system

Abstract

We provide the system. [Solution] Means for receiving user input, A means for analyzing the aforementioned input and extracting keywords and intent, A means for sending a request to an appropriate other system based on the aforementioned analysis results, Means for receiving responses from the aforementioned other systems, A means for integrating the received responses to generate a final response, A means of providing the user with the aforementioned final answer, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern enterprises, improving the efficiency of customer support is a major issue. In particular, it is important to respond quickly and accurately to inquiries from a large number of customers. However, in conventional systems, it takes a lot of time and effort to manually refer to multiple information sources for individual inquiries and provide an optimal answer. In addition, the integration and selection of information between different systems are complicated, and the quality of response may become unstable. Therefore, there is a need to develop a system that can respond to user inquiries more efficiently and accurately.

Means for Solving the Problems

[0005] The present invention provides a system that includes means for receiving user input, analyzing the input to extract keywords and intent, means for sending requests to appropriate other systems based on the analysis results, means for receiving responses from other systems, means for integrating the received responses to generate a final response, and means for providing the final response to the user. This enables a rapid and accurate response to user inquiries, thereby improving the efficiency of customer support. Furthermore, by using natural language processing, the system can analyze user input, select the most suitable information source based on that analysis, and integrate and provide data from multiple information sources. This improves the quality of responses and enables automation of tasks.

[0006] A "user" refers to an individual or organization that uses a system to make inquiries or requests for information.

[0007] "Input" refers to information that a user provides to the system, such as text messages or questions.

[0008] "Analysis" refers to the process of processing received input data to extract keywords and intent.

[0009] "Keywords" refer to important words or short phrases extracted from user input that characterize its content and intent.

[0010] "Intent" refers to what the user is seeking through their input, and is the target that the system identifies through analysis.

[0011] A "request" refers to a request for information or processing from another system based on the analysis results.

[0012] "Receiving" refers to the process by which a server retrieves data sent from another system.

[0013] "Integration" refers to the process of combining data obtained from multiple sources into a single, continuous piece of information.

[0014] "Answer" refers to the final response generated in response to user input.

[0015] "Providing" refers to the process of displaying or sending an integrated response to the user.

[0016] "Natural language processing" refers to the technology that enables computers to understand and analyze human language. [Brief explanation of the drawing]

[0017] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Modes for Carrying Out the Invention

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

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

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

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

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

[0023] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0025] [First Embodiment]

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

[0027] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0030] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0034] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0037] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0038] This invention is a system for providing quick and accurate answers to user-inputted inquiries, and operates efficiently through cooperation with servers, terminals, and other systems.

[0039] System Configuration

[0040] The system consists of the following main components:

[0041] Terminal: A device that the user directly operates (e.g., a personal computer, a smartphone).

[0042] Server: A central processing unit that receives and analyzes inquiries and generates responses in cooperation with other systems.

[0043] Other systems: External systems (e.g., databases or dedicated APIs) that the server uses to retrieve information in response to queries.

[0044] Program Processing Overview

[0045] When a user submits a query through their device, the content is received by the server. The server analyzes the received data using natural language processing to extract appropriate keywords and intent. Based on the analysis results, the server then identifies the most suitable other system and sends a request. When the response from the other system is returned to the server, the server integrates it to generate a single, continuous response, which is finally provided to the user via the device.

[0046] Specific example

[0047] Step 1: User input

[0048] The terminal sends the information to the server when the user enters "I want to know the delivery status of my product" into the inquiry form and presses the submit button.

[0049] For example, user A wants to know the delivery status of an item they ordered from an online shopping site, and enters a question.

[0050] Step 2: Server-based analysis

[0051] When the server receives a user inquiry, it uses natural language processing to analyze the inquiry. The analysis extracts the keyword "delivery status" and the user's intention, "I want to know the delivery status of the product ordered by user A."

[0052] Step 3: Integration with other systems

[0053] The server selects the most suitable other system from which to obtain "delivery status" information and sends the request. In this case, it determines that a database containing delivery information exists and sends the request to that database.

[0054] For example, you can query the logistics management system for the delivery status of "Order ID: 12345".

[0055] Step 4: Collecting and integrating responses

[0056] Other systems (for example, a logistics management system) search for the delivery status of the corresponding order ID and send back information to the server stating, "Product XYZ has now left the distribution center and is scheduled to arrive on time."

[0057] The server verifies the received information and, if necessary, collects additional information from other systems (e.g., customer management systems).

[0058] Step 5: Providing responses to users

[0059] The server integrates all the collected information and generates a final response. It creates a unified response such as "Product XYZ has now left the distribution center and is scheduled to arrive on time," and provides it to the user via the terminal.

[0060] The terminal displays the response received from the server on the user interface. User A can obtain a quick and accurate answer to the inquiry they entered.

[0061] In this way, the entire system efficiently implements a series of processes, from user inquiry input to server analysis and appropriate integration with other systems, ultimately providing a final answer.

[0062] The following describes the processing flow.

[0063] Step 1:

[0064] When a user enters "I want to know the delivery status of my product" into the inquiry form and presses the submit button, the device sends that information to the server. Specifically, when the form submission event occurs, the entered text data is sent to the server as an HTTP request.

[0065] Step 2:

[0066] The server receives user inquiries and analyzes their content. Specifically, it extracts text data from the body of the HTTP request and uses a natural language processing (NLP) library to extract keywords and intent from the text data.

[0067] Step 3:

[0068] The server identifies the keyword "delivery status" and the user's intention, "I want to know the delivery status of the product ordered by user A." Based on the analysis results, it selects an appropriate other system (e.g., a logistics management system).

[0069] Step 4:

[0070] The server sends API requests to other systems it uses. Specifically, it sends requests containing relevant data such as user IDs and order IDs to the logistics management system.

[0071] Step 5:

[0072] Other systems (for example, a logistics management system) process the received request, search their internal database, and generate a response. For example, they might send back information to the server such as, "Product XYZ has now left the distribution center and is scheduled to arrive on time."

[0073] Step 6:

[0074] The server receives responses from other systems. If necessary, it also collects relevant information from other systems, such as customer management systems.

[0075] Step 7:

[0076] The server integrates the collected information to generate a final response. For example, it might create a unified response such as, "Product XYZ has now left the distribution center and is scheduled to arrive on time."

[0077] Step 8:

[0078] The server sends the final response back to the user's device. Specifically, it sends the response data to the device as an HTTP response.

[0079] Step 9:

[0080] The terminal displays the received response on the user interface. For example, it might display a message on the screen such as, "Product delivery status: Product XYZ has now left the distribution center and is expected to arrive on schedule."

[0081] In this way, a process is realized that efficiently responds to user inquiries by having each step play a clear role.

[0082] (Example 1)

[0083] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0084] In today's world, systems that enable users to obtain information quickly and accurately are crucial, but conventional systems often take a long time to analyze inquiries and provide answers. Furthermore, improving efficiency and accuracy when integrating with multiple systems remains a challenge. This invention aims to solve the problem of providing quick and accurate answers to user inquiries and offering a method for efficiently integrating with other systems.

[0085] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0086] In this invention, the server includes means for receiving user input, means for analyzing the input to extract keywords and intent, means for sending a request to an appropriate other system based on the analysis results, means for receiving responses from the other system, means for integrating the received responses to generate a final response, means for providing the final response to the user, means for sending a request based on the user input and sending voice or email, and means for recording and analyzing the user's information. This enables the provision of quick and accurate responses to user inquiries and efficient cooperation with other systems.

[0087] "Means for receiving user input" refers to the means by which data is sent to a server when a user enters an inquiry or request via a terminal.

[0088] "Means for analyzing input and extracting keywords and intent" refers to methods for analyzing input data received from users using natural language processing technology to identify necessary keywords and the user's intent.

[0089] "Means for sending requests to appropriate other systems based on analysis results" refers to means for identifying the most suitable other system based on the analyzed data and sending necessary information requests to that system.

[0090] "Means for receiving responses from other systems" refers to means for receiving information or data sent back from other systems.

[0091] "Means for integrating received responses to generate a final response" refers to a means of integrating information received from multiple other systems and generating a single, continuous response to provide to the user.

[0092] "Means of providing the final answer to the user" refers to means of sending the generated final answer to the user's device and displaying it on the user interface.

[0093] "A means of sending requests based on user input and sending voice or email notifications" refers to a means of sending requests to an external system based on the content of a user's inquiry and providing notifications via voice or email as needed.

[0094] "Means for recording and analyzing user information" refers to methods for recording user inquiry history and behavioral logs, and analyzing the data for subsequent analysis and improvement.

[0095] This invention is a system for providing quick and accurate answers to user-inputted inquiries, and it operates efficiently through cooperation with servers, terminals, and other systems.

[0096] System Configuration

[0097] The system consists of the following main components:

[0098] Terminal: A device that the user directly operates (e.g., a personal computer, a smartphone).

[0099] Server: A central processing unit that receives and analyzes inquiries and generates responses in cooperation with other systems.

[0100] Other systems: External systems that the server uses to retrieve information in response to queries (e.g., databases and application programming interfaces (APIs)).

[0101] Program Processing Overview

[0102] The user operates their device and enters their question into the inquiry form. For example, using a personal computer or smartphone, they might enter "I want to know the delivery status of product with order ID 12345" and press the submit button. This causes the device to send the inquiry to the server as an HTTP POST request.

[0103] The server processes HTTP POST requests received from the terminal using web frameworks such as Python's Flask or Node.js's Express. The received data is parsed by a natural language processing (NLP) engine (e.g., Amazon Comprehend or Dialogflow) to extract keywords and intent. For example, the keyword "delivery status" and the intent "I want to know the delivery status of the product with order ID 12345" might be extracted.

[0104] Based on the analysis results, the server sends information requests to the most appropriate other systems. For example, it sends an HTTP GET request to the API endpoint of the logistics management system to retrieve delivery information for "Order ID 12345". This request includes the order ID specified by the user.

[0105] The logistics management system searches the database for delivery information corresponding to the specified order ID and sends back information to the server, such as "Product XYZ has now left the distribution center and is scheduled to arrive on time."

[0106] The server integrates data received from other systems and generates a final response. If necessary, it may also collect additional information from other systems, such as customer management systems. The integrated information is then sent to the user's terminal, which displays it on its user interface. This allows the user to obtain a quick and accurate response.

[0107] Specific example

[0108] User inquiry input

[0109] A user enters an inquiry on an online shopping site, stating, "I want to know the delivery status of my order," and presses the submit button. For example, they might enter, "Please tell me the delivery status of the item with order ID 12345."

[0110] Server-based analysis

[0111] The server analyzes the received input data using natural language processing to extract the keywords and intent behind "delivery status" and "order ID 12345".

[0112] Integration with other systems

[0113] The server calls the logistics management system's API to request delivery information for a specified order ID. For example, it might query the delivery status of order ID 12345.

[0114] Collection and integration of responses

[0115] The logistics management system searches for delivery information for "Order ID 12345" and returns the information "Product XYZ has now left the distribution center and is scheduled to arrive on time."

[0116] Providing answers to users

[0117] The server generates the final response and sends it to the terminal. The terminal displays the response, "Product XYZ has now left the distribution center and is scheduled to arrive on time," on the user interface.

[0118] Example of a prompt

[0119] "Please tell me the current delivery status of the item with order ID 12345."

[0120] This system enables a series of processes for providing quick and accurate answers to user inquiries.

[0121] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0122] Step 1:

[0123] The user operates the terminal and enters a question into the inquiry form. For example, they might enter "I want to know the delivery status of product with order ID 12345" into the form and press the submit button. This action sends the inquiry to the server as an HTTP POST request. The input is the user's inquiry, and the output is the HTTP POST request to the server.

[0124] Step 2:

[0125] The server processes the HTTP POST request received from the terminal. The server parses the request body using a web framework such as Flask or Express. This request body is the input, and the result of the parsing is the output. Specifically, the server uses a natural language processing (NLP) engine to parse the user's input and extract the keyword "delivery status" and the intent "I want to know the delivery status of the product with order ID 12345."

[0126] Step 3:

[0127] Based on the analysis results, the server sends a request to the appropriate other system. In this case, the server generates an HTTP GET request to the logistics management system's API endpoint. The input is the analysis result "Delivery Status" and "Order ID 12345," and the output is an HTTP GET request to the logistics management system. Specifically, the server finds the API endpoint and includes the necessary parameters in the request.

[0128] Step 4:

[0129] The other system (the logistics management system) processes the HTTP GET request received from the server. The logistics management system searches the database and retrieves the corresponding order ID information. The input is the HTTP GET request from the server, and the output is information about the delivery status (e.g., "Product XYZ has now left the distribution center and is expected to arrive on schedule"). This information is sent back to the server as an HTTP response.

[0130] Step 5:

[0131] The server verifies the information received from the logistics management system and collects additional information from other systems as needed. For example, it may collect verification information from the customer management system. The input is delivery status information from the logistics management system, and based on this, additional requests are generated to obtain other necessary data. The output is the final integrated information. Specifically, the server issues additional API requests and integrates all the information after collecting the additional information.

[0132] Step 6:

[0133] The server generates a final response based on the integrated information. For example, it might generate a response such as, "Product XYZ has now left the distribution center and is scheduled to arrive on time." This generated response is the input, and the output is the HTTP response sent to the terminal. Specifically, the server sends the generated response to the terminal as a JSON response.

[0134] Step 7:

[0135] The terminal displays the final response received from the server on the user interface. The user can confirm information such as, "Product XYZ has now left the distribution center and is scheduled to arrive on time." The input is the final response from the server, and the output is the information displayed on the user interface. Specifically, the terminal analyzes the received data and displays it in a user-friendly format.

[0136] This process ensures that users receive quick and accurate responses to their inquiries.

[0137] (Application Example 1)

[0138] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0139] Users of autonomous vehicles always want to know the vehicle's current location, battery status, and route status quickly and accurately. However, conventional systems often take a long time to acquire this information, which has led to decreased user satisfaction. This invention aims to solve this problem by providing a system that can provide information quickly and accurately.

[0140] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0141] In this invention, the server includes means for sending inquiries from a user terminal to the server and identifying appropriate other systems from the analysis results using a natural language processing model, and means for performing analysis again using the information of the other systems and integrating appropriate autonomous vehicle information to present to the user. This makes it possible for users to quickly and accurately obtain the information they want to know about autonomous vehicles.

[0142] A "user terminal" refers to a device operated by a user, and includes mobile devices such as smartphones and tablets.

[0143] A "server" is a central processing system that receives inquiries from user terminals, performs analysis, and coordinates with other systems.

[0144] A "natural language processing model" is an algorithm or system that analyzes user input and extracts appropriate keywords and intents.

[0145] "Other systems" refer to external information provision systems with which the server collaborates to retrieve information in response to inquiries.

[0146] "Analysis results" refer to keywords and intentions extracted by the natural language processing model.

[0147] A "request" is a request to retrieve information that is sent to another system based on the analysis results.

[0148] "Response" refers to information sent back to the server from another system.

[0149] "Integration" refers to the process by which a server combines multiple responses it has received into a single, continuous piece of information.

[0150] A "final answer" is a complete answer generated to provide the user with integrated information.

[0151] A "generative AI model" is a module that uses artificial intelligence to generate appropriate prompt sentences in response to user inquiries.

[0152] A "prompt" refers to a query or instruction in natural language output by a generative AI model.

[0153] This invention is a system that coordinates user terminals, servers, and other systems to respond quickly and accurately to user requests for information retrieval.

[0154] System Configuration

[0155] The system consists of the following main components:

[0156] 1. User terminal:

[0157] This refers to a device operated by the user, including smartphones and tablets. Users use this device to send inquiries.

[0158] 2. Server:

[0159] A central processing system that receives inquiries and performs analysis using natural language processing models. Based on the analysis results, the server sends requests to other systems, integrates the responses, and generates a final answer.

[0160] 3. Other systems:

[0161] An external information provider system that the server collaborates with to obtain necessary information. This includes location information, battery status, and route information for autonomous vehicles.

[0162] Program processing

[0163] The system works as follows:

[0164] 1. Receiving an inquiry:

[0165] The user sends a request through an application on their device. For example, they might type, "Tell me my current location."

[0166] 2. Data Analysis:

[0167] The server analyzes the received query using a natural language processing model to extract keywords and intent. Based on the analysis results, it sends a request to the appropriate other system.

[0168] 3. Information acquisition:

[0169] The server retrieves necessary information from other systems, such as the location and battery status of autonomous vehicles.

[0170] 4. Information Integration:

[0171] The server integrates the acquired information and generates a final response to provide to the user.

[0172] 5. Providing an answer:

[0173] The integrated final response is sent to the user's terminal and displayed on the user interface.

[0174] Hardware and software to be used

[0175] The main hardware and software used are as follows:

[0176] Hardware: Smartphones, tablets, servers

[0177] Software: transformers library, requests library

[0178] Natural Language Processing Models: Generative AI Models

[0179] Specific example

[0180] If a user wants to know the current location of an autonomous vehicle, it works as follows:

[0181] 1. The user enters "Tell me my current location" into the app's contact form.

[0182] 2. The server receives the query and uses a natural language processing model to analyze the keyword "current location" and the intent "tell me".

[0183] 3. The server sends a request to the appropriate other system (for example, a vehicle location information system).

[0184] 4. The server receives information from other systems, such as "The vehicle's current location is XX," and integrates it.

[0185] 5. The server generates integrated information and displays "The vehicle's current location is XX" on the user's terminal.

[0186] Example of a prompt

[0187] The following are examples of prompts to input into a specific generative AI model:

[0188] User inquiry: "What is the current battery status of the autonomous vehicle?"

[0189] Context: "The autonomous vehicle's battery is now fully charged and ready to depart."

[0190] This allows users to obtain information quickly and accurately, leading to increased satisfaction.

[0191] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0192] Step 1:

[0193] User Inquiry Submission

[0194] The user enters their question into the inquiry form using their own device (smartphone or tablet) and presses the "Send" button. For example, they might enter "Tell me your current location." This input is sent from the device to the server.

[0195] Input: User's question (e.g., "Tell me your current location")

[0196] Output: Server query data

[0197] Step 2:

[0198] Server receives and analyzes queries.

[0199] The server receives the query sent from the terminal. The received data is parsed using a natural language processing model (e.g., the transformers library). Through this parsing, the query's keywords ("current location") and intent ("tell me") are extracted.

[0200] Input: User inquiry data

[0201] Output: Extracted keywords and intent

[0202] Step 3:

[0203] Identifying and sending requests to appropriate other systems

[0204] Based on the analysis results, the server identifies appropriate other systems to obtain the necessary information. For example, a vehicle location information system might be selected. The server sends a request to this system to query for the required information (e.g., the vehicle's current location).

[0205] Input: Extracted keywords and intent

[0206] Output: Request to the appropriate other system

[0207] Step 4:

[0208] Acquiring information from other systems

[0209] Other systems provide the necessary information in response to requests from the server. For example, a vehicle location information system returns the response, "The vehicle's current location is XX." The server receives this response.

[0210] Input: Request from server

[0211] Output: Information from other systems (e.g., the vehicle's current location)

[0212] Step 5:

[0213] Information integration and final answer generation

[0214] The server integrates information obtained from other systems and generates a final answer to provide to the user. This includes generating prompts using a generative AI model. For example, it might generate an answer such as, "The vehicle's current location is XX."

[0215] Input: Information from other systems

[0216] Output: Integrated final answer

[0217] Step 6:

[0218] Providing answers to users

[0219] The server sends the final generated response to the user's terminal. The user's terminal displays this response on its user interface, allowing the user to verify the answer to their inquiry.

[0220] Input: Integrated final answer

[0221] Output: The response displayed on the user's terminal (e.g., "The vehicle's current location is XX")

[0222] This allows users to quickly and accurately obtain information about autonomous vehicles.

[0223] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0224] This invention is a system that adds a function to recognize user emotions and adjust responses accordingly, and operates efficiently through cooperation with servers, terminals, and other systems. This enables responses that are tailored to the user's emotions, thereby improving the quality of customer support.

[0225] System Configuration

[0226] The system consists of the following main components:

[0227] Terminal: A device that the user directly operates (e.g., a personal computer, a smartphone).

[0228] Server: A central processing unit that receives and analyzes inquiries and generates responses in cooperation with other systems.

[0229] Other systems: External systems (e.g., databases or dedicated APIs) that the server uses to retrieve information in response to queries.

[0230] Emotion Engine: A dedicated function that recognizes emotions from user input and reflects them in the analysis results.

[0231] Program Processing Overview

[0232] The user makes a query through their device, and the content is received by the server. The server analyzes the received data using natural language processing (NLP) and an emotion engine, extracting keywords, intent, and even the user's emotions. The server then identifies the most suitable other system based on the analysis results and sends a request, taking emotions into consideration. When the responses from the other systems are returned to the server, the server integrates them, generates a final response adjusted according to the user's emotions, and provides it to the user via their device.

[0233] Specific example

[0234] Step 1: User input

[0235] The terminal sends the information to the server when the user enters "I want to know the delivery status of my product" into the inquiry form and presses the submit button.

[0236] For example, user A wants to know the delivery status of an item they ordered from an online shopping site, and enters a question.

[0237] Step 2: Server-based analysis

[0238] When the server receives a user inquiry, it analyzes the inquiry using natural language processing and an emotion engine. The analysis extracts the keyword "delivery status," the user's intention ("I want to know the delivery status of the product ordered by user A"), and the user's emotions (e.g., impatience or dissatisfaction).

[0239] Step 3: Integration with other systems

[0240] The server selects the most suitable other system (e.g., a logistics management system) from which to obtain "delivery status" information and sends a request that takes emotions into consideration. For example, if an emotion indicating a need for a faster response is detected, the server will also send a request that includes this information.

[0241] Step 4: Collecting and integrating responses

[0242] Other systems (for example, a logistics management system) process the received request, search their internal database, and generate a response. For example, they might send back information to the server such as, "Product XYZ has now left the distribution center and is scheduled to arrive on time."

[0243] The server verifies the received information and, if necessary, collects additional information from other systems (e.g., customer management systems).

[0244] Step 5: Providing responses to users

[0245] The server integrates all the collected information and generates a final response tailored to the user's feelings. For example, if the user is dissatisfied, it will respond politely with something like, "We apologize for any inconvenience this may have caused. Product XYZ has now left the distribution center and is expected to arrive on schedule."

[0246] The terminal displays the response received from the server on the user interface. User A can receive a quick, accurate, and emotionally sensitive response to their inquiry.

[0247] In this way, the entire system efficiently implements a series of processes, from user inquiry input to server analysis, the introduction of an emotion engine, and appropriate integration with other systems, ultimately providing an emotionally sensitive response.

[0248] The following describes the processing flow.

[0249] Step 1:

[0250] When a user enters "I want to know the delivery status of my product" into the inquiry form and presses the submit button, the device sends that information to the server. Specifically, when the form submission event occurs, the entered text data is sent to the server as an HTTP request.

[0251] Step 2:

[0252] The server receives user inquiries and analyzes their content. Specifically, it extracts text data from the body of the HTTP request and uses a natural language processing (NLP) library to extract keywords and intent from the text data.

[0253] Step 3:

[0254] The server passes the user's input text to the sentiment engine, which then recognizes the user's emotions. For example, if the text is "I'm very worried. When will the product arrive?", the sentiment engine detects the user's emotion as "worried".

[0255] Step 4:

[0256] Based on the keyword "delivery status," the user's intention to "know the delivery status of the product ordered by user A," and the emotion of "concern," the server identifies the most suitable other system (for example, a logistics management system).

[0257] Step 5:

[0258] The server sends API requests to other systems it uses. Specifically, it sends requests to the logistics management system that include relevant data such as the user ID, order ID, and detected emotions ("worried").

[0259] Step 6:

[0260] Other systems (for example, a logistics management system) process the received request, search their internal database, and generate a response. For example, they might send back information to the server such as, "Product XYZ has now left the distribution center and is scheduled to arrive on time."

[0261] Step 7:

[0262] The server receives responses from other systems and, if necessary, collects additional information from other systems (e.g., customer management systems). For example, it may also collect user purchase history and current delivery status.

[0263] Step 8:

[0264] The server integrates the collected information to generate a final response. For example, it might combine messages such as, "Product XYZ has now left the distribution center and is expected to arrive on schedule," and "We apologize for any inconvenience this may have caused."

[0265] Step 9:

[0266] The server sends the final response back to the user's device. Specifically, it sends the response data to the device as an HTTP response.

[0267] Step 10:

[0268] The device displays the received response on the user interface. For example, it might display a message such as, "Product delivery status: Product XYZ has now left the distribution center and is expected to arrive on schedule. We apologize for any inconvenience this may have caused."

[0269] In this way, the entire system efficiently implements a series of processes, from user inquiry input to server analysis, the introduction of an emotion engine, and appropriate integration with other systems, ultimately providing an emotionally sensitive response.

[0270] (Example 2)

[0271] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0272] Traditional systems extracted only keywords and intent from user inquiries, without considering emotions. This resulted in a failure to address user frustration and impatience, leading to a decline in the quality of customer support. Furthermore, ineffective requests to appropriate external systems and inefficient integration of responses sometimes resulted in delays in user responses.

[0273] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0274] In this invention, the server includes means for receiving user input, means for analyzing the input to extract keywords, intentions, and emotions, means for sending requests to appropriate other systems based on the analysis results, means for receiving responses from the other systems, means for integrating the received responses and generating a final response adjusted according to the user's emotions, and means for providing the final response to the user. This enables the provision of quick and appropriate responses that take the user's emotions into consideration.

[0275] A "user" is the entity that operates the system and makes inquiries.

[0276] An "input" is the information that a user sends to the system through a terminal.

[0277] A "terminal" is a device that a user directly operates and includes personal computers, smartphones, etc.

[0278] A "server" is a device that receives and analyzes inquiries as a central processing unit and coordinates with other systems.

[0279] "Analysis" is the process of using natural language processing and sentiment analysis to understand the content of a user's input, extract keywords, intentions, and sentiment.

[0280] "Natural language processing" is the technology that analyzes text data and interprets grammar and meaning.

[0281] "Sentiment analysis" is the technology that recognizes sentiment from a user's input and reflects it in the analysis results.

[0282] A "keyword" is an important phrase extracted from a user's input.

[0283] An "intention" is the purpose or desire that a user attempts to achieve through an inquiry.

[0284] "Sentiment" is the psychological state recognized from a user's input, such as anxiety or dissatisfaction.

[0285] "Other systems" are external systems that a server uses to obtain information and include, for example, logistics management systems and customer management systems.

[0286] A "request" is a demand that a server sends to other systems to obtain information.

[0287] "Answer" refers to the information returned from other systems and is used by the server to provide to the user.

[0288] "Integration" is a process of combining multiple pieces of information into one consistent format.

[0289] "Final Answer" is the answer generated by the server based on the integrated information and provided to the user.

[0290] "Provision" is the act of the server sending the final answer generated to the user's terminal to show a response to the user.

[0291] This invention is a system with an added function of recognizing the user's emotion and adjusting the answer based on it. The system operates efficiently through the cooperation of the server, terminal, and other systems, enabling a response according to the user's emotion, thereby improving the quality of customer support. The embodiments of this system will be specifically described below.

[0292] Configuration of the System

[0293] The system is composed of the following main components:

[0294] Terminal: A device directly operated by the user (e.g., a personal computer, smartphone).

[0295] Server: A central processing unit that receives and analyzes inquiries and generates answers in cooperation with other systems.

[0296] Other Systems: External systems (e.g., databases, dedicated APIs) used by the server to obtain information according to the inquiry content.

[0297] Emotion Engine: A dedicated function that recognizes emotion from the user's input and reflects it in the analysis results.

[0298] Overview of Program Processing

[0299] When a user makes an inquiry through a terminal, the content is received by the server. The server analyzes the received data using natural language processing (NLP) and an emotion engine, and extracts keywords, intentions, and even the user's emotion. Then, based on the analysis results, the server identifies the optimal other system and sends a request while considering the emotion. When a response comes back from the other system to the server, the server integrates it, generates a final response adjusted according to the user's emotion, and provides it to the user via the terminal.

[0300] Hardware and Software to be Used

[0301] The following specific hardware and software are used for the server and the terminal:

[0302] Python: A programming language used for natural language processing and emotion analysis.

[0303] NLTK library: A Python library for performing natural language processing.

[0304] Google (registered trademark) Cloud Natural Language API: A cloud-based API for performing emotion analysis.

[0305] RabbitMQ: Used for message queue management within the server.

[0306] HTTP request: A communication protocol used when the server cooperates with other systems.

[0307] REST API and JSON: A format and protocol used for data exchange between the server and other systems.

[0308] Specific Examples

[0309] Step 1: User input

[0310] The user enters "I want to know the delivery status of my product" into the inquiry form on their device and presses the submit button.

[0311] The terminal internally constructs and sends an HTTP POST request to the server to send the contents of this inquiry.

[0312] Step 2: Server receives and analyzes data.

[0313] The server stores the query content received from the terminal in a message queue such as RabbitMQ.

[0314] The server executes a Python script and uses the NLTK library to extract the keyword "delivery status" and the intent "I want to know the delivery status of the items ordered by user A."

[0315] The server calls the Google Cloud Natural Language API to detect that the user is feeling anxious.

[0316] Step 3: Integration with other systems

[0317] The server uses an HTTP client (for example, Python's requests library) to send a request to the logistics management system to inquire about the "delivery status".

[0318] The server also adds additional information to the request header, such as "the user is feeling anxious."

[0319] Step 4: Collecting and integrating responses

[0320] The system processes the request received by another system (the logistics management system), searches its internal database, and generates information. It then sends back the information to the server stating, "Product XYZ has now left the distribution center and is scheduled to arrive on time."

[0321] The server collects necessary information from other related systems (e.g., customer management systems) and integrates all the data.

[0322] Step 5: Providing responses to users

[0323] Based on the information collected by the server, a final response is generated that is tailored to the user's emotions. For example, a response that reassures the user might be something like, "We apologize for any concern this may have caused. Product XYZ has now left the distribution center and is expected to arrive on schedule."

[0324] The device receives the HTTP response and displays the final answer in the user interface (e.g., a text area on a web page).

[0325] Example of a prompt

[0326] Analyze the following inquiry and generate the appropriate answer:

[0327] Inquiry: "I would like to know the delivery status of my order."

[0328] User emotion: "Anxiety"

[0329] Please obtain the necessary information from relevant systems and provide an emotionally sensitive response.

[0330] In this way, the responses provided, from user inquiry input to server analysis, the introduction of an emotion engine, and appropriate integration with other systems, are efficiently delivered in a manner that takes the user's emotions into consideration.

[0331] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0332] Step 1: User inquiry input

[0333] Input: Text entered by the user in the inquiry form (e.g., "I would like to know the delivery status of my order").

[0334] Output: Data sent to the server from the contents of the inquiry form.

[0335] Specific operation: The user enters "I want to know the delivery status of my product" into the inquiry form on the device and presses the submit button. The device constructs and sends an HTTP POST request to send this inquiry to the server. The request includes necessary metadata such as the user ID, inquiry content, and timestamp.

[0336] Step 2: Server receives and analyzes data.

[0337] Input: Inquiry content sent from the terminal (HTTP POST request)

[0338] Output: Keywords, intentions, and emotions as analysis results (Example: Keyword "Delivery status", Intention "I want to know the delivery status of the product", Emotion "Anxiety")

[0339] Specific operation: The server stores the content of the inquiry received from the terminal in a message queue such as RabbitMQ. The server then executes a Python script to parse the inquiry. First, it uses the NLTK library to extract the keyword "delivery status" and the intention "I want to know the delivery status of the product" from the text. Next, it calls the Google Cloud Natural Language API to detect the user's emotion (e.g., "anxiety").

[0340] Step 3: Integration with other systems

[0341] Input: Analysis results (Keyword "Delivery status", Intent "I want to know the delivery status of the product", Emotion "Anxiety")

[0342] Output: Requests to other systems (e.g., HTTP requests to a logistics management system)

[0343] Specific operation: Based on the analysis results, the server forwards the analysis data to the most suitable other system. Using the Python requests library, a request is sent to the logistics management system to inquire about the "delivery status". This request includes information such as the user ID, the content of the inquiry, and the analyzed emotion (e.g., "anxiety").

[0344] Step 4: Collecting and integrating responses

[0345] Input: Response from another system (Example: "Product XYZ has now left the distribution center and is scheduled to arrive on time.")

[0346] Output: Integrated response data (Example: "Product XYZ has now left the distribution center and is expected to arrive on schedule. We apologize for any inconvenience this may have caused.")

[0347] Specific operation: The logistics management system processes the received request and retrieves the necessary information by referring to its internal database. For example, it might return information in JSON format such as, "Product XYZ has now left the distribution center and is scheduled to arrive on time." The server verifies the received information and, if additional information is needed, gathers information from other systems (e.g., customer management system). The server integrates all the collected information and generates a final response that takes the user's feelings into consideration.

[0348] Step 5: Providing responses to users

[0349] Input: Integrated final response (Example: "Item XYZ has now left the distribution center and is expected to arrive on schedule. We apologize for any inconvenience this may have caused.")

[0350] Output: Response message provided to the user

[0351] Specific operation: The server sends the final response it generates to the terminal as an HTTP response. The terminal receives this and displays it in the user interface. The displayed message includes product information as well as language that takes the user's feelings into consideration (e.g., "We apologize for any inconvenience this may have caused"). This allows the user to receive a quick, accurate, and emotionally considerate response to their inquiry.

[0352] (Application Example 2)

[0353] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0354] Traditional content delivery services often provided uniform recommended content without considering users' emotional states, resulting in insufficient user satisfaction. Furthermore, accurately understanding user needs was difficult, leading to a decline in content quality and relevance. Therefore, personalized content delivery tailored to user emotions is in demand.

[0355] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0356] In this invention, the server includes means for receiving user input, means for analyzing the input to extract emotions, keywords, and intentions, means for sending requests to appropriate other systems based on the analysis results, means for receiving responses from the other systems, means for integrating the received responses and generating a final response adjusted based on emotions, and means for providing the final response to the user. This enables the recommendation of appropriate content according to the user's emotional state.

[0357] "Means for receiving user input" refers to devices or functions that receive operations or inquiries made by users to the system.

[0358] "Means for analyzing input to extract emotions, keywords, and intentions" refers to devices or functions that process input data received from a user to identify emotions, important words, and the purposes or requests that those words represent.

[0359] "Means for sending requests to appropriate other systems" refers to devices or functions that send requests to external systems selected based on the analysis results to obtain the necessary information.

[0360] "Means for receiving responses from other systems" refers to devices or functions for receiving responses from external systems that have sent requests.

[0361] "Means for integrating received responses and generating a final response adjusted based on emotions" refers to devices or functions that integrate information obtained from external systems and generate a final response optimized according to the user's emotional state.

[0362] "Means of providing the final answer to the user" refers to devices or functions that present the user with an answer generated based on analysis results and information from external systems.

[0363] "Natural language processing" is a technology that analyzes natural language input from users and understands its meaning and intent.

[0364] "Emotion recognition" is a technology that detects and classifies a user's emotional state based on input data, facial expressions, voice, and other factors.

[0365] "Means of selecting the optimal system from multiple other systems" refers to a device or function that selects the most appropriate system from several external systems and sends a request to that system.

[0366] This invention is a system that recognizes user emotions and adjusts responses accordingly, operating efficiently through collaboration with servers, terminals, and other systems. This system consists of the following main components:

[0367] System Configuration

[0368] Terminal: A device that the user directly operates (for example, a smartphone).

[0369] Server: A central processing unit that receives and analyzes inquiries and generates responses in cooperation with other systems.

[0370] Other systems: External systems that the server uses to retrieve information in response to queries (e.g., content databases or dedicated APIs).

[0371] Emotion Engine: A dedicated function that recognizes emotions from user input and facial expressions and reflects them in the analysis results.

[0372] Specific implementation methods

[0373] 1. User inquiry input

[0374] Users access content distribution service applications using devices such as smartphones to make inquiries and perform actions. For example, a user might type, "I'd like recommendations for relaxing music."

[0375] 2. Server-based analysis

[0376] When the server receives user input, it analyzes this input using natural language processing (NLP) and emotion recognition techniques. The analysis extracts the keyword "relaxing music," the intention "I want to relax," and the user's emotional state (e.g., feeling stressed).

[0377] 3. Integration with other systems

[0378] Based on the analysis results, the server sends requests to appropriate other systems (e.g., content databases or recommendation APIs). For example, if a user is experiencing stress, it might request other systems to retrieve a list of music specifically designed for relaxation.

[0379] 4. Collection and Integration of Responses

[0380] Other systems process received requests, search their internal databases, and generate appropriate content. For example, they might send information about a "relaxation music playlist" back to the server.

[0381] 5. Providing responses to users

[0382] The server integrates all the collected information and generates a final response tailored to the user's emotional state. This may include specific suggestions, such as, "To help reduce your stress, we recommend this relaxation music." The terminal displays the response received from the server on its user interface.

[0383] Hardware and software to use

[0384] Hardware: Smartphone with camera

[0385] Software: OpenCV, TENSORFLOW®, emotion recognition API, content recommendation API

[0386] Data processing and data calculation

[0387] The server receives input data from the user and performs semantic analysis using NLP technology. Next, the emotion engine recognizes the user's emotional state and sends a request to the most appropriate system based on the analysis results. Information obtained from the content recommendation API is integrated to generate a final response optimized according to the user's emotions.

[0388] Specific example

[0389] If you are feeling stressed: Relaxation music playlists and yoga videos are recommended.

[0390] If you are feeling joyful: Entertainment videos and adventure games are recommended.

[0391] If you are feeling sad: Encouraging messages or heartwarming documentary films are recommended.

[0392] Example of a prompt

[0393] Create an application that estimates a user's emotions from their facial expressions and recommends appropriate content based on that. Recommend different content for each of the following seven emotion categories: anger, disgust, fear, joy, sadness, surprise, and neutral.

[0394] In this way, a system is built that enables personalized content delivery that responds to the user's emotions.

[0395] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0396] Step 1:

[0397] Users access content distribution service applications using devices such as smartphones and perform inquiries and operations.

[0398] Input: User request (e.g., "Please recommend some relaxing music")

[0399] Output: User request data

[0400] Specific example: A user enters "relaxing music" into the search bar within the app and presses the search button.

[0401] Step 2:

[0402] The server receives user input sent from the terminal.

[0403] Input: User's request data

[0404] Output: Request data sent to the server

[0405] Specific example: The server receives text data from a user that says "relaxing music".

[0406] Step 3:

[0407] The server uses natural language processing (NLP) to analyze user input and extract keywords and intent. Simultaneously, it uses an emotion recognition engine to analyze the user's emotional state.

[0408] Input: Request data

[0409] Output: Keywords, intentions, emotional state

[0410] Specific example: The server analyzes the keywords "relax" and "music," the intention to "want to relax," and the emotional state as "stress."

[0411] Step 4:

[0412] Based on the analysis results, the server sends requests to the appropriate other systems (e.g., content databases or recommendation service APIs).

[0413] Input: Analysis results (keywords, intentions, emotional state)

[0414] Output: Request to other systems

[0415] Specific example: A server generates data requesting relaxation music recommendations for users experiencing stress and sends it to another system.

[0416] Step 5:

[0417] Other systems process the received request, search their internal database to select the appropriate content, and send the response to the server.

[0418] Input: Request to another system

[0419] Output: Recommended content data

[0420] Specific example: Information about a "relaxation music playlist" is sent back to the server from another system.

[0421] Step 6:

[0422] The server integrates the collected response data and generates a final response optimized based on the user's emotional state.

[0423] Input: Recommended content data

[0424] Output: Final response data

[0425] Specific example: The server generates a final response that includes a suggestion such as, "To reduce your stress, we recommend this relaxation music."

[0426] Step 7:

[0427] The final response data is sent from the server to the terminal. The terminal receives this data and displays it on the user interface.

[0428] Input: Final response data

[0429] Output: Display on the user interface

[0430] Specific example: A "relaxation music playlist" is displayed on the user's smartphone screen.

[0431] In this way, the specific processing steps from user input to the final proposal are carried out.

[0432] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0433] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0434] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0435] [Second Embodiment]

[0436] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0437] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0438] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0439] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0440] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0441] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0442] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0443] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0444] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0445] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0446] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0447] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0448] This invention is a system for providing quick and accurate answers to user-inputted inquiries, and operates efficiently through cooperation with servers, terminals, and other systems.

[0449] System Configuration

[0450] The system consists of the following main components:

[0451] Terminal: A device that the user directly operates (e.g., a personal computer, a smartphone).

[0452] Server: A central processing unit that receives and analyzes inquiries and generates responses in cooperation with other systems.

[0453] Other systems: External systems (e.g., databases or dedicated APIs) that the server uses to retrieve information in response to queries.

[0454] Program Processing Overview

[0455] When a user submits a query through their device, the content is received by the server. The server analyzes the received data using natural language processing to extract appropriate keywords and intent. Based on the analysis results, the server then identifies the most suitable other system and sends a request. When the response from the other system is returned to the server, the server integrates it to generate a single, continuous response, which is finally provided to the user via the device.

[0456] Specific example

[0457] Step 1: User input

[0458] The terminal sends the information to the server when the user enters "I want to know the delivery status of my product" into the inquiry form and presses the submit button.

[0459] For example, user A wants to know the delivery status of an item they ordered from an online shopping site, and enters a question.

[0460] Step 2: Server-based analysis

[0461] When the server receives a user inquiry, it uses natural language processing to analyze the inquiry. The analysis extracts the keyword "delivery status" and the user's intention, "I want to know the delivery status of the product ordered by user A."

[0462] Step 3: Integration with other systems

[0463] The server selects the most suitable other system from which to obtain "delivery status" information and sends the request. In this case, it determines that a database containing delivery information exists and sends the request to that database.

[0464] For example, you can query the logistics management system for the delivery status of "Order ID: 12345".

[0465] Step 4: Collecting and integrating responses

[0466] Other systems (for example, a logistics management system) search for the delivery status of the corresponding order ID and send back information to the server stating, "Product XYZ has now left the distribution center and is scheduled to arrive on time."

[0467] The server verifies the received information and, if necessary, collects additional information from other systems (e.g., customer management systems).

[0468] Step 5: Providing responses to users

[0469] The server integrates all the collected information and generates a final response. It creates a unified response such as "Product XYZ has now left the distribution center and is scheduled to arrive on time," and provides it to the user via the terminal.

[0470] The terminal displays the response received from the server on the user interface. User A can obtain a quick and accurate answer to the inquiry they entered.

[0471] In this way, the entire system efficiently implements a series of processes, from user inquiry input to server analysis and appropriate integration with other systems, ultimately providing a final answer.

[0472] The following describes the processing flow.

[0473] Step 1:

[0474] When a user enters "I want to know the delivery status of my product" into the inquiry form and presses the submit button, the device sends that information to the server. Specifically, when the form submission event occurs, the entered text data is sent to the server as an HTTP request.

[0475] Step 2:

[0476] The server receives user inquiries and analyzes their content. Specifically, it extracts text data from the body of the HTTP request and uses a natural language processing (NLP) library to extract keywords and intent from the text data.

[0477] Step 3:

[0478] The server identifies the keyword "delivery status" and the user's intention, "I want to know the delivery status of the product ordered by user A." Based on the analysis results, it selects an appropriate other system (e.g., a logistics management system).

[0479] Step 4:

[0480] The server sends API requests to other systems it uses. Specifically, it sends requests containing relevant data such as user IDs and order IDs to the logistics management system.

[0481] Step 5:

[0482] Other systems (for example, a logistics management system) process the received request, search their internal database, and generate a response. For example, they might send back information to the server such as, "Product XYZ has now left the distribution center and is scheduled to arrive on time."

[0483] Step 6:

[0484] The server receives responses from other systems. If necessary, it also collects relevant information from other systems, such as customer management systems.

[0485] Step 7:

[0486] The server integrates the collected information to generate a final response. For example, it might create a unified response such as, "Product XYZ has now left the distribution center and is scheduled to arrive on time."

[0487] Step 8:

[0488] The server sends the final response back to the user's device. Specifically, it sends the response data to the device as an HTTP response.

[0489] Step 9:

[0490] The terminal displays the received response on the user interface. For example, it might display a message on the screen such as, "Product delivery status: Product XYZ has now left the distribution center and is expected to arrive on schedule."

[0491] In this way, a process is realized that efficiently responds to user inquiries by having each step play a clear role.

[0492] (Example 1)

[0493] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0494] In today's world, systems that enable users to obtain information quickly and accurately are crucial, but conventional systems often take a long time to analyze inquiries and provide answers. Furthermore, improving efficiency and accuracy when integrating with multiple systems remains a challenge. This invention aims to solve the problem of providing quick and accurate answers to user inquiries and offering a method for efficiently integrating with other systems.

[0495] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0496] In this invention, the server includes means for receiving user input, means for analyzing the input to extract keywords and intent, means for sending a request to an appropriate other system based on the analysis results, means for receiving responses from the other system, means for integrating the received responses to generate a final response, means for providing the final response to the user, means for sending a request based on the user input and sending voice or email, and means for recording and analyzing the user's information. This enables the provision of quick and accurate responses to user inquiries and efficient cooperation with other systems.

[0497] "Means for receiving user input" refers to the means by which data is sent to a server when a user enters an inquiry or request via a terminal.

[0498] "Means for analyzing input and extracting keywords and intent" refers to methods for analyzing input data received from users using natural language processing technology to identify necessary keywords and the user's intent.

[0499] "Means for sending requests to appropriate other systems based on analysis results" refers to means for identifying the most suitable other system based on the analyzed data and sending necessary information requests to that system.

[0500] "Means for receiving responses from other systems" refers to means for receiving information or data sent back from other systems.

[0501] "Means for integrating received responses to generate a final response" refers to a means of integrating information received from multiple other systems and generating a single, continuous response to provide to the user.

[0502] "Means of providing the final answer to the user" refers to means of sending the generated final answer to the user's device and displaying it on the user interface.

[0503] "A means of sending requests based on user input and sending voice or email notifications" refers to a means of sending requests to an external system based on the content of a user's inquiry and providing notifications via voice or email as needed.

[0504] "Means for recording and analyzing user information" refers to methods for recording user inquiry history and behavioral logs, and analyzing the data for subsequent analysis and improvement.

[0505] This invention is a system for providing quick and accurate answers to user-inputted inquiries, and it operates efficiently through cooperation with servers, terminals, and other systems.

[0506] System Configuration

[0507] The system consists of the following main components:

[0508] Terminal: A device that the user directly operates (e.g., a personal computer, a smartphone).

[0509] Server: A central processing unit that receives and analyzes inquiries and generates responses in cooperation with other systems.

[0510] Other systems: External systems that the server uses to retrieve information in response to queries (e.g., databases and application programming interfaces (APIs)).

[0511] Program Processing Overview

[0512] The user operates their device and enters their question into the inquiry form. For example, using a personal computer or smartphone, they might enter "I want to know the delivery status of product with order ID 12345" and press the submit button. This causes the device to send the inquiry to the server as an HTTP POST request.

[0513] The server processes HTTP POST requests received from the terminal using web frameworks such as Python's Flask or Node.js's Express. The received data is parsed by a natural language processing (NLP) engine (e.g., Amazon Comprehend or Dialogflow) to extract keywords and intent. For example, the keyword "delivery status" and the intent "I want to know the delivery status of the product with order ID 12345" might be extracted.

[0514] Based on the analysis results, the server sends information requests to the most appropriate other systems. For example, it sends an HTTP GET request to the API endpoint of the logistics management system to retrieve delivery information for "Order ID 12345". This request includes the order ID specified by the user.

[0515] The logistics management system searches the database for delivery information corresponding to the specified order ID and sends back information to the server, such as "Product XYZ has now left the distribution center and is scheduled to arrive on time."

[0516] The server integrates data received from other systems and generates a final response. If necessary, it may also collect additional information from other systems, such as customer management systems. The integrated information is then sent to the user's terminal, which displays it on its user interface. This allows the user to obtain a quick and accurate response.

[0517] Specific example

[0518] User inquiry input

[0519] A user enters an inquiry on an online shopping site, stating, "I want to know the delivery status of my order," and presses the submit button. For example, they might enter, "Please tell me the delivery status of the item with order ID 12345."

[0520] Server-based analysis

[0521] The server analyzes the received input data using natural language processing to extract the keywords and intent behind "delivery status" and "order ID 12345".

[0522] Integration with other systems

[0523] The server calls the logistics management system's API to request delivery information for a specified order ID. For example, it might query the delivery status of order ID 12345.

[0524] Collection and integration of responses

[0525] The logistics management system searches for delivery information for "Order ID 12345" and returns the information "Product XYZ has now left the distribution center and is scheduled to arrive on time."

[0526] Providing answers to users

[0527] The server generates the final response and sends it to the terminal. The terminal displays the response, "Product XYZ has now left the distribution center and is scheduled to arrive on time," on the user interface.

[0528] Example of a prompt

[0529] "Please tell me the current delivery status of the item with order ID 12345."

[0530] This system enables a series of processes for providing quick and accurate answers to user inquiries.

[0531] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0532] Step 1:

[0533] The user operates the terminal and enters a question into the inquiry form. For example, they might enter "I want to know the delivery status of product with order ID 12345" into the form and press the submit button. This action sends the inquiry to the server as an HTTP POST request. The input is the user's inquiry, and the output is the HTTP POST request to the server.

[0534] Step 2:

[0535] The server processes the HTTP POST request received from the terminal. The server parses the request body using a web framework such as Flask or Express. This request body is the input, and the result of the parsing is the output. Specifically, the server uses a natural language processing (NLP) engine to parse the user's input and extract the keyword "delivery status" and the intent "I want to know the delivery status of the product with order ID 12345."

[0536] Step 3:

[0537] Based on the analysis results, the server sends a request to the appropriate other system. In this case, the server generates an HTTP GET request to the logistics management system's API endpoint. The input is the analysis result "Delivery Status" and "Order ID 12345," and the output is an HTTP GET request to the logistics management system. Specifically, the server finds the API endpoint and includes the necessary parameters in the request.

[0538] Step 4:

[0539] The other system (the logistics management system) processes the HTTP GET request received from the server. The logistics management system searches the database and retrieves the corresponding order ID information. The input is the HTTP GET request from the server, and the output is information about the delivery status (e.g., "Product XYZ has now left the distribution center and is expected to arrive on schedule"). This information is sent back to the server as an HTTP response.

[0540] Step 5:

[0541] The server verifies the information received from the logistics management system and collects additional information from other systems as needed. For example, it may collect verification information from the customer management system. The input is delivery status information from the logistics management system, and based on this, additional requests are generated to obtain other necessary data. The output is the final integrated information. Specifically, the server issues additional API requests and integrates all the information after collecting the additional information.

[0542] Step 6:

[0543] The server generates a final response based on the integrated information. For example, it might generate a response such as, "Product XYZ has now left the distribution center and is scheduled to arrive on time." This generated response is the input, and the output is the HTTP response sent to the terminal. Specifically, the server sends the generated response to the terminal as a JSON response.

[0544] Step 7:

[0545] The terminal displays the final response received from the server on the user interface. The user can confirm information such as, "Product XYZ has now left the distribution center and is scheduled to arrive on time." The input is the final response from the server, and the output is the information displayed on the user interface. Specifically, the terminal analyzes the received data and displays it in a user-friendly format.

[0546] This process ensures that users receive quick and accurate responses to their inquiries.

[0547] (Application Example 1)

[0548] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0549] Users of autonomous vehicles always want to know the vehicle's current location, battery status, and route status quickly and accurately. However, conventional systems often take a long time to acquire this information, which has led to decreased user satisfaction. This invention aims to solve this problem by providing a system that can provide information quickly and accurately.

[0550] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0551] In this invention, the server includes means for sending inquiries from a user terminal to the server and identifying appropriate other systems from the analysis results using a natural language processing model, and means for performing analysis again using the information of the other systems and integrating appropriate autonomous vehicle information to present to the user. This makes it possible for users to quickly and accurately obtain the information they want to know about autonomous vehicles.

[0552] A "user terminal" refers to a device operated by a user, and includes mobile devices such as smartphones and tablets.

[0553] A "server" is a central processing system that receives inquiries from user terminals, performs analysis, and coordinates with other systems.

[0554] A "natural language processing model" is an algorithm or system that analyzes user input and extracts appropriate keywords and intents.

[0555] "Other systems" refer to external information provision systems with which the server collaborates to retrieve information in response to inquiries.

[0556] "Analysis results" refer to keywords and intentions extracted by the natural language processing model.

[0557] A "request" is a request to retrieve information that is sent to another system based on the analysis results.

[0558] "Response" refers to information sent back to the server from another system.

[0559] "Integration" refers to the process by which a server combines multiple responses it has received into a single, continuous piece of information.

[0560] A "final answer" is a complete answer generated to provide the user with integrated information.

[0561] A "generative AI model" is a module that uses artificial intelligence to generate appropriate prompt sentences in response to user inquiries.

[0562] A "prompt" refers to a query or instruction in natural language output by a generative AI model.

[0563] This invention is a system that coordinates user terminals, servers, and other systems to respond quickly and accurately to user requests for information retrieval.

[0564] System Configuration

[0565] The system consists of the following main components:

[0566] 1. User terminal:

[0567] This refers to a device operated by the user, including smartphones and tablets. Users use this device to send inquiries.

[0568] 2. Server:

[0569] A central processing system that receives inquiries and performs analysis using natural language processing models. Based on the analysis results, the server sends requests to other systems, integrates the responses, and generates a final answer.

[0570] 3. Other systems:

[0571] An external information provider system that the server collaborates with to obtain necessary information. This includes location information, battery status, and route information for autonomous vehicles.

[0572] Program processing

[0573] The system works as follows:

[0574] 1. Receiving an inquiry:

[0575] The user sends a request through an application on their device. For example, they might type, "Tell me my current location."

[0576] 2. Data Analysis:

[0577] The server analyzes the received query using a natural language processing model to extract keywords and intent. Based on the analysis results, it sends a request to the appropriate other system.

[0578] 3. Information acquisition:

[0579] The server retrieves necessary information from other systems, such as the location and battery status of autonomous vehicles.

[0580] 4. Information Integration:

[0581] The server integrates the acquired information and generates a final response to provide to the user.

[0582] 5. Providing an answer:

[0583] The integrated final response is sent to the user's terminal and displayed on the user interface.

[0584] Hardware and software to be used

[0585] The main hardware and software used are as follows:

[0586] Hardware: Smartphones, tablets, servers

[0587] Software: transformers library, requests library

[0588] Natural Language Processing Models: Generative AI Models

[0589] Specific example

[0590] If a user wants to know the current location of an autonomous vehicle, it works as follows:

[0591] 1. The user enters "Tell me my current location" into the app's contact form.

[0592] 2. The server receives the query and uses a natural language processing model to analyze the keyword "current location" and the intent "tell me".

[0593] 3. The server sends a request to the appropriate other system (for example, a vehicle location information system).

[0594] 4. The server receives information from other systems, such as "The vehicle's current location is XX," and integrates it.

[0595] 5. The server generates integrated information and displays "The vehicle's current location is XX" on the user's terminal.

[0596] Example of a prompt

[0597] The following are examples of prompts to input into a specific generative AI model:

[0598] User inquiry: "What is the current battery status of the autonomous vehicle?"

[0599] Context: "The autonomous vehicle's battery is now fully charged and ready to depart."

[0600] This allows users to obtain information quickly and accurately, leading to increased satisfaction.

[0601] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0602] Step 1:

[0603] User Inquiry Submission

[0604] The user enters their question into the inquiry form using their own device (smartphone or tablet) and presses the "Send" button. For example, they might enter "Tell me your current location." This input is sent from the device to the server.

[0605] Input: User's question (e.g., "Tell me your current location")

[0606] Output: Server query data

[0607] Step 2:

[0608] Server receives and analyzes queries.

[0609] The server receives the query sent from the terminal. The received data is parsed using a natural language processing model (e.g., the transformers library). Through this parsing, the query's keywords ("current location") and intent ("tell me") are extracted.

[0610] Input: User inquiry data

[0611] Output: Extracted keywords and intent

[0612] Step 3:

[0613] Identifying and sending requests to appropriate other systems

[0614] Based on the analysis results, the server identifies appropriate other systems to obtain the necessary information. For example, a vehicle location information system might be selected. The server sends a request to this system to query for the required information (e.g., the vehicle's current location).

[0615] Input: Extracted keywords and intent

[0616] Output: Request to the appropriate other system

[0617] Step 4:

[0618] Acquiring information from other systems

[0619] Other systems provide the necessary information in response to requests from the server. For example, a vehicle location information system returns the response, "The vehicle's current location is XX." The server receives this response.

[0620] Input: Request from server

[0621] Output: Information from other systems (e.g., the vehicle's current location)

[0622] Step 5:

[0623] Information integration and final answer generation

[0624] The server integrates information obtained from other systems and generates a final answer to provide to the user. This includes generating prompts using a generative AI model. For example, it might generate an answer such as, "The vehicle's current location is XX."

[0625] Input: Information from other systems

[0626] Output: Integrated final answer

[0627] Step 6:

[0628] Providing answers to users

[0629] The server sends the final generated response to the user's terminal. The user's terminal displays this response on its user interface, allowing the user to verify the answer to their inquiry.

[0630] Input: Integrated final answer

[0631] Output: The response displayed on the user's terminal (e.g., "The vehicle's current location is XX")

[0632] This allows users to quickly and accurately obtain information about autonomous vehicles.

[0633] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0634] This invention is a system that adds a function to recognize user emotions and adjust responses accordingly, and operates efficiently through cooperation with servers, terminals, and other systems. This enables responses that are tailored to the user's emotions, thereby improving the quality of customer support.

[0635] System Configuration

[0636] The system consists of the following main components:

[0637] Terminal: A device that the user directly operates (e.g., a personal computer, a smartphone).

[0638] Server: A central processing unit that receives and analyzes inquiries and generates responses in cooperation with other systems.

[0639] Other systems: External systems (e.g., databases or dedicated APIs) that the server uses to retrieve information in response to queries.

[0640] Emotion Engine: A dedicated function that recognizes emotions from user input and reflects them in the analysis results.

[0641] Program Processing Overview

[0642] The user makes a query through their device, and the content is received by the server. The server analyzes the received data using natural language processing (NLP) and an emotion engine, extracting keywords, intent, and even the user's emotions. The server then identifies the most suitable other system based on the analysis results and sends a request, taking emotions into consideration. When the responses from the other systems are returned to the server, the server integrates them, generates a final response adjusted according to the user's emotions, and provides it to the user via their device.

[0643] Specific example

[0644] Step 1: User input

[0645] The terminal sends the information to the server when the user enters "I want to know the delivery status of my product" into the inquiry form and presses the submit button.

[0646] For example, user A wants to know the delivery status of an item they ordered from an online shopping site, and enters a question.

[0647] Step 2: Server-based analysis

[0648] When the server receives a user inquiry, it analyzes the inquiry using natural language processing and an emotion engine. The analysis extracts the keyword "delivery status," the user's intention ("I want to know the delivery status of the product ordered by user A"), and the user's emotions (e.g., impatience or dissatisfaction).

[0649] Step 3: Integration with other systems

[0650] The server selects the most suitable other system (e.g., a logistics management system) from which to obtain "delivery status" information and sends a request that takes emotions into consideration. For example, if an emotion indicating a need for a faster response is detected, the server will also send a request that includes this information.

[0651] Step 4: Collecting and integrating responses

[0652] Other systems (for example, a logistics management system) process the received request, search their internal database, and generate a response. For example, they might send back information to the server such as, "Product XYZ has now left the distribution center and is scheduled to arrive on time."

[0653] The server verifies the received information and, if necessary, collects additional information from other systems (e.g., customer management systems).

[0654] Step 5: Providing responses to users

[0655] The server integrates all the collected information and generates a final response tailored to the user's feelings. For example, if the user is dissatisfied, it will respond politely with something like, "We apologize for any inconvenience this may have caused. Product XYZ has now left the distribution center and is expected to arrive on schedule."

[0656] The terminal displays the response received from the server on the user interface. User A can receive a quick, accurate, and emotionally sensitive response to their inquiry.

[0657] In this way, the entire system efficiently implements a series of processes, from user inquiry input to server analysis, the introduction of an emotion engine, and appropriate integration with other systems, ultimately providing an emotionally sensitive response.

[0658] The following describes the processing flow.

[0659] Step 1:

[0660] The device sends the information to the server when the user enters "I want to know the delivery status of my product" into the inquiry form and presses the submit button. Specifically, when the form submission event occurs, the entered text data is sent to the server as an HTTP request.

[0661] Step 2:

[0662] The server receives user inquiries and analyzes their content. Specifically, it extracts text data from the body of the HTTP request and uses a natural language processing (NLP) library to extract keywords and intent from the text data.

[0663] Step 3:

[0664] The server passes the user's input text to the sentiment engine, which then recognizes the user's emotions. For example, if the text is "I'm very worried. When will the product arrive?", the sentiment engine detects the user's emotion as "worried".

[0665] Step 4:

[0666] Based on the keyword "delivery status," the user's intention to "know the delivery status of the product ordered by user A," and the emotion of "concern," the server identifies the most suitable other system (for example, a logistics management system).

[0667] Step 5:

[0668] The server sends API requests to other systems it uses. Specifically, it sends requests to the logistics management system that include relevant data such as the user ID, order ID, and detected emotions ("worried").

[0669] Step 6:

[0670] Other systems (for example, a logistics management system) process the received request, search their internal database, and generate a response. For example, they might send back information to the server such as, "Product XYZ has now left the distribution center and is scheduled to arrive on time."

[0671] Step 7:

[0672] The server receives responses from other systems and, if necessary, collects additional information from other systems (e.g., customer management systems). For example, it may also collect user purchase history and current delivery status.

[0673] Step 8:

[0674] The server integrates the collected information to generate a final response. For example, it might combine messages such as, "Product XYZ has now left the distribution center and is expected to arrive on schedule," and "We apologize for any inconvenience this may have caused."

[0675] Step 9:

[0676] The server sends the final response back to the user's device. Specifically, it sends the response data to the device as an HTTP response.

[0677] Step 10:

[0678] The device displays the received response on the user interface. For example, it might display a message such as, "Product delivery status: Product XYZ has now left the distribution center and is expected to arrive on schedule. We apologize for any inconvenience this may have caused."

[0679] In this way, the entire system efficiently implements a series of processes, from user inquiry input to server analysis, the introduction of an emotion engine, and appropriate integration with other systems, ultimately providing an emotionally sensitive response.

[0680] (Example 2)

[0681] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0682] Traditional systems extracted only keywords and intent from user inquiries, without considering emotions. This resulted in a failure to address user frustration and impatience, leading to a decline in the quality of customer support. Furthermore, ineffective requests to appropriate external systems and inefficient integration of responses sometimes resulted in delays in user responses.

[0683] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0684] In this invention, the server includes means for receiving user input, means for analyzing the input to extract keywords, intentions, and emotions, means for sending requests to appropriate other systems based on the analysis results, means for receiving responses from the other systems, means for integrating the received responses and generating a final response adjusted according to the user's emotions, and means for providing the final response to the user. This enables the provision of quick and appropriate responses that take the user's emotions into consideration.

[0685] A "user" is the entity that operates the system and makes inquiries.

[0686] "Input" refers to information that a user sends to the system through their device.

[0687] A "device" refers to a device that a user directly operates, and includes personal computers, smartphones, and other similar devices.

[0688] A "server" is a device that acts as a central processing unit, receiving and analyzing queries and coordinating with other systems.

[0689] "Analysis" is the process of understanding user input using natural language processing and sentiment analysis, and extracting keywords, intentions, and emotions.

[0690] "Natural language processing" is a technique that analyzes text data and interprets its grammar and meaning.

[0691] "Emotion analysis" is a technology that recognizes emotions from user input and reflects them in the analysis results.

[0692] "Keywords" are important words or phrases extracted from user input.

[0693] "Intention" refers to the purpose or request that the user is trying to achieve through their inquiry.

[0694] "Emotions" refer to psychological states recognized from user input, such as anxiety or dissatisfaction.

[0695] "Other systems" refers to external systems that the server uses to retrieve information, including, for example, logistics management systems and customer management systems.

[0696] A "request" is a request that a server sends to another system to obtain information.

[0697] "Responses" refer to information returned from other systems, which the server uses to provide to the user.

[0698] "Integration" is the process of combining multiple pieces of information into a single, coherent format.

[0699] The "final answer" is the response that the server generates based on the integrated information and provides to the user.

[0700] "Providing" refers to the act of sending the final response generated by the server to the user's terminal, thereby indicating a response to the user.

[0701] This invention is a system that adds a function to recognize user emotions and adjust responses accordingly. The system operates efficiently through cooperation with servers, terminals, and other systems, enabling responses that are responsive to user emotions, thereby improving the quality of customer support. The following describes specific embodiments of this system.

[0702] System Configuration

[0703] The system consists of the following main components:

[0704] Terminal: A device that the user directly operates (e.g., a personal computer, a smartphone).

[0705] Server: A central processing unit that receives and analyzes inquiries and generates responses in cooperation with other systems.

[0706] Other systems: These are external systems (such as databases or dedicated APIs) that the server uses to retrieve information in response to queries.

[0707] Emotion Engine: This is a dedicated function that recognizes emotions from user input and reflects them in the analysis results.

[0708] Program Processing Overview

[0709] When a user submits a query through their device, the content is received by the server. The server uses natural language processing (NLP) and an emotion engine to analyze the received data, extracting keywords, intent, and even the user's emotions. Based on the analysis, the server then identifies the most suitable other system and sends a request, taking emotions into consideration. When responses from other systems return to the server, the server integrates them, generates a final response adjusted according to the user's emotions, and provides it to the user via their device.

[0710] Hardware and software to be used

[0711] The following specific hardware and software will be used for the server and terminal:

[0712] Python is a programming language used for natural language processing and sentiment analysis.

[0713] NLTK library: A Python library for natural language processing.

[0714] Google Cloud Natural Language API: A cloud-based API for sentiment analysis.

[0715] RabbitMQ: Used for managing message queues within the server.

[0716] HTTP Request: A communication protocol used by servers to interact with other systems.

[0717] REST API and JSON: These are formats and protocols used for data exchange between servers and other systems.

[0718] Specific example

[0719] Step 1: User input

[0720] The user enters "I want to know the delivery status of my product" into the inquiry form on their device and presses the submit button.

[0721] The terminal internally constructs and sends an HTTP POST request to the server to send the contents of this inquiry.

[0722] Step 2: Server receives and analyzes data.

[0723] The server stores the query content received from the terminal in a message queue such as RabbitMQ.

[0724] The server executes a Python script and uses the NLTK library to extract the keyword "delivery status" and the intent "I want to know the delivery status of the items ordered by user A."

[0725] The server calls the Google Cloud Natural Language API to detect that the user is feeling anxious.

[0726] Step 3: Integration with other systems

[0727] The server uses an HTTP client (for example, Python's requests library) to send a request to the logistics management system to inquire about the "delivery status".

[0728] The server also adds additional information to the request header, such as "the user is feeling anxious."

[0729] Step 4: Collecting and integrating responses

[0730] The system processes the request received by another system (the logistics management system), searches its internal database, and generates information. It then sends back the information to the server stating, "Product XYZ has now left the distribution center and is scheduled to arrive on time."

[0731] The server collects necessary information from other related systems (e.g., customer management systems) and integrates all the data.

[0732] Step 5: Providing responses to users

[0733] Based on the information collected by the server, a final response is generated that is tailored to the user's emotions. For example, a response that reassures the user might be something like, "We apologize for any concern this may have caused. Product XYZ has now left the distribution center and is expected to arrive on schedule."

[0734] The device receives the HTTP response and displays the final answer in the user interface (e.g., a text area on a web page).

[0735] Example of a prompt

[0736] Analyze the following inquiry and generate the appropriate answer:

[0737] Inquiry: "I would like to know the delivery status of my order."

[0738] User emotion: "Anxiety"

[0739] Please obtain the necessary information from relevant systems and provide an emotionally sensitive response.

[0740] In this way, the responses provided, from user inquiry input to server analysis, the introduction of an emotion engine, and appropriate integration with other systems, are efficiently delivered in a manner that takes the user's emotions into consideration.

[0741] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0742] Step 1: User inquiry input

[0743] Input: Text entered by the user in the inquiry form (e.g., "I would like to know the delivery status of my order").

[0744] Output: Data sent to the server from the contents of the inquiry form.

[0745] Specific operation: The user enters "I want to know the delivery status of my product" into the inquiry form on the device and presses the submit button. The device constructs and sends an HTTP POST request to send this inquiry to the server. The request includes necessary metadata such as the user ID, inquiry content, and timestamp.

[0746] Step 2: Server receives and analyzes data.

[0747] Input: Inquiry content sent from the terminal (HTTP POST request)

[0748] Output: Keywords, intentions, and emotions as analysis results (Example: Keyword "Delivery status", Intention "I want to know the delivery status of the product", Emotion "Anxiety")

[0749] Specific operation: The server stores the content of the inquiry received from the terminal in a message queue such as RabbitMQ. The server then executes a Python script to parse the inquiry. First, it uses the NLTK library to extract the keyword "delivery status" and the intention "I want to know the delivery status of the product" from the text. Next, it calls the Google Cloud Natural Language API to detect the user's emotion (e.g., "anxiety").

[0750] Step 3: Integration with other systems

[0751] Input: Analysis results (Keyword "Delivery status", Intent "I want to know the delivery status of the product", Emotion "Anxiety")

[0752] Output: Requests to other systems (e.g., HTTP requests to a logistics management system)

[0753] Specific operation: Based on the analysis results, the server forwards the analysis data to the most suitable other system. Using the Python requests library, a request is sent to the logistics management system to inquire about the "delivery status". This request includes information such as the user ID, the content of the inquiry, and the analyzed emotion (e.g., "anxiety").

[0754] Step 4: Collecting and integrating responses

[0755] Input: Response from another system (Example: "Product XYZ has now left the distribution center and is scheduled to arrive on time.")

[0756] Output: Integrated response data (Example: "Product XYZ has now left the distribution center and is expected to arrive on schedule. We apologize for any inconvenience this may have caused.")

[0757] Specific operation: The logistics management system processes the received request and retrieves the necessary information by referring to its internal database. For example, it might return information in JSON format such as, "Product XYZ has now left the distribution center and is scheduled to arrive on time." The server verifies the received information and, if additional information is needed, gathers information from other systems (e.g., customer management system). The server integrates all the collected information and generates a final response that takes the user's feelings into consideration.

[0758] Step 5: Providing responses to users

[0759] Input: Integrated final response (Example: "Item XYZ has now left the distribution center and is expected to arrive on schedule. We apologize for any inconvenience this may have caused.")

[0760] Output: Response message provided to the user

[0761] Specific operation: The server sends the final response it generates to the terminal as an HTTP response. The terminal receives this and displays it in the user interface. The displayed message includes product information as well as language that takes the user's feelings into consideration (e.g., "We apologize for any inconvenience this may have caused"). This allows the user to receive a quick, accurate, and emotionally considerate response to their inquiry.

[0762] (Application Example 2)

[0763] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0764] Traditional content delivery services often provided uniform recommended content without considering users' emotional states, resulting in insufficient user satisfaction. Furthermore, accurately understanding user needs was difficult, leading to a decline in content quality and relevance. Therefore, personalized content delivery tailored to user emotions is in demand.

[0765] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0766] In this invention, the server includes means for receiving user input, means for analyzing the input to extract emotions, keywords, and intentions, means for sending requests to appropriate other systems based on the analysis results, means for receiving responses from the other systems, means for integrating the received responses and generating a final response adjusted based on emotions, and means for providing the final response to the user. This enables the recommendation of appropriate content according to the user's emotional state.

[0767] "Means for receiving user input" refers to devices or functions that receive operations or inquiries made by users to the system.

[0768] "Means for analyzing input to extract emotions, keywords, and intentions" refers to devices or functions that process input data received from a user to identify emotions, important words, and the purposes or requests that those words represent.

[0769] "Means for sending requests to appropriate other systems" refers to devices or functions that send requests to external systems selected based on the analysis results to obtain the necessary information.

[0770] "Means for receiving responses from other systems" refers to devices or functions for receiving responses from external systems that have sent requests.

[0771] "Means for integrating received responses and generating a final response adjusted based on emotions" refers to devices or functions that integrate information obtained from external systems and generate a final response optimized according to the user's emotional state.

[0772] "Means of providing the final answer to the user" refers to devices or functions that present the user with an answer generated based on analysis results and information from external systems.

[0773] "Natural language processing" is a technology that analyzes natural language input from users and understands its meaning and intent.

[0774] "Emotion recognition" is a technology that detects and classifies a user's emotional state based on input data, facial expressions, voice, and other factors.

[0775] "Means of selecting the optimal system from multiple other systems" refers to a device or function that selects the most appropriate system from several external systems and sends a request to that system.

[0776] This invention is a system that recognizes user emotions and adjusts responses accordingly, operating efficiently through collaboration with servers, terminals, and other systems. This system consists of the following main components:

[0777] System Configuration

[0778] Terminal: A device that the user directly operates (for example, a smartphone).

[0779] Server: A central processing unit that receives and analyzes inquiries and generates responses in cooperation with other systems.

[0780] Other systems: External systems that the server uses to retrieve information in response to queries (e.g., content databases or dedicated APIs).

[0781] Emotion Engine: A dedicated function that recognizes emotions from user input and facial expressions and reflects them in the analysis results.

[0782] Specific implementation methods

[0783] 1. User inquiry input

[0784] Users access content distribution service applications using devices such as smartphones to make inquiries and perform actions. For example, a user might type, "I'd like recommendations for relaxing music."

[0785] 2. Server-based analysis

[0786] When the server receives user input, it analyzes this input using natural language processing (NLP) and emotion recognition techniques. The analysis extracts the keyword "relaxing music," the intention "I want to relax," and the user's emotional state (e.g., feeling stressed).

[0787] 3. Integration with other systems

[0788] Based on the analysis results, the server sends requests to appropriate other systems (e.g., content databases or recommendation APIs). For example, if a user is experiencing stress, it might request other systems to retrieve a list of music specifically designed for relaxation.

[0789] 4. Collection and Integration of Responses

[0790] Other systems process received requests, search their internal databases, and generate appropriate content. For example, they might send information about a "relaxation music playlist" back to the server.

[0791] 5. Providing responses to users

[0792] The server integrates all the collected information and generates a final response tailored to the user's emotional state. This may include specific suggestions, such as, "To help reduce your stress, we recommend this relaxation music." The terminal displays the response received from the server on its user interface.

[0793] Hardware and software to use

[0794] Hardware: Smartphone with camera

[0795] Software: OpenCV, TensorFlow, Sentiment Recognition API, Content Recommendation API

[0796] Data processing and data calculation

[0797] The server receives input data from the user and performs semantic analysis using NLP technology. Next, the emotion engine recognizes the user's emotional state and sends a request to the most appropriate system based on the analysis results. Information obtained from the content recommendation API is integrated to generate a final response optimized according to the user's emotions.

[0798] Specific example

[0799] If you are feeling stressed: Relaxation music playlists and yoga videos are recommended.

[0800] If you are feeling joyful: Entertainment videos and adventure games are recommended.

[0801] If you are feeling sad: Encouraging messages or heartwarming documentary films are recommended.

[0802] Example of a prompt

[0803] Create an application that estimates a user's emotions from their facial expressions and recommends appropriate content based on that. Recommend different content for each of the following seven emotion categories: anger, disgust, fear, joy, sadness, surprise, and neutral.

[0804] In this way, a system is built that enables personalized content delivery that responds to the user's emotions.

[0805] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0806] Step 1:

[0807] Users access content distribution service applications using devices such as smartphones and perform inquiries and operations.

[0808] Input: User request (e.g., "Please recommend some relaxing music")

[0809] Output: User request data

[0810] Specific example: A user enters "relaxing music" into the search bar within the app and presses the search button.

[0811] Step 2:

[0812] The server receives user input sent from the terminal.

[0813] Input: User's request data

[0814] Output: Request data sent to the server

[0815] Specific example: The server receives text data from a user that says "relaxing music".

[0816] Step 3:

[0817] The server uses natural language processing (NLP) to analyze user input and extract keywords and intent. Simultaneously, it uses an emotion recognition engine to analyze the user's emotional state.

[0818] Input: Request data

[0819] Output: Keywords, intentions, emotional state

[0820] Specific example: The server analyzes the keywords "relax" and "music," the intention to "want to relax," and the emotional state as "stress."

[0821] Step 4:

[0822] Based on the analysis results, the server sends requests to the appropriate other systems (e.g., content databases or recommendation service APIs).

[0823] Input: Analysis results (keywords, intentions, emotional state)

[0824] Output: Request to other systems

[0825] Specific example: A server generates data requesting relaxation music recommendations for users experiencing stress and sends it to another system.

[0826] Step 5:

[0827] Other systems process the received request, search their internal database to select the appropriate content, and send the response to the server.

[0828] Input: Request to another system

[0829] Output: Recommended content data

[0830] Specific example: Information about a "relaxation music playlist" is sent back to the server from another system.

[0831] Step 6:

[0832] The server integrates the collected response data and generates a final response optimized based on the user's emotional state.

[0833] Input: Recommended content data

[0834] Output: Final response data

[0835] Specific example: The server generates a final response that includes a suggestion such as, "To reduce your stress, we recommend this relaxation music."

[0836] Step 7:

[0837] The final response data is sent from the server to the terminal. The terminal receives this data and displays it on the user interface.

[0838] Input: Final response data

[0839] Output: Display on the user interface

[0840] Specific example: A "relaxation music playlist" is displayed on the user's smartphone screen.

[0841] In this way, the specific processing steps from user input to the final proposal are carried out.

[0842] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0843] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0844] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0845] [Third Embodiment]

[0846] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0847] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0848] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0849] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0850] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0851] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0852] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0853] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0854] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0855] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0856] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0857] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0858] This invention is a system for providing quick and accurate answers to user-inputted inquiries, and operates efficiently through cooperation with servers, terminals, and other systems.

[0859] System Configuration

[0860] The system consists of the following main components:

[0861] Terminal: A device that the user directly operates (e.g., a personal computer, a smartphone).

[0862] Server: A central processing unit that receives and analyzes inquiries and generates responses in cooperation with other systems.

[0863] Other systems: External systems (e.g., databases or dedicated APIs) that the server uses to retrieve information in response to queries.

[0864] Program Processing Overview

[0865] When a user submits a query through their device, the content is received by the server. The server analyzes the received data using natural language processing to extract appropriate keywords and intent. Based on the analysis results, the server then identifies the most suitable other system and sends a request. When the response from the other system is returned to the server, the server integrates it to generate a single, continuous response, which is finally provided to the user via the device.

[0866] Specific example

[0867] Step 1: User input

[0868] The terminal sends the information to the server when the user enters "I want to know the delivery status of my product" into the inquiry form and presses the submit button.

[0869] For example, user A wants to know the delivery status of an item they ordered from an online shopping site, and enters a question.

[0870] Step 2: Server-based analysis

[0871] When the server receives a user inquiry, it uses natural language processing to analyze the inquiry. The analysis extracts the keyword "delivery status" and the user's intention, "I want to know the delivery status of the product ordered by user A."

[0872] Step 3: Integration with other systems

[0873] The server selects the most suitable other system from which to obtain "delivery status" information and sends the request. In this case, it determines that a database containing delivery information exists and sends the request to that database.

[0874] For example, you can query the logistics management system for the delivery status of "Order ID: 12345".

[0875] Step 4: Collecting and integrating responses

[0876] Other systems (for example, a logistics management system) search for the delivery status of the corresponding order ID and send back information to the server stating, "Product XYZ has now left the distribution center and is scheduled to arrive on time."

[0877] The server verifies the received information and, if necessary, collects additional information from other systems (e.g., customer management systems).

[0878] Step 5: Providing responses to users

[0879] The server integrates all the collected information and generates a final response. It creates a unified response such as "Product XYZ has now left the distribution center and is scheduled to arrive on time," and provides it to the user via the terminal.

[0880] The terminal displays the response received from the server on the user interface. User A can obtain a quick and accurate answer to the inquiry they entered.

[0881] In this way, the entire system efficiently implements a series of processes, from user inquiry input to server analysis and appropriate integration with other systems, ultimately providing a final answer.

[0882] The following describes the processing flow.

[0883] Step 1:

[0884] The device sends the information to the server when the user enters "I want to know the delivery status of my product" into the inquiry form and presses the submit button. Specifically, when the form submission event occurs, the entered text data is sent to the server as an HTTP request.

[0885] Step 2:

[0886] The server receives user inquiries and analyzes their content. Specifically, it extracts text data from the body of the HTTP request and uses a natural language processing (NLP) library to extract keywords and intent from the text data.

[0887] Step 3:

[0888] The server identifies the keyword "delivery status" and the user's intention, "I want to know the delivery status of the product ordered by user A." Based on the analysis results, it selects an appropriate other system (e.g., a logistics management system).

[0889] Step 4:

[0890] The server sends API requests to other systems it uses. Specifically, it sends requests containing relevant data such as user IDs and order IDs to the logistics management system.

[0891] Step 5:

[0892] Other systems (for example, a logistics management system) process the received request, search their internal database, and generate a response. For example, they might send back information to the server such as, "Product XYZ has now left the distribution center and is scheduled to arrive on time."

[0893] Step 6:

[0894] The server receives responses from other systems. If necessary, it also collects relevant information from other systems, such as customer management systems.

[0895] Step 7:

[0896] The server integrates the collected information to generate a final response. For example, it might create a unified response such as, "Product XYZ has now left the distribution center and is scheduled to arrive on time."

[0897] Step 8:

[0898] The server sends the final response back to the user's device. Specifically, it sends the response data to the device as an HTTP response.

[0899] Step 9:

[0900] The terminal displays the received response on the user interface. For example, it might display a message on the screen such as, "Product delivery status: Product XYZ has now left the distribution center and is expected to arrive on schedule."

[0901] In this way, a process is realized that efficiently responds to user inquiries by having each step play a clear role.

[0902] (Example 1)

[0903] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0904] In today's world, systems that enable users to obtain information quickly and accurately are crucial, but conventional systems often take a long time to analyze inquiries and provide answers. Furthermore, improving efficiency and accuracy when integrating with multiple systems remains a challenge. This invention aims to solve the problem of providing quick and accurate answers to user inquiries and offering a method for efficiently integrating with other systems.

[0905] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0906] In this invention, the server includes means for receiving user input, means for analyzing the input to extract keywords and intent, means for sending a request to an appropriate other system based on the analysis results, means for receiving responses from the other system, means for integrating the received responses to generate a final response, means for providing the final response to the user, means for sending a request based on the user input and sending voice or email, and means for recording and analyzing the user's information. This enables the provision of quick and accurate responses to user inquiries and efficient cooperation with other systems.

[0907] "Means for receiving user input" refers to the means by which data is sent to a server when a user enters an inquiry or request via a terminal.

[0908] "Means for analyzing input and extracting keywords and intent" refers to methods for analyzing input data received from users using natural language processing technology to identify necessary keywords and the user's intent.

[0909] "Means for sending requests to appropriate other systems based on analysis results" refers to means for identifying the most suitable other system based on the analyzed data and sending necessary information requests to that system.

[0910] "Means for receiving responses from other systems" refers to means for receiving information or data sent back from other systems.

[0911] "Means for integrating received responses to generate a final response" refers to a means of integrating information received from multiple other systems and generating a single, continuous response to provide to the user.

[0912] "Means of providing the final answer to the user" refers to means of sending the generated final answer to the user's device and displaying it on the user interface.

[0913] "A means of sending requests based on user input and sending voice or email notifications" refers to a means of sending requests to an external system based on the content of a user's inquiry and providing notifications via voice or email as needed.

[0914] "Means for recording and analyzing user information" refers to methods for recording user inquiry history and behavioral logs, and analyzing the data for subsequent analysis and improvement.

[0915] This invention is a system for providing quick and accurate answers to user-inputted inquiries, and it operates efficiently through cooperation with servers, terminals, and other systems.

[0916] System Configuration

[0917] The system consists of the following main components:

[0918] Terminal: A device that the user directly operates (e.g., a personal computer, a smartphone).

[0919] Server: A central processing unit that receives and analyzes inquiries and generates responses in cooperation with other systems.

[0920] Other systems: External systems that the server uses to retrieve information in response to queries (e.g., databases and application programming interfaces (APIs)).

[0921] Program Processing Overview

[0922] The user operates their device and enters their question into the inquiry form. For example, using a personal computer or smartphone, they might enter "I want to know the delivery status of product with order ID 12345" and press the submit button. This causes the device to send the inquiry to the server as an HTTP POST request.

[0923] The server processes HTTP POST requests received from the terminal using web frameworks such as Python's Flask or Node.js's Express. The received data is parsed by a natural language processing (NLP) engine (e.g., Amazon Comprehend or Dialogflow) to extract keywords and intent. For example, the keyword "delivery status" and the intent "I want to know the delivery status of the product with order ID 12345" might be extracted.

[0924] Based on the analysis results, the server sends information requests to the most appropriate other systems. For example, it sends an HTTP GET request to the API endpoint of the logistics management system to retrieve delivery information for "Order ID 12345". This request includes the order ID specified by the user.

[0925] The logistics management system searches the database for delivery information corresponding to the specified order ID and sends back information to the server, such as "Product XYZ has now left the distribution center and is scheduled to arrive on time."

[0926] The server integrates data received from other systems and generates a final response. If necessary, it may also collect additional information from other systems, such as customer management systems. The integrated information is then sent to the user's terminal, which displays it on its user interface. This allows the user to obtain a quick and accurate response.

[0927] Specific example

[0928] User inquiry input

[0929] A user enters an inquiry on an online shopping site, stating, "I want to know the delivery status of my order," and presses the submit button. For example, they might enter, "Please tell me the delivery status of the item with order ID 12345."

[0930] Server-based analysis

[0931] The server analyzes the received input data using natural language processing to extract the keywords and intent behind "delivery status" and "order ID 12345".

[0932] Integration with other systems

[0933] The server calls the logistics management system's API to request delivery information for a specified order ID. For example, it might query the delivery status of order ID 12345.

[0934] Collection and integration of responses

[0935] The logistics management system searches for delivery information for "Order ID 12345" and returns the information "Product XYZ has now left the distribution center and is scheduled to arrive on time."

[0936] Providing answers to users

[0937] The server generates the final response and sends it to the terminal. The terminal displays the response, "Product XYZ has now left the distribution center and is scheduled to arrive on time," on the user interface.

[0938] Example of a prompt

[0939] "Please tell me the current delivery status of the item with order ID 12345."

[0940] This system enables a series of processes for providing quick and accurate answers to user inquiries.

[0941] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0942] Step 1:

[0943] The user operates the terminal and enters a question into the inquiry form. For example, they might enter "I want to know the delivery status of product with order ID 12345" into the form and press the submit button. This action sends the inquiry to the server as an HTTP POST request. The input is the user's inquiry, and the output is the HTTP POST request to the server.

[0944] Step 2:

[0945] The server processes the HTTP POST request received from the terminal. The server parses the request body using a web framework such as Flask or Express. This request body is the input, and the result of the parsing is the output. Specifically, the server uses a natural language processing (NLP) engine to parse the user's input and extract the keyword "delivery status" and the intent "I want to know the delivery status of the product with order ID 12345."

[0946] Step 3:

[0947] Based on the analysis results, the server sends a request to the appropriate other system. In this case, the server generates an HTTP GET request to the logistics management system's API endpoint. The input is the analysis result "Delivery Status" and "Order ID 12345," and the output is an HTTP GET request to the logistics management system. Specifically, the server finds the API endpoint and includes the necessary parameters in the request.

[0948] Step 4:

[0949] The other system (the logistics management system) processes the HTTP GET request received from the server. The logistics management system searches the database and retrieves the corresponding order ID information. The input is the HTTP GET request from the server, and the output is information about the delivery status (e.g., "Product XYZ has now left the distribution center and is expected to arrive on schedule"). This information is sent back to the server as an HTTP response.

[0950] Step 5:

[0951] The server verifies the information received from the logistics management system and collects additional information from other systems as needed. For example, it may collect verification information from the customer management system. The input is delivery status information from the logistics management system, and based on this, additional requests are generated to obtain other necessary data. The output is the final integrated information. Specifically, the server issues additional API requests and integrates all the information after collecting the additional information.

[0952] Step 6:

[0953] The server generates a final response based on the integrated information. For example, it might generate a response such as, "Product XYZ has now left the distribution center and is scheduled to arrive on time." This generated response is the input, and the output is the HTTP response sent to the terminal. Specifically, the server sends the generated response to the terminal as a JSON response.

[0954] Step 7:

[0955] The terminal displays the final response received from the server on the user interface. The user can confirm information such as, "Product XYZ has now left the distribution center and is scheduled to arrive on time." The input is the final response from the server, and the output is the information displayed on the user interface. Specifically, the terminal analyzes the received data and displays it in a user-friendly format.

[0956] This process ensures that users receive quick and accurate responses to their inquiries.

[0957] (Application Example 1)

[0958] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0959] Users of autonomous vehicles always want to know the vehicle's current location, battery status, and route status quickly and accurately. However, conventional systems often take a long time to acquire this information, which has led to decreased user satisfaction. This invention aims to solve this problem by providing a system that can provide information quickly and accurately.

[0960] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0961] In this invention, the server includes means for sending inquiries from a user terminal to the server and identifying appropriate other systems from the analysis results using a natural language processing model, and means for performing analysis again using the information of the other systems and integrating appropriate autonomous vehicle information to present to the user. This makes it possible for users to quickly and accurately obtain the information they want to know about autonomous vehicles.

[0962] A "user terminal" refers to a device operated by a user, and includes mobile devices such as smartphones and tablets.

[0963] A "server" is a central processing system that receives inquiries from user terminals, performs analysis, and coordinates with other systems.

[0964] A "natural language processing model" is an algorithm or system that analyzes user input and extracts appropriate keywords and intents.

[0965] "Other systems" refer to external information provision systems with which the server collaborates to retrieve information in response to inquiries.

[0966] "Analysis results" refer to keywords and intentions extracted by the natural language processing model.

[0967] A "request" is a request to retrieve information that is sent to another system based on the analysis results.

[0968] "Response" refers to information sent back to the server from another system.

[0969] "Integration" refers to the process by which a server combines multiple responses it has received into a single, continuous piece of information.

[0970] A "final answer" is a complete answer generated to provide the user with integrated information.

[0971] A "generative AI model" is a module that uses artificial intelligence to generate appropriate prompt sentences in response to user inquiries.

[0972] A "prompt" refers to a query or instruction in natural language output by a generative AI model.

[0973] This invention is a system that coordinates user terminals, servers, and other systems to respond quickly and accurately to user requests for information retrieval.

[0974] System Configuration

[0975] The system consists of the following main components:

[0976] 1. User terminal:

[0977] This refers to a device operated by the user, including smartphones and tablets. Users use this device to send inquiries.

[0978] 2. Server:

[0979] A central processing system that receives inquiries and performs analysis using natural language processing models. Based on the analysis results, the server sends requests to other systems, integrates the responses, and generates a final answer.

[0980] 3. Other systems:

[0981] An external information provider system that the server collaborates with to obtain necessary information. This includes location information, battery status, and route information for autonomous vehicles.

[0982] Program processing

[0983] The system works as follows:

[0984] 1. Receiving an inquiry:

[0985] The user sends a request through an application on their device. For example, they might type, "Tell me my current location."

[0986] 2. Data Analysis:

[0987] The server analyzes the received query using a natural language processing model to extract keywords and intent. Based on the analysis results, it sends a request to the appropriate other system.

[0988] 3. Information acquisition:

[0989] The server retrieves necessary information from other systems, such as the location and battery status of autonomous vehicles.

[0990] 4. Information Integration:

[0991] The server integrates the acquired information and generates a final response to provide to the user.

[0992] 5. Providing an answer:

[0993] The integrated final response is sent to the user's terminal and displayed on the user interface.

[0994] Hardware and software to be used

[0995] The main hardware and software used are as follows:

[0996] Hardware: Smartphones, tablets, servers

[0997] Software: transformers library, requests library

[0998] Natural Language Processing Models: Generative AI Models

[0999] Specific example

[1000] If a user wants to know the current location of an autonomous vehicle, it works as follows:

[1001] 1. The user enters "Tell me my current location" into the app's contact form.

[1002] 2. The server receives the query and uses a natural language processing model to analyze the keyword "current location" and the intent "tell me".

[1003] 3. The server sends a request to the appropriate other system (for example, a vehicle location information system).

[1004] 4. The server receives information from other systems, such as "The vehicle's current location is XX," and integrates it.

[1005] 5. The server generates integrated information and displays "The vehicle's current location is XX" on the user's terminal.

[1006] Example of a prompt

[1007] The following are examples of prompts to input into a specific generative AI model:

[1008] User inquiry: "What is the current battery status of the autonomous vehicle?"

[1009] Context: "The autonomous vehicle's battery is now fully charged and ready to depart."

[1010] This allows users to obtain information quickly and accurately, leading to increased satisfaction.

[1011] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1012] Step 1:

[1013] User Inquiry Submission

[1014] The user enters their question into the inquiry form using their own device (smartphone or tablet) and presses the "Send" button. For example, they might enter "Tell me your current location." This input is sent from the device to the server.

[1015] Input: User's question (e.g., "Tell me your current location")

[1016] Output: Server query data

[1017] Step 2:

[1018] Server receives and analyzes queries.

[1019] The server receives the query sent from the terminal. The received data is parsed using a natural language processing model (e.g., the transformers library). Through this parsing, the query's keywords ("current location") and intent ("tell me") are extracted.

[1020] Input: User inquiry data

[1021] Output: Extracted keywords and intent

[1022] Step 3:

[1023] Identifying and sending requests to appropriate other systems

[1024] Based on the analysis results, the server identifies appropriate other systems to obtain the necessary information. For example, a vehicle location information system might be selected. The server sends a request to this system to query for the required information (e.g., the vehicle's current location).

[1025] Input: Extracted keywords and intent

[1026] Output: Request to the appropriate other system

[1027] Step 4:

[1028] Acquiring information from other systems

[1029] Other systems provide the necessary information in response to requests from the server. For example, a vehicle location information system returns the response, "The vehicle's current location is XX." The server receives this response.

[1030] Input: Request from server

[1031] Output: Information from other systems (e.g., the vehicle's current location)

[1032] Step 5:

[1033] Information integration and final answer generation

[1034] The server integrates information obtained from other systems and generates a final answer to provide to the user. This includes generating prompts using a generative AI model. For example, it might generate an answer such as, "The vehicle's current location is XX."

[1035] Input: Information from other systems

[1036] Output: Integrated final answer

[1037] Step 6:

[1038] Providing answers to users

[1039] The server sends the final generated response to the user's terminal. The user's terminal displays this response on its user interface, allowing the user to verify the answer to their inquiry.

[1040] Input: Integrated final answer

[1041] Output: The response displayed on the user's terminal (e.g., "The vehicle's current location is XX")

[1042] This allows users to quickly and accurately obtain information about autonomous vehicles.

[1043] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1044] This invention is a system that adds a function to recognize user emotions and adjust responses accordingly, and operates efficiently through cooperation with servers, terminals, and other systems. This enables responses that are tailored to the user's emotions, thereby improving the quality of customer support.

[1045] System Configuration

[1046] The system consists of the following main components:

[1047] Terminal: A device that the user directly operates (e.g., a personal computer, a smartphone).

[1048] Server: A central processing unit that receives and analyzes inquiries and generates responses in cooperation with other systems.

[1049] Other systems: External systems (e.g., databases or dedicated APIs) that the server uses to retrieve information in response to queries.

[1050] Emotion Engine: A dedicated function that recognizes emotions from user input and reflects them in the analysis results.

[1051] Program Processing Overview

[1052] The user makes a query through their device, and the content is received by the server. The server analyzes the received data using natural language processing (NLP) and an emotion engine, extracting keywords, intent, and even the user's emotions. The server then identifies the most suitable other system based on the analysis results and sends a request, taking emotions into consideration. When the responses from the other systems are returned to the server, the server integrates them, generates a final response adjusted according to the user's emotions, and provides it to the user via their device.

[1053] Specific example

[1054] Step 1: User input

[1055] The terminal sends the information to the server when the user enters "I want to know the delivery status of my product" into the inquiry form and presses the submit button.

[1056] For example, user A wants to know the delivery status of an item they ordered from an online shopping site, and enters a question.

[1057] Step 2: Server-based analysis

[1058] When the server receives a user inquiry, it analyzes the inquiry using natural language processing and an emotion engine. The analysis extracts the keyword "delivery status," the user's intention ("I want to know the delivery status of the product ordered by user A"), and the user's emotions (e.g., impatience or dissatisfaction).

[1059] Step 3: Integration with other systems

[1060] The server selects the most suitable other system (e.g., a logistics management system) from which to obtain "delivery status" information and sends a request that takes emotions into consideration. For example, if an emotion indicating a need for a faster response is detected, the server will also send a request that includes this information.

[1061] Step 4: Collecting and integrating responses

[1062] Other systems (for example, a logistics management system) process the received request, search their internal database, and generate a response. For example, they might send back information to the server such as, "Product XYZ has now left the distribution center and is scheduled to arrive on time."

[1063] The server verifies the received information and, if necessary, collects additional information from other systems (e.g., customer management systems).

[1064] Step 5: Providing responses to users

[1065] The server integrates all the collected information and generates a final response tailored to the user's feelings. For example, if the user is dissatisfied, it will respond politely with something like, "We apologize for any inconvenience this may have caused. Product XYZ has now left the distribution center and is expected to arrive on schedule."

[1066] The terminal displays the response received from the server on the user interface. User A can receive a quick, accurate, and emotionally sensitive response to their inquiry.

[1067] In this way, the entire system efficiently implements a series of processes, from user inquiry input to server analysis, the introduction of an emotion engine, and appropriate integration with other systems, ultimately providing an emotionally sensitive response.

[1068] The following describes the processing flow.

[1069] Step 1:

[1070] When a user enters "I want to know the delivery status of my product" into the inquiry form and presses the submit button, the device sends that information to the server. Specifically, when the form submission event occurs, the entered text data is sent to the server as an HTTP request.

[1071] Step 2:

[1072] The server receives user inquiries and analyzes their content. Specifically, it extracts text data from the body of the HTTP request and uses a natural language processing (NLP) library to extract keywords and intent from the text data.

[1073] Step 3:

[1074] The server passes the user's input text to the sentiment engine, which then recognizes the user's emotions. For example, if the text is "I'm very worried. When will the product arrive?", the sentiment engine detects the user's emotion as "worried".

[1075] Step 4:

[1076] Based on the keyword "delivery status," the user's intention to "know the delivery status of the product ordered by user A," and the emotion of "concern," the server identifies the most suitable other system (for example, a logistics management system).

[1077] Step 5:

[1078] The server sends API requests to other systems it uses. Specifically, it sends requests to the logistics management system that include relevant data such as the user ID, order ID, and detected emotions ("worried").

[1079] Step 6:

[1080] Other systems (for example, a logistics management system) process the received request, search their internal database, and generate a response. For example, they might send back information to the server such as, "Product XYZ has now left the distribution center and is scheduled to arrive on time."

[1081] Step 7:

[1082] The server receives responses from other systems and, if necessary, collects additional information from other systems (e.g., customer management systems). For example, it may also collect user purchase history and current delivery status.

[1083] Step 8:

[1084] The server integrates the collected information to generate a final response. For example, it might combine messages such as, "Product XYZ has now left the distribution center and is expected to arrive on schedule," and "We apologize for any inconvenience this may have caused."

[1085] Step 9:

[1086] The server sends the final response back to the user's device. Specifically, it sends the response data to the device as an HTTP response.

[1087] Step 10:

[1088] The device displays the received response on the user interface. For example, it might display a message such as, "Product delivery status: Product XYZ has now left the distribution center and is expected to arrive on schedule. We apologize for any inconvenience this may have caused."

[1089] In this way, the entire system efficiently implements a series of processes, from user inquiry input to server analysis, the introduction of an emotion engine, and appropriate integration with other systems, ultimately providing an emotionally sensitive response.

[1090] (Example 2)

[1091] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1092] Traditional systems extracted only keywords and intent from user inquiries, without considering emotions. This resulted in a failure to address user frustration and impatience, leading to a decline in the quality of customer support. Furthermore, ineffective requests to appropriate external systems and inefficient integration of responses sometimes resulted in delays in user responses.

[1093] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1094] In this invention, the server includes means for receiving user input, means for analyzing the input to extract keywords, intentions, and emotions, means for sending requests to appropriate other systems based on the analysis results, means for receiving responses from the other systems, means for integrating the received responses and generating a final response adjusted according to the user's emotions, and means for providing the final response to the user. This enables the provision of quick and appropriate responses that take the user's emotions into consideration.

[1095] A "user" is the entity that operates the system and makes inquiries.

[1096] "Input" refers to information that a user sends to the system through their device.

[1097] A "device" refers to a device that a user directly operates, and includes personal computers, smartphones, and other similar devices.

[1098] A "server" is a device that acts as a central processing unit, receiving and analyzing queries and coordinating with other systems.

[1099] "Analysis" is the process of understanding user input using natural language processing and sentiment analysis, and extracting keywords, intentions, and emotions.

[1100] "Natural language processing" is a technique that analyzes text data and interprets its grammar and meaning.

[1101] "Emotion analysis" is a technology that recognizes emotions from user input and reflects them in the analysis results.

[1102] "Keywords" are important words or phrases extracted from user input.

[1103] "Intention" refers to the purpose or request that the user is trying to achieve through their inquiry.

[1104] "Emotions" refer to psychological states recognized from user input, such as anxiety or dissatisfaction.

[1105] "Other systems" refers to external systems that the server uses to retrieve information, including, for example, logistics management systems and customer management systems.

[1106] A "request" is a request that a server sends to another system to obtain information.

[1107] "Responses" refer to information returned from other systems, which the server uses to provide to the user.

[1108] "Integration" is the process of combining multiple pieces of information into a single, coherent format.

[1109] The "final answer" is the response that the server generates based on the integrated information and provides to the user.

[1110] "Providing" refers to the act of sending the final response generated by the server to the user's terminal, thereby indicating a response to the user.

[1111] This invention is a system that adds a function to recognize user emotions and adjust responses accordingly. The system operates efficiently through cooperation with servers, terminals, and other systems, enabling responses that are responsive to user emotions, thereby improving the quality of customer support. The following describes specific embodiments of this system.

[1112] System Configuration

[1113] The system consists of the following main components:

[1114] Terminal: A device that the user directly operates (e.g., a personal computer, a smartphone).

[1115] Server: A central processing unit that receives and analyzes inquiries and generates responses in cooperation with other systems.

[1116] Other systems: These are external systems (such as databases or dedicated APIs) that the server uses to retrieve information in response to queries.

[1117] Emotion Engine: This is a dedicated function that recognizes emotions from user input and reflects them in the analysis results.

[1118] Program Processing Overview

[1119] When a user submits a query through their device, the content is received by the server. The server uses natural language processing (NLP) and an emotion engine to analyze the received data, extracting keywords, intent, and even the user's emotions. Based on the analysis, the server then identifies the most suitable other system and sends a request, taking emotions into consideration. When responses from other systems return to the server, the server integrates them, generates a final response adjusted according to the user's emotions, and provides it to the user via their device.

[1120] Hardware and software to be used

[1121] The following specific hardware and software will be used for the server and terminal:

[1122] Python is a programming language used for natural language processing and sentiment analysis.

[1123] NLTK library: A Python library for natural language processing.

[1124] Google Cloud Natural Language API: A cloud-based API for sentiment analysis.

[1125] RabbitMQ: Used for managing message queues within the server.

[1126] HTTP Request: A communication protocol used by servers to interact with other systems.

[1127] REST API and JSON: These are formats and protocols used for data exchange between servers and other systems.

[1128] Specific example

[1129] Step 1: User input

[1130] The user enters "I want to know the delivery status of my product" into the inquiry form on their device and presses the submit button.

[1131] The terminal internally constructs and sends an HTTP POST request to the server to send the contents of this inquiry.

[1132] Step 2: Server receives and analyzes data.

[1133] The server stores the query content received from the terminal in a message queue such as RabbitMQ.

[1134] The server executes a Python script and uses the NLTK library to extract the keyword "delivery status" and the intent "I want to know the delivery status of the items ordered by user A."

[1135] The server calls the Google Cloud Natural Language API to detect that the user is feeling anxious.

[1136] Step 3: Integration with other systems

[1137] The server uses an HTTP client (for example, Python's requests library) to send a request to the logistics management system to inquire about the "delivery status".

[1138] The server also adds additional information to the request header, such as "the user is feeling anxious."

[1139] Step 4: Collecting and integrating responses

[1140] The system processes the request received by another system (the logistics management system), searches its internal database, and generates information. It then sends back the information to the server stating, "Product XYZ has now left the distribution center and is scheduled to arrive on time."

[1141] The server collects necessary information from other related systems (e.g., customer management systems) and integrates all the data.

[1142] Step 5: Providing responses to users

[1143] Based on the information collected by the server, a final response is generated that is tailored to the user's emotions. For example, a response that reassures the user might be something like, "We apologize for any concern this may have caused. Product XYZ has now left the distribution center and is expected to arrive on schedule."

[1144] The device receives the HTTP response and displays the final answer in the user interface (e.g., a text area on a web page).

[1145] Example of a prompt

[1146] Analyze the following inquiry and generate the appropriate answer:

[1147] Inquiry: "I would like to know the delivery status of my order."

[1148] User emotion: "Anxiety"

[1149] Please obtain the necessary information from relevant systems and provide an emotionally sensitive response.

[1150] In this way, the responses provided, from user inquiry input to server analysis, the introduction of an emotion engine, and appropriate integration with other systems, are efficiently delivered in a manner that takes the user's emotions into consideration.

[1151] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1152] Step 1: User inquiry input

[1153] Input: Text entered by the user in the inquiry form (e.g., "I would like to know the delivery status of my order").

[1154] Output: Data sent to the server from the contents of the inquiry form.

[1155] Specific operation: The user enters "I want to know the delivery status of my product" into the inquiry form on the device and presses the submit button. The device constructs and sends an HTTP POST request to send this inquiry to the server. The request includes necessary metadata such as the user ID, inquiry content, and timestamp.

[1156] Step 2: Server receives and analyzes data.

[1157] Input: Inquiry content sent from the terminal (HTTP POST request)

[1158] Output: Keywords, intentions, and emotions as analysis results (Example: Keyword "Delivery status", Intention "I want to know the delivery status of the product", Emotion "Anxiety")

[1159] Specific operation: The server stores the content of the inquiry received from the terminal in a message queue such as RabbitMQ. The server then executes a Python script to parse the inquiry. First, it uses the NLTK library to extract the keyword "delivery status" and the intention "I want to know the delivery status of the product" from the text. Next, it calls the Google Cloud Natural Language API to detect the user's emotion (e.g., "anxiety").

[1160] Step 3: Integration with other systems

[1161] Input: Analysis results (Keyword "Delivery status", Intent "I want to know the delivery status of the product", Emotion "Anxiety")

[1162] Output: Requests to other systems (e.g., HTTP requests to a logistics management system)

[1163] Specific operation: Based on the analysis results, the server forwards the analysis data to the most suitable other system. Using the Python requests library, a request is sent to the logistics management system to inquire about the "delivery status". This request includes information such as the user ID, the content of the inquiry, and the analyzed emotion (e.g., "anxiety").

[1164] Step 4: Collecting and integrating responses

[1165] Input: Response from another system (Example: "Product XYZ has now left the distribution center and is scheduled to arrive on time.")

[1166] Output: Integrated response data (Example: "Product XYZ has now left the distribution center and is expected to arrive on schedule. We apologize for any inconvenience this may have caused.")

[1167] Specific operation: The logistics management system processes the received request and retrieves the necessary information by referring to its internal database. For example, it might return information in JSON format such as, "Product XYZ has now left the distribution center and is scheduled to arrive on time." The server verifies the received information and, if additional information is needed, gathers information from other systems (e.g., customer management system). The server integrates all the collected information and generates a final response that takes the user's feelings into consideration.

[1168] Step 5: Providing responses to users

[1169] Input: Integrated final response (Example: "Item XYZ has now left the distribution center and is expected to arrive on schedule. We apologize for any inconvenience this may have caused.")

[1170] Output: Response message provided to the user

[1171] Specific operation: The server sends the final response it generates to the terminal as an HTTP response. The terminal receives this and displays it in the user interface. The displayed message includes product information as well as language that takes the user's feelings into consideration (e.g., "We apologize for any inconvenience this may have caused"). This allows the user to receive a quick, accurate, and emotionally considerate response to their inquiry.

[1172] (Application Example 2)

[1173] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1174] Traditional content delivery services often provided uniform recommended content without considering users' emotional states, resulting in insufficient user satisfaction. Furthermore, accurately understanding user needs was difficult, leading to a decline in content quality and relevance. Therefore, personalized content delivery tailored to user emotions is in demand.

[1175] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1176] In this invention, the server includes means for receiving user input, means for analyzing the input to extract emotions, keywords, and intentions, means for sending requests to appropriate other systems based on the analysis results, means for receiving responses from the other systems, means for integrating the received responses and generating a final response adjusted based on emotions, and means for providing the final response to the user. This enables the recommendation of appropriate content according to the user's emotional state.

[1177] "Means for receiving user input" refers to devices or functions that receive operations or inquiries made by users to the system.

[1178] "Means for analyzing input to extract emotions, keywords, and intentions" refers to devices or functions that process input data received from a user to identify emotions, important words, and the purposes or requests that those words represent.

[1179] "Means for sending requests to appropriate other systems" refers to devices or functions that send requests to external systems selected based on the analysis results to obtain the necessary information.

[1180] "Means of receiving responses from other systems" refers to devices or functions for receiving responses from external systems that sent requests.

[1181] "Means for integrating received responses and generating a final response adjusted based on emotions" refers to devices or functions that integrate information obtained from external systems and generate a final response optimized according to the user's emotional state.

[1182] "Means of providing the final answer to the user" refers to devices or functions that present the user with an answer generated based on analysis results and information from external systems.

[1183] "Natural language processing" is a technology that analyzes natural language input from users and understands its meaning and intent.

[1184] "Emotion recognition" is a technology that detects and classifies a user's emotional state based on their input data, facial expressions, voice, and other factors.

[1185] "Means of selecting the optimal system from multiple other systems" refers to a device or function that selects the most appropriate system from several external systems and sends a request to that system.

[1186] This invention is a system that recognizes user emotions and adjusts responses accordingly, operating efficiently through collaboration with servers, terminals, and other systems. This system consists of the following main components:

[1187] System Configuration

[1188] Terminal: A device that the user directly operates (for example, a smartphone).

[1189] Server: A central processing unit that receives and analyzes inquiries and generates responses in cooperation with other systems.

[1190] Other systems: External systems that the server uses to retrieve information in response to queries (e.g., content databases or dedicated APIs).

[1191] Emotion Engine: A dedicated function that recognizes emotions from user input and facial expressions and reflects them in the analysis results.

[1192] Specific implementation methods

[1193] 1. User inquiry input

[1194] Users access content distribution service applications using devices such as smartphones to make inquiries and perform actions. For example, a user might type, "I'd like recommendations for relaxing music."

[1195] 2. Server-based analysis

[1196] When the server receives user input, it analyzes this input using natural language processing (NLP) and emotion recognition techniques. The analysis extracts the keyword "relaxing music," the intention "I want to relax," and the user's emotional state (e.g., feeling stressed).

[1197] 3. Integration with other systems

[1198] Based on the analysis results, the server sends requests to appropriate other systems (e.g., content databases or recommendation APIs). For example, if a user is experiencing stress, it might request other systems to retrieve a list of music specifically designed for relaxation.

[1199] 4. Collection and Integration of Responses

[1200] Other systems process received requests, search their internal databases, and generate appropriate content. For example, they might send information about a "relaxation music playlist" back to the server.

[1201] 5. Providing responses to users

[1202] The server integrates all the collected information and generates a final response tailored to the user's emotional state. This may include specific suggestions, such as, "To help reduce your stress, we recommend this relaxation music." The terminal displays the response received from the server on its user interface.

[1203] Hardware and software to use

[1204] Hardware: Smartphone with camera

[1205] Software: OpenCV, TensorFlow, Sentiment Recognition API, Content Recommendation API

[1206] Data processing and data calculation

[1207] The server receives input data from the user and performs semantic analysis using NLP technology. Next, the emotion engine recognizes the user's emotional state and sends a request to the most appropriate system based on the analysis results. Information obtained from the content recommendation API is integrated to generate a final response optimized according to the user's emotions.

[1208] Specific example

[1209] If you are feeling stressed: Relaxation music playlists and yoga videos are recommended.

[1210] If you are feeling joyful: Entertainment videos and adventure games are recommended.

[1211] If you are feeling sad: Encouraging messages or heartwarming documentary films are recommended.

[1212] Example of a prompt

[1213] Create an application that estimates a user's emotions from their facial expressions and recommends appropriate content based on that. Recommend different content for each of the following seven emotion categories: anger, disgust, fear, joy, sadness, surprise, and neutral.

[1214] In this way, a system is built that enables personalized content delivery that responds to the user's emotions.

[1215] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1216] Step 1:

[1217] Users access content distribution service applications using devices such as smartphones and perform inquiries and operations.

[1218] Input: User request (e.g., "Please recommend some relaxing music")

[1219] Output: User request data

[1220] Specific example: A user enters "relaxing music" into the search bar within the app and presses the search button.

[1221] Step 2:

[1222] The server receives user input sent from the terminal.

[1223] Input: User's request data

[1224] Output: Request data sent to the server

[1225] Specific example: The server receives text data from a user that says "relaxing music".

[1226] Step 3:

[1227] The server uses natural language processing (NLP) to analyze user input and extract keywords and intent. Simultaneously, it uses an emotion recognition engine to analyze the user's emotional state.

[1228] Input: Request data

[1229] Output: Keywords, intentions, emotional state

[1230] Specific example: The server analyzes the keywords "relax" and "music," the intention to "want to relax," and the emotional state as "stress."

[1231] Step 4:

[1232] Based on the analysis results, the server sends requests to the appropriate other systems (e.g., content databases or recommendation service APIs).

[1233] Input: Analysis results (keywords, intentions, emotional state)

[1234] Output: Request to other systems

[1235] Specific example: A server generates data requesting relaxation music recommendations for users experiencing stress and sends it to another system.

[1236] Step 5:

[1237] Other systems process the received request, search their internal database to select the appropriate content, and send the response to the server.

[1238] Input: Request to another system

[1239] Output: Recommended content data

[1240] Specific example: Information about a "relaxation music playlist" is sent back to the server from another system.

[1241] Step 6:

[1242] The server integrates the collected response data and generates a final response optimized based on the user's emotional state.

[1243] Input: Recommended content data

[1244] Output: Final response data

[1245] Specific example: The server generates a final response that includes a suggestion such as, "To reduce your stress, we recommend this relaxation music."

[1246] Step 7:

[1247] The final response data is sent from the server to the terminal. The terminal receives this data and displays it on the user interface.

[1248] Input: Final response data

[1249] Output: Display on the user interface

[1250] Specific example: A "relaxation music playlist" is displayed on the user's smartphone screen.

[1251] In this way, the specific processing steps from user input to the final proposal are carried out.

[1252] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1253] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1254] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1255] [Fourth Embodiment]

[1256] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1257] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1258] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1259] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1260] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1261] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1262] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1263] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1264] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1265] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1266] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1267] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1268] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1269] This invention is a system for providing quick and accurate answers to user-inputted inquiries, and operates efficiently through cooperation with servers, terminals, and other systems.

[1270] System Configuration

[1271] The system consists of the following main components:

[1272] Terminal: A device that the user directly operates (e.g., a personal computer, a smartphone).

[1273] Server: A central processing unit that receives and analyzes inquiries and generates responses in cooperation with other systems.

[1274] Other systems: External systems (e.g., databases or dedicated APIs) that the server uses to retrieve information in response to queries.

[1275] Program Processing Overview

[1276] When a user submits a query through their device, the content is received by the server. The server analyzes the received data using natural language processing to extract appropriate keywords and intent. Based on the analysis results, the server then identifies the most suitable other system and sends a request. When the response from the other system is returned to the server, the server integrates it to generate a single, continuous response, which is finally provided to the user via the device.

[1277] Specific example

[1278] Step 1: User input

[1279] The terminal sends the information to the server when the user enters "I want to know the delivery status of my product" into the inquiry form and presses the submit button.

[1280] For example, user A wants to know the delivery status of an item they ordered from an online shopping site, and enters a question.

[1281] Step 2: Server-based analysis

[1282] When the server receives a user inquiry, it uses natural language processing to analyze the inquiry. The analysis extracts the keyword "delivery status" and the user's intention, "I want to know the delivery status of the product ordered by user A."

[1283] Step 3: Integration with other systems

[1284] The server selects the most suitable other system from which to obtain "delivery status" information and sends the request. In this case, it determines that a database containing delivery information exists and sends the request to that database.

[1285] For example, you can query the logistics management system for the delivery status of "Order ID: 12345".

[1286] Step 4: Collecting and integrating responses

[1287] Other systems (for example, a logistics management system) search for the delivery status of the corresponding order ID and send back information to the server stating, "Product XYZ has now left the distribution center and is scheduled to arrive on time."

[1288] The server verifies the received information and, if necessary, collects additional information from other systems (e.g., customer management systems).

[1289] Step 5: Providing responses to users

[1290] The server integrates all the collected information and generates a final response. It creates a unified response such as "Product XYZ has now left the distribution center and is scheduled to arrive on time," and provides it to the user via the terminal.

[1291] The terminal displays the response received from the server on the user interface. User A can obtain a quick and accurate answer to the inquiry they entered.

[1292] In this way, the entire system efficiently implements a series of processes, from user inquiry input to server analysis and appropriate integration with other systems, ultimately providing a final answer.

[1293] The following describes the processing flow.

[1294] Step 1:

[1295] When a user enters "I want to know the delivery status of my product" into the inquiry form and presses the submit button, the device sends that information to the server. Specifically, when the form submission event occurs, the entered text data is sent to the server as an HTTP request.

[1296] Step 2:

[1297] The server receives user inquiries and analyzes their content. Specifically, it extracts text data from the body of the HTTP request and uses a natural language processing (NLP) library to extract keywords and intent from the text data.

[1298] Step 3:

[1299] The server identifies the keyword "delivery status" and the user's intention, "I want to know the delivery status of the product ordered by user A." Based on the analysis results, it selects an appropriate other system (e.g., a logistics management system).

[1300] Step 4:

[1301] The server sends API requests to other systems it uses. Specifically, it sends requests containing relevant data such as user IDs and order IDs to the logistics management system.

[1302] Step 5:

[1303] Other systems (for example, a logistics management system) process the received request, search their internal database, and generate a response. For example, they might send back information to the server such as, "Product XYZ has now left the distribution center and is scheduled to arrive on time."

[1304] Step 6:

[1305] The server receives responses from other systems. If necessary, it also collects relevant information from other systems, such as customer management systems.

[1306] Step 7:

[1307] The server integrates the collected information to generate a final response. For example, it might create a unified response such as, "Product XYZ has now left the distribution center and is scheduled to arrive on time."

[1308] Step 8:

[1309] The server sends the final response back to the user's device. Specifically, it sends the response data to the device as an HTTP response.

[1310] Step 9:

[1311] The terminal displays the received response on the user interface. For example, it might display a message on the screen such as, "Product delivery status: Product XYZ has now left the distribution center and is expected to arrive on schedule."

[1312] In this way, a process is realized that efficiently responds to user inquiries by having each step play a clear role.

[1313] (Example 1)

[1314] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1315] In today's world, systems that enable users to obtain information quickly and accurately are crucial, but conventional systems often take a long time to analyze inquiries and provide answers. Furthermore, improving efficiency and accuracy when integrating with multiple systems remains a challenge. This invention aims to solve the problem of providing quick and accurate answers to user inquiries and offering a method for efficiently integrating with other systems.

[1316] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1317] In this invention, the server includes means for receiving user input, means for analyzing the input to extract keywords and intent, means for sending a request to an appropriate other system based on the analysis results, means for receiving responses from the other system, means for integrating the received responses to generate a final response, means for providing the final response to the user, means for sending a request based on the user input and sending voice or email, and means for recording and analyzing the user's information. This enables the provision of quick and accurate responses to user inquiries and efficient cooperation with other systems.

[1318] "Means for receiving user input" refers to the means by which data is sent to a server when a user enters an inquiry or request via a terminal.

[1319] "Means for analyzing input and extracting keywords and intent" refers to methods for analyzing input data received from users using natural language processing technology to identify necessary keywords and the user's intent.

[1320] "Means for sending requests to appropriate other systems based on analysis results" refers to means for identifying the most suitable other system based on the analyzed data and sending necessary information requests to that system.

[1321] "Means for receiving responses from other systems" refers to means for receiving information or data sent back from other systems.

[1322] "Means for integrating received responses to generate a final response" refers to a means of integrating information received from multiple other systems and generating a single, continuous response to provide to the user.

[1323] "Means of providing the final answer to the user" refers to means of sending the generated final answer to the user's device and displaying it on the user interface.

[1324] "A means of sending requests based on user input and sending voice or email notifications" refers to a means of sending requests to an external system based on the content of a user's inquiry and providing notifications via voice or email as needed.

[1325] "Means for recording and analyzing user information" refers to methods for recording user inquiry history and behavioral logs, and analyzing the data for subsequent analysis and improvement.

[1326] This invention is a system for providing quick and accurate answers to user-inputted inquiries, and it operates efficiently through cooperation with servers, terminals, and other systems.

[1327] System Configuration

[1328] The system consists of the following main components:

[1329] Terminal: A device that the user directly operates (e.g., a personal computer, a smartphone).

[1330] Server: A central processing unit that receives and analyzes inquiries and generates responses in cooperation with other systems.

[1331] Other systems: External systems that the server uses to retrieve information in response to queries (e.g., databases and application programming interfaces (APIs)).

[1332] Program Processing Overview

[1333] The user operates their device and enters their question into the inquiry form. For example, using a personal computer or smartphone, they might enter "I want to know the delivery status of product with order ID 12345" and press the submit button. This causes the device to send the inquiry to the server as an HTTP POST request.

[1334] The server processes HTTP POST requests received from the terminal using web frameworks such as Python's Flask or Node.js's Express. The received data is parsed by a natural language processing (NLP) engine (e.g., Amazon Comprehend or Dialogflow) to extract keywords and intent. For example, the keyword "delivery status" and the intent "I want to know the delivery status of the product with order ID 12345" might be extracted.

[1335] Based on the analysis results, the server sends information requests to the most appropriate other systems. For example, it sends an HTTP GET request to the API endpoint of the logistics management system to retrieve delivery information for "Order ID 12345". This request includes the order ID specified by the user.

[1336] The logistics management system searches the database for delivery information corresponding to the specified order ID and sends back information to the server, such as "Product XYZ has now left the distribution center and is scheduled to arrive on time."

[1337] The server integrates data received from other systems and generates a final response. If necessary, it may also collect additional information from other systems, such as customer management systems. The integrated information is then sent to the user's terminal, which displays it on its user interface. This allows the user to obtain a quick and accurate response.

[1338] Specific example

[1339] User inquiry input

[1340] A user enters an inquiry on an online shopping site, stating, "I want to know the delivery status of my order," and presses the submit button. For example, they might enter, "Please tell me the delivery status of the item with order ID 12345."

[1341] Server-based analysis

[1342] The server analyzes the received input data using natural language processing to extract the keywords and intent behind "delivery status" and "order ID 12345".

[1343] Integration with other systems

[1344] The server calls the logistics management system's API to request delivery information for a specified order ID. For example, it might query the delivery status of order ID 12345.

[1345] Collection and integration of responses

[1346] The logistics management system searches for delivery information for "Order ID 12345" and returns the information "Product XYZ has now left the distribution center and is scheduled to arrive on time."

[1347] Providing answers to users

[1348] The server generates the final response and sends it to the terminal. The terminal displays the response, "Product XYZ has now left the distribution center and is scheduled to arrive on time," on the user interface.

[1349] Example of a prompt

[1350] "Please tell me the current delivery status of the item with order ID 12345."

[1351] This system enables a series of processes for providing quick and accurate answers to user inquiries.

[1352] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1353] Step 1:

[1354] The user operates the terminal and enters a question into the inquiry form. For example, they might enter "I want to know the delivery status of product with order ID 12345" into the form and press the submit button. This action sends the inquiry to the server as an HTTP POST request. The input is the user's inquiry, and the output is the HTTP POST request to the server.

[1355] Step 2:

[1356] The server processes the HTTP POST request received from the terminal. The server parses the request body using a web framework such as Flask or Express. This request body is the input, and the result of the parsing is the output. Specifically, the server uses a natural language processing (NLP) engine to parse the user's input and extract the keyword "delivery status" and the intent "I want to know the delivery status of the product with order ID 12345."

[1357] Step 3:

[1358] Based on the analysis results, the server sends a request to the appropriate other system. In this case, the server generates an HTTP GET request to the logistics management system's API endpoint. The input is the analysis result "Delivery Status" and "Order ID 12345," and the output is an HTTP GET request to the logistics management system. Specifically, the server finds the API endpoint and includes the necessary parameters in the request.

[1359] Step 4:

[1360] The other system (the logistics management system) processes the HTTP GET request received from the server. The logistics management system searches the database and retrieves the corresponding order ID information. The input is the HTTP GET request from the server, and the output is information about the delivery status (e.g., "Product XYZ has now left the distribution center and is expected to arrive on schedule"). This information is sent back to the server as an HTTP response.

[1361] Step 5:

[1362] The server verifies the information received from the logistics management system and collects additional information from other systems as needed. For example, it may collect verification information from the customer management system. The input is delivery status information from the logistics management system, and based on this, additional requests are generated to obtain other necessary data. The output is the final integrated information. Specifically, the server issues additional API requests and integrates all the information after collecting the additional information.

[1363] Step 6:

[1364] The server generates a final response based on the integrated information. For example, it might generate a response such as, "Product XYZ has now left the distribution center and is scheduled to arrive on time." This generated response is the input, and the output is the HTTP response sent to the terminal. Specifically, the server sends the generated response to the terminal as a JSON response.

[1365] Step 7:

[1366] The terminal displays the final response received from the server on the user interface. The user can confirm information such as, "Product XYZ has now left the distribution center and is scheduled to arrive on time." The input is the final response from the server, and the output is the information displayed on the user interface. Specifically, the terminal analyzes the received data and displays it in a user-friendly format.

[1367] This process ensures that users receive quick and accurate responses to their inquiries.

[1368] (Application Example 1)

[1369] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1370] Users of autonomous vehicles always want to know the vehicle's current location, battery status, and route status quickly and accurately. However, conventional systems often take a long time to acquire this information, which has led to decreased user satisfaction. This invention aims to solve this problem by providing a system that can provide information quickly and accurately.

[1371] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1372] In this invention, the server includes means for sending inquiries from a user terminal to the server and identifying appropriate other systems from the analysis results using a natural language processing model, and means for performing analysis again using the information of the other systems and integrating appropriate autonomous vehicle information to present to the user. This makes it possible for users to quickly and accurately obtain the information they want to know about autonomous vehicles.

[1373] A "user terminal" refers to a device operated by a user, and includes mobile devices such as smartphones and tablets.

[1374] A "server" is a central processing system that receives inquiries from user terminals, performs analysis, and coordinates with other systems.

[1375] A "natural language processing model" is an algorithm or system that analyzes user input and extracts appropriate keywords and intents.

[1376] "Other systems" refer to external information provision systems with which the server collaborates to retrieve information in response to inquiries.

[1377] "Analysis results" refer to keywords and intentions extracted by the natural language processing model.

[1378] A "request" is a request to retrieve information that is sent to another system based on the analysis results.

[1379] "Response" refers to information sent back to the server from another system.

[1380] "Integration" refers to the process by which a server combines multiple responses it has received into a single, continuous piece of information.

[1381] A "final answer" is a complete answer generated to provide the user with integrated information.

[1382] A "generative AI model" is a module that uses artificial intelligence to generate appropriate prompt sentences in response to user inquiries.

[1383] A "prompt" refers to a query or instruction in natural language output by a generative AI model.

[1384] This invention is a system that coordinates user terminals, servers, and other systems to respond quickly and accurately to user requests for information retrieval.

[1385] System Configuration

[1386] The system consists of the following main components:

[1387] 1. User terminal:

[1388] This refers to a device operated by the user, including smartphones and tablets. Users use this device to send inquiries.

[1389] 2. Server:

[1390] A central processing system that receives inquiries and performs analysis using natural language processing models. Based on the analysis results, the server sends requests to other systems, integrates the responses, and generates a final answer.

[1391] 3. Other systems:

[1392] An external information provider system that the server collaborates with to obtain necessary information. This includes location information, battery status, and route information for autonomous vehicles.

[1393] Program processing

[1394] The system works as follows:

[1395] 1. Receiving an inquiry:

[1396] The user sends a request through an application on their device. For example, they might type, "Tell me my current location."

[1397] 2. Data Analysis:

[1398] The server analyzes the received query using a natural language processing model to extract keywords and intent. Based on the analysis results, it sends a request to the appropriate other system.

[1399] 3. Information acquisition:

[1400] The server retrieves necessary information from other systems, such as the location and battery status of autonomous vehicles.

[1401] 4. Information Integration:

[1402] The server integrates the acquired information and generates a final response to provide to the user.

[1403] 5. Providing an answer:

[1404] The integrated final response is sent to the user's terminal and displayed on the user interface.

[1405] Hardware and software to be used

[1406] The main hardware and software used are as follows:

[1407] Hardware: Smartphones, tablets, servers

[1408] Software: transformers library, requests library

[1409] Natural Language Processing Models: Generative AI Models

[1410] Specific example

[1411] If a user wants to know the current location of an autonomous vehicle, it works as follows:

[1412] 1. The user enters "Tell me my current location" into the app's contact form.

[1413] 2. The server receives the query and uses a natural language processing model to analyze the keyword "current location" and the intent "tell me".

[1414] 3. The server sends a request to the appropriate other system (for example, a vehicle location information system).

[1415] 4. The server receives information from other systems, such as "The vehicle's current location is XX," and integrates it.

[1416] 5. The server generates integrated information and displays "The vehicle's current location is XX" on the user's terminal.

[1417] Example of a prompt

[1418] The following are examples of prompts to input into a specific generative AI model:

[1419] User inquiry: "What is the current battery status of the autonomous vehicle?"

[1420] Context: "The autonomous vehicle's battery is now fully charged and ready to depart."

[1421] This allows users to obtain information quickly and accurately, leading to increased satisfaction.

[1422] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1423] Step 1:

[1424] User Inquiry Submission

[1425] The user enters their question into the inquiry form using their own device (smartphone or tablet) and presses the "Send" button. For example, they might enter "Tell me your current location." This input is sent from the device to the server.

[1426] Input: User's question (e.g., "Tell me your current location")

[1427] Output: Server query data

[1428] Step 2:

[1429] Server receives and analyzes queries.

[1430] The server receives the query sent from the terminal. The received data is parsed using a natural language processing model (e.g., the transformers library). Through this parsing, the query's keywords ("current location") and intent ("tell me") are extracted.

[1431] Input: User inquiry data

[1432] Output: Extracted keywords and intent

[1433] Step 3:

[1434] Identifying and sending requests to appropriate other systems

[1435] Based on the analysis results, the server identifies appropriate other systems to obtain the necessary information. For example, a vehicle location information system might be selected. The server sends a request to this system to query for the required information (e.g., the vehicle's current location).

[1436] Input: Extracted keywords and intent

[1437] Output: Request to the appropriate other system

[1438] Step 4:

[1439] Acquiring information from other systems

[1440] Other systems provide the necessary information in response to requests from the server. For example, a vehicle location information system returns the response, "The vehicle's current location is XX." The server receives this response.

[1441] Input: Request from server

[1442] Output: Information from other systems (e.g., the vehicle's current location)

[1443] Step 5:

[1444] Information integration and final answer generation

[1445] The server integrates information obtained from other systems and generates a final answer to provide to the user. This includes generating prompts using a generative AI model. For example, it might generate an answer such as, "The vehicle's current location is XX."

[1446] Input: Information from other systems

[1447] Output: Integrated final answer

[1448] Step 6:

[1449] Providing answers to users

[1450] The server sends the final generated response to the user's terminal. The user's terminal displays this response on its user interface, allowing the user to verify the answer to their inquiry.

[1451] Input: Integrated final answer

[1452] Output: The response displayed on the user's terminal (e.g., "The vehicle's current location is XX")

[1453] This allows users to quickly and accurately obtain information about autonomous vehicles.

[1454] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1455] This invention is a system that adds a function to recognize user emotions and adjust responses accordingly, and operates efficiently through cooperation with servers, terminals, and other systems. This enables responses that are tailored to the user's emotions, thereby improving the quality of customer support.

[1456] System Configuration

[1457] The system consists of the following main components:

[1458] Terminal: A device that the user directly operates (e.g., a personal computer, a smartphone).

[1459] Server: A central processing unit that receives and analyzes inquiries and generates responses in cooperation with other systems.

[1460] Other systems: External systems (e.g., databases or dedicated APIs) that the server uses to retrieve information in response to queries.

[1461] Emotion Engine: A dedicated function that recognizes emotions from user input and reflects them in the analysis results.

[1462] Program Processing Overview

[1463] The user makes a query through their device, and the content is received by the server. The server analyzes the received data using natural language processing (NLP) and an emotion engine, extracting keywords, intent, and even the user's emotions. The server then identifies the most suitable other system based on the analysis results and sends a request, taking emotions into consideration. When the responses from the other systems are returned to the server, the server integrates them, generates a final response adjusted according to the user's emotions, and provides it to the user via their device.

[1464] Specific example

[1465] Step 1: User input

[1466] The terminal sends the information to the server when the user enters "I want to know the delivery status of my product" into the inquiry form and presses the submit button.

[1467] For example, user A wants to know the delivery status of an item they ordered from an online shopping site, and enters a question.

[1468] Step 2: Server-based analysis

[1469] When the server receives a user inquiry, it analyzes the inquiry using natural language processing and an emotion engine. The analysis extracts the keyword "delivery status," the user's intention ("I want to know the delivery status of the product ordered by user A"), and the user's emotions (e.g., impatience or dissatisfaction).

[1470] Step 3: Integration with other systems

[1471] The server selects the most suitable other system (e.g., a logistics management system) from which to obtain "delivery status" information and sends a request that takes emotions into consideration. For example, if an emotion indicating a need for a faster response is detected, the server will also send a request that includes this information.

[1472] Step 4: Collecting and integrating responses

[1473] Other systems (for example, a logistics management system) process the received request, search their internal database, and generate a response. For example, they might send back information to the server such as, "Product XYZ has now left the distribution center and is scheduled to arrive on time."

[1474] The server verifies the received information and, if necessary, collects additional information from other systems (e.g., customer management systems).

[1475] Step 5: Providing responses to users

[1476] The server integrates all the collected information and generates a final response tailored to the user's feelings. For example, if the user is dissatisfied, it will respond politely with something like, "We apologize for any inconvenience this may have caused. Product XYZ has now left the distribution center and is expected to arrive on schedule."

[1477] The terminal displays the response received from the server on the user interface. User A can receive a quick, accurate, and emotionally sensitive response to their inquiry.

[1478] In this way, the entire system efficiently implements a series of processes, from user inquiry input to server analysis, the introduction of an emotion engine, and appropriate integration with other systems, ultimately providing an emotionally sensitive response.

[1479] The following describes the processing flow.

[1480] Step 1:

[1481] When a user enters "I want to know the delivery status of my product" into the inquiry form and presses the submit button, the device sends that information to the server. Specifically, when the form submission event occurs, the entered text data is sent to the server as an HTTP request.

[1482] Step 2:

[1483] The server receives user inquiries and analyzes their content. Specifically, it extracts text data from the body of the HTTP request and uses a natural language processing (NLP) library to extract keywords and intent from the text data.

[1484] Step 3:

[1485] The server passes the user's input text to the sentiment engine, which then recognizes the user's emotions. For example, if the text is "I'm very worried. When will the product arrive?", the sentiment engine detects the user's emotion as "worried".

[1486] Step 4:

[1487] Based on the keyword "delivery status," the user's intention to "know the delivery status of the product ordered by user A," and the emotion of "concern," the server identifies the most suitable other system (for example, a logistics management system).

[1488] Step 5:

[1489] The server sends API requests to other systems it uses. Specifically, it sends requests to the logistics management system that include relevant data such as the user ID, order ID, and detected emotions ("worried").

[1490] Step 6:

[1491] Other systems (for example, a logistics management system) process the received request, search their internal database, and generate a response. For example, they might send back information to the server such as, "Product XYZ has now left the distribution center and is scheduled to arrive on time."

[1492] Step 7:

[1493] The server receives responses from other systems and, if necessary, collects additional information from other systems (e.g., customer management systems). For example, it may also collect user purchase history and current delivery status.

[1494] Step 8:

[1495] The server integrates the collected information to generate a final response. For example, it might combine messages such as, "Product XYZ has now left the distribution center and is expected to arrive on schedule," and "We apologize for any inconvenience this may have caused."

[1496] Step 9:

[1497] The server sends the final response back to the user's device. Specifically, it sends the response data to the device as an HTTP response.

[1498] Step 10:

[1499] The device displays the received response on the user interface. For example, it might display a message such as, "Product delivery status: Product XYZ has now left the distribution center and is expected to arrive on schedule. We apologize for any inconvenience this may have caused."

[1500] In this way, the entire system efficiently implements a series of processes, from user inquiry input to server analysis, the introduction of an emotion engine, and appropriate integration with other systems, ultimately providing an emotionally sensitive response.

[1501] (Example 2)

[1502] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1503] Traditional systems extracted only keywords and intent from user inquiries, without considering emotions. This resulted in a failure to address user frustration and impatience, leading to a decline in the quality of customer support. Furthermore, ineffective requests to appropriate external systems and inefficient integration of responses sometimes resulted in delays in user responses.

[1504] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1505] In this invention, the server includes means for receiving user input, means for analyzing the input to extract keywords, intentions, and emotions, means for sending requests to appropriate other systems based on the analysis results, means for receiving responses from the other systems, means for integrating the received responses and generating a final response adjusted according to the user's emotions, and means for providing the final response to the user. This enables the provision of quick and appropriate responses that take the user's emotions into consideration.

[1506] A "user" is the entity that operates the system and makes inquiries.

[1507] "Input" refers to information that a user sends to the system through their device.

[1508] A "device" refers to a device that a user directly operates, and includes personal computers, smartphones, and other similar devices.

[1509] A "server" is a device that acts as a central processing unit, receiving and analyzing queries and coordinating with other systems.

[1510] "Analysis" is the process of understanding user input using natural language processing and sentiment analysis, and extracting keywords, intentions, and emotions.

[1511] "Natural language processing" is a technique that analyzes text data and interprets its grammar and meaning.

[1512] "Emotion analysis" is a technology that recognizes emotions from user input and reflects them in the analysis results.

[1513] "Keywords" are important words or phrases extracted from user input.

[1514] "Intention" refers to the purpose or request that the user is trying to achieve through their inquiry.

[1515] "Emotions" refer to psychological states recognized from user input, such as anxiety or dissatisfaction.

[1516] "Other systems" refers to external systems that the server uses to retrieve information, including, for example, logistics management systems and customer management systems.

[1517] A "request" is a request that a server sends to another system to obtain information.

[1518] "Responses" refer to information returned from other systems, which the server uses to provide to the user.

[1519] "Integration" is the process of combining multiple pieces of information into a single, coherent format.

[1520] The "final answer" is the response that the server generates based on the integrated information and provides to the user.

[1521] "Providing" refers to the act of sending the final response generated by the server to the user's terminal, thereby indicating a response to the user.

[1522] This invention is a system that adds a function to recognize user emotions and adjust responses accordingly. The system operates efficiently through cooperation with servers, terminals, and other systems, enabling responses that are responsive to user emotions, thereby improving the quality of customer support. The following describes specific embodiments of this system.

[1523] System Configuration

[1524] The system consists of the following main components:

[1525] Terminal: A device that the user directly operates (e.g., a personal computer, a smartphone).

[1526] Server: A central processing unit that receives and analyzes inquiries and generates responses in cooperation with other systems.

[1527] Other systems: These are external systems (such as databases or dedicated APIs) that the server uses to retrieve information in response to queries.

[1528] Emotion Engine: This is a dedicated function that recognizes emotions from user input and reflects them in the analysis results.

[1529] Program Processing Overview

[1530] When a user submits a query through their device, the content is received by the server. The server uses natural language processing (NLP) and an emotion engine to analyze the received data, extracting keywords, intent, and even the user's emotions. Based on the analysis, the server then identifies the most suitable other system and sends a request, taking emotions into consideration. When responses from other systems return to the server, the server integrates them, generates a final response adjusted according to the user's emotions, and provides it to the user via their device.

[1531] Hardware and software to be used

[1532] The following specific hardware and software will be used for the server and terminal:

[1533] Python is a programming language used for natural language processing and sentiment analysis.

[1534] NLTK library: A Python library for natural language processing.

[1535] Google Cloud Natural Language API: A cloud-based API for sentiment analysis.

[1536] RabbitMQ: Used for managing message queues within the server.

[1537] HTTP Request: A communication protocol used by servers to interact with other systems.

[1538] REST API and JSON: These are formats and protocols used for data exchange between servers and other systems.

[1539] Specific example

[1540] Step 1: User input

[1541] The user enters "I want to know the delivery status of my product" into the inquiry form on their device and presses the submit button.

[1542] The terminal internally constructs and sends an HTTP POST request to the server to send the contents of this inquiry.

[1543] Step 2: Server receives and analyzes data.

[1544] The server stores the query content received from the terminal in a message queue such as RabbitMQ.

[1545] The server executes a Python script and uses the NLTK library to extract the keyword "delivery status" and the intent "I want to know the delivery status of the items ordered by user A."

[1546] The server calls the Google Cloud Natural Language API to detect that the user is feeling anxious.

[1547] Step 3: Integration with other systems

[1548] The server uses an HTTP client (for example, Python's requests library) to send a request to the logistics management system to inquire about the "delivery status".

[1549] The server also adds additional information to the request header, such as "the user is feeling anxious."

[1550] Step 4: Collecting and integrating responses

[1551] The system processes the request received by another system (the logistics management system), searches its internal database, and generates information. It then sends back the information to the server stating, "Product XYZ has now left the distribution center and is scheduled to arrive on time."

[1552] The server collects necessary information from other related systems (e.g., customer management systems) and integrates all the data.

[1553] Step 5: Providing responses to users

[1554] Based on the information collected by the server, a final response is generated that is tailored to the user's emotions. For example, a response that reassures the user might be something like, "We apologize for any concern this may have caused. Product XYZ has now left the distribution center and is expected to arrive on schedule."

[1555] The device receives the HTTP response and displays the final answer in the user interface (e.g., a text area on a web page).

[1556] Example of a prompt

[1557] Analyze the following inquiry and generate the appropriate answer:

[1558] Inquiry: "I would like to know the delivery status of my order."

[1559] User emotion: "Anxiety"

[1560] Please obtain the necessary information from relevant systems and provide an emotionally sensitive response.

[1561] In this way, the responses provided, from user inquiry input to server analysis, the introduction of an emotion engine, and appropriate integration with other systems, are efficiently delivered in a manner that takes the user's emotions into consideration.

[1562] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1563] Step 1: User inquiry input

[1564] Input: Text entered by the user in the inquiry form (e.g., "I would like to know the delivery status of my order").

[1565] Output: Data sent to the server from the contents of the inquiry form.

[1566] Specific operation: The user enters "I want to know the delivery status of my product" into the inquiry form on the device and presses the submit button. The device constructs and sends an HTTP POST request to send this inquiry to the server. The request includes necessary metadata such as the user ID, inquiry content, and timestamp.

[1567] Step 2: Server receives and analyzes data.

[1568] Input: Inquiry content sent from the terminal (HTTP POST request)

[1569] Output: Keywords, intentions, and emotions as analysis results (Example: Keyword "Delivery status", Intention "I want to know the delivery status of the product", Emotion "Anxiety")

[1570] Specific operation: The server stores the content of the inquiry received from the terminal in a message queue such as RabbitMQ. The server then executes a Python script to parse the inquiry. First, it uses the NLTK library to extract the keyword "delivery status" and the intention "I want to know the delivery status of the product" from the text. Next, it calls the Google Cloud Natural Language API to detect the user's emotion (e.g., "anxiety").

[1571] Step 3: Integration with other systems

[1572] Input: Analysis results (Keyword "Delivery status", Intent "I want to know the delivery status of the product", Emotion "Anxiety")

[1573] Output: Requests to other systems (e.g., HTTP requests to a logistics management system)

[1574] Specific operation: Based on the analysis results, the server forwards the analysis data to the most suitable other system. Using the Python requests library, a request is sent to the logistics management system to inquire about the "delivery status". This request includes information such as the user ID, the content of the inquiry, and the analyzed emotion (e.g., "anxiety").

[1575] Step 4: Collecting and integrating responses

[1576] Input: Response from another system (Example: "Product XYZ has now left the distribution center and is scheduled to arrive on time.")

[1577] Output: Integrated response data (Example: "Product XYZ has now left the distribution center and is expected to arrive on schedule. We apologize for any inconvenience this may have caused.")

[1578] Specific operation: The logistics management system processes the received request and retrieves the necessary information by referring to its internal database. For example, it might return information in JSON format such as, "Product XYZ has now left the distribution center and is scheduled to arrive on time." The server verifies the received information and, if additional information is needed, gathers information from other systems (e.g., customer management system). The server integrates all the collected information and generates a final response that takes the user's feelings into consideration.

[1579] Step 5: Providing responses to users

[1580] Input: Integrated final response (Example: "Item XYZ has now left the distribution center and is expected to arrive on schedule. We apologize for any inconvenience this may have caused.")

[1581] Output: Response message provided to the user

[1582] Specific operation: The server sends the final response it generates to the terminal as an HTTP response. The terminal receives this and displays it in the user interface. The displayed message includes product information as well as language that takes the user's feelings into consideration (e.g., "We apologize for any inconvenience this may have caused"). This allows the user to receive a quick, accurate, and emotionally considerate response to their inquiry.

[1583] (Application Example 2)

[1584] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1585] Traditional content delivery services often provided uniform recommended content without considering users' emotional states, resulting in insufficient user satisfaction. Furthermore, accurately understanding user needs was difficult, leading to a decline in content quality and relevance. Therefore, personalized content delivery tailored to user emotions is in demand.

[1586] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1587] In this invention, the server includes means for receiving user input, means for analyzing the input to extract emotions, keywords, and intentions, means for sending requests to appropriate other systems based on the analysis results, means for receiving responses from the other systems, means for integrating the received responses and generating a final response adjusted based on emotions, and means for providing the final response to the user. This enables the recommendation of appropriate content according to the user's emotional state.

[1588] "Means for receiving user input" refers to devices or functions that receive operations or inquiries made by users to the system.

[1589] "Means for analyzing input to extract emotions, keywords, and intentions" refers to devices or functions that process input data received from a user to identify emotions, important words, and the purposes or requests that those words represent.

[1590] "Means for sending requests to appropriate other systems" refers to devices or functions that send requests to external systems selected based on the analysis results to obtain the necessary information.

[1591] "Means for receiving responses from other systems" refers to devices or functions for receiving responses from external systems that have sent requests.

[1592] "Means for integrating received responses and generating a final response adjusted based on emotions" refers to devices or functions that integrate information obtained from external systems and generate a final response optimized according to the user's emotional state.

[1593] "Means of providing the final answer to the user" refers to devices or functions that present the user with an answer generated based on analysis results and information from external systems.

[1594] "Natural language processing" is a technology that analyzes natural language input from users and understands its meaning and intent.

[1595] "Emotion recognition" is a technology that detects and classifies a user's emotional state based on input data, facial expressions, voice, and other factors.

[1596] "Means of selecting the optimal system from multiple other systems" refers to a device or function that selects the most appropriate system from several external systems and sends a request to that system.

[1597] This invention is a system that recognizes user emotions and adjusts responses accordingly, operating efficiently through collaboration with servers, terminals, and other systems. This system consists of the following main components:

[1598] System Configuration

[1599] Terminal: A device that the user directly operates (for example, a smartphone).

[1600] Server: A central processing unit that receives and analyzes inquiries and generates responses in cooperation with other systems.

[1601] Other systems: External systems that the server uses to retrieve information in response to queries (e.g., content databases or dedicated APIs).

[1602] Emotion Engine: A dedicated function that recognizes emotions from user input and facial expressions and reflects them in the analysis results.

[1603] Specific implementation methods

[1604] 1. User inquiry input

[1605] Users access content distribution service applications using devices such as smartphones to make inquiries and perform actions. For example, a user might type, "I'd like recommendations for relaxing music."

[1606] 2. Server-based analysis

[1607] When the server receives user input, it analyzes this input using natural language processing (NLP) and emotion recognition techniques. The analysis extracts the keyword "relaxing music," the intention "I want to relax," and the user's emotional state (e.g., feeling stressed).

[1608] 3. Integration with other systems

[1609] Based on the analysis results, the server sends requests to appropriate other systems (e.g., content databases or recommendation APIs). For example, if a user is experiencing stress, it might request other systems to retrieve a list of music specifically designed for relaxation.

[1610] 4. Collection and Integration of Responses

[1611] Other systems process received requests, search their internal databases, and generate appropriate content. For example, they might send information about a "relaxation music playlist" back to the server.

[1612] 5. Providing responses to users

[1613] The server integrates all the collected information and generates a final response tailored to the user's emotional state. This may include specific suggestions, such as, "To help reduce your stress, we recommend this relaxation music." The terminal displays the response received from the server on its user interface.

[1614] Hardware and software to use

[1615] Hardware: Smartphone with camera

[1616] Software: OpenCV, TensorFlow, Sentiment Recognition API, Content Recommendation API

[1617] Data processing and data calculation

[1618] The server receives input data from the user and performs semantic analysis using NLP technology. Next, the emotion engine recognizes the user's emotional state and sends a request to the most appropriate system based on the analysis results. Information obtained from the content recommendation API is integrated to generate a final response optimized according to the user's emotions.

[1619] Specific example

[1620] If you are feeling stressed: Relaxation music playlists and yoga videos are recommended.

[1621] If you are feeling joyful: Entertainment videos and adventure games are recommended.

[1622] If you are feeling sad: Encouraging messages or heartwarming documentary films are recommended.

[1623] Example of a prompt

[1624] Create an application that estimates a user's emotions from their facial expressions and recommends appropriate content based on that. Recommend different content for each of the following seven emotion categories: anger, disgust, fear, joy, sadness, surprise, and neutral.

[1625] In this way, a system is built that enables personalized content delivery that responds to the user's emotions.

[1626] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1627] Step 1:

[1628] Users access content distribution service applications using devices such as smartphones and perform inquiries and operations.

[1629] Input: User request (e.g., "Please recommend some relaxing music")

[1630] Output: User request data

[1631] Specific example: A user enters "relaxing music" into the search bar within the app and presses the search button.

[1632] Step 2:

[1633] The server receives user input sent from the terminal.

[1634] Input: User's request data

[1635] Output: Request data sent to the server

[1636] Specific example: The server receives text data from a user that says "relaxing music".

[1637] Step 3:

[1638] The server uses natural language processing (NLP) to analyze user input and extract keywords and intent. Simultaneously, it uses an emotion recognition engine to analyze the user's emotional state.

[1639] Input: Request data

[1640] Output: Keywords, intentions, emotional state

[1641] Specific example: The server analyzes the keywords "relax" and "music," the intention to "want to relax," and the emotional state as "stress."

[1642] Step 4:

[1643] Based on the analysis results, the server sends requests to the appropriate other systems (e.g., content databases or recommendation service APIs).

[1644] Input: Analysis results (keywords, intentions, emotional state)

[1645] Output: Request to other systems

[1646] Specific example: A server generates data requesting relaxation music recommendations for users experiencing stress and sends it to another system.

[1647] Step 5:

[1648] Other systems process the received request, search their internal database to select the appropriate content, and send the response to the server.

[1649] Input: Request to another system

[1650] Output: Recommended content data

[1651] Specific example: Information about a "relaxation music playlist" is sent back to the server from another system.

[1652] Step 6:

[1653] The server integrates the collected response data and generates a final response optimized based on the user's emotional state.

[1654] Input: Recommended content data

[1655] Output: Final response data

[1656] Specific example: The server generates a final response that includes a suggestion such as, "To reduce your stress, we recommend this relaxation music."

[1657] Step 7:

[1658] The final response data is sent from the server to the terminal. The terminal receives this data and displays it on the user interface.

[1659] Input: Final response data

[1660] Output: Display on the user interface

[1661] Specific example: A "relaxation music playlist" is displayed on the user's smartphone screen.

[1662] In this way, the specific processing steps from user input to the final proposal are carried out.

[1663] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1664] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1665] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1666] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1667] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1668] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1669] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1670] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1671] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1672] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1673] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1674] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1675] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1676] 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.

[1677] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1678] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1679] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1680] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1681] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1682] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1683] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[1684] The following is further disclosed regarding the embodiments described above.

[1685] (Claim 1)

[1686] A means for receiving user input,

[1687] A means for analyzing the aforementioned input and extracting keywords and intent,

[1688] A means for sending a request to an appropriate other system based on the aforementioned analysis results,

[1689] Means for receiving responses from the aforementioned other systems,

[1690] A means for integrating the received responses to generate a final response,

[1691] A means of providing the user with the aforementioned final answer,

[1692] A system that includes this.

[1693] (Claim 2)

[1694] The system according to claim 1, wherein the means includes means for analyzing user input using natural language processing.

[1695] (Claim 3)

[1696] The system according to claim 1, wherein the means for sending a request to another system includes means for selecting the optimal system from a plurality of other systems and sending the request.

[1697] "Example 1"

[1698] (Claim 1)

[1699] A means for receiving user input,

[1700] A means for analyzing the aforementioned input and extracting keywords and intent,

[1701] A means for sending a request to an appropriate other system based on the aforementioned analysis results,

[1702] Means for receiving responses from the aforementioned other systems,

[1703] A means for integrating the received responses to generate a final response,

[1704] A means of providing the user with the aforementioned final answer,

[1705] A means for sending a request based on the user's input and sending voice or email,

[1706] Means for recording and analyzing the user's information,

[1707] A system that includes this.

[1708] (Claim 2)

[1709] The system according to claim 1, wherein the means includes means for analyzing user input using natural language processing.

[1710] (Claim 3)

[1711] The system according to claim 1, wherein the means for sending a request to another system includes means for selecting the optimal system from a plurality of other systems and sending the request.

[1712] "Application Example 1"

[1713] (Claim 1)

[1714] A means for receiving user input,

[1715] A means for analyzing the aforementioned input and extracting keywords and intent,

[1716] A means for sending a request to an appropriate other system based on the aforementioned analysis results,

[1717] Means for receiving responses from the aforementioned other systems,

[1718] A means for integrating the received responses to generate a final response,

[1719] A means of providing the user with the aforementioned final answer,

[1720] A means of sending inquiries from a user terminal to a server and identifying appropriate other systems from the analysis results using a natural language processing model,

[1721] A means of performing a re-analysis using information from other systems, integrating appropriate information on autonomous vehicles, and presenting it to the user,

[1722] A system that includes this.

[1723] (Claim 2)

[1724] The system according to claim 1, wherein the means includes means for analyzing user input using natural language processing.

[1725] (Claim 3)

[1726] The system according to claim 1, wherein the means for sending a request to another system includes means for selecting the optimal system from a plurality of other systems and sending a request, and means for generating a prompt sentence using a generative AI model and deriving a response.

[1727] "Example 2 of combining an emotion engine"

[1728] (Claim 1)

[1729] A means for receiving user input,

[1730] A means for analyzing the aforementioned input and extracting keywords, intentions, and emotions,

[1731] A means for sending a request to an appropriate other system based on the aforementioned analysis results,

[1732] Means for receiving responses from the aforementioned other systems,

[1733] A means for integrating the received responses and generating a final response adjusted according to the user's emotions,

[1734] A means of providing the user with the aforementioned final answer,

[1735] A system that includes this.

[1736] (Claim 2)

[1737] The system according to claim 1, wherein the means includes means for analyzing user input using natural language processing and sentiment analysis.

[1738] (Claim 3)

[1739] The system according to claim 1, wherein the means for sending a request to another system includes means for selecting the optimal system from a plurality of other systems and sending the request.

[1740] "Application example 2 of combining emotional engines"

[1741] (Claim 1)

[1742] A means for receiving user input,

[1743] A means for analyzing the aforementioned input to extract emotions, keywords, and intentions,

[1744] A means for sending a request to an appropriate other system based on the aforementioned analysis results,

[1745] Means for receiving responses from the aforementioned other systems,

[1746] A means for integrating the received responses and generating a final response adjusted based on emotions,

[1747] A means of providing the user with the aforementioned final answer,

[1748] A system that includes this.

[1749] (Claim 2)

[1750] The system according to claim 1, wherein the means includes means for analyzing user input using natural language processing and emotion recognition.

[1751] (Claim 3)

[1752] The system according to claim 1, wherein the means for sending a request to another system includes means for selecting the optimal system from a plurality of other systems and sending the request. [Explanation of Symbols]

[1753] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for receiving user input, A means for analyzing the aforementioned input and extracting keywords and intent, A means for sending a request to an appropriate other system based on the aforementioned analysis results, Means for receiving responses from the aforementioned other systems, A means for integrating the received responses to generate a final response, A means of providing the user with the aforementioned final answer, A system that includes this.

2. The system according to claim 1, wherein the means includes means for analyzing user input using natural language processing.

3. The system according to claim 1, wherein the means for sending a request to another system includes means for selecting the optimal system from a plurality of other systems and sending the request.

Images