system

Abstract

We provide the system. [Solution] A means by which the user inputs the problem in text format, A means for the terminal to send the entered text data to the server, A means for analyzing data received by the server and generating or searching for an appropriate response, A means of sending the server-generated or searched answer back to the terminal, A means of visually displaying the response received by the terminal to the user, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] The problem to be solved by the present invention is to improve the current situation where there are a variety of tasks that customers must perform after signing a contract, such as transferring data on a smartphone or submitting campaign-related documents, and customers feel difficulties during the process of proceeding with the tasks themselves or there are frequent inquiries to the store. In particular, due to the lack of appropriate support for these tasks, the progress of the tasks is not smooth, causing a decrease in customer satisfaction and an increase in the workload at the storefront, which is a problem.

Means for Solving the Problems

[0005] To solve the above problems, the present invention provides a system that includes means for a user to input a problem in text format, means for a terminal to send the input text data to a server, means for the server to analyze the received data and generate or retrieve an appropriate answer, means for the server to return the generated or retrieved answer to the terminal, and means for the terminal to visually display the received answer to the user. Furthermore, by adding means for the server to analyze the user's input using a natural language processing engine and means for querying a knowledge base or FAQ database to retrieve an appropriate answer, the system provides quick and accurate support for problems faced by users and enables smooth progress of work after the contract is signed. This improves user satisfaction and reduces inquiries to stores.

[0006] A "user" is an individual or legal entity that is using the support system to resolve their own problems.

[0007] A "terminal" is an electronic device used by a user to input questions and communicate with a server. Examples include smartphones and personal computers.

[0008] A "server" is a computer system that receives requests from users, analyzes the problem, generates or searches for appropriate answers, and sends them back to the terminal.

[0009] "Text format" refers to a method of inputting a user's problem as textual information. It refers to natural language text.

[0010] A "knowledge base" is a database that provides appropriate answers to user problems, including records of past problem-solving and FAQs (frequently asked questions and their answers).

[0011] A "natural language processing engine" is a software technology that analyzes text-based data to extract keywords and context.

[0012] An "HTTP request" is a protocol used to send information from a user's device to a server, and is a standard method particularly used for web communication.

[0013] "Analysis" is the process that a server performs to understand the data it receives from a user and to clarify the user's intentions and problems.

[0014] "Visually displaying" refers to displaying the response received by the device on the screen in a way that is easy for the user to understand. This can be done using text, images, links, etc.

[0015] "Generating or retrieving the appropriate answer" means that after the server analyzes the user's problem, it either creates a new answer or retrieves one from an existing database to provide the correct information and steps to address it. [Brief explanation of the drawing]

[0016] [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] Shows an emotion map where multiple emotions are mapped. [Figure 10] 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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), etc.

[0020] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0021] 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.

[0022] 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).

[0023] 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."

[0024] [First Embodiment]

[0025] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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".

[0037] This invention relates to a system for supporting tasks performed by customers after a contract has been signed. This system enables a series of processes in which the user inputs a problem in text format, sends the data to a server, the server analyzes the data, generates an answer, sends the answer back, and the terminal displays the answer to the user.

[0038] System Configuration

[0039] 1. The user enters the problem.

[0040] Users use devices such as smartphones or computers to enter the problem they need support for in text format. For example, they might enter a specific problem such as, "I don't know how to transfer data from my smartphone."

[0041] 2. The device sends the request to the server.

[0042] The terminal generates an HTTP request to send the entered text data to the server. This request includes the user's problem description.

[0043] 3. The server receives the request.

[0044] The server receives an HTTP request sent from the terminal. After receiving it, it extracts the user's problem details from the request body.

[0045] 4. The server analyzes the problem.

[0046] The server uses a natural language processing engine to analyze the text data entered by the user. Through this analysis, it extracts keywords and context to understand the user's problem.

[0047] 5. The server generates or searches for answers.

[0048] The server generates an appropriate answer to the user's problem based on the analysis results, or searches for an appropriate answer from a knowledge base or FAQ database. For example, it searches for and retrieves instructions on "how to transfer data from a smartphone."

[0049] 6. The server sends the response back to the terminal.

[0050] The server returns the generated or retrieved response data to the terminal as an HTTP response. This response data includes specific steps, links, and relevant resources for solving the problem.

[0051] 7. The device receives and displays the response.

[0052] The device analyzes the response received from the server and displays it in a format that is easy for the user to understand. For example, the procedure for transferring data from a smartphone might be displayed as text, images, and links.

[0053] Specific example

[0054] Data migration support

[0055] 1. The user enters the problem.

[0056] User: "I want to transfer my data to my new smartphone."

[0057] 2. The device sends the request to the server.

[0058] The device sends this request to the server as an HTTP request.

[0059] 3. The server receives the request.

[0060] The server receives the request and extracts the text, "I want to transfer data to a new smartphone."

[0061] 4. The server analyzes the problem.

[0062] The server uses a natural language processing engine to analyze the keyword "data migration" and understand the user's intent.

[0063] 5. The server generates or searches for answers.

[0064] The server searches the knowledge base for "Smartphone Data Migration Procedure" and generates the relevant information.

[0065] 6. The server sends the response back to the terminal.

[0066] The server sends the generated response data back to the terminal as an HTTP response.

[0067] 7. The device receives and displays the response.

[0068] The device visually displays the received responses, allowing the user to perform data migration while following the instructions.

[0069] This system allows users to smoothly complete the necessary tasks after signing a contract, reducing inquiries to stores and increasing user satisfaction. Furthermore, the server's natural language processing engine improves the accuracy of problem analysis, enabling the rapid provision of appropriate answers.

[0070] The following describes the processing flow.

[0071] Step 1:

[0072] Users enter the problem they need support for in text format into an input field on their device, such as a smartphone or computer. For example, "I don't know how to transfer data from my smartphone."

[0073] Step 2:

[0074] The terminal receives the text data entered by the user and generates an HTTP request to send to the server. The request includes the user's input.

[0075] Step 3:

[0076] The device sends the generated HTTP request to the server's API endpoint. This request contains the user's problem and is delivered to the server for analysis.

[0077] Step 4:

[0078] The server receives an HTTP request sent from the terminal. The server extracts the user's input from the request body. Example: "I don't know how to transfer data from my smartphone."

[0079] Step 5:

[0080] The server uses a natural language processing engine to analyze the received text data. It tokenizes the text and extracts keywords and context. For example, it extracts keywords such as "data migration" and "smartphone."

[0081] Step 6:

[0082] Based on the analysis results, the server generates an answer suitable for the user's problem or searches the knowledge base or FAQ database. For example, it searches the knowledge base for "Smartphone data migration procedure".

[0083] Step 7:

[0084] The server prepares the generated or retrieved answers as HTTP responses and constructs the data to send back to the terminal. The answers should include specific instructions and relevant links.

[0085] Step 8:

[0086] The server returns the prepared response data to the terminal as an HTTP response. The response data is sent along with a status code (e.g., 200 OK).

[0087] Step 9:

[0088] The terminal receives an HTTP response from the server. It parses the response body and prepares the data for display to the user.

[0089] Step 10:

[0090] The device displays the received response data to the user. This data is displayed in a visually easy-to-understand format, such as text, images, and links, making it accessible to the user. For example, a data migration procedure manual is displayed, allowing the user to migrate data from their smartphone by following the instructions.

[0091] The above outlines the specific processing flow within the customer support system after the contract is signed.

[0092] (Example 1)

[0093] 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."

[0094] Traditional support systems often resulted in long waiting times between users entering a problem and receiving a solution, and sometimes even inadequate answers. This led to decreased user satisfaction and an increase in inquiries to the support center.

[0095] 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.

[0096] In this invention, the server includes means for an input form and a submit button for the user to enter a problem; means for the terminal to generate an HTTP request and send it to the server's endpoint; means for the server to extract the user's problem details from the request body; means for understanding the user's problem using a natural language processing engine; and means for searching for an answer by referring to a knowledge base or FAQ database. This enables the user to obtain an answer for problem resolution quickly and accurately, reduces inquiries to the support center, and improves user satisfaction.

[0097] A "user" refers to an individual or legal entity that uses a support system to input a problem and seek a solution.

[0098] "Device" refers to electronic devices used by users, such as smartphones, personal computers, and tablets.

[0099] A "server" refers to a remote computer that receives and processes requests sent by users.

[0100] An "input form" refers to an online input field where a user enters a question in text format.

[0101] The term "send button" refers to an interface element used to send entered text data to the server.

[0102] An "HTTP request" refers to a type of internet communication protocol used to send data from a user's device to a server.

[0103] An "endpoint" refers to an address, such as a URL or URI, that is accessible on a server to provide a specific function or service.

[0104] The "request body" refers to the data contained in the message portion of an HTTP request.

[0105] A "natural language processing engine" refers to software and technology that allows computers to understand and analyze human language.

[0106] A "knowledge base" refers to a database system that stores and makes searchable past information and data.

[0107] An "FAQ database" refers to a database that compiles frequently asked questions and their answers.

[0108] "HTTP response" refers to a type of internet communication protocol used by a server to send a response to a user's device.

[0109] This invention relates to a system for supporting tasks performed by customers after a contract has been signed. This system enables a series of processes in which the user inputs a problem in text format, sends the data to a server, the server analyzes the data, generates an answer, sends the answer back, and the terminal displays the answer to the user.

[0110] System Configuration

[0111] 1. The user enters the problem.

[0112] Users use devices such as smartphones or computers to enter the problem they need support for in text format. For example, they might enter a specific problem such as, "I want to transfer data to my new smartphone."

[0113] 2. The device sends the request to the server.

[0114] The terminal generates an HTTP request to send the entered text data to the server. This request includes the user's problem description.

[0115] 3. The server receives the request.

[0116] The server receives an HTTP request sent from the terminal. After receiving it, it extracts the user's problem details from the request body.

[0117] 4. The server analyzes the problem.

[0118] The server uses a natural language processing engine (for example, Google® Cloud Natural Language API or OpenAI® GPT-3®) to analyze the text data entered by the user. Through this analysis, keywords and context are extracted to understand the user's problem.

[0119] 5. The server generates or searches for answers.

[0120] The server generates an appropriate answer to the user's problem based on the analysis results. Alternatively, it searches for the appropriate answer from a knowledge base or FAQ database (e.g., Zendesk). For example, it searches for and retrieves instructions on "how to transfer data from a smartphone."

[0121] 6. The server sends the response back to the terminal.

[0122] The server returns the generated or retrieved response data to the terminal as an HTTP response. This response data includes specific steps, links, and relevant resources for solving the problem.

[0123] 7. The device receives and displays the response.

[0124] The device analyzes the response received from the server and displays it in a format that is easy for the user to understand. For example, the procedure for transferring data from a smartphone might be displayed as text, images, and links.

[0125] Specific example

[0126] Data migration support

[0127] 1. The user enters the problem.

[0128] User: "I want to transfer my data to my new smartphone."

[0129] 2. The device sends the request to the server.

[0130] The device sends this request to the server as an HTTP request.

[0131] 3. The server receives the request.

[0132] The server receives the request and extracts the text, "I want to transfer data to a new smartphone."

[0133] 4. The server analyzes the problem.

[0134] The server uses a natural language processing engine to analyze the keyword "data migration" and understand the user's intent.

[0135] 5. The server generates or searches for answers.

[0136] The server searches the knowledge base for "Smartphone Data Migration Procedure" and generates the relevant information.

[0137] 6. The server sends the response back to the terminal.

[0138] The server sends the generated response data back to the terminal as an HTTP response.

[0139] 7. The device receives and displays the response.

[0140] The device visually displays the received responses, allowing the user to perform data migration while following the instructions.

[0141] This system allows users to smoothly complete the necessary tasks after signing a contract, reducing inquiries to stores and increasing user satisfaction. Furthermore, the server's natural language processing engine improves the accuracy of problem analysis, enabling the rapid provision of appropriate answers.

[0142] Example of a prompt

[0143] "Please tell me how to transfer data to a new smartphone."

[0144] By inputting this prompt into the generating AI model, specific and appropriate support content will be provided.

[0145] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0146] Step 1: The user enters the problem.

[0147] Users use their own devices (smartphones or computers) to enter the problem they need support for in text format. Specifically, they type "I want to transfer data to a new smartphone" into the input form on their browser and click the submit button. This action generates text as input data.

[0148] Step 2: The device sends the request to the server.

[0149] The terminal generates an HTTP POST request to send the entered text data to the server. This request contains the problem details entered by the user. Specifically, the browser captures the user's input, stores it in the request body, and sends it to the specified server endpoint.

[0150] Step 3: The server receives the request.

[0151] The server receives an HTTP request sent from the terminal. The request contains text data entered by the user. The server extracts the text "I want to transfer data to a new smartphone" from the request body. Specifically, a web server that processes HTTP requests (for example, Apache® or Nginx) receives the request and parses its contents.

[0152] Step 4: The server analyzes the problem.

[0153] The server uses a natural language processing engine (such as Google Cloud Natural Language API or OpenAI's GPT-3) to analyze the text data entered by the user. Based on the analysis, keywords and context are extracted to understand the user's intent. Specifically, the extracted text data is passed to the natural language processing engine, which then extracts keywords such as "data migration" and "smartphone."

[0154] Step 5: The server generates or searches for an answer.

[0155] The server generates appropriate answers to the user's problem based on the analysis results. Alternatively, it searches for appropriate answers in a knowledge base or FAQ database (e.g., Zendesk). Specifically, it queries the knowledge base for "smartphone data migration procedure" and retrieves relevant procedures and answers. It also utilizes a generative AI model to generate answers as needed.

[0156] Step 6: The server sends the response back to the terminal.

[0157] The server returns the generated or retrieved answer data to the terminal as an HTTP response. The response data includes specific steps for solving the problem and relevant links. Specifically, the server formats the retrieved or generated answer as an HTTP response and sends it to the user's terminal.

[0158] Step 7: The device receives and displays the response.

[0159] The device analyzes the response received from the server and displays it in a format that is easy for the user to understand. Specifically, the browser receives the HTTP response from the server and displays it as text, images, and links. For example, "Smartphone data migration procedure" might be displayed in bullet points, along with links to related support pages.

[0160] (Application Example 1)

[0161] 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."

[0162] Traditional text-based customer support systems have the challenge of not being able to respond quickly and accurately to user problems. As a result, users do not receive adequate support, which in turn leads to decreased customer satisfaction. Furthermore, there was a need for a system that efficiently provides support information to resolve issues related to products purchased by users on e-commerce sites and other platforms.

[0163] 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.

[0164] In this invention, the server includes means for parsing queries and generating or retrieving appropriate answers from a knowledge base or FAQ database, means for returning the generated or retrieved answers to the terminal, and means for the terminal to visually display the answers. This makes it possible to efficiently resolve user problems and improve customer satisfaction.

[0165] 1. A "user" is someone who attempts to solve a problem using the system.

[0166] 2. "Text format" refers to a format that uses character data to represent information.

[0167] 3. "Terminal" refers to a device such as a computer or smartphone used by a user.

[0168] 4. A "server" is a computer system that receives requests from terminals and performs analysis and generates responses.

[0169] 5. A "natural language processing engine" is a software technology used to analyze text data and understand its meaning.

[0170] 6. A "knowledge base" is a database in which solutions to problems are systematically compiled.

[0171] 7. An "FAQ database" is a database that compiles frequently asked questions and their answers.

[0172] 8. An "HTTP request" is one of the protocols used to exchange data between a client and a server.

[0173] 9. "Answer generation" is the process of creating appropriate solutions to the analyzed problem.

[0174] 10. "Searching" is the process of finding the desired information from a database.

[0175] 11. "Visual display" refers to the process of providing information to users in an easily understandable format.

[0176] This invention is a system designed to support tasks performed by customers after a contract has been signed. It enables a series of processes in which the user inputs a problem in text format, sends that data to a server, the server analyzes it, generates an answer, sends the answer back, and the terminal displays the answer to the user.

[0177] Hardware and software to use

[0178] Hardware:

[0179] smartphone

[0180] Cloud Server

[0181] software:

[0182] Mobile app frameworks (React Native, Flutter®, etc.)

[0183] Server-side frameworks (Node.js, Django, etc.)

[0184] Natural language processing engines (such as Google NLP, IBM Watson®, OpenAI GPT-4®, etc.)

[0185] System Overview

[0186] 1. The user enters the problem.

[0187] Users enter their problems in text format using a smartphone application. An example of such a problem is, "My new vacuum cleaner isn't working."

[0188] 2. The device sends a problem.

[0189] The smartphone sends the user-entered question to the server as an HTTP request. The request includes the text data entered by the user.

[0190] 3. The server receives and parses the request.

[0191] After receiving an HTTP request, the server uses a natural language processing engine to analyze the text data. Through this analysis, it extracts keywords and context related to the problem, thereby understanding its content.

[0192] 4. The server generates or searches for answers.

[0193] Based on the analysis results, the server generates or searches for appropriate answers from the knowledge base or FAQ database. For example, it searches for and retrieves troubleshooting information for a case where "the new vacuum cleaner isn't working."

[0194] 5. The server sends the response.

[0195] The server returns the generated or retrieved response data to the terminal as an HTTP response. The response data includes specific steps and related resources.

[0196] 6. The device displays the answer.

[0197] The smartphone analyzes the received response and displays it in a format that is easy for the user to understand. For example, it may display it in the form of text, images, or video links.

[0198] Specific example

[0199] When a user enters "My new vacuum cleaner isn't working," the following process is executed.

[0200] 1. User enters the problem: "My new vacuum cleaner isn't working."

[0201] 2. The device sends the request to the server.

[0202] 3. The server receives the request and analyzes the problem.

[0203] 4. Use a natural language processing engine to extract the keywords "vacuum cleaner" and "not working".

[0204] 5. Search for information on "vacuum cleaner troubleshooting" in the knowledge base or FAQ database.

[0205] 6. The server generates an appropriate response and sends it back to the terminal.

[0206] 7. Smartphones visually display the answers.

[0207] Example of a prompt

[0208] "The vacuum cleaner I recently bought isn't working at all. What should I do?"

[0209] As described above, this system enables users to efficiently resolve problems they face after signing a contract, thereby contributing to improved customer satisfaction.

[0210] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0211] Step 1:

[0212] The user enters the problem in text format. The user uses a smartphone application to enter the problem into a text box. For example, the user might enter "My new vacuum cleaner isn't working." The input data is saved in text format.

[0213] Step 2:

[0214] The terminal sends the entered text data to the server. The terminal generates an HTTP POST request containing the entered text data and sends it to the server. The input data is sent to the server, and an HTTP request is generated as output data from the terminal.

[0215] Step 3:

[0216] The server receives the request. The server receives the HTTP request and extracts the text data entered by the user from its body. The input data is the HTTP request, and the output data is the extracted problem text.

[0217] Step 4:

[0218] The server analyzes the received data using a natural language processing engine. The server uses a natural language processing engine (e.g., OpenAI GPT-4) to analyze the problem text and extract keywords and context. The input data is text data, and the output data is the analysis results, specifically extracted keywords (e.g., "vacuum cleaner," "doesn't work").

[0219] Step 5:

[0220] The server generates or retrieves appropriate answers from a knowledge base or FAQ database. Based on the analysis results, the server searches for relevant information from the knowledge base or FAQ database and generates appropriate answers. The input data is the analysis results, and the output data is the generated answers (e.g., a vacuum cleaner troubleshooting guide).

[0221] Step 6:

[0222] The server sends the generated or retrieved answer back to the terminal. The server generates an HTTP response containing the generated or retrieved answer and sends it back to the terminal. The input data is the generated answer, and the output data is the HTTP response.

[0223] Step 7:

[0224] The device analyzes the received response and displays it visually to the user. The device analyzes the received HTTP response and extracts the response data. The extracted data is displayed to the user in a visually easy-to-understand format such as text, images, and links. The input data is the HTTP response, and the output data is visually displayed information (e.g., a vacuum cleaner troubleshooting guide).

[0225] 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.

[0226] This invention relates to a system for supporting tasks performed by customers after a contract has been signed. This system combines a series of processes—where the user inputs a problem in text format, sends the data to a server, the server analyzes, generates, and returns the answer, and the terminal displays the answer to the user—with an emotion engine that recognizes the user's emotions. This configuration reduces the stress and difficulties the user experiences and provides more appropriate support.

[0227] System Configuration

[0228] 1. The user enters the problem.

[0229] Users use devices such as smartphones or computers to enter the problem they need support for in text format. For example, "I don't know how to transfer data from my smartphone."

[0230] 2. The device sends the request to the server.

[0231] The terminal generates an HTTP request to send the entered text data to the server. This request includes the user's input.

[0232] 3. The server receives the request.

[0233] The server receives an HTTP request sent from the terminal and extracts the user's input from the request body.

[0234] 4. The server analyzes the problem.

[0235] The server uses a natural language processing engine to analyze the received text data. It tokenizes the text and extracts keywords and context.

[0236] 5. The server uses an emotion engine for emotion recognition.

[0237] The server uses an emotion engine to recognize the user's emotions based on the analyzed text data. For example, it can detect feelings of frustration or confusion from text such as "I don't know how to transfer data on my smartphone."

[0238] 6. The server generates or searches for answers.

[0239] Based on the analysis results and sentiment recognition, the server generates an appropriate response to the user's problem or searches its knowledge base or FAQ database. It also adjusts the response's tone and content to match the user's psychological state, reflecting the sentiment recognition results. For example, if the user is highly frustrated, it provides detailed and helpful instructions.

[0240] 7. The server sends the response back to the terminal.

[0241] The server prepares the generated or retrieved response data as an HTTP response and constructs the data to be sent back to the terminal. The response should include specific steps and relevant links.

[0242] 8. The device receives and displays the response.

[0243] The device analyzes the HTTP response received from the server and displays it in a user-friendly format. For example, instructions for migrating data from a smartphone are displayed as text, images, and links. It also displays messages and additional support information that are tailored to the user's emotional state.

[0244] Specific example

[0245] Sentiment Recognition in Data Migration Support

[0246] 1. The user enters the problem.

[0247] User: "I want to transfer my data to my new smartphone, but I don't know how."

[0248] 2. The device sends the request to the server.

[0249] The device sends this request to the server as an HTTP request.

[0250] 3. The server receives the request.

[0251] The server receives the request and extracts the text, "I want to transfer data to my new smartphone, but I don't know how."

[0252] 4. The server analyzes the problem.

[0253] The server uses a natural language processing engine to analyze the keyword "data migration" and understand the user's intent.

[0254] 5. The server uses an emotion engine for emotion recognition.

[0255] The server uses an emotion engine to detect user frustration from the text and determines that the user is likely confused.

[0256] 6. The server generates or searches for answers.

[0257] To alleviate frustration, the server searches its knowledge base for detailed and helpful data migration instructions, along with additional support messages.

[0258] 7. The server sends the response back to the terminal.

[0259] The server sends the generated response data back to the terminal as an HTTP response.

[0260] 8. The device receives and displays the response.

[0261] The device visually displays the received responses. It also displays easy-to-follow instructions and encouraging messages to help users perform data migration while following the steps.

[0262] This system allows users to smoothly complete the necessary tasks after signing a contract, reducing inquiries to stores and increasing user satisfaction. The server's natural language processing and emotion engines enable problem analysis and appropriate psychological responses, providing even more advanced support.

[0263] The following describes the processing flow.

[0264] Step 1:

[0265] Users enter the problem they need support for in text format into an input field on their device, such as a smartphone or computer. For example, they might enter, "I don't know how to transfer data from my smartphone."

[0266] Step 2:

[0267] The terminal receives the entered text data and generates an HTTP request to send it to the server. The request contains the user's input.

[0268] Step 3:

[0269] The device sends the generated HTTP request to the server's API endpoint. This request contains the user's problem and is delivered to the server for analysis.

[0270] Step 4:

[0271] The server receives an HTTP request sent from the terminal. The server extracts the user's input from the request body. For example, it might extract the text "I don't know how to transfer data from my smartphone."

[0272] Step 5:

[0273] The server uses a natural language processing engine to analyze the received text data. It tokenizes the text and extracts keywords and context. For example, it extracts keywords such as "data migration" and "smartphone."

[0274] Step 6:

[0275] The server uses an emotion engine to recognize the user's emotions based on the analyzed text data. For example, the emotion engine detects the user's frustration or confusion from the text, "I don't know how to transfer data from my smartphone."

[0276] Step 7:

[0277] The server generates an appropriate answer to the user's problem based on the results of natural language processing and sentiment recognition, or searches a knowledge base or FAQ database. It then adjusts the tone and content of the answer to match the user's psychological state, reflecting the results of sentiment recognition.

[0278] Step 8:

[0279] The server constructs data for preparing the generated or retrieved answer data as an HTTP response and sending it back to the terminal. The answer should include specific procedures and relevant links.

[0280] Step 9:

[0281] The server sends the prepared answer data to the terminal as an HTTP response. The answer data is sent together with a status code (e.g., 200 OK).

[0282] Step 10:

[0283] The terminal receives the HTTP response from the server. It analyzes the answer data from the response body and prepares it for display to the user.

[0284] Step 11:

[0285] The terminal visually displays the received answer data to the user. For example, it is displayed in a visually understandable form such as text, images, links, etc., and is available for the user to use. Messages corresponding to the user's emotional state and additional support information are also displayed.

[0286] The above is the specific process of the processing in the support system combined with the emotion engine that recognizes the user's emotion.

[0287] (Example 2)

[0288] Next, Example 2 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart device 14 is referred to as the "terminal".

[0289] Traditional support systems often fail to adequately mitigate the stress and difficulties users experience, resulting in inadequate support. In particular, providing answers that disregard the user's feelings can exacerbate their dissatisfaction and confusion. Therefore, a system is needed that can properly analyze user problems and provide support tailored to their emotional needs.

[0290] 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.

[0291] In this invention, the server includes means for analyzing received data and analyzing the problem content using a natural language processing engine, means for recognizing the user's emotions using an emotion engine, and means for querying a knowledge base or FAQ database to search for an appropriate answer and adjusting the content according to the user's emotions. This makes it possible to accurately understand the user's problem and provide an answer that takes their emotions into consideration.

[0292] A "user" refers to an individual or legal entity that attempts to resolve a problem using the support system.

[0293] A "problem" refers to an issue or question that a user wants to resolve, and the content of that issue.

[0294] "Text format" refers to a format in which input is presented as a string of characters.

[0295] "Terminal" refers to computing devices such as computers, smartphones, and tablets used by users.

[0296] A "server" refers to a computer device that receives and processes information sent from a user's terminal.

[0297] "Analysis" refers to the process by which a server interprets the data it receives and understands its meaning.

[0298] The "Natural Language Processing Engine" refers to software for analyzing text data and extracting keywords and context.

[0299] The "Emotion Engine" refers to software for recognizing emotions from the user's text data.

[0300] The "Knowledge Base" refers to a database that accumulates information and solutions related to the user's questions.

[0301] The "FAQ Database" refers to a database that summarizes frequently asked questions and their answers.

[0302] The "HTTP Request" refers to a protocol for a terminal to send information to a server.

[0303] The "HTTP Response" refers to a protocol for a server to return information to a terminal.

[0304] "Tokenization" refers to the process of splitting text into the smallest meaningful units.

[0305] The "Prompt Sentence" refers to a sentence for expressing questions or instructions input by the user.

[0306] The "Generative AI Model" refers to an artificial intelligence model that performs natural language processing and generates text according to specific tasks.

[0307] The present invention relates to a system for supporting the work performed by customers after a contract. This system performs a series of processes in which the user inputs a problem in text form, sends the text data to the server, the server analyzes the data, generates or searches for an appropriate answer, returns the answer to the terminal, and finally the terminal displays the answer to the user. Furthermore, by combining an emotion engine that recognizes the user's emotions, more appropriate support can be provided.

[0308] Hardware and Software to be Used

[0309] hardware

[0310] Devices: PCs, smartphones, tablets, etc.

[0311] Server: A high-performance computing device (equipped with a CPU, memory, and storage).

[0312] software

[0313] Natural language processing engines: SpaCy, NLTK, etc.

[0314] Emotion engines: IBM Watson, Microsoft® Azure® Text Analytics, etc.

[0315] Knowledge base / FAQ database: Zendesk, Freshdesk, etc.

[0316] Generative AI models: GPT-3, etc.

[0317] Communication protocol: HTTP / HTTPS.

[0318] System Configuration

[0319] This system was configured as follows:

[0320] 1. The user enters the problem.

[0321] Users use devices such as smartphones or computers to enter the problem they need support for in text format. Specifically, they type "I don't know how to transfer data from my smartphone" into the text box and click the submit button.

[0322] 2. The device sends the request to the server.

[0323] The device sends the text data entered by the user to the server as an HTTP request. Specifically, it uses the HTTP POST method to generate an HTTP request that includes the text data in the request body and sends it to the server's API endpoint.

[0324] 3. The server receives the request.

[0325] The server receives HTTP requests sent from the terminal and extracts user input from the request body. Specifically, it uses a web framework (e.g., Django, Flask) to parse the request data and extract the text.

[0326] 4. The server analyzes the problem.

[0327] The server analyzes the received text data using a natural language processing engine (e.g., SpaCy). For example, it analyzes the text "I don't know how to transfer data from my smartphone" and extracts keywords and context such as "data transfer."

[0328] 5. The server uses an emotion engine for emotion recognition.

[0329] The server uses an emotion engine (e.g., IBM Watson) based on the analyzed text data to recognize the user's emotions. For example, it can detect user frustration from text such as "I don't know how to transfer data from my smartphone."

[0330] 6. The server generates or searches for answers.

[0331] The server searches for appropriate answers from knowledge bases and FAQ databases (e.g., Zendesk) based on the analysis results and sentiment recognition results. Alternatively, it uses generative AI models (e.g., GPT-3) to generate customized answers. The answers are tailored to the user's emotional state. For example, if the user is feeling frustrated, an answer with detailed and helpful instructions will be provided.

[0332] 7. The server sends the response back to the terminal.

[0333] The server prepares the generated or retrieved answer data as an HTTP response and sends it back to the terminal. Specifically, it formats the answer data in JSON format and sends it as an HTTP response.

[0334] 8. The device receives and displays the response.

[0335] The device analyzes the HTTP response received from the server and displays it in a format that is easy for the user to understand. Specifically, it formats the received data as text, images, and links and displays them to the user. For example, "Smartphone Data Migration Procedure" is displayed step by step. Encouraging messages tailored to the user's emotions are also displayed.

[0336] Specific example

[0337] Sentiment Recognition in Data Migration Support

[0338] 1. The user enters the problem.

[0339] User: "I want to transfer my data to my new smartphone, but I don't know how."

[0340] 2. The device sends the request to the server.

[0341] The device sends this request to the server as an HTTP request.

[0342] 3. The server receives the request.

[0343] The server receives the request and extracts the text, "I want to transfer data to my new smartphone, but I don't know how."

[0344] 4. The server analyzes the problem.

[0345] The server uses a natural language processing engine to analyze the keyword "data migration" and understand the user's intent.

[0346] 5. The server uses an emotion engine for emotion recognition.

[0347] The server uses an emotion engine to detect user frustration from the text and determines that the user is likely confused.

[0348] 6. The server generates or searches for answers.

[0349] To alleviate frustration, the server searches its knowledge base for detailed and helpful data migration instructions, along with additional support messages.

[0350] 7. The server sends the response back to the terminal.

[0351] The server sends the generated response data back to the terminal as an HTTP response.

[0352] 8. The device receives and displays the response.

[0353] The device visually displays the received responses. It also displays easy-to-understand instructions and encouraging messages so that users can perform the data migration while following the steps.

[0354] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0355] Step 1:

[0356] The user enters the problem.

[0357] Input: The user enters the problem they need support for in text format (e.g., "I don't know how to transfer data from my smartphone").

[0358] Specific actions: The user uses a smartphone or computer, enters the question into a text box, and clicks the submit button.

[0359] Output: Text data entered into the terminal.

[0360] Step 2:

[0361] The device sends the request to the server.

[0362] Input: Text data entered by the user.

[0363] Specific operation: The terminal sends the entered text data to the server as an HTTP POST request. Specifically, it includes the entered text data in the request body and sends it to the server's API endpoint.

[0364] Output: HTTP request sent to the server.

[0365] Step 3:

[0366] The server receives the request.

[0367] Input: HTTP request sent from the terminal.

[0368] Specific operation: The server uses a web framework to receive HTTP requests and extracts user input text from the request body.

[0369] Output: Extracted text data.

[0370] Step 4:

[0371] The server analyzes the problem.

[0372] Input: Extracted text data.

[0373] Specific operation: The server calls a natural language processing engine (e.g., SpaCy) to parse and tokenize the text data, and extract keywords and context. Specifically, it extracts the keyword "data migration" from the text "I don't know how to migrate data on my smartphone."

[0374] Output: Extracted keywords and context.

[0375] Step 5:

[0376] The server uses an emotion engine for emotion recognition.

[0377] Input: Extracted keywords or context.

[0378] Specific operation: The server invokes an emotion engine (e.g., IBM Watson) to recognize emotions such as frustration and confusion from the user's text data. For example, it might detect frustration from the phrase "I don't know how to transfer data from my smartphone."

[0379] Output: Recognized emotion data.

[0380] Step 6:

[0381] The server generates or searches for answers.

[0382] Input: Recognized sentiment data and extracted keywords or context.

[0383] Specific operation: The server queries a knowledge base or FAQ database to find the appropriate answer, or generates an answer using a generative AI model (e.g., GPT-3). Based on sentiment data, it adjusts the content and tone of the answer. For example, it provides detailed and courteous data migration instructions.

[0384] Output: Generated or retrieved response data.

[0385] Step 7:

[0386] The server sends the response back to the terminal.

[0387] Input: Generated or retrieved response data.

[0388] Specific operation: The server formats the generated response data in JSON format and sends it to the terminal as an HTTP response.

[0389] Output: HTTP response sent to the terminal.

[0390] Step 8:

[0391] The device receives and displays the response.

[0392] Input: HTTP response sent from the server.

[0393] Specific operation: The terminal analyzes the received response data and displays it to the user in an easy-to-understand format. Specifically, it formats it as text, images, and links to visually display data migration procedures and encouraging messages.

[0394] Output: User-recognizable response information.

[0395] (Application Example 2)

[0396] 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 device 14 will be referred to as the "terminal."

[0397] Traditional support systems were limited to basic functions such as users entering problems and receiving answers. However, this often failed to adequately alleviate the stress and difficulties users experienced. In particular, failing to consider the emotions users felt regarding the problems they faced meant that the support provided often did not fully meet their needs, making it difficult to increase user satisfaction. Current systems require the provision of specific and emotionally responsive support aimed at resolving problems.

[0398] 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.

[0399] In this invention, the server includes means for the user to input a problem in text format, means for the terminal to transmit the input text data to the server, means for the server to analyze the received data and generate or retrieve an appropriate answer, means for the server to return the generated or retrieved answer to the terminal, means for the terminal to visually display the received answer to the user, and means for the server to recognize the user's emotions using an emotion recognition engine and adjust the answer based on the result. This enables the provision of detailed support that responds to the user's emotions, and allows for quick and effective problem solving.

[0400] A "user" refers to an end-user who enters a problem and requests support.

[0401] "Text format" refers to a method of representing information using character data.

[0402] "Device" refers to a device used by a user, such as a smartphone, tablet, or personal computer.

[0403] A "server" refers to a computer system that processes requests sent by users, generates or searches for appropriate answers, and sends them back to the terminal.

[0404] "Analysis" refers to the process of understanding received data and identifying its meaning and intent.

[0405] "Generating or searching" refers to the act of creating a new, appropriate answer or finding suitable information from an existing knowledge base or database.

[0406] "Returning" refers to the act of sending a response generated or retrieved by the server to the terminal.

[0407] "Visual display" refers to methods of providing information to users using text, images, icons, etc.

[0408] An "emotion recognition engine" refers to a software component that detects a user's emotions from text data and takes appropriate action based on the results.

[0409] A "natural language processing engine" refers to a software component that analyzes text data and understands its meaning and intent.

[0410] A "knowledge base" refers to a database containing information and answers that have been stored in advance.

[0411] An "FAQ database" refers to a database containing frequently asked questions and their answers.

[0412] This invention is a system for quickly resolving problems that users face in food delivery services. Specific embodiments of this system are described below.

[0413] First, users use a device such as a smartphone or computer to input their problem in text format. For example, they describe the problem they are facing specifically, such as, "My delivery is delayed, but I don't know what to do."

[0414] The text data entered by the user is sent from the terminal to the server. This communication is performed using HTTP requests. The data received by the server is first parsed by a natural language processing engine to understand its content. Specifically, the text data is tokenized, and keywords and context are extracted.

[0415] Next, the server uses an emotion recognition engine to recognize emotions from the user's input. IBM Watson Tone Analyzer, for example, can be used as this emotion recognition engine. The user's emotional state is identified from the analysis results. For example, from the input "The delivery is delayed," the user's anxiety or frustration might be detected.

[0416] The server then generates or searches its knowledge base or FAQ database for an appropriate answer to the user's problem. At this stage, the tone and content of the answer are adjusted to match the user's psychological state, taking into account the results of sentiment recognition. For example, if the user is feeling frustrated, the server will provide very polite and specific instructions.

[0417] Once the answer is confirmed, the server sends it back to the terminal. The terminal then displays the received answer to the user visually. This display method may include text, images, links, etc.

[0418] As a concrete example, consider a case where a user enters "My delivery is delayed, and I don't know what to do." The emotion recognition engine recognizes the user's frustration, and the server generates a polite message such as, "We will look into this immediately, please wait a moment." This enables a more personalized response tailored to the user's emotions, improving user satisfaction.

[0419] Furthermore, examples of prompt statements to be input to the generative AI model are as follows:

[0420] "A user typed, 'My delivery is very late, what should I do?' Please provide an appropriate response that reflects their feelings."

[0421] In this way, this invention provides a system for food delivery services that enables quick and effective problem solving while taking into consideration the user's feelings.

[0422] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0423] Step 1:

[0424] The user enters the problem in text format.

[0425] Users use devices such as smartphones and computers to input specific problems in text, such as "My delivery is delayed, and I don't know what to do." They may also describe their anxieties and frustrations in detail.

[0426] Input: Text format issue from user

[0427] Output: Saving text data to the terminal

[0428] Step 2:

[0429] The terminal sends the entered text data to the server.

[0430] The terminal generates an HTTP request and sends the entered text data to the server. This request includes the user's input and is sent to the server in the appropriate format.

[0431] Input: Text data saved on the device

[0432] Output: HTTP request to the server

[0433] Step 3:

[0434] The server analyzes the data it receives.

[0435] The server receives an HTTP request and extracts text data from its body. This text data is then input into a natural language processing engine for tokenization, keyword extraction, and contextual analysis.

[0436] Input: Text data extracted from an HTTP request

[0437] Output: Analyzed keywords and contextual information

[0438] Step 4:

[0439] The server uses an emotion recognition engine to recognize the user's emotions.

[0440] Text data analyzed using natural language processing is passed to an emotion recognition engine to detect the user's emotions. For example, emotions such as "frustration" or "confusion" can be identified. IBM Watson Tone Analyzer can be used as the emotion recognition engine.

[0441] Input: Parsed text data

[0442] Output: Emotion recognition result (e.g., frustration)

[0443] Step 5:

[0444] The server generates the appropriate answer or searches for it in the knowledge base or FAQ database.

[0445] The server uses the emotion recognition results and analyzed text data to generate an appropriate response or search for relevant information in existing knowledge bases or FAQ databases. It prepares responses that include the appropriate tone and content for the emotion.

[0446] Input: Analyzed text data and sentiment recognition results

[0447] Output: Generated answers or search results from the database

[0448] Step 6:

[0449] The server sends the generated or retrieved answer back to the terminal.

[0450] The server prepares the response as an HTTP response and sends it back to the terminal. The response is structured in a format that is easily understandable to the user.

[0451] Input: Generated or retrieved response data

[0452] Output: HTTP response

[0453] Step 7:

[0454] The device visually displays the received response to the user.

[0455] The device receives an HTTP response, parses its contents, and displays them visually to the user. The display format includes text, images, and links. Messages tailored to the user's emotional state are also displayed.

[0456] Input: Response data extracted from HTTP response

[0457] Output: A display that the user can visually confirm.

[0458] 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.

[0459] 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.

[0460] 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.

[0461] [Second Embodiment]

[0462] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0463] 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.

[0464] 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).

[0465] 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.

[0466] 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.

[0467] 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).

[0468] 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.

[0469] 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.

[0470] 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.

[0471] 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.

[0472] 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.

[0473] 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".

[0474] This invention relates to a system for supporting tasks performed by customers after a contract has been signed. This system enables a series of processes in which the user inputs a problem in text format, sends the data to a server, the server analyzes the data, generates an answer, sends the answer back, and the terminal displays the answer to the user.

[0475] System Configuration

[0476] 1. The user enters the problem.

[0477] Users use devices such as smartphones or computers to enter the problem they need support for in text format. For example, they might enter a specific problem such as, "I don't know how to transfer data from my smartphone."

[0478] 2. The device sends the request to the server.

[0479] The terminal generates an HTTP request to send the entered text data to the server. This request includes the user's problem description.

[0480] 3. The server receives the request.

[0481] The server receives an HTTP request sent from the terminal. After receiving it, it extracts the user's problem details from the request body.

[0482] 4. The server analyzes the problem.

[0483] The server uses a natural language processing engine to analyze the text data entered by the user. Through this analysis, it extracts keywords and context to understand the user's problem.

[0484] 5. The server generates or searches for answers.

[0485] The server generates an appropriate answer to the user's problem based on the analysis results, or searches for an appropriate answer from a knowledge base or FAQ database. For example, it searches for and retrieves instructions on "how to transfer data from a smartphone."

[0486] 6. The server sends the response back to the terminal.

[0487] The server returns the generated or retrieved response data to the terminal as an HTTP response. This response data includes specific steps, links, and relevant resources for solving the problem.

[0488] 7. The device receives and displays the response.

[0489] The device analyzes the response received from the server and displays it in a format that is easy for the user to understand. For example, the procedure for transferring data from a smartphone might be displayed as text, images, and links.

[0490] Specific example

[0491] Data migration support

[0492] 1. The user enters the problem.

[0493] User: "I want to transfer my data to my new smartphone."

[0494] 2. The device sends the request to the server.

[0495] The device sends this request to the server as an HTTP request.

[0496] 3. The server receives the request.

[0497] The server receives the request and extracts the text, "I want to transfer data to a new smartphone."

[0498] 4. The server analyzes the problem.

[0499] The server uses a natural language processing engine to analyze the keyword "data migration" and understand the user's intent.

[0500] 5. The server generates or searches for answers.

[0501] The server searches the knowledge base for "Smartphone Data Migration Procedure" and generates the relevant information.

[0502] 6. The server sends the response back to the terminal.

[0503] The server sends the generated response data back to the terminal as an HTTP response.

[0504] 7. The device receives and displays the response.

[0505] The device visually displays the received responses, allowing the user to perform data migration while following the instructions.

[0506] This system allows users to smoothly complete the necessary tasks after signing a contract, reducing inquiries to stores and increasing user satisfaction. Furthermore, the server's natural language processing engine improves the accuracy of problem analysis, enabling the rapid provision of appropriate answers.

[0507] The following describes the processing flow.

[0508] Step 1:

[0509] Users enter the problem they need support for in text format into an input field on their device, such as a smartphone or computer. For example, "I don't know how to transfer data from my smartphone."

[0510] Step 2:

[0511] The terminal receives the text data entered by the user and generates an HTTP request to send to the server. The request includes the user's input.

[0512] Step 3:

[0513] The device sends the generated HTTP request to the server's API endpoint. This request contains the user's problem and is delivered to the server for analysis.

[0514] Step 4:

[0515] The server receives an HTTP request sent from the terminal. The server extracts the user's input from the request body. Example: "I don't know how to transfer data from my smartphone."

[0516] Step 5:

[0517] The server uses a natural language processing engine to analyze the received text data. It tokenizes the text and extracts keywords and context. For example, it extracts keywords such as "data migration" and "smartphone."

[0518] Step 6:

[0519] Based on the analysis results, the server generates an answer suitable for the user's problem or searches the knowledge base or FAQ database. For example, it searches the knowledge base for "Smartphone data migration procedure".

[0520] Step 7:

[0521] The server prepares the generated or retrieved answers as HTTP responses and constructs the data to send back to the terminal. The answers should include specific instructions and relevant links.

[0522] Step 8:

[0523] The server returns the prepared response data to the terminal as an HTTP response. The response data is sent along with a status code (e.g., 200 OK).

[0524] Step 9:

[0525] The terminal receives an HTTP response from the server. It parses the response body and prepares the data for display to the user.

[0526] Step 10:

[0527] The device displays the received response data to the user. This data is displayed in a visually easy-to-understand format, such as text, images, and links, making it accessible to the user. For example, a data migration procedure manual is displayed, allowing the user to migrate data from their smartphone by following the instructions.

[0528] The above outlines the specific processing flow within the customer support system after the contract is signed.

[0529] (Example 1)

[0530] 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."

[0531] Traditional support systems often resulted in long waiting times between users entering a problem and receiving a solution, and sometimes even inadequate answers. This led to decreased user satisfaction and an increase in inquiries to the support center.

[0532] 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.

[0533] In this invention, the server includes means for an input form and a submit button for the user to enter a problem; means for the terminal to generate an HTTP request and send it to the server's endpoint; means for the server to extract the user's problem details from the request body; means for understanding the user's problem using a natural language processing engine; and means for searching for an answer by referring to a knowledge base or FAQ database. This enables the user to obtain an answer for problem resolution quickly and accurately, reduces inquiries to the support center, and improves user satisfaction.

[0534] A "user" refers to an individual or legal entity that uses a support system to input a problem and seek a solution.

[0535] "Device" refers to electronic devices used by users, such as smartphones, personal computers, and tablets.

[0536] A "server" refers to a remote computer that receives and processes requests sent by users.

[0537] An "input form" refers to an online input field where a user enters a question in text format.

[0538] The term "send button" refers to an interface element used to send entered text data to the server.

[0539] An "HTTP request" refers to a type of internet communication protocol used to send data from a user's device to a server.

[0540] An "endpoint" refers to an address, such as a URL or URI, that is accessible on a server to provide a specific function or service.

[0541] The "request body" refers to the data contained in the message portion of an HTTP request.

[0542] A "natural language processing engine" refers to software and technology that allows computers to understand and analyze human language.

[0543] A "knowledge base" refers to a database system that stores and makes searchable past information and data.

[0544] An "FAQ database" refers to a database that compiles frequently asked questions and their answers.

[0545] "HTTP response" refers to a type of internet communication protocol used by a server to send a response to a user's device.

[0546] This invention relates to a system for supporting tasks performed by customers after a contract has been signed. This system enables a series of processes in which the user inputs a problem in text format, sends the data to a server, the server analyzes the data, generates an answer, sends the answer back, and the terminal displays the answer to the user.

[0547] System Configuration

[0548] 1. The user enters the problem.

[0549] Users use devices such as smartphones or computers to enter the problem they need support for in text format. For example, they might enter a specific problem such as, "I want to transfer data to my new smartphone."

[0550] 2. The device sends the request to the server.

[0551] The terminal generates an HTTP request to send the entered text data to the server. This request includes the user's problem description.

[0552] 3. The server receives the request.

[0553] The server receives an HTTP request sent from the terminal. After receiving it, it extracts the user's problem details from the request body.

[0554] 4. The server analyzes the problem.

[0555] The server uses a natural language processing engine (e.g., Google Cloud Natural Language API or OpenAI's GPT-3) to analyze the text data entered by the user. Through this analysis, keywords and context are extracted to understand the user's problem.

[0556] 5. The server generates or searches for answers.

[0557] The server generates an appropriate answer to the user's problem based on the analysis results. Alternatively, it searches for the appropriate answer from a knowledge base or FAQ database (e.g., Zendesk). For example, it searches for and retrieves instructions on "how to transfer data from a smartphone."

[0558] 6. The server sends the response back to the terminal.

[0559] The server returns the generated or retrieved response data to the terminal as an HTTP response. This response data includes specific steps, links, and relevant resources for solving the problem.

[0560] 7. The device receives and displays the response.

[0561] The device analyzes the response received from the server and displays it in a format that is easy for the user to understand. For example, the procedure for transferring data from a smartphone might be displayed as text, images, and links.

[0562] Specific example

[0563] Data migration support

[0564] 1. The user enters the problem.

[0565] User: "I want to transfer my data to my new smartphone."

[0566] 2. The device sends the request to the server.

[0567] The device sends this request to the server as an HTTP request.

[0568] 3. The server receives the request.

[0569] The server receives the request and extracts the text, "I want to transfer data to a new smartphone."

[0570] 4. The server analyzes the problem.

[0571] The server uses a natural language processing engine to analyze the keyword "data migration" and understand the user's intent.

[0572] 5. The server generates or searches for answers.

[0573] The server searches the knowledge base for "Smartphone Data Migration Procedure" and generates the relevant information.

[0574] 6. The server sends the response back to the terminal.

[0575] The server sends the generated response data back to the terminal as an HTTP response.

[0576] 7. The device receives and displays the response.

[0577] The device visually displays the received responses, allowing the user to perform data migration while following the instructions.

[0578] This system allows users to smoothly complete the necessary tasks after signing a contract, reducing inquiries to stores and increasing user satisfaction. Furthermore, the server's natural language processing engine improves the accuracy of problem analysis, enabling the rapid provision of appropriate answers.

[0579] Example of a prompt

[0580] "Please tell me how to transfer data to a new smartphone."

[0581] By inputting this prompt into the generating AI model, specific and appropriate support content will be provided.

[0582] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0583] Step 1: The user enters the problem.

[0584] Users use their own devices (smartphones or computers) to enter the problem they need support for in text format. Specifically, they type "I want to transfer data to a new smartphone" into the input form on their browser and click the submit button. This action generates text as input data.

[0585] Step 2: The device sends the request to the server.

[0586] The terminal generates an HTTP POST request to send the entered text data to the server. This request contains the problem details entered by the user. Specifically, the browser captures the user's input, stores it in the request body, and sends it to the specified server endpoint.

[0587] Step 3: The server receives the request.

[0588] The server receives an HTTP request sent from the terminal. The request contains text data entered by the user. The server extracts the text "I want to transfer data to a new smartphone" from the request body. Specifically, a web server that processes HTTP requests (such as Apache or Nginx) receives the request and parses its contents.

[0589] Step 4: The server analyzes the problem.

[0590] The server uses a natural language processing engine (such as Google Cloud Natural Language API or OpenAI's GPT-3) to analyze the text data entered by the user. Based on the analysis, keywords and context are extracted to understand the user's intent. Specifically, the extracted text data is passed to the natural language processing engine, which then extracts keywords such as "data migration" and "smartphone."

[0591] Step 5: The server generates or searches for an answer.

[0592] The server generates appropriate answers to the user's problem based on the analysis results. Alternatively, it searches for appropriate answers in a knowledge base or FAQ database (e.g., Zendesk). Specifically, it queries the knowledge base for "smartphone data migration procedure" and retrieves relevant procedures and answers. It also utilizes a generative AI model to generate answers as needed.

[0593] Step 6: The server sends the response back to the terminal.

[0594] The server returns the generated or retrieved answer data to the terminal as an HTTP response. The response data includes specific steps for solving the problem and relevant links. Specifically, the server formats the retrieved or generated answer as an HTTP response and sends it to the user's terminal.

[0595] Step 7: The device receives and displays the response.

[0596] The device analyzes the response received from the server and displays it in a format that is easy for the user to understand. Specifically, the browser receives the HTTP response from the server and displays it as text, images, and links. For example, "Smartphone data migration procedure" might be displayed in bullet points, along with links to related support pages.

[0597] (Application Example 1)

[0598] 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."

[0599] Traditional text-based customer support systems have the challenge of not being able to respond quickly and accurately to user problems. As a result, users do not receive adequate support, which in turn leads to decreased customer satisfaction. Furthermore, there was a need for a system that efficiently provides support information to resolve issues related to products purchased by users on e-commerce sites and other platforms.

[0600] 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.

[0601] In this invention, the server includes means for parsing queries and generating or retrieving appropriate answers from a knowledge base or FAQ database, means for returning the generated or retrieved answers to the terminal, and means for the terminal to visually display the answers. This makes it possible to efficiently resolve user problems and improve customer satisfaction.

[0602] 1. A "user" is someone who attempts to solve a problem using the system.

[0603] 2. "Text format" refers to a format that uses character data to represent information.

[0604] 3. "Terminal" refers to a device such as a computer or smartphone used by a user.

[0605] 4. A "server" is a computer system that receives requests from terminals and performs analysis and generates responses.

[0606] 5. A "natural language processing engine" is a software technology used to analyze text data and understand its meaning.

[0607] 6. A "knowledge base" is a database in which solutions to problems are systematically compiled.

[0608] 7. An "FAQ database" is a database that compiles frequently asked questions and their answers.

[0609] 8. An "HTTP request" is one of the protocols used to exchange data between a client and a server.

[0610] 9. "Answer generation" is the process of creating appropriate solutions to the analyzed problem.

[0611] 10. "Searching" is the process of finding the desired information from a database.

[0612] 11. "Visual display" refers to the process of providing information to users in an easily understandable format.

[0613] This invention is a system designed to support tasks performed by customers after a contract has been signed. It enables a series of processes in which the user inputs a problem in text format, sends that data to a server, the server analyzes it, generates an answer, sends the answer back, and the terminal displays the answer to the user.

[0614] Hardware and software to use

[0615] Hardware:

[0616] smartphone

[0617] Cloud Server

[0618] software:

[0619] Mobile app frameworks (React Native, Flutter, etc.)

[0620] Server-side frameworks (Node.js, Django, etc.)

[0621] Natural language processing engines (Google NLP, IBM Watson, OpenAI GPT-4, etc.)

[0622] System Overview

[0623] 1. The user enters the problem.

[0624] Users enter their problems in text format using a smartphone application. An example of such a problem is, "My new vacuum cleaner isn't working."

[0625] 2. The device sends a problem.

[0626] The smartphone sends the user-entered question to the server as an HTTP request. The request includes the text data entered by the user.

[0627] 3. The server receives and parses the request.

[0628] After receiving an HTTP request, the server uses a natural language processing engine to analyze the text data. Through this analysis, it extracts keywords and context related to the problem, thereby understanding its content.

[0629] 4. The server generates or searches for answers.

[0630] Based on the analysis results, the server generates or searches for appropriate answers from the knowledge base or FAQ database. For example, it searches for and retrieves troubleshooting information for a case where "the new vacuum cleaner isn't working."

[0631] 5. The server sends the response.

[0632] The server returns the generated or retrieved response data to the terminal as an HTTP response. The response data includes specific steps and related resources.

[0633] 6. The device displays the answer.

[0634] The smartphone analyzes the received response and displays it in a format that is easy for the user to understand. For example, it may display it in the form of text, images, or video links.

[0635] Specific example

[0636] When a user enters "My new vacuum cleaner isn't working," the following process is executed.

[0637] 1. User enters the problem: "My new vacuum cleaner isn't working."

[0638] 2. The device sends the request to the server.

[0639] 3. The server receives the request and analyzes the problem.

[0640] 4. Use a natural language processing engine to extract the keywords "vacuum cleaner" and "not working".

[0641] 5. Search for information on "vacuum cleaner troubleshooting" in the knowledge base or FAQ database.

[0642] 6. The server generates an appropriate response and sends it back to the terminal.

[0643] 7. Smartphones visually display the answers.

[0644] Example of a prompt

[0645] "The vacuum cleaner I recently bought isn't working at all. What should I do?"

[0646] As described above, this system enables users to efficiently resolve problems they face after signing a contract, thereby contributing to improved customer satisfaction.

[0647] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0648] Step 1:

[0649] The user enters the problem in text format. The user uses a smartphone application to enter the problem into a text box. For example, the user might enter "My new vacuum cleaner isn't working." The input data is saved in text format.

[0650] Step 2:

[0651] The terminal sends the entered text data to the server. The terminal generates an HTTP POST request containing the entered text data and sends it to the server. The input data is sent to the server, and an HTTP request is generated as output data from the terminal.

[0652] Step 3:

[0653] The server receives the request. The server receives the HTTP request and extracts the text data entered by the user from its body. The input data is the HTTP request, and the output data is the extracted problem text.

[0654] Step 4:

[0655] The server analyzes the received data using a natural language processing engine. The server uses a natural language processing engine (e.g., OpenAI GPT-4) to analyze the problem text and extract keywords and context. The input data is text data, and the output data is the analysis results, specifically extracted keywords (e.g., "vacuum cleaner," "doesn't work").

[0656] Step 5:

[0657] The server generates or retrieves appropriate answers from a knowledge base or FAQ database. Based on the analysis results, the server searches for relevant information from the knowledge base or FAQ database and generates appropriate answers. The input data is the analysis results, and the output data is the generated answers (e.g., a vacuum cleaner troubleshooting guide).

[0658] Step 6:

[0659] The server sends the generated or retrieved answer back to the terminal. The server generates an HTTP response containing the generated or retrieved answer and sends it back to the terminal. The input data is the generated answer, and the output data is the HTTP response.

[0660] Step 7:

[0661] The device analyzes the received response and displays it visually to the user. The device analyzes the received HTTP response and extracts the response data. The extracted data is displayed to the user in a visually easy-to-understand format such as text, images, and links. The input data is the HTTP response, and the output data is visually displayed information (e.g., a vacuum cleaner troubleshooting guide).

[0662] 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.

[0663] This invention relates to a system for supporting tasks performed by customers after a contract has been signed. This system combines a series of processes—where the user inputs a problem in text format, sends the data to a server, the server analyzes, generates, and returns the answer, and the terminal displays the answer to the user—with an emotion engine that recognizes the user's emotions. This configuration reduces the stress and difficulties the user experiences and provides more appropriate support.

[0664] System Configuration

[0665] 1. The user enters the problem.

[0666] Users use devices such as smartphones or computers to enter the problem they need support for in text format. For example, "I don't know how to transfer data from my smartphone."

[0667] 2. The device sends the request to the server.

[0668] The terminal generates an HTTP request to send the entered text data to the server. This request includes the user's input.

[0669] 3. The server receives the request.

[0670] The server receives an HTTP request sent from the terminal and extracts the user's input from the request body.

[0671] 4. The server analyzes the problem.

[0672] The server uses a natural language processing engine to analyze the received text data. It tokenizes the text and extracts keywords and context.

[0673] 5. The server uses an emotion engine for emotion recognition.

[0674] The server uses an emotion engine to recognize the user's emotions based on the analyzed text data. For example, it can detect feelings of frustration or confusion from text such as "I don't know how to transfer data on my smartphone."

[0675] 6. The server generates or searches for answers.

[0676] Based on the analysis results and sentiment recognition, the server generates an appropriate response to the user's problem or searches its knowledge base or FAQ database. It also adjusts the response's tone and content to match the user's psychological state, reflecting the sentiment recognition results. For example, if the user is highly frustrated, it provides detailed and helpful instructions.

[0677] 7. The server sends the response back to the terminal.

[0678] The server prepares the generated or retrieved response data as an HTTP response and constructs the data to be sent back to the terminal. The response should include specific steps and relevant links.

[0679] 8. The device receives and displays the response.

[0680] The device analyzes the HTTP response received from the server and displays it in a user-friendly format. For example, instructions for migrating data from a smartphone are displayed as text, images, and links. It also displays messages and additional support information that are tailored to the user's emotional state.

[0681] Specific example

[0682] Sentiment Recognition in Data Migration Support

[0683] 1. The user enters the problem.

[0684] User: "I want to transfer my data to my new smartphone, but I don't know how."

[0685] 2. The device sends the request to the server.

[0686] The device sends this request to the server as an HTTP request.

[0687] 3. The server receives the request.

[0688] The server receives the request and extracts the text, "I want to transfer data to my new smartphone, but I don't know how."

[0689] 4. The server analyzes the problem.

[0690] The server uses a natural language processing engine to analyze the keyword "data migration" and understand the user's intent.

[0691] 5. The server uses an emotion engine for emotion recognition.

[0692] The server uses an emotion engine to detect user frustration from the text and determines that the user is likely confused.

[0693] 6. The server generates or searches for answers.

[0694] To alleviate frustration, the server searches its knowledge base for detailed and helpful data migration instructions, along with additional support messages.

[0695] 7. The server sends the response back to the terminal.

[0696] The server sends the generated response data back to the terminal as an HTTP response.

[0697] 8. The device receives and displays the response.

[0698] The device visually displays the received responses. It also displays easy-to-follow instructions and encouraging messages to help users perform data migration while following the steps.

[0699] This system allows users to smoothly complete the necessary tasks after signing a contract, reducing inquiries to stores and increasing user satisfaction. The server's natural language processing and emotion engines enable problem analysis and appropriate psychological responses, providing even more advanced support.

[0700] The following describes the processing flow.

[0701] Step 1:

[0702] Users enter the problem they need support for in text format into an input field on their device, such as a smartphone or computer. For example, they might enter, "I don't know how to transfer data from my smartphone."

[0703] Step 2:

[0704] The terminal receives the entered text data and generates an HTTP request to send it to the server. The request contains the user's input.

[0705] Step 3:

[0706] The device sends the generated HTTP request to the server's API endpoint. This request contains the user's problem and is delivered to the server for analysis.

[0707] Step 4:

[0708] The server receives an HTTP request sent from the terminal. The server extracts the user's input from the request body. For example, it might extract the text "I don't know how to transfer data from my smartphone."

[0709] Step 5:

[0710] The server uses a natural language processing engine to analyze the received text data. It tokenizes the text and extracts keywords and context. For example, it extracts keywords such as "data migration" and "smartphone."

[0711] Step 6:

[0712] The server uses an emotion engine to recognize the user's emotions based on the analyzed text data. For example, the emotion engine detects the user's frustration or confusion from the text, "I don't know how to transfer data from my smartphone."

[0713] Step 7:

[0714] The server generates an appropriate answer to the user's problem based on the results of natural language processing and sentiment recognition, or searches a knowledge base or FAQ database. It then adjusts the tone and content of the answer to match the user's psychological state, reflecting the results of sentiment recognition.

[0715] Step 8:

[0716] The server prepares the generated or retrieved response data as an HTTP response and constructs the data to be sent back to the terminal. The response should include specific steps and relevant links.

[0717] Step 9:

[0718] The server returns the prepared response data to the terminal as an HTTP response. The response data is sent along with a status code (e.g., 200 OK).

[0719] Step 10:

[0720] The terminal receives an HTTP response from the server. It parses the response body and prepares the data for display to the user.

[0721] Step 11:

[0722] The device visually displays the received response data to the user. For example, it may be displayed in a visually easy-to-understand format such as text, images, and links, making it accessible to the user. It also displays messages and additional support information that correspond to the user's emotional state.

[0723] The above outlines the specific processing flow in a support system that incorporates an emotion engine to recognize user emotions.

[0724] (Example 2)

[0725] 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".

[0726] Traditional support systems often fail to adequately mitigate the stress and difficulties users experience, resulting in inadequate support. In particular, providing answers that disregard the user's feelings can exacerbate their dissatisfaction and confusion. Therefore, a system is needed that can properly analyze user problems and provide support tailored to their emotional needs.

[0727] 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.

[0728] In this invention, the server includes means for analyzing received data and analyzing the problem content using a natural language processing engine, means for recognizing the user's emotions using an emotion engine, and means for querying a knowledge base or FAQ database to search for an appropriate answer and adjusting the content according to the user's emotions. This makes it possible to accurately understand the user's problem and provide an answer that takes their emotions into consideration.

[0729] A "user" refers to an individual or legal entity that attempts to resolve a problem using the support system.

[0730] A "problem" refers to an issue or question that a user wants to resolve, and the content of that issue.

[0731] "Text format" refers to a format in which input is presented as a string of characters.

[0732] "Terminal" refers to computing devices such as computers, smartphones, and tablets used by users.

[0733] A "server" refers to a computer device that receives and processes information sent from a user's terminal.

[0734] "Analysis" refers to the process by which a server interprets the data it receives and understands its meaning.

[0735] A "natural language processing engine" refers to software that analyzes text data and extracts keywords and context.

[0736] An "emotion engine" refers to software that recognizes emotions from a user's text data.

[0737] A "knowledge base" refers to a database that stores information and solutions related to user problems.

[0738] An "FAQ database" refers to a database that compiles frequently asked questions and their answers.

[0739] An "HTTP request" refers to the protocol used by a device to send information to a server.

[0740] "HTTP response" refers to the protocol used by a server to send information back to a terminal.

[0741] "Tokenization" refers to the process of dividing text into the smallest meaningful units.

[0742] A "prompt message" refers to a sentence that expresses a question or instruction that the user will input.

[0743] A "generative AI model" refers to an artificial intelligence model that performs natural language processing and generates text tailored to a specific task.

[0744] This invention relates to a system for supporting tasks performed by customers after a contract has been signed. The system performs a series of processes in which the user inputs a problem in text format, sends the text data to a server, the server analyzes the data, generates or searches for an appropriate answer, sends the answer back to the terminal, and finally the terminal displays the answer to the user. Furthermore, by incorporating an emotion engine that recognizes the user's emotions, more appropriate support can be provided.

[0745] Hardware and software to use

[0746] hardware

[0747] Devices: PCs, smartphones, tablets, etc.

[0748] Server: A high-performance computing device (equipped with a CPU, memory, and storage).

[0749] software

[0750] Natural language processing engines: SpaCy, NLTK, etc.

[0751] Emotion engines: IBM Watson, Microsoft Azure Text Analytics, etc.

[0752] Knowledge base / FAQ database: Zendesk, Freshdesk, etc.

[0753] Generative AI models: GPT-3, etc.

[0754] Communication protocol: HTTP / HTTPS.

[0755] System Configuration

[0756] This system was configured as follows:

[0757] 1. The user enters the problem.

[0758] Users use devices such as smartphones or computers to enter the problem they need support for in text format. Specifically, they type "I don't know how to transfer data from my smartphone" into the text box and click the submit button.

[0759] 2. The device sends the request to the server.

[0760] The device sends the text data entered by the user to the server as an HTTP request. Specifically, it uses the HTTP POST method to generate an HTTP request that includes the text data in the request body and sends it to the server's API endpoint.

[0761] 3. The server receives the request.

[0762] The server receives HTTP requests sent from the terminal and extracts user input from the request body. Specifically, it uses a web framework (e.g., Django, Flask) to parse the request data and extract the text.

[0763] 4. The server analyzes the problem.

[0764] The server analyzes the received text data using a natural language processing engine (e.g., SpaCy). For example, it analyzes the text "I don't know how to transfer data from my smartphone" and extracts keywords and context such as "data transfer."

[0765] 5. The server uses an emotion engine for emotion recognition.

[0766] The server uses an emotion engine (e.g., IBM Watson) based on the analyzed text data to recognize the user's emotions. For example, it can detect user frustration from text such as "I don't know how to transfer data from my smartphone."

[0767] 6. The server generates or searches for answers.

[0768] The server searches for appropriate answers from knowledge bases and FAQ databases (e.g., Zendesk) based on the analysis results and sentiment recognition results. Alternatively, it uses generative AI models (e.g., GPT-3) to generate customized answers. The answers are tailored to the user's emotional state. For example, if the user is feeling frustrated, an answer with detailed and helpful instructions will be provided.

[0769] 7. The server sends the response back to the terminal.

[0770] The server prepares the generated or retrieved answer data as an HTTP response and sends it back to the terminal. Specifically, it formats the answer data in JSON format and sends it as an HTTP response.

[0771] 8. The device receives and displays the response.

[0772] The device analyzes the HTTP response received from the server and displays it in a format that is easy for the user to understand. Specifically, it formats the received data as text, images, and links and displays them to the user. For example, "Smartphone Data Migration Procedure" is displayed step by step. Encouraging messages tailored to the user's emotions are also displayed.

[0773] Specific example

[0774] Sentiment Recognition in Data Migration Support

[0775] 1. The user enters the problem.

[0776] User: "I want to transfer my data to my new smartphone, but I don't know how."

[0777] 2. The device sends the request to the server.

[0778] The device sends this request to the server as an HTTP request.

[0779] 3. The server receives the request.

[0780] The server receives the request and extracts the text, "I want to transfer data to my new smartphone, but I don't know how."

[0781] 4. The server analyzes the problem.

[0782] The server uses a natural language processing engine to analyze the keyword "data migration" and understand the user's intent.

[0783] 5. The server uses an emotion engine for emotion recognition.

[0784] The server uses an emotion engine to detect user frustration from the text and determines that the user is likely confused.

[0785] 6. The server generates or searches for answers.

[0786] To alleviate frustration, the server searches its knowledge base for detailed and helpful data migration instructions, along with additional support messages.

[0787] 7. The server sends the response back to the terminal.

[0788] The server sends the generated response data back to the terminal as an HTTP response.

[0789] 8. The device receives and displays the response.

[0790] The device visually displays the received responses. It also displays easy-to-understand instructions and encouraging messages so that users can perform the data migration while following the steps.

[0791] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0792] Step 1:

[0793] The user enters the problem.

[0794] Input: The user enters the problem they need support for in text format (e.g., "I don't know how to transfer data from my smartphone").

[0795] Specific actions: The user uses a smartphone or computer, enters the question into a text box, and clicks the submit button.

[0796] Output: Text data entered into the terminal.

[0797] Step 2:

[0798] The device sends the request to the server.

[0799] Input: Text data entered by the user.

[0800] Specific operation: The terminal sends the entered text data to the server as an HTTP POST request. Specifically, it includes the entered text data in the request body and sends it to the server's API endpoint.

[0801] Output: HTTP request sent to the server.

[0802] Step 3:

[0803] The server receives the request.

[0804] Input: HTTP request sent from the terminal.

[0805] Specific operation: The server uses a web framework to receive HTTP requests and extracts user input text from the request body.

[0806] Output: Extracted text data.

[0807] Step 4:

[0808] The server analyzes the problem.

[0809] Input: Extracted text data.

[0810] Specific operation: The server calls a natural language processing engine (e.g., SpaCy) to parse and tokenize the text data, and extract keywords and context. Specifically, it extracts the keyword "data migration" from the text "I don't know how to migrate data on my smartphone."

[0811] Output: Extracted keywords and context.

[0812] Step 5:

[0813] The server uses an emotion engine for emotion recognition.

[0814] Input: Extracted keywords or context.

[0815] Specific operation: The server invokes an emotion engine (e.g., IBM Watson) to recognize emotions such as frustration and confusion from the user's text data. For example, it might detect frustration from the phrase "I don't know how to transfer data from my smartphone."

[0816] Output: Recognized emotion data.

[0817] Step 6:

[0818] The server generates or searches for answers.

[0819] Input: Recognized sentiment data and extracted keywords or context.

[0820] Specific operation: The server queries a knowledge base or FAQ database to find the appropriate answer, or generates an answer using a generative AI model (e.g., GPT-3). Based on sentiment data, it adjusts the content and tone of the answer. For example, it provides detailed and courteous data migration instructions.

[0821] Output: Generated or retrieved response data.

[0822] Step 7:

[0823] The server sends the response back to the terminal.

[0824] Input: Generated or retrieved response data.

[0825] Specific operation: The server formats the generated response data in JSON format and sends it to the terminal as an HTTP response.

[0826] Output: HTTP response sent to the terminal.

[0827] Step 8:

[0828] The device receives and displays the response.

[0829] Input: HTTP response sent from the server.

[0830] Specific operation: The terminal analyzes the received response data and displays it to the user in an easy-to-understand format. Specifically, it formats it as text, images, and links to visually display data migration procedures and encouraging messages.

[0831] Output: User-recognizable response information.

[0832] (Application Example 2)

[0833] 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."

[0834] Traditional support systems were limited to basic functions such as users entering problems and receiving answers. However, this often failed to adequately alleviate the stress and difficulties users experienced. In particular, failing to consider the emotions users felt regarding the problems they faced meant that the support provided often did not fully meet their needs, making it difficult to increase user satisfaction. Current systems require the provision of specific and emotionally responsive support aimed at resolving problems.

[0835] 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.

[0836] In this invention, the server includes means for the user to input a problem in text format, means for the terminal to transmit the input text data to the server, means for the server to analyze the received data and generate or retrieve an appropriate answer, means for the server to return the generated or retrieved answer to the terminal, means for the terminal to visually display the received answer to the user, and means for the server to recognize the user's emotions using an emotion recognition engine and adjust the answer based on the result. This enables the provision of detailed support that responds to the user's emotions, and allows for quick and effective problem solving.

[0837] A "user" refers to an end-user who enters a problem and requests support.

[0838] "Text format" refers to a method of representing information using character data.

[0839] "Device" refers to a device used by a user, such as a smartphone, tablet, or personal computer.

[0840] A "server" refers to a computer system that processes requests sent by users, generates or searches for appropriate answers, and sends them back to the terminal.

[0841] "Analysis" refers to the process of understanding received data and identifying its meaning and intent.

[0842] "Generating or searching" refers to the act of creating a new, appropriate answer or finding suitable information from an existing knowledge base or database.

[0843] "Returning" refers to the act of sending a response generated or retrieved by the server to the terminal.

[0844] "Visual display" refers to methods of providing information to users using text, images, icons, etc.

[0845] An "emotion recognition engine" refers to a software component that detects a user's emotions from text data and takes appropriate action based on the results.

[0846] A "natural language processing engine" refers to a software component that analyzes text data and understands its meaning and intent.

[0847] A "knowledge base" refers to a database containing information and answers that have been stored in advance.

[0848] An "FAQ database" refers to a database containing frequently asked questions and their answers.

[0849] This invention is a system for quickly resolving problems that users face in food delivery services. Specific embodiments of this system are described below.

[0850] First, users use a device such as a smartphone or computer to input their problem in text format. For example, they describe the problem they are facing specifically, such as, "My delivery is delayed, but I don't know what to do."

[0851] The text data entered by the user is sent from the terminal to the server. This communication is performed using HTTP requests. The data received by the server is first parsed by a natural language processing engine to understand its content. Specifically, the text data is tokenized, and keywords and context are extracted.

[0852] Next, the server uses an emotion recognition engine to recognize emotions from the user's input. IBM Watson Tone Analyzer, for example, can be used as this emotion recognition engine. The user's emotional state is identified from the analysis results. For example, from the input "The delivery is delayed," the user's anxiety or frustration might be detected.

[0853] The server then generates or searches its knowledge base or FAQ database for an appropriate answer to the user's problem. At this stage, the tone and content of the answer are adjusted to match the user's psychological state, taking into account the results of sentiment recognition. For example, if the user is feeling frustrated, the server will provide very polite and specific instructions.

[0854] Once the answer is confirmed, the server sends it back to the terminal. The terminal then displays the received answer to the user visually. This display method may include text, images, links, etc.

[0855] As a concrete example, consider a case where a user enters "My delivery is delayed, and I don't know what to do." The emotion recognition engine recognizes the user's frustration, and the server generates a polite message such as, "We will look into this immediately, please wait a moment." This enables a more personalized response tailored to the user's emotions, improving user satisfaction.

[0856] Furthermore, examples of prompt statements to be input to the generative AI model are as follows:

[0857] "A user typed, 'My delivery is very late, what should I do?' Please provide an appropriate response that reflects their feelings."

[0858] In this way, this invention provides a system for food delivery services that enables quick and effective problem solving while taking into consideration the user's feelings.

[0859] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0860] Step 1:

[0861] The user enters the problem in text format.

[0862] Users use devices such as smartphones and computers to input specific problems in text, such as "My delivery is delayed, and I don't know what to do." They may also describe their anxieties and frustrations in detail.

[0863] Input: Text format issue from user

[0864] Output: Saving text data to the terminal

[0865] Step 2:

[0866] The terminal sends the entered text data to the server.

[0867] The terminal generates an HTTP request and sends the entered text data to the server. This request includes the user's input and is sent to the server in the appropriate format.

[0868] Input: Text data saved on the device

[0869] Output: HTTP request to the server

[0870] Step 3:

[0871] The server analyzes the data it receives.

[0872] The server receives an HTTP request and extracts text data from its body. This text data is then input into a natural language processing engine for tokenization, keyword extraction, and contextual analysis.

[0873] Input: Text data extracted from an HTTP request

[0874] Output: Analyzed keywords and contextual information

[0875] Step 4:

[0876] The server uses an emotion recognition engine to recognize the user's emotions.

[0877] Text data analyzed using natural language processing is passed to an emotion recognition engine to detect the user's emotions. For example, emotions such as "frustration" or "confusion" can be identified. IBM Watson Tone Analyzer can be used as the emotion recognition engine.

[0878] Input: Parsed text data

[0879] Output: Emotion recognition result (e.g., frustration)

[0880] Step 5:

[0881] The server generates the appropriate answer or searches for it in the knowledge base or FAQ database.

[0882] The server uses the emotion recognition results and analyzed text data to generate an appropriate response or search for relevant information in existing knowledge bases or FAQ databases. It prepares responses that include the appropriate tone and content for the emotion.

[0883] Input: Analyzed text data and sentiment recognition results

[0884] Output: Generated answers or search results from the database

[0885] Step 6:

[0886] The server sends the generated or retrieved answer back to the terminal.

[0887] The server prepares the response as an HTTP response and sends it back to the terminal. The response is structured in a format that is easily understandable to the user.

[0888] Input: Generated or retrieved response data

[0889] Output: HTTP response

[0890] Step 7:

[0891] The device visually displays the received response to the user.

[0892] The device receives an HTTP response, parses its contents, and displays them visually to the user. The display format includes text, images, and links. Messages tailored to the user's emotional state are also displayed.

[0893] Input: Response data extracted from HTTP response

[0894] Output: A display that the user can visually confirm.

[0895] 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.

[0896] 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.

[0897] 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.

[0898] [Third Embodiment]

[0899] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0900] 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.

[0901] 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).

[0902] 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.

[0903] 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.

[0904] 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).

[0905] 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.

[0906] 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.

[0907] 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.

[0908] 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.

[0909] 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.

[0910] 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".

[0911] This invention relates to a system for supporting tasks performed by customers after a contract has been signed. This system enables a series of processes in which the user inputs a problem in text format, sends the data to a server, the server analyzes the data, generates an answer, sends the answer back, and the terminal displays the answer to the user.

[0912] System Configuration

[0913] 1. The user enters the problem.

[0914] Users use devices such as smartphones or computers to enter the problem they need support for in text format. For example, they might enter a specific problem such as, "I don't know how to transfer data from my smartphone."

[0915] 2. The device sends the request to the server.

[0916] The terminal generates an HTTP request to send the entered text data to the server. This request includes the user's problem description.

[0917] 3. The server receives the request.

[0918] The server receives an HTTP request sent from the terminal. After receiving it, it extracts the user's problem details from the request body.

[0919] 4. The server analyzes the problem.

[0920] The server uses a natural language processing engine to analyze the text data entered by the user. Through this analysis, it extracts keywords and context to understand the user's problem.

[0921] 5. The server generates or searches for answers.

[0922] The server generates an appropriate answer to the user's problem based on the analysis results, or searches for an appropriate answer from a knowledge base or FAQ database. For example, it searches for and retrieves instructions on "how to transfer data from a smartphone."

[0923] 6. The server sends the response back to the terminal.

[0924] The server returns the generated or retrieved response data to the terminal as an HTTP response. This response data includes specific steps, links, and relevant resources for solving the problem.

[0925] 7. The device receives and displays the response.

[0926] The device analyzes the response received from the server and displays it in a format that is easy for the user to understand. For example, the procedure for transferring data from a smartphone might be displayed as text, images, and links.

[0927] Specific example

[0928] Data migration support

[0929] 1. The user enters the problem.

[0930] User: "I want to transfer my data to my new smartphone."

[0931] 2. The device sends the request to the server.

[0932] The device sends this request to the server as an HTTP request.

[0933] 3. The server receives the request.

[0934] The server receives the request and extracts the text, "I want to transfer data to a new smartphone."

[0935] 4. The server analyzes the problem.

[0936] The server uses a natural language processing engine to analyze the keyword "data migration" and understand the user's intent.

[0937] 5. The server generates or searches for answers.

[0938] The server searches the knowledge base for "Smartphone Data Migration Procedure" and generates the relevant information.

[0939] 6. The server sends the response back to the terminal.

[0940] The server sends the generated response data back to the terminal as an HTTP response.

[0941] 7. The device receives and displays the response.

[0942] The device visually displays the received responses, allowing the user to perform data migration while following the instructions.

[0943] This system allows users to smoothly complete the necessary tasks after signing a contract, reducing inquiries to stores and increasing user satisfaction. Furthermore, the server's natural language processing engine improves the accuracy of problem analysis, enabling the rapid provision of appropriate answers.

[0944] The following describes the processing flow.

[0945] Step 1:

[0946] Users enter the problem they need support for in text format into an input field on their device, such as a smartphone or computer. For example, "I don't know how to transfer data from my smartphone."

[0947] Step 2:

[0948] The terminal receives the text data entered by the user and generates an HTTP request to send to the server. The request includes the user's input.

[0949] Step 3:

[0950] The device sends the generated HTTP request to the server's API endpoint. This request contains the user's problem and is delivered to the server for analysis.

[0951] Step 4:

[0952] The server receives an HTTP request sent from the terminal. The server extracts the user's input from the request body. Example: "I don't know how to transfer data from my smartphone."

[0953] Step 5:

[0954] The server uses a natural language processing engine to analyze the received text data. It tokenizes the text and extracts keywords and context. For example, it extracts keywords such as "data migration" and "smartphone."

[0955] Step 6:

[0956] Based on the analysis results, the server generates an answer suitable for the user's problem or searches the knowledge base or FAQ database. For example, it searches the knowledge base for "Smartphone data migration procedure".

[0957] Step 7:

[0958] The server prepares the generated or retrieved answers as HTTP responses and constructs the data to send back to the terminal. The answers should include specific instructions and relevant links.

[0959] Step 8:

[0960] The server returns the prepared response data to the terminal as an HTTP response. The response data is sent along with a status code (e.g., 200 OK).

[0961] Step 9:

[0962] The terminal receives an HTTP response from the server. It parses the response body and prepares the data for display to the user.

[0963] Step 10:

[0964] The device displays the received response data to the user. This data is displayed in a visually easy-to-understand format, such as text, images, and links, making it accessible to the user. For example, a data migration procedure manual is displayed, allowing the user to migrate data from their smartphone by following the instructions.

[0965] The above outlines the specific processing flow within the customer support system after the contract is signed.

[0966] (Example 1)

[0967] 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."

[0968] Traditional support systems often resulted in long waiting times between users entering a problem and receiving a solution, and sometimes even inadequate answers. This led to decreased user satisfaction and an increase in inquiries to the support center.

[0969] 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.

[0970] In this invention, the server includes means for an input form and a submit button for the user to enter a problem; means for the terminal to generate an HTTP request and send it to the server's endpoint; means for the server to extract the user's problem details from the request body; means for understanding the user's problem using a natural language processing engine; and means for searching for an answer by referring to a knowledge base or FAQ database. This enables the user to obtain an answer for problem resolution quickly and accurately, reduces inquiries to the support center, and improves user satisfaction.

[0971] A "user" refers to an individual or legal entity that uses a support system to input a problem and seek a solution.

[0972] "Device" refers to electronic devices used by users, such as smartphones, personal computers, and tablets.

[0973] A "server" refers to a remote computer that receives and processes requests sent by users.

[0974] An "input form" refers to an online input field where a user enters a question in text format.

[0975] The term "send button" refers to an interface element used to send entered text data to the server.

[0976] An "HTTP request" refers to a type of internet communication protocol used to send data from a user's device to a server.

[0977] An "endpoint" refers to an address, such as a URL or URI, that is accessible on a server to provide a specific function or service.

[0978] The "request body" refers to the data contained in the message portion of an HTTP request.

[0979] A "natural language processing engine" refers to software and technology that allows computers to understand and analyze human language.

[0980] A "knowledge base" refers to a database system that stores and makes searchable past information and data.

[0981] An "FAQ database" refers to a database that compiles frequently asked questions and their answers.

[0982] "HTTP response" refers to a type of internet communication protocol used by a server to send a response to a user's device.

[0983] This invention relates to a system for supporting tasks performed by customers after a contract has been signed. This system enables a series of processes in which the user inputs a problem in text format, sends the data to a server, the server analyzes the data, generates an answer, sends the answer back, and the terminal displays the answer to the user.

[0984] System Configuration

[0985] 1. The user enters the problem.

[0986] Users use devices such as smartphones or computers to enter the problem they need support for in text format. For example, they might enter a specific problem such as, "I want to transfer data to my new smartphone."

[0987] 2. The device sends the request to the server.

[0988] The terminal generates an HTTP request to send the entered text data to the server. This request includes the user's problem description.

[0989] 3. The server receives the request.

[0990] The server receives an HTTP request sent from the terminal. After receiving it, it extracts the user's problem details from the request body.

[0991] 4. The server analyzes the problem.

[0992] The server uses a natural language processing engine (e.g., Google Cloud Natural Language API or OpenAI's GPT-3) to analyze the text data entered by the user. Through this analysis, keywords and context are extracted to understand the user's problem.

[0993] 5. The server generates or searches for answers.

[0994] The server generates an appropriate answer to the user's problem based on the analysis results. Alternatively, it searches for the appropriate answer from a knowledge base or FAQ database (e.g., Zendesk). For example, it searches for and retrieves instructions on "how to transfer data from a smartphone."

[0995] 6. The server sends the response back to the terminal.

[0996] The server returns the generated or retrieved response data to the terminal as an HTTP response. This response data includes specific steps, links, and relevant resources for solving the problem.

[0997] 7. The device receives and displays the response.

[0998] The device analyzes the response received from the server and displays it in a format that is easy for the user to understand. For example, the procedure for transferring data from a smartphone might be displayed as text, images, and links.

[0999] Specific example

[1000] Data migration support

[1001] 1. The user enters the problem.

[1002] User: "I want to transfer my data to my new smartphone."

[1003] 2. The device sends the request to the server.

[1004] The device sends this request to the server as an HTTP request.

[1005] 3. The server receives the request.

[1006] The server receives the request and extracts the text, "I want to transfer data to a new smartphone."

[1007] 4. The server analyzes the problem.

[1008] The server uses a natural language processing engine to analyze the keyword "data migration" and understand the user's intent.

[1009] 5. The server generates or searches for answers.

[1010] The server searches the knowledge base for "Smartphone Data Migration Procedure" and generates the relevant information.

[1011] 6. The server sends the response back to the terminal.

[1012] The server sends the generated response data back to the terminal as an HTTP response.

[1013] 7. The device receives and displays the response.

[1014] The device visually displays the received responses, allowing the user to perform data migration while following the instructions.

[1015] This system allows users to smoothly complete the necessary tasks after signing a contract, reducing inquiries to stores and increasing user satisfaction. Furthermore, the server's natural language processing engine improves the accuracy of problem analysis, enabling the rapid provision of appropriate answers.

[1016] Example of a prompt

[1017] "Please tell me how to transfer data to a new smartphone."

[1018] By inputting this prompt into the generating AI model, specific and appropriate support content will be provided.

[1019] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1020] Step 1: The user enters the problem.

[1021] Users use their own devices (smartphones or computers) to enter the problem they need support for in text format. Specifically, they type "I want to transfer data to a new smartphone" into the input form on their browser and click the submit button. This action generates text as input data.

[1022] Step 2: The device sends the request to the server.

[1023] The terminal generates an HTTP POST request to send the entered text data to the server. This request contains the problem details entered by the user. Specifically, the browser captures the user's input, stores it in the request body, and sends it to the specified server endpoint.

[1024] Step 3: The server receives the request.

[1025] The server receives an HTTP request sent from the terminal. The request contains text data entered by the user. The server extracts the text "I want to transfer data to a new smartphone" from the request body. Specifically, a web server that processes HTTP requests (such as Apache or Nginx) receives the request and parses its contents.

[1026] Step 4: The server analyzes the problem.

[1027] The server uses a natural language processing engine (such as Google Cloud Natural Language API or OpenAI's GPT-3) to analyze the text data entered by the user. Based on the analysis, keywords and context are extracted to understand the user's intent. Specifically, the extracted text data is passed to the natural language processing engine, which then extracts keywords such as "data migration" and "smartphone."

[1028] Step 5: The server generates or searches for an answer.

[1029] The server generates appropriate answers to the user's problem based on the analysis results. Alternatively, it searches for appropriate answers in a knowledge base or FAQ database (e.g., Zendesk). Specifically, it queries the knowledge base for "smartphone data migration procedure" and retrieves relevant procedures and answers. It also utilizes a generative AI model to generate answers as needed.

[1030] Step 6: The server sends the response back to the terminal.

[1031] The server returns the generated or retrieved answer data to the terminal as an HTTP response. The response data includes specific steps for solving the problem and relevant links. Specifically, the server formats the retrieved or generated answer as an HTTP response and sends it to the user's terminal.

[1032] Step 7: The device receives and displays the response.

[1033] The device analyzes the response received from the server and displays it in a format that is easy for the user to understand. Specifically, the browser receives the HTTP response from the server and displays it as text, images, and links. For example, "Smartphone data migration procedure" might be displayed in bullet points, along with links to related support pages.

[1034] (Application Example 1)

[1035] 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."

[1036] Traditional text-based customer support systems have the challenge of not being able to respond quickly and accurately to user problems. As a result, users do not receive adequate support, which in turn leads to decreased customer satisfaction. Furthermore, there was a need for a system that efficiently provides support information to resolve issues related to products purchased by users on e-commerce sites and other platforms.

[1037] 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.

[1038] In this invention, the server includes means for parsing queries and generating or retrieving appropriate answers from a knowledge base or FAQ database, means for returning the generated or retrieved answers to the terminal, and means for the terminal to visually display the answers. This makes it possible to efficiently resolve user problems and improve customer satisfaction.

[1039] 1. A "user" is someone who attempts to solve a problem using the system.

[1040] 2. "Text format" refers to a format that uses character data to represent information.

[1041] 3. "Terminal" refers to a device such as a computer or smartphone used by a user.

[1042] 4. A "server" is a computer system that receives requests from terminals and performs analysis and generates responses.

[1043] 5. A "natural language processing engine" is a software technology used to analyze text data and understand its meaning.

[1044] 6. A "knowledge base" is a database in which solutions to problems are systematically compiled.

[1045] 7. An "FAQ database" is a database that compiles frequently asked questions and their answers.

[1046] 8. An "HTTP request" is one of the protocols used to exchange data between a client and a server.

[1047] 9. "Answer generation" is the process of creating appropriate solutions to the analyzed problem.

[1048] 10. "Searching" is the process of finding the desired information from a database.

[1049] 11. "Visual display" refers to the process of providing information to users in an easily understandable format.

[1050] This invention is a system designed to support tasks performed by customers after a contract has been signed. It enables a series of processes in which the user inputs a problem in text format, sends that data to a server, the server analyzes it, generates an answer, sends the answer back, and the terminal displays the answer to the user.

[1051] Hardware and software to use

[1052] Hardware:

[1053] smartphone

[1054] Cloud Server

[1055] software:

[1056] Mobile app frameworks (React Native, Flutter, etc.)

[1057] Server-side frameworks (Node.js, Django, etc.)

[1058] Natural language processing engines (Google NLP, IBM Watson, OpenAI GPT-4, etc.)

[1059] System Overview

[1060] 1. The user enters the problem.

[1061] Users enter their problems in text format using a smartphone application. An example of such a problem is, "My new vacuum cleaner isn't working."

[1062] 2. The device sends a problem.

[1063] The smartphone sends the user-entered question to the server as an HTTP request. The request includes the text data entered by the user.

[1064] 3. The server receives and parses the request.

[1065] After receiving an HTTP request, the server uses a natural language processing engine to analyze the text data. Through this analysis, it extracts keywords and context related to the problem, thereby understanding its content.

[1066] 4. The server generates or searches for answers.

[1067] Based on the analysis results, the server generates or searches for appropriate answers from the knowledge base or FAQ database. For example, it searches for and retrieves troubleshooting information for a case where "the new vacuum cleaner isn't working."

[1068] 5. The server sends the response.

[1069] The server returns the generated or retrieved response data to the terminal as an HTTP response. The response data includes specific steps and related resources.

[1070] 6. The device displays the answer.

[1071] The smartphone analyzes the received response and displays it in a format that is easy for the user to understand. For example, it may display it in the form of text, images, or video links.

[1072] Specific example

[1073] When a user enters "My new vacuum cleaner isn't working," the following process is executed.

[1074] 1. User enters the problem: "My new vacuum cleaner isn't working."

[1075] 2. The device sends the request to the server.

[1076] 3. The server receives the request and analyzes the problem.

[1077] 4. Use a natural language processing engine to extract the keywords "vacuum cleaner" and "not working".

[1078] 5. Search for information on "vacuum cleaner troubleshooting" in the knowledge base or FAQ database.

[1079] 6. The server generates an appropriate response and sends it back to the terminal.

[1080] 7. Smartphones visually display the answers.

[1081] Example of a prompt

[1082] "The vacuum cleaner I recently bought isn't working at all. What should I do?"

[1083] As described above, this system enables users to efficiently resolve problems they face after signing a contract, thereby contributing to improved customer satisfaction.

[1084] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1085] Step 1:

[1086] The user enters the problem in text format. The user uses a smartphone application to enter the problem into a text box. For example, the user might enter "My new vacuum cleaner isn't working." The input data is saved in text format.

[1087] Step 2:

[1088] The terminal sends the entered text data to the server. The terminal generates an HTTP POST request containing the entered text data and sends it to the server. The input data is sent to the server, and an HTTP request is generated as output data from the terminal.

[1089] Step 3:

[1090] The server receives the request. The server receives the HTTP request and extracts the text data entered by the user from its body. The input data is the HTTP request, and the output data is the extracted problem text.

[1091] Step 4:

[1092] The server analyzes the received data using a natural language processing engine. The server uses a natural language processing engine (e.g., OpenAI GPT-4) to analyze the problem text and extract keywords and context. The input data is text data, and the output data is the analysis results, specifically extracted keywords (e.g., "vacuum cleaner," "doesn't work").

[1093] Step 5:

[1094] The server generates or retrieves appropriate answers from a knowledge base or FAQ database. Based on the analysis results, the server searches for relevant information from the knowledge base or FAQ database and generates appropriate answers. The input data is the analysis results, and the output data is the generated answers (e.g., a vacuum cleaner troubleshooting guide).

[1095] Step 6:

[1096] The server sends the generated or retrieved answer back to the terminal. The server generates an HTTP response containing the generated or retrieved answer and sends it back to the terminal. The input data is the generated answer, and the output data is the HTTP response.

[1097] Step 7:

[1098] The device analyzes the received response and displays it visually to the user. The device analyzes the received HTTP response and extracts the response data. The extracted data is displayed to the user in a visually easy-to-understand format such as text, images, and links. The input data is the HTTP response, and the output data is visually displayed information (e.g., a vacuum cleaner troubleshooting guide).

[1099] 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.

[1100] This invention relates to a system for supporting tasks performed by customers after a contract has been signed. This system combines a series of processes—where the user inputs a problem in text format, sends the data to a server, the server analyzes, generates, and returns the answer, and the terminal displays the answer to the user—with an emotion engine that recognizes the user's emotions. This configuration reduces the stress and difficulties the user experiences and provides more appropriate support.

[1101] System Configuration

[1102] 1. The user enters the problem.

[1103] Users use devices such as smartphones or computers to enter the problem they need support for in text format. For example, "I don't know how to transfer data from my smartphone."

[1104] 2. The device sends the request to the server.

[1105] The terminal generates an HTTP request to send the entered text data to the server. This request includes the user's input.

[1106] 3. The server receives the request.

[1107] The server receives an HTTP request sent from the terminal and extracts the user's input from the request body.

[1108] 4. The server analyzes the problem.

[1109] The server uses a natural language processing engine to analyze the received text data. It tokenizes the text and extracts keywords and context.

[1110] 5. The server uses an emotion engine for emotion recognition.

[1111] The server uses an emotion engine to recognize the user's emotions based on the analyzed text data. For example, it can detect feelings of frustration or confusion from text such as "I don't know how to transfer data on my smartphone."

[1112] 6. The server generates or searches for answers.

[1113] Based on the analysis results and sentiment recognition, the server generates an appropriate response to the user's problem or searches its knowledge base or FAQ database. It also adjusts the response's tone and content to match the user's psychological state, reflecting the sentiment recognition results. For example, if the user is highly frustrated, it provides detailed and helpful instructions.

[1114] 7. The server sends the response back to the terminal.

[1115] The server prepares the generated or retrieved response data as an HTTP response and constructs the data to be sent back to the terminal. The response should include specific steps and relevant links.

[1116] 8. The device receives and displays the response.

[1117] The device analyzes the HTTP response received from the server and displays it in a user-friendly format. For example, instructions for migrating data from a smartphone are displayed as text, images, and links. It also displays messages and additional support information that are tailored to the user's emotional state.

[1118] Specific example

[1119] Sentiment Recognition in Data Migration Support

[1120] 1. The user enters the problem.

[1121] User: "I want to transfer my data to my new smartphone, but I don't know how."

[1122] 2. The device sends the request to the server.

[1123] The device sends this request to the server as an HTTP request.

[1124] 3. The server receives the request.

[1125] The server receives the request and extracts the text, "I want to transfer data to my new smartphone, but I don't know how."

[1126] 4. The server analyzes the problem.

[1127] The server uses a natural language processing engine to analyze the keyword "data migration" and understand the user's intent.

[1128] 5. The server uses an emotion engine for emotion recognition.

[1129] The server uses an emotion engine to detect user frustration from the text and determines that the user is likely confused.

[1130] 6. The server generates or searches for answers.

[1131] To alleviate frustration, the server searches its knowledge base for detailed and helpful data migration instructions, along with additional support messages.

[1132] 7. The server sends the response back to the terminal.

[1133] The server sends the generated response data back to the terminal as an HTTP response.

[1134] 8. The device receives and displays the response.

[1135] The device visually displays the received responses. It also displays easy-to-follow instructions and encouraging messages to help users perform data migration while following the steps.

[1136] This system allows users to smoothly complete the necessary tasks after signing a contract, reducing inquiries to stores and increasing user satisfaction. The server's natural language processing and emotion engines enable problem analysis and appropriate psychological responses, providing even more advanced support.

[1137] The following describes the processing flow.

[1138] Step 1:

[1139] Users enter the problem they need support for in text format into an input field on their device, such as a smartphone or computer. For example, they might enter, "I don't know how to transfer data from my smartphone."

[1140] Step 2:

[1141] The terminal receives the entered text data and generates an HTTP request to send it to the server. The request contains the user's input.

[1142] Step 3:

[1143] The device sends the generated HTTP request to the server's API endpoint. This request contains the user's problem and is delivered to the server for analysis.

[1144] Step 4:

[1145] The server receives an HTTP request sent from the terminal. The server extracts the user's input from the request body. For example, it might extract the text "I don't know how to transfer data from my smartphone."

[1146] Step 5:

[1147] The server uses a natural language processing engine to analyze the received text data. It tokenizes the text and extracts keywords and context. For example, it extracts keywords such as "data migration" and "smartphone."

[1148] Step 6:

[1149] The server uses an emotion engine to recognize the user's emotions based on the analyzed text data. For example, the emotion engine detects the user's frustration or confusion from the text, "I don't know how to transfer data from my smartphone."

[1150] Step 7:

[1151] The server generates an appropriate answer to the user's problem based on the results of natural language processing and sentiment recognition, or searches a knowledge base or FAQ database. It then adjusts the tone and content of the answer to match the user's psychological state, reflecting the results of sentiment recognition.

[1152] Step 8:

[1153] The server prepares the generated or retrieved response data as an HTTP response and constructs the data to be sent back to the terminal. The response should include specific steps and relevant links.

[1154] Step 9:

[1155] The server returns the prepared response data to the terminal as an HTTP response. The response data is sent along with a status code (e.g., 200 OK).

[1156] Step 10:

[1157] The terminal receives an HTTP response from the server. It parses the response body and prepares the data for display to the user.

[1158] Step 11:

[1159] The device visually displays the received response data to the user. For example, it may be displayed in a visually easy-to-understand format such as text, images, and links, making it accessible to the user. It also displays messages and additional support information that correspond to the user's emotional state.

[1160] The above outlines the specific processing flow in a support system that incorporates an emotion engine to recognize user emotions.

[1161] (Example 2)

[1162] 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."

[1163] Traditional support systems often fail to adequately mitigate the stress and difficulties users experience, resulting in inadequate support. In particular, providing answers that disregard the user's feelings can exacerbate their dissatisfaction and confusion. Therefore, a system is needed that can properly analyze user problems and provide support tailored to their emotional needs.

[1164] 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.

[1165] In this invention, the server includes means for analyzing received data and analyzing the problem content using a natural language processing engine, means for recognizing the user's emotions using an emotion engine, and means for querying a knowledge base or FAQ database to search for an appropriate answer and adjusting the content according to the user's emotions. This makes it possible to accurately understand the user's problem and provide an answer that takes their emotions into consideration.

[1166] A "user" refers to an individual or legal entity that attempts to resolve a problem using the support system.

[1167] A "problem" refers to an issue or question that a user wants to resolve, and the content of that issue.

[1168] "Text format" refers to a format in which input is presented as a string of characters.

[1169] "Terminal" refers to computing devices such as computers, smartphones, and tablets used by users.

[1170] A "server" refers to a computer device that receives and processes information sent from a user's terminal.

[1171] "Analysis" refers to the process by which a server interprets the data it receives and understands its meaning.

[1172] A "natural language processing engine" refers to software that analyzes text data and extracts keywords and context.

[1173] An "emotion engine" refers to software that recognizes emotions from a user's text data.

[1174] A "knowledge base" refers to a database that stores information and solutions related to user problems.

[1175] An "FAQ database" refers to a database that compiles frequently asked questions and their answers.

[1176] An "HTTP request" refers to the protocol used by a device to send information to a server.

[1177] "HTTP response" refers to the protocol used by a server to send information back to a terminal.

[1178] "Tokenization" refers to the process of dividing text into the smallest meaningful units.

[1179] A "prompt message" refers to a sentence that expresses a question or instruction that the user will input.

[1180] A "generative AI model" refers to an artificial intelligence model that performs natural language processing and generates text tailored to a specific task.

[1181] This invention relates to a system for supporting tasks performed by customers after a contract has been signed. The system performs a series of processes in which the user inputs a problem in text format, sends the text data to a server, the server analyzes the data, generates or searches for an appropriate answer, sends the answer back to the terminal, and finally the terminal displays the answer to the user. Furthermore, by incorporating an emotion engine that recognizes the user's emotions, more appropriate support can be provided.

[1182] Hardware and software to use

[1183] hardware

[1184] Devices: PCs, smartphones, tablets, etc.

[1185] Server: A high-performance computing device (equipped with a CPU, memory, and storage).

[1186] software

[1187] Natural language processing engines: SpaCy, NLTK, etc.

[1188] Emotion engines: IBM Watson, Microsoft Azure Text Analytics, etc.

[1189] Knowledge base / FAQ database: Zendesk, Freshdesk, etc.

[1190] Generative AI models: GPT-3, etc.

[1191] Communication protocol: HTTP / HTTPS.

[1192] System Configuration

[1193] This system was configured as follows:

[1194] 1. The user enters the problem.

[1195] Users use devices such as smartphones or computers to enter the problem they need support for in text format. Specifically, they type "I don't know how to transfer data from my smartphone" into the text box and click the submit button.

[1196] 2. The device sends the request to the server.

[1197] The device sends the text data entered by the user to the server as an HTTP request. Specifically, it uses the HTTP POST method to generate an HTTP request that includes the text data in the request body and sends it to the server's API endpoint.

[1198] 3. The server receives the request.

[1199] The server receives HTTP requests sent from the terminal and extracts user input from the request body. Specifically, it uses a web framework (e.g., Django, Flask) to parse the request data and extract the text.

[1200] 4. The server analyzes the problem.

[1201] The server analyzes the received text data using a natural language processing engine (e.g., SpaCy). For example, it analyzes the text "I don't know how to transfer data from my smartphone" and extracts keywords and context such as "data transfer."

[1202] 5. The server uses an emotion engine for emotion recognition.

[1203] The server uses an emotion engine (e.g., IBM Watson) based on the analyzed text data to recognize the user's emotions. For example, it can detect user frustration from text such as "I don't know how to transfer data from my smartphone."

[1204] 6. The server generates or searches for answers.

[1205] The server searches for appropriate answers from knowledge bases and FAQ databases (e.g., Zendesk) based on the analysis results and sentiment recognition results. Alternatively, it uses generative AI models (e.g., GPT-3) to generate customized answers. The answers are tailored to the user's emotional state. For example, if the user is feeling frustrated, an answer with detailed and helpful instructions will be provided.

[1206] 7. The server sends the response back to the terminal.

[1207] The server prepares the generated or retrieved answer data as an HTTP response and sends it back to the terminal. Specifically, it formats the answer data in JSON format and sends it as an HTTP response.

[1208] 8. The device receives and displays the response.

[1209] The device analyzes the HTTP response received from the server and displays it in a format that is easy for the user to understand. Specifically, it formats the received data as text, images, and links and displays them to the user. For example, "Smartphone Data Migration Procedure" is displayed step by step. Encouraging messages tailored to the user's emotions are also displayed.

[1210] Specific example

[1211] Sentiment Recognition in Data Migration Support

[1212] 1. The user enters the problem.

[1213] User: "I want to transfer my data to my new smartphone, but I don't know how."

[1214] 2. The device sends the request to the server.

[1215] The device sends this request to the server as an HTTP request.

[1216] 3. The server receives the request.

[1217] The server receives the request and extracts the text, "I want to transfer data to my new smartphone, but I don't know how."

[1218] 4. The server analyzes the problem.

[1219] The server uses a natural language processing engine to analyze the keyword "data migration" and understand the user's intent.

[1220] 5. The server uses an emotion engine for emotion recognition.

[1221] The server uses an emotion engine to detect user frustration from the text and determines that the user is likely confused.

[1222] 6. The server generates or searches for answers.

[1223] To alleviate frustration, the server searches its knowledge base for detailed and helpful data migration instructions, along with additional support messages.

[1224] 7. The server sends the response back to the terminal.

[1225] The server sends the generated response data back to the terminal as an HTTP response.

[1226] 8. The device receives and displays the response.

[1227] The device visually displays the received responses. It also displays easy-to-understand instructions and encouraging messages so that users can perform the data migration while following the steps.

[1228] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1229] Step 1:

[1230] The user enters the problem.

[1231] Input: The user enters the problem they need support for in text format (e.g., "I don't know how to transfer data from my smartphone").

[1232] Specific actions: The user uses a smartphone or computer, enters the question into a text box, and clicks the submit button.

[1233] Output: Text data entered into the terminal.

[1234] Step 2:

[1235] The device sends the request to the server.

[1236] Input: Text data entered by the user.

[1237] Specific operation: The terminal sends the entered text data to the server as an HTTP POST request. Specifically, it includes the entered text data in the request body and sends it to the server's API endpoint.

[1238] Output: HTTP request sent to the server.

[1239] Step 3:

[1240] The server receives the request.

[1241] Input: HTTP request sent from the terminal.

[1242] Specific operation: The server uses a web framework to receive HTTP requests and extracts user input text from the request body.

[1243] Output: Extracted text data.

[1244] Step 4:

[1245] The server analyzes the problem.

[1246] Input: Extracted text data.

[1247] Specific operation: The server calls a natural language processing engine (e.g., SpaCy) to parse and tokenize the text data, and extract keywords and context. Specifically, it extracts the keyword "data migration" from the text "I don't know how to migrate data on my smartphone."

[1248] Output: Extracted keywords and context.

[1249] Step 5:

[1250] The server uses an emotion engine for emotion recognition.

[1251] Input: Extracted keywords or context.

[1252] Specific operation: The server invokes an emotion engine (e.g., IBM Watson) to recognize emotions such as frustration and confusion from the user's text data. For example, it might detect frustration from the phrase "I don't know how to transfer data from my smartphone."

[1253] Output: Recognized emotion data.

[1254] Step 6:

[1255] The server generates or searches for answers.

[1256] Input: Recognized sentiment data and extracted keywords or context.

[1257] Specific operation: The server queries a knowledge base or FAQ database to find the appropriate answer, or generates an answer using a generative AI model (e.g., GPT-3). Based on sentiment data, it adjusts the content and tone of the answer. For example, it provides detailed and courteous data migration instructions.

[1258] Output: Generated or retrieved response data.

[1259] Step 7:

[1260] The server sends the response back to the terminal.

[1261] Input: Generated or retrieved response data.

[1262] Specific operation: The server formats the generated response data in JSON format and sends it to the terminal as an HTTP response.

[1263] Output: HTTP response sent to the terminal.

[1264] Step 8:

[1265] The device receives and displays the response.

[1266] Input: HTTP response sent from the server.

[1267] Specific operation: The terminal analyzes the received response data and displays it to the user in an easy-to-understand format. Specifically, it formats it as text, images, and links to visually display data migration procedures and encouraging messages.

[1268] Output: User-recognizable response information.

[1269] (Application Example 2)

[1270] 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."

[1271] Traditional support systems were limited to basic functions such as users entering problems and receiving answers. However, this often failed to adequately alleviate the stress and difficulties users experienced. In particular, failing to consider the emotions users felt regarding the problems they faced meant that the support provided often did not fully meet their needs, making it difficult to increase user satisfaction. Current systems require the provision of specific and emotionally responsive support aimed at resolving problems.

[1272] 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.

[1273] In this invention, the server includes means for the user to input a problem in text format, means for the terminal to transmit the input text data to the server, means for the server to analyze the received data and generate or retrieve an appropriate answer, means for the server to return the generated or retrieved answer to the terminal, means for the terminal to visually display the received answer to the user, and means for the server to recognize the user's emotions using an emotion recognition engine and adjust the answer based on the result. This enables the provision of detailed support that responds to the user's emotions, and allows for quick and effective problem solving.

[1274] A "user" refers to an end-user who enters a problem and requests support.

[1275] "Text format" refers to a method of representing information using character data.

[1276] "Device" refers to a device used by a user, such as a smartphone, tablet, or personal computer.

[1277] A "server" refers to a computer system that processes requests sent by users, generates or searches for appropriate answers, and sends them back to the terminal.

[1278] "Analysis" refers to the process of understanding received data and identifying its meaning and intent.

[1279] "Generating or searching" refers to the act of creating a new, appropriate answer or finding suitable information from an existing knowledge base or database.

[1280] "Returning" refers to the act of sending a response generated or retrieved by the server to the terminal.

[1281] "Visual display" refers to methods of providing information to users using text, images, icons, etc.

[1282] An "emotion recognition engine" refers to a software component that detects a user's emotions from text data and takes appropriate action based on the results.

[1283] A "natural language processing engine" refers to a software component that analyzes text data and understands its meaning and intent.

[1284] A "knowledge base" refers to a database containing information and answers that have been stored in advance.

[1285] An "FAQ database" refers to a database containing frequently asked questions and their answers.

[1286] This invention is a system for quickly resolving problems that users face in food delivery services. Specific embodiments of this system are described below.

[1287] First, users use a device such as a smartphone or computer to input their problem in text format. For example, they describe the problem they are facing specifically, such as, "My delivery is delayed, but I don't know what to do."

[1288] The text data entered by the user is sent from the terminal to the server. This communication is performed using HTTP requests. The data received by the server is first parsed by a natural language processing engine to understand its content. Specifically, the text data is tokenized, and keywords and context are extracted.

[1289] Next, the server uses an emotion recognition engine to recognize emotions from the user's input. IBM Watson Tone Analyzer, for example, can be used as this emotion recognition engine. The user's emotional state is identified from the analysis results. For example, from the input "The delivery is delayed," the user's anxiety or frustration might be detected.

[1290] The server then generates or searches its knowledge base or FAQ database for an appropriate answer to the user's problem. At this stage, the tone and content of the answer are adjusted to match the user's psychological state, taking into account the results of sentiment recognition. For example, if the user is feeling frustrated, the server will provide very polite and specific instructions.

[1291] Once the answer is confirmed, the server sends it back to the terminal. The terminal then displays the received answer to the user visually. This display method may include text, images, links, etc.

[1292] As a concrete example, consider a case where a user enters "My delivery is delayed, and I don't know what to do." The emotion recognition engine recognizes the user's frustration, and the server generates a polite message such as, "We will look into this immediately, please wait a moment." This enables a more personalized response tailored to the user's emotions, improving user satisfaction.

[1293] Furthermore, examples of prompt statements to be input to the generative AI model are as follows:

[1294] "A user typed, 'My delivery is very late, what should I do?' Please provide an appropriate response that reflects their feelings."

[1295] In this way, this invention provides a system for food delivery services that enables quick and effective problem solving while taking into consideration the user's feelings.

[1296] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1297] Step 1:

[1298] The user enters the problem in text format.

[1299] Users use devices such as smartphones and computers to input specific problems in text, such as "My delivery is delayed, and I don't know what to do." They may also describe their anxieties and frustrations in detail.

[1300] Input: Text format issue from user

[1301] Output: Saving text data to the terminal

[1302] Step 2:

[1303] The terminal sends the entered text data to the server.

[1304] The terminal generates an HTTP request and sends the entered text data to the server. This request includes the user's input and is sent to the server in the appropriate format.

[1305] Input: Text data saved on the device

[1306] Output: HTTP request to the server

[1307] Step 3:

[1308] The server analyzes the data it receives.

[1309] The server receives an HTTP request and extracts text data from its body. This text data is then input into a natural language processing engine for tokenization, keyword extraction, and contextual analysis.

[1310] Input: Text data extracted from an HTTP request

[1311] Output: Analyzed keywords and contextual information

[1312] Step 4:

[1313] The server uses an emotion recognition engine to recognize the user's emotions.

[1314] Text data analyzed using natural language processing is passed to an emotion recognition engine to detect the user's emotions. For example, emotions such as "frustration" or "confusion" can be identified. IBM Watson Tone Analyzer can be used as the emotion recognition engine.

[1315] Input: Parsed text data

[1316] Output: Emotion recognition result (e.g., frustration)

[1317] Step 5:

[1318] The server generates the appropriate answer or searches for it in the knowledge base or FAQ database.

[1319] The server uses the emotion recognition results and analyzed text data to generate an appropriate response or search for relevant information in existing knowledge bases or FAQ databases. It prepares responses that include the appropriate tone and content for the emotion.

[1320] Input: Analyzed text data and sentiment recognition results

[1321] Output: Generated answers or search results from the database

[1322] Step 6:

[1323] The server sends the generated or retrieved answer back to the terminal.

[1324] The server prepares the response as an HTTP response and sends it back to the terminal. The response is structured in a format that is easily understandable to the user.

[1325] Input: Generated or retrieved response data

[1326] Output: HTTP response

[1327] Step 7:

[1328] The device visually displays the received response to the user.

[1329] The device receives an HTTP response, parses its contents, and displays them visually to the user. The display format includes text, images, and links. Messages tailored to the user's emotional state are also displayed.

[1330] Input: Response data extracted from HTTP response

[1331] Output: A display that the user can visually confirm.

[1332] 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.

[1333] 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.

[1334] 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.

[1335] [Fourth Embodiment]

[1336] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1337] 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.

[1338] 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).

[1339] 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.

[1340] 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.

[1341] 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).

[1342] 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.

[1343] 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.

[1344] 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.

[1345] 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.

[1346] 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.

[1347] 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.

[1348] 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".

[1349] This invention relates to a system for supporting tasks performed by customers after a contract has been signed. This system enables a series of processes in which the user inputs a problem in text format, sends the data to a server, the server analyzes the data, generates an answer, sends the answer back, and the terminal displays the answer to the user.

[1350] System Configuration

[1351] 1. The user enters the problem.

[1352] Users use devices such as smartphones or computers to enter the problem they need support for in text format. For example, they might enter a specific problem such as, "I don't know how to transfer data from my smartphone."

[1353] 2. The device sends the request to the server.

[1354] The terminal generates an HTTP request to send the entered text data to the server. This request includes the user's problem description.

[1355] 3. The server receives the request.

[1356] The server receives an HTTP request sent from the terminal. After receiving it, it extracts the user's problem details from the request body.

[1357] 4. The server analyzes the problem.

[1358] The server uses a natural language processing engine to analyze the text data entered by the user. Through this analysis, it extracts keywords and context to understand the user's problem.

[1359] 5. The server generates or searches for answers.

[1360] The server generates an appropriate answer to the user's problem based on the analysis results, or searches for an appropriate answer from a knowledge base or FAQ database. For example, it searches for and retrieves instructions on "how to transfer data from a smartphone."

[1361] 6. The server sends the response back to the terminal.

[1362] The server returns the generated or retrieved response data to the terminal as an HTTP response. This response data includes specific steps, links, and relevant resources for solving the problem.

[1363] 7. The device receives and displays the response.

[1364] The device analyzes the response received from the server and displays it in a format that is easy for the user to understand. For example, the procedure for transferring data from a smartphone might be displayed as text, images, and links.

[1365] Specific example

[1366] Data migration support

[1367] 1. The user enters the problem.

[1368] User: "I want to transfer my data to my new smartphone."

[1369] 2. The device sends the request to the server.

[1370] The device sends this request to the server as an HTTP request.

[1371] 3. The server receives the request.

[1372] The server receives the request and extracts the text, "I want to transfer data to a new smartphone."

[1373] 4. The server analyzes the problem.

[1374] The server uses a natural language processing engine to analyze the keyword "data migration" and understand the user's intent.

[1375] 5. The server generates or searches for answers.

[1376] The server searches the knowledge base for "Smartphone Data Migration Procedure" and generates the relevant information.

[1377] 6. The server sends the response back to the terminal.

[1378] The server sends the generated response data back to the terminal as an HTTP response.

[1379] 7. The device receives and displays the response.

[1380] The device visually displays the received responses, allowing the user to perform data migration while following the instructions.

[1381] This system allows users to smoothly complete the necessary tasks after signing a contract, reducing inquiries to stores and increasing user satisfaction. Furthermore, the server's natural language processing engine improves the accuracy of problem analysis, enabling the rapid provision of appropriate answers.

[1382] The following describes the processing flow.

[1383] Step 1:

[1384] Users enter the problem they need support for in text format into an input field on their device, such as a smartphone or computer. For example, "I don't know how to transfer data from my smartphone."

[1385] Step 2:

[1386] The terminal receives the text data entered by the user and generates an HTTP request to send it to the server. The request includes the user's input.

[1387] Step 3:

[1388] The device sends the generated HTTP request to the server's API endpoint. This request contains the user's problem and is delivered to the server for analysis.

[1389] Step 4:

[1390] The server receives an HTTP request sent from the terminal. The server extracts the user's input from the request body. Example: "I don't know how to transfer data from my smartphone."

[1391] Step 5:

[1392] The server uses a natural language processing engine to analyze the received text data. It tokenizes the text and extracts keywords and context. For example, it extracts keywords such as "data migration" and "smartphone."

[1393] Step 6:

[1394] Based on the analysis results, the server generates an answer suitable for the user's problem or searches the knowledge base or FAQ database. For example, it searches the knowledge base for "Smartphone data migration procedure".

[1395] Step 7:

[1396] The server prepares the generated or retrieved answers as HTTP responses and constructs the data to send back to the terminal. The answers should include specific instructions and relevant links.

[1397] Step 8:

[1398] The server returns the prepared response data to the terminal as an HTTP response. The response data is sent along with a status code (e.g., 200 OK).

[1399] Step 9:

[1400] The terminal receives an HTTP response from the server. It parses the response body and prepares the data for display to the user.

[1401] Step 10:

[1402] The device displays the received response data to the user. This data is displayed in a visually easy-to-understand format, such as text, images, and links, making it accessible to the user. For example, a data migration procedure manual is displayed, allowing the user to migrate data from their smartphone by following the instructions.

[1403] The above outlines the specific processing flow within the customer support system after the contract is signed.

[1404] (Example 1)

[1405] 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".

[1406] Traditional support systems often resulted in long waiting times between users entering a problem and receiving a solution, and sometimes even inadequate answers. This led to decreased user satisfaction and an increase in inquiries to the support center.

[1407] 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.

[1408] In this invention, the server includes means for an input form and a submit button for the user to enter a problem; means for the terminal to generate an HTTP request and send it to the server's endpoint; means for the server to extract the user's problem details from the request body; means for understanding the user's problem using a natural language processing engine; and means for searching for an answer by referring to a knowledge base or FAQ database. This enables the user to obtain an answer for problem resolution quickly and accurately, reduces inquiries to the support center, and improves user satisfaction.

[1409] A "user" refers to an individual or legal entity that uses a support system to input a problem and seek a solution.

[1410] "Device" refers to electronic devices used by users, such as smartphones, personal computers, and tablets.

[1411] A "server" refers to a remote computer that receives and processes requests sent by users.

[1412] An "input form" refers to an online input field where a user enters a question in text format.

[1413] The term "send button" refers to an interface element used to send entered text data to the server.

[1414] An "HTTP request" refers to a type of internet communication protocol used to send data from a user's device to a server.

[1415] An "endpoint" refers to an address, such as a URL or URI, that is accessible on a server to provide a specific function or service.

[1416] The "request body" refers to the data contained in the message portion of an HTTP request.

[1417] A "natural language processing engine" refers to software and technology that allows computers to understand and analyze human language.

[1418] A "knowledge base" refers to a database system that stores and makes searchable past information and data.

[1419] An "FAQ database" refers to a database that compiles frequently asked questions and their answers.

[1420] "HTTP response" refers to a type of internet communication protocol used by a server to send a response to a user's device.

[1421] This invention relates to a system for supporting tasks performed by customers after a contract has been signed. This system enables a series of processes in which the user inputs a problem in text format, sends the data to a server, the server analyzes the data, generates an answer, sends the answer back, and the terminal displays the answer to the user.

[1422] System Configuration

[1423] 1. The user enters the problem.

[1424] Users use devices such as smartphones or computers to enter the problem they need support for in text format. For example, they might enter a specific problem such as, "I want to transfer data to my new smartphone."

[1425] 2. The device sends the request to the server.

[1426] The terminal generates an HTTP request to send the entered text data to the server. This request includes the user's problem description.

[1427] 3. The server receives the request.

[1428] The server receives an HTTP request sent from the terminal. After receiving it, it extracts the user's problem details from the request body.

[1429] 4. The server analyzes the problem.

[1430] The server uses a natural language processing engine (e.g., Google Cloud Natural Language API or OpenAI's GPT-3) to analyze the text data entered by the user. Through this analysis, keywords and context are extracted to understand the user's problem.

[1431] 5. The server generates or searches for answers.

[1432] The server generates an appropriate answer to the user's problem based on the analysis results. Alternatively, it searches for the appropriate answer from a knowledge base or FAQ database (e.g., Zendesk). For example, it searches for and retrieves instructions on "how to transfer data from a smartphone."

[1433] 6. The server sends the response back to the terminal.

[1434] The server returns the generated or retrieved response data to the terminal as an HTTP response. This response data includes specific steps, links, and relevant resources for solving the problem.

[1435] 7. The device receives and displays the response.

[1436] The device analyzes the response received from the server and displays it in a format that is easy for the user to understand. For example, the procedure for transferring data from a smartphone might be displayed as text, images, and links.

[1437] Specific example

[1438] Data migration support

[1439] 1. The user enters the problem.

[1440] User: "I want to transfer my data to my new smartphone."

[1441] 2. The device sends the request to the server.

[1442] The device sends this request to the server as an HTTP request.

[1443] 3. The server receives the request.

[1444] The server receives the request and extracts the text, "I want to transfer data to a new smartphone."

[1445] 4. The server analyzes the problem.

[1446] The server uses a natural language processing engine to analyze the keyword "data migration" and understand the user's intent.

[1447] 5. The server generates or searches for answers.

[1448] The server searches the knowledge base for "Smartphone Data Migration Procedure" and generates the relevant information.

[1449] 6. The server sends the response back to the terminal.

[1450] The server sends the generated response data back to the terminal as an HTTP response.

[1451] 7. The device receives and displays the response.

[1452] The device visually displays the received responses, allowing the user to perform data migration while following the instructions.

[1453] This system allows users to smoothly complete the necessary tasks after signing a contract, reducing inquiries to stores and increasing user satisfaction. Furthermore, the server's natural language processing engine improves the accuracy of problem analysis, enabling the rapid provision of appropriate answers.

[1454] Example of a prompt

[1455] "Please tell me how to transfer data to a new smartphone."

[1456] By inputting this prompt into the generating AI model, specific and appropriate support content will be provided.

[1457] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1458] Step 1: The user enters the problem.

[1459] Users use their own devices (smartphones or computers) to enter the problem they need support for in text format. Specifically, they type "I want to transfer data to a new smartphone" into the input form on their browser and click the submit button. This action generates text as input data.

[1460] Step 2: The device sends the request to the server.

[1461] The terminal generates an HTTP POST request to send the entered text data to the server. This request contains the problem details entered by the user. Specifically, the browser captures the user's input, stores it in the request body, and sends it to the specified server endpoint.

[1462] Step 3: The server receives the request.

[1463] The server receives an HTTP request sent from the terminal. The request contains text data entered by the user. The server extracts the text "I want to transfer data to a new smartphone" from the request body. Specifically, a web server that processes HTTP requests (such as Apache or Nginx) receives the request and parses its contents.

[1464] Step 4: The server analyzes the problem.

[1465] The server uses a natural language processing engine (such as Google Cloud Natural Language API or OpenAI's GPT-3) to analyze the text data entered by the user. Based on the analysis, keywords and context are extracted to understand the user's intent. Specifically, the extracted text data is passed to the natural language processing engine, which then extracts keywords such as "data migration" and "smartphone."

[1466] Step 5: The server generates or searches for an answer.

[1467] The server generates appropriate answers to the user's problem based on the analysis results. Alternatively, it searches for appropriate answers in a knowledge base or FAQ database (e.g., Zendesk). Specifically, it queries the knowledge base for "smartphone data migration procedure" and retrieves relevant procedures and answers. It also utilizes a generative AI model to generate answers as needed.

[1468] Step 6: The server sends the response back to the terminal.

[1469] The server returns the generated or retrieved answer data to the terminal as an HTTP response. The response data includes specific steps for solving the problem and relevant links. Specifically, the server formats the retrieved or generated answer as an HTTP response and sends it to the user's terminal.

[1470] Step 7: The device receives and displays the response.

[1471] The device analyzes the response received from the server and displays it in a format that is easy for the user to understand. Specifically, the browser receives the HTTP response from the server and displays it as text, images, and links. For example, "Smartphone data migration procedure" might be displayed in bullet points, along with links to related support pages.

[1472] (Application Example 1)

[1473] 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".

[1474] Traditional text-based customer support systems have the challenge of not being able to respond quickly and accurately to user problems. As a result, users do not receive adequate support, which in turn leads to decreased customer satisfaction. Furthermore, there was a need for a system that efficiently provides support information to resolve issues related to products purchased by users on e-commerce sites and other platforms.

[1475] 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.

[1476] In this invention, the server includes means for parsing queries and generating or retrieving appropriate answers from a knowledge base or FAQ database, means for returning the generated or retrieved answers to the terminal, and means for the terminal to visually display the answers. This makes it possible to efficiently resolve user problems and improve customer satisfaction.

[1477] 1. A "user" is someone who attempts to solve a problem using the system.

[1478] 2. "Text format" refers to a format that uses character data to represent information.

[1479] 3. "Terminal" refers to a device such as a computer or smartphone used by a user.

[1480] 4. A "server" is a computer system that receives requests from terminals and performs analysis and generates responses.

[1481] 5. A "natural language processing engine" is a software technology used to analyze text data and understand its meaning.

[1482] 6. A "knowledge base" is a database in which solutions to problems are systematically compiled.

[1483] 7. An "FAQ database" is a database that compiles frequently asked questions and their answers.

[1484] 8. An "HTTP request" is one of the protocols used to exchange data between a client and a server.

[1485] 9. "Answer generation" is the process of creating appropriate solutions to the analyzed problem.

[1486] 10. "Searching" is the process of finding the desired information from a database.

[1487] 11. "Visual display" refers to the process of providing information to users in an easily understandable format.

[1488] This invention is a system designed to support tasks performed by customers after a contract has been signed. It enables a series of processes in which the user inputs a problem in text format, sends that data to a server, the server analyzes it, generates an answer, sends the answer back, and the terminal displays the answer to the user.

[1489] Hardware and software to use

[1490] Hardware:

[1491] smartphone

[1492] Cloud Server

[1493] software:

[1494] Mobile app frameworks (React Native, Flutter, etc.)

[1495] Server-side frameworks (Node.js, Django, etc.)

[1496] Natural language processing engines (Google NLP, IBM Watson, OpenAI GPT-4, etc.)

[1497] System Overview

[1498] 1. The user enters the problem.

[1499] Users enter their problems in text format using a smartphone application. An example of such a problem is, "My new vacuum cleaner isn't working."

[1500] 2. The device sends a problem.

[1501] The smartphone sends the user-entered question to the server as an HTTP request. The request includes the text data entered by the user.

[1502] 3. The server receives and parses the request.

[1503] After receiving an HTTP request, the server uses a natural language processing engine to analyze the text data. Through this analysis, it extracts keywords and context related to the problem, thereby understanding its content.

[1504] 4. The server generates or searches for answers.

[1505] Based on the analysis results, the server generates or searches for appropriate answers from the knowledge base or FAQ database. For example, it searches for and retrieves troubleshooting information for a case where "the new vacuum cleaner isn't working."

[1506] 5. The server sends the response.

[1507] The server returns the generated or retrieved response data to the terminal as an HTTP response. The response data includes specific steps and related resources.

[1508] 6. The device displays the answer.

[1509] The smartphone analyzes the received response and displays it in a format that is easy for the user to understand. For example, it may display it in the form of text, images, or video links.

[1510] Specific example

[1511] When a user enters "My new vacuum cleaner isn't working," the following process is executed.

[1512] 1. User enters the problem: "My new vacuum cleaner isn't working."

[1513] 2. The device sends the request to the server.

[1514] 3. The server receives the request and analyzes the problem.

[1515] 4. Use a natural language processing engine to extract the keywords "vacuum cleaner" and "not working".

[1516] 5. Search for information on "vacuum cleaner troubleshooting" in the knowledge base or FAQ database.

[1517] 6. The server generates an appropriate response and sends it back to the terminal.

[1518] 7. Smartphones visually display the answers.

[1519] Example of a prompt

[1520] "The vacuum cleaner I recently bought isn't working at all. What should I do?"

[1521] As described above, this system enables users to efficiently resolve problems they face after signing a contract, thereby contributing to improved customer satisfaction.

[1522] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1523] Step 1:

[1524] The user enters the problem in text format. The user uses a smartphone application to enter the problem into a text box. For example, the user might enter "My new vacuum cleaner isn't working." The input data is saved in text format.

[1525] Step 2:

[1526] The terminal sends the entered text data to the server. The terminal generates an HTTP POST request containing the entered text data and sends it to the server. The input data is sent to the server, and an HTTP request is generated as output data from the terminal.

[1527] Step 3:

[1528] The server receives the request. The server receives the HTTP request and extracts the text data entered by the user from its body. The input data is the HTTP request, and the output data is the extracted problem text.

[1529] Step 4:

[1530] The server analyzes the received data using a natural language processing engine. The server uses a natural language processing engine (e.g., OpenAI GPT-4) to analyze the problem text and extract keywords and context. The input data is text data, and the output data is the analysis results, specifically extracted keywords (e.g., "vacuum cleaner," "doesn't work").

[1531] Step 5:

[1532] The server generates or retrieves appropriate answers from a knowledge base or FAQ database. Based on the analysis results, the server searches for relevant information from the knowledge base or FAQ database and generates appropriate answers. The input data is the analysis results, and the output data is the generated answers (e.g., a vacuum cleaner troubleshooting guide).

[1533] Step 6:

[1534] The server sends the generated or retrieved answer back to the terminal. The server generates an HTTP response containing the generated or retrieved answer and sends it back to the terminal. The input data is the generated answer, and the output data is the HTTP response.

[1535] Step 7:

[1536] The device analyzes the received response and displays it visually to the user. The device analyzes the received HTTP response and extracts the response data. The extracted data is displayed to the user in a visually easy-to-understand format such as text, images, and links. The input data is the HTTP response, and the output data is visually displayed information (e.g., a vacuum cleaner troubleshooting guide).

[1537] 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.

[1538] This invention relates to a system for supporting tasks performed by customers after a contract has been signed. This system combines a series of processes—where the user inputs a problem in text format, sends the data to a server, the server analyzes, generates, and returns the answer, and the terminal displays the answer to the user—with an emotion engine that recognizes the user's emotions. This configuration reduces the stress and difficulties the user experiences and provides more appropriate support.

[1539] System Configuration

[1540] 1. The user enters the problem.

[1541] Users use devices such as smartphones or computers to enter the problem they need support for in text format. For example, "I don't know how to transfer data from my smartphone."

[1542] 2. The device sends the request to the server.

[1543] The terminal generates an HTTP request to send the entered text data to the server. This request includes the user's input.

[1544] 3. The server receives the request.

[1545] The server receives an HTTP request sent from the terminal and extracts the user's input from the request body.

[1546] 4. The server analyzes the problem.

[1547] The server uses a natural language processing engine to analyze the received text data. It tokenizes the text and extracts keywords and context.

[1548] 5. The server uses an emotion engine for emotion recognition.

[1549] The server uses an emotion engine to recognize the user's emotions based on the analyzed text data. For example, it can detect feelings of frustration or confusion from text such as "I don't know how to transfer data on my smartphone."

[1550] 6. The server generates or searches for answers.

[1551] Based on the analysis results and sentiment recognition, the server generates an appropriate response to the user's problem or searches its knowledge base or FAQ database. It also adjusts the response's tone and content to match the user's psychological state, reflecting the sentiment recognition results. For example, if the user is highly frustrated, it provides detailed and helpful instructions.

[1552] 7. The server sends the response back to the terminal.

[1553] The server prepares the generated or retrieved response data as an HTTP response and constructs the data to be sent back to the terminal. The response should include specific steps and relevant links.

[1554] 8. The device receives and displays the response.

[1555] The device analyzes the HTTP response received from the server and displays it in a user-friendly format. For example, instructions for migrating data from a smartphone are displayed as text, images, and links. It also displays messages and additional support information that are tailored to the user's emotional state.

[1556] Specific example

[1557] Sentiment Recognition in Data Migration Support

[1558] 1. The user enters the problem.

[1559] User: "I want to transfer my data to my new smartphone, but I don't know how."

[1560] 2. The device sends the request to the server.

[1561] The device sends this request to the server as an HTTP request.

[1562] 3. The server receives the request.

[1563] The server receives the request and extracts the text, "I want to transfer data to my new smartphone, but I don't know how."

[1564] 4. The server analyzes the problem.

[1565] The server uses a natural language processing engine to analyze the keyword "data migration" and understand the user's intent.

[1566] 5. The server uses an emotion engine for emotion recognition.

[1567] The server uses an emotion engine to detect user frustration from the text and determines that the user is likely confused.

[1568] 6. The server generates or searches for answers.

[1569] To alleviate frustration, the server searches its knowledge base for detailed and helpful data migration instructions, along with additional support messages.

[1570] 7. The server sends the response back to the terminal.

[1571] The server sends the generated response data back to the terminal as an HTTP response.

[1572] 8. The device receives and displays the response.

[1573] The device visually displays the received responses. It also displays easy-to-follow instructions and encouraging messages to help users perform data migration while following the steps.

[1574] This system allows users to smoothly complete the necessary tasks after signing a contract, reducing inquiries to stores and increasing user satisfaction. The server's natural language processing and emotion engines enable problem analysis and appropriate psychological responses, providing even more advanced support.

[1575] The following describes the processing flow.

[1576] Step 1:

[1577] Users enter the problem they need support for in text format into an input field on their device, such as a smartphone or computer. For example, they might enter, "I don't know how to transfer data from my smartphone."

[1578] Step 2:

[1579] The terminal receives the entered text data and generates an HTTP request to send it to the server. The request contains the user's input.

[1580] Step 3:

[1581] The device sends the generated HTTP request to the server's API endpoint. This request contains the user's problem and is delivered to the server for analysis.

[1582] Step 4:

[1583] The server receives an HTTP request sent from the terminal. The server extracts the user's input from the request body. For example, it might extract the text "I don't know how to transfer data from my smartphone."

[1584] Step 5:

[1585] The server uses a natural language processing engine to analyze the received text data. It tokenizes the text and extracts keywords and context. For example, it extracts keywords such as "data migration" and "smartphone."

[1586] Step 6:

[1587] The server uses an emotion engine to recognize the user's emotions based on the analyzed text data. For example, the emotion engine detects the user's frustration or confusion from the text, "I don't know how to transfer data from my smartphone."

[1588] Step 7:

[1589] The server generates an appropriate answer to the user's problem based on the results of natural language processing and sentiment recognition, or searches a knowledge base or FAQ database. It then adjusts the tone and content of the answer to match the user's psychological state, reflecting the results of sentiment recognition.

[1590] Step 8:

[1591] The server prepares the generated or retrieved response data as an HTTP response and constructs the data to be sent back to the terminal. The response should include specific steps and relevant links.

[1592] Step 9:

[1593] The server returns the prepared response data to the terminal as an HTTP response. The response data is sent along with a status code (e.g., 200 OK).

[1594] Step 10:

[1595] The terminal receives an HTTP response from the server. It parses the response body and prepares the data for display to the user.

[1596] Step 11:

[1597] The device visually displays the received response data to the user. For example, it may be displayed in a visually easy-to-understand format such as text, images, and links, making it accessible to the user. It also displays messages and additional support information that correspond to the user's emotional state.

[1598] The above outlines the specific processing flow in a support system that incorporates an emotion engine to recognize user emotions.

[1599] (Example 2)

[1600] 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".

[1601] Traditional support systems often fail to adequately mitigate the stress and difficulties users experience, resulting in inadequate support. In particular, providing answers that disregard the user's feelings can exacerbate their dissatisfaction and confusion. Therefore, a system is needed that can properly analyze user problems and provide support tailored to their emotional needs.

[1602] 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.

[1603] In this invention, the server includes means for analyzing received data and analyzing the problem content using a natural language processing engine, means for recognizing the user's emotions using an emotion engine, and means for querying a knowledge base or FAQ database to search for an appropriate answer and adjusting the content according to the user's emotions. This makes it possible to accurately understand the user's problem and provide an answer that takes their emotions into consideration.

[1604] A "user" refers to an individual or legal entity that attempts to resolve a problem using the support system.

[1605] A "problem" refers to an issue or question that a user wants to resolve, and the content of that issue.

[1606] "Text format" refers to a format in which input is presented as a string of characters.

[1607] "Terminal" refers to computing devices such as computers, smartphones, and tablets used by users.

[1608] A "server" refers to a computer device that receives and processes information sent from a user's terminal.

[1609] "Analysis" refers to the process by which a server interprets the data it receives and understands its meaning.

[1610] A "natural language processing engine" refers to software that analyzes text data and extracts keywords and context.

[1611] An "emotion engine" refers to software that recognizes emotions from a user's text data.

[1612] A "knowledge base" refers to a database that stores information and solutions related to user problems.

[1613] An "FAQ database" refers to a database that compiles frequently asked questions and their answers.

[1614] An "HTTP request" refers to the protocol used by a device to send information to a server.

[1615] "HTTP response" refers to the protocol used by a server to send information back to a terminal.

[1616] "Tokenization" refers to the process of dividing text into the smallest meaningful units.

[1617] A "prompt message" refers to a sentence that expresses a question or instruction that the user will input.

[1618] A "generative AI model" refers to an artificial intelligence model that performs natural language processing and generates text tailored to a specific task.

[1619] This invention relates to a system for supporting tasks performed by customers after a contract has been signed. The system performs a series of processes in which the user inputs a problem in text format, sends the text data to a server, the server analyzes the data, generates or searches for an appropriate answer, sends the answer back to the terminal, and finally the terminal displays the answer to the user. Furthermore, by incorporating an emotion engine that recognizes the user's emotions, more appropriate support can be provided.

[1620] Hardware and software to use

[1621] hardware

[1622] Devices: PCs, smartphones, tablets, etc.

[1623] Server: A high-performance computing device (equipped with a CPU, memory, and storage).

[1624] software

[1625] Natural language processing engines: SpaCy, NLTK, etc.

[1626] Emotion engines: IBM Watson, Microsoft Azure Text Analytics, etc.

[1627] Knowledge base / FAQ database: Zendesk, Freshdesk, etc.

[1628] Generative AI models: GPT-3, etc.

[1629] Communication protocol: HTTP / HTTPS.

[1630] System Configuration

[1631] This system was configured as follows:

[1632] 1. The user enters the problem.

[1633] Users use devices such as smartphones or computers to enter the problem they need support for in text format. Specifically, they type "I don't know how to transfer data from my smartphone" into the text box and click the submit button.

[1634] 2. The device sends the request to the server.

[1635] The device sends the text data entered by the user to the server as an HTTP request. Specifically, it uses the HTTP POST method to generate an HTTP request that includes the text data in the request body and sends it to the server's API endpoint.

[1636] 3. The server receives the request.

[1637] The server receives HTTP requests sent from the terminal and extracts user input from the request body. Specifically, it uses a web framework (e.g., Django, Flask) to parse the request data and extract the text.

[1638] 4. The server analyzes the problem.

[1639] The server analyzes the received text data using a natural language processing engine (e.g., SpaCy). For example, it analyzes the text "I don't know how to transfer data from my smartphone" and extracts keywords and context such as "data transfer."

[1640] 5. The server uses an emotion engine for emotion recognition.

[1641] The server uses an emotion engine (e.g., IBM Watson) based on the analyzed text data to recognize the user's emotions. For example, it can detect user frustration from text such as "I don't know how to transfer data from my smartphone."

[1642] 6. The server generates or searches for answers.

[1643] The server searches for appropriate answers from knowledge bases and FAQ databases (e.g., Zendesk) based on the analysis results and sentiment recognition results. Alternatively, it uses generative AI models (e.g., GPT-3) to generate customized answers. The answers are tailored to the user's emotional state. For example, if the user is feeling frustrated, an answer with detailed and helpful instructions will be provided.

[1644] 7. The server sends the response back to the terminal.

[1645] The server prepares the generated or retrieved answer data as an HTTP response and sends it back to the terminal. Specifically, it formats the answer data in JSON format and sends it as an HTTP response.

[1646] 8. The device receives and displays the response.

[1647] The device analyzes the HTTP response received from the server and displays it in a format that is easy for the user to understand. Specifically, it formats the received data as text, images, and links and displays them to the user. For example, "Smartphone Data Migration Procedure" is displayed step by step. Encouraging messages tailored to the user's emotions are also displayed.

[1648] Specific example

[1649] Sentiment Recognition in Data Migration Support

[1650] 1. The user enters the problem.

[1651] User: "I want to transfer my data to my new smartphone, but I don't know how."

[1652] 2. The device sends the request to the server.

[1653] The device sends this request to the server as an HTTP request.

[1654] 3. The server receives the request.

[1655] The server receives the request and extracts the text, "I want to transfer data to my new smartphone, but I don't know how."

[1656] 4. The server analyzes the problem.

[1657] The server uses a natural language processing engine to analyze the keyword "data migration" and understand the user's intent.

[1658] 5. The server uses an emotion engine for emotion recognition.

[1659] The server uses an emotion engine to detect user frustration from the text and determines that the user is likely confused.

[1660] 6. The server generates or searches for answers.

[1661] To alleviate frustration, the server searches its knowledge base for detailed and helpful data migration instructions, along with additional support messages.

[1662] 7. The server sends the response back to the terminal.

[1663] The server sends the generated response data back to the terminal as an HTTP response.

[1664] 8. The device receives and displays the response.

[1665] The device visually displays the received responses. It also displays easy-to-understand instructions and encouraging messages so that users can perform the data migration while following the steps.

[1666] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1667] Step 1:

[1668] The user enters the problem.

[1669] Input: The user enters the problem they need support for in text format (e.g., "I don't know how to transfer data from my smartphone").

[1670] Specific actions: The user uses a smartphone or computer, enters the question into a text box, and clicks the submit button.

[1671] Output: Text data entered into the terminal.

[1672] Step 2:

[1673] The device sends the request to the server.

[1674] Input: Text data entered by the user.

[1675] Specific operation: The terminal sends the entered text data to the server as an HTTP POST request. Specifically, it includes the entered text data in the request body and sends it to the server's API endpoint.

[1676] Output: HTTP request sent to the server.

[1677] Step 3:

[1678] The server receives the request.

[1679] Input: HTTP request sent from the terminal.

[1680] Specific operation: The server uses a web framework to receive HTTP requests and extracts user input text from the request body.

[1681] Output: Extracted text data.

[1682] Step 4:

[1683] The server analyzes the problem.

[1684] Input: Extracted text data.

[1685] Specific operation: The server calls a natural language processing engine (e.g., SpaCy) to parse and tokenize the text data, and extract keywords and context. Specifically, it extracts the keyword "data migration" from the text "I don't know how to migrate data on my smartphone."

[1686] Output: Extracted keywords and context.

[1687] Step 5:

[1688] The server uses an emotion engine for emotion recognition.

[1689] Input: Extracted keywords or context.

[1690] Specific operation: The server invokes an emotion engine (e.g., IBM Watson) to recognize emotions such as frustration and confusion from the user's text data. For example, it might detect frustration from the phrase "I don't know how to transfer data from my smartphone."

[1691] Output: Recognized emotion data.

[1692] Step 6:

[1693] The server generates or searches for answers.

[1694] Input: Recognized sentiment data and extracted keywords or context.

[1695] Specific operation: The server queries a knowledge base or FAQ database to find the appropriate answer, or generates an answer using a generative AI model (e.g., GPT-3). Based on sentiment data, it adjusts the content and tone of the answer. For example, it provides detailed and courteous data migration instructions.

[1696] Output: Generated or retrieved response data.

[1697] Step 7:

[1698] The server sends the response back to the terminal.

[1699] Input: Generated or retrieved response data.

[1700] Specific operation: The server formats the generated response data in JSON format and sends it to the terminal as an HTTP response.

[1701] Output: HTTP response sent to the terminal.

[1702] Step 8:

[1703] The device receives and displays the response.

[1704] Input: HTTP response sent from the server.

[1705] Specific operation: The terminal analyzes the received response data and displays it to the user in an easy-to-understand format. Specifically, it formats it as text, images, and links to visually display data migration procedures and encouraging messages.

[1706] Output: User-recognizable response information.

[1707] (Application Example 2)

[1708] 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".

[1709] Traditional support systems were limited to basic functions such as users entering problems and receiving answers. However, this often failed to adequately alleviate the stress and difficulties users experienced. In particular, failing to consider the emotions users felt regarding the problems they faced meant that the support provided often did not fully meet their needs, making it difficult to increase user satisfaction. Current systems require the provision of specific and emotionally responsive support aimed at resolving problems.

[1710] 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.

[1711] In this invention, the server includes means for the user to input a problem in text format, means for the terminal to transmit the input text data to the server, means for the server to analyze the received data and generate or retrieve an appropriate answer, means for the server to return the generated or retrieved answer to the terminal, means for the terminal to visually display the received answer to the user, and means for the server to recognize the user's emotions using an emotion recognition engine and adjust the answer based on the result. This enables the provision of detailed support that responds to the user's emotions, and allows for quick and effective problem solving.

[1712] A "user" refers to an end-user who enters a problem and requests support.

[1713] "Text format" refers to a method of representing information using character data.

[1714] "Device" refers to a device used by a user, such as a smartphone, tablet, or personal computer.

[1715] A "server" refers to a computer system that processes requests sent by users, generates or searches for appropriate answers, and sends them back to the terminal.

[1716] "Analysis" refers to the process of understanding received data and identifying its meaning and intent.

[1717] "Generating or searching" refers to the act of creating a new, appropriate answer or finding suitable information from an existing knowledge base or database.

[1718] "Returning" refers to the act of sending a response generated or retrieved by the server to the terminal.

[1719] "Visual display" refers to methods of providing information to users using text, images, icons, etc.

[1720] An "emotion recognition engine" refers to a software component that detects a user's emotions from text data and takes appropriate action based on the results.

[1721] A "natural language processing engine" refers to a software component that analyzes text data and understands its meaning and intent.

[1722] A "knowledge base" refers to a database containing information and answers that have been stored in advance.

[1723] An "FAQ database" refers to a database containing frequently asked questions and their answers.

[1724] This invention is a system for quickly resolving problems that users face in food delivery services. Specific embodiments of this system are described below.

[1725] First, users use a device such as a smartphone or computer to input their problem in text format. For example, they describe the problem they are facing specifically, such as, "My delivery is delayed, but I don't know what to do."

[1726] The text data entered by the user is sent from the terminal to the server. This communication is performed using HTTP requests. The data received by the server is first parsed by a natural language processing engine to understand its content. Specifically, the text data is tokenized, and keywords and context are extracted.

[1727] Next, the server uses an emotion recognition engine to recognize emotions from the user's input. IBM Watson Tone Analyzer, for example, can be used as this emotion recognition engine. The user's emotional state is identified from the analysis results. For example, from the input "The delivery is delayed," the user's anxiety or frustration might be detected.

[1728] The server then generates or searches its knowledge base or FAQ database for an appropriate answer to the user's problem. At this stage, the tone and content of the answer are adjusted to match the user's psychological state, taking into account the results of sentiment recognition. For example, if the user is feeling frustrated, the server will provide very polite and specific instructions.

[1729] Once the answer is confirmed, the server sends it back to the terminal. The terminal then displays the received answer to the user visually. This display method may include text, images, links, etc.

[1730] As a concrete example, consider a case where a user enters "My delivery is delayed, and I don't know what to do." The emotion recognition engine recognizes the user's frustration, and the server generates a polite message such as, "We will look into this immediately, please wait a moment." This enables a more personalized response tailored to the user's emotions, improving user satisfaction.

[1731] Furthermore, examples of prompt statements to be input to the generative AI model are as follows:

[1732] "A user typed, 'My delivery is very late, what should I do?' Please provide an appropriate response that reflects their feelings."

[1733] In this way, this invention provides a system for food delivery services that enables quick and effective problem solving while taking into consideration the user's feelings.

[1734] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1735] Step 1:

[1736] The user enters the problem in text format.

[1737] Users use devices such as smartphones and computers to input specific problems in text, such as "My delivery is delayed, and I don't know what to do." They may also describe their anxieties and frustrations in detail.

[1738] Input: Text format issue from user

[1739] Output: Saving text data to the terminal

[1740] Step 2:

[1741] The terminal sends the entered text data to the server.

[1742] The terminal generates an HTTP request and sends the entered text data to the server. This request includes the user's input and is sent to the server in the appropriate format.

[1743] Input: Text data saved on the device

[1744] Output: HTTP request to the server

[1745] Step 3:

[1746] The server analyzes the data it receives.

[1747] The server receives an HTTP request and extracts text data from its body. This text data is then input into a natural language processing engine for tokenization, keyword extraction, and contextual analysis.

[1748] Input: Text data extracted from an HTTP request

[1749] Output: Analyzed keywords and contextual information

[1750] Step 4:

[1751] The server uses an emotion recognition engine to recognize the user's emotions.

[1752] Text data analyzed using natural language processing is passed to an emotion recognition engine to detect the user's emotions. For example, emotions such as "frustration" or "confusion" can be identified. IBM Watson Tone Analyzer can be used as the emotion recognition engine.

[1753] Input: Parsed text data

[1754] Output: Emotion recognition result (e.g., frustration)

[1755] Step 5:

[1756] The server generates the appropriate answer or searches for it in the knowledge base or FAQ database.

[1757] The server uses the emotion recognition results and analyzed text data to generate an appropriate response or search for relevant information in existing knowledge bases or FAQ databases. It prepares responses that include the appropriate tone and content for the emotion.

[1758] Input: Analyzed text data and sentiment recognition results

[1759] Output: Generated answers or search results from the database

[1760] Step 6:

[1761] The server sends the generated or retrieved answer back to the terminal.

[1762] The server prepares the response as an HTTP response and sends it back to the terminal. The response is structured in a format that is easily understandable to the user.

[1763] Input: Generated or retrieved response data

[1764] Output: HTTP response

[1765] Step 7:

[1766] The device visually displays the received response to the user.

[1767] The device receives an HTTP response, parses its contents, and displays them visually to the user. The display format includes text, images, and links. Messages tailored to the user's emotional state are also displayed.

[1768] Input: Response data extracted from HTTP response

[1769] Output: A display that the user can visually confirm.

[1770] 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.

[1771] 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.

[1772] 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 robot 414.

[1773] 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.

[1774] 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.

[1775] 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.

[1776] 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.

[1777] 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.

[1778] 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."

[1779] 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.

[1780] 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.

[1781] 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.

[1782] 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.

[1783] 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.

[1784] 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.

[1785] 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.

[1786] 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.

[1787] 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.

[1788] 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.

[1789] 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.

[1790] 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 as being incorporated by reference.

[1791] The following is further disclosed regarding the embodiments described above.

[1792] (Claim 1)

[1793] A means for the user to enter the problem in text format,

[1794] A means for the terminal to send the entered text data to the server,

[1795] A means for analyzing data received by the server and generating or searching for an appropriate response,

[1796] A means of sending the server-generated or searched answer back to the terminal,

[1797] A means of visually displaying the response received by the terminal to the user,

[1798] A system that includes this.

[1799] (Claim 2)

[1800] The system according to claim 1, further comprising means for the server to analyze user input using a natural language processing engine.

[1801] (Claim 3)

[1802] The system according to claim 1, further comprising means for the server to query a knowledge base or FAQ database and retrieve an appropriate answer.

[1803] "Example 1"

[1804] (Claim 1)

[1805] A means for the user to enter the problem in text format,

[1806] A means for the terminal to send the entered text data to the server,

[1807] A means for analyzing data received by the server and generating or searching for an appropriate response,

[1808] A means of sending the server-generated or searched answer back to the terminal,

[1809] A means of visually displaying the response received by the terminal to the user,

[1810] A means including an input form and a submit button for the user to enter a question,

[1811] A means by which a terminal generates an HTTP request and sends it to the server's endpoint,

[1812] A means for the server to extract the user's problem details from the request body,

[1813] The server uses a natural language processing engine to understand the user's problem,

[1814] A means by which the server searches for answers by referring to a knowledge base or FAQ database,

[1815] A means of parsing and displaying the response data received by the terminal as an HTTP response,

[1816] A system that includes this.

[1817] (Claim 2)

[1818] The system according to claim 1, further comprising means for the server to analyze user input using a natural language processing engine.

[1819] (Claim 3)

[1820] The system according to claim 1, further comprising means for the server to query a knowledge base or FAQ database and retrieve an appropriate answer.

[1821] "Application Example 1"

[1822] Additional claims

[1823] (Claim 1)

[1824] A means for the user to enter the problem in text format,

[1825] A means for the terminal to send the entered text data to the server,

[1826] A means for analyzing data received by the server and generating or searching for an appropriate response,

[1827] A means of sending the server-generated or searched answer back to the terminal,

[1828] A means of visually displaying the response received by the terminal to the user,

[1829] A means by which the server searches for a solution in a database and returns the generated answer,

[1830] A means by which the device uses a natural language processing engine to display the answer to the user,

[1831] A system that includes this.

[1832] (Claim 2)

[1833] The system according to claim 1, further comprising means for the server to analyze user input using a natural language processing engine.

[1834] (Claim 3)

[1835] The system according to claim 1, further comprising means for the server to query a knowledge base or FAQ database and retrieve an appropriate answer.

[1836] "Example 2 of combining an emotion engine"

[1837] (Claim 1)

[1838] A means for the user to enter the problem in text format,

[1839] A means for the terminal to send the entered text data to the server,

[1840] A means for analyzing the data received by the server and analyzing the problem content using a natural language processing engine,

[1841] A means by which the server recognizes the user's emotions using the analysis results and the emotion engine,

[1842] The server queries a knowledge base or FAQ database, searches for appropriate answers, and adjusts the content according to the user's sentiment.

[1843] A means of sending the server-generated or searched answer back to the terminal,

[1844] A means of visually displaying the response received by the terminal to the user,

[1845] A system that includes this.

[1846] (Claim 2)

[1847] The system according to claim 1, further comprising means for the server to tokenize user input using a natural language processing engine and extract keywords and context.

[1848] (Claim 3)

[1849] The system according to claim 1, further comprising means for the server to use an emotion engine to evaluate the user's emotions and adjust the tone and content of the response based on the results.

[1850] "Application example 2 when combining with an emotional engine"

[1851] (Claim 1)

[1852] A means for the user to enter the problem in text format,

[1853] A means for the terminal to send the entered text data to the server,

[1854] A means for analyzing data received by the server and generating or searching for an appropriate response,

[1855] A means of sending the server-generated or searched answer back to the terminal,

[1856] A means of visually displaying the response received by the terminal to the user,

[1857] A means by which a server uses an emotion recognition engine to recognize the user's emotions and adjusts its response based on the results,

[1858] A system that includes this.

[1859] (Claim 2)

[1860] The system according to claim 1, further comprising means for the server to analyze user input using a natural language processing engine.

[1861] (Claim 3)

[1862] The system according to claim 1, further comprising means for the server to query a knowledge base or FAQ database and retrieve an appropriate answer. [Explanation of Symbols]

[1863] 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 the user to enter the problem in text format, A means for the terminal to send the entered text data to the server, A means for analyzing data received by the server and generating or searching for an appropriate response, A means of sending the server-generated or searched answer back to the terminal, A means of visually displaying the response received by the terminal to the user, A system that includes this.

2. The system according to claim 1, further comprising means for the server to analyze user input using a natural language processing engine.

3. The system according to claim 1, further comprising means for the server to query a knowledge base or FAQ database and retrieve an appropriate answer.

Images