system

Abstract

Provide a system. A means for a user to input a query using a terminal and send it to a server; a means for the server to receive an inquiry from the user and analyze the content of the inquiry; A means for generating an appropriate response by a generation AI based on the analyzed inquiry content; means for transmitting the generated response to the user's terminal; means for displaying said response on said user's terminal; A system including:

Description

[Technical Field]

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

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

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

[0004] In conventional call center operations, human resources and operational costs are major issues. Furthermore, there are restrictions on time slots and waiting times, which can lead to lower customer satisfaction. In particular, customer service is often inadequate at night or on holidays, causing inconvenience to customers. Furthermore, responses to inquiries can be delayed, lengthening the time it takes to resolve a problem. To solve these issues, new technology is needed. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for a user to input an inquiry using a terminal and send it to a server, a means for the server to receive the inquiry from the user and analyze the inquiry, a means for a generation AI to generate an appropriate response based on the analyzed inquiry, a means for sending the generated response to the user's terminal, and a means for the user's terminal to display the response. This enables 24 / 7 support, reducing wait times and enabling quick problem resolution. Furthermore, because the generation AI retrieves necessary information from a company's database, it can provide accurate responses and improve customer satisfaction.

[0006] "User" refers to any individual or legal entity that uses the System to make an inquiry.

[0007] A "terminal" is a device that a user uses to access the system and input inquiries, and includes smartphones, computers, etc.

[0008] "Server" refers to a computer system that receives inquiries from users and analyzes and coordinates with the generation AI.

[0009] An "inquiry" refers to a question or request that a user enters into the system, including a specific problem or matter to be clarified.

[0010] "Analysis" refers to the process by which the server understands the user's inquiry and extracts the necessary information, using techniques such as natural language processing (NLP).

[0011] "Generative AI" refers to artificial intelligence that generates appropriate responses based on the analysis results provided by the server.

[0012] A "database" is a system that stores product information and customer data held by a company, and is a source of information referenced by the generation AI.

[0013] "Response" refers to the answer to a user's inquiry generated by the generation AI.

[0014] "Display" refers to the process by which the device presents the response from the generated AI in a form that the user can understand. [Brief explanation of the drawings]

[0015] [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

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] This invention relates to a system in which a user inputs a query using a terminal and sends it to a server. The server receives the query from the user and analyzes its contents. The analyzed results are sent to a generation AI, which generates an appropriate response. The generated response is then sent to the user's terminal and displayed.

[0037] User inquiry processing

[0038] Users access the system using their own devices (such as smartphones or PCs). For example, they access a call center inquiry form using a web browser or dedicated application and enter an inquiry such as, "Please tell me the shipping status of order number 12345." The device then sends this inquiry to the server as an HTTP request.

[0039] Reception and analysis by the server

[0040] When the server receives a user inquiry, it automatically begins the process of analyzing the inquiry. The server uses natural language processing (NLP) technology to parse the inquiry and extract important information (such as the order number and requirements). Specifically, from the inquiry "Please tell me the shipping status of order number 12345," the keywords "order number 12345" and "shipping status" are extracted.

[0041] Response generation by generative AI

[0042] The server provides data to the generation AI based on the analysis results. The generation AI retrieves relevant information from the company's database and generates a response in natural language. For example, if order number 12345 is currently being delivered, the generation AI generates a response saying, "The shipping status of order number 12345 is currently being delivered."

[0043] Response transmission from the server to the terminal

[0044] The generated response is sent back to the user's device by the server, which then returns the response received from the generation AI to the user's device as an HTTP response.

[0045] Display on the user's device

[0046] The user's device receives the response from the server and displays it on the screen. Specifically, the information such as "Shipping status of order number 12345 is currently being delivered" is displayed in a chat window or as a notification message.

[0047] Specific examples

[0048] For example, if a user uses a device to make a query such as "Please reissue the invoice for order number 56789," the device sends this query to the server. The server uses NLP technology to analyze the query and extract the information "order number 56789" and "invoice reissue." The generation AI then references the company's database, checks the reissue procedure and status of the relevant invoice, and generates a response such as "The invoice for order number 56789 has been reissued and will be mailed shortly." This response is then sent back to the user's device via the server and displayed on the user's screen.

[0049] In this way, the present invention provides a system that can provide quick and accurate responses to user inquiries, and is beneficial to both companies and customers.

[0050] The processing flow will be explained below.

[0051] Step 1:

[0052] A user uses a terminal to enter an inquiry. The user enters "Please tell me the shipping status of order number 12345" into a call center inquiry form or chat window and clicks the send button.

[0053] Step 2:

[0054] The device sends the user's inquiry as an HTTP request to the server. Specifically, the inquiry content is packaged in a data format such as JSON and sent to the specified endpoint on the server.

[0055] Step 3:

[0056] The server receives an HTTP request from a user, which includes the query and the user's identity.

[0057] Step 4:

[0058] The server analyzes the query. It uses a natural language processing (NLP) module to understand the intent of the query. Specifically, it extracts "order number 12345" and "shipping status" from the text "Please tell me the shipping status of order number 12345."

[0059] Step 5:

[0060] The server passes the parsed results to the generation AI, which retrieves information about order number 12345 from the company database.

[0061] Step 6:

[0062] The generative AI searches the company's database to retrieve the necessary information. For example, it retrieves the latest delivery status of order number 12345 and obtains information such as "Currently being delivered."

[0063] Step 7:

[0064] The generation AI generates a response in natural language based on the information it obtains. For example, it generates a response text such as, "The shipping status of order number 12345 is currently being delivered."

[0065] Step 8:

[0066] The server receives the response from the generation AI and generates an HTTP response to send to the user's device.

[0067] Step 9:

[0068] The server sends an HTTP response to the user's device, which includes the generated response text.

[0069] Step 10:

[0070] The user's device displays the response received from the server. Specifically, it displays the message "Order number 12345 is currently being delivered" in a chat window or as a notification message.

[0071] This series of processing steps provides fast and accurate responses to user inquiries, improving customer satisfaction.

[0072] Example 1

[0073] 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."

[0074] Conventional inquiry systems have problems such as delayed responses to user inquiries and inaccurate information provided. Furthermore, the content of the user's inquiry is not clearly analyzed, leading to inappropriate responses. Therefore, there is a demand for a system that can respond to user inquiries quickly and accurately.

[0075] 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.

[0076] In this invention, the server includes means for a user to input an inquiry using an information processing device and transmit the inquiry to the server, means for the server to receive the inquiry from the user and analyze the inquiry, means for a generation AI to generate an appropriate response based on the analyzed inquiry, means for transmitting the generated response to the user's information processing device, and means for the user's information processing device to display the response, thereby making it possible to provide a quick and accurate response to a user's inquiry.

[0077] A "user" is a person who operates an information processing device to make an inquiry.

[0078] An "information processing device" is an electronic device that allows a user to input an inquiry and send it to a server via the Internet, and includes devices such as smartphones and personal computers.

[0079] A "server" is a computer system that receives inquiries sent by users and analyzes and processes the contents of those inquiries.

[0080] An "inquiry" refers to a question or request that a user sends to the system via an information processing device.

[0081] "Natural language processing technology" is a technical method that allows computers to understand and analyze human language, and includes techniques such as text analysis and keyword extraction.

[0082] "Generative AI" refers to an artificial intelligence model that generates appropriate responses based on analyzed query content.

[0083] An "information management system" is a system that includes databases and other information resources referenced by generative AI, such as corporate databases.

[0084] This invention relates to a system in which a user inputs a query using an information processing device and sends the query to a server. The server receives the query from the user and analyzes the content of the query using natural language processing technology. The analyzed results are sent to a generation AI, which generates an appropriate response. The generated response is then sent to the user's information processing device and displayed.

[0085] A user accesses the system using their own information processing device (for example, a smartphone or PC). Specifically, they use a web browser or a dedicated application to enter a query into an inquiry form, such as "Please tell me the shipping status of order number 12345." The information processing device then sends this query to the server as an HTTP request.

[0086] When the server receives a user inquiry, it automatically begins the process of analyzing the inquiry. The server uses natural language processing (NLP) technology to parse the inquiry and extract important information (such as the order number and requirements). Specifically, from the inquiry "Please tell me the shipping status of order number 12345," the keywords "order number 12345" and "shipping status" are extracted.

[0087] The server provides the extracted keyword information to the generation AI, which retrieves relevant information from the company's information management system (database) and generates a response in natural language. For example, if order number 12345 is currently being delivered, the generation AI generates the response, "The shipping status of order number 12345 is currently being delivered."

[0088] The generated response is sent again by the server to the user's information processing device. The server returns the response received from the generation AI to the user's information processing device as an HTTP response. The user's information processing device receives the response from the server and displays it on the screen. Specifically, information such as "Shipping status of order number 12345 is currently being delivered" is displayed in a chat window or as a notification message.

[0089] As a specific example, consider the case where a user makes an inquiry such as, "Please reissue the invoice for order number 56789." In this case, the information processing device sends this inquiry to the server. The server uses NLP technology to analyze the inquiry and extracts the information "order number 56789" and "invoice reissue." The generation AI references the company's information management system to obtain the relevant information and generates a response such as, "The invoice for order number 56789 has been reissued and will be mailed shortly." This response is then sent again via the server to the user's information processing device and displayed on the user's screen.

[0090] Here is an example prompt:

[0091] User's inquiry: Please let me know the shipping status of order number 12345.

[0092] Information from company database: Order number 12345 is currently being shipped.

[0093] Response to generate: Order 12345 is currently in transit.

[0094] In this way, the present invention can provide a fast and accurate response to user inquiries, thereby providing a system that is beneficial to both companies and customers.

[0095] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0096] Step 1:

[0097] A user inputs a query using an information processing device. Specifically, the user inputs a query such as "Please tell me the shipping status of order number 12345" using a dedicated application or web browser on a smartphone or PC. The input query is formatted as the payload of an HTTP request.

[0098] Input: User inquiry (e.g., "Please tell me the shipping status of order number 12345.")

[0099] Output: The query formatted as an HTTP request

[0100] Step 2:

[0101] The terminal sends the input query to the server. Specifically, it sends a request including the query content payload as an HTTP POST request to the specified server URL.

[0102] Input: Query content formatted as an HTTP request

[0103] Output: HTTP request sent to the server

[0104] Step 3:

[0105] The server receives an HTTP request from the user. The web server (e.g., Apache (registered trademark) or Nginx) receives the request and passes it to the application server. The query content is extracted from the payload of the received request.

[0106] Input: HTTP request

[0107] Output: Extracted inquiry content

[0108] Step 4:

[0109] The server analyzes the received inquiry using natural language processing technology (NLP engine). Specifically, the engine (e.g., spaCy or NLTK) extracts important keywords from the inquiry (e.g., "order number 12345" and "shipping status").

[0110] Input: Extracted inquiry content

[0111] Output: Extracted keywords (e.g. "Order number 12345" and "Shipping status")

[0112] Step 5:

[0113] The server sends the extracted keyword information to the generative AI model, providing the data to the generative AI model along with the analyzed keywords as a prompt sentence: "Please tell me the shipping status of order number 12345."

[0114] Input: Extracted keyword information

[0115] Output: Send prompt to generative AI model

[0116] Step 6:

[0117] The generative AI model references the company's information management system (database) based on the provided prompt sentence to retrieve relevant information. For example, it retrieves information from the database that "Order number 12345 is currently being delivered." Based on this, the generative AI generates a natural language response such as, "The shipping status of order number 12345 is currently being delivered."

[0118] Input: Prompt statement and associated information from information management system

[0119] Output: Generated response

[0120] Step 7:

[0121] The server receives the response text generated by the generation AI, formats it as an HTTP response, and prepares to send it to the user's information processing device.

[0122] Input: Generated response sentence

[0123] Output: Response text formatted as an HTTP response

[0124] Step 8:

[0125] The server transmits the generated response text to the user's information processing device as an HTTP response.

[0126] Input: Response text formatted as an HTTP response

[0127] Output: Sending an HTTP response to the user's information processing device

[0128] Step 9:

[0129] The user's information processing device receives the HTTP response from the server and extracts the response text from the payload of the received response.

[0130] Input: HTTP response from the server

[0131] Output: Extracted response sentence

[0132] Step 10:

[0133] The user's information processing device displays the extracted response sentence on the screen. Specifically, information such as "The shipping status of order number 12345 is currently being delivered" is displayed in a chat window or as a notification message.

[0134] Input: Extracted response sentence

[0135] Output: Response text displayed on the screen

[0136] (Application example 1)

[0137] 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."

[0138] With the existing inquiry system, it took a long time for logistics center employees to check inventory and delivery status, reducing efficiency. Responses to inquiries were often not returned immediately, which sometimes disrupted business operations. For this reason, a system was needed that would enable logistics center employees to quickly and accurately obtain the information they needed.

[0139] 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.

[0140] In this invention, the server includes: a means for a user to input an inquiry using a terminal and send it to the server; a means for the server to receive the inquiry from the user and analyze the inquiry; a means for a generation AI to generate an appropriate response based on the analyzed inquiry; a means for a logistics center employee to inquire about stock status and delivery status; a means for making the inquiry using a smartphone; a means for sending the inquiry to the server as an HTTP request; a means for sending the generated response to the user's terminal; and a means for the user's terminal to display the response. This enables logistics center employees to quickly check stock status and delivery status.

[0141] "Means for users to input inquiries using a terminal and send them to a server" refers to a system in which users input inquiries using electronic devices such as smartphones or personal computers and send the contents to a server via a network.

[0142] "Means for the server to receive the inquiry from the user and analyze the content of the inquiry" refers to a process in which the server receives the content of the inquiry sent by the user and analyzes its content.

[0143] "Means by which the generation AI generates an appropriate response based on the analyzed inquiry content" refers to the process by which the generation AI automatically generates an appropriate response based on the information obtained from the analysis results.

[0144] "Means for logistics center employees to inquire about inventory status and delivery status" refers to a system by which employees working at logistics centers can make inquiries to check inventory information and delivery information.

[0145] "Means for making an inquiry using a smartphone" refers to a method in which a user uses a portable electronic device called a smartphone to send an inquiry to the system.

[0146] "Means of sending to the server as an HTTP request" refers to a method of sending the inquiry content to the server using HyperText Transfer Protocol (HTTP).

[0147] "Means for sending the generated response to the user's terminal" refers to the procedure for sending the response generated by the AI ​​back to the user's terminal via the network.

[0148] "Means by which the user's terminal displays the response" refers to a mechanism by which the response is displayed on the user's device.

[0149] This invention relates to a system in which a user inputs an inquiry using a terminal and sends it to a server. Specifically, it provides a system in which a logistics center employee can inquire about inventory status and delivery status using a smartphone and receive an immediate response. An embodiment of this system is described in detail below.

[0150] User inquiry processing

[0151] A user (a logistics center employee) uses a dedicated application on their smartphone to enter an inquiry. For example, they might enter "Please tell me the stock status of order number 12345" into an input field on the screen. This inquiry is sent to the server as an HTTP request.

[0152] Reception and analysis by the server

[0153] When the server receives an HTTP request from a user, it analyzes its contents. Natural language processing (NLP) technology is used for the analysis. Specifically, the server uses an NLP library such as spaCy or NLTK to parse the query and extract important information (such as the order number and requirements). For example, from the query "Please tell me the stock status of order number 12345," the keywords "order number 12345" and "stock status" are extracted. The analysis results are then saved in JSON format.

[0154] Response generation by generative AI

[0155] The server provides data to the generative AI model based on the analyzed information. The generative AI model references the company's database and generates an appropriate response to the query. For example, if the stock quantity for order number 12345 is 5, the generative AI model generates the response "There are currently 5 units of order number 12345 in stock."

[0156] Response transmission from the server to the terminal

[0157] The generated response is then sent back to the user's device as an HTTP response. When the server receives the response from the AI ​​generator and sends it to the user's device, it converts the response into a format that is easy for the user to understand.

[0158] Display on the user's device

[0159] The user's device receives the response from the server and displays it on the screen. Specifically, the information, such as "There are currently 5 units of order number 12345 in stock," is displayed in a chat window in a dedicated application or as a notification message. In this way, employees at the logistics center can quickly check the information they need.

[0160] Technology Stack

[0161] Natural Language Processing (NLP) libraries: spaCy, NLTK

[0162] Generative AI model: OpenAI (registered trademark) GPT-3 (registered trademark)

[0163] Backend frameworks: Flask, Django

[0164] Database: MySQL (registered trademark), PostgreSQL

[0165] Examples of specific examples and prompts

[0166] For example, suppose a user makes the following query:

[0167] User Input: "What is the stock status for order number 67890?"

[0168] An example of the corresponding prompt for the generative AI model:

[0169] User's question: "What is the stock status of order number 67890?"

[0170] Parsing result: {"Order number": "67890", "Requirement": "Availability"}

[0171] Example of a response generated by the Generative AI:

[0172] There are currently 5 units of order number 67890 in stock.

[0173] In this way, by using the system of the present invention, employees at the logistics center can quickly and accurately obtain the necessary information, which contributes to improving work efficiency.

[0174] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0175] Step 1:

[0176] A user uses a terminal to enter a query and send it to the server.

[0177] Specific actions: An employee at the logistics center enters "Please tell me the inventory status of order number 12345" into the input field in a dedicated application on their smartphone and presses the "Send" button.

[0178] Input: The query entered by the user.

[0179] Output: The query sent to the server as an HTTP request.

[0180] Step 2:

[0181] The server receives a query from a user and analyzes the query.

[0182] What happens: The server receives the HTTP request and uses a natural language processing (NLP) library (such as spaCy or NLTK) to extract the query. The query is parsed into "order number 12345" and "stock status" and saved in JSON format.

[0183] Input: The query received as an HTTP request.

[0184] Output: The parsed query content is saved in JSON format.

[0185] Step 3:

[0186] Based on the analyzed inquiry content, the generative AI generates an appropriate response.

[0187] Specific operation: The server sends the analysis results to a generative AI model (e.g., OpenAI GPT-3). The generative AI model works with the company's database to generate an appropriate response to the query. For example, it retrieves information from the database that there are five units of order number 12345 in stock, and generates a response saying, "There are currently five units of order number 12345 in stock."

[0188] Input: Parsed query content (JSON format).

[0189] Output: The generated response (in natural language format).

[0190] Step 4:

[0191] The generated response is sent from the server to the user's terminal.

[0192] Specific operation: The server sends the response received from the generation AI to the user's device as an HTTP response.

[0193] Input: Response from the generation AI.

[0194] Output: The HTTP response sent to the user's device.

[0195] Step 5:

[0196] The user's terminal displays the response.

[0197] Specific operation: The user's device (a dedicated smartphone application) displays the HTTP response received from the server on the screen. For example, it displays information such as "There are currently 5 units of order number 12345 in stock" in a chat window or as a notification message.

[0198] Input: The HTTP response from the server.

[0199] Output: The displayed response.

[0200] 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.

[0201] This invention relates to a system in which a user inputs a query using a terminal and sends it to a server. This system provides an appropriate response according to the user's emotions by combining it with an emotion engine that recognizes the user's emotions. Specifically, the server receives the query from the user and analyzes the content and the user's emotions. A generation AI generates an appropriate response based on the analysis results and sends it to the user's terminal. The generated response is then displayed on the user's terminal.

[0202] User inquiry processing and emotion recognition

[0203] When a user uses their device to input a query, they can do so in text, voice, or video format. For example, when they input "What is the shipping status of order number 12345?" through a chat window or voice input assistant, the emotion engine recognizes the user's emotion from their tone of voice, facial expression, and the context of the text. The device then sends the emotion data along with the query to the server.

[0204] Reception and analysis by the server

[0205] When the server receives a user inquiry, it first analyzes the emotion data provided by the emotion engine. Using a natural language processing (NLP) module, the server understands the intent of the inquiry and simultaneously grasps the user's state (e.g., anger, joy, sadness, etc.) based on the emotion data. Specifically, in response to the inquiry, "Please tell me the shipping status of order number 12345," the keywords "order number 12345" and "shipping status" are extracted, and the emotion engine simultaneously recognizes that the user is dissatisfied.

[0206] Response generation by generative AI

[0207] The server provides the analysis results and emotional data to the generation AI, which retrieves relevant information from the company's database and considers the user's emotions when generating a natural language response. For example, if the user is dissatisfied, the generation AI generates a more polite and empathetic response. Specifically, it generates a response such as, "The shipping status of order number 12345 is currently being delivered. We apologize for the inconvenience."

[0208] Response transmission from the server to the terminal

[0209] The generated response is sent to the user's device by the server, which then returns the response received from the generation AI to the user's device as an HTTP response.

[0210] Display on the user's device

[0211] The user's device displays the response received from the server. Specifically, a chat window or notification message will appear stating, "The shipping status for order number 12345 is currently being delivered. We apologize for any inconvenience." This allows the user to receive a response that takes their feelings into consideration, improving satisfaction.

[0212] Specific examples

[0213] For example, if a user uses a device to make an inquiry such as "Please reissue the invoice for order number 56789," and expresses dissatisfaction at the time, the emotion engine recognizes the user's dissatisfaction from the voice data and text sent from the device. The emotion data and inquiry content are sent to the server for analysis. The generation AI generates a response that takes the user's emotions into consideration, such as "The invoice for order number 56789 has been reissued and will be mailed shortly. We apologize for the inconvenience," and sends this response to the device via the server. Finally, the device displays this response.

[0214] In this way, the present invention provides a system that can provide quick, accurate responses to user inquiries and that also take into consideration the user's feelings, thereby greatly improving customer satisfaction and contributing to improving the quality of service provided by companies.

[0215] The processing flow will be explained below.

[0216] Step 1:

[0217] The user uses the device to input an inquiry. For example, the user may use a chat window or a voice input assistant to input, "Please tell me the shipping status of order number 12345." At this time, the device collects emotional data such as voice and facial expressions along with the user's input.

[0218] Step 2:

[0219] The device sends the collected inquiry and emotion data to the server as an HTTP request. Specifically, the inquiry is packaged as text data, audio data, or video data and sent in a format that can be analyzed by the emotion engine.

[0220] Step 3:

[0221] The server receives an HTTP request from the user, which includes the query and emotion data.

[0222] Step 4:

[0223] The server analyzes the inquiry and uses an emotion engine to analyze the user's emotions. The server uses a natural language processing (NLP) module to understand the intent of the inquiry. For example, from the text "Please tell me the shipping status of order number 12345," it extracts "order number 12345" and "shipping status," and at the same time, the emotion engine recognizes the user's dissatisfaction.

[0224] Step 5:

[0225] The server passes the analysis results (order number and requirements) and emotion data to the generation AI, which then retrieves information about order number 12345 from the company database.

[0226] Step 6:

[0227] The generative AI searches the company's database to get the latest delivery status for order number 12345. For example, it might get information like "Currently being delivered."

[0228] Step 7:

[0229] Based on the information acquired, the generation AI generates a response in natural language that takes the user's feelings into consideration. For example, if the user is dissatisfied, it generates a polite and empathetic response such as, "The shipping status of order number 12345 is currently being delivered. We apologize for the inconvenience."

[0230] Step 8:

[0231] The server receives the response from the generation AI and generates an HTTP response to send to the user's device. The response contains the generated response text.

[0232] Step 9:

[0233] The server sends an HTTP response to the user's device, which contains sentiment-sensitive text.

[0234] Step 10:

[0235] The user's device displays the response received from the server. Specifically, a chat window or notification message might say, "The shipping status for order number 12345 is currently being delivered. We apologize for any inconvenience caused." This allows the user to receive information in a way that takes their feelings into consideration.

[0236] This series of processing steps enables a response to a user's inquiry to be provided quickly, accurately, and with consideration for the user's feelings, thereby improving customer satisfaction and the quality of service provided by the company.

[0237] Example 2

[0238] 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."

[0239] Conventional inquiry response systems generate responses without considering the user's emotions, which leads to a decrease in user satisfaction. Furthermore, the accuracy of analyzing the inquiry content is low, and appropriate responses are often not generated. This results in a lack of improvement in the user experience and the quality of service provided by companies.

[0240] 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.

[0241] In this invention, the server includes a means for a user to input a query using a terminal and send it to the server, a means for the server to receive the query from the user and analyze the query content and the user's emotions, and a means for the generation AI to generate an appropriate response based on the analyzed query content and user emotion data, thereby enabling an appropriate response that takes the user's emotions into consideration.

[0242] 1. "Terminal" means a device used by a user to enter an inquiry, such as a smartphone, PC, or tablet.

[0243] 2. "Server" means a computer system whose role is to receive and analyze queries sent by users.

[0244] 3. "Query" means a question or request sent by a User to a Server using a Terminal.

[0245] 4. "Emotion" refers to the psychological state that a user exhibits when making a query, including joy, anger, sadness, surprise, etc.

[0246] 5. "Emotion engine" means software or algorithms that recognize emotions from user input data.

[0247] 6. “Natural Language Processing (NLP)” refers to techniques or methods that enable computers to understand, analyze, and generate human language.

[0248] 7. "Generative AI" is an artificial intelligence system that generates appropriate responses based on the user's inquiry and emotional data.

[0249] 8. “Database” means a structured collection of data that stores information about a company and that is referenced by Generative AI when generating responses.

[0250] 9. "HTTP request" means a request message using an Internet protocol for a terminal to send data to a server.

[0251] 10. "HTTP response" means a response message using an Internet protocol that allows a server to return data to a terminal.

[0252] This invention relates to a system in which a user inputs a query using a terminal and sends it to a server. This system provides an appropriate response according to the user's emotion by combining it with an emotion engine that recognizes the user's emotion.

[0253] composition

[0254] User inquiry input and submission

[0255] A user uses a device such as a smartphone or PC to input a query in text, voice, or video format. For example, they might input "What is the shipping status of order number 12345?" through a chat window or voice input assistant. The device is equipped with an emotion engine that recognizes emotions from the user's tone of voice, facial expressions, and text context. The device then sends the emotion data along with the query to the server.

[0256] Reception and analysis by the server

[0257] When the server receives a query from a user, it first analyzes the provided emotion data using the emotion engine. Using a natural language processing (NLP) module, the server understands the intent of the query and simultaneously grasps the user's emotional state (e.g., anger, joy, sadness, etc.) based on the emotion data. For example, in response to a query such as "Please tell me the shipping status of order number 12345," the keywords "order number 12345" and "shipping status" are extracted, and it is recognized that the user is dissatisfied.

[0258] Response generation by generative AI

[0259] The server provides the analysis results and emotional data to the generation AI, which retrieves relevant information from the company's database and considers the user's emotions when generating a natural language response. For example, if the user is dissatisfied, the generation AI will generate a more polite and empathetic response. A response such as "The shipping status of order number 12345 is currently being delivered. We apologize for the inconvenience."

[0260] Response transmission from the server to the terminal

[0261] The generated response is sent to the user's device by the server. The server returns the response received from the generation AI to the user's device as an HTTP response.

[0262] Display on the user's device

[0263] The user's device displays the response received from the server. For example, a chat window or notification message might say, "The shipping status for order number 12345 is currently being delivered. We apologize for any inconvenience." This allows the user to receive a response that takes their feelings into consideration, improving satisfaction.

[0264] Specific examples and examples of prompts for generative AI models

[0265] For example, if a user uses a device to make an inquiry such as "Please reissue the invoice for order number 56789," and expresses dissatisfaction at the time, the emotion engine will recognize the user's dissatisfaction from the voice and text data sent from the device. The emotion data and the inquiry content are sent to the server for analysis. The generation AI will generate a response that takes the user's emotions into consideration, such as "The invoice for order number 56789 has been reissued and will be mailed shortly. We apologize for the inconvenience," and send it to the device via the server. Finally, the device will display this response.

[0266] Example prompt for a generative AI model: "The user is asking, 'What is the shipping status for order 12345?' The user is frustrated. Please respond in a kind and polite manner."

[0267] In this way, the present invention realizes a system that provides quick, accurate responses to user inquiries and takes into consideration the user's feelings, thereby contributing to improved customer satisfaction and the quality of corporate services.

[0268] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0269] Step 1:

[0270] The user enters a query

[0271] Input: The user uses a smartphone or computer to input a query by text or voice through a chat window or voice input assistant.

[0272] What happens: The user types into the chat window, "What is the shipping status of order number 12345?" If the user types, the device uses voice recognition software to convert the speech into text.

[0273] Output: Query data in text format.

[0274] Step 2:

[0275] The device recognizes emotions

[0276] Input: Query data in text format.

[0277] Specific operation: The device uses the emotion engine to recognize emotions from the user's input data. For example, it uses the "Emotion SDK" to analyze the user's tone of voice and facial expressions.

[0278] Output: Enquiry and sentiment data (e.g. dissatisfaction).

[0279] Step 3:

[0280] The device sends the data to the server

[0281] Input: Enquiry content and emotion data.

[0282] Specific operation: The device generates an HTTP request and sends the query content and emotion data to the server.

[0283] Output: The query and emotion data sent to the server.

[0284] Step 4:

[0285] The server receives and analyzes the data

[0286] Input: Inquiry content and emotion data sent from the device.

[0287] Specific operation: The server receives an HTTP request, analyzes the provided emotion data using the emotion engine, and then analyzes the intent of the query using the natural language processing (NLP) module.

[0288] Output: Parsed query content and sentiment data.

[0289] Step 5:

[0290] The server sends the data to the generated AI.

[0291] Input: Parsed query content and sentiment data.

[0292] Specific operation: The server sends the analysis results to the generation AI. A prompt is generated, for example, "Please tell me the shipping status of order number 12345. The user is dissatisfied. Please respond in a kind and polite manner."

[0293] Output: The prompt sent to the generation AI and the analysis results.

[0294] Step 6:

[0295] Generative AI generates responses

[0296] Input: Prompt sentence and parsed result sent from the server.

[0297] Specific operation: The generative AI (e.g., GPT-4 (registered trademark)) refers to a company's database (e.g., PostgreSQL) and generates a response that takes the user's emotions into account.

[0298] Output: The generated response text (e.g., "Order 12345 is currently on its way. We apologize for any inconvenience.").

[0299] Step 7:

[0300] The server receives the generated response

[0301] Input: The response text sent by the generation AI.

[0302] Specific operation: The server receives the response generated from the generation AI.

[0303] Output: The response text received.

[0304] Step 8:

[0305] The server sends the response to the user's device

[0306] Input: The response text received.

[0307] Specific operation: The server creates an HTTP response and sends the generated response to the user's terminal.

[0308] Output: The response text sent to the user's terminal.

[0309] Step 9:

[0310] The user's device displays the response

[0311] Input: The response text sent by the server.

[0312] Specific operation: The user's device receives the HTTP response and displays the response in a chat window or as a notification message.

[0313] Output: Response text displayed on the user's device (e.g., "Order 12345 is currently on its way. We apologize for any inconvenience.").

[0314] (Application example 2)

[0315] 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."

[0316] In electronic payment services, when responding to user inquiries, it is necessary to appropriately recognize the user's emotions and provide a response based on those emotions. Conventional systems do not take the user's emotions into consideration, which has led to the problem of not being able to fully alleviate the user's dissatisfaction and anxiety, resulting in a decrease in customer satisfaction. In order to solve this problem, the present invention aims to provide a system that recognizes the user's emotions and provides a response based on those emotions.

[0317] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0318] In this invention, the server includes: a means for a user to input a query using a terminal and send it to the server; a means for the server to receive the query from the user and analyze the query content and the user's emotions; a means for a generation AI to generate an appropriate response based on the analyzed query content and emotion data; a means for sending the generated response to the user's terminal; and a means for the user's terminal to display the response, characterized in that a response corresponding to the user's emotions is provided. This makes it possible to provide a quick and accurate response while taking the user's emotions into consideration.

[0319] "User" refers to a user who makes an inquiry using a terminal.

[0320] "Terminal" refers to a device through which a user inputs a query and communicates with a server.

[0321] "Server" refers to a computer system that receives queries from users, analyzes them, and generates responses.

[0322] "Query" refers to a question or request that a user sends to a server through a terminal.

[0323] "Emotion" refers to the psychological state that a user exhibits when making a query.

[0324] An "emotion engine" refers to software that analyzes a user's emotions and generates data based on them.

[0325] "Analyzing" means that the server understands the content of the inquiry and the emotional data and performs appropriate processing.

[0326] "Generative AI" refers to artificial intelligence that generates appropriate responses based on the content of inquiries and emotional data.

[0327] "Response" refers to the answer or information that the server generates in response to a user's inquiry through generation AI.

[0328] "Displaying" refers to visually showing the response sent from the server on the user's terminal.

[0329] The present invention relates to a system that allows a user to input a query using a terminal, transmit the query to a server, and provide an appropriate response based on the user's emotions. The system of the present invention has the following configuration.

[0330] System configuration

[0331] 1. User Device:

[0332] A device for users to input queries. This device can be a smartphone or a head-mounted display. Users can submit queries in text, voice, or video format.

[0333] 2. Server:

[0334] A computer system that receives and analyzes queries sent from user terminals. The server contains the following main modules:

[0335] Emotion engine: Software that analyzes the user's emotions. It uses an emotion recognition library (e.g., IBM Watson (registered trademark) Tone Analyzer, etc.).

[0336] Natural Language Processing (NLP) module: Analyzes the query content and extracts key intent and keywords. Uses natural language processing libraries (e.g., spaCy, NLTK, etc.).

[0337] Generative AI module: Artificial intelligence that generates appropriate responses based on analysis results. It uses a generative AI model (e.g., OpenAI's GPT-4).

[0338] HTTP communication module: Communicates with the user terminal using a web server (e.g., Flask, Django, etc.).

[0339] 3. Response display:

[0340] This module displays the generated responses on the user's device. It includes a user interface (UI) module, which displays the responses as chat windows and notification messages.

[0341] Processing flow and specific examples

[0342] 1. Inquiry received:

[0343] A user makes an inquiry via their smartphone, saying, "I'm worried about suspicious activity in my recent transaction history." This inquiry is sent to the server as text or voice data.

[0344] 2. Emotion analysis:

[0345] The server's emotion engine recognizes the user's anxiety from the inquiry content and generates emotion data.

[0346] 3. Query Analysis:

[0347] The server's natural language processing (NLP) module extracts keywords such as "recent transaction history" and "suspicious activity," while simultaneously recognizing that the user is feeling "anxious."

[0348] 4. Response generation by generative AI:

[0349] The generative AI module generates a response based on the extracted intent and sentiment data, such as, "We have not found any suspicious activity in your recent transaction history. Rest assured, if you require further clarification, please feel free to contact us."

[0350] 5. Response transmission and display:

[0351] The generated response is sent to the user's terminal via the server and displayed in a chat window or as a notification message.

[0352] Prompt Sentence Examples

[0353] If a user says, "I'm concerned about suspicious activity in my recent transactions," the following prompt is passed to the AI ​​generator:

[0354] User: I'm concerned about suspicious activity in my recent transaction history.

[0355] Emotion: Anxiety

[0356] Response: We have not found any suspicious activity in your recent transaction history. Rest assured, if you require further clarification, please feel free to contact us.

[0357] As described above, the present invention aims to improve customer satisfaction by providing a quick and accurate response while taking into consideration the user's feelings.

[0358] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0359] Step 1: Enter and submit your inquiry

[0360] A user uses a terminal to input a query. For example, text or voice data such as "I'm concerned about suspicious activity in my recent transaction history" is input. This query is sent from the terminal to the server. The input is text or voice data, and the output is query data. The terminal sends the query data to the server.

[0361] Step 2: Inquiry reception and sentiment analysis

[0362] The server receives the inquiry data sent by the user. The received data is passed to the emotion engine, which analyzes the user's emotions. Specifically, an emotion recognition library (e.g., IBM Watson Tone Analyzer) is used to analyze the tone of the voice and the context of the text using a unique algorithm to determine the user's mental state. The input is the inquiry data, and the output is the analyzed emotion data.

[0363] Step 3: Analyzing the inquiry

[0364] The server passes the query content, along with the emotion data received from the emotion engine, to a natural language processing (NLP) module. The NLP module extracts the intent and key keywords of the query through a directed process. For example, it uses libraries such as spaCy and NLTK to extract key keywords such as "transaction history" and "suspicious activity." The input is the query data and emotion data, and the output is the parsed intent and keywords.

[0365] Step 4: Response Generation

[0366] The analyzed intent, keywords, and even sentiment data are passed to a generative AI module, which uses this data to generate an appropriate response. This is done using an AI model (e.g., OpenAI GPT-4) that synthesizes the extracted information to generate a human-like natural language response. For example, a response might read, "We have not found any suspicious activity in your recent transaction history. Rest assured, if you require further clarification, please feel free to contact us." The input is the analyzed intent, keywords, and sentiment data, and the output is the generated response.

[0367] Step 5: Send response

[0368] The HTTP communication module receives the response generated by the generation AI module and sends it to the user's device. Specifically, the generated response is encoded as an HTTP response and sent to the device as appropriate. During this process, a security layer is applied to ensure the confidentiality and integrity of the data. The input is the generated response data, and the output is an HTTP response to the device.

[0369] Step 6: Display the response

[0370] The user terminal decodes the HTTP response received from the server and displays it through the user interface (UI) module. The response is displayed in a user-friendly format, such as a chat window or notification message, allowing the user to confirm the appropriate response. The input is the received HTTP response, and the output is the displayed response message.

[0371] 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.

[0372] 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.

[0373] 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.

[0374] [Second embodiment]

[0375] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0376] 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.

[0377] 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).

[0378] 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.

[0379] 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.

[0380] 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).

[0381] 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.

[0382] 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.

[0383] 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.

[0384] 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.

[0385] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0386] 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."

[0387] This invention relates to a system in which a user inputs a query using a terminal and sends it to a server. The server receives the query from the user and analyzes its contents. The analyzed results are sent to a generation AI, which generates an appropriate response. The generated response is then sent to the user's terminal and displayed.

[0388] User inquiry processing

[0389] Users access the system using their own devices (such as smartphones or PCs). For example, they access a call center inquiry form using a web browser or dedicated application and enter an inquiry such as, "Please tell me the shipping status of order number 12345." The device then sends this inquiry to the server as an HTTP request.

[0390] Reception and analysis by the server

[0391] When the server receives a user inquiry, it automatically begins the process of analyzing the inquiry. The server uses natural language processing (NLP) technology to parse the inquiry and extract important information (such as the order number and requirements). Specifically, from the inquiry "Please tell me the shipping status of order number 12345," the keywords "order number 12345" and "shipping status" are extracted.

[0392] Response generation by generative AI

[0393] The server provides data to the generation AI based on the analysis results. The generation AI retrieves relevant information from the company's database and generates a response in natural language. For example, if order number 12345 is currently being delivered, the generation AI generates a response saying, "The shipping status of order number 12345 is currently being delivered."

[0394] Response transmission from the server to the terminal

[0395] The generated response is sent back to the user's device by the server, which then returns the response received from the generation AI to the user's device as an HTTP response.

[0396] Display on the user's device

[0397] The user's device receives the response from the server and displays it on the screen. Specifically, the information such as "Shipping status of order number 12345 is currently being delivered" is displayed in a chat window or as a notification message.

[0398] Specific examples

[0399] For example, if a user uses a device to make a query such as "Please reissue the invoice for order number 56789," the device sends this query to the server. The server uses NLP technology to analyze the query and extract the information "order number 56789" and "invoice reissue." The generation AI then references the company's database, checks the reissue procedure and status of the relevant invoice, and generates a response such as "The invoice for order number 56789 has been reissued and will be mailed shortly." This response is then sent back to the user's device via the server and displayed on the user's screen.

[0400] In this way, the present invention provides a system that can provide quick and accurate responses to user inquiries, and is beneficial to both companies and customers.

[0401] The processing flow will be explained below.

[0402] Step 1:

[0403] A user uses a terminal to enter an inquiry. The user enters "Please tell me the shipping status of order number 12345" into a call center inquiry form or chat window and clicks the send button.

[0404] Step 2:

[0405] The device sends the user's inquiry as an HTTP request to the server. Specifically, the inquiry content is packaged in a data format such as JSON and sent to the specified endpoint on the server.

[0406] Step 3:

[0407] The server receives an HTTP request from a user, which includes the query and the user's identity.

[0408] Step 4:

[0409] The server analyzes the query. It uses a natural language processing (NLP) module to understand the intent of the query. Specifically, it extracts "order number 12345" and "shipping status" from the text "Please tell me the shipping status of order number 12345."

[0410] Step 5:

[0411] The server passes the parsed results to the generation AI, which retrieves information about order number 12345 from the company database.

[0412] Step 6:

[0413] The generative AI searches the company's database to retrieve the necessary information. For example, it retrieves the latest delivery status of order number 12345 and obtains information such as "Currently being delivered."

[0414] Step 7:

[0415] The generation AI generates a response in natural language based on the information it obtains. For example, it generates a response text such as, "The shipping status of order number 12345 is currently being delivered."

[0416] Step 8:

[0417] The server receives the response from the generation AI and generates an HTTP response to send to the user's device.

[0418] Step 9:

[0419] The server sends an HTTP response to the user's device, which includes the generated response text.

[0420] Step 10:

[0421] The user's device displays the response received from the server. Specifically, it displays the message "Order number 12345 is currently being delivered" in a chat window or as a notification message.

[0422] This series of processing steps provides fast and accurate responses to user inquiries, improving customer satisfaction.

[0423] Example 1

[0424] 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."

[0425] Conventional inquiry systems have problems such as delayed responses to user inquiries and inaccurate information provided. Furthermore, the content of the user's inquiry is not clearly analyzed, leading to inappropriate responses. Therefore, there is a demand for a system that can respond to user inquiries quickly and accurately.

[0426] 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.

[0427] In this invention, the server includes means for a user to input an inquiry using an information processing device and transmit the inquiry to the server, means for the server to receive the inquiry from the user and analyze the inquiry, means for a generation AI to generate an appropriate response based on the analyzed inquiry, means for transmitting the generated response to the user's information processing device, and means for the user's information processing device to display the response, thereby making it possible to provide a quick and accurate response to a user's inquiry.

[0428] A "user" is a person who operates an information processing device to make an inquiry.

[0429] An "information processing device" is an electronic device that allows a user to input an inquiry and send it to a server via the Internet, and includes devices such as smartphones and personal computers.

[0430] A "server" is a computer system that receives inquiries sent by users and analyzes and processes the contents of those inquiries.

[0431] An "inquiry" refers to a question or request that a user sends to the system via an information processing device.

[0432] "Natural language processing technology" is a technical method that allows computers to understand and analyze human language, and includes techniques such as text analysis and keyword extraction.

[0433] "Generative AI" refers to an artificial intelligence model that generates appropriate responses based on analyzed query content.

[0434] An "information management system" is a system that includes databases and other information resources referenced by generative AI, such as corporate databases.

[0435] This invention relates to a system in which a user inputs a query using an information processing device and sends the query to a server. The server receives the query from the user and analyzes the content of the query using natural language processing technology. The analyzed results are sent to a generation AI, which generates an appropriate response. The generated response is then sent to the user's information processing device and displayed.

[0436] A user accesses the system using their own information processing device (for example, a smartphone or PC). Specifically, they use a web browser or a dedicated application to enter a query into an inquiry form, such as "Please tell me the shipping status of order number 12345." The information processing device then sends this query to the server as an HTTP request.

[0437] When the server receives a user inquiry, it automatically begins the process of analyzing the inquiry. The server uses natural language processing (NLP) technology to parse the inquiry and extract important information (such as the order number and requirements). Specifically, from the inquiry "Please tell me the shipping status of order number 12345," the keywords "order number 12345" and "shipping status" are extracted.

[0438] The server provides the extracted keyword information to the generation AI, which retrieves relevant information from the company's information management system (database) and generates a response in natural language. For example, if order number 12345 is currently being delivered, the generation AI generates the response, "The shipping status of order number 12345 is currently being delivered."

[0439] The generated response is sent again by the server to the user's information processing device. The server returns the response received from the generation AI to the user's information processing device as an HTTP response. The user's information processing device receives the response from the server and displays it on the screen. Specifically, information such as "Shipping status of order number 12345 is currently being delivered" is displayed in a chat window or as a notification message.

[0440] As a specific example, consider the case where a user makes an inquiry such as, "Please reissue the invoice for order number 56789." In this case, the information processing device sends this inquiry to the server. The server uses NLP technology to analyze the inquiry and extracts the information "order number 56789" and "invoice reissue." The generation AI references the company's information management system to obtain the relevant information and generates a response such as, "The invoice for order number 56789 has been reissued and will be mailed shortly." This response is then sent again via the server to the user's information processing device and displayed on the user's screen.

[0441] Here is an example prompt:

[0442] User's inquiry: Please let me know the shipping status of order number 12345.

[0443] Information from company database: Order number 12345 is currently being shipped.

[0444] Response to generate: Order 12345 is currently in transit.

[0445] In this way, the present invention can provide a fast and accurate response to user inquiries, thereby providing a system that is beneficial to both companies and customers.

[0446] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0447] Step 1:

[0448] A user inputs a query using an information processing device. Specifically, the user inputs a query such as "Please tell me the shipping status of order number 12345" using a dedicated application or web browser on a smartphone or PC. The input query is formatted as the payload of an HTTP request.

[0449] Input: User inquiry (e.g., "Please tell me the shipping status of order number 12345.")

[0450] Output: The query formatted as an HTTP request

[0451] Step 2:

[0452] The terminal sends the input query to the server. Specifically, it sends a request including the query content payload as an HTTP POST request to the specified server URL.

[0453] Input: Query content formatted as an HTTP request

[0454] Output: HTTP request sent to the server

[0455] Step 3:

[0456] The server receives an HTTP request from the user. The web server (e.g., Apache or Nginx) receives the request and passes it to the application server. The query content is extracted from the payload of the received request.

[0457] Input: HTTP request

[0458] Output: Extracted inquiry content

[0459] Step 4:

[0460] The server analyzes the received inquiry using natural language processing technology (NLP engine). Specifically, the engine (e.g., spaCy or NLTK) extracts important keywords from the inquiry (e.g., "order number 12345" and "shipping status").

[0461] Input: Extracted inquiry content

[0462] Output: Extracted keywords (e.g. "Order number 12345" and "Shipping status")

[0463] Step 5:

[0464] The server sends the extracted keyword information to the generative AI model, providing the data to the generative AI model along with the analyzed keywords as a prompt sentence: "Please tell me the shipping status of order number 12345."

[0465] Input: Extracted keyword information

[0466] Output: Send prompt to generative AI model

[0467] Step 6:

[0468] The generative AI model references the company's information management system (database) based on the provided prompt sentence to retrieve relevant information. For example, it retrieves information from the database that "Order number 12345 is currently being delivered." Based on this, the generative AI generates a natural language response such as, "The shipping status of order number 12345 is currently being delivered."

[0469] Input: Prompt statement and associated information from information management system

[0470] Output: Generated response

[0471] Step 7:

[0472] The server receives the response text generated by the generation AI, formats it as an HTTP response, and prepares to send it to the user's information processing device.

[0473] Input: Generated response sentence

[0474] Output: Response text formatted as an HTTP response

[0475] Step 8:

[0476] The server transmits the generated response text to the user's information processing device as an HTTP response.

[0477] Input: Response text formatted as an HTTP response

[0478] Output: Sending an HTTP response to the user's information processing device

[0479] Step 9:

[0480] The user's information processing device receives the HTTP response from the server and extracts the response text from the payload of the received response.

[0481] Input: HTTP response from the server

[0482] Output: Extracted response sentence

[0483] Step 10:

[0484] The user's information processing device displays the extracted response sentence on the screen. Specifically, information such as "The shipping status of order number 12345 is currently being delivered" is displayed in a chat window or as a notification message.

[0485] Input: Extracted response sentence

[0486] Output: Response text displayed on the screen

[0487] (Application example 1)

[0488] 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."

[0489] With the existing inquiry system, it took a long time for logistics center employees to check inventory and delivery status, reducing efficiency. Responses to inquiries were often not returned immediately, which sometimes disrupted business operations. For this reason, a system was needed that would enable logistics center employees to quickly and accurately obtain the information they needed.

[0490] 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.

[0491] In this invention, the server includes: a means for a user to input an inquiry using a terminal and send it to the server; a means for the server to receive the inquiry from the user and analyze the inquiry; a means for a generation AI to generate an appropriate response based on the analyzed inquiry; a means for a logistics center employee to inquire about stock status and delivery status; a means for making the inquiry using a smartphone; a means for sending the inquiry to the server as an HTTP request; a means for sending the generated response to the user's terminal; and a means for the user's terminal to display the response. This enables logistics center employees to quickly check stock status and delivery status.

[0492] "Means for users to input inquiries using a terminal and send them to a server" refers to a system in which users input inquiries using electronic devices such as smartphones or personal computers and send the contents to a server via a network.

[0493] "Means for the server to receive the inquiry from the user and analyze the content of the inquiry" refers to a process in which the server receives the content of the inquiry sent by the user and analyzes its content.

[0494] "Means by which the generation AI generates an appropriate response based on the analyzed inquiry content" refers to the process by which the generation AI automatically generates an appropriate response based on the information obtained from the analysis results.

[0495] "Means for logistics center employees to inquire about inventory status and delivery status" refers to a system by which employees working at logistics centers can make inquiries to check inventory information and delivery information.

[0496] "Means for making an inquiry using a smartphone" refers to a method in which a user uses a portable electronic device called a smartphone to send an inquiry to the system.

[0497] "Means of sending to the server as an HTTP request" refers to a method of sending the inquiry content to the server using HyperText Transfer Protocol (HTTP).

[0498] "Means for sending the generated response to the user's terminal" refers to the procedure for sending the response generated by the AI ​​back to the user's terminal via the network.

[0499] "Means by which the user's terminal displays the response" refers to a mechanism by which the response is displayed on the user's device.

[0500] This invention relates to a system in which a user inputs an inquiry using a terminal and sends it to a server. Specifically, it provides a system in which a logistics center employee can inquire about inventory status and delivery status using a smartphone and receive an immediate response. An embodiment of this system is described in detail below.

[0501] User inquiry processing

[0502] A user (a logistics center employee) uses a dedicated application on their smartphone to enter an inquiry. For example, they might enter "Please tell me the stock status of order number 12345" into an input field on the screen. This inquiry is sent to the server as an HTTP request.

[0503] Reception and analysis by the server

[0504] When the server receives an HTTP request from a user, it analyzes its contents. Natural language processing (NLP) technology is used for the analysis. Specifically, the server uses an NLP library such as spaCy or NLTK to parse the query and extract important information (such as the order number and requirements). For example, from the query "Please tell me the stock status of order number 12345," the keywords "order number 12345" and "stock status" are extracted. The analysis results are then saved in JSON format.

[0505] Response generation by generative AI

[0506] The server provides data to the generative AI model based on the analyzed information. The generative AI model references the company's database and generates an appropriate response to the query. For example, if the stock quantity for order number 12345 is 5, the generative AI model generates the response "There are currently 5 units of order number 12345 in stock."

[0507] Response transmission from the server to the terminal

[0508] The generated response is then sent back to the user's device as an HTTP response. When the server receives the response from the AI ​​generator and sends it to the user's device, it converts the response into a format that is easy for the user to understand.

[0509] Display on the user's device

[0510] The user's device receives the response from the server and displays it on the screen. Specifically, the information, such as "There are currently 5 units of order number 12345 in stock," is displayed in a chat window in a dedicated application or as a notification message. In this way, employees at the logistics center can quickly check the information they need.

[0511] Technology Stack

[0512] Natural Language Processing (NLP) libraries: spaCy, NLTK

[0513] Generative AI model: OpenAI GPT-3

[0514] Backend frameworks: Flask, Django

[0515] Database: MySQL, PostgreSQL

[0516] Examples of concrete examples and prompts

[0517] For example, suppose a user makes the following query:

[0518] User Input: "What is the stock status for order number 67890?"

[0519] An example of the corresponding prompt for the generative AI model:

[0520] User's question: "What is the stock status of order number 67890?"

[0521] Parsing result: {"Order number": "67890", "Requirement": "Availability"}

[0522] Example of a response generated by the Generative AI:

[0523] There are currently 5 units of order number 67890 in stock.

[0524] In this way, by using the system of the present invention, employees at the logistics center can quickly and accurately obtain the necessary information, which contributes to improving work efficiency.

[0525] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0526] Step 1:

[0527] A user uses a terminal to enter a query and send it to the server.

[0528] Specific actions: An employee at the logistics center enters "Please tell me the inventory status of order number 12345" into the input field in a dedicated application on their smartphone and presses the "Send" button.

[0529] Input: The query entered by the user.

[0530] Output: The query sent to the server as an HTTP request.

[0531] Step 2:

[0532] The server receives a query from a user and analyzes the query.

[0533] What happens: The server receives the HTTP request and uses a natural language processing (NLP) library (such as spaCy or NLTK) to extract the query. The query is parsed into "order number 12345" and "stock status" and saved in JSON format.

[0534] Input: The query received as an HTTP request.

[0535] Output: The parsed query content is saved in JSON format.

[0536] Step 3:

[0537] Based on the analyzed inquiry content, the generative AI generates an appropriate response.

[0538] Specific operation: The server sends the analysis results to a generative AI model (e.g., OpenAI GPT-3). The generative AI model works with the company's database to generate an appropriate response to the query. For example, it retrieves information from the database that there are five units of order number 12345 in stock, and generates a response saying, "There are currently five units of order number 12345 in stock."

[0539] Input: Parsed query content (JSON format).

[0540] Output: The generated response (in natural language format).

[0541] Step 4:

[0542] The generated response is sent from the server to the user's terminal.

[0543] Specific operation: The server sends the response received from the generation AI to the user's device as an HTTP response.

[0544] Input: Response from the generation AI.

[0545] Output: The HTTP response sent to the user's device.

[0546] Step 5:

[0547] The user's terminal displays the response.

[0548] Specific operation: The user's device (a dedicated smartphone application) displays the HTTP response received from the server on the screen. For example, it displays information such as "There are currently 5 units of order number 12345 in stock" in a chat window or as a notification message.

[0549] Input: The HTTP response from the server.

[0550] Output: The displayed response.

[0551] 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.

[0552] This invention relates to a system in which a user inputs a query using a terminal and sends it to a server. This system provides an appropriate response according to the user's emotions by combining it with an emotion engine that recognizes the user's emotions. Specifically, the server receives the query from the user and analyzes the content and the user's emotions. A generation AI generates an appropriate response based on the analysis results and sends it to the user's terminal. The generated response is then displayed on the user's terminal.

[0553] User inquiry processing and emotion recognition

[0554] When a user uses their device to input a query, they can do so in text, voice, or video format. For example, when they input "What is the shipping status of order number 12345?" through a chat window or voice input assistant, the emotion engine recognizes the user's emotion from their tone of voice, facial expression, and the context of the text. The device then sends the emotion data along with the query to the server.

[0555] Reception and analysis by the server

[0556] When the server receives a user inquiry, it first analyzes the emotion data provided by the emotion engine. Using a natural language processing (NLP) module, the server understands the intent of the inquiry and simultaneously grasps the user's state (e.g., anger, joy, sadness, etc.) based on the emotion data. Specifically, in response to the inquiry, "Please tell me the shipping status of order number 12345," the keywords "order number 12345" and "shipping status" are extracted, and the emotion engine simultaneously recognizes that the user is dissatisfied.

[0557] Response generation by generative AI

[0558] The server provides the analysis results and emotional data to the generation AI, which retrieves relevant information from the company's database and considers the user's emotions when generating a natural language response. For example, if the user is dissatisfied, the generation AI generates a more polite and empathetic response. Specifically, it generates a response such as, "The shipping status of order number 12345 is currently being delivered. We apologize for the inconvenience."

[0559] Response transmission from the server to the terminal

[0560] The generated response is sent to the user's device by the server, which then returns the response received from the generation AI to the user's device as an HTTP response.

[0561] Display on the user's device

[0562] The user's device displays the response received from the server. Specifically, a chat window or notification message will appear stating, "The shipping status for order number 12345 is currently being delivered. We apologize for any inconvenience." This allows the user to receive a response that takes their feelings into consideration, improving satisfaction.

[0563] Specific examples

[0564] For example, if a user uses a device to make an inquiry such as "Please reissue the invoice for order number 56789," and expresses dissatisfaction at the time, the emotion engine recognizes the user's dissatisfaction from the voice data and text sent from the device. The emotion data and inquiry content are sent to the server for analysis. The generation AI generates a response that takes the user's emotions into consideration, such as "The invoice for order number 56789 has been reissued and will be mailed shortly. We apologize for the inconvenience," and sends this response to the device via the server. Finally, the device displays this response.

[0565] In this way, the present invention provides a system that can provide quick, accurate responses to user inquiries and that also take into consideration the user's feelings, thereby greatly improving customer satisfaction and contributing to improving the quality of service provided by companies.

[0566] The processing flow will be explained below.

[0567] Step 1:

[0568] The user uses the device to input an inquiry. For example, the user may use a chat window or a voice input assistant to input, "Please tell me the shipping status of order number 12345." At this time, the device collects emotional data such as voice and facial expressions along with the user's input.

[0569] Step 2:

[0570] The device sends the collected inquiry and emotion data to the server as an HTTP request. Specifically, the inquiry is packaged as text data, audio data, or video data and sent in a format that can be analyzed by the emotion engine.

[0571] Step 3:

[0572] The server receives an HTTP request from the user, which includes the query and emotion data.

[0573] Step 4:

[0574] The server analyzes the inquiry and uses an emotion engine to analyze the user's emotions. The server uses a natural language processing (NLP) module to understand the intent of the inquiry. For example, from the text "Please tell me the shipping status of order number 12345," it extracts "order number 12345" and "shipping status," and at the same time, the emotion engine recognizes the user's dissatisfaction.

[0575] Step 5:

[0576] The server passes the analysis results (order number and requirements) and emotion data to the generation AI, which then retrieves information about order number 12345 from the company database.

[0577] Step 6:

[0578] The generative AI searches the company's database to get the latest delivery status for order number 12345. For example, it might get information like "Currently being delivered."

[0579] Step 7:

[0580] Based on the information acquired, the generation AI generates a response in natural language that takes the user's feelings into consideration. For example, if the user is dissatisfied, it generates a polite and empathetic response such as, "The shipping status of order number 12345 is currently being delivered. We apologize for the inconvenience."

[0581] Step 8:

[0582] The server receives the response from the generation AI and generates an HTTP response to send to the user's device. The response contains the generated response text.

[0583] Step 9:

[0584] The server sends an HTTP response to the user's device, which contains sentiment-sensitive text.

[0585] Step 10:

[0586] The user's device displays the response received from the server. Specifically, a chat window or notification message might say, "The shipping status for order number 12345 is currently being delivered. We apologize for any inconvenience caused." This allows the user to receive information in a way that takes their feelings into consideration.

[0587] This series of processing steps enables a response to a user's inquiry to be provided quickly, accurately, and with consideration for the user's feelings, thereby improving customer satisfaction and the quality of service provided by the company.

[0588] Example 2

[0589] 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."

[0590] Conventional inquiry response systems generate responses without considering the user's emotions, which leads to a decrease in user satisfaction. Furthermore, the accuracy of analyzing the inquiry content is low, and appropriate responses are often not generated. This results in a lack of improvement in the user experience and the quality of service provided by companies.

[0591] 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.

[0592] In this invention, the server includes a means for a user to input a query using a terminal and send it to the server, a means for the server to receive the query from the user and analyze the query content and the user's emotions, and a means for the generation AI to generate an appropriate response based on the analyzed query content and user emotion data, thereby enabling an appropriate response that takes the user's emotions into consideration.

[0593] 1. "Terminal" means a device used by a user to enter an inquiry, such as a smartphone, PC, or tablet.

[0594] 2. "Server" means a computer system whose role is to receive and analyze queries sent by users.

[0595] 3. "Query" means a question or request sent by a User to a Server using a Terminal.

[0596] 4. "Emotion" refers to the psychological state that a user exhibits when making a query, including joy, anger, sadness, surprise, etc.

[0597] 5. "Emotion engine" means software or algorithms that recognize emotions from user input data.

[0598] 6. “Natural Language Processing (NLP)” refers to techniques or methods that enable computers to understand, analyze, and generate human language.

[0599] 7. "Generative AI" is an artificial intelligence system that generates appropriate responses based on the user's inquiry and emotional data.

[0600] 8. “Database” means a structured collection of data that stores information about a company and that is referenced by Generative AI when generating responses.

[0601] 9. "HTTP request" means a request message using an Internet protocol for a terminal to send data to a server.

[0602] 10. "HTTP response" means a response message using an Internet protocol that allows a server to return data to a terminal.

[0603] This invention relates to a system in which a user inputs a query using a terminal and sends it to a server. This system provides an appropriate response according to the user's emotion by combining it with an emotion engine that recognizes the user's emotion.

[0604] composition

[0605] User inquiry input and submission

[0606] A user uses a device such as a smartphone or PC to input a query in text, voice, or video format. For example, they might input "What is the shipping status of order number 12345?" through a chat window or voice input assistant. The device is equipped with an emotion engine that recognizes emotions from the user's tone of voice, facial expressions, and text context. The device then sends the emotion data along with the query to the server.

[0607] Reception and analysis by the server

[0608] When the server receives a query from a user, it first analyzes the provided emotion data using the emotion engine. Using a natural language processing (NLP) module, the server understands the intent of the query and simultaneously grasps the user's emotional state (e.g., anger, joy, sadness, etc.) based on the emotion data. For example, in response to a query such as "Please tell me the shipping status of order number 12345," the keywords "order number 12345" and "shipping status" are extracted, and it is recognized that the user is dissatisfied.

[0609] Response generation by generative AI

[0610] The server provides the analysis results and emotional data to the generation AI, which retrieves relevant information from the company's database and considers the user's emotions when generating a natural language response. For example, if the user is dissatisfied, the generation AI will generate a more polite and empathetic response. A response such as "The shipping status of order number 12345 is currently being delivered. We apologize for the inconvenience."

[0611] Response transmission from the server to the terminal

[0612] The generated response is sent to the user's device by the server. The server returns the response received from the generation AI to the user's device as an HTTP response.

[0613] Display on the user's device

[0614] The user's device displays the response received from the server. For example, a chat window or notification message might say, "The shipping status for order number 12345 is currently being delivered. We apologize for any inconvenience." This allows the user to receive a response that takes their feelings into consideration, improving satisfaction.

[0615] Specific examples and examples of prompts for generative AI models

[0616] For example, if a user uses a device to make an inquiry such as "Please reissue the invoice for order number 56789," and expresses dissatisfaction at the time, the emotion engine will recognize the user's dissatisfaction from the voice and text data sent from the device. The emotion data and the inquiry content are sent to the server for analysis. The generation AI will generate a response that takes the user's emotions into consideration, such as "The invoice for order number 56789 has been reissued and will be mailed shortly. We apologize for the inconvenience," and send it to the device via the server. Finally, the device will display this response.

[0617] Example prompt for a generative AI model: "The user is asking, 'What is the shipping status for order 12345?' The user is frustrated. Please respond in a kind and polite manner."

[0618] In this way, the present invention realizes a system that provides quick, accurate responses to user inquiries and takes into consideration the user's feelings, thereby contributing to improved customer satisfaction and the quality of corporate services.

[0619] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0620] Step 1:

[0621] The user enters a query

[0622] Input: The user uses a smartphone or computer to input a query by text or voice through a chat window or voice input assistant.

[0623] What happens: The user types into the chat window, "What is the shipping status of order number 12345?" If the user types, the device uses voice recognition software to convert the speech into text.

[0624] Output: Query data in text format.

[0625] Step 2:

[0626] The device recognizes emotions

[0627] Input: Query data in text format.

[0628] Specific operation: The device uses the emotion engine to recognize emotions from the user's input data. For example, it uses the "Emotion SDK" to analyze the user's tone of voice and facial expressions.

[0629] Output: Enquiry and sentiment data (e.g. dissatisfaction).

[0630] Step 3:

[0631] The device sends the data to the server

[0632] Input: Enquiry content and emotion data.

[0633] Specific operation: The device generates an HTTP request and sends the query content and emotion data to the server.

[0634] Output: The query and emotion data sent to the server.

[0635] Step 4:

[0636] The server receives and analyzes the data

[0637] Input: Inquiry content and emotion data sent from the device.

[0638] Specific operation: The server receives an HTTP request, analyzes the provided emotion data using the emotion engine, and then analyzes the intent of the query using the natural language processing (NLP) module.

[0639] Output: Parsed query content and sentiment data.

[0640] Step 5:

[0641] The server sends the data to the generated AI.

[0642] Input: Parsed query content and sentiment data.

[0643] Specific operation: The server sends the analysis results to the generation AI. A prompt is generated, for example, "Please tell me the shipping status of order number 12345. The user is dissatisfied. Please respond in a kind and polite manner."

[0644] Output: The prompt sent to the generation AI and the analysis results.

[0645] Step 6:

[0646] Generative AI generates responses

[0647] Input: Prompt sentence and parsed result sent from the server.

[0648] Specific operation: The generative AI (e.g., GPT-4) refers to a company's database (e.g., PostgreSQL) and generates a response that takes the user's emotions into account.

[0649] Output: The generated response text (e.g., "Order 12345 is currently on its way. We apologize for any inconvenience.").

[0650] Step 7:

[0651] The server receives the generated response

[0652] Input: The response text sent by the generation AI.

[0653] Specific operation: The server receives the response generated from the generation AI.

[0654] Output: The response text received.

[0655] Step 8:

[0656] The server sends the response to the user's device

[0657] Input: The response text received.

[0658] Specific operation: The server creates an HTTP response and sends the generated response to the user's terminal.

[0659] Output: The response text sent to the user's terminal.

[0660] Step 9:

[0661] The user's device displays the response

[0662] Input: The response text sent by the server.

[0663] Specific operation: The user's device receives the HTTP response and displays the response in a chat window or as a notification message.

[0664] Output: Response text displayed on the user's device (e.g., "Order 12345 is currently on its way. We apologize for any inconvenience.").

[0665] (Application example 2)

[0666] 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."

[0667] In electronic payment services, when responding to user inquiries, it is necessary to appropriately recognize the user's emotions and provide a response based on those emotions. Conventional systems do not take the user's emotions into consideration, which has led to the problem of not being able to fully alleviate the user's dissatisfaction and anxiety, resulting in a decrease in customer satisfaction. In order to solve this problem, the present invention aims to provide a system that recognizes the user's emotions and provides a response based on those emotions.

[0668] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0669] In this invention, the server includes: a means for a user to input a query using a terminal and send it to the server; a means for the server to receive the query from the user and analyze the query content and the user's emotions; a means for a generation AI to generate an appropriate response based on the analyzed query content and emotion data; a means for sending the generated response to the user's terminal; and a means for the user's terminal to display the response, characterized in that a response corresponding to the user's emotions is provided. This makes it possible to provide a quick and accurate response while taking the user's emotions into consideration.

[0670] "User" refers to a user who makes an inquiry using a terminal.

[0671] "Terminal" refers to a device through which a user inputs a query and communicates with a server.

[0672] "Server" refers to a computer system that receives queries from users, analyzes them, and generates responses.

[0673] "Query" refers to a question or request that a user sends to a server through a terminal.

[0674] "Emotion" refers to the psychological state that a user exhibits when making a query.

[0675] An "emotion engine" refers to software that analyzes a user's emotions and generates data based on them.

[0676] "Analyzing" means that the server understands the content of the inquiry and the emotional data and performs appropriate processing.

[0677] "Generative AI" refers to artificial intelligence that generates appropriate responses based on the content of inquiries and emotional data.

[0678] "Response" refers to the answer or information that the server generates in response to a user's inquiry through generation AI.

[0679] "Displaying" refers to visually showing the response sent from the server on the user's terminal.

[0680] The present invention relates to a system that allows a user to input a query using a terminal, transmit the query to a server, and provide an appropriate response based on the user's emotions. The system of the present invention has the following configuration.

[0681] System configuration

[0682] 1. User Device:

[0683] A device for users to input queries. This device can be a smartphone or a head-mounted display. Users can submit queries in text, voice, or video format.

[0684] 2. Server:

[0685] A computer system that receives and analyzes queries sent from user terminals. The server contains the following main modules:

[0686] Emotion engine: Software that analyzes user emotions. It uses emotion recognition libraries (e.g., IBM Watson Tone Analyzer).

[0687] Natural Language Processing (NLP) module: Analyzes the query content and extracts key intent and keywords. Uses natural language processing libraries (e.g., spaCy, NLTK, etc.).

[0688] Generative AI module: Artificial intelligence that generates appropriate responses based on analysis results. It uses a generative AI model (e.g., OpenAI's GPT-4).

[0689] HTTP communication module: Communicates with the user terminal using a web server (e.g., Flask, Django, etc.).

[0690] 3. Response display:

[0691] This module displays the generated responses on the user's device. It includes a user interface (UI) module, which displays the responses as chat windows and notification messages.

[0692] Processing flow and specific examples

[0693] 1. Inquiry received:

[0694] A user makes an inquiry via their smartphone, saying, "I'm worried about suspicious activity in my recent transaction history." This inquiry is sent to the server as text or voice data.

[0695] 2. Emotion analysis:

[0696] The server's emotion engine recognizes the user's anxiety from the inquiry content and generates emotion data.

[0697] 3. Query Analysis:

[0698] The server's natural language processing (NLP) module extracts keywords such as "recent transaction history" and "suspicious activity," while simultaneously recognizing that the user is feeling "anxious."

[0699] 4. Response generation by generative AI:

[0700] The generative AI module generates a response based on the extracted intent and sentiment data, such as, "We have not found any suspicious activity in your recent transaction history. Rest assured, if you require further clarification, please feel free to contact us."

[0701] 5. Response transmission and display:

[0702] The generated response is sent to the user's terminal via the server and displayed in a chat window or as a notification message.

[0703] Prompt Sentence Examples

[0704] If a user says, "I'm concerned about suspicious activity in my recent transactions," the following prompt is passed to the AI ​​generator:

[0705] User: I'm concerned about suspicious activity in my recent transaction history.

[0706] Emotion: Anxiety

[0707] Response: We have not found any suspicious activity in your recent transaction history. Rest assured, if you require further clarification, please feel free to contact us.

[0708] As described above, the present invention aims to improve customer satisfaction by providing a quick and accurate response while taking into consideration the user's feelings.

[0709] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0710] Step 1: Enter and submit your inquiry

[0711] A user uses a terminal to input a query. For example, text or voice data such as "I'm concerned about suspicious activity in my recent transaction history" is input. This query is sent from the terminal to the server. The input is text or voice data, and the output is query data. The terminal sends the query data to the server.

[0712] Step 2: Inquiry reception and sentiment analysis

[0713] The server receives the inquiry data sent by the user. The received data is passed to the emotion engine, which analyzes the user's emotions. Specifically, an emotion recognition library (e.g., IBM Watson Tone Analyzer) is used to analyze the tone of the voice and the context of the text using a unique algorithm to determine the user's mental state. The input is the inquiry data, and the output is the analyzed emotion data.

[0714] Step 3: Analyzing the inquiry

[0715] The server passes the query content, along with the emotion data received from the emotion engine, to a natural language processing (NLP) module. The NLP module extracts the intent and key keywords of the query through a directed process. For example, it uses libraries such as spaCy and NLTK to extract key keywords such as "transaction history" and "suspicious activity." The input is the query data and emotion data, and the output is the parsed intent and keywords.

[0716] Step 4: Response Generation

[0717] The analyzed intent, keywords, and even sentiment data are passed to a generative AI module, which uses this data to generate an appropriate response. This is done using an AI model (e.g., OpenAI GPT-4) that synthesizes the extracted information to generate a human-like natural language response. For example, a response might read, "We have not found any suspicious activity in your recent transaction history. Rest assured, if you require further clarification, please feel free to contact us." The input is the analyzed intent, keywords, and sentiment data, and the output is the generated response.

[0718] Step 5: Send response

[0719] The HTTP communication module receives the response generated by the generation AI module and sends it to the user's device. Specifically, the generated response is encoded as an HTTP response and sent to the device as appropriate. During this process, a security layer is applied to ensure the confidentiality and integrity of the data. The input is the generated response data, and the output is an HTTP response to the device.

[0720] Step 6: Display the response

[0721] The user terminal decodes the HTTP response received from the server and displays it through the user interface (UI) module. The response is displayed in a user-friendly format, such as a chat window or notification message, allowing the user to confirm the appropriate response. The input is the received HTTP response, and the output is the displayed response message.

[0722] 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.

[0723] 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.

[0724] 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.

[0725] [Third embodiment]

[0726] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0727] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0728] 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).

[0729] 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.

[0730] 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.

[0731] 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).

[0732] 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.

[0733] 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.

[0734] 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.

[0735] 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.

[0736] 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.

[0737] 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."

[0738] This invention relates to a system in which a user inputs a query using a terminal and sends it to a server. The server receives the query from the user and analyzes its contents. The analyzed results are sent to a generation AI, which generates an appropriate response. The generated response is then sent to the user's terminal and displayed.

[0739] User inquiry processing

[0740] Users access the system using their own devices (such as smartphones or PCs). For example, they access a call center inquiry form using a web browser or dedicated application and enter an inquiry such as, "Please tell me the shipping status of order number 12345." The device then sends this inquiry to the server as an HTTP request.

[0741] Reception and analysis by the server

[0742] When the server receives a user inquiry, it automatically begins the process of analyzing the inquiry. The server uses natural language processing (NLP) technology to parse the inquiry and extract important information (such as the order number and requirements). Specifically, from the inquiry "Please tell me the shipping status of order number 12345," the keywords "order number 12345" and "shipping status" are extracted.

[0743] Response generation by generative AI

[0744] The server provides data to the generation AI based on the analysis results. The generation AI retrieves relevant information from the company's database and generates a response in natural language. For example, if order number 12345 is currently being delivered, the generation AI generates a response saying, "The shipping status of order number 12345 is currently being delivered."

[0745] Response transmission from the server to the terminal

[0746] The generated response is sent back to the user's device by the server, which then returns the response received from the generation AI to the user's device as an HTTP response.

[0747] Display on the user's device

[0748] The user's device receives the response from the server and displays it on the screen. Specifically, the information such as "Shipping status of order number 12345 is currently being delivered" is displayed in a chat window or as a notification message.

[0749] Specific examples

[0750] For example, if a user uses a device to make a query such as "Please reissue the invoice for order number 56789," the device sends this query to the server. The server uses NLP technology to analyze the query and extract the information "order number 56789" and "invoice reissue." The generation AI then references the company's database, checks the reissue procedure and status of the relevant invoice, and generates a response such as "The invoice for order number 56789 has been reissued and will be mailed shortly." This response is then sent back to the user's device via the server and displayed on the user's screen.

[0751] In this way, the present invention provides a system that can provide quick and accurate responses to user inquiries, and is beneficial to both companies and customers.

[0752] The processing flow will be explained below.

[0753] Step 1:

[0754] A user uses a terminal to enter an inquiry. The user enters "Please tell me the shipping status of order number 12345" into a call center inquiry form or chat window and clicks the send button.

[0755] Step 2:

[0756] The device sends the user's inquiry as an HTTP request to the server. Specifically, the inquiry content is packaged in a data format such as JSON and sent to the specified endpoint on the server.

[0757] Step 3:

[0758] The server receives an HTTP request from a user, which includes the query and the user's identity.

[0759] Step 4:

[0760] The server analyzes the query. It uses a natural language processing (NLP) module to understand the intent of the query. Specifically, it extracts "order number 12345" and "shipping status" from the text "Please tell me the shipping status of order number 12345."

[0761] Step 5:

[0762] The server passes the parsed results to the generation AI, which retrieves information about order number 12345 from the company database.

[0763] Step 6:

[0764] The generative AI searches the company's database to retrieve the necessary information. For example, it retrieves the latest delivery status of order number 12345 and obtains information such as "Currently being delivered."

[0765] Step 7:

[0766] The generation AI generates a response in natural language based on the information it obtains. For example, it generates a response text such as, "The shipping status of order number 12345 is currently being delivered."

[0767] Step 8:

[0768] The server receives the response from the generation AI and generates an HTTP response to send to the user's device.

[0769] Step 9:

[0770] The server sends an HTTP response to the user's device, which includes the generated response text.

[0771] Step 10:

[0772] The user's device displays the response received from the server. Specifically, it displays the message "Order number 12345 is currently being delivered" in a chat window or as a notification message.

[0773] This series of processing steps provides fast and accurate responses to user inquiries, improving customer satisfaction.

[0774] Example 1

[0775] 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."

[0776] Conventional inquiry systems have problems such as delayed responses to user inquiries and inaccurate information provided. Furthermore, the content of the user's inquiry is not clearly analyzed, leading to inappropriate responses. Therefore, there is a demand for a system that can respond to user inquiries quickly and accurately.

[0777] 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.

[0778] In this invention, the server includes means for a user to input an inquiry using an information processing device and transmit the inquiry to the server, means for the server to receive the inquiry from the user and analyze the inquiry, means for a generation AI to generate an appropriate response based on the analyzed inquiry, means for transmitting the generated response to the user's information processing device, and means for the user's information processing device to display the response, thereby making it possible to provide a quick and accurate response to a user's inquiry.

[0779] A "user" is a person who operates an information processing device to make an inquiry.

[0780] An "information processing device" is an electronic device that allows a user to input an inquiry and send it to a server via the Internet, and includes devices such as smartphones and personal computers.

[0781] A "server" is a computer system that receives inquiries sent by users and analyzes and processes the contents of those inquiries.

[0782] An "inquiry" refers to a question or request that a user sends to the system via an information processing device.

[0783] "Natural language processing technology" is a technical method that allows computers to understand and analyze human language, and includes techniques such as text analysis and keyword extraction.

[0784] "Generative AI" refers to an artificial intelligence model that generates appropriate responses based on analyzed query content.

[0785] An "information management system" is a system that includes databases and other information resources referenced by generative AI, such as corporate databases.

[0786] This invention relates to a system in which a user inputs a query using an information processing device and sends the query to a server. The server receives the query from the user and analyzes the content of the query using natural language processing technology. The analyzed results are sent to a generation AI, which generates an appropriate response. The generated response is then sent to the user's information processing device and displayed.

[0787] A user accesses the system using their own information processing device (for example, a smartphone or PC). Specifically, they use a web browser or a dedicated application to enter a query into an inquiry form, such as "Please tell me the shipping status of order number 12345." The information processing device then sends this query to the server as an HTTP request.

[0788] When the server receives a user inquiry, it automatically begins the process of analyzing the inquiry. The server uses natural language processing (NLP) technology to parse the inquiry and extract important information (such as the order number and requirements). Specifically, from the inquiry "Please tell me the shipping status of order number 12345," the keywords "order number 12345" and "shipping status" are extracted.

[0789] The server provides the extracted keyword information to the generation AI, which retrieves relevant information from the company's information management system (database) and generates a response in natural language. For example, if order number 12345 is currently being delivered, the generation AI generates the response, "The shipping status of order number 12345 is currently being delivered."

[0790] The generated response is sent again by the server to the user's information processing device. The server returns the response received from the generation AI to the user's information processing device as an HTTP response. The user's information processing device receives the response from the server and displays it on the screen. Specifically, information such as "Shipping status of order number 12345 is currently being delivered" is displayed in a chat window or as a notification message.

[0791] As a specific example, consider the case where a user makes an inquiry such as, "Please reissue the invoice for order number 56789." In this case, the information processing device sends this inquiry to the server. The server uses NLP technology to analyze the inquiry and extracts the information "order number 56789" and "invoice reissue." The generation AI references the company's information management system to obtain the relevant information and generates a response such as, "The invoice for order number 56789 has been reissued and will be mailed shortly." This response is then sent again via the server to the user's information processing device and displayed on the user's screen.

[0792] Here is an example prompt:

[0793] User's inquiry: Please let me know the shipping status of order number 12345.

[0794] Information from company database: Order number 12345 is currently being shipped.

[0795] Response to generate: Order 12345 is currently in transit.

[0796] In this way, the present invention can provide a fast and accurate response to user inquiries, thereby providing a system that is beneficial to both companies and customers.

[0797] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0798] Step 1:

[0799] A user inputs a query using an information processing device. Specifically, the user inputs a query such as "Please tell me the shipping status of order number 12345" using a dedicated application or web browser on a smartphone or PC. The input query is formatted as the payload of an HTTP request.

[0800] Input: User inquiry (e.g., "Please tell me the shipping status of order number 12345.")

[0801] Output: The query formatted as an HTTP request

[0802] Step 2:

[0803] The terminal sends the input query to the server. Specifically, it sends a request including the query content payload as an HTTP POST request to the specified server URL.

[0804] Input: Query content formatted as an HTTP request

[0805] Output: HTTP request sent to the server

[0806] Step 3:

[0807] The server receives an HTTP request from the user. The web server (e.g., Apache or Nginx) receives the request and passes it to the application server. The query content is extracted from the payload of the received request.

[0808] Input: HTTP request

[0809] Output: Extracted inquiry content

[0810] Step 4:

[0811] The server analyzes the received inquiry using natural language processing technology (NLP engine). Specifically, the engine (e.g., spaCy or NLTK) extracts important keywords from the inquiry (e.g., "order number 12345" and "shipping status").

[0812] Input: Extracted inquiry content

[0813] Output: Extracted keywords (e.g. "Order number 12345" and "Shipping status")

[0814] Step 5:

[0815] The server sends the extracted keyword information to the generative AI model, providing the data to the generative AI model along with the analyzed keywords as a prompt sentence: "Please tell me the shipping status of order number 12345."

[0816] Input: Extracted keyword information

[0817] Output: Send prompt to generative AI model

[0818] Step 6:

[0819] The generative AI model references the company's information management system (database) based on the provided prompt sentence to retrieve relevant information. For example, it retrieves information from the database that "Order number 12345 is currently being delivered." Based on this, the generative AI generates a natural language response such as, "The shipping status of order number 12345 is currently being delivered."

[0820] Input: Prompt statement and associated information from information management system

[0821] Output: Generated response

[0822] Step 7:

[0823] The server receives the response text generated by the generation AI, formats it as an HTTP response, and prepares to send it to the user's information processing device.

[0824] Input: Generated response sentence

[0825] Output: Response text formatted as an HTTP response

[0826] Step 8:

[0827] The server transmits the generated response text to the user's information processing device as an HTTP response.

[0828] Input: Response text formatted as an HTTP response

[0829] Output: Sending an HTTP response to the user's information processing device

[0830] Step 9:

[0831] The user's information processing device receives the HTTP response from the server and extracts the response text from the payload of the received response.

[0832] Input: HTTP response from the server

[0833] Output: Extracted response sentence

[0834] Step 10:

[0835] The user's information processing device displays the extracted response sentence on the screen. Specifically, information such as "The shipping status of order number 12345 is currently being delivered" is displayed in a chat window or as a notification message.

[0836] Input: Extracted response sentence

[0837] Output: Response text displayed on the screen

[0838] (Application example 1)

[0839] 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."

[0840] With the existing inquiry system, it took a long time for logistics center employees to check inventory and delivery status, reducing efficiency. Responses to inquiries were often not returned immediately, which sometimes disrupted business operations. For this reason, a system was needed that would enable logistics center employees to quickly and accurately obtain the information they needed.

[0841] 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.

[0842] In this invention, the server includes: a means for a user to input an inquiry using a terminal and send it to the server; a means for the server to receive the inquiry from the user and analyze the inquiry; a means for a generation AI to generate an appropriate response based on the analyzed inquiry; a means for a logistics center employee to inquire about stock status and delivery status; a means for making the inquiry using a smartphone; a means for sending the inquiry to the server as an HTTP request; a means for sending the generated response to the user's terminal; and a means for the user's terminal to display the response. This enables logistics center employees to quickly check stock status and delivery status.

[0843] "Means for users to input inquiries using a terminal and send them to a server" refers to a system in which users input inquiries using electronic devices such as smartphones or personal computers and send the contents to a server via a network.

[0844] "Means for the server to receive the inquiry from the user and analyze the content of the inquiry" refers to a process in which the server receives the content of the inquiry sent by the user and analyzes its content.

[0845] "Means by which the generation AI generates an appropriate response based on the analyzed inquiry content" refers to the process by which the generation AI automatically generates an appropriate response based on the information obtained from the analysis results.

[0846] "Means for logistics center employees to inquire about inventory status and delivery status" refers to a system by which employees working at logistics centers can make inquiries to check inventory information and delivery information.

[0847] "Means for making an inquiry using a smartphone" refers to a method in which a user uses a portable electronic device called a smartphone to send an inquiry to the system.

[0848] "Means of sending to the server as an HTTP request" refers to a method of sending the inquiry content to the server using HyperText Transfer Protocol (HTTP).

[0849] "Means for sending the generated response to the user's terminal" refers to the procedure for sending the response generated by the AI ​​back to the user's terminal via the network.

[0850] "Means by which the user's terminal displays the response" refers to a mechanism by which the response is displayed on the user's device.

[0851] This invention relates to a system in which a user inputs an inquiry using a terminal and sends it to a server. Specifically, it provides a system in which a logistics center employee can inquire about inventory status and delivery status using a smartphone and receive an immediate response. An embodiment of this system is described in detail below.

[0852] User inquiry processing

[0853] A user (a logistics center employee) uses a dedicated application on their smartphone to enter an inquiry. For example, they might enter "Please tell me the stock status of order number 12345" into an input field on the screen. This inquiry is sent to the server as an HTTP request.

[0854] Reception and analysis by the server

[0855] When the server receives an HTTP request from a user, it analyzes its contents. Natural language processing (NLP) technology is used for the analysis. Specifically, the server uses an NLP library such as spaCy or NLTK to parse the query and extract important information (such as the order number and requirements). For example, from the query "Please tell me the stock status of order number 12345," the keywords "order number 12345" and "stock status" are extracted. The analysis results are then saved in JSON format.

[0856] Response generation by generative AI

[0857] The server provides data to the generative AI model based on the analyzed information. The generative AI model references the company's database and generates an appropriate response to the query. For example, if the stock quantity for order number 12345 is 5, the generative AI model generates the response "There are currently 5 units of order number 12345 in stock."

[0858] Response transmission from the server to the terminal

[0859] The generated response is then sent back to the user's device as an HTTP response. When the server receives the response from the AI ​​generator and sends it to the user's device, it converts the response into a format that is easy for the user to understand.

[0860] Display on the user's device

[0861] The user's device receives the response from the server and displays it on the screen. Specifically, the information, such as "There are currently 5 units of order number 12345 in stock," is displayed in a chat window in a dedicated application or as a notification message. In this way, employees at the logistics center can quickly check the information they need.

[0862] Technology Stack

[0863] Natural Language Processing (NLP) libraries: spaCy, NLTK

[0864] Generative AI model: OpenAI GPT-3

[0865] Backend frameworks: Flask, Django

[0866] Database: MySQL, PostgreSQL

[0867] Examples of specific examples and prompts

[0868] For example, suppose a user makes the following query:

[0869] User Input: "What is the stock status for order number 67890?"

[0870] An example of the corresponding prompt for the generative AI model:

[0871] User's question: "What is the stock status of order number 67890?"

[0872] Parsing result: {"Order number": "67890", "Requirement": "Availability"}

[0873] Example of a response generated by the Generative AI:

[0874] There are currently 5 units of order number 67890 in stock.

[0875] In this way, by using the system of the present invention, employees at the logistics center can quickly and accurately obtain the necessary information, which contributes to improving work efficiency.

[0876] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0877] Step 1:

[0878] A user uses a terminal to enter a query and send it to the server.

[0879] Specific actions: An employee at the logistics center enters "Please tell me the inventory status of order number 12345" into the input field in a dedicated application on their smartphone and presses the "Send" button.

[0880] Input: The query entered by the user.

[0881] Output: The query sent to the server as an HTTP request.

[0882] Step 2:

[0883] The server receives a query from a user and analyzes the query.

[0884] What happens: The server receives the HTTP request and uses a natural language processing (NLP) library (such as spaCy or NLTK) to extract the query. The query is parsed into "order number 12345" and "stock status" and saved in JSON format.

[0885] Input: The query received as an HTTP request.

[0886] Output: The parsed query content is saved in JSON format.

[0887] Step 3:

[0888] Based on the analyzed inquiry content, the generative AI generates an appropriate response.

[0889] Specific operation: The server sends the analysis results to a generative AI model (e.g., OpenAI GPT-3). The generative AI model works with the company's database to generate an appropriate response to the query. For example, it retrieves information from the database that there are five units of order number 12345 in stock, and generates a response saying, "There are currently five units of order number 12345 in stock."

[0890] Input: Parsed query content (JSON format).

[0891] Output: The generated response (in natural language format).

[0892] Step 4:

[0893] The generated response is sent from the server to the user's terminal.

[0894] Specific operation: The server sends the response received from the generation AI to the user's device as an HTTP response.

[0895] Input: Response from the generation AI.

[0896] Output: The HTTP response sent to the user's device.

[0897] Step 5:

[0898] The user's terminal displays the response.

[0899] Specific operation: The user's device (a dedicated smartphone application) displays the HTTP response received from the server on the screen. For example, it displays information such as "There are currently 5 units of order number 12345 in stock" in a chat window or as a notification message.

[0900] Input: The HTTP response from the server.

[0901] Output: The displayed response.

[0902] 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.

[0903] This invention relates to a system in which a user inputs a query using a terminal and sends it to a server. This system provides an appropriate response according to the user's emotions by combining it with an emotion engine that recognizes the user's emotions. Specifically, the server receives the query from the user and analyzes the content and the user's emotions. A generation AI generates an appropriate response based on the analysis results and sends it to the user's terminal. The generated response is then displayed on the user's terminal.

[0904] User inquiry processing and emotion recognition

[0905] When a user uses their device to input a query, they can do so in text, voice, or video format. For example, when they input "What is the shipping status of order number 12345?" through a chat window or voice input assistant, the emotion engine recognizes the user's emotion from their tone of voice, facial expression, and the context of the text. The device then sends the emotion data along with the query to the server.

[0906] Reception and analysis by the server

[0907] When the server receives a user inquiry, it first analyzes the emotion data provided by the emotion engine. Using a natural language processing (NLP) module, the server understands the intent of the inquiry and simultaneously grasps the user's state (e.g., anger, joy, sadness, etc.) based on the emotion data. Specifically, in response to the inquiry, "Please tell me the shipping status of order number 12345," the keywords "order number 12345" and "shipping status" are extracted, and the emotion engine simultaneously recognizes that the user is dissatisfied.

[0908] Response generation by generative AI

[0909] The server provides the analysis results and emotional data to the generation AI, which retrieves relevant information from the company's database and considers the user's emotions when generating a natural language response. For example, if the user is dissatisfied, the generation AI generates a more polite and empathetic response. Specifically, it generates a response such as, "The shipping status of order number 12345 is currently being delivered. We apologize for the inconvenience."

[0910] Response transmission from the server to the terminal

[0911] The generated response is sent to the user's device by the server, which then returns the response received from the generation AI to the user's device as an HTTP response.

[0912] Display on the user's device

[0913] The user's device displays the response received from the server. Specifically, a chat window or notification message will appear stating, "The shipping status for order number 12345 is currently being delivered. We apologize for any inconvenience." This allows the user to receive a response that takes their feelings into consideration, improving satisfaction.

[0914] Specific examples

[0915] For example, if a user uses a device to make an inquiry such as "Please reissue the invoice for order number 56789," and expresses dissatisfaction at the time, the emotion engine recognizes the user's dissatisfaction from the voice data and text sent from the device. The emotion data and inquiry content are sent to the server for analysis. The generation AI generates a response that takes the user's emotions into consideration, such as "The invoice for order number 56789 has been reissued and will be mailed shortly. We apologize for the inconvenience," and sends this response to the device via the server. Finally, the device displays this response.

[0916] In this way, the present invention provides a system that can provide quick, accurate responses to user inquiries and that also take into consideration the user's feelings, thereby greatly improving customer satisfaction and contributing to improving the quality of service provided by companies.

[0917] The processing flow will be explained below.

[0918] Step 1:

[0919] The user uses the device to input an inquiry. For example, the user may use a chat window or a voice input assistant to input, "Please tell me the shipping status of order number 12345." At this time, the device collects emotional data such as voice and facial expressions along with the user's input.

[0920] Step 2:

[0921] The device sends the collected inquiry and emotion data to the server as an HTTP request. Specifically, the inquiry is packaged as text data, audio data, or video data and sent in a format that can be analyzed by the emotion engine.

[0922] Step 3:

[0923] The server receives an HTTP request from the user, which includes the query and emotion data.

[0924] Step 4:

[0925] The server analyzes the inquiry and uses an emotion engine to analyze the user's emotions. The server uses a natural language processing (NLP) module to understand the intent of the inquiry. For example, from the text "Please tell me the shipping status of order number 12345," it extracts "order number 12345" and "shipping status," and at the same time, the emotion engine recognizes the user's dissatisfaction.

[0926] Step 5:

[0927] The server passes the analysis results (order number and requirements) and emotion data to the generation AI, which then retrieves information about order number 12345 from the company database.

[0928] Step 6:

[0929] The generative AI searches the company's database to get the latest delivery status for order number 12345. For example, it might get information like "Currently being delivered."

[0930] Step 7:

[0931] Based on the information acquired, the generation AI generates a response in natural language that takes the user's feelings into consideration. For example, if the user is dissatisfied, it generates a polite and empathetic response such as, "The shipping status of order number 12345 is currently being delivered. We apologize for the inconvenience."

[0932] Step 8:

[0933] The server receives the response from the generation AI and generates an HTTP response to send to the user's device. The response contains the generated response text.

[0934] Step 9:

[0935] The server sends an HTTP response to the user's device, which contains sentiment-sensitive text.

[0936] Step 10:

[0937] The user's device displays the response received from the server. Specifically, a chat window or notification message might say, "The shipping status for order number 12345 is currently being delivered. We apologize for any inconvenience caused." This allows the user to receive information in a way that takes their feelings into consideration.

[0938] This series of processing steps enables a response to a user's inquiry to be provided quickly, accurately, and with consideration for the user's feelings, thereby improving customer satisfaction and the quality of service provided by the company.

[0939] Example 2

[0940] 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."

[0941] Conventional inquiry response systems generate responses without considering the user's emotions, which leads to a decrease in user satisfaction. Furthermore, the accuracy of analyzing the inquiry content is low, and appropriate responses are often not generated. This results in a lack of improvement in the user experience and the quality of service provided by companies.

[0942] 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.

[0943] In this invention, the server includes a means for a user to input a query using a terminal and send it to the server, a means for the server to receive the query from the user and analyze the query content and the user's emotions, and a means for the generation AI to generate an appropriate response based on the analyzed query content and user emotion data, thereby enabling an appropriate response that takes the user's emotions into consideration.

[0944] 1. "Terminal" means a device used by a user to enter an inquiry, such as a smartphone, PC, or tablet.

[0945] 2. "Server" means a computer system whose role is to receive and analyze queries sent by users.

[0946] 3. "Query" means a question or request sent by a User to a Server using a Terminal.

[0947] 4. "Emotion" refers to the psychological state that a user exhibits when making a query, including joy, anger, sadness, surprise, etc.

[0948] 5. "Emotion engine" means software or algorithms that recognize emotions from user input data.

[0949] 6. “Natural Language Processing (NLP)” refers to techniques or methods that enable computers to understand, analyze, and generate human language.

[0950] 7. "Generative AI" is an artificial intelligence system that generates appropriate responses based on the user's inquiry and emotional data.

[0951] 8. “Database” means a structured collection of data that stores information about a company and that is referenced by Generative AI when generating responses.

[0952] 9. "HTTP request" means a request message using an Internet protocol for a terminal to send data to a server.

[0953] 10. "HTTP response" means a response message using an Internet protocol that allows a server to return data to a terminal.

[0954] This invention relates to a system in which a user inputs a query using a terminal and sends it to a server. This system provides an appropriate response according to the user's emotion by combining it with an emotion engine that recognizes the user's emotion.

[0955] composition

[0956] User inquiry input and submission

[0957] A user uses a device such as a smartphone or PC to input a query in text, voice, or video format. For example, they might input "What is the shipping status of order number 12345?" through a chat window or voice input assistant. The device is equipped with an emotion engine that recognizes emotions from the user's tone of voice, facial expressions, and text context. The device then sends the emotion data along with the query to the server.

[0958] Reception and analysis by the server

[0959] When the server receives a query from a user, it first analyzes the provided emotion data using the emotion engine. Using a natural language processing (NLP) module, the server understands the intent of the query and simultaneously grasps the user's emotional state (e.g., anger, joy, sadness, etc.) based on the emotion data. For example, in response to a query such as "Please tell me the shipping status of order number 12345," the keywords "order number 12345" and "shipping status" are extracted, and it is recognized that the user is dissatisfied.

[0960] Response generation by generative AI

[0961] The server provides the analysis results and emotional data to the generation AI, which retrieves relevant information from the company's database and considers the user's emotions when generating a natural language response. For example, if the user is dissatisfied, the generation AI will generate a more polite and empathetic response. A response such as "The shipping status of order number 12345 is currently being delivered. We apologize for the inconvenience."

[0962] Response transmission from the server to the terminal

[0963] The generated response is sent to the user's device by the server. The server returns the response received from the generation AI to the user's device as an HTTP response.

[0964] Display on the user's device

[0965] The user's device displays the response received from the server. For example, a chat window or notification message might say, "The shipping status for order number 12345 is currently being delivered. We apologize for any inconvenience." This allows the user to receive a response that takes their feelings into consideration, improving satisfaction.

[0966] Specific examples and examples of prompts for generative AI models

[0967] For example, if a user uses a device to make an inquiry such as "Please reissue the invoice for order number 56789," and expresses dissatisfaction at the time, the emotion engine will recognize the user's dissatisfaction from the voice and text data sent from the device. The emotion data and the inquiry content are sent to the server for analysis. The generation AI will generate a response that takes the user's emotions into consideration, such as "The invoice for order number 56789 has been reissued and will be mailed shortly. We apologize for the inconvenience," and send it to the device via the server. Finally, the device will display this response.

[0968] Example prompt for a generative AI model: "The user is asking, 'What is the shipping status for order 12345?' The user is frustrated. Please respond in a kind and polite manner."

[0969] In this way, the present invention realizes a system that provides quick, accurate responses to user inquiries and takes into consideration the user's feelings, thereby contributing to improved customer satisfaction and the quality of corporate services.

[0970] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0971] Step 1:

[0972] The user enters a query

[0973] Input: The user uses a smartphone or computer to input a query by text or voice through a chat window or voice input assistant.

[0974] What happens: The user types into the chat window, "What is the shipping status of order number 12345?" If the user types, the device uses voice recognition software to convert the speech into text.

[0975] Output: Query data in text format.

[0976] Step 2:

[0977] The device recognizes emotions

[0978] Input: Query data in text format.

[0979] Specific operation: The device uses the emotion engine to recognize emotions from the user's input data. For example, it uses the "Emotion SDK" to analyze the user's tone of voice and facial expressions.

[0980] Output: Enquiry and sentiment data (e.g. dissatisfaction).

[0981] Step 3:

[0982] The device sends the data to the server

[0983] Input: Enquiry content and emotion data.

[0984] Specific operation: The device generates an HTTP request and sends the query content and emotion data to the server.

[0985] Output: The query and emotion data sent to the server.

[0986] Step 4:

[0987] The server receives and analyzes the data

[0988] Input: Inquiry content and emotion data sent from the device.

[0989] Specific operation: The server receives an HTTP request, analyzes the provided emotion data using the emotion engine, and then analyzes the intent of the query using the natural language processing (NLP) module.

[0990] Output: Parsed query content and sentiment data.

[0991] Step 5:

[0992] The server sends the data to the generated AI.

[0993] Input: Parsed query content and sentiment data.

[0994] Specific operation: The server sends the analysis results to the generation AI. A prompt is generated, for example, "Please tell me the shipping status of order number 12345. The user is dissatisfied. Please respond in a kind and polite manner."

[0995] Output: The prompt sent to the generation AI and the analysis results.

[0996] Step 6:

[0997] Generative AI generates responses

[0998] Input: Prompt sentence and parsed result sent from the server.

[0999] Specific operation: The generative AI (e.g., GPT-4) refers to a company's database (e.g., PostgreSQL) and generates a response that takes the user's emotions into account.

[1000] Output: The generated response text (e.g., "Order 12345 is currently on its way. We apologize for any inconvenience.").

[1001] Step 7:

[1002] The server receives the generated response

[1003] Input: The response text sent by the generation AI.

[1004] Specific operation: The server receives the response generated from the generation AI.

[1005] Output: The response text received.

[1006] Step 8:

[1007] The server sends the response to the user's device

[1008] Input: The response text received.

[1009] Specific operation: The server creates an HTTP response and sends the generated response to the user's terminal.

[1010] Output: The response text sent to the user's terminal.

[1011] Step 9:

[1012] The user's device displays the response

[1013] Input: The response text sent by the server.

[1014] Specific operation: The user's device receives the HTTP response and displays the response in a chat window or as a notification message.

[1015] Output: Response text displayed on the user's device (e.g., "Order 12345 is currently on its way. We apologize for any inconvenience.").

[1016] (Application example 2)

[1017] 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."

[1018] In electronic payment services, when responding to user inquiries, it is necessary to appropriately recognize the user's emotions and provide a response based on those emotions. Conventional systems do not take the user's emotions into consideration, which has led to the problem of not being able to fully alleviate the user's dissatisfaction and anxiety, resulting in a decrease in customer satisfaction. In order to solve this problem, the present invention aims to provide a system that recognizes the user's emotions and provides a response based on those emotions.

[1019] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1020] In this invention, the server includes: a means for a user to input a query using a terminal and send it to the server; a means for the server to receive the query from the user and analyze the query content and the user's emotions; a means for a generation AI to generate an appropriate response based on the analyzed query content and emotion data; a means for sending the generated response to the user's terminal; and a means for the user's terminal to display the response, characterized in that a response corresponding to the user's emotions is provided. This makes it possible to provide a quick and accurate response while taking the user's emotions into consideration.

[1021] "User" refers to a user who makes an inquiry using a terminal.

[1022] "Terminal" refers to a device through which a user inputs a query and communicates with a server.

[1023] "Server" refers to a computer system that receives queries from users, analyzes them, and generates responses.

[1024] "Query" refers to a question or request that a user sends to a server through a terminal.

[1025] "Emotion" refers to the psychological state that a user exhibits when making a query.

[1026] An "emotion engine" refers to software that analyzes a user's emotions and generates data based on them.

[1027] "Analyzing" means that the server understands the content of the inquiry and the emotional data and performs appropriate processing.

[1028] "Generative AI" refers to artificial intelligence that generates appropriate responses based on the content of inquiries and emotional data.

[1029] "Response" refers to the answer or information that the server generates in response to a user's inquiry through generation AI.

[1030] "Displaying" refers to visually showing the response sent from the server on the user's terminal.

[1031] The present invention relates to a system that allows a user to input a query using a terminal, transmit the query to a server, and provide an appropriate response based on the user's emotions. The system of the present invention has the following configuration.

[1032] System configuration

[1033] 1. User Device:

[1034] A device for users to input queries. This device can be a smartphone or a head-mounted display. Users can submit queries in text, voice, or video format.

[1035] 2. Server:

[1036] A computer system that receives and analyzes queries sent from user terminals. The server contains the following main modules:

[1037] Emotion engine: Software that analyzes user emotions. It uses emotion recognition libraries (e.g., IBM Watson Tone Analyzer).

[1038] Natural Language Processing (NLP) module: Analyzes the query content and extracts key intent and keywords. Uses natural language processing libraries (e.g., spaCy, NLTK, etc.).

[1039] Generative AI module: Artificial intelligence that generates appropriate responses based on analysis results. It uses a generative AI model (e.g., OpenAI's GPT-4).

[1040] HTTP communication module: Communicates with the user terminal using a web server (e.g., Flask, Django, etc.).

[1041] 3. Response display:

[1042] This module displays the generated responses on the user's device. It includes a user interface (UI) module, which displays the responses as chat windows and notification messages.

[1043] Processing flow and specific examples

[1044] 1. Inquiry received:

[1045] A user makes an inquiry via their smartphone, saying, "I'm worried about suspicious activity in my recent transaction history." This inquiry is sent to the server as text or voice data.

[1046] 2. Emotion analysis:

[1047] The server's emotion engine recognizes the user's anxiety from the inquiry content and generates emotion data.

[1048] 3. Query Analysis:

[1049] The server's natural language processing (NLP) module extracts keywords such as "recent transaction history" and "suspicious activity," while simultaneously recognizing that the user is feeling "anxious."

[1050] 4. Response generation by generative AI:

[1051] The generative AI module generates a response based on the extracted intent and sentiment data, such as, "We have not found any suspicious activity in your recent transaction history. Rest assured, if you require further clarification, please feel free to contact us."

[1052] 5. Response transmission and display:

[1053] The generated response is sent to the user's terminal via the server and displayed in a chat window or as a notification message.

[1054] Prompt Sentence Examples

[1055] If a user says, "I'm concerned about suspicious activity in my recent transactions," the following prompt is passed to the AI ​​generator:

[1056] User: I'm concerned about suspicious activity in my recent transaction history.

[1057] Emotion: Anxiety

[1058] Response: We have not found any suspicious activity in your recent transaction history. Rest assured, if you require further clarification, please feel free to contact us.

[1059] As described above, the present invention aims to improve customer satisfaction by providing a quick and accurate response while taking into consideration the user's feelings.

[1060] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1061] Step 1: Enter and submit your inquiry

[1062] A user uses a terminal to input a query. For example, text or voice data such as "I'm concerned about suspicious activity in my recent transaction history" is input. This query is sent from the terminal to the server. The input is text or voice data, and the output is query data. The terminal sends the query data to the server.

[1063] Step 2: Inquiry reception and sentiment analysis

[1064] The server receives the inquiry data sent by the user. The received data is passed to the emotion engine, which analyzes the user's emotions. Specifically, an emotion recognition library (e.g., IBM Watson Tone Analyzer) is used to analyze the tone of the voice and the context of the text using a unique algorithm to determine the user's mental state. The input is the inquiry data, and the output is the analyzed emotion data.

[1065] Step 3: Analyzing the inquiry

[1066] The server passes the query content, along with the emotion data received from the emotion engine, to a natural language processing (NLP) module. The NLP module extracts the intent and key keywords of the query through a directed process. For example, it uses libraries such as spaCy and NLTK to extract key keywords such as "transaction history" and "suspicious activity." The input is the query data and emotion data, and the output is the parsed intent and keywords.

[1067] Step 4: Response Generation

[1068] The analyzed intent, keywords, and even sentiment data are passed to a generative AI module, which uses this data to generate an appropriate response. This is done using an AI model (e.g., OpenAI GPT-4) that synthesizes the extracted information to generate a human-like natural language response. For example, a response might read, "We have not found any suspicious activity in your recent transaction history. Rest assured, if you require further clarification, please feel free to contact us." The input is the analyzed intent, keywords, and sentiment data, and the output is the generated response.

[1069] Step 5: Send response

[1070] The HTTP communication module receives the response generated by the generation AI module and sends it to the user's device. Specifically, the generated response is encoded as an HTTP response and sent to the device as appropriate. During this process, a security layer is applied to ensure the confidentiality and integrity of the data. The input is the generated response data, and the output is an HTTP response to the device.

[1071] Step 6: Display the response

[1072] The user terminal decodes the HTTP response received from the server and displays it through the user interface (UI) module. The response is displayed in a user-friendly format, such as a chat window or notification message, allowing the user to confirm the appropriate response. The input is the received HTTP response, and the output is the displayed response message.

[1073] 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.

[1074] 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.

[1075] 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.

[1076] [Fourth embodiment]

[1077] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1078] 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.

[1079] 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).

[1080] 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.

[1081] 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.

[1082] 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).

[1083] 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.

[1084] 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.

[1085] 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.

[1086] 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.

[1087] 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.

[1088] 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.

[1089] 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."

[1090] This invention relates to a system in which a user inputs a query using a terminal and sends it to a server. The server receives the query from the user and analyzes its contents. The analyzed results are sent to a generation AI, which generates an appropriate response. The generated response is then sent to the user's terminal and displayed.

[1091] User inquiry processing

[1092] Users access the system using their own devices (such as smartphones or PCs). For example, they access a call center inquiry form using a web browser or dedicated application and enter an inquiry such as, "Please tell me the shipping status of order number 12345." The device then sends this inquiry to the server as an HTTP request.

[1093] Reception and analysis by the server

[1094] When the server receives a user inquiry, it automatically begins the process of analyzing the inquiry. The server uses natural language processing (NLP) technology to parse the inquiry and extract important information (such as the order number and requirements). Specifically, from the inquiry "Please tell me the shipping status of order number 12345," the keywords "order number 12345" and "shipping status" are extracted.

[1095] Response generation by generative AI

[1096] The server provides data to the generation AI based on the analysis results. The generation AI retrieves relevant information from the company's database and generates a response in natural language. For example, if order number 12345 is currently being delivered, the generation AI generates a response saying, "The shipping status of order number 12345 is currently being delivered."

[1097] Response transmission from the server to the terminal

[1098] The generated response is sent back to the user's device by the server, which then returns the response received from the generation AI to the user's device as an HTTP response.

[1099] Display on the user's device

[1100] The user's device receives the response from the server and displays it on the screen. Specifically, the information such as "Shipping status of order number 12345 is currently being delivered" is displayed in a chat window or as a notification message.

[1101] Specific examples

[1102] For example, if a user uses a device to make a query such as "Please reissue the invoice for order number 56789," the device sends this query to the server. The server uses NLP technology to analyze the query and extract the information "order number 56789" and "invoice reissue." The generation AI then references the company's database, checks the reissue procedure and status of the relevant invoice, and generates a response such as "The invoice for order number 56789 has been reissued and will be mailed shortly." This response is then sent back to the user's device via the server and displayed on the user's screen.

[1103] In this way, the present invention provides a system that can provide quick and accurate responses to user inquiries, and is beneficial to both companies and customers.

[1104] The processing flow will be explained below.

[1105] Step 1:

[1106] A user uses a terminal to enter an inquiry. The user enters "Please tell me the shipping status of order number 12345" into a call center inquiry form or chat window and clicks the send button.

[1107] Step 2:

[1108] The device sends the user's inquiry as an HTTP request to the server. Specifically, the inquiry content is packaged in a data format such as JSON and sent to the specified endpoint on the server.

[1109] Step 3:

[1110] The server receives an HTTP request from a user, which includes the query and the user's identity.

[1111] Step 4:

[1112] The server analyzes the query. It uses a natural language processing (NLP) module to understand the intent of the query. Specifically, it extracts "order number 12345" and "shipping status" from the text "Please tell me the shipping status of order number 12345."

[1113] Step 5:

[1114] The server passes the parsed results to the generation AI, which retrieves information about order number 12345 from the company database.

[1115] Step 6:

[1116] The generative AI searches the company's database to retrieve the necessary information. For example, it retrieves the latest delivery status of order number 12345 and obtains information such as "Currently being delivered."

[1117] Step 7:

[1118] The generation AI generates a response in natural language based on the information it obtains. For example, it generates a response text such as, "The shipping status of order number 12345 is currently being delivered."

[1119] Step 8:

[1120] The server receives the response from the generation AI and generates an HTTP response to send to the user's device.

[1121] Step 9:

[1122] The server sends an HTTP response to the user's device, which includes the generated response text.

[1123] Step 10:

[1124] The user's device displays the response received from the server. Specifically, it displays the message "Order number 12345 is currently being delivered" in a chat window or as a notification message.

[1125] This series of processing steps provides fast and accurate responses to user inquiries, improving customer satisfaction.

[1126] Example 1

[1127] 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."

[1128] Conventional inquiry systems have problems such as delayed responses to user inquiries and inaccurate information provided. Furthermore, the content of the user's inquiry is not clearly analyzed, leading to inappropriate responses. Therefore, there is a demand for a system that can respond to user inquiries quickly and accurately.

[1129] 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.

[1130] In this invention, the server includes means for a user to input an inquiry using an information processing device and transmit the inquiry to the server, means for the server to receive the inquiry from the user and analyze the inquiry, means for a generation AI to generate an appropriate response based on the analyzed inquiry, means for transmitting the generated response to the user's information processing device, and means for the user's information processing device to display the response, thereby making it possible to provide a quick and accurate response to a user's inquiry.

[1131] A "user" is a person who operates an information processing device to make an inquiry.

[1132] An "information processing device" is an electronic device that allows a user to input an inquiry and send it to a server via the Internet, and includes devices such as smartphones and personal computers.

[1133] A "server" is a computer system that receives inquiries sent by users and analyzes and processes the contents of those inquiries.

[1134] An "inquiry" refers to a question or request that a user sends to the system via an information processing device.

[1135] "Natural language processing technology" is a technical method that allows computers to understand and analyze human language, and includes techniques such as text analysis and keyword extraction.

[1136] "Generative AI" refers to an artificial intelligence model that generates appropriate responses based on analyzed query content.

[1137] An "information management system" is a system that includes databases and other information resources referenced by generative AI, such as corporate databases.

[1138] This invention relates to a system in which a user inputs a query using an information processing device and sends the query to a server. The server receives the query from the user and analyzes the content of the query using natural language processing technology. The analyzed results are sent to a generation AI, which generates an appropriate response. The generated response is then sent to the user's information processing device and displayed.

[1139] A user accesses the system using their own information processing device (for example, a smartphone or PC). Specifically, they use a web browser or a dedicated application to enter a query into an inquiry form, such as "Please tell me the shipping status of order number 12345." The information processing device then sends this query to the server as an HTTP request.

[1140] When the server receives a user inquiry, it automatically begins the process of analyzing the inquiry. The server uses natural language processing (NLP) technology to parse the inquiry and extract important information (such as the order number and requirements). Specifically, from the inquiry "Please tell me the shipping status of order number 12345," the keywords "order number 12345" and "shipping status" are extracted.

[1141] The server provides the extracted keyword information to the generation AI, which retrieves relevant information from the company's information management system (database) and generates a response in natural language. For example, if order number 12345 is currently being delivered, the generation AI generates the response, "The shipping status of order number 12345 is currently being delivered."

[1142] The generated response is sent again by the server to the user's information processing device. The server returns the response received from the generation AI to the user's information processing device as an HTTP response. The user's information processing device receives the response from the server and displays it on the screen. Specifically, information such as "Shipping status of order number 12345 is currently being delivered" is displayed in a chat window or as a notification message.

[1143] As a specific example, consider the case where a user makes an inquiry such as, "Please reissue the invoice for order number 56789." In this case, the information processing device sends this inquiry to the server. The server uses NLP technology to analyze the inquiry and extracts the information "order number 56789" and "invoice reissue." The generation AI references the company's information management system to obtain the relevant information and generates a response such as, "The invoice for order number 56789 has been reissued and will be mailed shortly." This response is then sent again via the server to the user's information processing device and displayed on the user's screen.

[1144] Here is an example prompt:

[1145] User's inquiry: Please let me know the shipping status of order number 12345.

[1146] Information from company database: Order number 12345 is currently being shipped.

[1147] Response to generate: Order 12345 is currently in transit.

[1148] In this way, the present invention can provide a fast and accurate response to user inquiries, thereby providing a system that is beneficial to both companies and customers.

[1149] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1150] Step 1:

[1151] A user inputs a query using an information processing device. Specifically, the user inputs a query such as "Please tell me the shipping status of order number 12345" using a dedicated application or web browser on a smartphone or PC. The input query is formatted as the payload of an HTTP request.

[1152] Input: User inquiry (e.g., "Please tell me the shipping status of order number 12345.")

[1153] Output: The query formatted as an HTTP request

[1154] Step 2:

[1155] The terminal sends the input query to the server. Specifically, it sends a request including the query content payload as an HTTP POST request to the specified server URL.

[1156] Input: Query content formatted as an HTTP request

[1157] Output: HTTP request sent to the server

[1158] Step 3:

[1159] The server receives an HTTP request from the user. The web server (e.g., Apache or Nginx) receives the request and passes it to the application server. The query content is extracted from the payload of the received request.

[1160] Input: HTTP request

[1161] Output: Extracted inquiry content

[1162] Step 4:

[1163] The server analyzes the received inquiry using natural language processing technology (NLP engine). Specifically, the engine (e.g., spaCy or NLTK) extracts important keywords from the inquiry (e.g., "order number 12345" and "shipping status").

[1164] Input: Extracted inquiry content

[1165] Output: Extracted keywords (e.g. "Order number 12345" and "Shipping status")

[1166] Step 5:

[1167] The server sends the extracted keyword information to the generative AI model, providing the data to the generative AI model along with the analyzed keywords as a prompt sentence: "Please tell me the shipping status of order number 12345."

[1168] Input: Extracted keyword information

[1169] Output: Send prompt to generative AI model

[1170] Step 6:

[1171] The generative AI model references the company's information management system (database) based on the provided prompt sentence to retrieve relevant information. For example, it retrieves information from the database that "Order number 12345 is currently being delivered." Based on this, the generative AI generates a natural language response such as, "The shipping status of order number 12345 is currently being delivered."

[1172] Input: Prompt statement and associated information from information management system

[1173] Output: Generated response

[1174] Step 7:

[1175] The server receives the response text generated by the generation AI, formats it as an HTTP response, and prepares to send it to the user's information processing device.

[1176] Input: Generated response sentence

[1177] Output: Response text formatted as an HTTP response

[1178] Step 8:

[1179] The server transmits the generated response text to the user's information processing device as an HTTP response.

[1180] Input: Response text formatted as an HTTP response

[1181] Output: Sending an HTTP response to the user's information processing device

[1182] Step 9:

[1183] The user's information processing device receives the HTTP response from the server and extracts the response text from the payload of the received response.

[1184] Input: HTTP response from the server

[1185] Output: Extracted response sentence

[1186] Step 10:

[1187] The user's information processing device displays the extracted response sentence on the screen. Specifically, information such as "The shipping status of order number 12345 is currently being delivered" is displayed in a chat window or as a notification message.

[1188] Input: Extracted response sentence

[1189] Output: Response text displayed on the screen

[1190] (Application example 1)

[1191] 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."

[1192] With the existing inquiry system, it took a long time for logistics center employees to check inventory and delivery status, reducing efficiency. Responses to inquiries were often not returned immediately, which sometimes disrupted business operations. For this reason, a system was needed that would enable logistics center employees to quickly and accurately obtain the information they needed.

[1193] 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.

[1194] In this invention, the server includes: a means for a user to input an inquiry using a terminal and send it to the server; a means for the server to receive the inquiry from the user and analyze the inquiry; a means for a generation AI to generate an appropriate response based on the analyzed inquiry; a means for a logistics center employee to inquire about stock status and delivery status; a means for making the inquiry using a smartphone; a means for sending the inquiry to the server as an HTTP request; a means for sending the generated response to the user's terminal; and a means for the user's terminal to display the response. This enables logistics center employees to quickly check stock status and delivery status.

[1195] "Means for users to input inquiries using a terminal and send them to a server" refers to a system in which users input inquiries using electronic devices such as smartphones or personal computers and send the contents to a server via a network.

[1196] "Means for the server to receive the inquiry from the user and analyze the content of the inquiry" refers to a process in which the server receives the content of the inquiry sent by the user and analyzes its content.

[1197] "Means by which the generation AI generates an appropriate response based on the analyzed inquiry content" refers to the process by which the generation AI automatically generates an appropriate response based on the information obtained from the analysis results.

[1198] "Means for logistics center employees to inquire about inventory status and delivery status" refers to a system by which employees working at logistics centers can make inquiries to check inventory information and delivery information.

[1199] "Means for making an inquiry using a smartphone" refers to a method in which a user uses a portable electronic device called a smartphone to send an inquiry to the system.

[1200] "Means of sending to the server as an HTTP request" refers to a method of sending the inquiry content to the server using HyperText Transfer Protocol (HTTP).

[1201] "Means for sending the generated response to the user's terminal" refers to the procedure for sending the response generated by the AI ​​back to the user's terminal via the network.

[1202] "Means by which the user's terminal displays the response" refers to a mechanism by which the response is displayed on the user's device.

[1203] This invention relates to a system in which a user inputs an inquiry using a terminal and sends it to a server. Specifically, it provides a system in which a logistics center employee can inquire about inventory status and delivery status using a smartphone and receive an immediate response. An embodiment of this system is described in detail below.

[1204] User inquiry processing

[1205] A user (a logistics center employee) uses a dedicated application on their smartphone to enter an inquiry. For example, they might enter "Please tell me the stock status of order number 12345" into an input field on the screen. This inquiry is sent to the server as an HTTP request.

[1206] Reception and analysis by the server

[1207] When the server receives an HTTP request from a user, it analyzes its contents. Natural language processing (NLP) technology is used for the analysis. Specifically, the server uses an NLP library such as spaCy or NLTK to parse the query and extract important information (such as the order number and requirements). For example, from the query "Please tell me the stock status of order number 12345," the keywords "order number 12345" and "stock status" are extracted. The analysis results are then saved in JSON format.

[1208] Response generation by generative AI

[1209] The server provides data to the generative AI model based on the analyzed information. The generative AI model references the company's database and generates an appropriate response to the query. For example, if the stock quantity for order number 12345 is 5, the generative AI model generates the response "There are currently 5 units of order number 12345 in stock."

[1210] Response transmission from the server to the terminal

[1211] The generated response is then sent back to the user's device as an HTTP response. When the server receives the response from the AI ​​generator and sends it to the user's device, it converts the response into a format that is easy for the user to understand.

[1212] Display on the user's device

[1213] The user's device receives the response from the server and displays it on the screen. Specifically, the information, such as "There are currently 5 units of order number 12345 in stock," is displayed in a chat window in a dedicated application or as a notification message. In this way, employees at the logistics center can quickly check the information they need.

[1214] Technology Stack

[1215] Natural Language Processing (NLP) libraries: spaCy, NLTK

[1216] Generative AI model: OpenAI GPT-3

[1217] Backend frameworks: Flask, Django

[1218] Database: MySQL, PostgreSQL

[1219] Examples of specific examples and prompts

[1220] For example, suppose a user makes the following query:

[1221] User Input: "What is the stock status for order number 67890?"

[1222] An example of the corresponding prompt for the generative AI model:

[1223] User's question: "What is the stock status of order number 67890?"

[1224] Parsing result: {"Order number": "67890", "Requirement": "Availability"}

[1225] Example of a response generated by the Generative AI:

[1226] There are currently 5 units of order number 67890 in stock.

[1227] In this way, by using the system of the present invention, employees at the logistics center can quickly and accurately obtain the necessary information, which contributes to improving work efficiency.

[1228] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1229] Step 1:

[1230] A user uses a terminal to enter a query and send it to the server.

[1231] Specific actions: An employee at the logistics center enters "Please tell me the inventory status of order number 12345" into the input field in a dedicated application on their smartphone and presses the "Send" button.

[1232] Input: The query entered by the user.

[1233] Output: The query sent to the server as an HTTP request.

[1234] Step 2:

[1235] The server receives a query from a user and analyzes the query.

[1236] What happens: The server receives the HTTP request and uses a natural language processing (NLP) library (such as spaCy or NLTK) to extract the query. The query is parsed into "order number 12345" and "stock status" and saved in JSON format.

[1237] Input: The query received as an HTTP request.

[1238] Output: The parsed query content is saved in JSON format.

[1239] Step 3:

[1240] Based on the analyzed inquiry content, the generative AI generates an appropriate response.

[1241] Specific operation: The server sends the analysis results to a generative AI model (e.g., OpenAI GPT-3). The generative AI model works with the company's database to generate an appropriate response to the query. For example, it retrieves information from the database that there are five units of order number 12345 in stock, and generates a response saying, "There are currently five units of order number 12345 in stock."

[1242] Input: Parsed query content (JSON format).

[1243] Output: The generated response (in natural language format).

[1244] Step 4:

[1245] The generated response is sent from the server to the user's terminal.

[1246] Specific operation: The server sends the response received from the generation AI to the user's device as an HTTP response.

[1247] Input: Response from the generation AI.

[1248] Output: The HTTP response sent to the user's device.

[1249] Step 5:

[1250] The user's terminal displays the response.

[1251] Specific operation: The user's device (a dedicated smartphone application) displays the HTTP response received from the server on the screen. For example, it displays information such as "There are currently 5 units of order number 12345 in stock" in a chat window or as a notification message.

[1252] Input: The HTTP response from the server.

[1253] Output: The displayed response.

[1254] 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.

[1255] This invention relates to a system in which a user inputs a query using a terminal and sends it to a server. This system provides an appropriate response according to the user's emotions by combining it with an emotion engine that recognizes the user's emotions. Specifically, the server receives the query from the user and analyzes the content and the user's emotions. A generation AI generates an appropriate response based on the analysis results and sends it to the user's terminal. The generated response is then displayed on the user's terminal.

[1256] User inquiry processing and emotion recognition

[1257] When a user uses their device to input a query, they can do so in text, voice, or video format. For example, when they input "What is the shipping status of order number 12345?" through a chat window or voice input assistant, the emotion engine recognizes the user's emotion from their tone of voice, facial expression, and the context of the text. The device then sends the emotion data along with the query to the server.

[1258] Reception and analysis by the server

[1259] When the server receives a user inquiry, it first analyzes the emotion data provided by the emotion engine. Using a natural language processing (NLP) module, the server understands the intent of the inquiry and simultaneously grasps the user's state (e.g., anger, joy, sadness, etc.) based on the emotion data. Specifically, in response to the inquiry, "Please tell me the shipping status of order number 12345," the keywords "order number 12345" and "shipping status" are extracted, and the emotion engine simultaneously recognizes that the user is dissatisfied.

[1260] Response generation by generative AI

[1261] The server provides the analysis results and emotional data to the generation AI, which retrieves relevant information from the company's database and considers the user's emotions when generating a natural language response. For example, if the user is dissatisfied, the generation AI generates a more polite and empathetic response. Specifically, it generates a response such as, "The shipping status of order number 12345 is currently being delivered. We apologize for the inconvenience."

[1262] Response transmission from the server to the terminal

[1263] The generated response is sent to the user's device by the server, which then returns the response received from the generation AI to the user's device as an HTTP response.

[1264] Display on the user's device

[1265] The user's device displays the response received from the server. Specifically, a chat window or notification message will appear stating, "The shipping status for order number 12345 is currently being delivered. We apologize for any inconvenience." This allows the user to receive a response that takes their feelings into consideration, improving satisfaction.

[1266] Specific examples

[1267] For example, if a user uses a device to make an inquiry such as "Please reissue the invoice for order number 56789," and expresses dissatisfaction at the time, the emotion engine recognizes the user's dissatisfaction from the voice data and text sent from the device. The emotion data and inquiry content are sent to the server for analysis. The generation AI generates a response that takes the user's emotions into consideration, such as "The invoice for order number 56789 has been reissued and will be mailed shortly. We apologize for the inconvenience," and sends this response to the device via the server. Finally, the device displays this response.

[1268] In this way, the present invention provides a system that can provide quick, accurate responses to user inquiries and that also take into consideration the user's feelings, thereby greatly improving customer satisfaction and contributing to improving the quality of service provided by companies.

[1269] The processing flow will be explained below.

[1270] Step 1:

[1271] The user uses the device to input an inquiry. For example, the user may use a chat window or a voice input assistant to input, "Please tell me the shipping status of order number 12345." At this time, the device collects emotional data such as voice and facial expressions along with the user's input.

[1272] Step 2:

[1273] The device sends the collected inquiry and emotion data to the server as an HTTP request. Specifically, the inquiry is packaged as text data, audio data, or video data and sent in a format that can be analyzed by the emotion engine.

[1274] Step 3:

[1275] The server receives an HTTP request from the user, which includes the query and emotion data.

[1276] Step 4:

[1277] The server analyzes the inquiry and uses an emotion engine to analyze the user's emotions. The server uses a natural language processing (NLP) module to understand the intent of the inquiry. For example, from the text "Please tell me the shipping status of order number 12345," it extracts "order number 12345" and "shipping status," and at the same time, the emotion engine recognizes the user's dissatisfaction.

[1278] Step 5:

[1279] The server passes the analysis results (order number and requirements) and emotion data to the generation AI, which then retrieves information about order number 12345 from the company database.

[1280] Step 6:

[1281] The generative AI searches the company's database to get the latest delivery status for order number 12345. For example, it might get information like "Currently being delivered."

[1282] Step 7:

[1283] Based on the information acquired, the generation AI generates a response in natural language that takes the user's feelings into consideration. For example, if the user is dissatisfied, it generates a polite and empathetic response such as, "The shipping status of order number 12345 is currently being delivered. We apologize for the inconvenience."

[1284] Step 8:

[1285] The server receives the response from the generation AI and generates an HTTP response to send to the user's device. The response contains the generated response text.

[1286] Step 9:

[1287] The server sends an HTTP response to the user's device, which contains sentiment-sensitive text.

[1288] Step 10:

[1289] The user's device displays the response received from the server. Specifically, a chat window or notification message might say, "The shipping status for order number 12345 is currently being delivered. We apologize for any inconvenience caused." This allows the user to receive information in a way that takes their feelings into consideration.

[1290] This series of processing steps enables a response to a user's inquiry to be provided quickly, accurately, and with consideration for the user's feelings, thereby improving customer satisfaction and the quality of service provided by the company.

[1291] Example 2

[1292] 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."

[1293] Conventional inquiry response systems generate responses without considering the user's emotions, which leads to a decrease in user satisfaction. Furthermore, the accuracy of analyzing the inquiry content is low, and appropriate responses are often not generated. This results in a lack of improvement in the user experience and the quality of service provided by companies.

[1294] 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.

[1295] In this invention, the server includes a means for a user to input a query using a terminal and send it to the server, a means for the server to receive the query from the user and analyze the query content and the user's emotions, and a means for the generation AI to generate an appropriate response based on the analyzed query content and user emotion data, thereby enabling an appropriate response that takes the user's emotions into consideration.

[1296] 1. "Terminal" means a device used by a user to enter an inquiry, such as a smartphone, PC, or tablet.

[1297] 2. "Server" means a computer system whose role is to receive and analyze queries sent by users.

[1298] 3. "Query" means a question or request sent by a User to a Server using a Terminal.

[1299] 4. "Emotion" refers to the psychological state that a user exhibits when making a query, including joy, anger, sadness, surprise, etc.

[1300] 5. "Emotion engine" means software or algorithms that recognize emotions from user input data.

[1301] 6. “Natural Language Processing (NLP)” refers to techniques or methods that enable computers to understand, analyze, and generate human language.

[1302] 7. "Generative AI" is an artificial intelligence system that generates appropriate responses based on the user's inquiry and emotional data.

[1303] 8. “Database” means a structured collection of data that stores information about a company and that is referenced by Generative AI when generating responses.

[1304] 9. "HTTP request" means a request message using an Internet protocol for a terminal to send data to a server.

[1305] 10. "HTTP response" means a response message using an Internet protocol that allows a server to return data to a terminal.

[1306] This invention relates to a system in which a user inputs a query using a terminal and sends it to a server. This system provides an appropriate response according to the user's emotion by combining it with an emotion engine that recognizes the user's emotion.

[1307] composition

[1308] User inquiry input and submission

[1309] A user uses a device such as a smartphone or PC to input a query in text, voice, or video format. For example, they might input "What is the shipping status of order number 12345?" through a chat window or voice input assistant. The device is equipped with an emotion engine that recognizes emotions from the user's tone of voice, facial expressions, and text context. The device then sends the emotion data along with the query to the server.

[1310] Reception and analysis by the server

[1311] When the server receives a query from a user, it first analyzes the provided emotion data using the emotion engine. Using a natural language processing (NLP) module, the server understands the intent of the query and simultaneously grasps the user's emotional state (e.g., anger, joy, sadness, etc.) based on the emotion data. For example, in response to a query such as "Please tell me the shipping status of order number 12345," the keywords "order number 12345" and "shipping status" are extracted, and it is recognized that the user is dissatisfied.

[1312] Response generation by generative AI

[1313] The server provides the analysis results and emotional data to the generation AI, which retrieves relevant information from the company's database and considers the user's emotions when generating a natural language response. For example, if the user is dissatisfied, the generation AI will generate a more polite and empathetic response. A response such as "The shipping status of order number 12345 is currently being delivered. We apologize for the inconvenience."

[1314] Response transmission from the server to the terminal

[1315] The generated response is sent to the user's device by the server. The server returns the response received from the generation AI to the user's device as an HTTP response.

[1316] Display on the user's device

[1317] The user's device displays the response received from the server. For example, a chat window or notification message might say, "The shipping status for order number 12345 is currently being delivered. We apologize for any inconvenience." This allows the user to receive a response that takes their feelings into consideration, improving satisfaction.

[1318] Specific examples and examples of prompts for generative AI models

[1319] For example, if a user uses a device to make an inquiry such as "Please reissue the invoice for order number 56789," and expresses dissatisfaction at the time, the emotion engine will recognize the user's dissatisfaction from the voice and text data sent from the device. The emotion data and the inquiry content are sent to the server for analysis. The generation AI will generate a response that takes the user's emotions into consideration, such as "The invoice for order number 56789 has been reissued and will be mailed shortly. We apologize for the inconvenience," and send it to the device via the server. Finally, the device will display this response.

[1320] Example prompt for a generative AI model: "The user is asking, 'What is the shipping status for order 12345?' The user is frustrated. Please respond in a kind and polite manner."

[1321] In this way, the present invention realizes a system that provides quick, accurate responses to user inquiries and takes into consideration the user's feelings, thereby contributing to improved customer satisfaction and the quality of corporate services.

[1322] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1323] Step 1:

[1324] The user enters a query

[1325] Input: The user uses a smartphone or computer to input a query by text or voice through a chat window or voice input assistant.

[1326] What happens: The user types into the chat window, "What is the shipping status of order number 12345?" If the user types, the device uses voice recognition software to convert the speech into text.

[1327] Output: Query data in text format.

[1328] Step 2:

[1329] The device recognizes emotions

[1330] Input: Query data in text format.

[1331] Specific operation: The device uses an emotion engine to recognize emotions from the user's input data. For example, it uses the "Emotion SDK" to analyze the user's tone of voice and facial expressions.

[1332] Output: Enquiry and sentiment data (e.g. dissatisfaction).

[1333] Step 3:

[1334] The device sends the data to the server

[1335] Input: Enquiry content and sentiment data.

[1336] Specific operation: The device generates an HTTP request and sends the query content and emotion data to the server.

[1337] Output: The query and emotion data sent to the server.

[1338] Step 4:

[1339] The server receives and analyzes the data

[1340] Input: Inquiry content and emotion data sent from the device.

[1341] Specific operation: The server receives an HTTP request, analyzes the provided emotion data using the emotion engine, and then analyzes the intent of the query using the natural language processing (NLP) module.

[1342] Output: Parsed query content and sentiment data.

[1343] Step 5:

[1344] The server sends the data to the generated AI.

[1345] Input: Parsed query content and sentiment data.

[1346] Specific operation: The server sends the analysis results to the generation AI. A prompt is generated, for example, "Please tell me the shipping status of order number 12345. The user is dissatisfied. Please respond in a kind and polite manner."

[1347] Output: The prompt sent to the generation AI and the analysis results.

[1348] Step 6:

[1349] Generative AI generates responses

[1350] Input: Prompt sentence and parsed result sent from the server.

[1351] Specific operation: The generative AI (e.g., GPT-4) refers to a company's database (e.g., PostgreSQL) and generates a response that takes the user's emotions into account.

[1352] Output: The generated response text (e.g., "Order 12345 is currently on its way. We apologize for any inconvenience.").

[1353] Step 7:

[1354] The server receives the generated response

[1355] Input: The response text sent by the generation AI.

[1356] Specific operation: The server receives the response generated from the generation AI.

[1357] Output: The response text received.

[1358] Step 8:

[1359] The server sends the response to the user's device

[1360] Input: The response text received.

[1361] Specific operation: The server creates an HTTP response and sends the generated response to the user's terminal.

[1362] Output: The response text sent to the user's terminal.

[1363] Step 9:

[1364] The user's device displays the response

[1365] Input: The response text sent by the server.

[1366] Specific operation: The user's device receives the HTTP response and displays the response in a chat window or as a notification message.

[1367] Output: Response text displayed on the user's device (e.g., "Order 12345 is currently on its way. We apologize for any inconvenience.").

[1368] (Application example 2)

[1369] 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."

[1370] In electronic payment services, when responding to user inquiries, it is necessary to appropriately recognize the user's emotions and provide a response based on those emotions. Conventional systems do not take the user's emotions into consideration, which has led to the problem of not being able to fully alleviate the user's dissatisfaction and anxiety, resulting in a decrease in customer satisfaction. In order to solve this problem, the present invention aims to provide a system that recognizes the user's emotions and provides a response based on those emotions.

[1371] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1372] In this invention, the server includes: a means for a user to input a query using a terminal and send it to the server; a means for the server to receive the query from the user and analyze the query content and the user's emotions; a means for a generation AI to generate an appropriate response based on the analyzed query content and emotion data; a means for sending the generated response to the user's terminal; and a means for the user's terminal to display the response, characterized in that a response corresponding to the user's emotions is provided. This makes it possible to provide a quick and accurate response while taking the user's emotions into consideration.

[1373] "User" refers to a user who makes an inquiry using a terminal.

[1374] "Terminal" refers to a device through which a user inputs a query and communicates with a server.

[1375] "Server" refers to a computer system that receives queries from users, analyzes them, and generates responses.

[1376] "Query" refers to a question or request that a user sends to a server through a terminal.

[1377] "Emotion" refers to the psychological state that a user exhibits when making a query.

[1378] An "emotion engine" refers to software that analyzes a user's emotions and generates data based on them.

[1379] "Analyzing" means that the server understands the content of the inquiry and the emotional data and performs appropriate processing.

[1380] "Generative AI" refers to artificial intelligence that generates appropriate responses based on the content of inquiries and emotional data.

[1381] "Response" refers to the answer or information that the server generates in response to a user's inquiry through generation AI.

[1382] "Displaying" refers to visually showing the response sent from the server on the user's terminal.

[1383] The present invention relates to a system that allows a user to input a query using a terminal, transmit the query to a server, and provide an appropriate response based on the user's emotions. The system of the present invention has the following configuration.

[1384] System configuration

[1385] 1. User Device:

[1386] A device for users to input queries. This device can be a smartphone or a head-mounted display. Users can submit queries in text, voice, or video format.

[1387] 2. Server:

[1388] A computer system that receives and analyzes queries sent from user terminals. The server contains the following main modules:

[1389] Emotion engine: Software that analyzes user emotions. It uses emotion recognition libraries (e.g., IBM Watson Tone Analyzer).

[1390] Natural Language Processing (NLP) module: Analyzes the query content and extracts key intent and keywords. Uses natural language processing libraries (e.g., spaCy, NLTK, etc.).

[1391] Generative AI module: Artificial intelligence that generates appropriate responses based on analysis results. It uses a generative AI model (e.g., OpenAI's GPT-4).

[1392] HTTP communication module: Communicates with the user terminal using a web server (e.g., Flask, Django, etc.).

[1393] 3. Response display:

[1394] This module displays the generated responses on the user's device. It includes a user interface (UI) module, which displays the responses as chat windows and notification messages.

[1395] Processing flow and specific examples

[1396] 1. Inquiry received:

[1397] A user makes an inquiry via their smartphone, saying, "I'm worried about suspicious activity in my recent transaction history." This inquiry is sent to the server as text or voice data.

[1398] 2. Emotion analysis:

[1399] The server's emotion engine recognizes the user's anxiety from the inquiry content and generates emotion data.

[1400] 3. Query Analysis:

[1401] The server's natural language processing (NLP) module extracts keywords such as "recent transaction history" and "suspicious activity," while simultaneously recognizing that the user is feeling "anxious."

[1402] 4. Response generation by generative AI:

[1403] The generative AI module generates a response based on the extracted intent and sentiment data, such as, "We have not found any suspicious activity in your recent transaction history. Rest assured, if you require further clarification, please feel free to contact us."

[1404] 5. Response transmission and display:

[1405] The generated response is sent to the user's terminal via the server and displayed in a chat window or as a notification message.

[1406] Prompt Sentence Examples

[1407] If a user says, "I'm concerned about suspicious activity in my recent transactions," the following prompt is passed to the AI ​​generator:

[1408] User: I'm concerned about suspicious activity in my recent transaction history.

[1409] Emotion: Anxiety

[1410] Response: We have not found any suspicious activity in your recent transaction history. Rest assured, if you require further clarification, please feel free to contact us.

[1411] As described above, the present invention aims to improve customer satisfaction by providing a quick and accurate response while taking into consideration the user's feelings.

[1412] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1413] Step 1: Enter and submit your inquiry

[1414] A user uses a terminal to input a query. For example, text or voice data such as "I'm concerned about suspicious activity in my recent transaction history" is input. This query is sent from the terminal to the server. The input is text or voice data, and the output is query data. The terminal sends the query data to the server.

[1415] Step 2: Inquiry reception and sentiment analysis

[1416] The server receives the inquiry data sent by the user. The received data is passed to the emotion engine, which analyzes the user's emotions. Specifically, an emotion recognition library (e.g., IBM Watson Tone Analyzer) is used to analyze the tone of the voice and the context of the text using a unique algorithm to determine the user's mental state. The input is the inquiry data, and the output is the analyzed emotion data.

[1417] Step 3: Analyzing the inquiry

[1418] The server passes the query content, along with the emotion data received from the emotion engine, to a natural language processing (NLP) module. The NLP module extracts the intent and key keywords of the query through a directed process. For example, it uses libraries such as spaCy and NLTK to extract key keywords such as "transaction history" and "suspicious activity." The input is the query data and emotion data, and the output is the parsed intent and keywords.

[1419] Step 4: Response Generation

[1420] The analyzed intent, keywords, and even sentiment data are passed to a generative AI module, which uses this data to generate an appropriate response. This is done using an AI model (e.g., OpenAI GPT-4) that synthesizes the extracted information to generate a human-like natural language response. For example, a response might read, "We have not found any suspicious activity in your recent transaction history. Rest assured, if you require further clarification, please feel free to contact us." The input is the analyzed intent, keywords, and sentiment data, and the output is the generated response.

[1421] Step 5: Send response

[1422] The HTTP communication module receives the response generated by the generation AI module and sends it to the user's device. Specifically, the generated response is encoded as an HTTP response and sent to the device as appropriate. During this process, a security layer is applied to ensure the confidentiality and integrity of the data. The input is the generated response data, and the output is an HTTP response to the device.

[1423] Step 6: Display the response

[1424] The user terminal decodes the HTTP response received from the server and displays it through the user interface (UI) module. The response is displayed in a user-friendly format, such as a chat window or notification message, allowing the user to confirm the appropriate response. The input is the received HTTP response, and the output is the displayed response message.

[1425] 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.

[1426] 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.

[1427] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1428] 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.

[1429] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1430] 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.

[1431] 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).

[1432] 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.

[1433] 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."

[1434] 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.

[1435] 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).

[1436] 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.

[1437] 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.

[1438] 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.

[1439] 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.

[1440] 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.

[1441] 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.

[1442] 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.

[1443] 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.

[1444] 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.

[1445] 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.

[1446] The following is further disclosed regarding the above embodiment.

[1447] (Claim 1)

[1448] means for a user to input a query using a terminal and send it to a server;

[1449] a means for the server to receive an inquiry from the user and analyze the content of the inquiry;

[1450] A means for generating an appropriate response by a generation AI based on the analyzed inquiry content;

[1451] means for transmitting the generated response to the user's terminal;

[1452] means for displaying said response on said user's terminal;

[1453] A system including:

[1454] (Claim 2)

[1455] 2. The system according to claim 1, wherein the analysis means analyzes the content of the inquiry using natural language processing.

[1456] (Claim 3)

[1457] The system according to claim 1, characterized in that the generation AI generates the response by referring to a company database.

[1458] "Example 1"

[1459] (Claim 1)

[1460] A means for a user to input a query using an information processing device and transmit the query to a server;

[1461] a means for the server to receive an inquiry from the user and analyze the content of the inquiry;

[1462] A means for generating an appropriate response by a generation AI based on the analyzed inquiry content;

[1463] means for transmitting the generated response to the user's information processing device;

[1464] a means for displaying the response on the user's information processing device;

[1465] A system including:

[1466] (Claim 2)

[1467] 2. The system according to claim 1, wherein the analysis means analyzes the content of the inquiry using natural language processing technology.

[1468] (Claim 3)

[1469] The system according to claim 1, wherein the generation AI generates the response by referring to an information management system.

[1470] "Application Example 1"

[1471] (Claim 1)

[1472] means for a user to input a query using a terminal and send it to a server;

[1473] a means for the server to receive an inquiry from the user and analyze the content of the inquiry;

[1474] A means for generating an appropriate response by a generation AI based on the analyzed inquiry content;

[1475] A means for logistics center employees to inquire about inventory and delivery status,

[1476] A means for making inquiries using a smartphone;

[1477] A means of sending it to the server as an HTTP request;

[1478] means for transmitting the generated response to the user's terminal;

[1479] means for displaying said response on said user's terminal;

[1480] A system including:

[1481] (Claim 2)

[1482] 2. The system according to claim 1, wherein the analysis means analyzes the content of the inquiry using natural language processing.

[1483] (Claim 3)

[1484] The system according to claim 1, characterized in that the generation AI generates the response by referring to a company database.

[1485] "Example 2: Combining Emotion Engines"

[1486] (Claim 1)

[1487] means for a user to input a query using a terminal and send it to a server;

[1488] a means for the server to receive an inquiry from the user and analyze the content of the inquiry and the user's emotions;

[1489] A means for generating an appropriate response by a generation AI based on the analyzed inquiry content and user emotion data;

[1490] means for transmitting the generated response to the user's terminal;

[1491] means for displaying said response on said user's terminal;

[1492] A system including:

[1493] (Claim 2)

[1494] 2. The system according to claim 1, wherein the analysis means analyzes the inquiry content and emotion data using natural language processing.

[1495] (Claim 3)

[1496] The system according to claim 1, wherein the generation AI generates the response by referring to a database.

[1497] "Application example 2 when combining emotion engines"

[1498] (Claim 1)

[1499] means for a user to input a query using a terminal and send it to a server;

[1500] a means for the server to receive an inquiry from the user and analyze the content of the inquiry and the user's emotions;

[1501] A means for generating an appropriate response by a generation AI based on the analyzed inquiry content and emotion data;

[1502] means for transmitting the generated response to the user's terminal;

[1503] a means for displaying the response on the user's terminal, the response corresponding to the user's emotion being provided;

[1504] A system including:

[1505] (Claim 2)

[1506] 2. The system according to claim 1, wherein the analysis means analyzes the inquiry content and the user's sentiment using natural language processing.

[1507] (Claim 3)

[1508] The system of claim 1, wherein the generation AI generates the response by referencing a relational database. [Explanation of symbols]

[1509] 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 a user to input a query using a terminal and send it to a server; a means for the server to receive an inquiry from the user and analyze the content of the inquiry; A means for generating an appropriate response by a generation AI based on the analyzed inquiry content; means for transmitting the generated response to the user's terminal; means for displaying said response on said user's terminal; A system including:

2. 2. The system according to claim 1, wherein the analyzing means analyzes the content of the inquiry using natural language processing.

3. The system according to claim 1, wherein the generation AI generates the response by referring to a company database.

Images