system

Abstract

We provide the system. [Solution] A means for a user to input a support request using an information device, A means for receiving and storing the aforementioned support request, A means for analyzing the content of the aforementioned support request and searching for an appropriate solution, A means for presenting the aforementioned solution to the user, Means of collecting user feedback, Based on the aforementioned feedback, a means of escalating the matter to a support agent as needed, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a conventional support center system, the response to a support request from a user is often delayed, and particularly in private companies and individual users, quick support is required. In addition, the burden on support agents is large, and human errors and missed responses are likely to occur. As a result, there are problems such as a decline in the quality of support and a decline in user satisfaction. Furthermore, it is difficult to achieve 24 / 7 / 365 continuous support, and there are restrictions on the provision of support. Therefore, it is necessary to develop a new system that solves these problems and provides efficient and high-quality support.

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 support request using an information device, means for receiving and storing the support request, means for analyzing the content of the support request and searching for an appropriate solution, means for presenting the solution to the user, means for collecting feedback from the user, and means for escalating to a support agent as necessary based on the feedback. Specifically, by using natural language processing technology as the analysis means to understand the content of the support request and presenting a solution based on past support data and an FAQ database, a quick and accurate response becomes possible. Furthermore, the escalation means can automatically request support agents to handle difficult problems, thereby improving the quality of support. With this system, 24 / 7 support can be realized, and improvements in user satisfaction and reduction of the burden on support agents can be expected.

[0006] A "user" is an individual or legal entity that uses the system to submit a support request.

[0007] "Information device" refers to an electronic device used by a user to input and submit support requests, and includes PCs, smartphones, tablets, etc.

[0008] A "support request" is data that shows the content of inquiries and problem reports submitted by users to the system.

[0009] "Means" refers to a functional block or process designed to perform a specific function or operation within the scope of the patent claims.

[0010] "Receiving" refers to the process by which the system takes in support requests sent by users.

[0011] "Saving" refers to the process of registering and storing received support requests in a system database or similar location.

[0012] "Analysis" refers to the process of deciphering the content of received support requests and extracting keywords and important information.

[0013] "Searching" refers to the process of finding solutions from databases and information resources based on information obtained through analysis.

[0014] "Solution" refers to information that outlines specific countermeasures and procedures for responding to a user's support request.

[0015] "Presentation" refers to the process of displaying or notifying the user of the searched solution through the system.

[0016] "Feedback" refers to the process by which users send their evaluations and opinions regarding the solutions and support provided back to the system.

[0017] "Escalation" refers to the process by which the system automatically determines that a problem is difficult to resolve and requests assistance from a support agent.

[0018] "Natural language processing technology" refers to the technology that enables computers to understand and analyze human language.

[0019] A "support database" is a database that stores past support history and solutions, and manages them in a searchable format.

[0020] An "FAQ database" is a database that collects frequently asked questions and their answers and manages them in an accessible format.

[0021] A "support agent" refers to a human operator responsible for handling support requests that the system could not resolve.

[0022] The "system" refers to the overall mechanism that automatically processes a series of processes from the reception to the resolution, feedback, and escalation of support requests.

Brief Explanation of Drawings

[0023] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when the emotion engine is combined. [Figure 14]This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0024] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0025] First, let's explain the terminology used in the following explanation.

[0026] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, 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), and APU (Accelerated Processing Unit).

[0027] 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.

[0028] 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.

[0029] 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).

[0030] 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."

[0031] [First Embodiment]

[0032] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0033] 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.

[0034] 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).

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0040] 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.

[0041] 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.

[0042] 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.

[0043] 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".

[0044] This invention relates to a system in which a user enters a support request using an information device, a server receives and analyzes the request, presents a solution, and escalates it to a support agent as necessary.

[0045] Users access the support center system using information devices such as PCs, smartphones, or tablets. Through the provided user interface, users create a new account and enter the required information. Once registration is complete, the server saves the entered information to a database and sends a verification email to the user. Users verify their account by clicking the link in the verification email.

[0046] When a user logs into the system, a support request form is displayed, and the user enters details of the problem, screenshots, etc. For example, they may enter information about software error messages or system malfunctions. Once the user submits the request, the server receives it and stores it in the database.

[0047] Next, an AI module on the server analyzes the content of the support request. Specifically, it uses natural language processing technology to understand the content of the request and extract keywords and important phrases. Based on this analysis, the server searches its past support database and FAQ database for the best solution. For example, it searches for information such as "how to reset a password" or "how to deal with a specific error message."

[0048] The search results list multiple possible solutions, presented to the user based on priority. The user reviews the suggested solutions on their device and attempts to resolve the problem by following the instructions. In most cases, the problem is resolved through this process.

[0049] If the suggested solution does not resolve the issue, the user can report this through the feedback form. The server will receive the feedback and, if necessary, escalate it to a support agent. Once escalated, the agent will take steps to provide detailed support based on the request and the user's feedback.

[0050] For example, an agent might communicate directly with the user and resolve the issue through remote access.

[0051] After the problem is resolved, the user evaluates the quality of support and provides feedback. The server stores this feedback in a database and uses it as training material for the AI ​​module to solve future problems.

[0052] In this way, the system provides fast and efficient support by receiving, analyzing, and suggesting solutions for user support requests. Furthermore, the escalation function allows support agents to intervene in complex issues, thereby improving the quality of support.

[0053] The following describes the processing flow.

[0054] Step 1:

[0055] Users access the support center system using information devices (e.g., PCs, smartphones, tablets). Through the provided user interface, users register an account and enter necessary information such as their name, email address, and password.

[0056] Step 2:

[0057] The server receives the registration information sent from the terminal and stores it in the database. The server then sends an authentication email to the entered email address, requesting the user to confirm.

[0058] Step 3:

[0059] The user clicks the link in the verification email they received to verify their account. This activates the user's account.

[0060] Step 4:

[0061] The user logs into the system. After logging in, a support request form is displayed. The user enters details of the problem, screenshots, error messages, etc.

[0062] Step 5:

[0063] The server receives the support request sent from the terminal and stores it in the database. The server then passes the request details to the AI ​​module.

[0064] Step 6:

[0065] The server's AI module analyzes the content of the support request. It uses natural language processing techniques to extract keywords and important phrases from the request.

[0066] Step 7:

[0067] The server searches past support databases and FAQ databases based on the extracted keywords. It then lists multiple optimal solutions and prioritizes them.

[0068] Step 8:

[0069] The server presents the user with a list of solutions in order of priority. The user reviews the solutions presented on their terminal and attempts to resolve the problem by following the instructions.

[0070] Step 9:

[0071] If a user is unable to resolve their issue using the provided solution, they should report this through the feedback form. The server will then receive the feedback from the device.

[0072] Step 10:

[0073] The server will escalate the issue to a support agent based on the feedback received, if necessary. The request and feedback will be sent to the agent along with an escalation notification.

[0074] Step 11:

[0075] A support agent receives the notification and reviews the request and feedback. The agent contacts the user and assists in resolving the issue through remote access and detailed instructions.

[0076] Step 12:

[0077] After the problem is resolved, the user evaluates the quality of support and provides feedback. The server receives the feedback from the device and stores it in a database.

[0078] Step 13:

[0079] The server analyzes the feedback it collects and uses it as training material for the AI ​​module, thereby improving its future problem-solving capabilities.

[0080] (Example 1)

[0081] 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."

[0082] Traditional support systems struggled to efficiently analyze user-submitted support requests and promptly provide appropriate solutions. In particular, the diversity and complexity of requests made it difficult to find solutions quickly, leading to decreased user satisfaction. Furthermore, the escalation process for unresolved issues was inefficient, resulting in an increase in manual intervention by support agents.

[0083] 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.

[0084] In this invention, the server includes means for a user to input a support request using an information device, means for receiving and storing the support request, means for using a generative AI model to analyze the content of the support request, means for the generative AI model to analyze the content of the support request using natural language processing technology and extract keywords and important phrases, means for searching for solutions from past support databases and FAQ databases, means for presenting the solutions to the user, means for collecting feedback from the user, and means for escalating to a support agent as necessary based on the feedback. This makes it possible to quickly and accurately analyze support requests and present appropriate solutions to users. Furthermore, if the problem cannot be resolved, escalation is carried out efficiently, enabling a rapid response by support agents.

[0085] "Information device" refers to electronic devices such as computers, smartphones, and tablets that users use to enter support requests.

[0086] A "support request" is a request submitted by a user to the system, detailing a problem and seeking assistance.

[0087] "Means" refers to a method, technique, or apparatus used to perform a particular function or task.

[0088] A "generative AI model" refers to an algorithm or model trained to perform a specific task using artificial intelligence.

[0089] "Natural language processing technology" refers to the technology that enables computers to understand, analyze, and generate human language.

[0090] "Keywords and important phrases" refer to words and sentences that are particularly important when analyzing the content of a support request.

[0091] The "past support database" is a database that stores support requests and response histories recorded to date.

[0092] An "FAQ database" is a database that compiles frequently asked questions and their answers.

[0093] "Feedback" refers to the opinions and results that users provide regarding the quality of support and the solutions provided.

[0094] "Escalation" is the process of transferring a problem that could not be resolved in the initial support process to a higher-level support agent.

[0095] A "support agent" is a specialized operator or technician who directly handles user support requests.

[0096] This invention is a system in which a user inputs a support request using an information device, a server receives and analyzes the request, presents a solution, and escalates it to a support agent as necessary. Specific embodiments are described below.

[0097] Users access the support center system using information devices such as PCs, smartphones, and tablets. First, users create a new account through the provided user interface and enter the necessary information (e.g., username, email address, password). The server stores this information in its database and sends an authentication email to the user for verification. This authentication email is sent using an SMTP server. Users authenticate their account by clicking a link in the authentication email. Clicking this link updates the server's account status, marking it as authenticated.

[0098] When a user logs into the system, a support request form is displayed. The user enters details of the problem and screenshots into this form. For example, a user might enter "The software displays an error message and does not work." Once the user submits the request, the server receives it and saves it to the database.

[0099] Next, a generative AI model on the server (for example, a natural language processing model using TENSORFLOW®) analyzes the content of the support request. The server uses this generative AI model to understand the content of the request and extract keywords and important phrases. Specifically, it analyzes the user's input using natural language processing technology and extracts important information.

[0100] Based on the analysis results, the server searches its past support database and FAQ database (e.g., ElasticSearch®) for the best solution. For example, for "Error Code 1234," it might search for solutions such as "How to reinstall the app" or "How to clear the cache." Multiple solutions are listed and presented to the user in order of priority. The user reviews the presented solutions and attempts to resolve the problem by following the instructions.

[0101] If the suggested solution does not resolve the issue, the user can report this through the feedback form. The server receives the feedback and, if necessary, escalates it to a support agent. Once escalated, the support agent provides detailed support based on the request and the user's feedback. For example, the agent may communicate directly with the user and resolve the issue through remote access.

[0102] Finally, after the problem is resolved, the user evaluates the quality of support and provides feedback. The server stores this feedback in a database and uses it as training material for a generative AI model to solve future problems.

[0103] As a concrete example, consider a case where a user enters a problem, such as "An error message appears when I open the app." In this case, the user enters "When I open the app, I get error code 1234 and it doesn't work" into the support request form. The server's generated AI model analyzes "error code 1234" and searches its past support database and FAQ database for solutions to this error. The server then prioritizes and presents these solutions to the user.

[0104] An example of a prompt statement you can enter is as follows:

[0105] "Users should log in to their account and submit a support request using the following prompt: 'When I open the app, I get error code 1234 and it doesn't work. Please tell me how to fix it.'"

[0106] This system enables the rapid and accurate analysis of user support requests, leading to efficient problem-solving. Furthermore, detailed support from support agents is provided as needed, improving overall support quality.

[0107] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0108] Step 1:

[0109] Account creation and verification

[0110] Users access the support center system using information devices such as PCs, smartphones, and tablets.

[0111] Input: Account information such as username, email address, and password.

[0112] The server receives information entered through the provided user interface.

[0113] The server saves the entered account information to the database.

[0114] The server sends an authentication email to the user for verification. The authentication email is sent using an SMTP server.

[0115] Output: An authentication email is sent to the user.

[0116] The user authenticates their account by clicking the link in the authentication email. By clicking the link, the server updates the user's account status and marks it as authenticated.

[0117] Step 2:

[0118] Login and support request submission

[0119] Input: User's authenticated account information (username, password).

[0120] The user logs into the system.

[0121] The server receives the login request and verifies the authentication credentials.

[0122] Output: Login successful, and the user is displayed with a support request form.

[0123] The user enters details of the problem and screenshots into the support request form.

[0124] Input: Details of the problem (e.g., software error message) and attachments (e.g., screenshots).

[0125] When a user submits a request, the server receives the request and stores it in the database.

[0126] Output: Saved support request data.

[0127] Step 3:

[0128] Support request analysis

[0129] Input: Support request data.

[0130] A generative AI model on the server (for example, a natural language processing model using TensorFlow) analyzes the content of the support request.

[0131] The server uses a generative AI model to understand the content of the request and extract keywords and important phrases.

[0132] Data processing: Use natural language processing techniques to extract keywords and important phrases from the text of support requests.

[0133] Output: Extracted keywords and important phrases.

[0134] Step 4:

[0135] Searching for and presenting solutions

[0136] Input: Extracted keywords and important phrases.

[0137] The server searches its past support and FAQ databases for the best solution. For example, it might use Elasticsearch to search the database.

[0138] Data Calculation: Generate search queries and search the database.

[0139] Output: A list of multiple solutions.

[0140] The server prioritizes the search results and presents solutions to the user.

[0141] Output: A list of solutions presented to the user.

[0142] Step 5:

[0143] Attempting to resolve the user issue

[0144] The user reviews the suggested solutions and attempts to resolve the problem by following the instructions.

[0145] Input: User feedback (results of attempted solutions).

[0146] Output: User feedback on whether the problem was resolved.

[0147] Step 6:

[0148] Feedback and escalation

[0149] Input: User feedback (if the problem persists).

[0150] If a user is unable to resolve their issue using the suggested solution, they should report this through the feedback form.

[0151] The server receives feedback and escalates it to a support agent as needed.

[0152] Output: Request escalated to a support agent.

[0153] Step 7:

[0154] Intervention by a support agent

[0155] Input: Escalated request.

[0156] Support agents provide detailed support based on the request and user feedback.

[0157] Specific operation: In some cases, the agent communicates directly with the user and resolves issues through remote access.

[0158] Output: Detailed support for problem resolution.

[0159] Step 8:

[0160] Supportive feedback and learning

[0161] Input: User feedback after problem resolution (evaluation of support quality).

[0162] Users rate the quality of support and provide feedback.

[0163] The server stores this feedback in a database and uses it as training material for generative AI models to solve future problems.

[0164] Output: Saved feedback data and an enhanced AI model.

[0165] In this way, the system can quickly and accurately analyze support requests and resolve problems efficiently.

[0166] (Application Example 1)

[0167] 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."

[0168] Traditional support systems have presented challenges in quickly finding appropriate solutions when users encounter problems with ad performance or settings. Issues related to ad management and performance tracking are particularly complex and often beyond the capabilities of general FAQs and support databases. Furthermore, when escalation is necessary, it can be difficult to transfer the issue to a support agent at the appropriate time, leading to delays in problem resolution.

[0169] 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.

[0170] In this invention, the server includes means for a user to input a support request using an information device, means for receiving and storing the support request, means for analyzing the content of the support request and searching for an appropriate solution, means for presenting the solution to the user, means for collecting feedback from the user, means for escalating to a support agent as necessary based on the feedback, means for resolving issues related to advertising performance and settings, means for presenting an optimal solution regarding advertising performance using a generative AI model, and means for the solution to automatically determine the requirements for escalation. This enables quick and appropriate resolution of advertising-related issues, thereby improving user satisfaction.

[0171] "Information device" refers to computer systems and devices used by users to enter support requests, and includes PCs, smartphones, tablets, etc.

[0172] A "support request" refers to inquiry information that includes details of the problem or question the user is facing.

[0173] A "server" refers to a computer system that receives and analyzes support requests and provides appropriate solutions.

[0174] "Analysis tools" refer to the part of a system that has the functionality to understand the content of a support request and derive an appropriate solution.

[0175] "Natural language processing technology" refers to techniques that enable computers to understand and analyze human language, and includes keyword extraction and semantic analysis of text.

[0176] "Feedback" refers to the evaluations and comments that users provide regarding the solutions presented.

[0177] "Escalation" refers to the process by which a user's problem is handed over to a support agent when they are unable to resolve it themselves.

[0178] "Ad performance" refers to metrics that indicate how effectively an ad is working, and includes metrics such as click-through rate and conversion rate.

[0179] A "generative AI model" refers to an artificial intelligence model that has been trained using machine learning or deep learning to perform a specific task.

[0180] "Providing a solution" refers to the process of showing the user the best possible answer or procedure for their support request.

[0181] This invention relates to a system in which a user enters a support request using an information device, a server receives and analyzes the request, presents a solution, and escalates it to a support agent as necessary.

[0182] Users access the support system using information devices such as PCs, smartphones, and tablets. Through the provided interface, users first create a new account and enter the required information. Once registration is complete, the server saves the entered information to its database and sends a verification email to the user. Users then verify their account by clicking the link in the verification email.

[0183] When a user logs into the system, a support request form is displayed, and the user enters details of the problem, screenshots, etc. The server receives the request and saves it to the database.

[0184] Next, an AI module on the server analyzes the support request. Specifically, it uses natural language processing technology to understand the content of the request and extract keywords and important phrases. Based on this analysis, the server searches its past support database and FAQ database for the best solution.

[0185] The search results list multiple possible solutions, presented to the user based on priority. The user reviews the suggested solutions on their device and attempts to resolve the problem by following the instructions. In most cases, the problem is resolved through this process.

[0186] For issues related to ad performance and settings, a generative AI model is used to suggest the optimal solution. The server utilizes the AI ​​model based on the prompt text entered by the user to find the appropriate solution. For example, prompt texts such as "How can I track ad performance?" or "I want to know how to reset my ad password?" might be entered.

[0187] If the suggested solution does not resolve the issue, the user can report this through the feedback form. The server will receive the feedback and, if necessary, escalate it to a support agent. Once escalated, the agent will take steps to provide detailed support based on the request and the user's feedback.

[0188] After the problem is resolved, the user evaluates the quality of support and provides feedback. The server stores this feedback in a database and uses it as training material for the AI ​​module to solve future problems.

[0189] The hardware and software used will consist of a server environment using Flask, the Hugging Face Transformers library and a pre-trained model (distilbert-base-cased-distilled-squad), and a simple in-memory database (using a Python dictionary).

[0190] In this way, a system is created that provides fast and efficient support, and can easily address issues, especially those related to ad performance and settings.

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

[0192] Step 1:

[0193] The user uses an information device to access the support system and create a new account. The user enters the required information and submits it.

[0194] Input: User registration information (e.g., email address, name)

[0195] Output: User information stored on the server, confirmation email sent.

[0196] Specific operation: The user enters the required information into a web form from an information device such as a PC or smartphone and clicks the "Submit" button. The server saves the received information to a database, generates a confirmation email, and sends it to the user.

[0197] Step 2:

[0198] The user clicks the link in the verification email to verify their account. The server receives the verification request and updates the user's account to verified.

[0199] Input: Click the link in the verification email.

[0200] Output: Confirmed account information, authentication complete message

[0201] Specific operation: The user clicks the link in the received authentication email, the server receives the request and updates the user's account information, and the server displays a confirmation message.

[0202] Step 3:

[0203] The user logs into the system, enters details of the problem into the support request form, and submits it. The server receives the request and saves it to the database.

[0204] Input: Support request information (e.g., problem details, screenshots)

[0205] Output: Support requests stored in the database

[0206] Specific operation: After logging in, the user enters details of the problem into the support request form that appears and clicks the "Submit" button. The server saves the received information to the database.

[0207] Step 4:

[0208] An AI module on the server analyzes support requests and extracts keywords and phrases using natural language processing techniques.

[0209] Input: Support Request Information

[0210] Output: Extracted keywords and phrases

[0211] Specific operation: The server sends the received support request to the AI ​​module, which then uses natural language processing techniques to analyze the text. It extracts important keywords and phrases.

[0212] Step 5:

[0213] The server searches for the best solution based on keywords extracted from past support databases and FAQ databases.

[0214] Input: Extracted keywords or phrases

[0215] Output: List of optimal solutions

[0216] Specific operation: The server searches the support database and FAQ database based on the extracted keywords and lists relevant solutions.

[0217] Step 6:

[0218] The server prioritizes and presents the user with the optimal solution.

[0219] Input: List of optimal solutions

[0220] Output: Solutions presented to the user

[0221] Specific operation: The server ranks the listed solutions based on priority and displays them on the user's terminal.

[0222] Step 7:

[0223] The user reviews the suggested solutions and attempts to resolve the problem. The user reports the results through a feedback form.

[0224] Input: User feedback

[0225] Output: Feedback information stored on the server

[0226] Specific operation: The user tries the displayed solution, enters the results and comments in the feedback form, and submits it. The server saves the feedback information to the database.

[0227] Step 8:

[0228] The server will escalate the issue to a support agent as needed based on the feedback. The support agent will review the details of the problem and provide additional support.

[0229] Input: User feedback

[0230] Output: Escalated support request, additional support

[0231] Specific operation: The server analyzes the feedback and, if it cannot resolve the issue, escalates it to a support agent. The agent reviews the request and feedback and provides support as needed.

[0232] Example prompt:

[0233] "How can I track the performance of my ads?"

[0234] "I want to know the password reset procedure for advertisements."

[0235] 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.

[0236] This invention relates to a system in which a user enters a support request using an information device, a server receives, analyzes, and proposes a solution to the request, and escalates it to a support agent as needed. Furthermore, the invention incorporates an emotion engine that recognizes the user's emotions and optimizes the response accordingly.

[0237] Users access the support center system using information devices such as PCs, smartphones, or tablets. Through the provided user interface, users create a new account and enter the required information. Once registration is complete, the server saves the entered information to a database and sends a verification email to the user. Users verify their account by clicking the link in the verification email.

[0238] When a user logs into the system, a support request form is displayed, and the user enters details of the problem, screenshots, etc. For example, they may enter information about software error messages or system malfunctions. Once the user submits the request, the server receives it and stores it in the database.

[0239] Next, an AI module on the server analyzes the content of the support request. Specifically, it uses natural language processing technology to understand the request and extract keywords and important phrases. Furthermore, an emotion engine analyzes the user's emotions and determines the user's emotional state (e.g., frustration, anger, sadness, etc.) from the request content, input text, and voice data. Based on this analysis, the server searches its past support database and FAQ database for the best solution. For example, it searches for information such as "how to reset a password" or "how to deal with a specific error message."

[0240] The search results list multiple possible solutions, presented to the user based on priority. The user reviews the suggested solutions on their device and attempts to resolve the problem by following the instructions. In most cases, the problem is resolved through this process. Furthermore, the tone and content of the messages presented are adjusted according to the user's emotional state. For example, if the emotion recognition engine determines that the user is feeling frustrated, the system will display a more empathetic and considerate message.

[0241] If the suggested solution does not resolve the issue, the user reports this through a feedback form. The server receives the feedback and, if necessary, escalates it to a support agent. Once escalated, the agent takes steps to provide detailed support based on the request, the user's feedback, and the sentiment engine's emotional state information. For example, the agent may communicate directly with the user and resolve the issue through remote access. In this case, the agent can understand the user's emotional state and select the appropriate course of action.

[0242] After the problem is resolved, the user evaluates the quality of support and provides feedback. The server stores this feedback in a database and uses it as training material for the AI ​​module to solve future problems. The emotion engine is also continuously improved, enabling more accurate emotion recognition.

[0243] In this way, the system provides fast and efficient support by receiving, analyzing, and suggesting solutions for user support requests. Furthermore, the emotion engine enables personalized responses based on the user's emotional state, and the escalation function allows support agents to intervene in complex issues, thereby improving the quality of support.

[0244] The following describes the processing flow.

[0245] Step 1:

[0246] Users access the support center system using information devices (e.g., PCs, smartphones, tablets). Through the provided user interface, users register an account and enter necessary information such as their name, email address, and password.

[0247] Step 2:

[0248] The server receives the registration information sent from the terminal and stores it in the database. The server then sends an authentication email to the entered email address, requesting the user to confirm.

[0249] Step 3:

[0250] The user clicks the link in the verification email they received to verify their account. This activates the user's account.

[0251] Step 4:

[0252] The user logs into the system. After logging in, a support request form is displayed, and the user enters details of the problem, screenshots, error messages, etc.

[0253] Step 5:

[0254] The server receives the support request sent from the terminal and stores it in the database. The server then passes the request details to the AI ​​module.

[0255] Step 6:

[0256] The server's AI module analyzes the content of the support request. It uses natural language processing technology to understand the request and extract keywords and important phrases.

[0257] Step 7:

[0258] The server's emotion engine analyzes the user's emotional state from the request content, input text, and, if necessary, audio data. For example, it determines whether the user is experiencing emotions such as frustration, anger, or sadness based on keywords and context.

[0259] Step 8:

[0260] The server searches past support and FAQ databases based on extracted keywords and user sentiment information. The server then lists the best solutions and prioritizes them.

[0261] Step 9:

[0262] When the server presents a list of solutions to the user, it adjusts the tone and content of the message according to the user's emotional state. For example, if the user is feeling frustrated, it will use empathetic and polite language.

[0263] Step 10:

[0264] The user checks the suggested solutions on their device and attempts to resolve the problem by following the instructions. In most cases, the problem is resolved through this process.

[0265] Step 11:

[0266] If a user is unable to resolve their issue using the provided solution, they should report this through the feedback form. The server will then receive the feedback from the device.

[0267] Step 12:

[0268] Based on the feedback, the server escalates the issue to a support agent as needed. Along with the escalation notification, the server sends the request details and the user's emotional state information to the agent.

[0269] Step 13:

[0270] A support agent receives the notification and reviews the request, feedback, and emotional state information from the emotion engine. The agent then contacts the user to resolve the issue through remote access and detailed instructions.

[0271] Step 14:

[0272] After the problem is resolved, the user evaluates the quality of support and provides feedback. The server receives the feedback from the device and stores it in a database.

[0273] Step 15:

[0274] The server analyzes the collected feedback and uses it as training material for the AI ​​module and emotion engine. This will improve future problem-solving and emotion recognition capabilities.

[0275] (Example 2)

[0276] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0277] Traditional support systems often failed to consider the user's emotional state, resulting in inappropriate responses and decreased user satisfaction. Furthermore, the solutions provided frequently did not meet user needs, leading to frequent escalations and increased workload for support agents.

[0278] 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.

[0279] In this invention, the server includes means for a user to input a support request using a device, means for receiving and storing the support request, means for analyzing the content of the support request and searching for an appropriate solution, means for analyzing the user's emotional state, means for adjusting the presentation of the solution based on the emotional state, means for presenting the solution to the user, means for collecting feedback from the user, and means for escalating to a support agent as necessary based on the feedback. This enables individualized responses that take into account the user's emotional state, and by providing an appropriate solution, it is possible to reduce the frequency of escalations to support agents and improve overall user satisfaction.

[0280] A "user" refers to a person who uses the system to submit a support request.

[0281] "Device" refers to information devices such as PCs, smartphones, and tablets.

[0282] A "support request" refers to information that a user submits to the system, such as a problem or question.

[0283] "Means" refers to the technical methods or devices for realizing specific functions within a system.

[0284] "Server" refers to the central computer that receives requests from users, analyzes them, and manages the entire corresponding system.

[0285] "Natural language processing technology" refers to the technology for a computer to understand and analyze human natural language.

[0286] "Keyword" refers to the important words or phrases indicating the content of a support request.

[0287] "Emotional state" refers to the mood or feeling of a user when making a support request, such as frustration or joy.

[0288] "Escalation" refers to the process in which, when a problem cannot be solved by the initial automatic resolution method, a human such as a support agent provides additional support.

[0289] "Feedback" refers to the opinions or evaluations provided by a user regarding a support response.

[0290] "Support agent" refers to the professional staff who directly responds to solve a user's problem.

[0291] "Solution" refers to the appropriate countermeasures or procedures for a user's support request.

[0292] This invention relates to a system in which a user inputs a support request using a device, the server receives and analyzes the request, presents a solution method, and escalates it to a support agent as necessary. Furthermore, by incorporating an emotion engine, it provides a mechanism for recognizing the emotional state of a user and optimizing the response.

[0293] Hardware and Software

[0294] hardware

[0295] This system consists of the following information devices:

[0296] User devices (PCs, smartphones, tablets, etc.)

[0297] Server System

[0298] software

[0299] The software used includes the following specific technologies:

[0300] Natural Language Processing (NLTK, SpaCy)

[0301] Sentiment analysis tool (Natural Language Understanding by IBM Watson®)

[0302] Database management systems (MySQL®, MongoDB, Firebase, Elasticsearch)

[0303] Remote access tools (TeamViewer, AnyDesk)

[0304] Submitting and receiving support requests

[0305] Users access the support center system using information devices such as PCs, smartphones, and tablets. After accessing the system, users create a new account and enter the required information. At this time, the server saves the entered information to a database and sends an authentication email to the user for verification. Once the user clicks the link in the authentication email to authenticate their account, they will be able to log in.

[0306] Next, after the user logs in, they enter the details of the problem in the support request form. For example, they write "An error message is displayed during software installation" and attach a screenshot. When the user sends the request, the server receives the request and saves it in the database.

[0307] Analysis and Sentiment Recognition of Requests

[0308] The AI module on the server analyzes the content of the support request. Specifically, it uses natural language processing technology to extract keywords and important phrases from the request. Furthermore, the server's sentiment engine determines the user's emotional state from the input text or voice data. For example, "frustration", "anger", "sadness", etc. are detected.

[0309] Presentation of Solutions

[0310] Based on the analysis results, the server searches for the optimal solution from the past support database or FAQ database. For example, "Procedures for resetting the password" or "Solutions for specific error messages" are listed as candidates. The search results list multiple candidates as solutions and are presented to the user based on the priority. The user checks the presented solutions and tries to solve the problem according to the instructions.

[0311] Optimization of Responses According to Emotions

[0312] The sentiment recognition engine determines the user's emotional state. For example, when the sentiment engine determines that "the user is feeling frustrated", the system displays a more personal and polite message. This can reduce the user's stress and make the support experience better.

[0313] Escalation and Provision of Detailed Support

[0314] If the suggested solution does not resolve the issue, the user can report this through the feedback form. The server receives the feedback and escalates it to a support agent as needed. The support agent will provide detailed support based on the request and the user's emotional state. For example, the agent may resolve the issue through remote access.

[0315] Gathering feedback and improving the system

[0316] After the problem is resolved, the user evaluates the quality of support and provides feedback. The server stores this feedback in a database and uses it as training material for the AI ​​module to solve future problems. The emotion engine is also continuously improved, enabling more accurate emotion recognition.

[0317] Examples of specific cases and prompt statements

[0318] Specific example

[0319] When a user enters and submits a support request such as "My PC freezes," the server receives the request and analyzes it as follows:

[0320] 1. The server extracts keywords such as "freeze" and "PC".

[0321] 2. The emotion engine detects "frustration" from the user's text.

[0322] 3. Search for the best solution (e.g., "How to fix computer freezing problems") and present it in order of priority.

[0323] Example of a prompt

[0324] "Please tell me what to do if the software installation fails."

[0325] "Please enter the password reset procedure."

[0326] "Please tell me how to fix the problem of my PC freezing."

[0327] In this way, the system efficiently processes user support requests and provides users with the best possible support experience.

[0328] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0329] Step 1: User access to the support center system and account creation

[0330] Specific actions

[0331] 1. Users access the support center system using information devices such as PCs, smartphones, and tablets.

[0332] Input: Access the support center website from your device's browser (enter the URL).

[0333] Output: The support center user interface is displayed.

[0334] 2. The user enters the necessary information (username, email address, password, etc.) into the form for creating a new account.

[0335] Input: Account information (username, email address, password)

[0336] Output: The input information will be displayed in the form.

[0337] 3. When the user presses the submit button, the server receives the entered information and saves it to the database. It also sends an authentication email to the user.

[0338] Input: Click the submit button

[0339] Output: Save information to the database and send an authentication email.

[0340] 4. The user authenticates their account by clicking the link in the verification email they received.

[0341] Input: Click the link in the verification email.

[0342] Output: Account becomes active

[0343] Step 2: Submit a support request

[0344] Specific actions

[0345] 1. The user logs into their account.

[0346] Input: Login information (email address, password)

[0347] Output: A support request form is displayed.

[0348] 2. The user enters details of the problem (e.g., software error details, screenshots, etc.) into the support request form.

[0349] Input: Support request details and required attachments

[0350] Output: The information entered in the form will be displayed.

[0351] 3. The user submits a request. The server receives the request, saves it to the database, and prepares it for analysis.

[0352] Input: Click the submit button

[0353] Output: Save request information to the database

[0354] Step 3: Request analysis and sentiment recognition

[0355] Specific actions

[0356] 1. The AI ​​module on the server analyzes the support requests it receives.

[0357] Input: Received request data

[0358] Output: Analysis results (keywords and phrases)

[0359] 2. Extract keywords and phrases from the request content using natural language processing techniques (e.g., using SpaCy or NLTK).

[0360] Input: Request text

[0361] Output: Extracted keywords and phrases

[0362] 3. The server's emotion engine determines the user's emotional state from their input text and voice data (e.g., using IBM Watson's Natural Language Understanding).

[0363] Input: Request text, audio data

[0364] Output: Emotional state (frustration, anger, sadness, etc.)

[0365] Step 4: Presenting a solution

[0366] Specific actions

[0367] 1. The server searches for the best solution from past support databases and FAQ databases.

[0368] Input: Keywords, phrases, emotional states

[0369] Output: List of possible solutions

[0370] 2. Organize search results in order of priority and present them to the user.

[0371] Input: List of possible solutions

[0372] Output: List of prioritized solutions

[0373] 3. A list of solutions will be displayed on the user's device.

[0374] Input: List of solutions

[0375] Output: List of solutions displayed on the terminal

[0376] Step 5: Escalation and provision of detailed support

[0377] Specific actions

[0378] 1. If the user's problem is not resolved by the suggested solution, they should report this through the feedback form.

[0379] Input: Feedback content

[0380] Output: Sending feedback

[0381] 2. The server receives the feedback and escalates it to a support agent as needed.

[0382] Input: Received feedback

[0383] Output: Escalation notification

[0384] 3. Support agents provide detailed support based on the request and the user's emotional state. For example, they may use remote access tools to resolve the issue.

[0385] Input: Escalation information, emotional state information

[0386] Output: Detailed support provided

[0387] Step 6: Gathering Feedback and Improving the System

[0388] Specific actions

[0389] 1. After the problem is resolved, the user evaluates the quality of support and provides feedback.

[0390] Input: Evaluation content, feedback

[0391] Output: Sending feedback

[0392] 2. The server saves the feedback to a database and uses it as training material for the AI ​​module to solve future problems.

[0393] Input: Feedback data

[0394] Output: Feedback stored in the database

[0395] Through the steps outlined above, the system can efficiently process user support requests and provide users with the best possible support experience.

[0396] (Application Example 2)

[0397] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0398] Traditional support systems have the means to receive support requests from users and offer appropriate solutions, but they often resulted in a poor user experience due to insufficient consideration of the user's emotional state. Furthermore, the uniform approach to solutions frequently caused dissatisfaction and stress, especially for emotionally unstable users. Additionally, the escalation process when a problem could not be resolved also lacked consideration for the user's feelings, leading to difficulties in smooth communication with support agents.

[0399] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for a user to input a support request using an information device, means for receiving and storing the support request, means for analyzing the content of the support request and searching for an appropriate solution, means for presenting the solution to the user, means for the analysis means to recognize the user's emotions and optimize the response, means for collecting feedback from the user, and means for escalating to a support agent as necessary based on the feedback. This enables optimal support that takes into account the user's emotional state, and particularly enables rapid and efficient problem solving in electronic payment services. In addition, since the escalation process can also be handled with an understanding of the user's emotional state, smoother support can be provided.

[0400] An "information device" refers to a terminal such as a computer or smartphone that a user uses to enter a support request.

[0401] A "support request" is information that details the problems or inquiries a user is facing.

[0402] The "means of receiving and storing" refer to a mechanism where the server receives a support request and stores its contents in a database.

[0403] "Analysis method" refers to a technique that uses natural language processing technology to understand the content of a support request, extract keywords and phrases, and identify the problem.

[0404] A "solution" refers to the methods or procedures for dealing with and resolving an identified problem.

[0405] "Means of presentation" refers to an interface for showing the user the solution obtained through analysis.

[0406] "Means of recognizing emotions and optimizing responses" refers to technologies that analyze a user's emotional state and provide the most appropriate response based on that analysis.

[0407] "Feedback" refers to evaluations and comments made by users regarding the solutions and support provided.

[0408] "Means of collection" refers to a system for receiving user feedback and sending and storing it on a server.

[0409] "Escalation" refers to the process of transferring a user's problem to an agent who can provide more advanced support if the problem cannot be resolved in the initial stages.

[0410] A "database" is a system for storing and managing information such as support requests, solutions, and user feedback.

[0411] "Natural language processing technology" is a technology that enables computers to understand and interpret human language and extract its meaning.

[0412] This invention relates to a system in which a user inputs a support request using an information device, a server receives and analyzes the request, and presents the optimal solution. Furthermore, by incorporating an emotion engine that recognizes the user's emotions and optimizes the response, personalized support becomes possible.

[0413] System Configuration Description

[0414] The system consists of the following main hardware and software components:

[0415] 1. Information equipment

[0416] This is a device used by users to enter support requests. These devices include computers, smartphones, and tablets.

[0417] 2. Server

[0418] This is the central computing unit responsible for receiving support requests, storing them in a database, and processing and presenting solutions. Specific examples of software used include Google® Cloud Natural Language API and OpenAI® GPT-4® for natural language processing engines, and IBM Watson Tone Analyzer and Microsoft® Azure® Cognitive Services for sentiment engines.

[0419] 3. Database

[0420] This is a system for accumulating support requests, past support data, FAQs, and user feedback. Specific examples include MySQL and PostgreSQL.

[0421] Processing flow

[0422] 1. Initial Setup

[0423] Users access the app using their smartphones and create a new account. They enter the required information, receive a verification email, and verify their account.

[0424] 2. Enter your support request

[0425] Users submit support requests through the app. These requests may include issues such as login problems or transaction errors with electronic payment services. The request includes error messages and details of the problem.

[0426] 3. Receiving and saving requests

[0427] The server receives the submitted support request and saves it to the database.

[0428] 4. Analysis and Sentiment Recognition

[0429] The natural language processing engine analyzes the request content and extracts keywords and important phrases. The emotion engine analyzes the user's emotional state (e.g., frustration, anger, sadness).

[0430] 5. Searching for and presenting solutions

[0431] The system searches for the best solution from support databases and FAQs, and then presents the message with a tone and content adjusted according to the user's emotional state.

[0432] 6. Feedback and Escalation

[0433] We collect user feedback and escalate it to support agents as needed. The agents understand the user's emotional state and take appropriate action.

[0434] Specific example

[0435] For example, if a user is unable to log in to their account with an electronic payment service, the support request will be processed as follows:

[0436] Example of a prompt

[0437] "Analysis of a support request when a user is unable to log in to their account on an electronic payment service. The user created the account two weeks ago. The error message is 'Incorrect password.' The user appears frustrated. The emotion engine presents empathetic messages and searches the past database for the best solution. If the user tries the suggested solutions and the problem persists, the issue is escalated to an agent."

[0438] Thus, the embodiments of the invention aim to provide prompt and accurate support in response to the diverse needs of users.

[0439] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0440] Step 1:

[0441] The user enters a support request using an information device (smartphone, PC, etc.). They enter details of the problem they are facing and attach supporting documents such as screenshots as needed. The entered information is then sent from the device to the server.

[0442] Input: User-submitted details of the problem, error message, and screenshot.

[0443] Output: Support Request Data

[0444] Step 2:

[0445] The server receives support requests and stores them in the database. The server ensures reliability and security.

[0446] Input: Support Request Data

[0447] Output: Support request records stored in the database

[0448] Step 3:

[0449] The server's natural language processing engine analyzes the content of the support request. It extracts keywords and important phrases from the request to identify the problem.

[0450] Input: Support Request Data

[0451] Output: Extracted keywords, identified issues

[0452] Step 4:

[0453] The server's emotion engine recognizes the user's emotions. It analyzes the request content and various input data (text, audio data, etc.) to evaluate the user's emotional state. For example, it determines whether the user is feeling frustrated.

[0454] Input: Support request data, text data, audio data

[0455] Output: User's emotional state (e.g., frustration, anger, sadness)

[0456] Step 5:

[0457] The server searches the database for the best solution. Based on past support and FAQ databases, it selects and prioritizes the most suitable solution for the user. It also adjusts the tone and content of messages according to the user's emotional state.

[0458] Input: Identified problem, user's emotional state

[0459] Output: Optimal solution, adjusted message

[0460] Step 6:

[0461] The server presents a solution to the user. The terminal displays the optimal solution and a tailored message.

[0462] Input: Optimal solution, tailored message

[0463] Output: Solution and message displayed on the user terminal

[0464] Step 7:

[0465] The user attempts to solve the problem according to the suggested solution and provides feedback on the results.

[0466] Input: Solution trial results, feedback data

[0467] Output: User feedback

[0468] Step 8:

[0469] The server receives feedback from the user and stores it in the database. The server analyzes the feedback and determines whether the issue was successfully resolved.

[0470] Input: Feedback data

[0471] Output: Feedback records stored in the database, resolution result

[0472] Step 9:

[0473] If the problem persists, the server will escalate it to a support agent based on the feedback. The agent will then take steps to provide detailed support based on the request and the user's emotional state.

[0474] Input: Feedback data, user's emotional state

[0475] Output: Escalation data to the agent

[0476] In this way, each step works together to form a system that supports the rapid and appropriate resolution of user problems.

[0477] 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.

[0478] 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.

[0479] 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.

[0480] [Second Embodiment]

[0481] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0482] 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.

[0483] 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).

[0484] 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.

[0485] 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.

[0486] 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).

[0487] 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.

[0488] 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.

[0489] 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.

[0490] 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.

[0491] 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.

[0492] 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".

[0493] This invention relates to a system in which a user enters a support request using an information device, a server receives and analyzes the request, presents a solution, and escalates it to a support agent as necessary.

[0494] Users access the support center system using information devices such as PCs, smartphones, or tablets. Through the provided user interface, users create a new account and enter the required information. Once registration is complete, the server saves the entered information to a database and sends a verification email to the user. Users verify their account by clicking the link in the verification email.

[0495] When a user logs into the system, a support request form is displayed, and the user enters details of the problem, screenshots, etc. For example, they may enter information about software error messages or system malfunctions. Once the user submits the request, the server receives it and stores it in the database.

[0496] Next, an AI module on the server analyzes the content of the support request. Specifically, it uses natural language processing technology to understand the content of the request and extract keywords and important phrases. Based on this analysis, the server searches its past support database and FAQ database for the best solution. For example, it searches for information such as "how to reset a password" or "how to deal with a specific error message."

[0497] The search results list multiple possible solutions, presented to the user based on priority. The user reviews the suggested solutions on their device and attempts to resolve the problem by following the instructions. In most cases, the problem is resolved through this process.

[0498] If the suggested solution does not resolve the issue, the user can report this through the feedback form. The server will receive the feedback and, if necessary, escalate it to a support agent. Once escalated, the agent will take steps to provide detailed support based on the request and the user's feedback.

[0499] For example, an agent might communicate directly with the user and resolve the issue through remote access.

[0500] After the problem is resolved, the user evaluates the quality of support and provides feedback. The server stores this feedback in a database and uses it as training material for the AI ​​module to solve future problems.

[0501] In this way, the system provides fast and efficient support by receiving, analyzing, and suggesting solutions for user support requests. Furthermore, the escalation function allows support agents to intervene in complex issues, thereby improving the quality of support.

[0502] The following describes the processing flow.

[0503] Step 1:

[0504] Users access the support center system using information devices (e.g., PCs, smartphones, tablets). Through the provided user interface, users register an account and enter necessary information such as their name, email address, and password.

[0505] Step 2:

[0506] The server receives the registration information sent from the terminal and stores it in the database. The server then sends an authentication email to the entered email address, requesting the user to confirm.

[0507] Step 3:

[0508] The user clicks the link in the verification email they received to verify their account. This activates the user's account.

[0509] Step 4:

[0510] The user logs into the system. After logging in, a support request form is displayed. The user enters details of the problem, screenshots, error messages, etc.

[0511] Step 5:

[0512] The server receives the support request sent from the terminal and stores it in the database. The server then passes the request details to the AI ​​module.

[0513] Step 6:

[0514] The server's AI module analyzes the content of the support request. It uses natural language processing techniques to extract keywords and important phrases from the request.

[0515] Step 7:

[0516] The server searches past support databases and FAQ databases based on the extracted keywords. It then lists multiple optimal solutions and prioritizes them.

[0517] Step 8:

[0518] The server presents the user with a list of solutions in order of priority. The user reviews the solutions presented on their terminal and attempts to resolve the problem by following the instructions.

[0519] Step 9:

[0520] If a user is unable to resolve their issue using the provided solution, they should report this through the feedback form. The server will then receive the feedback from the device.

[0521] Step 10:

[0522] The server will escalate the issue to a support agent based on the feedback received, if necessary. The request and feedback will be sent to the agent along with an escalation notification.

[0523] Step 11:

[0524] A support agent receives the notification and reviews the request and feedback. The agent contacts the user and assists in resolving the issue through remote access and detailed instructions.

[0525] Step 12:

[0526] After the problem is resolved, the user evaluates the quality of support and provides feedback. The server receives the feedback from the device and stores it in a database.

[0527] Step 13:

[0528] The server analyzes the feedback it collects and uses it as training material for the AI ​​module, thereby improving its future problem-solving capabilities.

[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 struggled to efficiently analyze user-submitted support requests and promptly provide appropriate solutions. In particular, the diversity and complexity of requests made it difficult to find solutions quickly, leading to decreased user satisfaction. Furthermore, the escalation process for unresolved issues was inefficient, resulting in an increase in manual intervention by support agents.

[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 a user to input a support request using an information device, means for receiving and storing the support request, means for using a generative AI model to analyze the content of the support request, means for the generative AI model to analyze the content of the support request using natural language processing technology and extract keywords and important phrases, means for searching for solutions from past support databases and FAQ databases, means for presenting the solutions to the user, means for collecting feedback from the user, and means for escalating to a support agent as necessary based on the feedback. This makes it possible to quickly and accurately analyze support requests and present appropriate solutions to users. Furthermore, if the problem cannot be resolved, escalation is carried out efficiently, enabling a rapid response by support agents.

[0534] "Information device" refers to electronic devices such as computers, smartphones, and tablets that users use to enter support requests.

[0535] A "support request" is a request submitted by a user to the system, detailing a problem and seeking assistance.

[0536] "Means" refers to a method, technique, or apparatus used to perform a particular function or task.

[0537] A "generative AI model" refers to an algorithm or model trained to perform a specific task using artificial intelligence.

[0538] "Natural language processing technology" refers to the technology that enables computers to understand, analyze, and generate human language.

[0539] "Keywords and important phrases" refer to words and sentences that are particularly important when analyzing the content of a support request.

[0540] The "past support database" is a database that stores support requests and response histories recorded to date.

[0541] An "FAQ database" is a database that compiles frequently asked questions and their answers.

[0542] "Feedback" refers to the opinions and results that users provide regarding the quality of support and the solutions provided.

[0543] "Escalation" is the process of transferring a problem that could not be resolved in the initial support process to a higher-level support agent.

[0544] A "support agent" is a specialized operator or technician who directly handles user support requests.

[0545] This invention is a system in which a user inputs a support request using an information device, a server receives and analyzes the request, presents a solution, and escalates it to a support agent as necessary. Specific embodiments are described below.

[0546] Users access the support center system using information devices such as PCs, smartphones, and tablets. First, users create a new account through the provided user interface and enter the necessary information (e.g., username, email address, password). The server stores this information in its database and sends an authentication email to the user for verification. This authentication email is sent using an SMTP server. Users authenticate their account by clicking a link in the authentication email. Clicking this link updates the server's account status, marking it as authenticated.

[0547] When a user logs into the system, a support request form is displayed. The user enters details of the problem and screenshots into this form. For example, a user might enter "The software displays an error message and does not work." Once the user submits the request, the server receives it and saves it to the database.

[0548] Next, a generative AI model on the server (for example, a natural language processing model using TensorFlow) analyzes the content of the support request. The server uses this generative AI model to understand the content of the request and extract keywords and important phrases. Specifically, it analyzes the user's input using natural language processing techniques and extracts important information.

[0549] Based on the analysis results, the server searches its past support database and FAQ database (e.g., Elasticsearch) for the best solution. For example, for "error code 1234," it might search for solutions such as "how to reinstall the app" or "how to clear the cache." Multiple solutions are listed and presented to the user in order of priority. The user reviews the presented solutions and attempts to resolve the problem by following the instructions.

[0550] If the suggested solution does not resolve the issue, the user can report this through the feedback form. The server receives the feedback and, if necessary, escalates it to a support agent. Once escalated, the support agent provides detailed support based on the request and the user's feedback. For example, the agent may communicate directly with the user and resolve the issue through remote access.

[0551] Finally, after the problem is resolved, the user evaluates the quality of support and provides feedback. The server stores this feedback in a database and uses it as training material for a generative AI model to solve future problems.

[0552] As a concrete example, consider a case where a user enters a problem, such as "An error message appears when I open the app." In this case, the user enters "When I open the app, I get error code 1234 and it doesn't work" into the support request form. The server's generated AI model analyzes "error code 1234" and searches its past support database and FAQ database for solutions to this error. The server then prioritizes and presents these solutions to the user.

[0553] An example of a prompt statement you can enter is as follows:

[0554] "Users should log in to their account and submit a support request using the following prompt: 'When I open the app, I get error code 1234 and it doesn't work. Please tell me how to fix it.'"

[0555] This system enables the rapid and accurate analysis of user support requests, leading to efficient problem-solving. Furthermore, detailed support from support agents is provided as needed, improving overall support quality.

[0556] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0557] Step 1:

[0558] Account creation and verification

[0559] Users access the support center system using information devices such as PCs, smartphones, and tablets.

[0560] Input: Account information such as username, email address, and password.

[0561] The server receives information entered through the provided user interface.

[0562] The server saves the entered account information to the database.

[0563] The server sends an authentication email to the user for verification. The authentication email is sent using an SMTP server.

[0564] Output: An authentication email is sent to the user.

[0565] The user authenticates their account by clicking the link in the authentication email. By clicking the link, the server updates the user's account status and marks it as authenticated.

[0566] Step 2:

[0567] Login and support request submission

[0568] Input: User's authenticated account information (username, password).

[0569] The user logs into the system.

[0570] The server receives the login request and verifies the authentication credentials.

[0571] Output: Login successful, and the user is displayed with a support request form.

[0572] The user enters details of the problem and screenshots into the support request form.

[0573] Input: Details of the problem (e.g., software error message) and attachments (e.g., screenshots).

[0574] When a user submits a request, the server receives the request and stores it in the database.

[0575] Output: Saved support request data.

[0576] Step 3:

[0577] Support request analysis

[0578] Input: Support request data.

[0579] A generative AI model on the server (for example, a natural language processing model using TensorFlow) analyzes the content of the support request.

[0580] The server uses a generative AI model to understand the content of the request and extract keywords and important phrases.

[0581] Data processing: Use natural language processing techniques to extract keywords and important phrases from the text of support requests.

[0582] Output: Extracted keywords and important phrases.

[0583] Step 4:

[0584] Searching for and presenting solutions

[0585] Input: Extracted keywords and important phrases.

[0586] The server searches its past support and FAQ databases for the best solution. For example, it might use Elasticsearch to search the database.

[0587] Data Calculation: Generate search queries and search the database.

[0588] Output: A list of multiple solutions.

[0589] The server prioritizes the search results and presents solutions to the user.

[0590] Output: A list of solutions presented to the user.

[0591] Step 5:

[0592] Attempting to resolve the user issue

[0593] The user reviews the suggested solutions and attempts to resolve the problem by following the instructions.

[0594] Input: User feedback (results of attempted solutions).

[0595] Output: User feedback on whether the problem was resolved.

[0596] Step 6:

[0597] Feedback and escalation

[0598] Input: User feedback (if the problem persists).

[0599] If a user is unable to resolve their issue using the suggested solution, they should report this through the feedback form.

[0600] The server receives feedback and escalates it to a support agent as needed.

[0601] Output: Request escalated to a support agent.

[0602] Step 7:

[0603] Intervention by a support agent

[0604] Input: Escalated request.

[0605] Support agents provide detailed support based on the request and user feedback.

[0606] Specific operation: In some cases, the agent communicates directly with the user and resolves issues through remote access.

[0607] Output: Detailed support for problem resolution.

[0608] Step 8:

[0609] Supportive feedback and learning

[0610] Input: User feedback after problem resolution (evaluation of support quality).

[0611] Users rate the quality of support and provide feedback.

[0612] The server stores this feedback in a database and uses it as training material for generative AI models to solve future problems.

[0613] Output: Saved feedback data and an enhanced AI model.

[0614] In this way, the system can quickly and accurately analyze support requests and resolve problems efficiently.

[0615] (Application Example 1)

[0616] 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."

[0617] Traditional support systems have presented challenges in quickly finding appropriate solutions when users encounter problems with ad performance or settings. Issues related to ad management and performance tracking are particularly complex and often beyond the capabilities of general FAQs and support databases. Furthermore, when escalation is necessary, it can be difficult to transfer the issue to a support agent at the appropriate time, leading to delays in problem resolution.

[0618] 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.

[0619] In this invention, the server includes means for a user to input a support request using an information device, means for receiving and storing the support request, means for analyzing the content of the support request and searching for an appropriate solution, means for presenting the solution to the user, means for collecting feedback from the user, means for escalating to a support agent as necessary based on the feedback, means for resolving issues related to advertising performance and settings, means for presenting an optimal solution regarding advertising performance using a generative AI model, and means for the solution to automatically determine the requirements for escalation. This enables quick and appropriate resolution of advertising-related issues, thereby improving user satisfaction.

[0620] "Information device" refers to computer systems and devices used by users to enter support requests, and includes PCs, smartphones, tablets, etc.

[0621] A "support request" refers to inquiry information that includes details of the problem or question the user is facing.

[0622] A "server" refers to a computer system that receives and analyzes support requests and provides appropriate solutions.

[0623] "Analysis tools" refer to the part of a system that has the functionality to understand the content of a support request and derive an appropriate solution.

[0624] "Natural language processing technology" refers to techniques that enable computers to understand and analyze human language, and includes keyword extraction and semantic analysis of text.

[0625] "Feedback" refers to the evaluations and comments that users provide regarding the solutions presented.

[0626] "Escalation" refers to the process by which a user's problem is handed over to a support agent when they are unable to resolve it themselves.

[0627] "Ad performance" refers to metrics that indicate how effectively an ad is working, and includes metrics such as click-through rate and conversion rate.

[0628] A "generative AI model" refers to an artificial intelligence model that has been trained using machine learning or deep learning to perform a specific task.

[0629] "Providing a solution" refers to the process of showing the user the best possible answer or procedure for their support request.

[0630] This invention relates to a system in which a user enters a support request using an information device, a server receives and analyzes the request, presents a solution, and escalates it to a support agent as necessary.

[0631] Users access the support system using information devices such as PCs, smartphones, and tablets. Through the provided interface, users first create a new account and enter the required information. Once registration is complete, the server saves the entered information to its database and sends a verification email to the user. Users then verify their account by clicking the link in the verification email.

[0632] When a user logs into the system, a support request form is displayed, and the user enters details of the problem, screenshots, etc. The server receives the request and saves it to the database.

[0633] Next, an AI module on the server analyzes the support request. Specifically, it uses natural language processing technology to understand the content of the request and extract keywords and important phrases. Based on this analysis, the server searches its past support database and FAQ database for the best solution.

[0634] The search results list multiple possible solutions, presented to the user based on priority. The user reviews the suggested solutions on their device and attempts to resolve the problem by following the instructions. In most cases, the problem is resolved through this process.

[0635] For issues related to ad performance and settings, a generative AI model is used to suggest the optimal solution. The server utilizes the AI ​​model based on the prompt text entered by the user to find the appropriate solution. For example, prompt texts such as "How can I track ad performance?" or "I want to know how to reset my ad password?" might be entered.

[0636] If the suggested solution does not resolve the issue, the user can report this through the feedback form. The server will receive the feedback and, if necessary, escalate it to a support agent. Once escalated, the agent will take steps to provide detailed support based on the request and the user's feedback.

[0637] After the problem is resolved, the user evaluates the quality of support and provides feedback. The server stores this feedback in a database and uses it as training material for the AI ​​module to solve future problems.

[0638] The hardware and software used will consist of a server environment using Flask, the Hugging Face Transformers library and a pre-trained model (distilbert-base-cased-distilled-squad), and a simple in-memory database (using a Python dictionary).

[0639] In this way, a system is created that provides fast and efficient support, and can easily address issues, especially those related to ad performance and settings.

[0640] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0641] Step 1:

[0642] The user uses an information device to access the support system and create a new account. The user enters the required information and submits it.

[0643] Input: User registration information (e.g., email address, name)

[0644] Output: User information stored on the server, confirmation email sent.

[0645] Specific operation: The user enters the required information into a web form from an information device such as a PC or smartphone and clicks the "Submit" button. The server saves the received information to a database, generates a confirmation email, and sends it to the user.

[0646] Step 2:

[0647] The user clicks the link in the verification email to verify their account. The server receives the verification request and updates the user's account to verified.

[0648] Input: Click the link in the verification email.

[0649] Output: Confirmed account information, authentication complete message

[0650] Specific operation: The user clicks the link in the received authentication email, the server receives the request and updates the user's account information, and the server displays a confirmation message.

[0651] Step 3:

[0652] The user logs into the system, enters details of the problem into the support request form, and submits it. The server receives the request and saves it to the database.

[0653] Input: Support request information (e.g., problem details, screenshots)

[0654] Output: Support requests stored in the database

[0655] Specific operation: After logging in, the user enters details of the problem into the support request form that appears and clicks the "Submit" button. The server saves the received information to the database.

[0656] Step 4:

[0657] An AI module on the server analyzes support requests and extracts keywords and phrases using natural language processing techniques.

[0658] Input: Support Request Information

[0659] Output: Extracted keywords and phrases

[0660] Specific operation: The server sends the received support request to the AI ​​module, which then uses natural language processing techniques to analyze the text. It extracts important keywords and phrases.

[0661] Step 5:

[0662] The server searches for the best solution based on keywords extracted from past support databases and FAQ databases.

[0663] Input: Extracted keywords or phrases

[0664] Output: List of optimal solutions

[0665] Specific operation: The server searches the support database and FAQ database based on the extracted keywords and lists relevant solutions.

[0666] Step 6:

[0667] The server prioritizes and presents the user with the optimal solution.

[0668] Input: List of optimal solutions

[0669] Output: Solutions presented to the user

[0670] Specific operation: The server ranks the listed solutions based on priority and displays them on the user's terminal.

[0671] Step 7:

[0672] The user reviews the suggested solutions and attempts to resolve the problem. The user reports the results through a feedback form.

[0673] Input: User feedback

[0674] Output: Feedback information stored on the server

[0675] Specific operation: The user tries the displayed solution, enters the results and comments in the feedback form, and submits it. The server saves the feedback information to the database.

[0676] Step 8:

[0677] The server will escalate the issue to a support agent as needed based on the feedback. The support agent will review the details of the problem and provide additional support.

[0678] Input: User feedback

[0679] Output: Escalated support request, additional support

[0680] Specific operation: The server analyzes the feedback and, if it cannot resolve the issue, escalates it to a support agent. The agent reviews the request and feedback and provides support as needed.

[0681] Example prompt:

[0682] "How can I track the performance of my ads?"

[0683] "I want to know the password reset procedure for advertisements."

[0684] 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.

[0685] This invention relates to a system in which a user enters a support request using an information device, a server receives, analyzes, and proposes a solution to the request, and escalates it to a support agent as needed. Furthermore, the invention incorporates an emotion engine that recognizes the user's emotions and optimizes the response accordingly.

[0686] Users access the support center system using information devices such as PCs, smartphones, or tablets. Through the provided user interface, users create a new account and enter the required information. Once registration is complete, the server saves the entered information to a database and sends a verification email to the user. Users verify their account by clicking the link in the verification email.

[0687] When a user logs into the system, a support request form is displayed, and the user enters details of the problem, screenshots, etc. For example, they may enter information about software error messages or system malfunctions. Once the user submits the request, the server receives it and stores it in the database.

[0688] Next, an AI module on the server analyzes the content of the support request. Specifically, it uses natural language processing technology to understand the request and extract keywords and important phrases. Furthermore, an emotion engine analyzes the user's emotions and determines the user's emotional state (e.g., frustration, anger, sadness, etc.) from the request content, input text, and voice data. Based on this analysis, the server searches its past support database and FAQ database for the best solution. For example, it searches for information such as "how to reset a password" or "how to deal with a specific error message."

[0689] The search results list multiple possible solutions, presented to the user based on priority. The user reviews the suggested solutions on their device and attempts to resolve the problem by following the instructions. In most cases, the problem is resolved through this process. Furthermore, the tone and content of the messages presented are adjusted according to the user's emotional state. For example, if the emotion recognition engine determines that the user is feeling frustrated, the system will display a more empathetic and considerate message.

[0690] If the suggested solution does not resolve the issue, the user reports this through a feedback form. The server receives the feedback and, if necessary, escalates it to a support agent. Once escalated, the agent takes steps to provide detailed support based on the request, the user's feedback, and the sentiment engine's emotional state information. For example, the agent may communicate directly with the user and resolve the issue through remote access. In this case, the agent can understand the user's emotional state and select the appropriate course of action.

[0691] After the problem is resolved, the user evaluates the quality of support and provides feedback. The server stores this feedback in a database and uses it as training material for the AI ​​module to solve future problems. The emotion engine is also continuously improved, enabling more accurate emotion recognition.

[0692] In this way, the system provides fast and efficient support by receiving, analyzing, and suggesting solutions for user support requests. Furthermore, the emotion engine enables personalized responses based on the user's emotional state, and the escalation function allows support agents to intervene in complex issues, thereby improving the quality of support.

[0693] The following describes the processing flow.

[0694] Step 1:

[0695] Users access the support center system using information devices (e.g., PCs, smartphones, tablets). Through the provided user interface, users register an account and enter necessary information such as their name, email address, and password.

[0696] Step 2:

[0697] The server receives the registration information sent from the terminal and stores it in the database. The server then sends an authentication email to the entered email address, requesting the user to confirm.

[0698] Step 3:

[0699] The user clicks the link in the verification email they received to verify their account. This activates the user's account.

[0700] Step 4:

[0701] The user logs into the system. After logging in, a support request form is displayed, and the user enters details of the problem, screenshots, error messages, etc.

[0702] Step 5:

[0703] The server receives the support request sent from the terminal and stores it in the database. The server then passes the request details to the AI ​​module.

[0704] Step 6:

[0705] The server's AI module analyzes the content of the support request. It uses natural language processing technology to understand the request and extract keywords and important phrases.

[0706] Step 7:

[0707] The server's emotion engine analyzes the user's emotional state from the request content, input text, and, if necessary, audio data. For example, it determines whether the user is experiencing emotions such as frustration, anger, or sadness based on keywords and context.

[0708] Step 8:

[0709] The server searches past support and FAQ databases based on extracted keywords and user sentiment information. The server then lists the best solutions and prioritizes them.

[0710] Step 9:

[0711] When the server presents a list of solutions to the user, it adjusts the tone and content of the message according to the user's emotional state. For example, if the user is feeling frustrated, it will use empathetic and polite language.

[0712] Step 10:

[0713] The user checks the suggested solutions on their device and attempts to resolve the problem by following the instructions. In most cases, the problem is resolved through this process.

[0714] Step 11:

[0715] If a user is unable to resolve their issue using the provided solution, they should report this through the feedback form. The server will then receive the feedback from the device.

[0716] Step 12:

[0717] Based on the feedback, the server escalates the issue to a support agent as needed. Along with the escalation notification, the server sends the request details and the user's emotional state information to the agent.

[0718] Step 13:

[0719] A support agent receives the notification and reviews the request, feedback, and emotional state information from the emotion engine. The agent then contacts the user to resolve the issue through remote access and detailed instructions.

[0720] Step 14:

[0721] After the problem is resolved, the user evaluates the quality of support and provides feedback. The server receives the feedback from the device and stores it in a database.

[0722] Step 15:

[0723] The server analyzes the collected feedback and uses it as training material for the AI ​​module and emotion engine. This will improve future problem-solving and emotion recognition capabilities.

[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 failed to consider the user's emotional state, resulting in inappropriate responses and decreased user satisfaction. Furthermore, the solutions provided frequently did not meet user needs, leading to frequent escalations and increased workload for support agents.

[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 a user to input a support request using a device, means for receiving and storing the support request, means for analyzing the content of the support request and searching for an appropriate solution, means for analyzing the user's emotional state, means for adjusting the presentation of the solution based on the emotional state, means for presenting the solution to the user, means for collecting feedback from the user, and means for escalating to a support agent as necessary based on the feedback. This enables individualized responses that take into account the user's emotional state, and by providing an appropriate solution, it is possible to reduce the frequency of escalations to support agents and improve overall user satisfaction.

[0729] A "user" refers to a person who uses the system to submit a support request.

[0730] "Device" refers to information devices such as PCs, smartphones, and tablets.

[0731] A "support request" refers to information that a user submits to the system, such as a problem or question.

[0732] "Means" refers to technical methods or devices used to achieve a specific function within a system.

[0733] A "server" refers to a central computer that receives and analyzes user requests and manages the entire system.

[0734] "Natural language processing technology" refers to the technology that enables computers to understand and analyze human natural language.

[0735] "Keywords" refer to important words or phrases that indicate the content of a support request.

[0736] "Emotional state" refers to the feelings and sensations a user experiences when making a support request, such as frustration or joy.

[0737] "Escalation" refers to the process by which a human, such as a support agent, provides additional support when the initial automated resolution method fails to resolve the issue.

[0738] "Feedback" refers to the opinions and evaluations that users provide regarding support services.

[0739] A "support agent" refers to a specialist staff member who directly addresses users' problems.

[0740] "Solution" refers to the appropriate response or procedure for a user's support request.

[0741] This invention relates to a system in which a user enters a support request using a device, a server receives and analyzes the request, proposes a solution, and escalates it to a support agent as needed. Furthermore, by incorporating an emotion engine, it provides a mechanism to recognize the user's emotional state and optimize the response.

[0742] Hardware and software

[0743] hardware

[0744] This system consists of the following information devices:

[0745] User devices (PCs, smartphones, tablets, etc.)

[0746] Server System

[0747] software

[0748] The software used includes the following specific technologies:

[0749] Natural Language Processing (NLTK, SpaCy)

[0750] Sentiment analysis tool (IBM Watson's Natural Language Understanding)

[0751] Database management systems (MySQL, MongoDB, Firebase, Elasticsearch)

[0752] Remote access tools (TeamViewer, AnyDesk)

[0753] Submitting and receiving support requests

[0754] Users access the support center system using information devices such as PCs, smartphones, and tablets. After accessing the system, users create a new account and enter the required information. At this time, the server saves the entered information to a database and sends an authentication email to the user for verification. Once the user clicks the link in the authentication email to authenticate their account, they will be able to log in.

[0755] Next, after logging in, the user enters details of the problem into a support request form. For example, they might write, "An error message appears during software installation," and attach a screenshot. Once the user submits the request, the server receives it and stores it in the database.

[0756] Request analysis and sentiment recognition

[0757] An AI module on the server analyzes the content of the support request. Specifically, it uses natural language processing techniques to extract keywords and important phrases from the request. Furthermore, the server's emotion engine determines the user's emotional state from the input text and voice data. For example, it may detect "frustration," "anger," or "sadness."

[0758] Providing solutions

[0759] Based on the analysis results, the server searches its past support database and FAQ database for the best solution. For example, "how to reset your password" or "how to deal with a specific error message" may be suggested. The search results list multiple possible solutions and present them to the user based on priority. The user reviews the suggested solutions and attempts to resolve the problem by following the instructions.

[0760] Optimizing responses based on emotions

[0761] The emotion recognition engine determines the user's emotional state. For example, if the emotion engine determines that the user is feeling frustrated, the system will display a more empathetic and considerate message. This can reduce user stress and improve the support experience.

[0762] Escalation and detailed support

[0763] If the suggested solution does not resolve the issue, the user can report this through the feedback form. The server receives the feedback and escalates it to a support agent as needed. The support agent will provide detailed support based on the request and the user's emotional state. For example, the agent may resolve the issue through remote access.

[0764] Gathering feedback and improving the system

[0765] After the problem is resolved, the user evaluates the quality of support and provides feedback. The server stores this feedback in a database and uses it as training material for the AI ​​module to solve future problems. The emotion engine is also continuously improved, enabling more accurate emotion recognition.

[0766] Examples of specific cases and prompt statements

[0767] Specific example

[0768] When a user enters and submits a support request such as "My PC freezes," the server receives the request and analyzes it as follows:

[0769] 1. The server extracts keywords such as "freeze" and "PC".

[0770] 2. The emotion engine detects "frustration" from the user's text.

[0771] 3. Search for the best solution (e.g., "How to fix computer freezing problems") and present it in order of priority.

[0772] Example of a prompt

[0773] "Please tell me what to do if the software installation fails."

[0774] "Please enter the password reset procedure."

[0775] "Please tell me how to fix the problem of my PC freezing."

[0776] In this way, the system efficiently processes user support requests and provides users with the best possible support experience.

[0777] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0778] Step 1: User access to the support center system and account creation

[0779] Specific actions

[0780] 1. Users access the support center system using information devices such as PCs, smartphones, and tablets.

[0781] Input: Access the support center website from your device's browser (enter the URL).

[0782] Output: The support center user interface is displayed.

[0783] 2. The user enters the necessary information (username, email address, password, etc.) into the form for creating a new account.

[0784] Input: Account information (username, email address, password)

[0785] Output: The input information will be displayed in the form.

[0786] 3. When the user presses the submit button, the server receives the entered information and saves it to the database. It also sends an authentication email to the user.

[0787] Input: Click the submit button

[0788] Output: Save information to the database and send an authentication email.

[0789] 4. The user authenticates their account by clicking the link in the verification email they received.

[0790] Input: Click the link in the verification email.

[0791] Output: Account becomes active

[0792] Step 2: Submit a support request

[0793] Specific actions

[0794] 1. The user logs into their account.

[0795] Input: Login information (email address, password)

[0796] Output: A support request form is displayed.

[0797] 2. The user enters details of the problem (e.g., software error details, screenshots, etc.) into the support request form.

[0798] Input: Support request details and required attachments

[0799] Output: The information entered in the form will be displayed.

[0800] 3. The user submits a request. The server receives the request, saves it to the database, and prepares it for analysis.

[0801] Input: Click the submit button

[0802] Output: Save request information to the database

[0803] Step 3: Request analysis and sentiment recognition

[0804] Specific actions

[0805] 1. The AI ​​module on the server analyzes the support requests it receives.

[0806] Input: Received request data

[0807] Output: Analysis results (keywords and phrases)

[0808] 2. Extract keywords and phrases from the request content using natural language processing techniques (e.g., using SpaCy or NLTK).

[0809] Input: Request text

[0810] Output: Extracted keywords and phrases

[0811] 3. The server's emotion engine determines the user's emotional state from their input text and voice data (e.g., using IBM Watson's Natural Language Understanding).

[0812] Input: Request text, audio data

[0813] Output: Emotional state (frustration, anger, sadness, etc.)

[0814] Step 4: Presenting a solution

[0815] Specific actions

[0816] 1. The server searches for the best solution from past support databases and FAQ databases.

[0817] Input: Keywords, phrases, emotional states

[0818] Output: List of possible solutions

[0819] 2. Organize search results in order of priority and present them to the user.

[0820] Input: List of possible solutions

[0821] Output: List of prioritized solutions

[0822] 3. A list of solutions will be displayed on the user's device.

[0823] Input: List of solutions

[0824] Output: List of solutions displayed on the terminal

[0825] Step 5: Escalation and provision of detailed support

[0826] Specific actions

[0827] 1. If the user's problem is not resolved by the suggested solution, they should report this through the feedback form.

[0828] Input: Feedback content

[0829] Output: Sending feedback

[0830] 2. The server receives the feedback and escalates it to a support agent as needed.

[0831] Input: Received feedback

[0832] Output: Escalation notification

[0833] 3. Support agents provide detailed support based on the request and the user's emotional state. For example, they may use remote access tools to resolve the issue.

[0834] Input: Escalation information, emotional state information

[0835] Output: Detailed support provided

[0836] Step 6: Gathering Feedback and Improving the System

[0837] Specific actions

[0838] 1. After the problem is resolved, the user evaluates the quality of support and provides feedback.

[0839] Input: Evaluation content, feedback

[0840] Output: Sending feedback

[0841] 2. The server saves the feedback to a database and uses it as training material for the AI ​​module to solve future problems.

[0842] Input: Feedback data

[0843] Output: Feedback stored in the database

[0844] Through the steps outlined above, the system can efficiently process user support requests and provide users with the best possible support experience.

[0845] (Application Example 2)

[0846] 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."

[0847] Traditional support systems have the means to receive support requests from users and offer appropriate solutions, but they often resulted in a poor user experience due to insufficient consideration of the user's emotional state. Furthermore, the uniform approach to solutions frequently caused dissatisfaction and stress, especially for emotionally unstable users. Additionally, the escalation process when a problem could not be resolved also lacked consideration for the user's feelings, leading to difficulties in smooth communication with support agents.

[0848] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for a user to input a support request using an information device, means for receiving and storing the support request, means for analyzing the content of the support request and searching for an appropriate solution, means for presenting the solution to the user, means for the analysis means to recognize the user's emotions and optimize the response, means for collecting feedback from the user, and means for escalating to a support agent as necessary based on the feedback. This enables optimal support that takes into account the user's emotional state, and particularly enables rapid and efficient problem solving in electronic payment services. In addition, since the escalation process can also be handled with an understanding of the user's emotional state, smoother support can be provided.

[0849] An "information device" refers to a terminal such as a computer or smartphone that a user uses to enter a support request.

[0850] A "support request" is information that details the problems or inquiries a user is facing.

[0851] The "means of receiving and storing" refer to a mechanism where the server receives a support request and stores its contents in a database.

[0852] "Analysis method" refers to a technique that uses natural language processing technology to understand the content of a support request, extract keywords and phrases, and identify the problem.

[0853] A "solution" refers to the methods or procedures for dealing with and resolving an identified problem.

[0854] "Means of presentation" refers to an interface for showing the user the solution obtained through analysis.

[0855] "Means of recognizing emotions and optimizing responses" refers to technologies that analyze a user's emotional state and provide the most appropriate response based on that analysis.

[0856] "Feedback" refers to evaluations and comments made by users regarding the solutions and support provided.

[0857] "Means of collection" refers to a system for receiving user feedback and sending and storing it on a server.

[0858] "Escalation" refers to the process of transferring a user's problem to an agent who can provide more advanced support if the problem cannot be resolved in the initial stages.

[0859] A "database" is a system for storing and managing information such as support requests, solutions, and user feedback.

[0860] "Natural language processing technology" is a technology that enables computers to understand and interpret human language and extract its meaning.

[0861] This invention relates to a system in which a user inputs a support request using an information device, a server receives and analyzes the request, and presents the optimal solution. Furthermore, by incorporating an emotion engine that recognizes the user's emotions and optimizes the response, personalized support becomes possible.

[0862] System Configuration Description

[0863] The system consists of the following main hardware and software components:

[0864] 1. Information equipment

[0865] This is a device used by users to enter support requests. These devices include computers, smartphones, and tablets.

[0866] 2. Server

[0867] This is the central computing unit responsible for receiving support requests, storing them in a database, and processing and presenting solutions. Specific examples of software used include Google Cloud Natural Language API and OpenAI GPT-4 for natural language processing engines, and IBM Watson Tone Analyzer and Microsoft Azure Cognitive Services for sentiment engines.

[0868] 3. Database

[0869] This is a system for accumulating support requests, past support data, FAQs, and user feedback. Specific examples include MySQL and PostgreSQL.

[0870] Processing flow

[0871] 1. Initial Setup

[0872] Users access the app using their smartphones and create a new account. They enter the required information, receive a verification email, and verify their account.

[0873] 2. Enter your support request

[0874] Users submit support requests through the app. These requests may include issues such as login problems or transaction errors with electronic payment services. The request includes error messages and details of the problem.

[0875] 3. Receiving and saving requests

[0876] The server receives the submitted support request and saves it to the database.

[0877] 4. Analysis and Sentiment Recognition

[0878] The natural language processing engine analyzes the request content and extracts keywords and important phrases. The emotion engine analyzes the user's emotional state (e.g., frustration, anger, sadness).

[0879] 5. Searching for and presenting solutions

[0880] The system searches for the best solution from support databases and FAQs, and then presents the message with a tone and content adjusted according to the user's emotional state.

[0881] 6. Feedback and Escalation

[0882] We collect user feedback and escalate it to support agents as needed. The agents understand the user's emotional state and take appropriate action.

[0883] Specific example

[0884] For example, if a user is unable to log in to their account with an electronic payment service, the support request will be processed as follows:

[0885] Example of a prompt

[0886] "Analysis of a support request when a user is unable to log in to their account on an electronic payment service. The user created the account two weeks ago. The error message is 'Incorrect password.' The user appears frustrated. The emotion engine presents empathetic messages and searches the past database for the best solution. If the user tries the suggested solutions and the problem persists, the issue is escalated to an agent."

[0887] Thus, the embodiments of the invention aim to provide prompt and accurate support in response to the diverse needs of users.

[0888] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0889] Step 1:

[0890] The user enters a support request using an information device (smartphone, PC, etc.). They enter details of the problem they are facing and attach supporting documents such as screenshots as needed. The entered information is then sent from the device to the server.

[0891] Input: User-submitted details of the problem, error message, and screenshot.

[0892] Output: Support Request Data

[0893] Step 2:

[0894] The server receives support requests and stores them in the database. The server ensures reliability and security.

[0895] Input: Support Request Data

[0896] Output: Support request records stored in the database

[0897] Step 3:

[0898] The server's natural language processing engine analyzes the content of the support request. It extracts keywords and important phrases from the request to identify the problem.

[0899] Input: Support Request Data

[0900] Output: Extracted keywords, identified issues

[0901] Step 4:

[0902] The server's emotion engine recognizes the user's emotions. It analyzes the request content and various input data (text, audio data, etc.) to evaluate the user's emotional state. For example, it determines whether the user is feeling frustrated.

[0903] Input: Support request data, text data, audio data

[0904] Output: User's emotional state (e.g., frustration, anger, sadness)

[0905] Step 5:

[0906] The server searches the database for the best solution. Based on past support and FAQ databases, it selects and prioritizes the most suitable solution for the user. It also adjusts the tone and content of messages according to the user's emotional state.

[0907] Input: Identified problem, user's emotional state

[0908] Output: Optimal solution, adjusted message

[0909] Step 6:

[0910] The server presents a solution to the user. The terminal displays the optimal solution and a tailored message.

[0911] Input: Optimal solution, tailored message

[0912] Output: Solution and message displayed on the user terminal

[0913] Step 7:

[0914] The user attempts to solve the problem according to the suggested solution and provides feedback on the results.

[0915] Input: Solution trial results, feedback data

[0916] Output: User feedback

[0917] Step 8:

[0918] The server receives feedback from the user and stores it in the database. The server analyzes the feedback and determines whether the issue was successfully resolved.

[0919] Input: Feedback data

[0920] Output: Feedback records stored in the database, resolution result

[0921] Step 9:

[0922] If the problem persists, the server will escalate it to a support agent based on the feedback. The agent will then take steps to provide detailed support based on the request and the user's emotional state.

[0923] Input: Feedback data, user's emotional state

[0924] Output: Escalation data to the agent

[0925] In this way, each step works together to form a system that supports the rapid and appropriate resolution of user problems.

[0926] 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.

[0927] 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.

[0928] 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.

[0929] [Third Embodiment]

[0930] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0931] 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.

[0932] 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).

[0933] 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.

[0934] 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.

[0935] 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).

[0936] 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.

[0937] 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.

[0938] 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.

[0939] 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.

[0940] 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.

[0941] 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".

[0942] This invention relates to a system in which a user enters a support request using an information device, a server receives and analyzes the request, presents a solution, and escalates it to a support agent as necessary.

[0943] Users access the support center system using information devices such as PCs, smartphones, or tablets. Through the provided user interface, users create a new account and enter the required information. Once registration is complete, the server saves the entered information to a database and sends a verification email to the user. Users verify their account by clicking the link in the verification email.

[0944] When a user logs into the system, a support request form is displayed, and the user enters details of the problem, screenshots, etc. For example, they may enter information about software error messages or system malfunctions. Once the user submits the request, the server receives it and stores it in the database.

[0945] Next, an AI module on the server analyzes the content of the support request. Specifically, it uses natural language processing technology to understand the content of the request and extract keywords and important phrases. Based on this analysis, the server searches its past support database and FAQ database for the best solution. For example, it searches for information such as "how to reset a password" or "how to deal with a specific error message."

[0946] The search results list multiple possible solutions, presented to the user based on priority. The user reviews the suggested solutions on their device and attempts to resolve the problem by following the instructions. In most cases, the problem is resolved through this process.

[0947] If the suggested solution does not resolve the issue, the user can report this through the feedback form. The server will receive the feedback and, if necessary, escalate it to a support agent. Once escalated, the agent will take steps to provide detailed support based on the request and the user's feedback.

[0948] For example, an agent might communicate directly with the user and resolve the issue through remote access.

[0949] After the problem is resolved, the user evaluates the quality of support and provides feedback. The server stores this feedback in a database and uses it as training material for the AI ​​module to solve future problems.

[0950] In this way, the system provides fast and efficient support by receiving, analyzing, and suggesting solutions for user support requests. Furthermore, the escalation function allows support agents to intervene in complex issues, thereby improving the quality of support.

[0951] The following describes the processing flow.

[0952] Step 1:

[0953] Users access the support center system using information devices (e.g., PCs, smartphones, tablets). Through the provided user interface, users register an account and enter necessary information such as their name, email address, and password.

[0954] Step 2:

[0955] The server receives the registration information sent from the terminal and stores it in the database. The server then sends an authentication email to the entered email address, requesting the user to confirm.

[0956] Step 3:

[0957] The user clicks the link in the verification email they received to verify their account. This activates the user's account.

[0958] Step 4:

[0959] The user logs into the system. After logging in, a support request form is displayed. The user enters details of the problem, screenshots, error messages, etc.

[0960] Step 5:

[0961] The server receives the support request sent from the terminal and stores it in the database. The server then passes the request details to the AI ​​module.

[0962] Step 6:

[0963] The server's AI module analyzes the content of the support request. It uses natural language processing techniques to extract keywords and important phrases from the request.

[0964] Step 7:

[0965] The server searches past support databases and FAQ databases based on the extracted keywords. It then lists multiple optimal solutions and prioritizes them.

[0966] Step 8:

[0967] The server presents the user with a list of solutions in order of priority. The user reviews the solutions presented on their terminal and attempts to resolve the problem by following the instructions.

[0968] Step 9:

[0969] If a user is unable to resolve their issue using the provided solution, they should report this through the feedback form. The server will then receive the feedback from the device.

[0970] Step 10:

[0971] The server will escalate the issue to a support agent based on the feedback received, if necessary. The request and feedback will be sent to the agent along with an escalation notification.

[0972] Step 11:

[0973] A support agent receives the notification and reviews the request and feedback. The agent contacts the user and assists in resolving the issue through remote access and detailed instructions.

[0974] Step 12:

[0975] After the problem is resolved, the user evaluates the quality of support and provides feedback. The server receives the feedback from the device and stores it in a database.

[0976] Step 13:

[0977] The server analyzes the feedback it collects and uses it as training material for the AI ​​module, thereby improving its future problem-solving capabilities.

[0978] (Example 1)

[0979] 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."

[0980] Traditional support systems struggled to efficiently analyze user-submitted support requests and promptly provide appropriate solutions. In particular, the diversity and complexity of requests made it difficult to find solutions quickly, leading to decreased user satisfaction. Furthermore, the escalation process for unresolved issues was inefficient, resulting in an increase in manual intervention by support agents.

[0981] 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.

[0982] In this invention, the server includes means for a user to input a support request using an information device, means for receiving and storing the support request, means for using a generative AI model to analyze the content of the support request, means for the generative AI model to analyze the content of the support request using natural language processing technology and extract keywords and important phrases, means for searching for solutions from past support databases and FAQ databases, means for presenting the solutions to the user, means for collecting feedback from the user, and means for escalating to a support agent as necessary based on the feedback. This makes it possible to quickly and accurately analyze support requests and present appropriate solutions to users. Furthermore, if the problem cannot be resolved, escalation is carried out efficiently, enabling a rapid response by support agents.

[0983] "Information device" refers to electronic devices such as computers, smartphones, and tablets that users use to enter support requests.

[0984] A "support request" is a request submitted by a user to the system, detailing a problem and seeking assistance.

[0985] "Means" refers to a method, technique, or apparatus used to perform a particular function or task.

[0986] A "generative AI model" refers to an algorithm or model trained to perform a specific task using artificial intelligence.

[0987] "Natural language processing technology" refers to the technology that enables computers to understand, analyze, and generate human language.

[0988] "Keywords and important phrases" refer to words and sentences that are particularly important when analyzing the content of a support request.

[0989] The "past support database" is a database that stores support requests and response histories recorded to date.

[0990] An "FAQ database" is a database that compiles frequently asked questions and their answers.

[0991] "Feedback" refers to the opinions and results that users provide regarding the quality of support and the solutions provided.

[0992] "Escalation" is the process of transferring a problem that could not be resolved in the initial support process to a higher-level support agent.

[0993] A "support agent" is a specialized operator or technician who directly handles user support requests.

[0994] This invention is a system in which a user inputs a support request using an information device, a server receives and analyzes the request, presents a solution, and escalates it to a support agent as necessary. Specific embodiments are described below.

[0995] Users access the support center system using information devices such as PCs, smartphones, and tablets. First, users create a new account through the provided user interface and enter the necessary information (e.g., username, email address, password). The server stores this information in its database and sends an authentication email to the user for verification. This authentication email is sent using an SMTP server. Users authenticate their account by clicking a link in the authentication email. Clicking this link updates the server's account status, marking it as authenticated.

[0996] When a user logs into the system, a support request form is displayed. The user enters details of the problem and screenshots into this form. For example, a user might enter "The software displays an error message and does not work." Once the user submits the request, the server receives it and saves it to the database.

[0997] Next, a generative AI model on the server (for example, a natural language processing model using TensorFlow) analyzes the content of the support request. The server uses this generative AI model to understand the content of the request and extract keywords and important phrases. Specifically, it analyzes the user's input using natural language processing techniques and extracts important information.

[0998] Based on the analysis results, the server searches its past support database and FAQ database (e.g., Elasticsearch) for the best solution. For example, for "error code 1234," it might search for solutions such as "how to reinstall the app" or "how to clear the cache." Multiple solutions are listed and presented to the user in order of priority. The user reviews the presented solutions and attempts to resolve the problem by following the instructions.

[0999] If the suggested solution does not resolve the issue, the user can report this through the feedback form. The server receives the feedback and, if necessary, escalates it to a support agent. Once escalated, the support agent provides detailed support based on the request and the user's feedback. For example, the agent may communicate directly with the user and resolve the issue through remote access.

[1000] Finally, after the problem is resolved, the user evaluates the quality of support and provides feedback. The server stores this feedback in a database and uses it as training material for a generative AI model to solve future problems.

[1001] As a concrete example, consider a case where a user enters a problem, such as "An error message appears when I open the app." In this case, the user enters "When I open the app, I get error code 1234 and it doesn't work" into the support request form. The server's generated AI model analyzes "error code 1234" and searches its past support database and FAQ database for solutions to this error. The server then prioritizes and presents these solutions to the user.

[1002] An example of a prompt statement you can enter is as follows:

[1003] "Users should log in to their account and submit a support request using the following prompt: 'When I open the app, I get error code 1234 and it doesn't work. Please tell me how to fix it.'"

[1004] This system enables the rapid and accurate analysis of user support requests, leading to efficient problem-solving. Furthermore, detailed support from support agents is provided as needed, improving overall support quality.

[1005] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1006] Step 1:

[1007] Account creation and verification

[1008] Users access the support center system using information devices such as PCs, smartphones, and tablets.

[1009] Input: Account information such as username, email address, and password.

[1010] The server receives information entered through the provided user interface.

[1011] The server saves the entered account information to the database.

[1012] The server sends an authentication email to the user for verification. The authentication email is sent using an SMTP server.

[1013] Output: An authentication email is sent to the user.

[1014] The user authenticates their account by clicking the link in the authentication email. By clicking the link, the server updates the user's account status and marks it as authenticated.

[1015] Step 2:

[1016] Login and support request submission

[1017] Input: User's authenticated account information (username, password).

[1018] The user logs into the system.

[1019] The server receives the login request and verifies the authentication credentials.

[1020] Output: Login successful, and the user is displayed with a support request form.

[1021] The user enters details of the problem and screenshots into the support request form.

[1022] Input: Details of the problem (e.g., software error message) and attachments (e.g., screenshots).

[1023] When a user submits a request, the server receives the request and stores it in the database.

[1024] Output: Saved support request data.

[1025] Step 3:

[1026] Support request analysis

[1027] Input: Support request data.

[1028] A generative AI model on the server (for example, a natural language processing model using TensorFlow) analyzes the content of the support request.

[1029] The server uses a generative AI model to understand the content of the request and extract keywords and important phrases.

[1030] Data processing: Use natural language processing techniques to extract keywords and important phrases from the text of support requests.

[1031] Output: Extracted keywords and important phrases.

[1032] Step 4:

[1033] Searching for and presenting solutions

[1034] Input: Extracted keywords and important phrases.

[1035] The server searches its past support and FAQ databases for the best solution. For example, it might use Elasticsearch to search the database.

[1036] Data Calculation: Generate search queries and search the database.

[1037] Output: A list of multiple solutions.

[1038] The server prioritizes the search results and presents solutions to the user.

[1039] Output: A list of solutions presented to the user.

[1040] Step 5:

[1041] Attempting to resolve the user issue

[1042] The user reviews the suggested solutions and attempts to resolve the problem by following the instructions.

[1043] Input: User feedback (results of attempted solutions).

[1044] Output: User feedback on whether the problem was resolved.

[1045] Step 6:

[1046] Feedback and escalation

[1047] Input: User feedback (if the problem persists).

[1048] If a user is unable to resolve their issue using the suggested solution, they should report this through the feedback form.

[1049] The server receives feedback and escalates it to a support agent as needed.

[1050] Output: Request escalated to a support agent.

[1051] Step 7:

[1052] Intervention by a support agent

[1053] Input: Escalated request.

[1054] Support agents provide detailed support based on the request and user feedback.

[1055] Specific operation: In some cases, the agent communicates directly with the user and resolves issues through remote access.

[1056] Output: Detailed support for problem resolution.

[1057] Step 8:

[1058] Supportive feedback and learning

[1059] Input: User feedback after problem resolution (evaluation of support quality).

[1060] Users rate the quality of support and provide feedback.

[1061] The server stores this feedback in a database and uses it as training material for generative AI models to solve future problems.

[1062] Output: Saved feedback data and an enhanced AI model.

[1063] In this way, the system can quickly and accurately analyze support requests and resolve problems efficiently.

[1064] (Application Example 1)

[1065] 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."

[1066] Traditional support systems have presented challenges in quickly finding appropriate solutions when users encounter problems with ad performance or settings. Issues related to ad management and performance tracking are particularly complex and often beyond the capabilities of general FAQs and support databases. Furthermore, when escalation is necessary, it can be difficult to transfer the issue to a support agent at the appropriate time, leading to delays in problem resolution.

[1067] 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.

[1068] In this invention, the server includes means for a user to input a support request using an information device, means for receiving and storing the support request, means for analyzing the content of the support request and searching for an appropriate solution, means for presenting the solution to the user, means for collecting feedback from the user, means for escalating to a support agent as necessary based on the feedback, means for resolving issues related to advertising performance and settings, means for presenting an optimal solution regarding advertising performance using a generative AI model, and means for the solution to automatically determine the requirements for escalation. This enables quick and appropriate resolution of advertising-related issues, thereby improving user satisfaction.

[1069] "Information device" refers to computer systems and devices used by users to enter support requests, and includes PCs, smartphones, tablets, etc.

[1070] A "support request" refers to inquiry information that includes details of the problem or question the user is facing.

[1071] A "server" refers to a computer system that receives and analyzes support requests and provides appropriate solutions.

[1072] "Analysis tools" refer to the part of a system that has the functionality to understand the content of a support request and derive an appropriate solution.

[1073] "Natural language processing technology" refers to techniques that enable computers to understand and analyze human language, and includes keyword extraction and semantic analysis of text.

[1074] "Feedback" refers to the evaluations and comments that users provide regarding the solutions presented.

[1075] "Escalation" refers to the process by which a user's problem is handed over to a support agent when they are unable to resolve it themselves.

[1076] "Ad performance" refers to metrics that indicate how effectively an ad is working, and includes metrics such as click-through rate and conversion rate.

[1077] A "generative AI model" refers to an artificial intelligence model that has been trained using machine learning or deep learning to perform a specific task.

[1078] "Providing a solution" refers to the process of showing the user the best possible answer or procedure for their support request.

[1079] This invention relates to a system in which a user enters a support request using an information device, a server receives and analyzes the request, presents a solution, and escalates it to a support agent as necessary.

[1080] Users access the support system using information devices such as PCs, smartphones, and tablets. Through the provided interface, users first create a new account and enter the required information. Once registration is complete, the server saves the entered information to its database and sends a verification email to the user. Users then verify their account by clicking the link in the verification email.

[1081] When a user logs into the system, a support request form is displayed, and the user enters details of the problem, screenshots, etc. The server receives the request and saves it to the database.

[1082] Next, an AI module on the server analyzes the support request. Specifically, it uses natural language processing technology to understand the content of the request and extract keywords and important phrases. Based on this analysis, the server searches its past support database and FAQ database for the best solution.

[1083] The search results list multiple possible solutions, presented to the user based on priority. The user reviews the suggested solutions on their device and attempts to resolve the problem by following the instructions. In most cases, the problem is resolved through this process.

[1084] For issues related to ad performance and settings, a generative AI model is used to suggest the optimal solution. The server utilizes the AI ​​model based on the prompt text entered by the user to find the appropriate solution. For example, prompt texts such as "How can I track ad performance?" or "I want to know how to reset my ad password?" might be entered.

[1085] If the suggested solution does not resolve the issue, the user can report this through the feedback form. The server will receive the feedback and, if necessary, escalate it to a support agent. Once escalated, the agent will take steps to provide detailed support based on the request and the user's feedback.

[1086] After the problem is resolved, the user evaluates the quality of support and provides feedback. The server stores this feedback in a database and uses it as training material for the AI ​​module to solve future problems.

[1087] The hardware and software used will consist of a server environment using Flask, the Hugging Face Transformers library and a pre-trained model (distilbert-base-cased-distilled-squad), and a simple in-memory database (using a Python dictionary).

[1088] In this way, a system is created that provides fast and efficient support, and can easily address issues, especially those related to ad performance and settings.

[1089] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1090] Step 1:

[1091] The user uses an information device to access the support system and create a new account. The user enters the required information and submits it.

[1092] Input: User registration information (e.g., email address, name)

[1093] Output: User information stored on the server, confirmation email sent.

[1094] Specific operation: The user enters the required information into a web form from an information device such as a PC or smartphone and clicks the "Submit" button. The server saves the received information to a database, generates a confirmation email, and sends it to the user.

[1095] Step 2:

[1096] The user clicks the link in the verification email to verify their account. The server receives the verification request and updates the user's account to verified.

[1097] Input: Click the link in the verification email.

[1098] Output: Confirmed account information, authentication complete message

[1099] Specific operation: The user clicks the link in the received authentication email, the server receives the request and updates the user's account information, and the server displays a confirmation message.

[1100] Step 3:

[1101] The user logs into the system, enters details of the problem into the support request form, and submits it. The server receives the request and saves it to the database.

[1102] Input: Support request information (e.g., problem details, screenshots)

[1103] Output: Support requests stored in the database

[1104] Specific operation: After logging in, the user enters details of the problem into the support request form that appears and clicks the "Submit" button. The server saves the received information to the database.

[1105] Step 4:

[1106] An AI module on the server analyzes support requests and extracts keywords and phrases using natural language processing techniques.

[1107] Input: Support Request Information

[1108] Output: Extracted keywords and phrases

[1109] Specific operation: The server sends the received support request to the AI ​​module, which then uses natural language processing techniques to analyze the text. It extracts important keywords and phrases.

[1110] Step 5:

[1111] The server searches for the best solution based on keywords extracted from past support databases and FAQ databases.

[1112] Input: Extracted keywords or phrases

[1113] Output: List of optimal solutions

[1114] Specific operation: The server searches the support database and FAQ database based on the extracted keywords and lists relevant solutions.

[1115] Step 6:

[1116] The server prioritizes and presents the user with the optimal solution.

[1117] Input: List of optimal solutions

[1118] Output: Solutions presented to the user

[1119] Specific operation: The server ranks the listed solutions based on priority and displays them on the user's terminal.

[1120] Step 7:

[1121] The user reviews the suggested solutions and attempts to resolve the problem. The user reports the results through a feedback form.

[1122] Input: User feedback

[1123] Output: Feedback information stored on the server

[1124] Specific operation: The user tries the displayed solution, enters the results and comments in the feedback form, and submits it. The server saves the feedback information to the database.

[1125] Step 8:

[1126] The server will escalate the issue to a support agent as needed based on the feedback. The support agent will review the details of the problem and provide additional support.

[1127] Input: User feedback

[1128] Output: Escalated support request, additional support

[1129] Specific operation: The server analyzes the feedback and, if it cannot resolve the issue, escalates it to a support agent. The agent reviews the request and feedback and provides support as needed.

[1130] Example prompt:

[1131] "How can I track the performance of my ads?"

[1132] "I want to know the password reset procedure for advertisements."

[1133] 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.

[1134] This invention relates to a system in which a user enters a support request using an information device, a server receives, analyzes, and proposes a solution to the request, and escalates it to a support agent as needed. Furthermore, the invention incorporates an emotion engine that recognizes the user's emotions and optimizes the response accordingly.

[1135] Users access the support center system using information devices such as PCs, smartphones, or tablets. Through the provided user interface, users create a new account and enter the required information. Once registration is complete, the server saves the entered information to a database and sends a verification email to the user. Users verify their account by clicking the link in the verification email.

[1136] When a user logs into the system, a support request form is displayed, and the user enters details of the problem, screenshots, etc. For example, they may enter information about software error messages or system malfunctions. Once the user submits the request, the server receives it and stores it in the database.

[1137] Next, an AI module on the server analyzes the content of the support request. Specifically, it uses natural language processing technology to understand the request and extract keywords and important phrases. Furthermore, an emotion engine analyzes the user's emotions and determines the user's emotional state (e.g., frustration, anger, sadness, etc.) from the request content, input text, and voice data. Based on this analysis, the server searches its past support database and FAQ database for the best solution. For example, it searches for information such as "how to reset a password" or "how to deal with a specific error message."

[1138] The search results list multiple possible solutions, presented to the user based on priority. The user reviews the suggested solutions on their device and attempts to resolve the problem by following the instructions. In most cases, the problem is resolved through this process. Furthermore, the tone and content of the messages presented are adjusted according to the user's emotional state. For example, if the emotion recognition engine determines that the user is feeling frustrated, the system will display a more empathetic and considerate message.

[1139] If the suggested solution does not resolve the issue, the user reports this through a feedback form. The server receives the feedback and, if necessary, escalates it to a support agent. Once escalated, the agent takes steps to provide detailed support based on the request, the user's feedback, and the sentiment engine's emotional state information. For example, the agent may communicate directly with the user and resolve the issue through remote access. In this case, the agent can understand the user's emotional state and select the appropriate course of action.

[1140] After the problem is resolved, the user evaluates the quality of support and provides feedback. The server stores this feedback in a database and uses it as training material for the AI ​​module to solve future problems. The emotion engine is also continuously improved, enabling more accurate emotion recognition.

[1141] In this way, the system provides fast and efficient support by receiving, analyzing, and suggesting solutions for user support requests. Furthermore, the emotion engine enables personalized responses based on the user's emotional state, and the escalation function allows support agents to intervene in complex issues, thereby improving the quality of support.

[1142] The following describes the processing flow.

[1143] Step 1:

[1144] Users access the support center system using information devices (e.g., PCs, smartphones, tablets). Through the provided user interface, users register an account and enter necessary information such as their name, email address, and password.

[1145] Step 2:

[1146] The server receives the registration information sent from the terminal and stores it in the database. The server then sends an authentication email to the entered email address, requesting the user to confirm.

[1147] Step 3:

[1148] The user clicks the link in the verification email they received to verify their account. This activates the user's account.

[1149] Step 4:

[1150] The user logs into the system. After logging in, a support request form is displayed, and the user enters details of the problem, screenshots, error messages, etc.

[1151] Step 5:

[1152] The server receives the support request sent from the terminal and stores it in the database. The server then passes the request details to the AI ​​module.

[1153] Step 6:

[1154] The server's AI module analyzes the content of the support request. It uses natural language processing technology to understand the request and extract keywords and important phrases.

[1155] Step 7:

[1156] The server's emotion engine analyzes the user's emotional state from the request content, input text, and, if necessary, audio data. For example, it determines whether the user is experiencing emotions such as frustration, anger, or sadness based on keywords and context.

[1157] Step 8:

[1158] The server searches past support and FAQ databases based on extracted keywords and user sentiment information. The server then lists the best solutions and prioritizes them.

[1159] Step 9:

[1160] When the server presents a list of solutions to the user, it adjusts the tone and content of the message according to the user's emotional state. For example, if the user is feeling frustrated, it will use empathetic and polite language.

[1161] Step 10:

[1162] The user checks the suggested solutions on their device and attempts to resolve the problem by following the instructions. In most cases, the problem is resolved through this process.

[1163] Step 11:

[1164] If a user is unable to resolve their issue using the provided solution, they should report this through the feedback form. The server will then receive the feedback from the device.

[1165] Step 12:

[1166] Based on the feedback, the server escalates the issue to a support agent as needed. Along with the escalation notification, the server sends the request details and the user's emotional state information to the agent.

[1167] Step 13:

[1168] A support agent receives the notification and reviews the request, feedback, and emotional state information from the emotion engine. The agent then contacts the user to resolve the issue through remote access and detailed instructions.

[1169] Step 14:

[1170] After the problem is resolved, the user evaluates the quality of support and provides feedback. The server receives the feedback from the device and stores it in a database.

[1171] Step 15:

[1172] The server analyzes the collected feedback and uses it as training material for the AI ​​module and emotion engine. This will improve future problem-solving and emotion recognition capabilities.

[1173] (Example 2)

[1174] 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."

[1175] Traditional support systems often failed to consider the user's emotional state, resulting in inappropriate responses and decreased user satisfaction. Furthermore, the solutions provided frequently did not meet user needs, leading to frequent escalations and increased workload for support agents.

[1176] 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.

[1177] In this invention, the server includes means for a user to input a support request using a device, means for receiving and storing the support request, means for analyzing the content of the support request and searching for an appropriate solution, means for analyzing the user's emotional state, means for adjusting the presentation of the solution based on the emotional state, means for presenting the solution to the user, means for collecting feedback from the user, and means for escalating to a support agent as necessary based on the feedback. This enables individualized responses that take into account the user's emotional state, and by providing an appropriate solution, it is possible to reduce the frequency of escalations to support agents and improve overall user satisfaction.

[1178] A "user" refers to a person who uses the system to submit a support request.

[1179] "Device" refers to information devices such as PCs, smartphones, and tablets.

[1180] A "support request" refers to information that a user submits to the system, such as a problem or question.

[1181] "Means" refers to technical methods or devices used to achieve a specific function within a system.

[1182] A "server" refers to a central computer that receives and analyzes user requests and manages the entire system.

[1183] "Natural language processing technology" refers to the technology that enables computers to understand and analyze human natural language.

[1184] "Keywords" refer to important words or phrases that indicate the content of a support request.

[1185] "Emotional state" refers to the feelings and sensations a user experiences when making a support request, such as frustration or joy.

[1186] "Escalation" refers to the process by which a human, such as a support agent, provides additional support when the initial automated resolution method fails to resolve the issue.

[1187] "Feedback" refers to the opinions and evaluations that users provide regarding support services.

[1188] A "support agent" refers to a specialist staff member who directly addresses users' problems.

[1189] "Solution" refers to the appropriate response or procedure for a user's support request.

[1190] This invention relates to a system in which a user enters a support request using a device, a server receives and analyzes the request, proposes a solution, and escalates it to a support agent as needed. Furthermore, by incorporating an emotion engine, it provides a mechanism to recognize the user's emotional state and optimize the response.

[1191] Hardware and software

[1192] hardware

[1193] This system consists of the following information devices:

[1194] User devices (PCs, smartphones, tablets, etc.)

[1195] Server System

[1196] software

[1197] The software used includes the following specific technologies:

[1198] Natural Language Processing (NLTK, SpaCy)

[1199] Sentiment analysis tool (IBM Watson's Natural Language Understanding)

[1200] Database management systems (MySQL, MongoDB, Firebase, Elasticsearch)

[1201] Remote access tools (TeamViewer, AnyDesk)

[1202] Submitting and receiving support requests

[1203] Users access the support center system using information devices such as PCs, smartphones, and tablets. After accessing the system, users create a new account and enter the required information. At this time, the server saves the entered information to a database and sends an authentication email to the user for verification. Once the user clicks the link in the authentication email to authenticate their account, they will be able to log in.

[1204] Next, after logging in, the user enters details of the problem into a support request form. For example, they might write, "An error message appears during software installation," and attach a screenshot. Once the user submits the request, the server receives it and stores it in the database.

[1205] Request analysis and sentiment recognition

[1206] An AI module on the server analyzes the content of the support request. Specifically, it uses natural language processing techniques to extract keywords and important phrases from the request. Furthermore, the server's emotion engine determines the user's emotional state from the input text and voice data. For example, it may detect "frustration," "anger," or "sadness."

[1207] Providing solutions

[1208] Based on the analysis results, the server searches its past support database and FAQ database for the best solution. For example, "how to reset your password" or "how to deal with a specific error message" may be suggested. The search results list multiple possible solutions and present them to the user based on priority. The user reviews the suggested solutions and attempts to resolve the problem by following the instructions.

[1209] Optimizing responses based on emotions

[1210] The emotion recognition engine determines the user's emotional state. For example, if the emotion engine determines that the user is feeling frustrated, the system will display a more empathetic and considerate message. This can reduce user stress and improve the support experience.

[1211] Escalation and detailed support

[1212] If the suggested solution does not resolve the issue, the user can report this through the feedback form. The server receives the feedback and escalates it to a support agent as needed. The support agent will provide detailed support based on the request and the user's emotional state. For example, the agent may resolve the issue through remote access.

[1213] Gathering feedback and improving the system

[1214] After the problem is resolved, the user evaluates the quality of support and provides feedback. The server stores this feedback in a database and uses it as training material for the AI ​​module to solve future problems. The emotion engine is also continuously improved, enabling more accurate emotion recognition.

[1215] Examples of specific cases and prompt statements

[1216] Specific example

[1217] When a user enters and submits a support request such as "My PC freezes," the server receives the request and analyzes it as follows:

[1218] 1. The server extracts keywords such as "freeze" and "PC".

[1219] 2. The emotion engine detects "frustration" from the user's text.

[1220] 3. Search for the best solution (e.g., "How to fix computer freezing problems") and present it in order of priority.

[1221] Example of a prompt

[1222] "Please tell me what to do if the software installation fails."

[1223] "Please enter the password reset procedure."

[1224] "Please tell me how to fix the problem of my PC freezing."

[1225] In this way, the system efficiently processes user support requests and provides users with the best possible support experience.

[1226] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1227] Step 1: User access to the support center system and account creation

[1228] Specific actions

[1229] 1. Users access the support center system using information devices such as PCs, smartphones, and tablets.

[1230] Input: Access the support center website from your device's browser (enter the URL).

[1231] Output: The support center user interface is displayed.

[1232] 2. The user enters the necessary information (username, email address, password, etc.) into the form for creating a new account.

[1233] Input: Account information (username, email address, password)

[1234] Output: The input information will be displayed in the form.

[1235] 3. When the user presses the submit button, the server receives the entered information and saves it to the database. It also sends an authentication email to the user.

[1236] Input: Click the submit button

[1237] Output: Save information to the database and send an authentication email.

[1238] 4. The user authenticates their account by clicking the link in the verification email they received.

[1239] Input: Click the link in the verification email.

[1240] Output: Account becomes active

[1241] Step 2: Submit a support request

[1242] Specific actions

[1243] 1. The user logs into their account.

[1244] Input: Login information (email address, password)

[1245] Output: A support request form is displayed.

[1246] 2. The user enters details of the problem (e.g., software error details, screenshots, etc.) into the support request form.

[1247] Input: Support request details and required attachments

[1248] Output: The information entered in the form will be displayed.

[1249] 3. The user submits a request. The server receives the request, saves it to the database, and prepares it for analysis.

[1250] Input: Click the submit button

[1251] Output: Save request information to the database

[1252] Step 3: Request analysis and sentiment recognition

[1253] Specific actions

[1254] 1. The AI ​​module on the server analyzes the support requests it receives.

[1255] Input: Received request data

[1256] Output: Analysis results (keywords and phrases)

[1257] 2. Extract keywords and phrases from the request content using natural language processing techniques (e.g., using SpaCy or NLTK).

[1258] Input: Request text

[1259] Output: Extracted keywords and phrases

[1260] 3. The server's emotion engine determines the user's emotional state from their input text and voice data (e.g., using IBM Watson's Natural Language Understanding).

[1261] Input: Request text, audio data

[1262] Output: Emotional state (frustration, anger, sadness, etc.)

[1263] Step 4: Presenting a solution

[1264] Specific actions

[1265] 1. The server searches for the best solution from past support databases and FAQ databases.

[1266] Input: Keywords, phrases, emotional states

[1267] Output: List of possible solutions

[1268] 2. Organize search results in order of priority and present them to the user.

[1269] Input: List of possible solutions

[1270] Output: List of prioritized solutions

[1271] 3. A list of solutions will be displayed on the user's device.

[1272] Input: List of solutions

[1273] Output: List of solutions displayed on the terminal

[1274] Step 5: Escalation and provision of detailed support

[1275] Specific actions

[1276] 1. If the user's problem is not resolved by the suggested solution, they should report this through the feedback form.

[1277] Input: Feedback content

[1278] Output: Sending feedback

[1279] 2. The server receives the feedback and escalates it to a support agent as needed.

[1280] Input: Received feedback

[1281] Output: Escalation notification

[1282] 3. Support agents provide detailed support based on the request and the user's emotional state. For example, they may use remote access tools to resolve the issue.

[1283] Input: Escalation information, emotional state information

[1284] Output: Detailed support provided

[1285] Step 6: Gathering Feedback and Improving the System

[1286] Specific actions

[1287] 1. After the problem is resolved, the user evaluates the quality of support and provides feedback.

[1288] Input: Evaluation content, feedback

[1289] Output: Sending feedback

[1290] 2. The server saves the feedback to a database and uses it as training material for the AI ​​module to solve future problems.

[1291] Input: Feedback data

[1292] Output: Feedback stored in the database

[1293] Through the steps outlined above, the system can efficiently process user support requests and provide users with the best possible support experience.

[1294] (Application Example 2)

[1295] 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."

[1296] Traditional support systems have the means to receive support requests from users and offer appropriate solutions, but they often resulted in a poor user experience due to insufficient consideration of the user's emotional state. Furthermore, the uniform approach to solutions frequently caused dissatisfaction and stress, especially for emotionally unstable users. Additionally, the escalation process when a problem could not be resolved also lacked consideration for the user's feelings, leading to difficulties in smooth communication with support agents.

[1297] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for a user to input a support request using an information device, means for receiving and storing the support request, means for analyzing the content of the support request and searching for an appropriate solution, means for presenting the solution to the user, means for the analysis means to recognize the user's emotions and optimize the response, means for collecting feedback from the user, and means for escalating to a support agent as necessary based on the feedback. This enables optimal support that takes into account the user's emotional state, and particularly enables rapid and efficient problem solving in electronic payment services. In addition, since the escalation process can also be handled with an understanding of the user's emotional state, smoother support can be provided.

[1298] An "information device" refers to a terminal such as a computer or smartphone that a user uses to enter a support request.

[1299] A "support request" is information that details the problems or inquiries a user is facing.

[1300] The "means of receiving and storing" refer to a mechanism where the server receives a support request and stores its contents in a database.

[1301] "Analysis method" refers to a technique that uses natural language processing technology to understand the content of a support request, extract keywords and phrases, and identify the problem.

[1302] A "solution" refers to the methods or procedures for dealing with and resolving an identified problem.

[1303] "Means of presentation" refers to an interface for showing the user the solution obtained through analysis.

[1304] "Means of recognizing emotions and optimizing responses" refers to technologies that analyze a user's emotional state and provide the most appropriate response based on that analysis.

[1305] "Feedback" refers to evaluations and comments made by users regarding the solutions and support provided.

[1306] "Means of collection" refers to a system for receiving user feedback and sending and storing it on a server.

[1307] "Escalation" refers to the process of transferring a user's problem to an agent who can provide more advanced support if the problem cannot be resolved in the initial stages.

[1308] A "database" is a system for storing and managing information such as support requests, solutions, and user feedback.

[1309] "Natural language processing technology" is a technology that enables computers to understand and interpret human language and extract its meaning.

[1310] This invention relates to a system in which a user inputs a support request using an information device, a server receives and analyzes the request, and presents the optimal solution. Furthermore, by incorporating an emotion engine that recognizes the user's emotions and optimizes the response, personalized support becomes possible.

[1311] System Configuration Description

[1312] The system consists of the following main hardware and software components:

[1313] 1. Information equipment

[1314] This is a device used by users to enter support requests. These devices include computers, smartphones, and tablets.

[1315] 2. Server

[1316] This is the central computing unit responsible for receiving support requests, storing them in a database, and processing and presenting solutions. Specific examples of software used include Google Cloud Natural Language API and OpenAI GPT-4 for natural language processing engines, and IBM Watson Tone Analyzer and Microsoft Azure Cognitive Services for sentiment engines.

[1317] 3. Database

[1318] This is a system for accumulating support requests, past support data, FAQs, and user feedback. Specific examples include MySQL and PostgreSQL.

[1319] Processing flow

[1320] 1. Initial Setup

[1321] Users access the app using their smartphones and create a new account. They enter the required information, receive a verification email, and verify their account.

[1322] 2. Enter your support request

[1323] Users submit support requests through the app. These requests may include issues such as login problems or transaction errors with electronic payment services. The request includes error messages and details of the problem.

[1324] 3. Receiving and saving requests

[1325] The server receives the submitted support request and saves it to the database.

[1326] 4. Analysis and Sentiment Recognition

[1327] The natural language processing engine analyzes the request content and extracts keywords and important phrases. The emotion engine analyzes the user's emotional state (e.g., frustration, anger, sadness).

[1328] 5. Searching for and presenting solutions

[1329] The system searches for the best solution from support databases and FAQs, and then presents the message with a tone and content adjusted according to the user's emotional state.

[1330] 6. Feedback and Escalation

[1331] We collect user feedback and escalate it to support agents as needed. The agents understand the user's emotional state and take appropriate action.

[1332] Specific example

[1333] For example, if a user is unable to log in to their account with an electronic payment service, the support request will be processed as follows:

[1334] Example of a prompt

[1335] "Analysis of a support request when a user is unable to log in to their account on an electronic payment service. The user created the account two weeks ago. The error message is 'Incorrect password.' The user appears frustrated. The emotion engine presents empathetic messages and searches the past database for the best solution. If the user tries the suggested solutions and the problem persists, the issue is escalated to an agent."

[1336] Thus, the embodiments of the invention aim to provide prompt and accurate support in response to the diverse needs of users.

[1337] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1338] Step 1:

[1339] The user enters a support request using an information device (smartphone, PC, etc.). They enter details of the problem they are facing and attach supporting documents such as screenshots as needed. The entered information is then sent from the device to the server.

[1340] Input: User-submitted details of the problem, error message, and screenshot.

[1341] Output: Support Request Data

[1342] Step 2:

[1343] The server receives support requests and stores them in the database. The server ensures reliability and security.

[1344] Input: Support Request Data

[1345] Output: Support request records stored in the database

[1346] Step 3:

[1347] The server's natural language processing engine analyzes the content of the support request. It extracts keywords and important phrases from the request to identify the problem.

[1348] Input: Support Request Data

[1349] Output: Extracted keywords, identified issues

[1350] Step 4:

[1351] The server's emotion engine recognizes the user's emotions. It analyzes the request content and various input data (text, audio data, etc.) to evaluate the user's emotional state. For example, it determines whether the user is feeling frustrated.

[1352] Input: Support request data, text data, audio data

[1353] Output: User's emotional state (e.g., frustration, anger, sadness)

[1354] Step 5:

[1355] The server searches the database for the best solution. Based on past support and FAQ databases, it selects and prioritizes the most suitable solution for the user. It also adjusts the tone and content of messages according to the user's emotional state.

[1356] Input: Identified problem, user's emotional state

[1357] Output: Optimal solution, adjusted message

[1358] Step 6:

[1359] The server presents a solution to the user. The terminal displays the optimal solution and a tailored message.

[1360] Input: Optimal solution, tailored message

[1361] Output: Solution and message displayed on the user terminal

[1362] Step 7:

[1363] The user attempts to solve the problem according to the suggested solution and provides feedback on the results.

[1364] Input: Solution trial results, feedback data

[1365] Output: User feedback

[1366] Step 8:

[1367] The server receives feedback from the user and stores it in the database. The server analyzes the feedback and determines whether the issue was successfully resolved.

[1368] Input: Feedback data

[1369] Output: Feedback records stored in the database, resolution result

[1370] Step 9:

[1371] If the problem persists, the server will escalate it to a support agent based on the feedback. The agent will then take steps to provide detailed support based on the request and the user's emotional state.

[1372] Input: Feedback data, user's emotional state

[1373] Output: Escalation data to the agent

[1374] In this way, each step works together to form a system that supports the rapid and appropriate resolution of user problems.

[1375] 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.

[1376] 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.

[1377] 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.

[1378] [Fourth Embodiment]

[1379] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1380] 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.

[1381] 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).

[1382] 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.

[1383] 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.

[1384] 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).

[1385] 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.

[1386] 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.

[1387] 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.

[1388] 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.

[1389] 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.

[1390] 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.

[1391] 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".

[1392] This invention relates to a system in which a user enters a support request using an information device, a server receives and analyzes the request, presents a solution, and escalates it to a support agent as necessary.

[1393] Users access the support center system using information devices such as PCs, smartphones, or tablets. Through the provided user interface, users create a new account and enter the required information. Once registration is complete, the server saves the entered information to a database and sends a verification email to the user. Users verify their account by clicking the link in the verification email.

[1394] When a user logs into the system, a support request form is displayed, and the user enters details of the problem, screenshots, etc. For example, they may enter information about software error messages or system malfunctions. Once the user submits the request, the server receives it and stores it in the database.

[1395] Next, an AI module on the server analyzes the content of the support request. Specifically, it uses natural language processing technology to understand the content of the request and extract keywords and important phrases. Based on this analysis, the server searches its past support database and FAQ database for the best solution. For example, it searches for information such as "how to reset a password" or "how to deal with a specific error message."

[1396] The search results list multiple possible solutions, presented to the user based on priority. The user reviews the suggested solutions on their device and attempts to resolve the problem by following the instructions. In most cases, the problem is resolved through this process.

[1397] If the suggested solution does not resolve the issue, the user can report this through the feedback form. The server will receive the feedback and, if necessary, escalate it to a support agent. Once escalated, the agent will take steps to provide detailed support based on the request and the user's feedback.

[1398] For example, an agent might communicate directly with the user and resolve the issue through remote access.

[1399] After the problem is resolved, the user evaluates the quality of support and provides feedback. The server stores this feedback in a database and uses it as training material for the AI ​​module to solve future problems.

[1400] In this way, the system provides fast and efficient support by receiving, analyzing, and suggesting solutions for user support requests. Furthermore, the escalation function allows support agents to intervene in complex issues, thereby improving the quality of support.

[1401] The following describes the processing flow.

[1402] Step 1:

[1403] Users access the support center system using information devices (e.g., PCs, smartphones, tablets). Through the provided user interface, users register an account and enter necessary information such as their name, email address, and password.

[1404] Step 2:

[1405] The server receives the registration information sent from the terminal and stores it in the database. The server then sends an authentication email to the entered email address, requesting the user to confirm.

[1406] Step 3:

[1407] The user clicks the link in the verification email they received to verify their account. This activates the user's account.

[1408] Step 4:

[1409] The user logs into the system. After logging in, a support request form is displayed. The user enters details of the problem, screenshots, error messages, etc.

[1410] Step 5:

[1411] The server receives the support request sent from the terminal and stores it in the database. The server then passes the request details to the AI ​​module.

[1412] Step 6:

[1413] The server's AI module analyzes the content of the support request. It uses natural language processing techniques to extract keywords and important phrases from the request.

[1414] Step 7:

[1415] The server searches past support databases and FAQ databases based on the extracted keywords. It then lists multiple optimal solutions and prioritizes them.

[1416] Step 8:

[1417] The server presents the user with a list of solutions in order of priority. The user reviews the solutions presented on their terminal and attempts to resolve the problem by following the instructions.

[1418] Step 9:

[1419] If a user is unable to resolve their issue using the provided solution, they should report this through the feedback form. The server will then receive the feedback from the device.

[1420] Step 10:

[1421] The server will escalate the issue to a support agent based on the feedback received, if necessary. The request and feedback will be sent to the agent along with an escalation notification.

[1422] Step 11:

[1423] A support agent receives the notification and reviews the request and feedback. The agent contacts the user and assists in resolving the issue through remote access and detailed instructions.

[1424] Step 12:

[1425] After the problem is resolved, the user evaluates the quality of support and provides feedback. The server receives the feedback from the device and stores it in a database.

[1426] Step 13:

[1427] The server analyzes the feedback it collects and uses it as training material for the AI ​​module, thereby improving its future problem-solving capabilities.

[1428] (Example 1)

[1429] 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".

[1430] Traditional support systems struggled to efficiently analyze user-submitted support requests and promptly provide appropriate solutions. In particular, the diversity and complexity of requests made it difficult to find solutions quickly, leading to decreased user satisfaction. Furthermore, the escalation process for unresolved issues was inefficient, resulting in an increase in manual intervention by support agents.

[1431] 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.

[1432] In this invention, the server includes means for a user to input a support request using an information device, means for receiving and storing the support request, means for using a generative AI model to analyze the content of the support request, means for the generative AI model to analyze the content of the support request using natural language processing technology and extract keywords and important phrases, means for searching for solutions from past support databases and FAQ databases, means for presenting the solutions to the user, means for collecting feedback from the user, and means for escalating to a support agent as necessary based on the feedback. This makes it possible to quickly and accurately analyze support requests and present appropriate solutions to users. Furthermore, if the problem cannot be resolved, escalation is carried out efficiently, enabling a rapid response by support agents.

[1433] "Information device" refers to electronic devices such as computers, smartphones, and tablets that users use to enter support requests.

[1434] A "support request" is a request submitted by a user to the system, detailing a problem and seeking assistance.

[1435] "Means" refers to a method, technique, or apparatus used to perform a particular function or task.

[1436] A "generative AI model" refers to an algorithm or model trained to perform a specific task using artificial intelligence.

[1437] "Natural language processing technology" refers to the technology that enables computers to understand, analyze, and generate human language.

[1438] "Keywords and important phrases" refer to words and sentences that are particularly important when analyzing the content of a support request.

[1439] The "past support database" is a database that stores support requests and response histories recorded to date.

[1440] An "FAQ database" is a database that compiles frequently asked questions and their answers.

[1441] "Feedback" refers to the opinions and results that users provide regarding the quality of support and the solutions provided.

[1442] "Escalation" is the process of transferring a problem that could not be resolved in the initial support process to a higher-level support agent.

[1443] A "support agent" is a specialized operator or technician who directly handles user support requests.

[1444] This invention is a system in which a user inputs a support request using an information device, a server receives and analyzes the request, presents a solution, and escalates it to a support agent as necessary. Specific embodiments are described below.

[1445] Users access the support center system using information devices such as PCs, smartphones, and tablets. First, users create a new account through the provided user interface and enter the necessary information (e.g., username, email address, password). The server stores this information in its database and sends an authentication email to the user for verification. This authentication email is sent using an SMTP server. Users authenticate their account by clicking a link in the authentication email. Clicking this link updates the server's account status, marking it as authenticated.

[1446] When a user logs into the system, a support request form is displayed. The user enters details of the problem and screenshots into this form. For example, a user might enter "The software displays an error message and does not work." Once the user submits the request, the server receives it and saves it to the database.

[1447] Next, a generative AI model on the server (for example, a natural language processing model using TensorFlow) analyzes the content of the support request. The server uses this generative AI model to understand the content of the request and extract keywords and important phrases. Specifically, it analyzes the user's input using natural language processing techniques and extracts important information.

[1448] Based on the analysis results, the server searches its past support database and FAQ database (e.g., Elasticsearch) for the best solution. For example, for "error code 1234," it might search for solutions such as "how to reinstall the app" or "how to clear the cache." Multiple solutions are listed and presented to the user in order of priority. The user reviews the presented solutions and attempts to resolve the problem by following the instructions.

[1449] If the suggested solution does not resolve the issue, the user can report this through the feedback form. The server receives the feedback and, if necessary, escalates it to a support agent. Once escalated, the support agent provides detailed support based on the request and the user's feedback. For example, the agent may communicate directly with the user and resolve the issue through remote access.

[1450] Finally, after the problem is resolved, the user evaluates the quality of support and provides feedback. The server stores this feedback in a database and uses it as training material for a generative AI model to solve future problems.

[1451] As a concrete example, consider a case where a user enters a problem, such as "An error message appears when I open the app." In this case, the user enters "When I open the app, I get error code 1234 and it doesn't work" into the support request form. The server's generated AI model analyzes "error code 1234" and searches its past support database and FAQ database for solutions to this error. The server then prioritizes and presents these solutions to the user.

[1452] An example of a prompt statement you can enter is as follows:

[1453] "Users should log in to their account and submit a support request using the following prompt: 'When I open the app, I get error code 1234 and it doesn't work. Please tell me how to fix it.'"

[1454] This system enables the rapid and accurate analysis of user support requests, leading to efficient problem-solving. Furthermore, detailed support from support agents is provided as needed, improving overall support quality.

[1455] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1456] Step 1:

[1457] Account creation and verification

[1458] Users access the support center system using information devices such as PCs, smartphones, and tablets.

[1459] Input: Account information such as username, email address, and password.

[1460] The server receives information entered through the provided user interface.

[1461] The server saves the entered account information to the database.

[1462] The server sends an authentication email to the user for verification. The authentication email is sent using an SMTP server.

[1463] Output: An authentication email is sent to the user.

[1464] The user authenticates their account by clicking the link in the authentication email. By clicking the link, the server updates the user's account status and marks it as authenticated.

[1465] Step 2:

[1466] Login and support request submission

[1467] Input: User's authenticated account information (username, password).

[1468] The user logs into the system.

[1469] The server receives the login request and verifies the authentication credentials.

[1470] Output: Login successful, and the user is displayed with a support request form.

[1471] The user enters details of the problem and screenshots into the support request form.

[1472] Input: Details of the problem (e.g., software error message) and attachments (e.g., screenshots).

[1473] When a user submits a request, the server receives the request and stores it in the database.

[1474] Output: Saved support request data.

[1475] Step 3:

[1476] Support request analysis

[1477] Input: Support request data.

[1478] A generative AI model on the server (for example, a natural language processing model using TensorFlow) analyzes the content of the support request.

[1479] The server uses a generative AI model to understand the content of the request and extract keywords and important phrases.

[1480] Data processing: Use natural language processing techniques to extract keywords and important phrases from the text of support requests.

[1481] Output: Extracted keywords and important phrases.

[1482] Step 4:

[1483] Searching for and presenting solutions

[1484] Input: Extracted keywords and important phrases.

[1485] The server searches its past support and FAQ databases for the best solution. For example, it might use Elasticsearch to search the database.

[1486] Data Calculation: Generate search queries and search the database.

[1487] Output: A list of multiple solutions.

[1488] The server prioritizes the search results and presents solutions to the user.

[1489] Output: A list of solutions presented to the user.

[1490] Step 5:

[1491] Attempting to resolve the user issue

[1492] The user reviews the suggested solutions and attempts to resolve the problem by following the instructions.

[1493] Input: User feedback (results of attempted solutions).

[1494] Output: User feedback on whether the problem was resolved.

[1495] Step 6:

[1496] Feedback and escalation

[1497] Input: User feedback (if the problem persists).

[1498] If a user is unable to resolve their issue using the suggested solution, they should report this through the feedback form.

[1499] The server receives feedback and escalates it to a support agent as needed.

[1500] Output: Request escalated to a support agent.

[1501] Step 7:

[1502] Intervention by a support agent

[1503] Input: Escalated request.

[1504] Support agents provide detailed support based on the request and user feedback.

[1505] Specific operation: In some cases, the agent communicates directly with the user and resolves issues through remote access.

[1506] Output: Detailed support for problem resolution.

[1507] Step 8:

[1508] Supportive feedback and learning

[1509] Input: User feedback after problem resolution (evaluation of support quality).

[1510] Users rate the quality of support and provide feedback.

[1511] The server stores this feedback in a database and uses it as training material for generative AI models to solve future problems.

[1512] Output: Saved feedback data and an enhanced AI model.

[1513] In this way, the system can quickly and accurately analyze support requests and resolve problems efficiently.

[1514] (Application Example 1)

[1515] 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".

[1516] Traditional support systems have presented challenges in quickly finding appropriate solutions when users encounter problems with ad performance or settings. Issues related to ad management and performance tracking are particularly complex and often beyond the capabilities of general FAQs and support databases. Furthermore, when escalation is necessary, it can be difficult to transfer the issue to a support agent at the appropriate time, leading to delays in problem resolution.

[1517] 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.

[1518] In this invention, the server includes means for a user to input a support request using an information device, means for receiving and storing the support request, means for analyzing the content of the support request and searching for an appropriate solution, means for presenting the solution to the user, means for collecting feedback from the user, means for escalating to a support agent as necessary based on the feedback, means for resolving issues related to advertising performance and settings, means for presenting an optimal solution regarding advertising performance using a generative AI model, and means for the solution to automatically determine the requirements for escalation. This enables quick and appropriate resolution of advertising-related issues, thereby improving user satisfaction.

[1519] "Information device" refers to computer systems and devices used by users to enter support requests, and includes PCs, smartphones, tablets, etc.

[1520] A "support request" refers to inquiry information that includes details of the problem or question the user is facing.

[1521] A "server" refers to a computer system that receives and analyzes support requests and provides appropriate solutions.

[1522] "Analysis tools" refer to the part of a system that has the functionality to understand the content of a support request and derive an appropriate solution.

[1523] "Natural language processing technology" refers to techniques that enable computers to understand and analyze human language, and includes keyword extraction and semantic analysis of text.

[1524] "Feedback" refers to the evaluations and comments that users provide regarding the solutions presented.

[1525] "Escalation" refers to the process by which a user's problem is handed over to a support agent when they are unable to resolve it themselves.

[1526] "Ad performance" refers to metrics that indicate how effectively an ad is working, and includes metrics such as click-through rate and conversion rate.

[1527] A "generative AI model" refers to an artificial intelligence model that has been trained using machine learning or deep learning to perform a specific task.

[1528] "Providing a solution" refers to the process of showing the user the best possible answer or procedure for their support request.

[1529] This invention relates to a system in which a user enters a support request using an information device, a server receives and analyzes the request, presents a solution, and escalates it to a support agent as necessary.

[1530] Users access the support system using information devices such as PCs, smartphones, and tablets. Through the provided interface, users first create a new account and enter the required information. Once registration is complete, the server saves the entered information to its database and sends a verification email to the user. Users then verify their account by clicking the link in the verification email.

[1531] When a user logs into the system, a support request form is displayed, and the user enters details of the problem, screenshots, etc. The server receives the request and saves it to the database.

[1532] Next, an AI module on the server analyzes the support request. Specifically, it uses natural language processing technology to understand the content of the request and extract keywords and important phrases. Based on this analysis, the server searches its past support database and FAQ database for the best solution.

[1533] The search results list multiple possible solutions, presented to the user based on priority. The user reviews the suggested solutions on their device and attempts to resolve the problem by following the instructions. In most cases, the problem is resolved through this process.

[1534] For issues related to ad performance and settings, a generative AI model is used to suggest the optimal solution. The server utilizes the AI ​​model based on the prompt text entered by the user to find the appropriate solution. For example, prompt texts such as "How can I track ad performance?" or "I want to know how to reset my ad password?" might be entered.

[1535] If the suggested solution does not resolve the issue, the user can report this through the feedback form. The server will receive the feedback and, if necessary, escalate it to a support agent. Once escalated, the agent will take steps to provide detailed support based on the request and the user's feedback.

[1536] After the problem is resolved, the user evaluates the quality of support and provides feedback. The server stores this feedback in a database and uses it as training material for the AI ​​module to solve future problems.

[1537] The hardware and software used will consist of a server environment using Flask, the Hugging Face Transformers library and a pre-trained model (distilbert-base-cased-distilled-squad), and a simple in-memory database (using a Python dictionary).

[1538] In this way, a system is created that provides fast and efficient support, and can easily address issues, especially those related to ad performance and settings.

[1539] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1540] Step 1:

[1541] The user uses an information device to access the support system and create a new account. The user enters the required information and submits it.

[1542] Input: User registration information (e.g., email address, name)

[1543] Output: User information stored on the server, confirmation email sent.

[1544] Specific operation: The user enters the required information into a web form from an information device such as a PC or smartphone and clicks the "Submit" button. The server saves the received information to a database, generates a confirmation email, and sends it to the user.

[1545] Step 2:

[1546] The user clicks the link in the verification email to verify their account. The server receives the verification request and updates the user's account to verified.

[1547] Input: Click the link in the verification email.

[1548] Output: Confirmed account information, authentication complete message

[1549] Specific operation: The user clicks the link in the received authentication email, the server receives the request and updates the user's account information, and the server displays a confirmation message.

[1550] Step 3:

[1551] The user logs into the system, enters details of the problem into the support request form, and submits it. The server receives the request and saves it to the database.

[1552] Input: Support request information (e.g., problem details, screenshots)

[1553] Output: Support requests stored in the database

[1554] Specific operation: After logging in, the user enters details of the problem into the support request form that appears and clicks the "Submit" button. The server saves the received information to the database.

[1555] Step 4:

[1556] An AI module on the server analyzes support requests and extracts keywords and phrases using natural language processing techniques.

[1557] Input: Support Request Information

[1558] Output: Extracted keywords and phrases

[1559] Specific operation: The server sends the received support request to the AI ​​module, which then uses natural language processing techniques to analyze the text. It extracts important keywords and phrases.

[1560] Step 5:

[1561] The server searches for the best solution based on keywords extracted from past support databases and FAQ databases.

[1562] Input: Extracted keywords or phrases

[1563] Output: List of optimal solutions

[1564] Specific operation: The server searches the support database and FAQ database based on the extracted keywords and lists relevant solutions.

[1565] Step 6:

[1566] The server prioritizes and presents the user with the optimal solution.

[1567] Input: List of optimal solutions

[1568] Output: Solutions presented to the user

[1569] Specific operation: The server ranks the listed solutions based on priority and displays them on the user's terminal.

[1570] Step 7:

[1571] The user reviews the suggested solutions and attempts to resolve the problem. The user reports the results through a feedback form.

[1572] Input: User feedback

[1573] Output: Feedback information stored on the server

[1574] Specific operation: The user tries the displayed solution, enters the results and comments in the feedback form, and submits it. The server saves the feedback information to the database.

[1575] Step 8:

[1576] The server will escalate the issue to a support agent as needed based on the feedback. The support agent will review the details of the problem and provide additional support.

[1577] Input: User feedback

[1578] Output: Escalated support request, additional support

[1579] Specific operation: The server analyzes the feedback and, if it cannot resolve the issue, escalates it to a support agent. The agent reviews the request and feedback and provides support as needed.

[1580] Example prompt:

[1581] "How can I track the performance of my ads?"

[1582] "I want to know the password reset procedure for advertisements."

[1583] 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.

[1584] This invention relates to a system in which a user enters a support request using an information device, a server receives, analyzes, and proposes a solution to the request, and escalates it to a support agent as needed. Furthermore, the invention incorporates an emotion engine that recognizes the user's emotions and optimizes the response accordingly.

[1585] Users access the support center system using information devices such as PCs, smartphones, or tablets. Through the provided user interface, users create a new account and enter the required information. Once registration is complete, the server saves the entered information to a database and sends a verification email to the user. Users verify their account by clicking the link in the verification email.

[1586] When a user logs into the system, a support request form is displayed, and the user enters details of the problem, screenshots, etc. For example, they may enter information about software error messages or system malfunctions. Once the user submits the request, the server receives it and stores it in the database.

[1587] Next, an AI module on the server analyzes the content of the support request. Specifically, it uses natural language processing technology to understand the request and extract keywords and important phrases. Furthermore, an emotion engine analyzes the user's emotions and determines the user's emotional state (e.g., frustration, anger, sadness, etc.) from the request content, input text, and voice data. Based on this analysis, the server searches its past support database and FAQ database for the best solution. For example, it searches for information such as "how to reset a password" or "how to deal with a specific error message."

[1588] The search results list multiple possible solutions, presented to the user based on priority. The user reviews the suggested solutions on their device and attempts to resolve the problem by following the instructions. In most cases, the problem is resolved through this process. Furthermore, the tone and content of the messages presented are adjusted according to the user's emotional state. For example, if the emotion recognition engine determines that the user is feeling frustrated, the system will display a more empathetic and considerate message.

[1589] If the suggested solution does not resolve the issue, the user reports this through a feedback form. The server receives the feedback and, if necessary, escalates it to a support agent. Once escalated, the agent takes steps to provide detailed support based on the request, the user's feedback, and the sentiment engine's emotional state information. For example, the agent may communicate directly with the user and resolve the issue through remote access. In this case, the agent can understand the user's emotional state and select the appropriate course of action.

[1590] After the problem is resolved, the user evaluates the quality of support and provides feedback. The server stores this feedback in a database and uses it as training material for the AI ​​module to solve future problems. The emotion engine is also continuously improved, enabling more accurate emotion recognition.

[1591] In this way, the system provides fast and efficient support by receiving, analyzing, and suggesting solutions for user support requests. Furthermore, the emotion engine enables personalized responses based on the user's emotional state, and the escalation function allows support agents to intervene in complex issues, thereby improving the quality of support.

[1592] The following describes the processing flow.

[1593] Step 1:

[1594] Users access the support center system using information devices (e.g., PCs, smartphones, tablets). Through the provided user interface, users register an account and enter necessary information such as their name, email address, and password.

[1595] Step 2:

[1596] The server receives the registration information sent from the terminal and stores it in the database. The server then sends an authentication email to the entered email address, requesting the user to confirm.

[1597] Step 3:

[1598] The user clicks the link in the verification email they received to verify their account. This activates the user's account.

[1599] Step 4:

[1600] The user logs into the system. After logging in, a support request form is displayed, and the user enters details of the problem, screenshots, error messages, etc.

[1601] Step 5:

[1602] The server receives the support request sent from the terminal and stores it in the database. The server then passes the request details to the AI ​​module.

[1603] Step 6:

[1604] The server's AI module analyzes the content of the support request. It uses natural language processing technology to understand the request and extract keywords and important phrases.

[1605] Step 7:

[1606] The server's emotion engine analyzes the user's emotional state from the request content, input text, and, if necessary, audio data. For example, it determines whether the user is experiencing emotions such as frustration, anger, or sadness based on keywords and context.

[1607] Step 8:

[1608] The server searches past support and FAQ databases based on extracted keywords and user sentiment information. The server then lists the best solutions and prioritizes them.

[1609] Step 9:

[1610] When the server presents a list of solutions to the user, it adjusts the tone and content of the message according to the user's emotional state. For example, if the user is feeling frustrated, it will use empathetic and polite language.

[1611] Step 10:

[1612] The user checks the suggested solutions on their device and attempts to resolve the problem by following the instructions. In most cases, the problem is resolved through this process.

[1613] Step 11:

[1614] If a user is unable to resolve their issue using the provided solution, they should report this through the feedback form. The server will then receive the feedback from the device.

[1615] Step 12:

[1616] Based on the feedback, the server escalates the issue to a support agent as needed. Along with the escalation notification, the server sends the request details and the user's emotional state information to the agent.

[1617] Step 13:

[1618] A support agent receives the notification and reviews the request, feedback, and emotional state information from the emotion engine. The agent then contacts the user to resolve the issue through remote access and detailed instructions.

[1619] Step 14:

[1620] After the problem is resolved, the user evaluates the quality of support and provides feedback. The server receives the feedback from the device and stores it in a database.

[1621] Step 15:

[1622] The server analyzes the collected feedback and uses it as training material for the AI ​​module and emotion engine. This will improve future problem-solving and emotion recognition capabilities.

[1623] (Example 2)

[1624] 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".

[1625] Traditional support systems often failed to consider the user's emotional state, resulting in inappropriate responses and decreased user satisfaction. Furthermore, the solutions provided frequently did not meet user needs, leading to frequent escalations and increased workload for support agents.

[1626] 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.

[1627] In this invention, the server includes means for a user to input a support request using a device, means for receiving and storing the support request, means for analyzing the content of the support request and searching for an appropriate solution, means for analyzing the user's emotional state, means for adjusting the presentation of the solution based on the emotional state, means for presenting the solution to the user, means for collecting feedback from the user, and means for escalating to a support agent as necessary based on the feedback. This enables individualized responses that take into account the user's emotional state, and by providing an appropriate solution, it is possible to reduce the frequency of escalations to support agents and improve overall user satisfaction.

[1628] A "user" refers to a person who uses the system to submit a support request.

[1629] "Device" refers to information devices such as PCs, smartphones, and tablets.

[1630] A "support request" refers to information that a user submits to the system, such as a problem or question.

[1631] "Means" refers to technical methods or devices used to achieve a specific function within a system.

[1632] A "server" refers to a central computer that receives and analyzes user requests and manages the entire system.

[1633] "Natural language processing technology" refers to the technology that enables computers to understand and analyze human natural language.

[1634] "Keywords" refer to important words or phrases that indicate the content of a support request.

[1635] "Emotional state" refers to the feelings and sensations a user experiences when making a support request, such as frustration or joy.

[1636] "Escalation" refers to the process where, if an initial automated solution fails to resolve the issue, a human, such as a support agent, provides additional support.

[1637] "Feedback" refers to the opinions and evaluations that users provide regarding support services.

[1638] A "support agent" refers to a specialist staff member who directly addresses users' problems.

[1639] "Solution" refers to the appropriate response or procedure for a user's support request.

[1640] This invention relates to a system in which a user enters a support request using a device, a server receives and analyzes the request, proposes a solution, and escalates it to a support agent as needed. Furthermore, by incorporating an emotion engine, it provides a mechanism to recognize the user's emotional state and optimize the response.

[1641] Hardware and software

[1642] hardware

[1643] This system consists of the following information devices:

[1644] User devices (PCs, smartphones, tablets, etc.)

[1645] Server System

[1646] software

[1647] The software used includes the following specific technologies:

[1648] Natural Language Processing (NLTK, SpaCy)

[1649] Sentiment analysis tool (IBM Watson's Natural Language Understanding)

[1650] Database management systems (MySQL, MongoDB, Firebase, Elasticsearch)

[1651] Remote access tools (TeamViewer, AnyDesk)

[1652] Submitting and receiving support requests

[1653] Users access the support center system using information devices such as PCs, smartphones, and tablets. After accessing the system, users create a new account and enter the required information. At this time, the server saves the entered information to a database and sends an authentication email to the user for verification. Once the user clicks the link in the authentication email to authenticate their account, they will be able to log in.

[1654] Next, after logging in, the user enters details of the problem into a support request form. For example, they might write, "An error message appears during software installation," and attach a screenshot. Once the user submits the request, the server receives it and stores it in the database.

[1655] Request analysis and sentiment recognition

[1656] An AI module on the server analyzes the content of the support request. Specifically, it uses natural language processing techniques to extract keywords and important phrases from the request. Furthermore, the server's emotion engine determines the user's emotional state from the input text and voice data. For example, it may detect "frustration," "anger," or "sadness."

[1657] Providing solutions

[1658] Based on the analysis results, the server searches its past support database and FAQ database for the best solution. For example, "how to reset your password" or "how to deal with a specific error message" may be suggested. The search results list multiple possible solutions and present them to the user based on priority. The user reviews the suggested solutions and attempts to resolve the problem by following the instructions.

[1659] Optimizing responses based on emotions

[1660] The emotion recognition engine determines the user's emotional state. For example, if the emotion engine determines that the user is feeling frustrated, the system will display a more empathetic and considerate message. This can reduce user stress and improve the support experience.

[1661] Escalation and detailed support

[1662] If the suggested solution does not resolve the issue, the user can report this through the feedback form. The server receives the feedback and escalates it to a support agent as needed. The support agent will provide detailed support based on the request and the user's emotional state. For example, the agent may resolve the issue through remote access.

[1663] Gathering feedback and improving the system

[1664] After the problem is resolved, the user evaluates the quality of support and provides feedback. The server stores this feedback in a database and uses it as training material for the AI ​​module to solve future problems. The emotion engine is also continuously improved, enabling more accurate emotion recognition.

[1665] Examples of specific cases and prompt statements

[1666] Specific example

[1667] When a user enters and submits a support request such as "My PC freezes," the server receives the request and analyzes it as follows:

[1668] 1. The server extracts keywords such as "freeze" and "PC".

[1669] 2. The emotion engine detects "frustration" from the user's text.

[1670] 3. Search for the best solution (e.g., "How to fix computer freezing problems") and present it in order of priority.

[1671] Example of a prompt

[1672] "Please tell me what to do if the software installation fails."

[1673] "Please enter the password reset procedure."

[1674] "Please tell me how to fix the problem of my PC freezing."

[1675] In this way, the system efficiently processes user support requests and provides users with the best possible support experience.

[1676] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1677] Step 1: User access to the support center system and account creation

[1678] Specific actions

[1679] 1. Users access the support center system using information devices such as PCs, smartphones, and tablets.

[1680] Input: Access the support center website from your device's browser (enter the URL).

[1681] Output: The support center user interface is displayed.

[1682] 2. The user enters the necessary information (username, email address, password, etc.) into the form for creating a new account.

[1683] Input: Account information (username, email address, password)

[1684] Output: The input information will be displayed in the form.

[1685] 3. When the user presses the submit button, the server receives the entered information and saves it to the database. It also sends an authentication email to the user.

[1686] Input: Click the submit button

[1687] Output: Save information to the database and send an authentication email.

[1688] 4. The user authenticates their account by clicking the link in the verification email they received.

[1689] Input: Click the link in the verification email.

[1690] Output: Account becomes active

[1691] Step 2: Submit a support request

[1692] Specific actions

[1693] 1. The user logs into their account.

[1694] Input: Login information (email address, password)

[1695] Output: A support request form is displayed.

[1696] 2. The user enters details of the problem (e.g., software error details, screenshots, etc.) into the support request form.

[1697] Input: Support request details and required attachments

[1698] Output: The information entered in the form will be displayed.

[1699] 3. The user submits a request. The server receives the request, saves it to the database, and prepares it for analysis.

[1700] Input: Click the submit button

[1701] Output: Save request information to the database

[1702] Step 3: Request analysis and sentiment recognition

[1703] Specific actions

[1704] 1. The AI ​​module on the server analyzes the support requests it receives.

[1705] Input: Received request data

[1706] Output: Analysis results (keywords and phrases)

[1707] 2. Extract keywords and phrases from the request content using natural language processing techniques (e.g., using SpaCy or NLTK).

[1708] Input: Request text

[1709] Output: Extracted keywords and phrases

[1710] 3. The server's emotion engine determines the user's emotional state from their input text and voice data (e.g., using IBM Watson's Natural Language Understanding).

[1711] Input: Request text, audio data

[1712] Output: Emotional state (frustration, anger, sadness, etc.)

[1713] Step 4: Presenting a solution

[1714] Specific actions

[1715] 1. The server searches for the best solution from past support databases and FAQ databases.

[1716] Input: Keywords, phrases, emotional states

[1717] Output: List of possible solutions

[1718] 2. Organize search results in order of priority and present them to the user.

[1719] Input: List of possible solutions

[1720] Output: List of prioritized solutions

[1721] 3. A list of solutions will be displayed on the user's device.

[1722] Input: List of solutions

[1723] Output: List of solutions displayed on the terminal

[1724] Step 5: Escalation and provision of detailed support

[1725] Specific actions

[1726] 1. If the user's problem is not resolved by the suggested solution, they should report this through the feedback form.

[1727] Input: Feedback content

[1728] Output: Sending feedback

[1729] 2. The server receives the feedback and escalates it to a support agent as needed.

[1730] Input: Received feedback

[1731] Output: Escalation notification

[1732] 3. Support agents provide detailed support based on the request and the user's emotional state. For example, they may use remote access tools to resolve the issue.

[1733] Input: Escalation information, emotional state information

[1734] Output: Detailed support provided

[1735] Step 6: Gathering Feedback and Improving the System

[1736] Specific actions

[1737] 1. After the problem is resolved, the user evaluates the quality of support and provides feedback.

[1738] Input: Evaluation content, feedback

[1739] Output: Sending feedback

[1740] 2. The server saves the feedback to a database and uses it as training material for the AI ​​module to solve future problems.

[1741] Input: Feedback data

[1742] Output: Feedback stored in the database

[1743] Through the steps outlined above, the system can efficiently process user support requests and provide users with the best possible support experience.

[1744] (Application Example 2)

[1745] 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".

[1746] Traditional support systems have the means to receive support requests from users and offer appropriate solutions, but they often resulted in a poor user experience due to insufficient consideration of the user's emotional state. Furthermore, the uniform approach to solutions frequently caused dissatisfaction and stress, especially for emotionally unstable users. Additionally, the escalation process when a problem could not be resolved also lacked consideration for the user's feelings, leading to difficulties in smooth communication with support agents.

[1747] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for a user to input a support request using an information device, means for receiving and storing the support request, means for analyzing the content of the support request and searching for an appropriate solution, means for presenting the solution to the user, means for the analysis means to recognize the user's emotions and optimize the response, means for collecting feedback from the user, and means for escalating to a support agent as necessary based on the feedback. This enables optimal support that takes into account the user's emotional state, and particularly enables rapid and efficient problem solving in electronic payment services. In addition, since the escalation process can also be handled with an understanding of the user's emotional state, smoother support can be provided.

[1748] An "information device" refers to a terminal such as a computer or smartphone that a user uses to enter a support request.

[1749] A "support request" is information that details the problems or inquiries a user is facing.

[1750] The "means of receiving and storing" refer to a mechanism where the server receives a support request and stores its contents in a database.

[1751] "Analysis method" refers to a technique that uses natural language processing technology to understand the content of a support request, extract keywords and phrases, and identify the problem.

[1752] A "solution" refers to the methods or procedures for dealing with and resolving an identified problem.

[1753] "Means of presentation" refers to an interface for showing the user the solution obtained through analysis.

[1754] "Means of recognizing emotions and optimizing responses" refers to technologies that analyze a user's emotional state and provide the most appropriate response based on that analysis.

[1755] "Feedback" refers to evaluations and comments made by users regarding the solutions and support provided.

[1756] "Means of collection" refers to a system for receiving user feedback and sending and storing it on a server.

[1757] "Escalation" refers to the process of transferring a user's problem to an agent who can provide more advanced support if the problem cannot be resolved in the initial stages.

[1758] A "database" is a system for storing and managing information such as support requests, solutions, and user feedback.

[1759] "Natural language processing technology" is a technology that enables computers to understand and interpret human language and extract its meaning.

[1760] This invention relates to a system in which a user inputs a support request using an information device, a server receives and analyzes the request, and presents the optimal solution. Furthermore, by incorporating an emotion engine that recognizes the user's emotions and optimizes the response, personalized support becomes possible.

[1761] System Configuration Description

[1762] The system consists of the following main hardware and software components:

[1763] 1. Information equipment

[1764] This is a device used by users to enter support requests. These devices include computers, smartphones, and tablets.

[1765] 2. Server

[1766] This is the central computing unit responsible for receiving support requests, storing them in a database, and processing and presenting solutions. Specific examples of software used include Google Cloud Natural Language API and OpenAI GPT-4 for natural language processing engines, and IBM Watson Tone Analyzer and Microsoft Azure Cognitive Services for sentiment engines.

[1767] 3. Database

[1768] This is a system for accumulating support requests, past support data, FAQs, and user feedback. Specific examples include MySQL and PostgreSQL.

[1769] Processing flow

[1770] 1. Initial Setup

[1771] Users access the app using their smartphones and create a new account. They enter the required information, receive a verification email, and verify their account.

[1772] 2. Enter your support request

[1773] Users submit support requests through the app. These requests may include issues such as login problems or transaction errors with electronic payment services. The request includes error messages and details of the problem.

[1774] 3. Receiving and saving requests

[1775] The server receives the submitted support request and saves it to the database.

[1776] 4. Analysis and Sentiment Recognition

[1777] The natural language processing engine analyzes the request content and extracts keywords and important phrases. The emotion engine analyzes the user's emotional state (e.g., frustration, anger, sadness).

[1778] 5. Searching for and presenting solutions

[1779] The system searches for the best solution from support databases and FAQs, and then presents the message with a tone and content adjusted according to the user's emotional state.

[1780] 6. Feedback and Escalation

[1781] We collect user feedback and escalate it to support agents as needed. The agents understand the user's emotional state and take appropriate action.

[1782] Specific example

[1783] For example, if a user is unable to log in to their account with an electronic payment service, the support request will be processed as follows:

[1784] Example of a prompt

[1785] "Analysis of a support request when a user is unable to log in to their account on an electronic payment service. The user created the account two weeks ago. The error message is 'Incorrect password.' The user appears frustrated. The emotion engine presents empathetic messages and searches the past database for the best solution. If the user tries the suggested solutions and the problem persists, the issue is escalated to an agent."

[1786] Thus, the embodiments of the invention aim to provide prompt and accurate support in response to the diverse needs of users.

[1787] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1788] Step 1:

[1789] The user enters a support request using an information device (smartphone, PC, etc.). They enter details of the problem they are facing and attach supporting documents such as screenshots as needed. The entered information is then sent from the device to the server.

[1790] Input: User-submitted details of the problem, error message, and screenshot.

[1791] Output: Support Request Data

[1792] Step 2:

[1793] The server receives support requests and stores them in the database. The server ensures reliability and security.

[1794] Input: Support Request Data

[1795] Output: Support request records stored in the database

[1796] Step 3:

[1797] The server's natural language processing engine analyzes the content of the support request. It extracts keywords and important phrases from the request to identify the problem.

[1798] Input: Support Request Data

[1799] Output: Extracted keywords, identified issues

[1800] Step 4:

[1801] The server's emotion engine recognizes the user's emotions. It analyzes the request content and various input data (text, audio data, etc.) to evaluate the user's emotional state. For example, it determines whether the user is feeling frustrated.

[1802] Input: Support request data, text data, audio data

[1803] Output: User's emotional state (e.g., frustration, anger, sadness)

[1804] Step 5:

[1805] The server searches the database for the best solution. Based on past support and FAQ databases, it selects and prioritizes the most suitable solution for the user. It also adjusts the tone and content of messages according to the user's emotional state.

[1806] Input: Identified problem, user's emotional state

[1807] Output: Optimal solution, adjusted message

[1808] Step 6:

[1809] The server presents a solution to the user. The terminal displays the optimal solution and a tailored message.

[1810] Input: Optimal solution, tailored message

[1811] Output: Solution and message displayed on the user terminal

[1812] Step 7:

[1813] The user attempts to solve the problem according to the suggested solution and provides feedback on the results.

[1814] Input: Solution trial results, feedback data

[1815] Output: User feedback

[1816] Step 8:

[1817] The server receives feedback from the user and stores it in the database. The server analyzes the feedback and determines whether the issue was successfully resolved.

[1818] Input: Feedback data

[1819] Output: Feedback records stored in the database, resolution result

[1820] Step 9:

[1821] If the problem persists, the server will escalate it to a support agent based on the feedback. The agent will then take steps to provide detailed support based on the request and the user's emotional state.

[1822] Input: Feedback data, user's emotional state

[1823] Output: Escalation data to the agent

[1824] In this way, each step works together to form a system that supports the rapid and appropriate resolution of user problems.

[1825] 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.

[1826] 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.

[1827] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1828] 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.

[1829] 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.

[1830] 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.

[1831] 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.

[1832] 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.

[1833] 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."

[1834] 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.

[1835] 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.

[1836] 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.

[1837] 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.

[1838] 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.

[1839] 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.

[1840] 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.

[1841] 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.

[1842] 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.

[1843] 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.

[1844] 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.

[1845] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[1846] The following is further disclosed regarding the embodiments described above.

[1847] (Claim 1)

[1848] A means for a user to enter a support request using an information device,

[1849] A means for receiving and storing the aforementioned support request,

[1850] A means for analyzing the content of the aforementioned support request and searching for an appropriate solution,

[1851] A means for presenting the aforementioned solution to the user,

[1852] Means of collecting user feedback,

[1853] Based on the aforementioned feedback, a means of escalating the matter to a support agent as needed,

[1854] A system that includes this.

[1855] (Claim 2)

[1856] The system according to claim 1, characterized in that the analysis means uses natural language processing technology to extract keywords from the support request.

[1857] (Claim 3)

[1858] The system according to claim 1, characterized in that the aforementioned solution is selected based on past support databases and FAQ databases.

[1859] "Example 1"

[1860] (Claim 1)

[1861] A means for a user to enter a support request using an information device,

[1862] A means for receiving and storing the aforementioned support request,

[1863] A means for analyzing the content of the aforementioned support request and searching for an appropriate solution,

[1864] A means for presenting the aforementioned solution to the user,

[1865] Means of collecting user feedback,

[1866] Based on the aforementioned feedback, a means of escalating the matter to a support agent as needed,

[1867] A means of using a generative AI model to analyze the content of the aforementioned support request,

[1868] The aforementioned generation AI model includes means for analyzing the content of support requests using natural language processing technology and extracting keywords and important phrases,

[1869] A means of searching for solutions from past support databases and FAQ databases,

[1870] A system that includes this.

[1871] (Claim 2)

[1872] The system according to claim 1, characterized in that the generating AI model uses natural language processing technology to extract keywords and important phrases from a support request.

[1873] (Claim 3)

[1874] The system according to claim 1, characterized in that the aforementioned solution is selected based on past support databases and FAQ databases.

[1875] "Application Example 1"

[1876] (Claim 1)

[1877] A means for a user to enter a support request using an information device,

[1878] A means for receiving and storing the aforementioned support request,

[1879] A means for analyzing the content of the aforementioned support request and searching for an appropriate solution,

[1880] A means for presenting the aforementioned solution to the user,

[1881] Means of collecting user feedback,

[1882] Based on the aforementioned feedback, a means of escalating the matter to a support agent as needed,

[1883] A means to resolve issues related to ad performance and settings,

[1884] A means of presenting the optimal solution regarding advertising performance using a generative AI model,

[1885] The aforementioned solution method includes means for automatically determining the requirements for escalation,

[1886] A system that includes this.

[1887] (Claim 2)

[1888] The system according to claim 1, characterized in that the analysis means uses natural language processing technology to extract keywords from the support request.

[1889] (Claim 3)

[1890] The system according to claim 1, characterized in that the aforementioned solution is selected based on past support databases and FAQ databases.

[1891] "Example 2 of combining an emotion engine"

[1892] (Claim 1)

[1893] A means for users to enter support requests using their devices,

[1894] A means for receiving and storing the aforementioned support request,

[1895] A means for analyzing the content of the aforementioned support request and searching for an appropriate solution,

[1896] A means of analyzing the user's emotional state,

[1897] A means for adjusting the presentation of solutions based on the aforementioned emotional state,

[1898] A means for presenting the aforementioned solution to the user,

[1899] Means of collecting user feedback,

[1900] Based on the aforementioned feedback, a means of escalating the matter to a support agent as needed,

[1901] A system that includes this.

[1902] (Claim 2)

[1903] The system according to claim 1, characterized in that the analysis means uses natural language processing technology to extract keywords from the support request.

[1904] (Claim 3)

[1905] The system according to claim 1, characterized in that the aforementioned solution is selected based on past support databases and FAQ databases.

[1906] "Application example 2 of combining emotional engines"

[1907] (Claim 1)

[1908] A means for a user to enter a support request using an information device,

[1909] A means for receiving and storing the aforementioned support request,

[1910] A means for analyzing the content of the aforementioned support request and searching for an appropriate solution,

[1911] A means for presenting the aforementioned solution to the user,

[1912] The aforementioned analysis means includes means for recognizing the user's emotions and optimizing the response,

[1913] Means of collecting user feedback,

[1914] Based on the aforementioned feedback, a means of escalating the matter to a support agent as needed,

[1915] A system that includes this.

[1916] (Claim 2)

[1917] The system according to claim 1, characterized in that the analysis means uses natural language processing technology to extract keywords from the support request.

[1918] (Claim 3)

[1919] The system according to claim 1, characterized in that the aforementioned solution is selected based on past support databases and FAQ databases, and the tone and content of the message presented are adjusted according to the user's emotional state. [Explanation of Symbols]

[1920] 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 a user to enter a support request using an information device, A means for receiving and storing the aforementioned support request, A means for analyzing the content of the aforementioned support request and searching for an appropriate solution, A means for presenting the aforementioned solution to the user, Means of collecting user feedback, Based on the aforementioned feedback, a means of escalating the matter to a support agent as needed, A system that includes this.

2. The system according to claim 1, characterized in that the analysis means uses natural language processing technology to extract keywords from the support request.

3. The system according to claim 1, characterized in that the aforementioned solution is selected based on past support databases and FAQ databases.

Images