[0277] software

[0278] Emotion Engine: IBM Watson(R) Tone Analyzer

[0279] Generative model: OpenAI GPT-4 (registered trademark)

[0280] API communication framework: Flask (Python library)

[0281] Data processing and calculation

[0282] Users access customer support using their smartphones and input their inquiries, which are then sent to the server in JSON format, while also collecting data on the user's emotions.

[0283] The server first uses an emotion engine (IBM Watson Tone Analyzer) to analyze the user's emotional state from the content of the user's inquiry. The emotion engine analyzes the tone and context of the language and determines whether the user is happy, troubled, or angry.

[0284] Next, a generative model (OpenAI GPT-4) is used to generate a response based on the analyzed emotional state. The generative model creates appropriate prompts taking the emotional state into account and generates a response to the user based on that. This response is sent in text format from the server to the device and displayed on the screen.

[0285] Specific examples

[0286] Suppose a user makes a query such as, "My delivery is late and I'm worried. What's going on?" The device sends this query to the server, which analyzes it with its emotion engine and detects that the user is worried. The generative model takes this emotion into account and generates a response using the following prompt:

[0287] Prompt Sentence Examples

[0288] User Emotion: Anxiety

[0289] Enquiry: I'm worried about the delay in delivery. What's going on?

[0290] Appropriate response:

[0291] The generative model responds by generating the following sentence: "We are very sorry. It appears that delivery is currently delayed. We are currently investigating the details, so please wait a little longer. If you have any complaints, could you please contact customer support directly?" This response is sent from the server to the device, and the user can check it on their smartphone.

[0292] In this way, personalized responses tailored to the user's emotions are provided, thereby improving the quality of customer support and user satisfaction.

[0293] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0294] Step 1:

[0295] The user uses the device to input a query to customer support. For example, the input might be, "My delivery is delayed and I'm worried. What's going on?" The user's input is stored on the device as JSON-formatted data and awaits transmission to the server.

[0296] Input: User's inquiry (e.g. "My delivery is late and I'm worried. What's going on?")

[0297] Output: The query content is saved in JSON format on the terminal.

[0298] Step 2:

[0299] The device sends the user's query to the server in JSON format. The device also collects data on the user's emotions and sends it to the server.

[0300] Input: JSON formatted query content, data on user emotions (e.g., voice tone information, keyboard input speed, etc.)

[0301] Output: JSON format data is sent to the server

[0302] Step 3:

[0303] The server analyzes the JSON data received from the device. First, it launches the emotion engine (IBM Watson Tone Analyzer) to analyze the user's inquiry and identify their emotional state. The emotion engine reads the user's emotions from their text and determines whether they are worried, angry, confused, etc.

[0304] Input: JSON data received from the terminal

[0305] Output: Parsed emotional state (e.g., "worried")

[0306] Step 4:

[0307] The server generates an appropriate response based on the analyzed emotional state using a generative model (OpenAI GPT-4). The generative model receives prompts based on specific emotions and generates a response based on them.

[0308] Input: Analyzed emotional state, inquiry content

[0309] Output: The response generated by the generative model (e.g., "We're very sorry, but it appears your delivery is currently delayed. We're currently investigating the details, so please be patient. If you're unhappy, could you please contact customer support directly?")

[0310] Step 5:

[0311] The server then sends the generated response back to the device in JSON format. The device then analyzes the response data received from the server and displays it on the screen or reads it out loud, allowing the user to check the response to their query.

[0312] Input: The generated response JSON data sent from the server

[0313] Output: The response displayed on the device screen or read aloud

[0314] Step 6:

[0315] The user checks the responses provided by the terminal and makes additional inquiries as needed. By repeating this cycle, the system continuously provides answers to the user's inquiries.

[0316] Input: The response displayed on the device screen or read aloud

[0317] Output: User confirmation and further prompts

[0318] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0319] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0320] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0321] [Second embodiment]

[0322] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0323] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0324] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0325] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0326] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0327] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0328] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0329] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0330] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0331] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0332] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0333] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0334] This invention describes a customer support system that uses generative models to receive inquiries from users, analyze the inquiries, and generate and present appropriate responses.

[0335] First, we will describe the terminal in this system. Users use the terminal to access the customer support page and enter their questions or requests. The terminal provides an interface to receive the user's inquiry and send it to the server for analysis and response generation. This interface may be implemented as a web form or a dedicated application.

[0336] Next, we will explain the server. The server receives the inquiry content sent by the user and analyzes that content using a generative model. Specifically, the server uses natural language processing to properly understand the user's inquiry content and generate an optimal response based on that understanding. For example, a generative AI model is used as this generative model. This generative model is trained using a pre-learned dataset and is capable of generating appropriate responses with high accuracy.

[0337] The server sends the generated response to the terminal. The terminal provides a means for presenting the response received from the server to the user. For example, the response can be displayed on a screen or read aloud. This allows users to receive real-time support 24 hours a day, 365 days a year.

[0338] Next, we will explain the operation of this system using a concrete example. When a user makes an inquiry such as "I would like to change my check-in time," the terminal receives this inquiry and sends it to the server. The server uses a generative model to analyze the inquiry and generate a response such as "To change your check-in time, please access this link." The server then sends the generated response to the terminal, which displays it to the user. In this way, the user can receive a prompt and accurate response.

[0339] The system has the ability to maintain context based on the inquiry content and retrieve necessary information from an FAQ database. The system also operates 24 hours a day, ensuring availability at all times and reducing human error. This results in improved customer satisfaction and more efficient customer support operations.

[0340] The above is a description of the mode for carrying out the invention. The present system is useful in that it has a wide range of applicability and can respond to a variety of inquiries.

[0341] The processing flow will be explained below.

[0342] Step 1:

[0343] The terminal displays a customer support page and provides a form for the user to enter their inquiry. The user enters their inquiry into the form and clicks the submit button.

[0344] Step 2:

[0345] The device receives the query entered by the user, packages it as JSON-formatted data for processing, and then sends the data to the server as an HTTP POST request.

[0346] Step 3:

[0347] The server receives an HTTP POST request sent from the device, extracts the query content from the request, and passes it to the generative model for analysis.

[0348] Step 4:

[0349] A generative model on the server analyzes the query and generates an appropriate response. This generative model is pre-trained with a large amount of data, enabling highly accurate natural language processing.

[0350] Step 5:

[0351] The server receives the response generated by the generative model, packages it again as JSON-formatted data, and sends this response data to the terminal as an HTTP response.

[0352] Step 6:

[0353] The terminal analyzes the HTTP response received from the server, extracts the response content, and provides an interface for displaying the extracted response content to the user.

[0354] Step 7:

[0355] The terminal displays the response to the user, who can then confirm the response, completing the response to the user's inquiry.

[0356] Example 1

[0357] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0358] Conventional customer support systems often had slow responses to inquiries, which led to lower user satisfaction. Furthermore, they often relied on human intervention, making it difficult to provide 24-hour support. Furthermore, it was difficult to generate appropriate responses to inquiries, which sometimes led to inefficient support.

[0359] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0360] In this invention, the server includes a means for receiving inquiries from users, a means having a generative model using natural language processing technology for analyzing the content of the received inquiry, and a terminal for generating a response using the generative model and presenting the response to the user. This enables the generation of quick and appropriate responses to inquiries, realizing efficient customer support around the clock.

[0361] A "user" is a person or organization that uses the system to make an inquiry.

[0362] An "inquiry" is information about a question or request that a user enters through the system.

[0363] A "terminal" is an electronic device used by a user to enter inquiries and receive responses, and includes personal computers, smartphones, tablets, and the like.

[0364] The "server" is a central processing unit that receives the contents of an inquiry sent by a user, analyzes it, generates a response, and sends it to the terminal.

[0365] "Natural language processing technology" is a technology for converting the content of inquiries entered by users into a format that is easy for machines to understand and analyzing it.

[0366] A "generative model" is an algorithm that uses a pre-trained dataset to generate appropriate responses to user queries.

[0367] A "response" is information or instructions that the server generates in response to a user's query using a generative model and that are presented to the user via the terminal.

[0368] "24-hour system" means that the system operates continuously 24 hours a day, seven days a week, and is able to respond to user inquiries at any time.

[0369] This invention describes a customer support system that uses a generative AI model to receive inquiries from users, analyze the inquiries, and generate and present appropriate responses.

[0370] First, we will explain the terminals in this system. Users use the terminals to access the customer support page and enter their questions or requests. The terminals provide an interface for receiving the user's inquiries and sending them to the server for analysis and response generation. This interface may be implemented as a web form or a dedicated application. For example, this could be a form on a web browser or a smartphone application.

[0371] Next, we will explain the server. The server receives the inquiry content sent by the user and analyzes that content using a generative AI model. Specifically, the server uses natural language processing technology to properly understand the user's inquiry content and generate an optimal response based on that understanding. For example, a natural language generation AI model is used as this generative model. This model is trained using a large pre-learned dataset, and is capable of generating appropriate responses with high accuracy.

[0372] The server sends the generated response to the terminal. The terminal provides a means for presenting the response received from the server to the user. For example, the response can be displayed on a screen or read aloud. This allows users to receive real-time support 24 hours a day, 365 days a year.

[0373] Next, we will explain the operation of this system using a concrete example. When a user makes an inquiry such as "I would like to change my check-in time," the terminal receives this inquiry and sends it to the server. The server uses a generative model to analyze the inquiry and generate a response such as "To change your check-in time, please access this link." The server then sends the generated response to the terminal, which displays it to the user. In this way, the user can receive a prompt and accurate response.

[0374] For example, you might send the following prompt to a generative AI model:

[0375] "The user has asked, 'I would like to change the check-in time.' Please generate an appropriate response."

[0376] The system has the ability to maintain context based on the inquiry content and retrieve necessary information from an FAQ database. The system also operates 24 hours a day, ensuring availability at all times and reducing human error. This results in improved customer satisfaction and more efficient customer support operations.

[0377] The above is an embodiment of the present invention. The system has wide applicability and can respond to a variety of inquiries.

[0378] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0379] Step 1:

[0380] User input of query

[0381] A user accesses the customer support page using a terminal and enters their question or request. Specifically, the user enters "I would like to change my check-in time" in the text box. This entered data is treated as an inquiry to be used in the next step.

[0382] Step 2:

[0383] Sending inquiries via the device

[0384] The terminal receives the inquiry entered by the user and sends that data to the server. Specifically, the terminal sends the data "I would like to change the check-in time" to the server. At this time, a highly reliable communication method (e.g. HTTPS) is used. The user's inquiry is the input, and the data sent to the server is the output.

[0385] Step 3:

[0386] Receipt and analysis of query content by the server

[0387] The server receives the inquiry sent from the device. The server receives the inquiry "I would like to change the check-in time" and analyzes it using natural language processing technology. Specifically, the generative AI model receives a prompt sentence, "The user has inquired, 'I would like to change the check-in time.' Please generate an appropriate response.", and an appropriate response is generated. In this step, the inquiry is received as input, and the response from the generative AI model is obtained as output.

[0388] Step 4:

[0389] Server response generation

[0390] The server uses the generative AI model to generate an appropriate response to the query. For example, the generative AI model might generate a response like, "To change your check-in time, please visit this link." The input in this step is the prompt for the generative AI model, and the output is the generated response.

[0391] Step 5:

[0392] Server sends response

[0393] The server sends the generated response to the terminal. Specifically, it sends the generated response "To change your check-in time, please visit this link." to the terminal. The input in this step is the generated response, and the output is the data sent to the terminal.

[0394] Step 6:

[0395] Terminal display of responses

[0396] The terminal presents the response received from the server to the user. Specifically, it displays the text "To change your check-in time, please follow this link." on the screen. If necessary, it can also be read aloud. The input in this step is the response data sent from the server, and the output is the response content displayed to the user.

[0397] Step 7:

[0398] User response confirmation

[0399] The user checks the displayed response and takes the necessary action. Specifically, the user clicks the link displayed on the screen to change the check-in time. The input in this step is the response displayed on the terminal, and the output is the user's action.

[0400] (Application example 1)

[0401] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0402] Conventional customer support systems often delayed responses to user inquiries and sometimes failed to provide appropriate support. This was especially true for content distribution services, where users often made a wide variety of inquiries, making it difficult to respond quickly and accurately. Furthermore, ongoing support based on past inquiry history was not provided adequately, leading to lower customer satisfaction and worsening operational efficiency.

[0403] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0404] In this invention, the server includes means for receiving inquiries from users, means for having a generative model for analyzing the received inquiry, means for generating a response using the generative model and presenting the response to the user, means for sending inquiries using a smartphone and receiving the response, means for generating an appropriate response based on the inquiry in a content distribution service and presenting the response to the user, means for implementing natural language processing for analyzing the inquiry using the generative model and generating an appropriate response, and means for providing continuous support based on past inquiry history. This makes it possible to respond quickly and appropriately to user inquiries, improving customer satisfaction and streamlining customer support operations.

[0405] The "means for receiving inquiries from users" is an interface that allows users to input and send their own questions or requests.

[0406] A "server having a generative model for analyzing received inquiry content" is a server device equipped with a generative AI model for understanding the inquiry content sent by a user and generating an appropriate response.

[0407] "Means for generating a response using a generative model and presenting that response to the user" refers to a mechanism that generates an appropriate response from the results of analysis using a generative AI model and notifies the user of that response visually or audibly.

[0408] The "means for sending an inquiry and receiving a response using a smartphone" is an interface that allows a user to input an inquiry using a smartphone and receive a response to the inquiry.

[0409] "Means for generating an appropriate response based on the content of an inquiry in a content distribution service and presenting it to the user" refers to a mechanism for collecting and analyzing information related to a user's inquiry within a content distribution service, and generating and providing an appropriate response based on that information.

[0410] A "server that implements natural language processing to analyze inquiries using a generative model and generate appropriate responses" is a server that can analyze inquiries from users and generate accurate responses using a generative model and natural language processing technology.

[0411] "Means having the function of providing continuous support based on past inquiry history" refers to a mechanism that has the function of retaining the user's past inquiry history and providing continuous appropriate support based on that information.

[0412] The system for realizing this invention receives a query from a user, analyzes the query, and generates and presents an appropriate response. The system is composed of the following main components:

[0413] 1. Program Generation

[0414] The smartphone application provides an interface for users to submit queries and receive responses. When a user enters a query using their smartphone, the information is immediately sent to the server.

[0415] The server analyzes the received query using generative AI models and natural language processing techniques. As a result of the analysis, it generates an appropriate response based on the generative AI model. The server performs this processing using open-source natural language processing libraries (e.g., Spacy and NLTK) and generative AI models (e.g., OpenAI's GPT-3).

[0416] 2. Program processing explanation

[0417] Hardware and Software Use:

[0418] Hardware:

[0419] Smartphones (devices for entering and displaying user queries)

[0420] Server (a device that analyzes the query and generates a response)

[0421] software:

[0422] Smartphone application (interface for sending inquiries and displaying responses)

[0423] Generative AI model on the server (model for query analysis and response generation)

[0424] Data processing and calculation:

[0425] 1. Inquiry received:

[0426] A user uses a smartphone application to send a query and transmits the content to the server.

[0427] 2. Content analysis:

[0428] The server uses a generative AI model (such as GPT-3) to analyze the query, using natural language processing technology to understand the meaning of the query.

[0429] 3. Response generation:

[0430] Based on the analysis results, the generative AI model generates an appropriate response, taking into account past inquiry history and context.

[0431] 4. Response prompts:

[0432] The server returns the generated response to the smartphone application and presents it to the user, who can view the response on the smartphone screen.

[0433] 3. Examples of concrete examples and prompts

[0434] Examples:

[0435] When a user sends an inquiry such as "How do I use the content distribution service?", the system operates as follows.

[0436] 1. The user uses their smartphone to enter an inquiry and tap the send button.

[0437] 2. The server receives the query and the generative AI model begins analysis.

[0438] 3. The generative AI model generates a response saying, "Here's how to use our content streaming service: First, download the app and create an account. Then you can search for content that interests you and start watching."

[0439] 4. The server generates a response and sends it back to the smartphone application, which displays it to the user.

[0440] Example prompt sentence:

[0441] User Question: "How do I use the content delivery service?"

[0442] Generate an appropriate response.

[0443] In this way, the present invention realizes a system for providing quick and accurate responses to user inquiries, and provides specific means for improving user satisfaction with content distribution services.

[0444] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0445] Step 1:

[0446] The user enters a query:

[0447] The user opens the smartphone application and enters a query. For example, the input is text such as "Please tell me how to use the content distribution service." Once the input is complete, the user taps the send button. This operation sends the query from the smartphone to the server.

[0448] Step 2:

[0449] The server receives the query:

[0450] The server receives a query sent from a smartphone application. The query is received as text data. The server prepares the text data to be passed to the generative AI model for analysis.

[0451] Step 3:

[0452] Inquiry analysis:

[0453] The server inputs the received query text into a generative AI model. The generative AI model (e.g., GPT-3) uses natural language processing to analyze the query and understand its meaning. The input data is the query text, and the output data is the context and key information of the analyzed query.

[0454] Step 4:

[0455] Producing the appropriate response:

[0456] The server uses a generative AI model based on the parsed query content to generate an appropriate response. Specifically, the generative AI model generates text such as, "To use our content distribution service, first download the app and create an account. Then, you can search for content that interests you and start watching." The input data is the parsed query context, and the output data is the generated response text.

[0457] Step 5:

[0458] Sending a response:

[0459] The server sends the generated response text to the smartphone application, where the input data is the generated response text and the output data is the response text received by the smartphone application.

[0460] Step 6:

[0461] Present the response to the user:

[0462] The smartphone application visually displays the response text received from the server to the user. The user can confirm the appropriate response content on the screen. Specifically, the app screen displays the following message: "To use our content distribution service, first download the app and create an account. Then, you can search for content that interests you and start watching."

[0463] In this way, the system can provide quick and accurate responses to user inquiries.

[0464] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0465] This invention relates to a customer support system that combines a generative model and an emotion engine. This system not only generates appropriate responses to user inquiries, but also recognizes the user's emotional state and provides responses based on that, thereby realizing more personalized support.

[0466] First, a user accesses the customer support page using a device and enters their inquiry. The device receives the user's inquiry and sends it in JSON format to the server. At this time, information for analyzing the user's sentiment is also collected.

[0467] Next, we will explain the server. The server receives data sent from the terminal. The received data includes the content of the inquiry and information about the user's emotional state. The server first starts the emotion engine and analyzes the user's emotional state. The emotion engine reads the user's emotions from their vocabulary and context, and determines whether the user is angry, troubled, or happy, for example.

[0468] The server uses a generative model to analyze the query based on the emotional state obtained from the emotion engine and generate an appropriate response. The generative model uses natural language processing to provide a response with a tone and content that matches the user's emotions. For example, if the user is angry, the generative model will generate a response with a calming tone, and if the user is in trouble, it will provide a kind and easy-to-understand explanation.

[0469] The server then sends the generated response to the device, which then displays it to the user. The response can be displayed as text on the screen or read aloud, allowing the user to view it and receive help in resolving the problem.

[0470] For example, if a user inquires, "I'd like to change my check-in time," the emotion engine may recognize an irritated emotion from the user's writing style. In this case, the generative model generates a polite response such as, "We're very sorry. You can change your check-in time. Please follow this link to complete the procedure. Please let us know if you need any further assistance." The server sends this response to the device, which then displays it to the user.

[0471] This system has the ability to maintain context and quickly retrieve necessary information from an FAQ database, and operates 24 hours a day, making it available at any time. The emotion engine provides responses based on the user's emotional state, improving customer satisfaction and streamlining customer support operations. This enables the system to provide highly reliable, friendly customer support to users.

[0472] The processing flow will be explained below.

[0473] Step 1:

[0474] The terminal displays a customer support page and provides a form for the user to enter their inquiry. The user enters their inquiry into the form and clicks the submit button.

[0475] Step 2:

[0476] The device receives the user's query, packages it as JSON data, performs rudimentary sentiment analysis based on the input to interpret the user's emotional state, and then sends this data to the server as an HTTP POST request.

[0477] Step 3:

[0478] The server receives an HTTP POST request sent from the device. The request data includes the query and simple emotional information. The server then launches the emotion engine to analyze this information.

[0479] Step 4:

[0480] The server-side emotion engine analyzes the user's inquiry in detail to determine the user's emotional state, which is then classified into multiple emotion categories, such as whether the user is angry, confused, happy, etc.

[0481] Step 5:

[0482] The server then uses the generative model to analyze the query and generate an appropriate response, taking into account the emotion engine's findings and tailoring the response to the user's emotional state. For example, if the user is angry, it might use a soothing tone, or if they are confused, it might provide a friendly, easy-to-understand explanation.

[0483] Step 6:

[0484] The server packages the generated response as JSON format data and sends it to the terminal as an HTTP response.

[0485] Step 7:

[0486] The terminal analyzes the HTTP response received from the server and extracts the response content. The terminal provides an interface to display this response to the user. Specifically, the terminal displays the response content as text or reads it out loud.

[0487] Step 8:

[0488] The user can check the displayed response to get an answer to their query, and can make further queries if necessary.

[0489] Through the above processing steps, the system can provide a quick and emotional response to user inquiries, thereby improving customer satisfaction.

[0490] Example 2

[0491] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0492] Conventional customer support systems do not take the user's emotions into consideration when generating responses to user inquiries, making it difficult to provide personalized responses and improving customer satisfaction. Furthermore, there is a demand for systems that can operate 24 hours a day and respond in line with the customer's emotions.

[0493] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0494] In this invention, the server includes means for receiving a query from a user, means having an emotion engine for analyzing the emotional state of the user, means for analyzing and generating a response using a generative model based on the received query content and the emotional state, and means for presenting the generated response to the user, thereby enabling the generation of a personalized response that is in line with the user's emotions.

[0495] "User" refers to any individual or legal entity that uses the System to make an inquiry.

[0496] "Enquiry" refers to a request for information or a question that a user makes to the system for support.

[0497] "Emotion engine" refers to software or algorithms for analyzing a user's emotional state.

[0498] A "generative model" refers to an AI model that performs natural language processing based on received data and generates an appropriate response.

[0499] "Server" refers to a computing device that receives queries from users and generates responses using an emotion engine or generative model.

[0500] "Terminal" refers to a device (e.g., smartphone, PC) through which a user enters a query and receives and displays responses generated by a server.

[0501] "JSON format" is an abbreviation for JavaScript Object Notation, and is a lightweight data exchange format used as a data exchange format.

[0502] "24-hour system" refers to an operational mode in which the system operates continuously without daytime restrictions.

[0503] "Personalized response" refers to a response that is customized according to the user's inquiry and emotional state.

[0504] This invention relates to a customer support system that combines a generative model and an emotion engine. This system not only generates appropriate responses to user inquiries, but also recognizes the user's emotional state and provides responses based on that, thereby realizing more personalized support.

[0505] First, a user accesses the customer support page using a device and enters their inquiry. The device receives the user's inquiry and sends it in JSON format to the server. At this time, information for analyzing the user's sentiment is also collected.

[0506] The server receives the data sent from the terminal. The received data includes the inquiry content and information about the user's emotional state. The server first activates the emotion engine to analyze the user's emotional state. The emotion engine reads the user's emotions from their vocabulary and context, and determines whether the user is angry, troubled, or happy, for example.

[0507] The server uses a generative model to analyze the query based on the emotional state obtained from the emotion engine and generate an appropriate response. The generative model uses natural language processing to provide a response with a tone and content that matches the user's emotions. For example, if the user is angry, the generative model will generate a response with a calming tone, and if the user is in trouble, it will provide a kind and easy-to-understand explanation.

[0508] The server then sends the generated response to the device, which then displays it to the user. The response can be displayed as text on the screen or read aloud, allowing the user to view it and receive help in resolving the problem.

[0509] The specific hardware and software configuration of this system is as follows:

[0510] Emotion Engine

[0511] Software used: Python-based sentiment analysis libraries (e.g., NLTK, TextBlob)

[0512] Hardware used: Cloud server (e.g. AWS EC2)

[0513] Generative Model

[0514] Software used: Natural language processing model (e.g. GPT-3)

[0515] Hardware used: High-performance GPU servers or cloud-based AI infrastructure (e.g., Google Cloud AI, Azure AI)

[0516] Specific examples

[0517] If a user inquires, "I'd like to change my check-in time," the emotion engine may recognize an irritated emotion from the user's writing style. In this case, the generative model generates a polite response such as, "We're very sorry. You can change your check-in time. Please follow this link to complete the procedure. Please let us know if you need any further assistance." The server sends this response to the device, which then displays it to the user.

[0518] Prompt Sentence Examples

[0519] Type: "My flight has been delayed and I would like to change my check-in time. How do I do this?"

[0520] Prompt to generative AI model: "The user has inquired about changing their check-in time. Analysis from the emotion engine indicates that the user is frustrated by their flight delay. Please provide an appropriate response to calm the user."

[0521] The system aims to improve customer satisfaction by providing emotion-based responses, and is capable of operating 24 hours a day, enabling fast and accurate customer support.

[0522] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0523] Step 1:

[0524] The user accesses the customer support page using the device and enters the inquiry.

[0525] Input: The inquiry entered by the user (e.g., "I would like to change my check-in time").

[0526] Specific operation: The user opens the device's web browser or a dedicated application and enters a question into the inquiry form.

[0527] Step 2:

[0528] The device collects the inquiry content and information for sentiment analysis and sends it to the server in JSON format.

[0529] Input: The inquiry entered by the user, and information for sentiment analysis (e.g., keyboard input speed, past inquiry history).

[0530] Data processing: Convert the input content and information for sentiment analysis into JSON format.

[0531] Output: Sends the query data in JSON format to the server.

[0532] Specific operation: The device packages the query content and accompanying emotion analysis data into a single JSON object and sends it to the server via an HTTP request.

[0533] Step 3:

[0534] The server receives and parses the JSON data.

[0535] Input: JSON formatted inquiry data sent from the terminal.

[0536] Data processing: Parsing JSON data.

[0537] Output: Analyzed query content and information for sentiment analysis.

[0538] Specific operation: The server receives an HTTP request, analyzes the JSON format data, and extracts the inquiry content and information for sentiment analysis.

[0539] Step 4:

[0540] The server activates an emotion engine to analyze the user's emotional state.

[0541] Input: Parsed inquiry content and information for sentiment analysis.

[0542] Data computation: Emotional state analysis using an emotion engine (e.g., using a natural language processing library).

[0543] Output: The user's emotional state (e.g., annoyed, troubled).

[0544] Specific operation: The server uses an emotion analysis library to analyze the user's language, context, keyboard input speed, etc. to determine the user's emotional state.

[0545] Step 5:

[0546] The server uses a generative model based on the emotional state to generate an appropriate response.

[0547] Input: Parsed query content and user's emotional state.

[0548] Data Computing: Generating responses with generative models (e.g., natural language processing using GPT-3).

[0549] Output: The generated response (e.g., "Your check-in time can be changed. Please complete the process here.").

[0550] Specific operation: The server activates the generative model and generates a response with appropriate tone and content depending on the user's query content and emotional state.

[0551] Step 6:

[0552] The server sends the generated response to the terminal.

[0553] Input: The generated response.

[0554] Data processing: Convert the response into JSON format.

[0555] Output: Sends JSON formatted response data to the terminal.

[0556] Specific operation: The server converts the generated response into JSON format and sends it to the terminal as an HTTP response.

[0557] Step 7:

[0558] The terminal displays the generated response to the user.

[0559] Input: JSON formatted response data sent from the server.

[0560] Data processing: Parse the JSON data to extract the text response.

[0561] Output: The response text or audio that is displayed to the user.

[0562] Specific operation: The device parses the JSON format response data and displays it as text on a web page or application, or reads it aloud using speech synthesis.

[0563] (Application example 2)

[0564] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0565] Conventional customer support systems often provide uniform responses without considering the user's emotional state, which can lead to lower user satisfaction and ineffective support. It is also difficult to provide appropriate responses depending on the user's emotions, such as distress or anger, making it necessary to improve the quality of customer support.

[0566] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving an inquiry from a user, means having a generative model and an emotion engine for analyzing the content of the received inquiry and the user's emotional state, and means for the server to generate a response based on the user's emotional state using the generative model and present the response to the user. This enables a personalized response tailored to the user's emotions, making it possible to improve the quality of customer support and user satisfaction.

[0567] The "means for receiving an inquiry from a user" is a mechanism for transmitting the contents of an inquiry entered by a user using a terminal to a server.

[0568] The "server with a generative model and emotion engine for analyzing the received inquiry content and the user's emotional state" is a server that has the function of analyzing questions from users and reading emotions from wording and context.

[0569] "Means for using a generative model to generate a response based on the user's emotional state and presenting that response to the user" is a mechanism for automatically generating a response that takes the user's emotions into consideration and displaying or communicating that response to the user.

[0570] The present invention is a customer support system that analyzes the content of a user's inquiry and emotional state and generates a personalized response according to the user's emotion. This system includes a mechanism in which a user makes an inquiry using a device such as a smartphone, and the content of the inquiry is processed by a server.

[0571] Hardware and software used

[0572] Hardware

[0573] Smartphone: Devices running iOS or Android OS

[0574] Server: A cloud server with suitable capabilities (e.g., AWS EC2 server)

[0575] Network equipment: Infrastructure equipment for data communication from terminals to servers

[0576] software

[0577] Emotion engine: IBM Watson Tone Analyzer

[0578] Generative model: OpenAI GPT-4

[0579] API communication framework: Flask (Python library)

[0580] Data processing and calculation

[0581] Users access customer support using their smartphones and input their inquiries, which are then sent to the server in JSON format, while also collecting data on the user's emotions.

[0582] The server first uses an emotion engine (IBM Watson Tone Analyzer) to analyze the user's emotional state from the content of the user's inquiry. The emotion engine analyzes the tone and context of the language and determines whether the user is happy, troubled, or angry.

[0583] Next, a generative model (OpenAI GPT-4) is used to generate a response based on the analyzed emotional state. The generative model creates appropriate prompts taking the emotional state into account and generates a response to the user based on that. This response is sent in text format from the server to the device and displayed on the screen.

[0584] Specific examples

[0585] Suppose a user makes a query such as, "My delivery is late and I'm worried. What's going on?" The device sends this query to the server, which analyzes it with its emotion engine and detects that the user is worried. The generative model takes this emotion into account and generates a response using the following prompt:

[0586] Prompt Sentence Examples

[0587] User Emotion: Anxiety

[0588] Enquiry: I'm worried about the delay in delivery. What's going on?

[0589] Appropriate response:

[0590] The generative model responds by generating the following sentence: "We are very sorry. It appears that delivery is currently delayed. We are currently investigating the details, so please wait a little longer. If you have any complaints, could you please contact customer support directly?" This response is sent from the server to the device, and the user can check it on their smartphone.

[0591] In this way, personalized responses tailored to the user's emotions are provided, thereby improving the quality of customer support and user satisfaction.

[0592] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0593] Step 1:

[0594] The user uses the device to input a query to customer support. For example, the input might be, "My delivery is delayed and I'm worried. What's going on?" The user's input is stored on the device as JSON-formatted data and awaits transmission to the server.

[0595] Input: User's inquiry (e.g. "My delivery is late and I'm worried. What's going on?")

[0596] Output: The query content is saved in JSON format on the terminal.

[0597] Step 2:

[0598] The device sends the user's query to the server in JSON format. The device also collects data on the user's emotions and sends it to the server.

[0599] Input: JSON formatted query content, data on user emotions (e.g., voice tone information, keyboard input speed, etc.)

[0600] Output: JSON format data is sent to the server

[0601] Step 3:

[0602] The server analyzes the JSON data received from the device. First, it launches the emotion engine (IBM Watson Tone Analyzer) to analyze the user's inquiry and identify their emotional state. The emotion engine reads the user's emotions from their text and determines whether they are worried, angry, confused, etc.

[0603] Input: JSON data received from the terminal

[0604] Output: Parsed emotional state (e.g., "worried")

[0605] Step 4:

[0606] The server generates an appropriate response based on the analyzed emotional state using a generative model (OpenAI GPT-4). The generative model receives prompts based on specific emotions and generates a response based on them.

[0607] Input: Analyzed emotional state, inquiry content

[0608] Output: The response generated by the generative model (e.g., "We're very sorry, but it appears your delivery is currently delayed. We're currently investigating the details, so please be patient. If you're unhappy, could you please contact customer support directly?")

[0609] Step 5:

[0610] The server then sends the generated response back to the device in JSON format. The device then analyzes the response data received from the server and displays it on the screen or reads it out loud, allowing the user to check the response to their query.

[0611] Input: The generated response JSON data sent from the server

[0612] Output: The response displayed on the device screen or read aloud

[0613] Step 6:

[0614] The user checks the responses provided by the terminal and makes additional inquiries as needed. By repeating this cycle, the system continuously provides answers to the user's inquiries.

[0615] Input: The response displayed on the device screen or read aloud

[0616] Output: User confirmation and further prompts

[0617] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0618] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0619] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0620] [Third embodiment]

[0621] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0622] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0623] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0624] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0625] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0626] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0627] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0628] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0629] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0630] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0631] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0632] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0633] This invention describes a customer support system that uses generative models to receive inquiries from users, analyze the inquiries, and generate and present appropriate responses.

[0634] First, we will describe the terminal in this system. Users use the terminal to access the customer support page and enter their questions or requests. The terminal provides an interface to receive the user's inquiry and send it to the server for analysis and response generation. This interface may be implemented as a web form or a dedicated application.

[0635] Next, we will explain the server. The server receives the inquiry content sent by the user and analyzes that content using a generative model. Specifically, the server uses natural language processing to properly understand the user's inquiry content and generate an optimal response based on that understanding. For example, a generative AI model is used as this generative model. This generative model is trained using a pre-learned dataset and is capable of generating appropriate responses with high accuracy.

[0636] The server sends the generated response to the terminal. The terminal provides a means for presenting the response received from the server to the user. For example, the response can be displayed on a screen or read aloud. This allows users to receive real-time support 24 hours a day, 365 days a year.

[0637] Next, we will explain the operation of this system using a concrete example. When a user makes an inquiry such as "I would like to change my check-in time," the terminal receives this inquiry and sends it to the server. The server uses a generative model to analyze the inquiry and generate a response such as "To change your check-in time, please access this link." The server then sends the generated response to the terminal, which displays it to the user. In this way, the user can receive a prompt and accurate response.

[0638] The system has the ability to maintain context based on the inquiry content and retrieve necessary information from an FAQ database. The system also operates 24 hours a day, ensuring availability at all times and reducing human error. This results in improved customer satisfaction and more efficient customer support operations.

[0639] The above is a description of the mode for carrying out the invention. The present system is useful in that it has a wide range of applicability and can respond to a variety of inquiries.

[0640] The processing flow will be explained below.

[0641] Step 1:

[0642] The terminal displays a customer support page and provides a form for the user to enter their inquiry. The user enters their inquiry into the form and clicks the submit button.

[0643] Step 2:

[0644] The device receives the query entered by the user, packages it as JSON-formatted data for processing, and then sends the data to the server as an HTTP POST request.

[0645] Step 3:

[0646] The server receives an HTTP POST request sent from the device, extracts the query content from the request, and passes it to the generative model for analysis.

[0647] Step 4:

[0648] A generative model on the server analyzes the query and generates an appropriate response. This generative model is pre-trained with a large amount of data, enabling highly accurate natural language processing.

[0649] Step 5:

[0650] The server receives the response generated by the generative model, packages it again as JSON-formatted data, and sends this response data to the terminal as an HTTP response.

[0651] Step 6:

[0652] The terminal analyzes the HTTP response received from the server, extracts the response content, and provides an interface for displaying the extracted response content to the user.

[0653] Step 7:

[0654] The terminal displays the response to the user, who can then confirm the response, completing the response to the user's inquiry.

[0655] Example 1

[0656] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0657] Conventional customer support systems often had slow responses to inquiries, which led to lower user satisfaction. Furthermore, they often relied on human intervention, making it difficult to provide 24-hour support. Furthermore, it was difficult to generate appropriate responses to inquiries, which sometimes led to inefficient support.

[0658] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0659] In this invention, the server includes a means for receiving inquiries from users, a means having a generative model using natural language processing technology for analyzing the content of the received inquiry, and a terminal for generating a response using the generative model and presenting the response to the user. This enables the generation of quick and appropriate responses to inquiries, realizing efficient customer support around the clock.

[0660] A "user" is a person or organization that uses the system to make an inquiry.

[0661] An "inquiry" is information about a question or request that a user enters through the system.

[0662] A "terminal" is an electronic device used by a user to enter inquiries and receive responses, and includes personal computers, smartphones, tablets, and the like.

[0663] The "server" is a central processing unit that receives the contents of an inquiry sent by a user, analyzes it, generates a response, and sends it to the terminal.

[0664] "Natural language processing technology" is a technology for converting the content of inquiries entered by users into a format that is easy for machines to understand and analyzing it.

[0665] A "generative model" is an algorithm that uses a pre-trained dataset to generate appropriate responses to user queries.

[0666] A "response" is information or instructions that the server generates in response to a user's query using a generative model and that are presented to the user via the terminal.

[0667] "24-hour system" means that the system operates continuously 24 hours a day, seven days a week, and is able to respond to user inquiries at any time.

[0668] This invention describes a customer support system that uses a generative AI model to receive inquiries from users, analyze the inquiries, and generate and present appropriate responses.

[0669] First, we will explain the terminals in this system. Users use the terminals to access the customer support page and enter their questions or requests. The terminals provide an interface for receiving the user's inquiries and sending them to the server for analysis and response generation. This interface may be implemented as a web form or a dedicated application. For example, this could be a form on a web browser or a smartphone application.

[0670] Next, we will explain the server. The server receives the inquiry content sent by the user and analyzes that content using a generative AI model. Specifically, the server uses natural language processing technology to properly understand the user's inquiry content and generate an optimal response based on that understanding. For example, a natural language generation AI model is used as this generative model. This model is trained using a large pre-learned dataset, and is capable of generating appropriate responses with high accuracy.

[0671] The server sends the generated response to the terminal. The terminal provides a means for presenting the response received from the server to the user. For example, the response can be displayed on a screen or read aloud. This allows users to receive real-time support 24 hours a day, 365 days a year.

[0672] Next, we will explain the operation of this system using a concrete example. When a user makes an inquiry such as "I would like to change my check-in time," the terminal receives this inquiry and sends it to the server. The server uses a generative model to analyze the inquiry and generate a response such as "To change your check-in time, please access this link." The server then sends the generated response to the terminal, which displays it to the user. In this way, the user can receive a prompt and accurate response.

[0673] For example, you might send the following prompt to a generative AI model:

[0674] "The user has asked, 'I would like to change the check-in time.' Please generate an appropriate response."

[0675] The system has the ability to maintain context based on the inquiry content and retrieve necessary information from an FAQ database. The system also operates 24 hours a day, ensuring availability at all times and reducing human error. This results in improved customer satisfaction and more efficient customer support operations.

[0676] The above is an embodiment of the present invention. The system has wide applicability and can respond to a variety of inquiries.

[0677] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0678] Step 1:

[0679] User input of query

[0680] A user accesses the customer support page using a terminal and enters their question or request. Specifically, the user enters "I would like to change my check-in time" in the text box. This entered data is treated as an inquiry to be used in the next step.

[0681] Step 2:

[0682] Sending inquiries via the device

[0683] The terminal receives the inquiry entered by the user and sends that data to the server. Specifically, the terminal sends the data "I would like to change the check-in time" to the server. At this time, a highly reliable communication method (e.g. HTTPS) is used. The user's inquiry is the input, and the data sent to the server is the output.

[0684] Step 3:

[0685] Receipt and analysis of query content by the server

[0686] The server receives the inquiry sent from the device. The server receives the inquiry "I would like to change the check-in time" and analyzes it using natural language processing technology. Specifically, the generative AI model receives a prompt sentence, "The user has inquired, 'I would like to change the check-in time.' Please generate an appropriate response.", and an appropriate response is generated. In this step, the inquiry is received as input, and the response from the generative AI model is obtained as output.

[0687] Step 4:

[0688] Server response generation

[0689] The server uses the generative AI model to generate an appropriate response to the query. For example, the generative AI model might generate a response like, "To change your check-in time, please visit this link." The input in this step is the prompt for the generative AI model, and the output is the generated response.

[0690] Step 5:

[0691] Server sends response

[0692] The server sends the generated response to the terminal. Specifically, it sends the generated response "To change your check-in time, please visit this link." to the terminal. The input in this step is the generated response, and the output is the data sent to the terminal.

[0693] Step 6:

[0694] Terminal display of responses

[0695] The terminal presents the response received from the server to the user. Specifically, it displays the text "To change your check-in time, please follow this link." on the screen. If necessary, it can also be read aloud. The input in this step is the response data sent from the server, and the output is the response content displayed to the user.

[0696] Step 7:

[0697] User response confirmation

[0698] The user checks the displayed response and takes the necessary action. Specifically, the user clicks the link displayed on the screen to change the check-in time. The input in this step is the response displayed on the terminal, and the output is the user's action.

[0699] (Application example 1)

[0700] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0701] Conventional customer support systems often delayed responses to user inquiries and sometimes failed to provide appropriate support. This was especially true for content distribution services, where users often made a wide variety of inquiries, making it difficult to respond quickly and accurately. Furthermore, ongoing support based on past inquiry history was not provided adequately, leading to lower customer satisfaction and worsening operational efficiency.

[0702] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0703] In this invention, the server includes means for receiving inquiries from users, means for having a generative model for analyzing the received inquiry, means for generating a response using the generative model and presenting the response to the user, means for sending inquiries using a smartphone and receiving the response, means for generating an appropriate response based on the inquiry in a content distribution service and presenting the response to the user, means for implementing natural language processing for analyzing the inquiry using the generative model and generating an appropriate response, and means for providing continuous support based on past inquiry history. This makes it possible to respond quickly and appropriately to user inquiries, improving customer satisfaction and streamlining customer support operations.

[0704] The "means for receiving inquiries from users" is an interface that allows users to input and send their own questions or requests.

[0705] A "server having a generative model for analyzing received inquiry content" is a server device equipped with a generative AI model for understanding the inquiry content sent by a user and generating an appropriate response.

[0706] "Means for generating a response using a generative model and presenting that response to the user" refers to a mechanism that generates an appropriate response from the results of analysis using a generative AI model and notifies the user of that response visually or audibly.

[0707] The "means for sending an inquiry and receiving a response using a smartphone" is an interface that allows a user to input an inquiry using a smartphone and receive a response to the inquiry.

[0708] "Means for generating an appropriate response based on the content of an inquiry in a content distribution service and presenting it to the user" refers to a mechanism for collecting and analyzing information related to a user's inquiry within a content distribution service, and generating and providing an appropriate response based on that information.

[0709] A "server that implements natural language processing to analyze inquiries using a generative model and generate appropriate responses" is a server that can analyze inquiries from users and generate accurate responses using a generative model and natural language processing technology.

[0710] "Means having the function of providing continuous support based on past inquiry history" refers to a mechanism that has the function of retaining the user's past inquiry history and providing continuous appropriate support based on that information.

[0711] The system for realizing this invention receives a query from a user, analyzes the query, and generates and presents an appropriate response. The system is composed of the following main components:

[0712] 1. Program Generation

[0713] The smartphone application provides an interface for users to submit queries and receive responses. When a user enters a query using their smartphone, the information is immediately sent to the server.

[0714] The server analyzes the received query using generative AI models and natural language processing techniques. As a result of the analysis, it generates an appropriate response based on the generative AI model. The server performs this processing using open-source natural language processing libraries (e.g., Spacy and NLTK) and generative AI models (e.g., OpenAI's GPT-3).

[0715] 2. Program processing explanation

[0716] Hardware and Software Use:

[0717] Hardware:

[0718] Smartphones (devices for entering and displaying user queries)

[0719] Server (a device that analyzes the query and generates a response)

[0720] software:

[0721] Smartphone application (interface for sending inquiries and displaying responses)

[0722] Generative AI model on the server (model for query analysis and response generation)

[0723] Data processing and calculation:

[0724] 1. Inquiry received:

[0725] A user uses a smartphone application to send a query and transmits the content to the server.

[0726] 2. Content analysis:

[0727] The server uses a generative AI model (such as GPT-3) to analyze the query, using natural language processing technology to understand the meaning of the query.

[0728] 3. Response generation:

[0729] Based on the analysis results, the generative AI model generates an appropriate response, taking into account past inquiry history and context.

[0730] 4. Response prompts:

[0731] The server returns the generated response to the smartphone application and presents it to the user, who can view the response on the smartphone screen.

[0732] 3. Examples of concrete examples and prompts

[0733] Examples:

[0734] When a user sends an inquiry such as "How do I use the content distribution service?", the system operates as follows.

[0735] 1. The user uses their smartphone to enter an inquiry and tap the send button.

[0736] 2. The server receives the query and the generative AI model begins analysis.

[0737] 3. The generative AI model generates a response saying, "Here's how to use our content streaming service: First, download the app and create an account. Then you can search for content that interests you and start watching."

[0738] 4. The server generates a response and sends it back to the smartphone application, which displays it to the user.

[0739] Example prompt sentence:

[0740] User Question: "How do I use the content delivery service?"

[0741] Generate an appropriate response.

[0742] In this way, the present invention realizes a system for providing quick and accurate responses to user inquiries, and provides specific means for improving user satisfaction with content distribution services.

[0743] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0744] Step 1:

[0745] The user enters a query:

[0746] The user opens the smartphone application and enters a query. For example, the input is text such as "Please tell me how to use the content distribution service." Once the input is complete, the user taps the send button. This operation sends the query from the smartphone to the server.

[0747] Step 2:

[0748] The server receives the query:

[0749] The server receives a query sent from a smartphone application. The query is received as text data. The server prepares the text data to be passed to the generative AI model for analysis.

[0750] Step 3:

[0751] Inquiry analysis:

[0752] The server inputs the received query text into a generative AI model. The generative AI model (e.g., GPT-3) uses natural language processing to analyze the query and understand its meaning. The input data is the query text, and the output data is the context and key information of the analyzed query.

[0753] Step 4:

[0754] Producing the appropriate response:

[0755] The server uses a generative AI model based on the parsed query content to generate an appropriate response. Specifically, the generative AI model generates text such as, "To use our content distribution service, first download the app and create an account. Then, you can search for content that interests you and start watching." The input data is the parsed query context, and the output data is the generated response text.

[0756] Step 5:

[0757] Sending a response:

[0758] The server sends the generated response text to the smartphone application, where the input data is the generated response text and the output data is the response text received by the smartphone application.

[0759] Step 6:

[0760] Present the response to the user:

[0761] The smartphone application visually displays the response text received from the server to the user. The user can confirm the appropriate response content on the screen. Specifically, the app screen displays the following message: "To use our content distribution service, first download the app and create an account. Then, you can search for content that interests you and start watching."

[0762] In this way, the system can provide quick and accurate responses to user inquiries.

[0763] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0764] This invention relates to a customer support system that combines a generative model and an emotion engine. This system not only generates appropriate responses to user inquiries, but also recognizes the user's emotional state and provides responses based on that, thereby realizing more personalized support.

[0765] First, a user accesses the customer support page using a device and enters their inquiry. The device receives the user's inquiry and sends it in JSON format to the server. At this time, information for analyzing the user's sentiment is also collected.

[0766] Next, we will explain the server. The server receives data sent from the terminal. The received data includes the content of the inquiry and information about the user's emotional state. The server first starts the emotion engine and analyzes the user's emotional state. The emotion engine reads the user's emotions from their vocabulary and context, and determines whether the user is angry, troubled, or happy, for example.

[0767] The server uses a generative model to analyze the query based on the emotional state obtained from the emotion engine and generate an appropriate response. The generative model uses natural language processing to provide a response with a tone and content that matches the user's emotions. For example, if the user is angry, the generative model will generate a response with a calming tone, and if the user is in trouble, it will provide a kind and easy-to-understand explanation.

[0768] The server then sends the generated response to the device, which then displays it to the user. The response can be displayed as text on the screen or read aloud, allowing the user to view it and receive help in resolving the problem.

[0769] For example, if a user inquires, "I'd like to change my check-in time," the emotion engine may recognize an irritated emotion from the user's writing style. In this case, the generative model generates a polite response such as, "We're very sorry. You can change your check-in time. Please follow this link to complete the procedure. Please let us know if you need any further assistance." The server sends this response to the device, which then displays it to the user.

[0770] This system has the ability to maintain context and quickly retrieve necessary information from an FAQ database, and operates 24 hours a day, making it available at any time. The emotion engine provides responses based on the user's emotional state, improving customer satisfaction and streamlining customer support operations. This enables the system to provide highly reliable, friendly customer support to users.

[0771] The processing flow will be explained below.

[0772] Step 1:

[0773] The terminal displays a customer support page and provides a form for the user to enter their inquiry. The user enters their inquiry into the form and clicks the submit button.

[0774] Step 2:

[0775] The device receives the user's query, packages it as JSON data, performs rudimentary sentiment analysis based on the input to interpret the user's emotional state, and then sends this data to the server as an HTTP POST request.

[0776] Step 3:

[0777] The server receives an HTTP POST request sent from the device. The request data includes the query and simple emotional information. The server then launches the emotion engine to analyze this information.

[0778] Step 4:

[0779] The server-side emotion engine analyzes the user's inquiry in detail to determine the user's emotional state, which is then classified into multiple emotion categories, such as whether the user is angry, confused, happy, etc.

[0780] Step 5:

[0781] The server then uses the generative model to analyze the query and generate an appropriate response, taking into account the emotion engine's findings and tailoring the response to the user's emotional state. For example, if the user is angry, it might use a soothing tone, or if they are confused, it might provide a friendly, easy-to-understand explanation.

[0782] Step 6:

[0783] The server packages the generated response as JSON format data and sends it to the terminal as an HTTP response.

[0784] Step 7:

[0785] The terminal analyzes the HTTP response received from the server and extracts the response content. The terminal provides an interface to display this response to the user. Specifically, the terminal displays the response content as text or reads it out loud.

[0786] Step 8:

[0787] The user can check the displayed response to get an answer to their query, and can make further queries if necessary.

[0788] Through the above processing steps, the system can provide a quick and emotional response to user inquiries, thereby improving customer satisfaction.

[0789] Example 2

[0790] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0791] Conventional customer support systems do not take the user's emotions into consideration when generating responses to user inquiries, making it difficult to provide personalized responses and improving customer satisfaction. Furthermore, there is a demand for systems that can operate 24 hours a day and respond in line with the customer's emotions.

[0792] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0793] In this invention, the server includes means for receiving a query from a user, means having an emotion engine for analyzing the emotional state of the user, means for analyzing and generating a response using a generative model based on the received query content and the emotional state, and means for presenting the generated response to the user, thereby enabling the generation of a personalized response that is in line with the user's emotions.

[0794] "User" refers to any individual or legal entity that uses the System to make an inquiry.

[0795] "Enquiry" refers to a request for information or a question that a user makes to the system for support.

[0796] "Emotion engine" refers to software or algorithms for analyzing a user's emotional state.

[0797] A "generative model" refers to an AI model that performs natural language processing based on received data and generates an appropriate response.

[0798] "Server" refers to a computing device that receives queries from users and generates responses using an emotion engine or generative model.

[0799] "Terminal" refers to a device (e.g., smartphone, PC) through which a user enters a query and receives and displays responses generated by a server.

[0800] "JSON format" is an abbreviation for JavaScript Object Notation, and is a lightweight data exchange format used as a data exchange format.

[0801] "24-hour system" refers to an operational mode in which the system operates continuously without daytime restrictions.

[0802] "Personalized response" refers to a response that is customized according to the user's inquiry and emotional state.

[0803] This invention relates to a customer support system that combines a generative model and an emotion engine. This system not only generates appropriate responses to user inquiries, but also recognizes the user's emotional state and provides responses based on that, thereby realizing more personalized support.

[0804] First, a user accesses the customer support page using a device and enters their inquiry. The device receives the user's inquiry and sends it in JSON format to the server. At this time, information for analyzing the user's sentiment is also collected.

[0805] The server receives the data sent from the terminal. The received data includes the inquiry content and information about the user's emotional state. The server first activates the emotion engine to analyze the user's emotional state. The emotion engine reads the user's emotions from their vocabulary and context, and determines whether the user is angry, troubled, or happy, for example.

[0806] The server uses a generative model to analyze the query based on the emotional state obtained from the emotion engine and generate an appropriate response. The generative model uses natural language processing to provide a response with a tone and content that matches the user's emotions. For example, if the user is angry, the generative model will generate a response with a calming tone, and if the user is in trouble, it will provide a kind and easy-to-understand explanation.

[0807] The server then sends the generated response to the device, which then displays it to the user. The response can be displayed as text on the screen or read aloud, allowing the user to view it and receive help in resolving the problem.

[0808] The specific hardware and software configuration of this system is as follows:

[0809] Emotion Engine

[0810] Software used: Python-based sentiment analysis libraries (e.g., NLTK, TextBlob)

[0811] Hardware used: Cloud server (e.g. AWS EC2)

[0812] Generative Model

[0813] Software used: Natural language processing model (e.g. GPT-3)

[0814] Hardware used: High-performance GPU servers or cloud-based AI infrastructure (e.g., Google Cloud AI, Azure AI)

[0815] Specific examples

[0816] If a user inquires, "I'd like to change my check-in time," the emotion engine may recognize an irritated emotion from the user's writing style. In this case, the generative model generates a polite response such as, "We're very sorry. You can change your check-in time. Please follow this link to complete the procedure. Please let us know if you need any further assistance." The server sends this response to the device, which then displays it to the user.

[0817] Prompt Sentence Examples

[0818] Type: "My flight has been delayed and I would like to change my check-in time. How do I do this?"

[0819] Prompt to generative AI model: "The user has inquired about changing their check-in time. Analysis from the emotion engine indicates that the user is frustrated by their flight delay. Please provide an appropriate response to calm the user."

[0820] The system aims to improve customer satisfaction by providing emotion-based responses, and is capable of operating 24 hours a day, enabling fast and accurate customer support.

[0821] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0822] Step 1:

[0823] The user accesses the customer support page using the device and enters the inquiry.

[0824] Input: The inquiry entered by the user (e.g., "I would like to change my check-in time").

[0825] Specific operation: The user opens the device's web browser or a dedicated application and enters a question into the inquiry form.

[0826] Step 2:

[0827] The device collects the inquiry content and information for sentiment analysis and sends it to the server in JSON format.

[0828] Input: The inquiry entered by the user, and information for sentiment analysis (e.g., keyboard input speed, past inquiry history).

[0829] Data processing: Convert the input content and information for sentiment analysis into JSON format.

[0830] Output: Sends the query data in JSON format to the server.

[0831] Specific operation: The device packages the query content and accompanying emotion analysis data into a single JSON object and sends it to the server via an HTTP request.

[0832] Step 3:

[0833] The server receives and parses the JSON data.

[0834] Input: JSON formatted inquiry data sent from the terminal.

[0835] Data processing: Parsing JSON data.

[0836] Output: Analyzed query content and information for sentiment analysis.

[0837] Specific operation: The server receives an HTTP request, analyzes the JSON format data, and extracts the inquiry content and information for sentiment analysis.

[0838] Step 4:

[0839] The server activates an emotion engine to analyze the user's emotional state.

[0840] Input: Parsed inquiry content and information for sentiment analysis.

[0841] Data computation: Emotional state analysis using an emotion engine (e.g., using a natural language processing library).

[0842] Output: The user's emotional state (e.g., annoyed, troubled).

[0843] Specific operation: The server uses an emotion analysis library to analyze the user's language, context, keyboard input speed, etc. to determine the user's emotional state.

[0844] Step 5:

[0845] The server uses a generative model based on the emotional state to generate an appropriate response.

[0846] Input: Parsed query content and user's emotional state.

[0847] Data Computing: Generating responses with generative models (e.g., natural language processing using GPT-3).

[0848] Output: The generated response (e.g., "Your check-in time can be changed. Please complete the process here.").

[0849] Specific operation: The server activates the generative model and generates a response with appropriate tone and content depending on the user's query content and emotional state.

[0850] Step 6:

[0851] The server sends the generated response to the terminal.

[0852] Input: The generated response.

[0853] Data processing: Convert the response into JSON format.

[0854] Output: Sends JSON formatted response data to the terminal.

[0855] Specific operation: The server converts the generated response into JSON format and sends it to the terminal as an HTTP response.

[0856] Step 7:

[0857] The terminal displays the generated response to the user.

[0858] Input: JSON formatted response data sent from the server.

[0859] Data processing: Parse the JSON data to extract the text response.

[0860] Output: The response text or audio that is displayed to the user.

[0861] Specific operation: The device parses the JSON format response data and displays it as text on a web page or application, or reads it aloud using speech synthesis.

[0862] (Application example 2)

[0863] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0864] Conventional customer support systems often provide uniform responses without considering the user's emotional state, which can lead to lower user satisfaction and ineffective support. It is also difficult to provide appropriate responses depending on the user's emotions, such as distress or anger, making it necessary to improve the quality of customer support.

[0865] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving an inquiry from a user, means having a generative model and an emotion engine for analyzing the content of the received inquiry and the user's emotional state, and means for the server to generate a response based on the user's emotional state using the generative model and present the response to the user. This enables a personalized response tailored to the user's emotions, making it possible to improve the quality of customer support and user satisfaction.

[0866] The "means for receiving an inquiry from a user" is a mechanism for transmitting the contents of an inquiry entered by a user using a terminal to a server.

[0867] The "server with a generative model and emotion engine for analyzing the received inquiry content and the user's emotional state" is a server that has the function of analyzing questions from users and reading emotions from wording and context.

[0868] "Means for using a generative model to generate a response based on the user's emotional state and presenting that response to the user" is a mechanism for automatically generating a response that takes the user's emotions into consideration and displaying or communicating that response to the user.

[0869] The present invention is a customer support system that analyzes the content of a user's inquiry and emotional state and generates a personalized response according to the user's emotion. This system includes a mechanism in which a user makes an inquiry using a device such as a smartphone, and the content of the inquiry is processed by a server.

[0870] Hardware and software used

[0871] Hardware

[0872] Smartphone: Devices running iOS or Android OS

[0873] Server: A cloud server with suitable capabilities (e.g., AWS EC2 server)

[0874] Network equipment: Infrastructure equipment for data communication from terminals to servers

[0875] software

[0876] Emotion engine: IBM Watson Tone Analyzer

[0877] Generative model: OpenAI GPT-4

[0878] API communication framework: Flask (Python library)

[0879] Data processing and calculation

[0880] Users access customer support using their smartphones and input their inquiries, which are then sent to the server in JSON format, while also collecting data on the user's emotions.

[0881] The server first uses an emotion engine (IBM Watson Tone Analyzer) to analyze the user's emotional state from the content of the user's inquiry. The emotion engine analyzes the tone and context of the language and determines whether the user is happy, troubled, or angry.

[0882] Next, a generative model (OpenAI GPT-4) is used to generate a response based on the analyzed emotional state. The generative model creates appropriate prompts taking the emotional state into account and generates a response to the user based on that. This response is sent in text format from the server to the device and displayed on the screen.

[0883] Specific examples

[0884] Suppose a user makes a query such as, "My delivery is late and I'm worried. What's going on?" The device sends this query to the server, which analyzes it with its emotion engine and detects that the user is worried. The generative model takes this emotion into account and generates a response using the following prompt:

[0885] Prompt Sentence Examples

[0886] User Emotion: Anxiety

[0887] Enquiry: I'm worried about the delay in delivery. What's going on?

[0888] Appropriate response:

[0889] The generative model responds by generating the following sentence: "We are very sorry. It appears that delivery is currently delayed. We are currently investigating the details, so please wait a little longer. If you have any complaints, could you please contact customer support directly?" This response is sent from the server to the device, and the user can check it on their smartphone.

[0890] In this way, personalized responses tailored to the user's emotions are provided, thereby improving the quality of customer support and user satisfaction.

[0891] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0892] Step 1:

[0893] The user uses the device to input a query to customer support. For example, the input might be, "My delivery is delayed and I'm worried. What's going on?" The user's input is stored on the device as JSON-formatted data and awaits transmission to the server.

[0894] Input: User's inquiry (e.g. "My delivery is late and I'm worried. What's going on?")

[0895] Output: The query content is saved in JSON format on the terminal.

[0896] Step 2:

[0897] The device sends the user's query to the server in JSON format. The device also collects data on the user's emotions and sends it to the server.

[0898] Input: JSON formatted query content, data on user emotions (e.g., voice tone information, keyboard input speed, etc.)

[0899] Output: JSON format data is sent to the server

[0900] Step 3:

[0901] The server analyzes the JSON data received from the device. First, it launches the emotion engine (IBM Watson Tone Analyzer) to analyze the user's inquiry and identify their emotional state. The emotion engine reads the user's emotions from their text and determines whether they are worried, angry, confused, etc.

[0902] Input: JSON data received from the terminal

[0903] Output: Parsed emotional state (e.g., "worried")

[0904] Step 4:

[0905] The server generates an appropriate response based on the analyzed emotional state using a generative model (OpenAI GPT-4). The generative model receives prompts based on specific emotions and generates a response based on them.

[0906] Input: Analyzed emotional state, inquiry content

[0907] Output: The response generated by the generative model (e.g., "We're very sorry, but it appears your delivery is currently delayed. We're currently investigating the details, so please be patient. If you're unhappy, could you please contact customer support directly?")

[0908] Step 5:

[0909] The server then sends the generated response back to the device in JSON format. The device then analyzes the response data received from the server and displays it on the screen or reads it out loud, allowing the user to check the response to their query.

[0910] Input: The generated response JSON data sent from the server

[0911] Output: The response displayed on the device screen or read aloud

[0912] Step 6:

[0913] The user checks the responses provided by the terminal and makes additional inquiries as needed. By repeating this cycle, the system continuously provides answers to the user's inquiries.

[0914] Input: The response displayed on the device screen or read aloud

[0915] Output: User confirmation and further prompts

[0916] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0917] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0918] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[0919] [Fourth embodiment]

[0920] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0921] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0922] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0923] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0924] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0925] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0926] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0927] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0928] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0929] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0930] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0931] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0932] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0933] This invention describes a customer support system that uses generative models to receive inquiries from users, analyze the inquiries, and generate and present appropriate responses.

[0934] First, we will describe the terminal in this system. Users use the terminal to access the customer support page and enter their questions or requests. The terminal provides an interface to receive the user's inquiry and send it to the server for analysis and response generation. This interface may be implemented as a web form or a dedicated application.

[0935] Next, we will explain the server. The server receives the inquiry content sent by the user and analyzes that content using a generative model. Specifically, the server uses natural language processing to properly understand the user's inquiry content and generate an optimal response based on that understanding. For example, a generative AI model is used as this generative model. This generative model is trained using a pre-learned dataset and is capable of generating appropriate responses with high accuracy.

[0936] The server sends the generated response to the terminal. The terminal provides a means for presenting the response received from the server to the user. For example, the response can be displayed on a screen or read aloud. This allows users to receive real-time support 24 hours a day, 365 days a year.

[0937] Next, we will explain the operation of this system using a concrete example. When a user makes an inquiry such as "I would like to change my check-in time," the terminal receives this inquiry and sends it to the server. The server uses a generative model to analyze the inquiry and generate a response such as "To change your check-in time, please access this link." The server then sends the generated response to the terminal, which displays it to the user. In this way, the user can receive a prompt and accurate response.

[0938] The system has the ability to maintain context based on the inquiry content and retrieve necessary information from an FAQ database. The system also operates 24 hours a day, ensuring availability at all times and reducing human error. This results in improved customer satisfaction and more efficient customer support operations.

[0939] The above is a description of the mode for carrying out the invention. The present system is useful in that it has a wide range of applicability and can respond to a variety of inquiries.

[0940] The processing flow will be explained below.

[0941] Step 1:

[0942] The terminal displays a customer support page and provides a form for the user to enter their inquiry. The user enters their inquiry into the form and clicks the submit button.

[0943] Step 2:

[0944] The device receives the query entered by the user, packages it as JSON-formatted data for processing, and then sends the data to the server as an HTTP POST request.

[0945] Step 3:

[0946] The server receives an HTTP POST request sent from the device, extracts the query content from the request, and passes it to the generative model for analysis.

[0947] Step 4:

[0948] A generative model on the server analyzes the query and generates an appropriate response. This generative model is pre-trained with a large amount of data, enabling highly accurate natural language processing.

[0949] Step 5:

[0950] The server receives the response generated by the generative model, packages it again as JSON-formatted data, and sends this response data to the terminal as an HTTP response.

[0951] Step 6:

[0952] The terminal analyzes the HTTP response received from the server, extracts the response content, and provides an interface for displaying the extracted response content to the user.

[0953] Step 7:

[0954] The terminal displays the response to the user, who can then confirm the response, completing the response to the user's inquiry.

[0955] Example 1

[0956] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0957] Conventional customer support systems often had slow responses to inquiries, which led to lower user satisfaction. Furthermore, they often relied on human intervention, making it difficult to provide 24-hour support. Furthermore, it was difficult to generate appropriate responses to inquiries, which sometimes led to inefficient support.

[0958] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0959] In this invention, the server includes a means for receiving inquiries from users, a means having a generative model using natural language processing technology for analyzing the content of the received inquiry, and a terminal for generating a response using the generative model and presenting the response to the user. This enables the generation of quick and appropriate responses to inquiries, realizing efficient customer support around the clock.

[0960] A "user" is a person or organization that uses the system to make an inquiry.

[0961] An "inquiry" is information about a question or request that a user enters through the system.

[0962] A "terminal" is an electronic device used by a user to enter inquiries and receive responses, and includes personal computers, smartphones, tablets, and the like.

[0963] The "server" is a central processing unit that receives the contents of an inquiry sent by a user, analyzes it, generates a response, and sends it to the terminal.

[0964] "Natural language processing technology" is a technology for converting the content of inquiries entered by users into a format that is easy for machines to understand and analyzing it.

[0965] A "generative model" is an algorithm that uses a pre-trained dataset to generate appropriate responses to user queries.

[0966] A "response" is information or instructions that the server generates in response to a user's query using a generative model and that are presented to the user via the terminal.

[0967] "24-hour system" means that the system operates continuously 24 hours a day, seven days a week, and is able to respond to user inquiries at any time.

[0968] This invention describes a customer support system that uses a generative AI model to receive inquiries from users, analyze the inquiries, and generate and present appropriate responses.

[0969] First, we will explain the terminals in this system. Users use the terminals to access the customer support page and enter their questions or requests. The terminals provide an interface for receiving the user's inquiries and sending them to the server for analysis and response generation. This interface may be implemented as a web form or a dedicated application. For example, this could be a form on a web browser or a smartphone application.

[0970] Next, we will explain the server. The server receives the inquiry content sent by the user and analyzes that content using a generative AI model. Specifically, the server uses natural language processing technology to properly understand the user's inquiry content and generate an optimal response based on that understanding. For example, a natural language generation AI model is used as this generative model. This model is trained using a large pre-learned dataset, and is capable of generating appropriate responses with high accuracy.

[0971] The server sends the generated response to the terminal. The terminal provides a means for presenting the response received from the server to the user. For example, the response can be displayed on a screen or read aloud. This allows users to receive real-time support 24 hours a day, 365 days a year.

[0972] Next, we will explain the operation of this system using a concrete example. When a user makes an inquiry such as "I would like to change my check-in time," the terminal receives this inquiry and sends it to the server. The server uses a generative model to analyze the inquiry and generate a response such as "To change your check-in time, please access this link." The server then sends the generated response to the terminal, which displays it to the user. In this way, the user can receive a prompt and accurate response.

[0973] For example, you might send the following prompt to a generative AI model:

[0974] "The user has asked, 'I would like to change the check-in time.' Please generate an appropriate response."

[0975] The system has the ability to maintain context based on the inquiry content and retrieve necessary information from an FAQ database. The system also operates 24 hours a day, ensuring availability at all times and reducing human error. This results in improved customer satisfaction and more efficient customer support operations.

[0976] The above is an embodiment of the present invention. The system has wide applicability and can respond to a variety of inquiries.

[0977] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0978] Step 1:

[0979] User input of query

[0980] A user accesses the customer support page using a terminal and enters their question or request. Specifically, the user enters "I would like to change my check-in time" in the text box. This entered data is treated as an inquiry to be used in the next step.

[0981] Step 2:

[0982] Sending inquiries via the device

[0983] The terminal receives the inquiry entered by the user and sends that data to the server. Specifically, the terminal sends the data "I would like to change the check-in time" to the server. At this time, a highly reliable communication method (e.g. HTTPS) is used. The user's inquiry is the input, and the data sent to the server is the output.

[0984] Step 3:

[0985] Receipt and analysis of query content by the server

[0986] The server receives the inquiry sent from the device. The server receives the inquiry "I would like to change the check-in time" and analyzes it using natural language processing technology. Specifically, the generative AI model receives a prompt sentence, "The user has inquired, 'I would like to change the check-in time.' Please generate an appropriate response.", and an appropriate response is generated. In this step, the inquiry is received as input, and the response from the generative AI model is obtained as output.

[0987] Step 4:

[0988] Server response generation

[0989] The server uses the generative AI model to generate an appropriate response to the query. For example, the generative AI model might generate a response like, "To change your check-in time, please visit this link." The input in this step is the prompt for the generative AI model, and the output is the generated response.

[0990] Step 5:

[0991] Server sends response

[0992] The server sends the generated response to the terminal. Specifically, it sends the generated response "To change your check-in time, please visit this link." to the terminal. The input in this step is the generated response, and the output is the data sent to the terminal.

[0993] Step 6:

[0994] Terminal display of responses

[0995] The terminal presents the response received from the server to the user. Specifically, it displays the text "To change your check-in time, please follow this link." on the screen. If necessary, it can also be read aloud. The input in this step is the response data sent from the server, and the output is the response content displayed to the user.

[0996] Step 7:

[0997] User response confirmation

[0998] The user checks the displayed response and takes the necessary action. Specifically, the user clicks the link displayed on the screen to change the check-in time. The input in this step is the response displayed on the terminal, and the output is the user's action.

[0999] (Application example 1)

[1000] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1001] Conventional customer support systems often delayed responses to user inquiries and sometimes failed to provide appropriate support. This was especially true for content distribution services, where users often made a wide variety of inquiries, making it difficult to respond quickly and accurately. Furthermore, ongoing support based on past inquiry history was not provided adequately, leading to lower customer satisfaction and worsening operational efficiency.

[1002] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1003] In this invention, the server includes means for receiving inquiries from users, means for having a generative model for analyzing the received inquiry, means for generating a response using the generative model and presenting the response to the user, means for sending inquiries using a smartphone and receiving the response, means for generating an appropriate response based on the inquiry in a content distribution service and presenting the response to the user, means for implementing natural language processing for analyzing the inquiry using the generative model and generating an appropriate response, and means for providing continuous support based on past inquiry history. This makes it possible to respond quickly and appropriately to user inquiries, improving customer satisfaction and streamlining customer support operations.

[1004] The "means for receiving inquiries from users" is an interface that allows users to input and send their own questions or requests.

[1005] A "server having a generative model for analyzing received inquiry content" is a server device equipped with a generative AI model for understanding the inquiry content sent by a user and generating an appropriate response.

[1006] "Means for generating a response using a generative model and presenting that response to the user" refers to a mechanism that generates an appropriate response from the results of analysis using a generative AI model and notifies the user of that response visually or audibly.

[1007] The "means for sending an inquiry and receiving a response using a smartphone" is an interface that allows a user to input an inquiry using a smartphone and receive a response to the inquiry.

[1008] "Means for generating an appropriate response based on the content of an inquiry in a content distribution service and presenting it to the user" refers to a mechanism for collecting and analyzing information related to a user's inquiry within a content distribution service, and generating and providing an appropriate response based on that information.

[1009] A "server that implements natural language processing to analyze inquiries using a generative model and generate appropriate responses" is a server that can analyze inquiries from users and generate accurate responses using a generative model and natural language processing technology.

[1010] "Means having the function of providing continuous support based on past inquiry history" refers to a mechanism that has the function of retaining the user's past inquiry history and providing continuous appropriate support based on that information.

[1011] The system for realizing this invention receives a query from a user, analyzes the query, and generates and presents an appropriate response. The system is composed of the following main components:

[1012] 1. Program Generation

[1013] The smartphone application provides an interface for users to submit queries and receive responses. When a user enters a query using their smartphone, the information is immediately sent to the server.

[1014] The server analyzes the received query using generative AI models and natural language processing techniques. As a result of the analysis, it generates an appropriate response based on the generative AI model. The server performs this processing using open-source natural language processing libraries (e.g., Spacy and NLTK) and generative AI models (e.g., OpenAI's GPT-3).

[1015] 2. Program processing explanation

[1016] Hardware and Software Use:

[1017] Hardware:

[1018] Smartphones (devices for entering and displaying user queries)

[1019] Server (a device that analyzes the query and generates a response)

[1020] software:

[1021] Smartphone application (interface for sending inquiries and displaying responses)

[1022] Generative AI model on the server (model for query analysis and response generation)

[1023] Data processing and calculation:

[1024] 1. Inquiry received:

[1025] A user uses a smartphone application to send a query and transmits the content to the server.

[1026] 2. Content analysis:

[1027] The server uses a generative AI model (such as GPT-3) to analyze the query, using natural language processing technology to understand the meaning of the query.

[1028] 3. Response generation:

[1029] Based on the analysis results, the generative AI model generates an appropriate response, taking into account past inquiry history and context.

[1030] 4. Response prompts:

[1031] The server returns the generated response to the smartphone application and presents it to the user, who can view the response on the smartphone screen.

[1032] 3. Examples of concrete examples and prompts

[1033] Examples:

[1034] When a user sends an inquiry such as "How do I use the content distribution service?", the system operates as follows.

[1035] 1. The user uses their smartphone to enter an inquiry and tap the send button.

[1036] 2. The server receives the query and the generative AI model begins analysis.

[1037] 3. The generative AI model generates a response saying, "Here's how to use our content streaming service: First, download the app and create an account. Then you can search for content that interests you and start watching."

[1038] 4. The server generates a response and sends it back to the smartphone application, which displays it to the user.

[1039] Example prompt sentence:

[1040] User Question: "How do I use the content delivery service?"

[1041] Generate an appropriate response.

[1042] In this way, the present invention realizes a system for providing quick and accurate responses to user inquiries, and provides specific means for improving user satisfaction with content distribution services.

[1043] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1044] Step 1:

[1045] The user enters a query:

[1046] The user opens the smartphone application and enters a query. For example, the input is text such as "Please tell me how to use the content distribution service." Once the input is complete, the user taps the send button. This operation sends the query from the smartphone to the server.

[1047] Step 2:

[1048] The server receives the query:

[1049] The server receives a query sent from a smartphone application. The query is received as text data. The server prepares the text data to be passed to the generative AI model for analysis.

[1050] Step 3:

[1051] Inquiry analysis:

[1052] The server inputs the received query text into a generative AI model. The generative AI model (e.g., GPT-3) uses natural language processing to analyze the query and understand its meaning. The input data is the query text, and the output data is the context and key information of the analyzed query.

[1053] Step 4:

[1054] Producing the appropriate response:

[1055] The server uses a generative AI model based on the parsed query content to generate an appropriate response. Specifically, the generative AI model generates text such as, "To use our content distribution service, first download the app and create an account. Then, you can search for content that interests you and start watching." The input data is the parsed query context, and the output data is the generated response text.

[1056] Step 5:

[1057] Sending a response:

[1058] The server sends the generated response text to the smartphone application, where the input data is the generated response text and the output data is the response text received by the smartphone application.

[1059] Step 6:

[1060] Present the response to the user:

[1061] The smartphone application visually displays the response text received from the server to the user. The user can confirm the appropriate response content on the screen. Specifically, the app screen displays the following message: "To use our content distribution service, first download the app and create an account. Then, you can search for content that interests you and start watching."

[1062] In this way, the system can provide quick and accurate responses to user inquiries.

[1063] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1064] This invention relates to a customer support system that combines a generative model and an emotion engine. This system not only generates appropriate responses to user inquiries, but also recognizes the user's emotional state and provides responses based on that, thereby realizing more personalized support.

[1065] First, a user accesses the customer support page using a device and enters their inquiry. The device receives the user's inquiry and sends it in JSON format to the server. At this time, information for analyzing the user's sentiment is also collected.

[1066] Next, we will explain the server. The server receives data sent from the terminal. The received data includes the content of the inquiry and information about the user's emotional state. The server first starts the emotion engine and analyzes the user's emotional state. The emotion engine reads the user's emotions from their vocabulary and context, and determines whether the user is angry, troubled, or happy, for example.

[1067] The server uses a generative model to analyze the query based on the emotional state obtained from the emotion engine and generate an appropriate response. The generative model uses natural language processing to provide a response with a tone and content that matches the user's emotions. For example, if the user is angry, the generative model will generate a response with a calming tone, and if the user is in trouble, it will provide a kind and easy-to-understand explanation.

[1068] The server then sends the generated response to the device, which then displays it to the user. The response can be displayed as text on the screen or read aloud, allowing the user to view it and receive help in resolving the problem.

[1069] For example, if a user inquires, "I'd like to change my check-in time," the emotion engine may recognize an irritated emotion from the user's writing style. In this case, the generative model generates a polite response such as, "We're very sorry. You can change your check-in time. Please follow this link to complete the procedure. Please let us know if you need any further assistance." The server sends this response to the device, which then displays it to the user.

[1070] This system has the ability to maintain context and quickly retrieve necessary information from an FAQ database, and operates 24 hours a day, making it available at any time. The emotion engine provides responses based on the user's emotional state, improving customer satisfaction and streamlining customer support operations. This enables the system to provide highly reliable, friendly customer support to users.

[1071] The processing flow will be explained below.

[1072] Step 1:

[1073] The terminal displays a customer support page and provides a form for the user to enter their inquiry. The user enters their inquiry into the form and clicks the submit button.

[1074] Step 2:

[1075] The device receives the user's query, packages it as JSON data, performs rudimentary sentiment analysis based on the input to interpret the user's emotional state, and then sends this data to the server as an HTTP POST request.

[1076] Step 3:

[1077] The server receives an HTTP POST request sent from the device. The request data includes the query and simple emotional information. The server then launches the emotion engine to analyze this information.

[1078] Step 4:

[1079] The server-side emotion engine analyzes the user's inquiry in detail to determine the user's emotional state, which is then classified into multiple emotion categories, such as whether the user is angry, confused, happy, etc.

[1080] Step 5:

[1081] The server then uses the generative model to analyze the query and generate an appropriate response, taking into account the emotion engine's findings and tailoring the response to the user's emotional state. For example, if the user is angry, it might use a soothing tone, or if they are confused, it might provide a friendly, easy-to-understand explanation.

[1082] Step 6:

[1083] The server packages the generated response as JSON format data and sends it to the terminal as an HTTP response.

[1084] Step 7:

[1085] The terminal analyzes the HTTP response received from the server and extracts the response content. The terminal provides an interface to display this response to the user. Specifically, the terminal displays the response content as text or reads it out loud.

[1086] Step 8:

[1087] The user can check the displayed response to get an answer to their query, and can make further queries if necessary.

[1088] Through the above processing steps, the system can provide a quick and emotional response to user inquiries, thereby improving customer satisfaction.

[1089] Example 2

[1090] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1091] Conventional customer support systems do not take the user's emotions into consideration when generating responses to user inquiries, making it difficult to provide personalized responses and improving customer satisfaction. Furthermore, there is a demand for systems that can operate 24 hours a day and respond in line with the customer's emotions.

[1092] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1093] In this invention, the server includes means for receiving a query from a user, means having an emotion engine for analyzing the emotional state of the user, means for analyzing and generating a response using a generative model based on the received query content and the emotional state, and means for presenting the generated response to the user, thereby enabling the generation of a personalized response that is in line with the user's emotions.

[1094] "User" refers to any individual or legal entity that uses the System to make an inquiry.

[1095] "Enquiry" refers to a request for information or a question that a user makes to the system for support.

[1096] "Emotion engine" refers to software or algorithms for analyzing a user's emotional state.

[1097] A "generative model" refers to an AI model that performs natural language processing based on received data and generates an appropriate response.

[1098] "Server" refers to a computing device that receives queries from users and generates responses using an emotion engine or generative model.

[1099] "Terminal" refers to a device (e.g., smartphone, PC) through which a user enters a query and receives and displays responses generated by a server.

[1100] "JSON format" is an abbreviation for JavaScript Object Notation, and is a lightweight data exchange format used as a data exchange format.

[1101] "24-hour system" refers to an operational mode in which the system operates continuously without daytime restrictions.

[1102] "Personalized response" refers to a response that is customized according to the user's inquiry and emotional state.

[1103] This invention relates to a customer support system that combines a generative model and an emotion engine. This system not only generates appropriate responses to user inquiries, but also recognizes the user's emotional state and provides responses based on that, thereby realizing more personalized support.

[1104] First, a user accesses the customer support page using a device and enters their inquiry. The device receives the user's inquiry and sends it in JSON format to the server. At this time, information for analyzing the user's sentiment is also collected.

[1105] The server receives the data sent from the terminal. The received data includes the inquiry content and information about the user's emotional state. The server first activates the emotion engine to analyze the user's emotional state. The emotion engine reads the user's emotions from their vocabulary and context, and determines whether the user is angry, troubled, or happy, for example.

[1106] The server uses a generative model to analyze the query based on the emotional state obtained from the emotion engine and generate an appropriate response. The generative model uses natural language processing to provide a response with a tone and content that matches the user's emotions. For example, if the user is angry, the generative model will generate a response with a calming tone, and if the user is in trouble, it will provide a kind and easy-to-understand explanation.

[1107] The server then sends the generated response to the device, which then displays it to the user. The response can be displayed as text on the screen or read aloud, allowing the user to view it and receive help in resolving the problem.

[1108] The specific hardware and software configuration of this system is as follows:

[1109] Emotion Engine

[1110] Software used: Python-based sentiment analysis libraries (e.g., NLTK, TextBlob)

[1111] Hardware used: Cloud server (e.g. AWS EC2)

[1112] Generative Model

[1113] Software used: Natural language processing model (e.g. GPT-3)

[1114] Hardware used: High-performance GPU servers or cloud-based AI infrastructure (e.g., Google Cloud AI, Azure AI)

[1115] Specific examples

[1116] If a user inquires, "I'd like to change my check-in time," the emotion engine may recognize an irritated emotion from the user's writing style. In this case, the generative model generates a polite response such as, "We're very sorry. You can change your check-in time. Please follow this link to complete the procedure. Please let us know if you need any further assistance." The server sends this response to the device, which then displays it to the user.

[1117] Prompt Sentence Examples

[1118] Type: "My flight has been delayed and I would like to change my check-in time. How do I do this?"

[1119] Prompt to generative AI model: "The user has inquired about changing their check-in time. Analysis from the emotion engine indicates that the user is frustrated by their flight delay. Please provide an appropriate response to calm the user."

[1120] The system aims to improve customer satisfaction by providing emotion-based responses, and is capable of operating 24 hours a day, enabling fast and accurate customer support.

[1121] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1122] Step 1:

[1123] The user accesses the customer support page using the device and enters the inquiry.

[1124] Input: The inquiry entered by the user (e.g., "I would like to change my check-in time").

[1125] Specific operation: The user opens the device's web browser or a dedicated application and enters a question into the inquiry form.

[1126] Step 2:

[1127] The device collects the inquiry content and information for sentiment analysis and sends it to the server in JSON format.

[1128] Input: The inquiry entered by the user, and information for sentiment analysis (e.g., keyboard input speed, past inquiry history).

[1129] Data processing: Convert the input content and information for sentiment analysis into JSON format.

[1130] Output: Sends the query data in JSON format to the server.

[1131] Specific operation: The device packages the query content and accompanying emotion analysis data into a single JSON object and sends it to the server via an HTTP request.

[1132] Step 3:

[1133] The server receives and parses the JSON data.

[1134] Input: JSON formatted inquiry data sent from the terminal.

[1135] Data processing: Parsing JSON data.

[1136] Output: Analyzed query content and information for sentiment analysis.

[1137] Specific operation: The server receives an HTTP request, analyzes the JSON format data, and extracts the inquiry content and information for sentiment analysis.

[1138] Step 4:

[1139] The server activates an emotion engine to analyze the user's emotional state.

[1140] Input: Parsed inquiry content and information for sentiment analysis.

[1141] Data computation: Emotional state analysis using an emotion engine (e.g., using a natural language processing library).

[1142] Output: The user's emotional state (e.g., annoyed, troubled).

[1143] Specific operation: The server uses an emotion analysis library to analyze the user's language, context, keyboard input speed, etc. to determine the user's emotional state.

[1144] Step 5:

[1145] The server uses a generative model based on the emotional state to generate an appropriate response.

[1146] Input: Parsed query content and user's emotional state.

[1147] Data Computing: Generating responses with generative models (e.g., natural language processing using GPT-3).

[1148] Output: The generated response (e.g., "Your check-in time can be changed. Please complete the process here.").

[1149] Specific operation: The server activates the generative model and generates a response with appropriate tone and content depending on the user's query content and emotional state.

[1150] Step 6:

[1151] The server sends the generated response to the terminal.

[1152] Input: The generated response.

[1153] Data processing: Convert the response into JSON format.

[1154] Output: Sends JSON formatted response data to the terminal.

[1155] Specific operation: The server converts the generated response into JSON format and sends it to the terminal as an HTTP response.

[1156] Step 7:

[1157] The terminal displays the generated response to the user.

[1158] Input: JSON formatted response data sent from the server.

[1159] Data processing: Parse the JSON data to extract the text response.

[1160] Output: The response text or audio that is displayed to the user.

[1161] Specific operation: The device parses the JSON format response data and displays it as text on a web page or application, or reads it aloud using speech synthesis.

[1162] (Application example 2)

[1163] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1164] Conventional customer support systems often provide uniform responses without considering the user's emotional state, which can lead to lower user satisfaction and ineffective support. It is also difficult to provide appropriate responses depending on the user's emotions, such as distress or anger, making it necessary to improve the quality of customer support.

[1165] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving an inquiry from a user, means having a generative model and an emotion engine for analyzing the content of the received inquiry and the user's emotional state, and means for the server to generate a response based on the user's emotional state using the generative model and present the response to the user. This enables a personalized response tailored to the user's emotions, making it possible to improve the quality of customer support and user satisfaction.

[1166] The "means for receiving an inquiry from a user" is a mechanism for transmitting the contents of an inquiry entered by a user using a terminal to a server.

[1167] The "server with a generative model and emotion engine for analyzing the received inquiry content and the user's emotional state" is a server that has the function of analyzing questions from users and reading emotions from wording and context.

[1168] "Means for using a generative model to generate a response based on the user's emotional state and presenting that response to the user" is a mechanism for automatically generating a response that takes the user's emotions into consideration and displaying or communicating that response to the user.

[1169] The present invention is a customer support system that analyzes the content of a user's inquiry and emotional state and generates a personalized response according to the user's emotion. This system includes a mechanism in which a user makes an inquiry using a device such as a smartphone, and the content of the inquiry is processed by a server.

[1170] Hardware and software used

[1171] Hardware

[1172] Smartphone: Devices running iOS or Android OS

[1173] Server: A cloud server with suitable capabilities (e.g., AWS EC2 server)

[1174] Network equipment: Infrastructure equipment for data communication from terminals to servers

[1175] software

[1176] Emotion engine: IBM Watson Tone Analyzer

[1177] Generative model: OpenAI GPT-4

[1178] API communication framework: Flask (Python library)

[1179] Data processing and calculation

[1180] Users access customer support using their smartphones and input their inquiries, which are then sent to the server in JSON format, while also collecting data on the user's emotions.

[1181] The server first uses an emotion engine (IBM Watson Tone Analyzer) to analyze the user's emotional state from the content of the user's inquiry. The emotion engine analyzes the tone and context of the language and determines whether the user is happy, troubled, or angry.

[1182] Next, a generative model (OpenAI GPT-4) is used to generate a response based on the analyzed emotional state. The generative model creates appropriate prompts taking the emotional state into account and generates a response to the user based on that. This response is sent in text format from the server to the device and displayed on the screen.

[1183] Specific examples

[1184] Suppose a user makes a query such as, "My delivery is late and I'm worried. What's going on?" The device sends this query to the server, which analyzes it with its emotion engine and detects that the user is worried. The generative model takes this emotion into account and generates a response using the following prompt:

[1185] Prompt Sentence Examples

[1186] User Emotion: Anxiety

[1187] Enquiry: I'm worried about the delay in delivery. What's going on?

[1188] Appropriate response:

[1189] The generative model responds by generating the following sentence: "We are very sorry. It appears that delivery is currently delayed. We are currently investigating the details, so please wait a little longer. If you have any complaints, could you please contact customer support directly?" This response is sent from the server to the device, and the user can check it on their smartphone.

[1190] In this way, personalized responses tailored to the user's emotions are provided, thereby improving the quality of customer support and user satisfaction.

[1191] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1192] Step 1:

[1193] The user uses the device to input a query to customer support. For example, the input might be, "My delivery is delayed and I'm worried. What's going on?" The user's input is stored on the device as JSON-formatted data and awaits transmission to the server.

[1194] Input: User's inquiry (e.g. "My delivery is late and I'm worried. What's going on?")

[1195] Output: The query content is saved in JSON format on the terminal.

[1196] Step 2:

[1197] The device sends the user's query to the server in JSON format. The device also collects data on the user's emotions and sends it to the server.

[1198] Input: JSON formatted query content, data on user emotions (e.g., voice tone information, keyboard input speed, etc.)

[1199] Output: JSON format data is sent to the server

[1200] Step 3:

[1201] The server analyzes the JSON data received from the device. First, it launches the emotion engine (IBM Watson Tone Analyzer) to analyze the user's inquiry and identify their emotional state. The emotion engine reads the user's emotions from their text and determines whether they are worried, angry, confused, etc.

[1202] Input: JSON data received from the terminal

[1203] Output: Parsed emotional state (e.g., "worried")

[1204] Step 4:

[1205] The server generates an appropriate response based on the analyzed emotional state using a generative model (OpenAI GPT-4). The generative model receives prompts based on specific emotions and generates a response based on them.

[1206] Input: Analyzed emotional state, inquiry content

[1207] Output: The response generated by the generative model (e.g., "We're very sorry, but it appears your delivery is currently delayed. We're currently investigating the details, so please be patient. If you're unhappy, could you please contact customer support directly?")

[1208] Step 5:

[1209] The server then sends the generated response back to the device in JSON format. The device then analyzes the response data received from the server and displays it on the screen or reads it out loud, allowing the user to check the response to their query.

[1210] Input: The generated response JSON data sent from the server

[1211] Output: The response displayed on the device screen or read aloud

[1212] Step 6:

[1213] The user checks the responses provided by the terminal and makes additional inquiries as needed. By repeating this cycle, the system continuously provides answers to the user's inquiries.

[1214] Input: The response displayed on the device screen or read aloud

[1215] Output: User confirmation and further prompts

[1216] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1217] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1218] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1219] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1220] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1221] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1222] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1223] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1224] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1225] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1226] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1227] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1228] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1229] 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.

[1230] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1231] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1232] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1233] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1234] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1235] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1236] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1237] The following is further disclosed regarding the above embodiment.

[1238] (Claim 1)

[1239] means for receiving a query from a user;

[1240] a server having a generative model for analyzing received queries;

[1241] means for the server to generate a response using the generative model and present the response to the user;

[1242] A system including:

[1243] (Claim 2)

[1244] 10. The system of claim 1, which operates 24 hours a day.

[1245] (Claim 3)

[1246] 2. The system according to claim 1, further comprising a terminal for transmitting a query to the server and displaying a response to the user.

[1247] (Claim 4)

[1248] 2. The system according to claim 1, wherein the generative model that analyzes the content of a query and generates a response uses natural language processing.

[1249] (Claim 5)

[1250] 10. The system of claim 1, further comprising means for maintaining a context based on the query content for response generation.

[1251] (Claim 6)

[1252] 2. The system according to claim 1, further comprising means for responding to an inquiry and obtaining information from an FAQ database.

[1253] "Example 1"

[1254] (Claim 1)

[1255] means for receiving a query from a user;

[1256] a server having a generative model using natural language processing technology for analyzing the content of a received inquiry;

[1257] a terminal for the server to generate a response using the generative model and present the response to a user;

[1258] A system including:

[1259] (Claim 2)

[1260] 10. The system of claim 1, which operates 24 hours a day.

[1261] (Claim 3)

[1262] 2. The system according to claim 1, further comprising a terminal for transmitting a query to the server and displaying a response received from the server to the user.

[1263] "Application Example 1"

[1264] (Claim 1)

[1265] means for receiving a query from a user;

[1266] a server having a generative model for analyzing received queries;

[1267] means for the server to generate a response using the generative model and present the response to the user;

[1268] a means for sending inquiries and receiving responses using a smartphone;

[1269] a means for generating an appropriate response based on the inquiry content in the content distribution service and presenting the response to the user;

[1270] a server that implements natural language processing to analyze the content of inquiries using a generative model and generate appropriate responses;

[1271] A means having a function of providing continuous support based on past inquiry history;

[1272] A system including:

[1273] (Claim 2)

[1274] 10. The system of claim 1, which operates 24 hours a day.

[1275] (Claim 3)

[1276] 2. The system according to claim 1, further comprising a terminal for transmitting a query to the server and displaying a response to the user.

[1277] "Example 2: Combining Emotion Engines"

[1278] (Claim 1)

[1279] means for receiving a query from a user;

[1280] a server having an emotion engine for analyzing the emotional state of a user;

[1281] A means for analyzing and generating a response using a generative model based on the received inquiry content and emotional state;

[1282] means for presenting the generated response to a user;

[1283] A system including:

[1284] (Claim 2)

[1285] 10. The system of claim 1, which operates around the clock and provides personalized responses based on emotional state.

[1286] (Claim 3)

[1287] 2. The system according to claim 1, further comprising a terminal that transmits the content of the inquiry and the information for emotion analysis to the server and displays the obtained response to the user.

[1288] "Application example 2 when combining emotion engines"

[1289] (Claim 1)

[1290] means for receiving a query from a user;

[1291] a server having a generative model and an emotion engine for analyzing received query content and the user's emotional state;

[1292] means for the server to use the generative model to generate a response based on the user's emotional state and present the response to the user;

[1293] A system including:

[1294] (Claim 2)

[1295] 10. The system of claim 1, which operates 24 hours a day.

[1296] (Claim 3)

[1297] 2. The system according to claim 1, further comprising a terminal for transmitting a query to the server and displaying a response to the user. [Explanation of symbols]

[1298] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving a query from a user; a server having a generative model for analyzing received queries; means for the server to generate a response using the generative model and present the response to the user; A system including:

2. 10. The system according to claim 1, which operates 24 hours a day.

3. 2. The system according to claim 1, further comprising a terminal for transmitting a query to the server and displaying a response to the user.

4. The system according to claim 1 , wherein the generative model that analyzes the content of a query and generates a response uses natural language processing.

5. 10. The system of claim 1, further comprising means for maintaining a context based on the query content for response generation.

6. 2. The system according to claim 1, further comprising means for responding to an inquiry and obtaining information from an FAQ database.

Images