system

Abstract

We provide the system. [Solution] Means of receiving inquiries from various channels, An analysis means for processing received queries using natural language, A means of proposing an automated response based on the analysis results, A means of routing inquiries to the appropriate person in case the automated response is insufficient, A means of recording and sharing the history of inquiries, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including 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 as a 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 corporate inquiry response, inquiries from various channels are sent to separate windows, which may lead to duplicate responses and reduced efficiency. Also, when the automatic response system does not function sufficiently, it may not be escalated appropriately to the person in charge, raising concerns about the decline in response quality. As a result, there is a problem that the labor of operators increases and customer satisfaction decreases.

Means for Solving the Problems

[0005] The present invention solves the above problems with a system that includes means for receiving inquiries from various channels, means for analyzing received inquiries using natural language processing, means for proposing an automated response based on the analysis results, means for routing inquiries to the appropriate person in case the automated response is insufficient, and means for recording and sharing the inquiry handling history. Specifically, it centrally manages received inquiries and provides appropriate automated responses by analyzing them using natural language processing technology. Furthermore, even if the automated response is insufficient, it prevents duplication of responses by quickly routing inquiries to the appropriate person, thereby reducing the workload of operators. In addition, by recording and sharing the handling history, all personnel can check past responses, enabling consistent responses.

[0006] "Inquiry" refers to the act of a user sending questions or requests regarding a product or service to a company.

[0007] "Channel" refers to the medium or means used when inquiries are sent to a company, specifically email, telephone, chatbot, etc.

[0008] "Natural language processing" refers to the technology that enables computers to understand, analyze, and process human language, and is primarily used to extract meaning and keywords from text data.

[0009] "Analysis means" refers to systems and algorithms that analyze received queries using natural language processing techniques to extract their meaning and important keywords.

[0010] "Automated response" refers to a function in which a system automatically generates an appropriate answer based on the content of an inquiry and sends it to the user.

[0011] "Proposed means" refers to systems and algorithms that provide appropriate automated responses based on the information extracted by the analysis means.

[0012] "Methods for routing inquiries to the appropriate person" refers to systems or algorithms used to escalate inquiries to the appropriate department or person when the inquiry is complex and automated responses are insufficient.

[0013] "Means for recording and sharing history" refers to systems and algorithms for storing information about inquiries and their responses in a database and sharing it among the relevant personnel. [Brief explanation of the drawing]

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

Mode for Carrying Out the Invention

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

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

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

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

[0019] 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.

[0020] 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).

[0021] 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."

[0022] [First Embodiment]

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

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0029] 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.

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

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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".

[0035] This invention relates to an inquiry management system that centrally manages inquiries received by a company from various channels and performs automated responses and escalations. Specific embodiments for carrying out this invention are described below.

[0036] This system receives inquiries from various channels, analyzes their content, and provides automated responses. Furthermore, if the automated response is insufficient, it routes the inquiry to the appropriate person in charge. In addition, inquiry handling history is recorded in a database and shared among operators to prevent duplicate responses and reduce workload.

[0037] System Overview

[0038] 1. Receiving an inquiry

[0039] The server receives user inquiries through multiple channels, including email, phone, and chatbots.

[0040] 2. Analysis of the inquiry content

[0041] The server extracts the received query content as text data and analyzes it using natural language processing techniques.

[0042] 3. Generating automated responses

[0043] Based on the analysis results, the server refers to the FAQ database to generate an appropriate automated response and provides it to the user.

[0044] 4. Escalation

[0045] If the server's automated response is insufficient, it will forward the inquiry to the appropriate person in charge.

[0046] 5. Recording and sharing of support history

[0047] The server records all inquiry handling history in a database, making it accessible to all operators.

[0048] Detailed processing flow

[0049] Inquiry received

[0050] The server receives user inquiries through multiple channels, such as email, phone, and chatbot. For example, if a user sends an email asking "How do I return a product?", the server will receive that email.

[0051] Analysis of inquiry content

[0052] The server converts the received inquiry into text data format. Next, this inquiry is analyzed using natural language processing techniques to extract key keywords and intent. Here, key keywords such as "return" and "method" are extracted.

[0053] Generating an automated response

[0054] The server searches the FAQ database based on the extracted keywords to find the most suitable answer. For example, if an FAQ exists regarding "how to return a product," it generates an automated response based on that answer. This automated response is then provided to the user.

[0055] escalation

[0056] If the automated response is insufficient, the server re-evaluates the inquiry and routes it to the appropriate person or department. For example, if an inquiry concerns complex return conditions or a specific case, the server will forward the information to the relevant customer support department.

[0057] Recording and sharing of support history

[0058] The server records all inquiries and their responses in a database. This database is accessible to all operators, enabling quick and consistent responses by referring to past inquiry history.

[0059] Specific example

[0060] For example, if a user sends an email inquiry asking "How do I return a product?", this inquiry is received by the server. The server extracts the inquiry as text data and uses natural language processing technology to extract the keywords "return" and "method". The server then searches the FAQ database for answers regarding "how to return a product," generates an automated response, and sends it back to the user. If the user inquires about more detailed conditions, the information is forwarded to the appropriate department, and the response history is recorded and shared in the database.

[0061] In this way, this system centrally manages inquiries from various channels and provides appropriate responses quickly, thereby reducing the workload of operators while improving customer satisfaction.

[0062] The following describes the processing flow.

[0063] Step 1:

[0064] The server receives user inquiries through various channels, including email, telephone, and chatbots. For email, the server checks for new emails from the mail server using the IMAP protocol. For chatbots, the server receives new messages via WebSocket. For telephone calls, the server obtains incoming call information using SIP (Session Initiation Protocol).

[0065] Step 2:

[0066] The server extracts the received inquiry content as text data. Text is extracted from the body of emails and chat messages, and in the case of telephone inquiries, a speech recognition system is used to convert the speech into text.

[0067] Step 3:

[0068] The server extracts text data and passes it to a natural language processing engine for semantic analysis and keyword extraction of the query. Specifically, the server sends text data to a natural language processing API for keyword and intent analysis.

[0069] Step 4:

[0070] The server searches the FAQ database based on the analysis results. It queries the FAQ database based on keywords and phrases to retrieve the most relevant answers.

[0071] Step 5:

[0072] The server generates an automated response based on the answers it receives. The generated automated response is converted to an adaptive format and organized into a format that is provided to the user.

[0073] Step 6:

[0074] The server sends an automated response to the user. In the case of email, the server sends the reply email using the SMTP protocol. In the case of a chatbot, the server sends the message using WebSocket.

[0075] Step 7:

[0076] If the server's automated response is insufficient, it will determine whether to escalate the inquiry to a responsible person. Based on the analysis results, an escalation flag will be set, and the appropriate person or department will be determined.

[0077] Step 8:

[0078] The server routes the inquiry to the appropriate person. Based on the content and category of the escalated inquiry, it refers to a list of tasks that the person can handle. Once a suitable person is determined, a notification is sent.

[0079] Step 9:

[0080] The server records all inquiries and their responses in a database. Detailed information, including inquiry content, automated responses, and the actions taken by the assigned staff member in case of escalation, is stored in the database.

[0081] Step 10:

[0082] The server sends a survey form or rating template to the user to collect feedback after handling their inquiry. The collected feedback information is stored in a database and analyzed to help improve the quality of service.

[0083] (Example 1)

[0084] 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."

[0085] In modern society, it is crucial for companies to efficiently and quickly handle inquiries received from various channels. However, if automated responses are insufficient or if the sharing of response history is not done properly, customer satisfaction may decline and the burden on operators may increase. To solve these problems, a system is needed that accurately analyzes inquiry content, provides appropriate responses, and efficiently manages and shares response history.

[0086] 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.

[0087] In this invention, the server includes means for receiving inquiries from various channels, means for analyzing the received inquiries using natural language processing, means for generating automatic responses based on the analysis results, means for routing inquiries to appropriate personnel if the automatic response is insufficient, means for recording and sharing inquiry handling history, means for evaluating and escalating inquiry content, means for analyzing inquiry content using a natural language processing library, means including an evaluation algorithm for evaluating the effectiveness of automatic responses, and means for providing a management screen and making the inquiry history accessible. This enables centralized management of inquiries from various channels, prompt provision of appropriate responses, reduction of operator workload, and improvement of customer satisfaction.

[0088] An "inquiry" refers to information that a user sends to a company to request information or support.

[0089] A "channel" refers to the medium or method that a user uses to send an inquiry to a company.

[0090] A "server" refers to a computer system that receives, analyzes, generates automated responses to, escalates, and records and shares response history.

[0091] "Natural language processing" refers to the technology that enables computers to understand and process human language.

[0092] "Automated response" refers to a system where a computer automatically generates and provides answers based on the content of an inquiry.

[0093] "Escalation" refers to the process of transferring an inquiry to a human representative when the automated response is insufficient or inappropriate.

[0094] "Analysis" refers to the process of understanding the content of an inquiry using natural language processing technology and extracting important keywords and intents.

[0095] An "FAQ database" refers to a database that compiles frequently asked questions and their answers.

[0096] A "database" refers to a system for organizing and storing digital information.

[0097] An "evaluation algorithm" refers to a mathematical method used to assess the effectiveness of automated responses.

[0098] The term "administration screen" refers to an interface used by operators to manage the system and view inquiry history.

[0099] This invention relates to an inquiry management system that centrally manages inquiries received by a company from various channels and performs automated responses and escalations. Specific embodiments for carrying out this invention are described below.

[0100] This system operates server-centric, receiving inquiries from various channels, analyzing their content, and providing automated responses. Furthermore, if the automated response is insufficient, it routes the inquiry to the appropriate person. In addition, inquiry handling history is recorded in a database and shared among operators to prevent duplicate responses and reduce workload.

[0101] Hardware and software to be used

[0102] The server is the main component and uses the following hardware and software:

[0103] Hardware: Server machines, database servers

[0104] Software: Email receiving servers (e.g., SMTP servers), natural language processing libraries (e.g., spaCy, NLTK), database management systems (e.g., MySQL®, PostgreSQL), web application frameworks for administration panels (e.g., Django, Flask)

[0105] System Overview

[0106] This system has the following functions:

[0107] 1. Receiving inquiries: The server receives inquiries from users through multiple channels, such as email, telephone, and chatbots.

[0108] 2. Analysis of the inquiry content: The server extracts the received inquiry content as text data and analyzes it using natural language processing technology.

[0109] 3. Generation of automated responses: Based on the analysis results, the server generates an appropriate automated response by referring to the FAQ database and provides it to the user.

[0110] 4. Escalation: If the server's automated response is insufficient, it will forward the inquiry to the appropriate person in charge.

[0111] 5. Recording and sharing of response history: The server records all inquiry response history in a database and makes it accessible to all operators.

[0112] Specific examples of receiving inquiries

[0113] A user sends an email message saying, "Please tell me how to return an item." The server receives this message via the email receiving server and stores it in the inquiry database.

[0114] Specific examples of analyzing inquiry content

[0115] The server extracts the body of the received email as text data and uses a natural language processing library to identify the keywords "return" and "method." The server then uses these keywords to understand the user's intent.

[0116] Specific examples of automated response generation

[0117] The server queries the FAQ database to retrieve answers regarding "how to return a product." Then, based on the retrieved answers, the server generates an automated response message, which is sent to the user, for example, via email.

[0118] Specific examples of escalation

[0119] If the automated response is insufficient, the server will receive a reply from the user stating that they would like to know more specific return conditions. In this case, the server will re-analyze the inquiry and escalate it to the appropriate person in charge.

[0120] Examples of recording and sharing support history

[0121] The server stores all inquiries and their responses in a database. Furthermore, all operators can access past inquiry history through a web-based management screen. For example, an operator can log into the management screen and search for past inquiries related to "returns."

[0122] Example of a prompt

[0123] The following is an example of an input prompt statement for a specific generative AI model:

[0124] "We have an inquiry regarding the return process for a product. Please extract keywords to generate an automated response."

[0125] "If the automated response is insufficient, please escalate the issue to the appropriate person."

[0126] Thus, this system provides a set of functions to efficiently and effectively process inquiries and improve customer satisfaction.

[0127] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0128] Step 1:

[0129] Inquiry received

[0130] The server receives user inquiries through multiple channels, such as email, phone, and chatbot. For example, if a user sends an email asking "How do I return this item?", the server's email receiving server receives the email. In this case, the input is the user's inquiry message, and the output is the received inquiry data.

[0131] Specific actions:

[0132] The server receives emails via an email receiving server (e.g., an SMTP server).

[0133] The received message is saved to the query database.

[0134] Step 2:

[0135] Analysis of inquiry content

[0136] The server extracts the received query content as text data and analyzes it using natural language processing techniques. The input is the received query data, and the output is the analyzed keywords and intent.

[0137] Specific actions:

[0138] The server extracts the body of the received message as text data.

[0139] We use natural language processing libraries (e.g., spaCy, NLTK) to extract key keywords and intent. For example, we identify the keywords "return" and "method".

[0140] Step 3:

[0141] Generating an automated response

[0142] The server generates an appropriate automated response based on the analysis results, referencing the FAQ database, and provides it to the user. The input in this process consists of the analyzed keywords and intent, while the output is the generated automated response message.

[0143] Specific actions:

[0144] The server searches the FAQ database based on the analyzed keywords.

[0145] Retrieve relevant answers and generate automated response messages. For example, generate an automated response based on FAQ answers regarding "how to return a product."

[0146] The generated automated response message is provided to the user via email or other means.

[0147] Step 4:

[0148] escalation

[0149] If the automated response is insufficient, the server will forward the inquiry to the appropriate person in charge. The input at this time is the user's follow-up inquiry or feedback on the automated response, and the output is the inquiry data that will be passed on to the person in charge.

[0150] Specific actions:

[0151] The server runs an evaluation algorithm to assess the effectiveness of the automated response. For example, if the user makes another inquiry or if the user's feedback is negative, the server may determine that the automated response was insufficient.

[0152] Analyze the inquiry and forward it to the appropriate person in charge. Send a notification to the person in charge.

[0153] Step 5:

[0154] Recording and sharing of support history

[0155] The server records all inquiry handling history in a database, making it accessible to all operators. The input consists of processed inquiry data and its response result, while the output is the recorded handling history.

[0156] Specific actions:

[0157] The server saves each query, its response, and the escalation details to a database management system (e.g., MySQL, PostgreSQL).

[0158] The server provides an administration screen for operators, allowing them to view past inquiry history. Operators log in to the administration screen and search and display history using specific keywords or dates.

[0159] Step 6:

[0160] Evaluation of the effectiveness of automated responses

[0161] The server continuously evaluates the effectiveness of the generated automated responses and uses this as a criterion for escalation decisions. The inputs at this stage are user feedback and follow-up query data regarding the generated automated responses, while the output is the escalation decision result and the improved automated response message.

[0162] Specific actions:

[0163] The server collects user feedback data and information on whether or not the user has made a follow-up inquiry.

[0164] The evaluation algorithm is executed to assess the effectiveness of the automated response.

[0165] If escalation is deemed necessary, the inquiry will be re-analyzed and handed over to the appropriate person.

[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] In recent years, with the spread of online shopping, the importance of customer support in virtual stores has increased. However, customer inquiries come from a variety of channels, which can lead to a loss of consistency and speed in responses. Furthermore, if appropriate automated responses are not provided, escalation becomes necessary, and efficient inquiry management is required. This invention aims to solve these problems by providing a system that can respond to customer inquiries quickly and consistently in virtual stores.

[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 receiving inquiries from various channels, means for analyzing the received inquiries using natural language processing, means for proposing an automated response based on the analysis results, means for routing inquiries to the appropriate person in case the automated response is insufficient, means for recording and sharing the inquiry handling history, means for receiving and analyzing user inquiries in real time within the virtual store, and means for creating an appropriate automated response using a generative AI model. This enables a rapid and consistent response to customer inquiries within the virtual store, and is expected to improve the efficiency of customer support and enhance customer satisfaction.

[0171] "Means of receiving inquiries from diverse channels" refers to a system for receiving customer inquiries through multiple communication methods, such as email, telephone, chatbots, and in-virtual store chats.

[0172] "Analysis means for natural language processing received inquiries" refers to a function that uses natural language processing technology to analyze the content of inquiries as text data and extract key keywords and intents.

[0173] "Means of proposing automated responses based on analysis results" refers to a function that generates the optimal automated response by referring to an appropriate FAQ database based on the analyzed keywords and intent.

[0174] "Means for routing inquiries to the appropriate person in case of insufficient automated responses" refers to a function that forwards inquiries to the appropriate person or department when the generated automated response is inadequate to the customer's inquiry.

[0175] "Means for recording and sharing inquiry response history" refers to a function that records all inquiries and their responses in a database, making this information accessible to all operators, thereby sharing past response history and preventing duplicate responses.

[0176] "A means of receiving and analyzing user inquiries in real time within a virtual store" refers to a function that receives inquiries made by users within a virtual store in real time, analyzes their content immediately, and responds to them promptly.

[0177] "Means for creating appropriate automated responses using a generative AI model" refers to a function that uses an AI model to generate the optimal automated response based on the analyzed inquiry content and provide it to the user.

[0178] This invention provides a system for centrally managing inquiries from various channels in a virtual store and enabling automated responses and escalation. The system includes a series of processes for receiving inquiries, analyzing them, generating responses, and escalating them as necessary.

[0179] System Configuration

[0180] This system is implemented using the following main components:

[0181] 1. Inquiry receiving server

[0182] Inquiries are received through multiple channels, including email, phone, chatbots, and in-virtual store chats. Received inquiries are converted into a format that can be processed as text data.

[0183] 2. Natural Language Processing (NLP) Analysis Module

[0184] This module analyzes received inquiries and extracts key keywords and intents. Specifically, it extracts important keywords through text analysis using natural language processing techniques.

[0185] 3. Generating AI Module

[0186] Based on the analyzed keywords, the system consults the FAQ database and generates an appropriate automated response. The generated response is then sent to the user.

[0187] 4. Escalation Module

[0188] If the automated response is insufficient, this module will re-evaluate the inquiry and route it to the appropriate person or department.

[0189] 5. Inquiry Response History Database

[0190] This is a database that records all inquiries and their responses. All operators can access this database, enabling consistent responses by referring to past inquiry history.

[0191] System processing flow

[0192] When a user submits an inquiry within the virtual store, the inquiry is received by a receiving server. The receiving server processes the inquiry as text data and forwards it to an NLP analysis module. The NLP analysis module extracts the main keywords of the inquiry and passes them on to a generation AI module. The generation AI module selects the most appropriate answer from the FAQ database and generates a response. If the generated response is insufficient, an escalation module routes the inquiry to the appropriate person or department. All inquiries and their responses are recorded in an inquiry response history database and used for future inquiry handling.

[0193] Technologies used and specific examples

[0194] Hardware: Servers, cloud storage

[0195] Software: AIChatbot, TextAnalyzer, DatabaseConnector, FAQ

[0196] For example, if a user sends a chat message in a virtual store asking "How do I return an item?", this inquiry is received by the receiving server. TextAnalyzer extracts the keywords "return" and "how," and uses a generative AI model to search for FAQs related to "how to return an item." As a result, an appropriate automated response is provided to the user.

[0197] Example of a prompt

[0198] "Please tell me how to return an item."

[0199] "I'd like to know the reason for the delivery delay."

[0200] "I would like to change the size of the product."

[0201] "I have a question about a specific product."

[0202] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0203] Step 1:

[0204] Users make inquiries within the virtual store. For example, a user might use the chat function to send a message saying, "How do I return an item?" This message becomes input into the system.

[0205] Step 2:

[0206] The server receives inquiries from users. The processing flow involves receiving inquiries via various channels such as email, telephone, chatbot, and in-virtual store chat, and converting them into text data format. The received inquiry text becomes the input for the next step.

[0207] Step 3:

[0208] The server's natural language processing (NLP) analysis module analyzes the received query. In this step, TextAnalyzer is used to extract key keywords and intent from the text data. For example, keywords such as "return" and "method" are extracted. The extracted keywords become the input for the next step.

[0209] Step 4:

[0210] The server's generation AI module generates an automated response based on keywords from the NLP analysis module. In this step, the generation AI model is used to search for appropriate answers in the FAQ database and create a response message using natural language generation technology. For example, it retrieves an answer regarding "how to return a product" from the FAQ and generates a response such as "Details on how to return a product are as follows:...". The generated automated response becomes the input for the next step.

[0211] Step 5:

[0212] The server sends an automated response to the user. The response message is then sent to the user's chat. The user receives the automated response and obtains a solution to their inquiry. This response serves as input for the next step.

[0213] Step 6:

[0214] If the server's automated response is insufficient, it forwards the inquiry to the escalation module. The escalation module re-evaluates the generated automated response if it determines that the automated response is insufficient based on certain criteria, and routes the inquiry to the appropriate person or department. For example, if an exception to the return procedure is required, it will be forwarded to the customer support team. The assigned person's information becomes the input for the next step.

[0215] Step 7:

[0216] The server's inquiry response history database module records all inquiries and their responses in the database. This includes the inquiry reception time, content, analysis results, automated response content, and escalation history. This allows operators to refer to past inquiry history. The recorded data is used for future inquiry handling.

[0217] The above are the specific processing steps.

[0218] 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.

[0219] This invention relates to an inquiry management system that centrally manages inquiries received by a company from various channels, and performs automated responses, escalation, and sentiment recognition using an emotion engine. Specific embodiments for carrying out this invention are described below.

[0220] This system receives user inquiries from various channels, analyzes their content, and uses an emotion engine to recognize the user's emotions, providing appropriate responses based on those emotions. If the automated response is insufficient, it forwards the inquiry to the appropriate person in charge. Inquiry handling history is also recorded in a database and can be shared among operators.

[0221] System Overview

[0222] 1. Receiving an inquiry

[0223] The server receives user inquiries through various channels, including email, phone, and chatbots.

[0224] 2. Analysis of the inquiry content

[0225] The server extracts the received query content as text data and analyzes it using natural language processing techniques.

[0226] 3. Emotion recognition

[0227] The server uses an emotion engine to recognize the user's emotions from text and audio data and reflects them in the analysis results.

[0228] 4. Generating automated responses

[0229] The server generates an appropriate automated response based on the analysis results and sentiment recognition results, referencing the FAQ database, and provides it to the user.

[0230] 5. Escalation

[0231] If the server's automated response is insufficient, it will forward the inquiry to the appropriate person in charge.

[0232] 6. Recording and sharing of support history

[0233] The server records all inquiry handling history in a database, making it accessible to all operators.

[0234] Detailed processing flow

[0235] Inquiry received

[0236] The server receives user inquiries through various channels such as email, phone, and chatbots. For example, if a user sends an email asking "How do I return a product?", the server will receive that email.

[0237] Analysis of inquiry content

[0238] The server converts the received inquiry into text data format. Next, this inquiry is analyzed using natural language processing techniques to extract key keywords and intent. Here, key keywords such as "return" and "method" are extracted.

[0239] emotion recognition

[0240] The server uses an emotion engine to recognize user emotions from text and audio data. For example, it analyzes the user's emotions, such as "angry" or "troubled," from text and recognizes their emotional state. The recognition results are fed back to the analysis system and used to adjust the response.

[0241] Generating an automated response

[0242] The server searches the FAQ database based on the analysis results and sentiment recognition results to find the most appropriate answer. For example, if there is an FAQ about "how to return a product," it generates an automated response based on the content of that FAQ. This automated response is then provided to the user. For example, if the user is in a state of "anxiety," a more helpful response will be generated.

[0243] escalation

[0244] If the automated response is insufficient, the server re-evaluates the inquiry and routes it to the appropriate person or department. For example, if an inquiry concerns complex return conditions or a specific case, the server will forward the information to the relevant customer support department.

[0245] Recording and sharing of support history

[0246] The server records all inquiries and their responses in a database. This database is accessible to all operators, enabling quick and consistent responses by referring to past inquiry history.

[0247] Specific example

[0248] For example, if a user sends an email inquiry asking "How do I return a product?", the server receives the inquiry. The server analyzes the content using natural language processing and recognizes the user's emotions using an emotion engine. As a result of the analysis, keywords such as "return" and "how" are extracted, and the emotion engine detects that the user is "confused." Based on this information, the server generates a more helpful automated response and sends it back to the user. If necessary, the server escalates the inquiry to a specialist and records the entire response history in a database to ensure consistent service.

[0249] In this way, this system centrally manages inquiries from various channels and incorporates sentiment recognition technology to provide more appropriate responses quickly. This makes it possible to reduce the workload of operators while improving customer satisfaction.

[0250] The following describes the processing flow.

[0251] Step 1:

[0252] The server receives user inquiries through various channels, including email, telephone, and chatbots. For email, the server retrieves new emails from the mail server using the IMAP protocol. For chatbots, the server receives new messages via WebSocket. For telephone calls, the server retrieves incoming call information using the SIP protocol.

[0253] Step 2:

[0254] The server extracts the content of the received inquiry as text data. For emails and chat messages, text is extracted from the body, and for phone calls, a speech recognition system is used to convert the speech into text.

[0255] Step 3:

[0256] The server extracts text data and passes it to a natural language processing engine for semantic analysis and keyword extraction of the query. Specifically, the server sends text data to a natural language processing API, and keywords and intent are obtained as analysis results.

[0257] Step 4:

[0258] The server passes text data to the emotion engine to analyze the user's emotions. The emotion engine performs the analysis and detects emotions such as "joy," "anger," and "sadness." The detected emotion data is returned to the server and fed back into the analysis system.

[0259] Step 5:

[0260] The server searches the FAQ database based on the analysis results and sentiment recognition results. The server retrieves the most relevant answers from the FAQ database based on keywords and detected sentiments.

[0261] Step 6:

[0262] The server generates an automated response based on answers retrieved from the FAQ database, and adjusts the response content while also taking into account the emotion recognition results. For example, if the server detects that the user is "angry," it generates a response that includes an apology. This response is then formatted appropriately and sent to the user.

[0263] Step 7:

[0264] The server sends an automated response to the user. If it's email, the server sends the reply using the SMTP protocol. If it's a chatbot, the server sends the message using WebSocket.

[0265] Step 8:

[0266] If the server determines that its automated response is insufficient, it will escalate the inquiry to a relevant person. Based on the analysis results and sentiment recognition results, the appropriate person or department will be selected, an escalation flag will be set, and a notification will be sent.

[0267] Step 9:

[0268] The server routes the inquiry to the appropriate person in charge. The escalated inquiry is compared to a list of tasks that the person in charge can handle, and a notification is sent once a suitable person is determined.

[0269] Step 10:

[0270] The server records all inquiries and their responses in a database. Detailed information such as the inquiry content, automated responses, the actions taken by the assigned staff during escalation, and the user's emotional state are stored in the database.

[0271] Step 11:

[0272] After handling an inquiry, the server sends a survey form or rating template to the user to collect feedback. The collected feedback information is stored in a database and used to improve the quality of future support.

[0273] (Example 2)

[0274] 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".

[0275] A key challenge for companies is to centrally manage inquiries received from various channels and respond quickly and appropriately. In particular, accurately recognizing user emotions and generating responses based on them is crucial for improving customer satisfaction, and it is also necessary to quickly escalate issues to the appropriate personnel when automated responses are insufficient.

[0276] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving inquiries from various channels, means for analyzing the received inquiries using natural language processing technology, means for generating an automated response based on the analysis results and sentiment recognition by the sentiment engine, means for routing inquiries to the appropriate person in charge if the automated response is insufficient, and means for recording and sharing the inquiry handling history. This enables companies to centrally manage inquiries from various channels and quickly provide appropriate responses that take into account the user's emotions.

[0277] An "inquiry" is a question or request that a user sends to a company or organization to seek information.

[0278] A "channel" refers to a means of communication used for sending and receiving inquiries and information, and specifically includes email, telephone, and chatbots.

[0279] "Natural language processing technology" is the technology that understands, interprets, and generates human language on a computer.

[0280] "Analysis means" refers to the techniques and methods used to analyze received inquiries and understand their content and intent.

[0281] An "emotion engine" is a system or technology that recognizes a user's emotional state from text data or audio data.

[0282] "Automatic response" refers to a function in which a system automatically provides pre-set answers to user inquiries.

[0283] An "FAQ database" is a database that compiles frequently asked questions and their answers.

[0284] "Escalation" is the process of transferring an inquiry to the appropriate person or department when the initial response is insufficient.

[0285] "The 'person in charge' refers to a person or department responsible for handling escalated inquiries."

[0286] "The 'correspondence history' is data that records each inquiry and the corresponding response content."

[0287] "The'sharing means' is a system or method for enabling multiple operators or persons in charge to view and utilize the correspondence history."

[0288] The present invention relates to an inquiry management system that centrally manages inquiries received by a company from various channels and performs automatic response, escalation, and emotion recognition. This system receives inquiries from users through various channels, analyzes the content, recognizes the user's emotion using an emotion engine, and makes an appropriate response based on that. Also, when the automatic response is insufficient, the inquiry is assigned to an appropriate person in charge. The inquiry response history is also recorded in a database and can be shared among operators.

[0289] Specifically, the system is configured as follows.

[0290] Receiving of Inquiries

[0291] The server receives inquiries from users through various channels such as email, phone, chatbot, etc. This receiving process includes capturing voice data and analyzing text messages. For example, when a user enters "I want to know the method of returning a product" into a chatbot, the server immediately receives that message.

[0292] Analysis of Inquiry Content

[0293] The server converts the received inquiry into text data. For voice input, speech recognition technology is used for this purpose. Next, the server analyzes the inquiry using a natural language processing (NLP) engine to extract key keywords and context. For example, keywords such as "return" and "method" are identified.

[0294] emotion recognition

[0295] The server uses an emotion engine to recognize the user's emotions from text and audio data. For example, an NLP engine analyzes emotions such as "confused" or "angry." The results of the emotion recognition are fed back into the analysis results and used to adjust the response.

[0296] Generating an automated response

[0297] The server uses the analysis results and sentiment recognition results to refer to the FAQ database and generate the most appropriate answer. For example, if an FAQ about "how to return a product" exists in the database, the server will generate an automated response based on that information. If the sentiment engine recognizes that the user is "confused," the server will generate a response using more helpful and polite language.

[0298] escalation

[0299] If the automated response is insufficient, the server re-evaluates the inquiry and routes it to the appropriate person or department. For example, if the process is complex and cannot be handled by the FAQ, the server escalates the matter to the customer support department. This ensures that the right person can respond quickly.

[0300] Recording and sharing of support history

[0301] The server records all inquiries and their responses in a database. This database is accessible to all operators, enabling them to provide fast and consistent service based on past response history.

[0302] Specific Example

[0303] For example, when a user sends an email inquiry saying "I want to know the method of returning goods", the server receives the email. The server analyzes the content of the email using natural language processing technology and extracts the main keywords "return" and "method". At the same time, the emotion engine recognizes that the user is "confused". Based on the analysis results and the emotional state, the server generates an automatic response in a kind manner and replies to the user. If necessary, the server escalates the inquiry to a dedicated person in charge and records the entire response history in the database for future reference.

[0304] Examples of Prompt Sentences

[0305] The following shows examples where appropriate answers can be obtained by inputting the following prompt sentences into the generation AI model:

[0306] "The user is confused about the method of returning goods. In this case, how can a kind response be automatically generated?"

[0307] "The user has inquired about returning goods using the chatbot, and the emotion engine has recognized the emotion of anger. What is the appropriate response method in this case?"

[0308] In this way, this system centrally manages inquiries from various channels and incorporates emotion recognition technology to quickly provide more appropriate responses. Thereby, it is possible to reduce the workload of operators while improving customer satisfaction.

[0309] The flow of specific processing in Example 2 will be described using FIG. 13.

[0310] Step 1: Receiving an Inquiry

[0311] The server receives user inquiries through various channels, such as email, phone, and chatbots. For example, if a user enters "How do I return a product?" into the chatbot, that message is sent to the server. The server then internally records the received message in its data store. The input is the inquiry content, and the output is the received inquiry data.

[0312] Step 2: Analyzing the inquiry content

[0313] The server converts the received inquiry into text data format. In the case of voice input, the server uses speech recognition technology. For example, if a user makes an inquiry by phone, the server converts the voice data into text and then analyzes that text data. Next, the server uses a natural language processing (NLP) engine to analyze the inquiry and extract key keywords and context. For example, keywords such as "return" and "method" are identified. The input is text data or voice data, and the output is the analyzed keyword and context data.

[0314] Step 3: Emotion Recognition

[0315] The server uses an emotion engine to recognize the user's emotions from text and audio data. For example, the NLP engine can detect emotions such as "confused" or "angry" from the user's message. This information is then fed back into subsequent response generation. The input is the parsed text data, and the output is the emotion recognition result.

[0316] Step 4: Generating an automated response

[0317] The server references the FAQ database based on analysis results and sentiment recognition results to generate the most appropriate answer. For example, if an FAQ about "how to return a product" exists in the database, it will generate an automated response based on that information. If the sentiment engine determines that the user is "confused," a more helpful and easy-to-understand response will be generated. The input is the FAQ database and sentiment recognition results, and the output is an automated response message.

[0318] Step 5: Escalation

[0319] If the automated response is insufficient, the server re-evaluates the inquiry and routes it to the appropriate person or department. For example, if the process is complex and cannot be resolved through FAQs, the server escalates the inquiry to the customer support department. In this process, the person in charge is notified of the inquiry and its status. The input is the inquiry and the result of the automated response suitability evaluation, and the output is the contact person to whom the inquiry has been escalated.

[0320] Step 6: Record and share the history of interactions

[0321] The server records all inquiries and their responses in a database. This database is accessible to all operators and is used to provide fast and consistent service based on past response history. For example, if a similar inquiry has occurred in the past, the response time can be reduced by referring to that history. Inputs include inquiry content, response content, and escalation history, while output is the recorded response history data.

[0322] (Application Example 2)

[0323] 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".

[0324] Traditional inquiry management systems struggle to centrally manage inquiries received from various channels, and in particular, they have difficulty providing appropriate responses tailored to the user's emotional state. Furthermore, they lack adequate mechanisms for analyzing inquiry content, generating automated responses, and then routing inquiries to the appropriate personnel if the automated responses are insufficient. This results in problems such as a reduced user experience and increased response times.

[0325] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0326] In this invention, the server includes means for receiving inquiries from various channels, means for analyzing the received inquiries using natural language processing, means for proposing an automated response based on the analysis results, means for recognizing the user's emotions and generating an appropriate automated response based on the results, means for routing inquiries to the appropriate person in charge if the automated response is insufficient, and means for recording and sharing the inquiry handling history. This enables centralized management of inquiries from various channels and allows for the rapid provision of more appropriate responses by incorporating emotion recognition technology.

[0327] "Means of receiving inquiries from diverse channels" refers to a system for receiving inquiries from different communication methods such as email, telephone, chatbots, and smartphone applications.

[0328] "Analysis means for natural language processing received inquiries" refers to the process of converting the received inquiry content into text data, analyzing the content using natural language processing techniques, and extracting key keywords and intents.

[0329] "Means for proposing automated responses based on analysis results" refers to a system that automatically generates and proposes appropriate responses based on the analyzed inquiry content and the results of sentiment recognition.

[0330] "Means for recognizing user emotions and generating appropriate automated responses based on the results" refers to a technology that uses an emotion engine to identify the user's emotional state and generates the optimal response accordingly.

[0331] "A means of routing inquiries to the appropriate person when automated responses are insufficient" refers to a function that re-evaluates inquiries that cannot be resolved by automated responses and routes them to the appropriate person or department with the necessary expertise.

[0332] "Means for recording and sharing inquiry response history" refers to a system that stores all inquiries and their responses in a database and shares them in a way that all operators can access.

[0333] An "emotion engine" is a technology that analyzes a user's emotional state from text and audio data, recognizing and classifying emotions such as positive, negative, and neutral.

[0334] A "smartphone application" is software that runs on a smartphone or tablet and interacts directly with the user through an interface.

[0335] This invention relates to an inquiry management system that centrally manages inquiries received by a company from various channels, and performs automated responses, escalation, and sentiment recognition using an sentiment engine. Specific embodiments for carrying out this invention are described below.

[0336] System Overview

[0337] This system has the following main features:

[0338] 1. Receiving an inquiry:

[0339] The server receives user inquiries through various channels, including email, telephone, chatbots, and smartphone applications.

[0340] 2. Analysis of the inquiry content:

[0341] The server extracts the received inquiry content as text data, analyzes it using natural language processing techniques, and extracts key keywords and intent.

[0342] 3. Emotion recognition:

[0343] The server uses an emotion engine to recognize the user's emotions from text and audio data, and reflects that emotional state in the analysis results.

[0344] 4. Generating automated responses:

[0345] Based on the analysis results and emotion recognition results, the server refers to the FAQ database to generate an appropriate automated response and provides it to the user. The response is expressed in a friendly manner that matches the user's emotional state.

[0346] 5. Escalation:

[0347] If the automated response is insufficient, the server will re-evaluate the inquiry and route it to the appropriate person or department.

[0348] 6. Recording and sharing of interaction history:

[0349] The server records all inquiry handling history in a database, making it accessible to all operators.

[0350] Hardware and software to be used

[0351] 1. Hardware:

[0352] Smartphones, tablets, and servers (including multiple servers for running the inquiry management system).

[0353] 2. Software:

[0354] Python programming language, TextBlob library for sentiment analysis, FAQ database, and libraries for natural language processing.

[0355] Specific example

[0356] For example, if a user makes a request through a smartphone application saying, "I'm tired today, so I'd like to listen to some relaxing music," the server receives the request and extracts it as text data. Then, using natural language processing technology, the request is analyzed, and the main keywords "relax" and "music" are extracted. Furthermore, an emotion engine is used to recognize the user's emotional state of being "tired." Based on this information, the server automatically generates and provides a "relaxing music playlist."

[0357] Example of a prompt

[0358] If a user inputs "Please recommend some relaxing music," an example of the input prompt text for the generating AI model would be as follows:

[0359] "Users are looking for relaxation. Please suggest some relaxing music."

[0360] Thus, the present invention centrally manages inquiries from various channels and incorporates emotion recognition technology to quickly provide appropriate automated responses tailored to the user's emotional state. This reduces the workload of operators while improving user satisfaction.

[0361] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0362] Step 1:

[0363] Inquiry received

[0364] Users input and submit their inquiries via smartphones, email, phone, chatbots, etc. The server receives inquiries from these various channels. The input data may be in text or audio format. For example, a user might send "I want to listen to relaxing music" via a smartphone application.

[0365] Step 2:

[0366] Extraction of inquiry content

[0367] The server extracts the received query content as text data. This process also includes converting audio data to text. If audio data is present, it is converted to text format and passed on to the next step.

[0368] Step 3:

[0369] Analysis using natural language processing

[0370] The server analyzes text data using natural language processing techniques. Specifically, it analyzes the text data to extract key keywords and intent. For example, the keywords "relax" and "music" might be extracted. The input is text data, and the output is the analyzed keyword data.

[0371] Step 4:

[0372] emotion recognition

[0373] The server uses an emotion engine to recognize the user's emotions from text data. Here, it classifies and identifies emotions as positive, negative, or neutral. For example, it might recognize the negative emotion "tired" from the user's text. The input is keyword data, and the output is the user's emotional state.

[0374] Step 5:

[0375] Generating an automated response

[0376] The server generates an appropriate automated response by referencing the FAQ database and pre-configured response patterns based on the analysis results and emotion recognition results. For example, it might generate a response offering a "relaxing music playlist." The input is keyword data and emotion state, and the output is the generated automated response.

[0377] Step 6:

[0378] Judgment and handling of escalation

[0379] The server evaluates the generated automated response, and if it determines the response is insufficient, it routes the inquiry to the appropriate person or department. For example, complex requests are escalated to specialized support staff. The input is the automated response, and the output is the escalated inquiry.

[0380] Step 7:

[0381] Providing a response

[0382] The server sends a generated automated response to the user. The user receives the response through a smartphone application or the channel used. For example, a generated playlist is provided to the user. The input is the generated response, and the output is the response sent to the user.

[0383] Step 8:

[0384] Recording and sharing of inquiry response history

[0385] The server records all inquiries and their responses in a database. This record is accessible to all operators and is used as reference material to ensure consistent responses. Input is the response content, and output is the record stored in the database.

[0386] 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.

[0387] 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.

[0388] 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.

[0389] [Second Embodiment]

[0390] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0391] 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.

[0392] 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).

[0393] 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.

[0394] 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.

[0395] 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).

[0396] 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.

[0397] 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.

[0398] 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.

[0399] 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.

[0400] 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.

[0401] 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".

[0402] This invention relates to an inquiry management system that centrally manages inquiries received by a company from various channels and performs automated responses and escalations. Specific embodiments for carrying out this invention are described below.

[0403] This system receives inquiries from various channels, analyzes their content, and provides automated responses. Furthermore, if the automated response is insufficient, it routes the inquiry to the appropriate person in charge. In addition, inquiry handling history is recorded in a database and shared among operators to prevent duplicate responses and reduce workload.

[0404] System Overview

[0405] 1. Receiving an inquiry

[0406] The server receives user inquiries through multiple channels, including email, phone, and chatbots.

[0407] 2. Analysis of the inquiry content

[0408] The server extracts the received query content as text data and analyzes it using natural language processing techniques.

[0409] 3. Generating automated responses

[0410] Based on the analysis results, the server refers to the FAQ database to generate an appropriate automated response and provides it to the user.

[0411] 4. Escalation

[0412] If the server's automated response is insufficient, it will forward the inquiry to the appropriate person in charge.

[0413] 5. Recording and sharing of support history

[0414] The server records all inquiry handling history in a database, making it accessible to all operators.

[0415] Detailed processing flow

[0416] Inquiry received

[0417] The server receives user inquiries through multiple channels, such as email, phone, and chatbot. For example, if a user sends an email asking "How do I return a product?", the server will receive that email.

[0418] Analysis of inquiry content

[0419] The server converts the received inquiry into text data format. Next, this inquiry is analyzed using natural language processing techniques to extract key keywords and intent. Here, key keywords such as "return" and "method" are extracted.

[0420] Generating an automated response

[0421] The server searches the FAQ database based on the extracted keywords to find the most suitable answer. For example, if an FAQ exists regarding "how to return a product," it generates an automated response based on that answer. This automated response is then provided to the user.

[0422] escalation

[0423] If the automated response is insufficient, the server re-evaluates the inquiry and routes it to the appropriate person or department. For example, if an inquiry concerns complex return conditions or a specific case, the server will forward the information to the relevant customer support department.

[0424] Recording and sharing of support history

[0425] The server records all inquiries and their responses in a database. This database is accessible to all operators, enabling quick and consistent responses by referring to past inquiry history.

[0426] Specific example

[0427] For example, if a user sends an email inquiry asking "How do I return a product?", this inquiry is received by the server. The server extracts the inquiry as text data and uses natural language processing technology to extract the keywords "return" and "method". The server then searches the FAQ database for answers regarding "how to return a product," generates an automated response, and sends it back to the user. If the user inquires about more detailed conditions, the information is forwarded to the appropriate department, and the response history is recorded and shared in the database.

[0428] In this way, this system centrally manages inquiries from various channels and provides appropriate responses quickly, thereby reducing the workload of operators while improving customer satisfaction.

[0429] The following describes the processing flow.

[0430] Step 1:

[0431] The server receives user inquiries through various channels, including email, telephone, and chatbots. For email, the server checks for new emails from the mail server using the IMAP protocol. For chatbots, the server receives new messages via WebSocket. For telephone calls, the server obtains incoming call information using SIP (Session Initiation Protocol).

[0432] Step 2:

[0433] The server extracts the received inquiry content as text data. Text is extracted from the body of emails and chat messages, and in the case of telephone inquiries, a speech recognition system is used to convert the speech into text.

[0434] Step 3:

[0435] The server extracts text data and passes it to a natural language processing engine for semantic analysis and keyword extraction of the query. Specifically, the server sends text data to a natural language processing API for keyword and intent analysis.

[0436] Step 4:

[0437] The server searches the FAQ database based on the analysis results. It queries the FAQ database based on keywords and phrases to retrieve the most relevant answers.

[0438] Step 5:

[0439] The server generates an automated response based on the answers it receives. The generated automated response is converted to an adaptive format and organized into a format that is provided to the user.

[0440] Step 6:

[0441] The server sends an automated response to the user. In the case of email, the server sends the reply email using the SMTP protocol. In the case of a chatbot, the server sends the message using WebSocket.

[0442] Step 7:

[0443] If the server's automated response is insufficient, it will determine whether to escalate the inquiry to a responsible person. Based on the analysis results, an escalation flag will be set, and the appropriate person or department will be determined.

[0444] Step 8:

[0445] The server routes the inquiry to the appropriate person. Based on the content and category of the escalated inquiry, it refers to a list of tasks that the person can handle. Once a suitable person is determined, a notification is sent.

[0446] Step 9:

[0447] The server records all inquiries and their responses in a database. Detailed information, including inquiry content, automated responses, and the actions taken by the assigned staff member in case of escalation, is stored in the database.

[0448] Step 10:

[0449] The server sends a survey form or rating template to the user to collect feedback after handling their inquiry. The collected feedback information is stored in a database and analyzed to help improve the quality of service.

[0450] (Example 1)

[0451] 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."

[0452] In modern society, it is crucial for companies to efficiently and quickly handle inquiries received from various channels. However, if automated responses are insufficient or if the sharing of response history is not done properly, customer satisfaction may decline and the burden on operators may increase. To solve these problems, a system is needed that accurately analyzes inquiry content, provides appropriate responses, and efficiently manages and shares response history.

[0453] 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.

[0454] In this invention, the server includes means for receiving inquiries from various channels, means for analyzing the received inquiries using natural language processing, means for generating automatic responses based on the analysis results, means for routing inquiries to appropriate personnel if the automatic response is insufficient, means for recording and sharing inquiry handling history, means for evaluating and escalating inquiry content, means for analyzing inquiry content using a natural language processing library, means including an evaluation algorithm for evaluating the effectiveness of automatic responses, and means for providing a management screen and making the inquiry history accessible. This enables centralized management of inquiries from various channels, prompt provision of appropriate responses, reduction of operator workload, and improvement of customer satisfaction.

[0455] An "inquiry" refers to information that a user sends to a company to request information or support.

[0456] A "channel" refers to the medium or method that a user uses to send an inquiry to a company.

[0457] A "server" refers to a computer system that receives, analyzes, generates automated responses to, escalates, and records and shares response history.

[0458] "Natural language processing" refers to the technology that enables computers to understand and process human language.

[0459] "Automated response" refers to a system where a computer automatically generates and provides answers based on the content of an inquiry.

[0460] "Escalation" refers to the process of transferring an inquiry to a human representative when the automated response is insufficient or inappropriate.

[0461] "Analysis" refers to the process of understanding the content of an inquiry using natural language processing technology and extracting important keywords and intents.

[0462] An "FAQ database" refers to a database that compiles frequently asked questions and their answers.

[0463] A "database" refers to a system for organizing and storing digital information.

[0464] An "evaluation algorithm" refers to a mathematical method used to assess the effectiveness of automated responses.

[0465] The term "administration screen" refers to an interface used by operators to manage the system and view inquiry history.

[0466] This invention relates to an inquiry management system that centrally manages inquiries received by a company from various channels and performs automated responses and escalations. Specific embodiments for carrying out this invention are described below.

[0467] This system operates server-centric, receiving inquiries from various channels, analyzing their content, and providing automated responses. Furthermore, if the automated response is insufficient, it routes the inquiry to the appropriate person. In addition, inquiry handling history is recorded in a database and shared among operators to prevent duplicate responses and reduce workload.

[0468] Hardware and software to be used

[0469] The server is the main component and uses the following hardware and software:

[0470] Hardware: Server machines, database servers

[0471] Software: Email receiving servers (e.g., SMTP servers), natural language processing libraries (e.g., spaCy, NLTK), database management systems (e.g., MySQL, PostgreSQL), web application frameworks for administration panels (e.g., Django, Flask)

[0472] System Overview

[0473] This system has the following functions:

[0474] 1. Receiving inquiries: The server receives inquiries from users through multiple channels, such as email, telephone, and chatbots.

[0475] 2. Analysis of the inquiry content: The server extracts the received inquiry content as text data and analyzes it using natural language processing technology.

[0476] 3. Generation of automated responses: Based on the analysis results, the server generates an appropriate automated response by referring to the FAQ database and provides it to the user.

[0477] 4. Escalation: If the server's automated response is insufficient, it will forward the inquiry to the appropriate person in charge.

[0478] 5. Recording and sharing of response history: The server records all inquiry response history in a database and makes it accessible to all operators.

[0479] Specific examples of receiving inquiries

[0480] A user sends an email message saying, "Please tell me how to return an item." The server receives this message via the email receiving server and stores it in the inquiry database.

[0481] Specific examples of analyzing inquiry content

[0482] The server extracts the body of the received email as text data and uses a natural language processing library to identify the keywords "return" and "method." The server then uses these keywords to understand the user's intent.

[0483] Specific examples of automated response generation

[0484] The server queries the FAQ database to retrieve answers regarding "how to return a product." Then, based on the retrieved answers, the server generates an automated response message, which is sent to the user, for example, via email.

[0485] Specific examples of escalation

[0486] If the automated response is insufficient, the server will receive a reply from the user stating that they would like to know more specific return conditions. In this case, the server will re-analyze the inquiry and escalate it to the appropriate person in charge.

[0487] Examples of recording and sharing support history

[0488] The server stores all inquiries and their responses in a database. Furthermore, all operators can access past inquiry history through a web-based management screen. For example, an operator can log into the management screen and search for past inquiries related to "returns."

[0489] Example of a prompt

[0490] The following is an example of an input prompt statement for a specific generative AI model:

[0491] "We have an inquiry regarding the return process for a product. Please extract keywords to generate an automated response."

[0492] "If the automated response is insufficient, please escalate the issue to the appropriate person."

[0493] Thus, this system provides a set of functions to efficiently and effectively process inquiries and improve customer satisfaction.

[0494] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0495] Step 1:

[0496] Inquiry received

[0497] The server receives user inquiries through multiple channels, such as email, phone, and chatbot. For example, if a user sends an email asking "How do I return this item?", the server's email receiving server receives the email. In this case, the input is the user's inquiry message, and the output is the received inquiry data.

[0498] Specific actions:

[0499] The server receives emails via an email receiving server (e.g., an SMTP server).

[0500] The received message is saved to the query database.

[0501] Step 2:

[0502] Analysis of inquiry content

[0503] The server extracts the received query content as text data and analyzes it using natural language processing techniques. The input is the received query data, and the output is the analyzed keywords and intent.

[0504] Specific actions:

[0505] The server extracts the body of the received message as text data.

[0506] We use natural language processing libraries (e.g., spaCy, NLTK) to extract key keywords and intent. For example, we identify the keywords "return" and "method".

[0507] Step 3:

[0508] Generating an automated response

[0509] The server generates an appropriate automated response based on the analysis results, referencing the FAQ database, and provides it to the user. The input in this process consists of the analyzed keywords and intent, while the output is the generated automated response message.

[0510] Specific actions:

[0511] The server searches the FAQ database based on the analyzed keywords.

[0512] Retrieve relevant answers and generate automated response messages. For example, generate an automated response based on FAQ answers regarding "how to return a product."

[0513] The generated automated response message is provided to the user via email or other means.

[0514] Step 4:

[0515] escalation

[0516] If the automated response is insufficient, the server will forward the inquiry to the appropriate person in charge. The input at this time is the user's follow-up inquiry or feedback on the automated response, and the output is the inquiry data that will be passed on to the person in charge.

[0517] Specific actions:

[0518] The server runs an evaluation algorithm to assess the effectiveness of the automated response. For example, if the user makes another inquiry or if the user's feedback is negative, the server may determine that the automated response was insufficient.

[0519] Analyze the inquiry and forward it to the appropriate person in charge. Send a notification to the person in charge.

[0520] Step 5:

[0521] Recording and sharing of support history

[0522] The server records all inquiry handling history in a database, making it accessible to all operators. The input consists of processed inquiry data and its response result, while the output is the recorded handling history.

[0523] Specific actions:

[0524] The server saves each query, its response, and the escalation details to a database management system (e.g., MySQL, PostgreSQL).

[0525] The server provides an administration screen for operators, allowing them to view past inquiry history. Operators log in to the administration screen and search and display history using specific keywords or dates.

[0526] Step 6:

[0527] Evaluation of the effectiveness of automated responses

[0528] The server continuously evaluates the effectiveness of the generated automated responses and uses this as a criterion for escalation decisions. The inputs at this stage are user feedback and follow-up query data regarding the generated automated responses, while the output is the escalation decision result and the improved automated response message.

[0529] Specific actions:

[0530] The server collects user feedback data and information on whether or not the user has made a follow-up inquiry.

[0531] The evaluation algorithm is executed to assess the effectiveness of the automated response.

[0532] If escalation is deemed necessary, the inquiry will be re-analyzed and handed over to the appropriate person.

[0533] (Application Example 1)

[0534] 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."

[0535] In recent years, with the spread of online shopping, the importance of customer support in virtual stores has increased. However, customer inquiries come from a variety of channels, which can lead to a loss of consistency and speed in responses. Furthermore, if appropriate automated responses are not provided, escalation becomes necessary, and efficient inquiry management is required. This invention aims to solve these problems by providing a system that can respond to customer inquiries quickly and consistently in virtual stores.

[0536] 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.

[0537] In this invention, the server includes means for receiving inquiries from various channels, means for analyzing the received inquiries using natural language processing, means for proposing an automated response based on the analysis results, means for routing inquiries to the appropriate person in case the automated response is insufficient, means for recording and sharing the inquiry handling history, means for receiving and analyzing user inquiries in real time within the virtual store, and means for creating an appropriate automated response using a generative AI model. This enables a rapid and consistent response to customer inquiries within the virtual store, and is expected to improve the efficiency of customer support and enhance customer satisfaction.

[0538] "Means of receiving inquiries from diverse channels" refers to a system for receiving customer inquiries through multiple communication methods, such as email, telephone, chatbots, and in-virtual store chats.

[0539] "Analysis means for natural language processing received inquiries" refers to a function that uses natural language processing technology to analyze the content of inquiries as text data and extract key keywords and intents.

[0540] "Means of proposing automated responses based on analysis results" refers to a function that generates the optimal automated response by referring to an appropriate FAQ database based on the analyzed keywords and intent.

[0541] "Means for routing inquiries to the appropriate person in case of insufficient automated responses" refers to a function that forwards inquiries to the appropriate person or department when the generated automated response is inadequate to the customer's inquiry.

[0542] "Means for recording and sharing inquiry response history" refers to a function that records all inquiries and their responses in a database, making this information accessible to all operators, thereby sharing past response history and preventing duplicate responses.

[0543] "A means of receiving and analyzing user inquiries in real time within a virtual store" refers to a function that receives inquiries made by users within a virtual store in real time, analyzes their content immediately, and responds to them promptly.

[0544] "Means for creating appropriate automated responses using a generative AI model" refers to a function that uses an AI model to generate the optimal automated response based on the analyzed inquiry content and provide it to the user.

[0545] This invention provides a system for centrally managing inquiries from various channels in a virtual store and enabling automated responses and escalation. The system includes a series of processes for receiving inquiries, analyzing them, generating responses, and escalating them as necessary.

[0546] System Configuration

[0547] This system is implemented using the following main components:

[0548] 1. Inquiry receiving server

[0549] Inquiries are received through multiple channels, including email, phone, chatbots, and in-virtual store chats. Received inquiries are converted into a format that can be processed as text data.

[0550] 2. Natural Language Processing (NLP) Analysis Module

[0551] This module analyzes received inquiries and extracts key keywords and intents. Specifically, it extracts important keywords through text analysis using natural language processing techniques.

[0552] 3. Generating AI Module

[0553] Based on the analyzed keywords, the system consults the FAQ database and generates an appropriate automated response. The generated response is then sent to the user.

[0554] 4. Escalation Module

[0555] If the automated response is insufficient, this module will re-evaluate the inquiry and route it to the appropriate person or department.

[0556] 5. Inquiry Response History Database

[0557] This is a database that records all inquiries and their responses. All operators can access this database, enabling consistent responses by referring to past inquiry history.

[0558] System processing flow

[0559] When a user submits an inquiry within the virtual store, the inquiry is received by a receiving server. The receiving server processes the inquiry as text data and forwards it to an NLP analysis module. The NLP analysis module extracts the main keywords of the inquiry and passes them on to a generation AI module. The generation AI module selects the most appropriate answer from the FAQ database and generates a response. If the generated response is insufficient, an escalation module routes the inquiry to the appropriate person or department. All inquiries and their responses are recorded in an inquiry response history database and used for future inquiry handling.

[0560] Technologies used and specific examples

[0561] Hardware: Servers, cloud storage

[0562] Software: AIChatbot, TextAnalyzer, DatabaseConnector, FAQ

[0563] For example, if a user sends a chat message in a virtual store asking "How do I return an item?", this inquiry is received by the receiving server. TextAnalyzer extracts the keywords "return" and "how," and uses a generative AI model to search for FAQs related to "how to return an item." As a result, an appropriate automated response is provided to the user.

[0564] Example of a prompt

[0565] "Please tell me how to return an item."

[0566] "I'd like to know the reason for the delivery delay."

[0567] "I would like to change the size of the product."

[0568] "I have a question about a specific product."

[0569] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0570] Step 1:

[0571] Users make inquiries within the virtual store. For example, a user might use the chat function to send a message saying, "How do I return an item?" This message becomes input into the system.

[0572] Step 2:

[0573] The server receives inquiries from users. The processing flow involves receiving inquiries via various channels such as email, telephone, chatbot, and in-virtual store chat, and converting them into text data format. The received inquiry text becomes the input for the next step.

[0574] Step 3:

[0575] The server's natural language processing (NLP) analysis module analyzes the received query. In this step, TextAnalyzer is used to extract key keywords and intent from the text data. For example, keywords such as "return" and "method" are extracted. The extracted keywords become the input for the next step.

[0576] Step 4:

[0577] The server's generation AI module generates an automated response based on keywords from the NLP analysis module. In this step, the generation AI model is used to search for appropriate answers in the FAQ database and create a response message using natural language generation technology. For example, it retrieves an answer regarding "how to return a product" from the FAQ and generates a response such as "Details on how to return a product are as follows:...". The generated automated response becomes the input for the next step.

[0578] Step 5:

[0579] The server sends an automated response to the user. The response message is then sent to the user's chat. The user receives the automated response and obtains a solution to their inquiry. This response serves as input for the next step.

[0580] Step 6:

[0581] If the server's automated response is insufficient, it forwards the inquiry to the escalation module. The escalation module re-evaluates the generated automated response if it determines that the automated response is insufficient based on certain criteria, and routes the inquiry to the appropriate person or department. For example, if an exception to the return procedure is required, it will be forwarded to the customer support team. The assigned person's information becomes the input for the next step.

[0582] Step 7:

[0583] The server's inquiry response history database module records all inquiries and their responses in the database. This includes the inquiry reception time, content, analysis results, automated response content, and escalation history. This allows operators to refer to past inquiry history. The recorded data is used for future inquiry handling.

[0584] The above are the specific processing steps.

[0585] 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.

[0586] This invention relates to an inquiry management system that centrally manages inquiries received by a company from various channels, and performs automated responses, escalation, and sentiment recognition using an emotion engine. Specific embodiments for carrying out this invention are described below.

[0587] This system receives user inquiries from various channels, analyzes their content, and uses an emotion engine to recognize the user's emotions, providing appropriate responses based on those emotions. If the automated response is insufficient, it forwards the inquiry to the appropriate person in charge. Inquiry handling history is also recorded in a database and can be shared among operators.

[0588] System Overview

[0589] 1. Receiving an inquiry

[0590] The server receives user inquiries through various channels, including email, phone, and chatbots.

[0591] 2. Analysis of the inquiry content

[0592] The server extracts the received query content as text data and analyzes it using natural language processing techniques.

[0593] 3. Emotion recognition

[0594] The server uses an emotion engine to recognize the user's emotions from text and audio data and reflects them in the analysis results.

[0595] 4. Generating automated responses

[0596] The server generates an appropriate automated response based on the analysis results and sentiment recognition results, referencing the FAQ database, and provides it to the user.

[0597] 5. Escalation

[0598] If the server's automated response is insufficient, it will forward the inquiry to the appropriate person in charge.

[0599] 6. Recording and sharing of support history

[0600] The server records all inquiry handling history in a database, making it accessible to all operators.

[0601] Detailed processing flow

[0602] Inquiry received

[0603] The server receives user inquiries through various channels such as email, phone, and chatbots. For example, if a user sends an email asking "How do I return a product?", the server will receive that email.

[0604] Analysis of inquiry content

[0605] The server converts the received inquiry into text data format. Next, this inquiry is analyzed using natural language processing techniques to extract key keywords and intent. Here, key keywords such as "return" and "method" are extracted.

[0606] emotion recognition

[0607] The server uses an emotion engine to recognize user emotions from text and audio data. For example, it analyzes the user's emotions, such as "angry" or "troubled," from text and recognizes their emotional state. The recognition results are fed back to the analysis system and used to adjust the response.

[0608] Generating an automated response

[0609] The server searches the FAQ database based on the analysis results and sentiment recognition results to find the most appropriate answer. For example, if there is an FAQ about "how to return a product," it generates an automated response based on the content of that FAQ. This automated response is then provided to the user. For example, if the user is in a state of "anxiety," a more helpful response will be generated.

[0610] escalation

[0611] If the automated response is insufficient, the server re-evaluates the inquiry and routes it to the appropriate person or department. For example, if an inquiry concerns complex return conditions or a specific case, the server will forward the information to the relevant customer support department.

[0612] Recording and sharing of support history

[0613] The server records all inquiries and their responses in a database. This database is accessible to all operators, enabling quick and consistent responses by referring to past inquiry history.

[0614] Specific example

[0615] For example, if a user sends an email inquiry asking "How do I return a product?", the server receives the inquiry. The server analyzes the content using natural language processing and recognizes the user's emotions using an emotion engine. As a result of the analysis, keywords such as "return" and "how" are extracted, and the emotion engine detects that the user is "confused." Based on this information, the server generates a more helpful automated response and sends it back to the user. If necessary, the server escalates the inquiry to a specialist and records the entire response history in a database to ensure consistent service.

[0616] In this way, this system centrally manages inquiries from various channels and incorporates sentiment recognition technology to provide more appropriate responses quickly. This makes it possible to reduce the workload of operators while improving customer satisfaction.

[0617] The following describes the processing flow.

[0618] Step 1:

[0619] The server receives user inquiries through various channels, including email, telephone, and chatbots. For email, the server retrieves new emails from the mail server using the IMAP protocol. For chatbots, the server receives new messages via WebSocket. For telephone calls, the server retrieves incoming call information using the SIP protocol.

[0620] Step 2:

[0621] The server extracts the content of the received inquiry as text data. For emails and chat messages, text is extracted from the body, and for phone calls, a speech recognition system is used to convert the speech into text.

[0622] Step 3:

[0623] The server extracts text data and passes it to a natural language processing engine for semantic analysis and keyword extraction of the query. Specifically, the server sends text data to a natural language processing API, and keywords and intent are obtained as analysis results.

[0624] Step 4:

[0625] The server passes text data to the emotion engine to analyze the user's emotions. The emotion engine performs the analysis and detects emotions such as "joy," "anger," and "sadness." The detected emotion data is returned to the server and fed back into the analysis system.

[0626] Step 5:

[0627] The server searches the FAQ database based on the analysis results and sentiment recognition results. The server retrieves the most relevant answers from the FAQ database based on keywords and detected sentiments.

[0628] Step 6:

[0629] The server generates an automated response based on answers retrieved from the FAQ database, and adjusts the response content while also taking into account the emotion recognition results. For example, if the server detects that the user is "angry," it generates a response that includes an apology. This response is then formatted appropriately and sent to the user.

[0630] Step 7:

[0631] The server sends an automated response to the user. If it's email, the server sends the reply using the SMTP protocol. If it's a chatbot, the server sends the message using WebSocket.

[0632] Step 8:

[0633] If the server determines that its automated response is insufficient, it will escalate the inquiry to a relevant person. Based on the analysis results and sentiment recognition results, the appropriate person or department will be selected, an escalation flag will be set, and a notification will be sent.

[0634] Step 9:

[0635] The server routes the inquiry to the appropriate person in charge. The escalated inquiry is compared to a list of tasks that the person in charge can handle, and a notification is sent once a suitable person is determined.

[0636] Step 10:

[0637] The server records all inquiries and their responses in a database. Detailed information such as the inquiry content, automated responses, the actions taken by the assigned staff during escalation, and the user's emotional state are stored in the database.

[0638] Step 11:

[0639] After handling an inquiry, the server sends a survey form or rating template to the user to collect feedback. The collected feedback information is stored in a database and used to improve the quality of future support.

[0640] (Example 2)

[0641] 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".

[0642] A key challenge for companies is to centrally manage inquiries received from various channels and respond quickly and appropriately. In particular, accurately recognizing user emotions and generating responses based on them is crucial for improving customer satisfaction, and it is also necessary to quickly escalate issues to the appropriate personnel when automated responses are insufficient.

[0643] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving inquiries from various channels, means for analyzing the received inquiries using natural language processing technology, means for generating an automated response based on the analysis results and sentiment recognition by the sentiment engine, means for routing inquiries to the appropriate person in charge if the automated response is insufficient, and means for recording and sharing the inquiry handling history. This enables companies to centrally manage inquiries from various channels and quickly provide appropriate responses that take into account the user's emotions.

[0644] An "inquiry" is a question or request that a user sends to a company or organization to seek information.

[0645] A "channel" refers to a means of communication used for sending and receiving inquiries and information, and specifically includes email, telephone, and chatbots.

[0646] "Natural language processing technology" is the technology that understands, interprets, and generates human language on a computer.

[0647] "Analysis means" refers to the techniques and methods used to analyze received inquiries and understand their content and intent.

[0648] An "emotion engine" is a system or technology that recognizes a user's emotional state from text data or audio data.

[0649] "Automatic response" refers to a function in which a system automatically provides pre-set answers to user inquiries.

[0650] An "FAQ database" is a database that compiles frequently asked questions and their answers.

[0651] "Escalation" is the process of transferring an inquiry to the appropriate person or department when the initial response is insufficient.

[0652] A "person in charge" refers to the individual or department responsible for handling an escalated inquiry.

[0653] "Response history" refers to data that records each inquiry and the details of the response to it.

[0654] "Sharing methods" refer to systems or methods that enable multiple operators or staff members to view and use the service history.

[0655] This invention relates to an inquiry management system that centrally manages inquiries received by a company from various channels, and performs automated responses, escalation, and sentiment recognition. This system receives user inquiries from various channels, analyzes their content, recognizes the user's emotions using a sentiment engine, and provides an appropriate response based on that. Furthermore, if the automated response is insufficient, it routes the inquiry to the appropriate person. Inquiry handling history is also recorded in a database and can be shared among operators.

[0656] Specifically, the system is configured as follows:

[0657] Inquiry received

[0658] The server receives user inquiries through various channels, including email, phone, and chatbots. This receiving process includes capturing voice data and parsing text messages. For example, if a user types "How do I return this item?" into the chatbot, the server receives the message immediately.

[0659] Analysis of inquiry content

[0660] The server converts the received inquiry into text data. For voice input, speech recognition technology is used for this purpose. Next, the server analyzes the inquiry using a natural language processing (NLP) engine to extract key keywords and context. For example, keywords such as "return" and "method" are identified.

[0661] emotion recognition

[0662] The server uses an emotion engine to recognize the user's emotions from text and audio data. For example, an NLP engine analyzes emotions such as "confused" or "angry." The results of the emotion recognition are fed back into the analysis results and used to adjust the response.

[0663] Generating an automated response

[0664] The server uses the analysis results and sentiment recognition results to refer to the FAQ database and generate the most appropriate answer. For example, if an FAQ about "how to return a product" exists in the database, the server will generate an automated response based on that information. If the sentiment engine recognizes that the user is "confused," the server will generate a response using more helpful and polite language.

[0665] escalation

[0666] If the automated response is insufficient, the server re-evaluates the inquiry and routes it to the appropriate person or department. For example, if the process is complex and cannot be handled by the FAQ, the server escalates the matter to the customer support department. This ensures that the right person can respond quickly.

[0667] Recording and sharing of support history

[0668] The server records all inquiries and their responses in a database. This database is accessible to all operators, enabling them to provide fast and consistent service based on past response history.

[0669] Specific example

[0670] For example, if a user sends an email inquiry asking "How do I return a product?", the server receives the email. The server analyzes the email content using natural language processing technology and extracts the main keywords "return" and "how to return". At the same time, the sentiment engine recognizes that the user is "confused". Based on the analysis results and sentiment state, the server generates an automated response in a friendly tone and sends it back to the user. If necessary, the server escalates the inquiry to a specialist and records the entire response history in a database for future reference.

[0671] Example of a prompt

[0672] The following is an example of how inputting the following prompt into the AI ​​model can produce an appropriate response:

[0673] "A user is confused about how to return a product. How can we automatically generate a helpful response in this case?"

[0674] "A user contacted us via chatbot regarding a product return, but the emotion engine detected anger. What is the appropriate response in this case?"

[0675] In this way, this system centrally manages inquiries from various channels and incorporates sentiment recognition technology to provide more appropriate responses quickly. This makes it possible to reduce operator workload while improving customer satisfaction.

[0676] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0677] Step 1: Receiving an inquiry

[0678] The server receives user inquiries through various channels, such as email, phone, and chatbots. For example, if a user enters "How do I return a product?" into the chatbot, that message is sent to the server. The server then internally records the received message in its data store. The input is the inquiry content, and the output is the received inquiry data.

[0679] Step 2: Analyzing the inquiry content

[0680] The server converts the received inquiry into text data format. In the case of voice input, the server uses speech recognition technology. For example, if a user makes an inquiry by phone, the server converts the voice data into text and then analyzes that text data. Next, the server uses a natural language processing (NLP) engine to analyze the inquiry and extract key keywords and context. For example, keywords such as "return" and "method" are identified. The input is text data or voice data, and the output is the analyzed keyword and context data.

[0681] Step 3: Emotion Recognition

[0682] The server uses an emotion engine to recognize the user's emotions from text and audio data. For example, the NLP engine can detect emotions such as "confused" or "angry" from the user's message. This information is then fed back into subsequent response generation. The input is the parsed text data, and the output is the emotion recognition result.

[0683] Step 4: Generating an automated response

[0684] The server references the FAQ database based on analysis results and sentiment recognition results to generate the most appropriate answer. For example, if an FAQ about "how to return a product" exists in the database, it will generate an automated response based on that information. If the sentiment engine determines that the user is "confused," a more helpful and easy-to-understand response will be generated. The input is the FAQ database and sentiment recognition results, and the output is an automated response message.

[0685] Step 5: Escalation

[0686] If the automated response is insufficient, the server re-evaluates the inquiry and routes it to the appropriate person or department. For example, if the process is complex and cannot be resolved through FAQs, the server escalates the inquiry to the customer support department. In this process, the person in charge is notified of the inquiry and its status. The input is the inquiry and the result of the automated response suitability evaluation, and the output is the contact person to whom the inquiry has been escalated.

[0687] Step 6: Record and share the history of interactions

[0688] The server records all inquiries and their responses in a database. This database is accessible to all operators and is used to provide fast and consistent service based on past response history. For example, if a similar inquiry has occurred in the past, the response time can be reduced by referring to that history. Inputs include inquiry content, response content, and escalation history, while output is the recorded response history data.

[0689] (Application Example 2)

[0690] 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."

[0691] Traditional inquiry management systems struggle to centrally manage inquiries received from various channels, and in particular, they have difficulty providing appropriate responses tailored to the user's emotional state. Furthermore, they lack adequate mechanisms for analyzing inquiry content, generating automated responses, and then routing inquiries to the appropriate personnel if the automated responses are insufficient. This results in problems such as a reduced user experience and increased response times.

[0692] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0693] In this invention, the server includes means for receiving inquiries from various channels, means for analyzing the received inquiries using natural language processing, means for proposing an automated response based on the analysis results, means for recognizing the user's emotions and generating an appropriate automated response based on the results, means for routing inquiries to the appropriate person in charge if the automated response is insufficient, and means for recording and sharing the inquiry handling history. This enables centralized management of inquiries from various channels and allows for the rapid provision of more appropriate responses by incorporating emotion recognition technology.

[0694] "Means of receiving inquiries from diverse channels" refers to a system for receiving inquiries from different communication methods such as email, telephone, chatbots, and smartphone applications.

[0695] "Analysis means for natural language processing received inquiries" refers to the process of converting the received inquiry content into text data, analyzing the content using natural language processing techniques, and extracting key keywords and intents.

[0696] "Means for proposing automated responses based on analysis results" refers to a system that automatically generates and proposes appropriate responses based on the analyzed inquiry content and the results of sentiment recognition.

[0697] "Means for recognizing user emotions and generating appropriate automated responses based on the results" refers to a technology that uses an emotion engine to identify the user's emotional state and generates the optimal response accordingly.

[0698] "A means of routing inquiries to the appropriate person when automated responses are insufficient" refers to a function that re-evaluates inquiries that cannot be resolved by automated responses and routes them to the appropriate person or department with the necessary expertise.

[0699] "Means for recording and sharing inquiry response history" refers to a system that stores all inquiries and their responses in a database and shares them in a way that all operators can access.

[0700] An "emotion engine" is a technology that analyzes a user's emotional state from text and audio data, recognizing and classifying emotions such as positive, negative, and neutral.

[0701] A "smartphone application" is software that runs on a smartphone or tablet and interacts directly with the user through an interface.

[0702] This invention relates to an inquiry management system that centrally manages inquiries received by a company from various channels, and performs automated responses, escalation, and sentiment recognition using an sentiment engine. Specific embodiments for carrying out this invention are described below.

[0703] System Overview

[0704] This system has the following main features:

[0705] 1. Receiving an inquiry:

[0706] The server receives user inquiries through various channels, including email, telephone, chatbots, and smartphone applications.

[0707] 2. Analysis of the inquiry content:

[0708] The server extracts the received inquiry content as text data, analyzes it using natural language processing techniques, and extracts key keywords and intent.

[0709] 3. Emotion recognition:

[0710] The server uses an emotion engine to recognize the user's emotions from text and audio data, and reflects that emotional state in the analysis results.

[0711] 4. Generating automated responses:

[0712] Based on the analysis results and emotion recognition results, the server refers to the FAQ database to generate an appropriate automated response and provides it to the user. The response is expressed in a friendly manner that matches the user's emotional state.

[0713] 5. Escalation:

[0714] If the automated response is insufficient, the server will re-evaluate the inquiry and route it to the appropriate person or department.

[0715] 6. Recording and sharing of interaction history:

[0716] The server records all inquiry handling history in a database, making it accessible to all operators.

[0717] Hardware and software to be used

[0718] 1. Hardware:

[0719] Smartphones, tablets, and servers (including multiple servers for running the inquiry management system).

[0720] 2. Software:

[0721] Python programming language, TextBlob library for sentiment analysis, FAQ database, and libraries for natural language processing.

[0722] Specific example

[0723] For example, if a user makes a request through a smartphone application saying, "I'm tired today, so I'd like to listen to some relaxing music," the server receives the request and extracts it as text data. Then, using natural language processing technology, the request is analyzed, and the main keywords "relax" and "music" are extracted. Furthermore, an emotion engine is used to recognize the user's emotional state of being "tired." Based on this information, the server automatically generates and provides a "relaxing music playlist."

[0724] Example of a prompt

[0725] If a user inputs "Please recommend some relaxing music," an example of the input prompt text for the generating AI model would be as follows:

[0726] "Users are looking for relaxation. Please suggest some relaxing music."

[0727] Thus, the present invention centrally manages inquiries from various channels and incorporates emotion recognition technology to quickly provide appropriate automated responses tailored to the user's emotional state. This reduces the workload of operators while improving user satisfaction.

[0728] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0729] Step 1:

[0730] Inquiry received

[0731] Users input and submit their inquiries via smartphones, email, phone, chatbots, etc. The server receives inquiries from these various channels. The input data may be in text or audio format. For example, a user might send "I want to listen to relaxing music" via a smartphone application.

[0732] Step 2:

[0733] Extraction of inquiry content

[0734] The server extracts the received query content as text data. This process also includes converting audio data to text. If audio data is present, it is converted to text format and passed on to the next step.

[0735] Step 3:

[0736] Analysis using natural language processing

[0737] The server analyzes text data using natural language processing techniques. Specifically, it analyzes the text data to extract key keywords and intent. For example, the keywords "relax" and "music" might be extracted. The input is text data, and the output is the analyzed keyword data.

[0738] Step 4:

[0739] emotion recognition

[0740] The server uses an emotion engine to recognize the user's emotions from text data. Here, it classifies and identifies emotions as positive, negative, or neutral. For example, it might recognize the negative emotion "tired" from the user's text. The input is keyword data, and the output is the user's emotional state.

[0741] Step 5:

[0742] Generating an automated response

[0743] The server generates an appropriate automated response by referencing the FAQ database and pre-configured response patterns based on the analysis results and emotion recognition results. For example, it might generate a response offering a "relaxing music playlist." The input is keyword data and emotion state, and the output is the generated automated response.

[0744] Step 6:

[0745] Judgment and handling of escalation

[0746] The server evaluates the generated automated response, and if it determines the response is insufficient, it routes the inquiry to the appropriate person or department. For example, complex requests are escalated to specialized support staff. The input is the automated response, and the output is the escalated inquiry.

[0747] Step 7:

[0748] Providing a response

[0749] The server sends a generated automated response to the user. The user receives the response through a smartphone application or the channel used. For example, a generated playlist is provided to the user. The input is the generated response, and the output is the response sent to the user.

[0750] Step 8:

[0751] Recording and sharing of inquiry response history

[0752] The server records all inquiries and their responses in a database. This record is accessible to all operators and is used as reference material to ensure consistent responses. Input is the response content, and output is the record stored in the database.

[0753] 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.

[0754] 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.

[0755] 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.

[0756] [Third Embodiment]

[0757] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0758] 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.

[0759] 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).

[0760] 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.

[0761] 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.

[0762] 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).

[0763] 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.

[0764] 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.

[0765] 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.

[0766] 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.

[0767] 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.

[0768] 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".

[0769] This invention relates to an inquiry management system that centrally manages inquiries received by a company from various channels and performs automated responses and escalations. Specific embodiments for carrying out this invention are described below.

[0770] This system receives inquiries from various channels, analyzes their content, and provides automated responses. Furthermore, if the automated response is insufficient, it routes the inquiry to the appropriate person in charge. In addition, inquiry handling history is recorded in a database and shared among operators to prevent duplicate responses and reduce workload.

[0771] System Overview

[0772] 1. Receiving an inquiry

[0773] The server receives user inquiries through multiple channels, including email, phone, and chatbots.

[0774] 2. Analysis of the inquiry content

[0775] The server extracts the received query content as text data and analyzes it using natural language processing techniques.

[0776] 3. Generating automated responses

[0777] Based on the analysis results, the server refers to the FAQ database to generate an appropriate automated response and provides it to the user.

[0778] 4. Escalation

[0779] If the server's automated response is insufficient, it will forward the inquiry to the appropriate person in charge.

[0780] 5. Recording and sharing of support history

[0781] The server records all inquiry handling history in a database, making it accessible to all operators.

[0782] Detailed processing flow

[0783] Inquiry received

[0784] The server receives user inquiries through multiple channels, such as email, phone, and chatbot. For example, if a user sends an email asking "How do I return a product?", the server will receive that email.

[0785] Analysis of inquiry content

[0786] The server converts the received inquiry into text data format. Next, this inquiry is analyzed using natural language processing techniques to extract key keywords and intent. Here, key keywords such as "return" and "method" are extracted.

[0787] Generating an automated response

[0788] The server searches the FAQ database based on the extracted keywords to find the most suitable answer. For example, if an FAQ exists regarding "how to return a product," it generates an automated response based on that answer. This automated response is then provided to the user.

[0789] escalation

[0790] If the automated response is insufficient, the server re-evaluates the inquiry and routes it to the appropriate person or department. For example, if an inquiry concerns complex return conditions or a specific case, the server will forward the information to the relevant customer support department.

[0791] Recording and sharing of support history

[0792] The server records all inquiries and their responses in a database. This database is accessible to all operators, enabling quick and consistent responses by referring to past inquiry history.

[0793] Specific example

[0794] For example, if a user sends an email inquiry asking "How do I return a product?", this inquiry is received by the server. The server extracts the inquiry as text data and uses natural language processing technology to extract the keywords "return" and "method". The server then searches the FAQ database for answers regarding "how to return a product," generates an automated response, and sends it back to the user. If the user inquires about more detailed conditions, the information is forwarded to the appropriate department, and the response history is recorded and shared in the database.

[0795] In this way, this system centrally manages inquiries from various channels and provides appropriate responses quickly, thereby reducing the workload of operators while improving customer satisfaction.

[0796] The following describes the processing flow.

[0797] Step 1:

[0798] The server receives user inquiries through various channels, including email, telephone, and chatbots. For email, the server checks for new emails from the mail server using the IMAP protocol. For chatbots, the server receives new messages via WebSocket. For telephone calls, the server obtains incoming call information using SIP (Session Initiation Protocol).

[0799] Step 2:

[0800] The server extracts the received inquiry content as text data. Text is extracted from the body of emails and chat messages, and in the case of telephone inquiries, a speech recognition system is used to convert the speech into text.

[0801] Step 3:

[0802] The server extracts text data and passes it to a natural language processing engine for semantic analysis and keyword extraction of the query. Specifically, the server sends text data to a natural language processing API for keyword and intent analysis.

[0803] Step 4:

[0804] The server searches the FAQ database based on the analysis results. It queries the FAQ database based on keywords and phrases to retrieve the most relevant answers.

[0805] Step 5:

[0806] The server generates an automated response based on the answers it receives. The generated automated response is converted to an adaptive format and organized into a format that is provided to the user.

[0807] Step 6:

[0808] The server sends an automated response to the user. In the case of email, the server sends the reply email using the SMTP protocol. In the case of a chatbot, the server sends the message using WebSocket.

[0809] Step 7:

[0810] If the server's automated response is insufficient, it will determine whether to escalate the inquiry to a responsible person. Based on the analysis results, an escalation flag will be set, and the appropriate person or department will be determined.

[0811] Step 8:

[0812] The server routes the inquiry to the appropriate person. Based on the content and category of the escalated inquiry, it refers to a list of tasks that the person can handle. Once a suitable person is determined, a notification is sent.

[0813] Step 9:

[0814] The server records all inquiries and their responses in a database. Detailed information, including inquiry content, automated responses, and the actions taken by the assigned staff member in case of escalation, is stored in the database.

[0815] Step 10:

[0816] The server sends a survey form or rating template to the user to collect feedback after handling their inquiry. The collected feedback information is stored in a database and analyzed to help improve the quality of service.

[0817] (Example 1)

[0818] 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."

[0819] In modern society, it is crucial for companies to efficiently and quickly handle inquiries received from various channels. However, if automated responses are insufficient or if the sharing of response history is not done properly, customer satisfaction may decline and the burden on operators may increase. To solve these problems, a system is needed that accurately analyzes inquiry content, provides appropriate responses, and efficiently manages and shares response history.

[0820] 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.

[0821] In this invention, the server includes means for receiving inquiries from various channels, means for analyzing the received inquiries using natural language processing, means for generating automatic responses based on the analysis results, means for routing inquiries to appropriate personnel if the automatic response is insufficient, means for recording and sharing inquiry handling history, means for evaluating and escalating inquiry content, means for analyzing inquiry content using a natural language processing library, means including an evaluation algorithm for evaluating the effectiveness of automatic responses, and means for providing a management screen and making the inquiry history accessible. This enables centralized management of inquiries from various channels, prompt provision of appropriate responses, reduction of operator workload, and improvement of customer satisfaction.

[0822] An "inquiry" refers to information that a user sends to a company to request information or support.

[0823] A "channel" refers to the medium or method that a user uses to send an inquiry to a company.

[0824] A "server" refers to a computer system that receives, analyzes, generates automated responses to, escalates, and records and shares response history.

[0825] "Natural language processing" refers to the technology that enables computers to understand and process human language.

[0826] "Automated response" refers to a system where a computer automatically generates and provides answers based on the content of an inquiry.

[0827] "Escalation" refers to the process of transferring an inquiry to a human representative when the automated response is insufficient or inappropriate.

[0828] "Analysis" refers to the process of understanding the content of an inquiry using natural language processing technology and extracting important keywords and intents.

[0829] An "FAQ database" refers to a database that compiles frequently asked questions and their answers.

[0830] A "database" refers to a system for organizing and storing digital information.

[0831] An "evaluation algorithm" refers to a mathematical method used to assess the effectiveness of automated responses.

[0832] The term "administration screen" refers to an interface used by operators to manage the system and view inquiry history.

[0833] This invention relates to an inquiry management system that centrally manages inquiries received by a company from various channels and performs automated responses and escalations. Specific embodiments for carrying out this invention are described below.

[0834] This system operates server-centric, receiving inquiries from various channels, analyzing their content, and providing automated responses. Furthermore, if the automated response is insufficient, it routes the inquiry to the appropriate person. In addition, inquiry handling history is recorded in a database and shared among operators to prevent duplicate responses and reduce workload.

[0835] Hardware and software to be used

[0836] The server is the main component and uses the following hardware and software:

[0837] Hardware: Server machines, database servers

[0838] Software: Email receiving servers (e.g., SMTP servers), natural language processing libraries (e.g., spaCy, NLTK), database management systems (e.g., MySQL, PostgreSQL), web application frameworks for administration panels (e.g., Django, Flask)

[0839] System Overview

[0840] This system has the following functions:

[0841] 1. Receiving inquiries: The server receives inquiries from users through multiple channels, such as email, telephone, and chatbots.

[0842] 2. Analysis of the inquiry content: The server extracts the received inquiry content as text data and analyzes it using natural language processing technology.

[0843] 3. Generation of automated responses: Based on the analysis results, the server generates an appropriate automated response by referring to the FAQ database and provides it to the user.

[0844] 4. Escalation: If the server's automated response is insufficient, it will forward the inquiry to the appropriate person in charge.

[0845] 5. Recording and sharing of response history: The server records all inquiry response history in a database and makes it accessible to all operators.

[0846] Specific examples of receiving inquiries

[0847] A user sends an email message saying, "Please tell me how to return an item." The server receives this message via the email receiving server and stores it in the inquiry database.

[0848] Specific examples of analyzing inquiry content

[0849] The server extracts the body of the received email as text data and uses a natural language processing library to identify the keywords "return" and "method." The server then uses these keywords to understand the user's intent.

[0850] Specific examples of automated response generation

[0851] The server queries the FAQ database to retrieve answers regarding "how to return a product." Then, based on the retrieved answers, the server generates an automated response message, which is sent to the user, for example, via email.

[0852] Specific examples of escalation

[0853] If the automated response is insufficient, the server will receive a reply from the user stating that they would like to know more specific return conditions. In this case, the server will re-analyze the inquiry and escalate it to the appropriate person in charge.

[0854] Examples of recording and sharing support history

[0855] The server stores all inquiries and their responses in a database. Furthermore, all operators can access past inquiry history through a web-based management screen. For example, an operator can log into the management screen and search for past inquiries related to "returns."

[0856] Example of a prompt

[0857] The following is an example of an input prompt statement for a specific generative AI model:

[0858] "We have an inquiry regarding the return process for a product. Please extract keywords to generate an automated response."

[0859] "If the automated response is insufficient, please escalate the issue to the appropriate person."

[0860] Thus, this system provides a set of functions to efficiently and effectively process inquiries and improve customer satisfaction.

[0861] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0862] Step 1:

[0863] Inquiry received

[0864] The server receives user inquiries through multiple channels, such as email, phone, and chatbot. For example, if a user sends an email asking "How do I return this item?", the server's email receiving server receives the email. In this case, the input is the user's inquiry message, and the output is the received inquiry data.

[0865] Specific actions:

[0866] The server receives emails via an email receiving server (e.g., an SMTP server).

[0867] The received message is saved to the query database.

[0868] Step 2:

[0869] Analysis of inquiry content

[0870] The server extracts the received query content as text data and analyzes it using natural language processing techniques. The input is the received query data, and the output is the analyzed keywords and intent.

[0871] Specific actions:

[0872] The server extracts the body of the received message as text data.

[0873] We use natural language processing libraries (e.g., spaCy, NLTK) to extract key keywords and intent. For example, we identify the keywords "return" and "method".

[0874] Step 3:

[0875] Generating an automated response

[0876] The server generates an appropriate automated response based on the analysis results, referencing the FAQ database, and provides it to the user. The input in this process consists of the analyzed keywords and intent, while the output is the generated automated response message.

[0877] Specific actions:

[0878] The server searches the FAQ database based on the analyzed keywords.

[0879] Retrieve relevant answers and generate automated response messages. For example, generate an automated response based on FAQ answers regarding "how to return a product."

[0880] The generated automated response message is provided to the user via email or other means.

[0881] Step 4:

[0882] escalation

[0883] If the automated response is insufficient, the server will forward the inquiry to the appropriate person in charge. The input at this time is the user's follow-up inquiry or feedback on the automated response, and the output is the inquiry data that will be passed on to the person in charge.

[0884] Specific actions:

[0885] The server runs an evaluation algorithm to assess the effectiveness of the automated response. For example, if the user makes another inquiry or if the user's feedback is negative, the server may determine that the automated response was insufficient.

[0886] Analyze the inquiry and forward it to the appropriate person in charge. Send a notification to the person in charge.

[0887] Step 5:

[0888] Recording and sharing of support history

[0889] The server records all inquiry handling history in a database, making it accessible to all operators. The input consists of processed inquiry data and its response result, while the output is the recorded handling history.

[0890] Specific actions:

[0891] The server saves each query, its response, and the escalation details to a database management system (e.g., MySQL, PostgreSQL).

[0892] The server provides an administration screen for operators, allowing them to view past inquiry history. Operators log in to the administration screen and search and display history using specific keywords or dates.

[0893] Step 6:

[0894] Evaluation of the effectiveness of automated responses

[0895] The server continuously evaluates the effectiveness of the generated automated responses and uses this as a criterion for escalation decisions. The inputs at this stage are user feedback and follow-up query data regarding the generated automated responses, while the output is the escalation decision result and the improved automated response message.

[0896] Specific actions:

[0897] The server collects user feedback data and information on whether or not the user has made a follow-up inquiry.

[0898] The evaluation algorithm is executed to assess the effectiveness of the automated response.

[0899] If escalation is deemed necessary, the inquiry will be re-analyzed and handed over to the appropriate person.

[0900] (Application Example 1)

[0901] 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."

[0902] In recent years, with the spread of online shopping, the importance of customer support in virtual stores has increased. However, customer inquiries come from a variety of channels, which can lead to a loss of consistency and speed in responses. Furthermore, if appropriate automated responses are not provided, escalation becomes necessary, and efficient inquiry management is required. This invention aims to solve these problems by providing a system that can respond to customer inquiries quickly and consistently in virtual stores.

[0903] 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.

[0904] In this invention, the server includes means for receiving inquiries from various channels, means for analyzing the received inquiries using natural language processing, means for proposing an automated response based on the analysis results, means for routing inquiries to the appropriate person in case the automated response is insufficient, means for recording and sharing the inquiry handling history, means for receiving and analyzing user inquiries in real time within the virtual store, and means for creating an appropriate automated response using a generative AI model. This enables a rapid and consistent response to customer inquiries within the virtual store, and is expected to improve the efficiency of customer support and enhance customer satisfaction.

[0905] "Means of receiving inquiries from diverse channels" refers to a system for receiving customer inquiries through multiple communication methods, such as email, telephone, chatbots, and in-virtual store chats.

[0906] "Analysis means for natural language processing received inquiries" refers to a function that uses natural language processing technology to analyze the content of inquiries as text data and extract key keywords and intents.

[0907] "Means of proposing automated responses based on analysis results" refers to a function that generates the optimal automated response by referring to an appropriate FAQ database based on the analyzed keywords and intent.

[0908] "Means for routing inquiries to the appropriate person in case of insufficient automated responses" refers to a function that forwards inquiries to the appropriate person or department when the generated automated response is inadequate to the customer's inquiry.

[0909] "Means for recording and sharing inquiry response history" refers to a function that records all inquiries and their responses in a database, making this information accessible to all operators, thereby sharing past response history and preventing duplicate responses.

[0910] "A means of receiving and analyzing user inquiries in real time within a virtual store" refers to a function that receives inquiries made by users within a virtual store in real time, analyzes their content immediately, and responds to them promptly.

[0911] "Means for creating appropriate automated responses using a generative AI model" refers to a function that uses an AI model to generate the optimal automated response based on the analyzed inquiry content and provide it to the user.

[0912] This invention provides a system for centrally managing inquiries from various channels in a virtual store and enabling automated responses and escalation. The system includes a series of processes for receiving inquiries, analyzing them, generating responses, and escalating them as necessary.

[0913] System Configuration

[0914] This system is implemented using the following main components:

[0915] 1. Inquiry receiving server

[0916] Inquiries are received through multiple channels, including email, phone, chatbots, and in-virtual store chats. Received inquiries are converted into a format that can be processed as text data.

[0917] 2. Natural Language Processing (NLP) Analysis Module

[0918] This module analyzes received inquiries and extracts key keywords and intents. Specifically, it extracts important keywords through text analysis using natural language processing techniques.

[0919] 3. Generating AI Module

[0920] Based on the analyzed keywords, the system consults the FAQ database and generates an appropriate automated response. The generated response is then sent to the user.

[0921] 4. Escalation Module

[0922] If the automated response is insufficient, this module will re-evaluate the inquiry and route it to the appropriate person or department.

[0923] 5. Inquiry Response History Database

[0924] This is a database that records all inquiries and their responses. All operators can access this database, enabling consistent responses by referring to past inquiry history.

[0925] System processing flow

[0926] When a user submits an inquiry within the virtual store, the inquiry is received by a receiving server. The receiving server processes the inquiry as text data and forwards it to an NLP analysis module. The NLP analysis module extracts the main keywords of the inquiry and passes them on to a generation AI module. The generation AI module selects the most appropriate answer from the FAQ database and generates a response. If the generated response is insufficient, an escalation module routes the inquiry to the appropriate person or department. All inquiries and their responses are recorded in an inquiry response history database and used for future inquiry handling.

[0927] Technologies used and specific examples

[0928] Hardware: Servers, cloud storage

[0929] Software: AIChatbot, TextAnalyzer, DatabaseConnector, FAQ

[0930] For example, if a user sends a chat message in a virtual store asking "How do I return an item?", this inquiry is received by the receiving server. TextAnalyzer extracts the keywords "return" and "how," and uses a generative AI model to search for FAQs related to "how to return an item." As a result, an appropriate automated response is provided to the user.

[0931] Example of a prompt

[0932] "Please tell me how to return an item."

[0933] "I'd like to know the reason for the delivery delay."

[0934] "I would like to change the size of the product."

[0935] "I have a question about a specific product."

[0936] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0937] Step 1:

[0938] Users make inquiries within the virtual store. For example, a user might use the chat function to send a message saying, "How do I return an item?" This message becomes input into the system.

[0939] Step 2:

[0940] The server receives inquiries from users. The processing flow involves receiving inquiries via various channels such as email, telephone, chatbot, and in-virtual store chat, and converting them into text data format. The received inquiry text becomes the input for the next step.

[0941] Step 3:

[0942] The server's natural language processing (NLP) analysis module analyzes the received query. In this step, TextAnalyzer is used to extract key keywords and intent from the text data. For example, keywords such as "return" and "method" are extracted. The extracted keywords become the input for the next step.

[0943] Step 4:

[0944] The server's generation AI module generates an automated response based on keywords from the NLP analysis module. In this step, the generation AI model is used to search for appropriate answers in the FAQ database and create a response message using natural language generation technology. For example, it retrieves an answer regarding "how to return a product" from the FAQ and generates a response such as "Details on how to return a product are as follows:...". The generated automated response becomes the input for the next step.

[0945] Step 5:

[0946] The server sends an automated response to the user. The response message is then sent to the user's chat. The user receives the automated response and obtains a solution to their inquiry. This response serves as input for the next step.

[0947] Step 6:

[0948] If the server's automated response is insufficient, it forwards the inquiry to the escalation module. The escalation module re-evaluates the generated automated response if it determines that the automated response is insufficient based on certain criteria, and routes the inquiry to the appropriate person or department. For example, if an exception to the return procedure is required, it will be forwarded to the customer support team. The assigned person's information becomes the input for the next step.

[0949] Step 7:

[0950] The server's inquiry response history database module records all inquiries and their responses in the database. This includes the inquiry reception time, content, analysis results, automated response content, and escalation history. This allows operators to refer to past inquiry history. The recorded data is used for future inquiry handling.

[0951] The above are the specific processing steps.

[0952] 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.

[0953] This invention relates to an inquiry management system that centrally manages inquiries received by a company from various channels, and performs automated responses, escalation, and sentiment recognition using an emotion engine. Specific embodiments for carrying out this invention are described below.

[0954] This system receives user inquiries from various channels, analyzes their content, and uses an emotion engine to recognize the user's emotions, providing appropriate responses based on those emotions. If the automated response is insufficient, it forwards the inquiry to the appropriate person in charge. Inquiry handling history is also recorded in a database and can be shared among operators.

[0955] System Overview

[0956] 1. Receiving an inquiry

[0957] The server receives user inquiries through various channels, including email, phone, and chatbots.

[0958] 2. Analysis of the inquiry content

[0959] The server extracts the received query content as text data and analyzes it using natural language processing techniques.

[0960] 3. Emotion recognition

[0961] The server uses an emotion engine to recognize the user's emotions from text and audio data and reflects them in the analysis results.

[0962] 4. Generating automated responses

[0963] The server generates an appropriate automated response based on the analysis results and sentiment recognition results, referencing the FAQ database, and provides it to the user.

[0964] 5. Escalation

[0965] If the server's automated response is insufficient, it will forward the inquiry to the appropriate person in charge.

[0966] 6. Recording and sharing of support history

[0967] The server records all inquiry handling history in a database, making it accessible to all operators.

[0968] Detailed processing flow

[0969] Inquiry received

[0970] The server receives user inquiries through various channels such as email, phone, and chatbots. For example, if a user sends an email asking "How do I return a product?", the server will receive that email.

[0971] Analysis of inquiry content

[0972] The server converts the received inquiry into text data format. Next, this inquiry is analyzed using natural language processing techniques to extract key keywords and intent. Here, key keywords such as "return" and "method" are extracted.

[0973] emotion recognition

[0974] The server uses an emotion engine to recognize user emotions from text and audio data. For example, it analyzes the user's emotions, such as "angry" or "troubled," from text and recognizes their emotional state. The recognition results are fed back to the analysis system and used to adjust the response.

[0975] Generating an automated response

[0976] The server searches the FAQ database based on the analysis results and sentiment recognition results to find the most appropriate answer. For example, if there is an FAQ about "how to return a product," it generates an automated response based on the content of that FAQ. This automated response is then provided to the user. For example, if the user is in a state of "anxiety," a more helpful response will be generated.

[0977] escalation

[0978] If the automated response is insufficient, the server re-evaluates the inquiry and routes it to the appropriate person or department. For example, if an inquiry concerns complex return conditions or a specific case, the server will forward the information to the relevant customer support department.

[0979] Recording and sharing of support history

[0980] The server records all inquiries and their responses in a database. This database is accessible to all operators, enabling quick and consistent responses by referring to past inquiry history.

[0981] Specific example

[0982] For example, if a user sends an email inquiry asking "How do I return a product?", the server receives the inquiry. The server analyzes the content using natural language processing and recognizes the user's emotions using an emotion engine. As a result of the analysis, keywords such as "return" and "how" are extracted, and the emotion engine detects that the user is "confused." Based on this information, the server generates a more helpful automated response and sends it back to the user. If necessary, the server escalates the inquiry to a specialist and records the entire response history in a database to ensure consistent service.

[0983] In this way, this system centrally manages inquiries from various channels and incorporates sentiment recognition technology to provide more appropriate responses quickly. This makes it possible to reduce the workload of operators while improving customer satisfaction.

[0984] The following describes the processing flow.

[0985] Step 1:

[0986] The server receives user inquiries through various channels, including email, telephone, and chatbots. For email, the server retrieves new emails from the mail server using the IMAP protocol. For chatbots, the server receives new messages via WebSocket. For telephone calls, the server retrieves incoming call information using the SIP protocol.

[0987] Step 2:

[0988] The server extracts the content of the received inquiry as text data. For emails and chat messages, text is extracted from the body, and for phone calls, a speech recognition system is used to convert the speech into text.

[0989] Step 3:

[0990] The server extracts text data and passes it to a natural language processing engine for semantic analysis and keyword extraction of the query. Specifically, the server sends text data to a natural language processing API, and keywords and intent are obtained as analysis results.

[0991] Step 4:

[0992] The server passes text data to the emotion engine to analyze the user's emotions. The emotion engine performs the analysis and detects emotions such as "joy," "anger," and "sadness." The detected emotion data is returned to the server and fed back into the analysis system.

[0993] Step 5:

[0994] The server searches the FAQ database based on the analysis results and sentiment recognition results. The server retrieves the most relevant answers from the FAQ database based on keywords and detected sentiments.

[0995] Step 6:

[0996] The server generates an automated response based on answers retrieved from the FAQ database, and adjusts the response content while also taking into account the emotion recognition results. For example, if the server detects that the user is "angry," it generates a response that includes an apology. This response is then formatted appropriately and sent to the user.

[0997] Step 7:

[0998] The server sends an automated response to the user. If it's email, the server sends the reply using the SMTP protocol. If it's a chatbot, the server sends the message using WebSocket.

[0999] Step 8:

[1000] If the server determines that its automated response is insufficient, it will escalate the inquiry to a relevant person. Based on the analysis results and sentiment recognition results, the appropriate person or department will be selected, an escalation flag will be set, and a notification will be sent.

[1001] Step 9:

[1002] The server routes the inquiry to the appropriate person in charge. The escalated inquiry is compared to a list of tasks that the person in charge can handle, and a notification is sent once a suitable person is determined.

[1003] Step 10:

[1004] The server records all inquiries and their responses in a database. Detailed information such as the inquiry content, automated responses, the actions taken by the assigned staff during escalation, and the user's emotional state are stored in the database.

[1005] Step 11:

[1006] After handling an inquiry, the server sends a survey form or rating template to the user to collect feedback. The collected feedback information is stored in a database and used to improve the quality of future support.

[1007] (Example 2)

[1008] 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."

[1009] A key challenge for companies is to centrally manage inquiries received from various channels and respond quickly and appropriately. In particular, accurately recognizing user emotions and generating responses based on them is crucial for improving customer satisfaction, and it is also necessary to quickly escalate issues to the appropriate personnel when automated responses are insufficient.

[1010] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving inquiries from various channels, means for analyzing the received inquiries using natural language processing technology, means for generating an automated response based on the analysis results and sentiment recognition by the sentiment engine, means for routing inquiries to the appropriate person in charge if the automated response is insufficient, and means for recording and sharing the inquiry handling history. This enables companies to centrally manage inquiries from various channels and quickly provide appropriate responses that take into account the user's emotions.

[1011] An "inquiry" is a question or request that a user sends to a company or organization to seek information.

[1012] A "channel" refers to a means of communication used for sending and receiving inquiries and information, and specifically includes email, telephone, and chatbots.

[1013] "Natural language processing technology" is the technology that understands, interprets, and generates human language on a computer.

[1014] "Analysis means" refers to the techniques and methods used to analyze received inquiries and understand their content and intent.

[1015] An "emotion engine" is a system or technology that recognizes a user's emotional state from text data or audio data.

[1016] "Automatic response" refers to a function in which a system automatically provides pre-set answers to user inquiries.

[1017] An "FAQ database" is a database that compiles frequently asked questions and their answers.

[1018] "Escalation" is the process of transferring an inquiry to the appropriate person or department when the initial response is insufficient.

[1019] A "person in charge" refers to the individual or department responsible for handling an escalated inquiry.

[1020] "Response history" refers to data that records each inquiry and the details of the response to it.

[1021] "Sharing methods" refer to systems or methods that enable multiple operators or staff members to view and use the service history.

[1022] This invention relates to an inquiry management system that centrally manages inquiries received by a company from various channels, and performs automated responses, escalation, and sentiment recognition. This system receives user inquiries from various channels, analyzes their content, recognizes the user's emotions using a sentiment engine, and provides an appropriate response based on that. Furthermore, if the automated response is insufficient, it routes the inquiry to the appropriate person. Inquiry handling history is also recorded in a database and can be shared among operators.

[1023] Specifically, the system is configured as follows:

[1024] Inquiry received

[1025] The server receives user inquiries through various channels, including email, phone, and chatbots. This receiving process includes capturing voice data and parsing text messages. For example, if a user types "How do I return this item?" into the chatbot, the server receives the message immediately.

[1026] Analysis of inquiry content

[1027] The server converts the received inquiry into text data. For voice input, speech recognition technology is used for this purpose. Next, the server analyzes the inquiry using a natural language processing (NLP) engine to extract key keywords and context. For example, keywords such as "return" and "method" are identified.

[1028] emotion recognition

[1029] The server uses an emotion engine to recognize the user's emotions from text and audio data. For example, an NLP engine analyzes emotions such as "confused" or "angry." The results of the emotion recognition are fed back into the analysis results and used to adjust the response.

[1030] Generating an automated response

[1031] The server uses the analysis results and sentiment recognition results to refer to the FAQ database and generate the most appropriate answer. For example, if an FAQ about "how to return a product" exists in the database, the server will generate an automated response based on that information. If the sentiment engine recognizes that the user is "confused," the server will generate a response using more helpful and polite language.

[1032] escalation

[1033] If the automated response is insufficient, the server re-evaluates the inquiry and routes it to the appropriate person or department. For example, if the process is complex and cannot be handled by the FAQ, the server escalates the matter to the customer support department. This ensures that the right person can respond quickly.

[1034] Recording and sharing of support history

[1035] The server records all inquiries and their responses in a database. This database is accessible to all operators, enabling them to provide fast and consistent service based on past response history.

[1036] Specific example

[1037] For example, if a user sends an email inquiry asking "How do I return a product?", the server receives the email. The server analyzes the email content using natural language processing technology and extracts the main keywords "return" and "how to return". At the same time, the sentiment engine recognizes that the user is "confused". Based on the analysis results and sentiment state, the server generates an automated response in a friendly tone and sends it back to the user. If necessary, the server escalates the inquiry to a specialist and records the entire response history in a database for future reference.

[1038] Example of a prompt

[1039] The following is an example of how inputting the following prompt into the AI ​​model can produce an appropriate response:

[1040] "A user is confused about how to return a product. How can we automatically generate a helpful response in this case?"

[1041] "A user contacted us via chatbot regarding a product return, but the emotion engine detected anger. What is the appropriate response in this case?"

[1042] In this way, this system centrally manages inquiries from various channels and incorporates sentiment recognition technology to provide more appropriate responses quickly. This makes it possible to reduce operator workload while improving customer satisfaction.

[1043] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1044] Step 1: Receiving an inquiry

[1045] The server receives user inquiries through various channels, such as email, phone, and chatbots. For example, if a user enters "How do I return a product?" into the chatbot, that message is sent to the server. The server then internally records the received message in its data store. The input is the inquiry content, and the output is the received inquiry data.

[1046] Step 2: Analyzing the inquiry content

[1047] The server converts the received inquiry into text data format. In the case of voice input, the server uses speech recognition technology. For example, if a user makes an inquiry by phone, the server converts the voice data into text and then analyzes that text data. Next, the server uses a natural language processing (NLP) engine to analyze the inquiry and extract key keywords and context. For example, keywords such as "return" and "method" are identified. The input is text data or voice data, and the output is the analyzed keyword and context data.

[1048] Step 3: Emotion Recognition

[1049] The server uses an emotion engine to recognize the user's emotions from text and audio data. For example, the NLP engine can detect emotions such as "confused" or "angry" from the user's message. This information is then fed back into subsequent response generation. The input is the parsed text data, and the output is the emotion recognition result.

[1050] Step 4: Generating an automated response

[1051] The server references the FAQ database based on analysis results and sentiment recognition results to generate the most appropriate answer. For example, if an FAQ about "how to return a product" exists in the database, it will generate an automated response based on that information. If the sentiment engine determines that the user is "confused," a more helpful and easy-to-understand response will be generated. The input is the FAQ database and sentiment recognition results, and the output is an automated response message.

[1052] Step 5: Escalation

[1053] If the automated response is insufficient, the server re-evaluates the inquiry and routes it to the appropriate person or department. For example, if the process is complex and cannot be resolved through FAQs, the server escalates the inquiry to the customer support department. In this process, the person in charge is notified of the inquiry and its status. The input is the inquiry and the result of the automated response suitability evaluation, and the output is the contact person to whom the inquiry has been escalated.

[1054] Step 6: Record and share the history of interactions

[1055] The server records all inquiries and their responses in a database. This database is accessible to all operators and is used to provide fast and consistent service based on past response history. For example, if a similar inquiry has occurred in the past, the response time can be reduced by referring to that history. Inputs include inquiry content, response content, and escalation history, while output is the recorded response history data.

[1056] (Application Example 2)

[1057] 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."

[1058] Traditional inquiry management systems struggle to centrally manage inquiries received from various channels, and in particular, they have difficulty providing appropriate responses tailored to the user's emotional state. Furthermore, they lack adequate mechanisms for analyzing inquiry content, generating automated responses, and then routing inquiries to the appropriate personnel if the automated responses are insufficient. This results in problems such as a reduced user experience and increased response times.

[1059] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1060] In this invention, the server includes means for receiving inquiries from various channels, means for analyzing the received inquiries using natural language processing, means for proposing an automated response based on the analysis results, means for recognizing the user's emotions and generating an appropriate automated response based on the results, means for routing inquiries to the appropriate person in charge if the automated response is insufficient, and means for recording and sharing the inquiry handling history. This enables centralized management of inquiries from various channels and allows for the rapid provision of more appropriate responses by incorporating emotion recognition technology.

[1061] "Means of receiving inquiries from diverse channels" refers to a system for receiving inquiries from different communication methods such as email, telephone, chatbots, and smartphone applications.

[1062] "Analysis means for natural language processing received inquiries" refers to the process of converting the received inquiry content into text data, analyzing the content using natural language processing techniques, and extracting key keywords and intents.

[1063] "Means for proposing automated responses based on analysis results" refers to a system that automatically generates and proposes appropriate responses based on the analyzed inquiry content and the results of sentiment recognition.

[1064] "Means for recognizing user emotions and generating appropriate automated responses based on the results" refers to a technology that uses an emotion engine to identify the user's emotional state and generates the optimal response accordingly.

[1065] "A means of routing inquiries to the appropriate person when automated responses are insufficient" refers to a function that re-evaluates inquiries that cannot be resolved by automated responses and routes them to the appropriate person or department with the necessary expertise.

[1066] "Means for recording and sharing inquiry response history" refers to a system that stores all inquiries and their responses in a database and shares them in a way that all operators can access.

[1067] An "emotion engine" is a technology that analyzes a user's emotional state from text and audio data, recognizing and classifying emotions such as positive, negative, and neutral.

[1068] A "smartphone application" is software that runs on a smartphone or tablet and interacts directly with the user through an interface.

[1069] This invention relates to an inquiry management system that centrally manages inquiries received by a company from various channels, and performs automated responses, escalation, and sentiment recognition using an sentiment engine. Specific embodiments for carrying out this invention are described below.

[1070] System Overview

[1071] This system has the following main features:

[1072] 1. Receiving an inquiry:

[1073] The server receives user inquiries through various channels, including email, telephone, chatbots, and smartphone applications.

[1074] 2. Analysis of the inquiry content:

[1075] The server extracts the received inquiry content as text data, analyzes it using natural language processing techniques, and extracts key keywords and intent.

[1076] 3. Emotion recognition:

[1077] The server uses an emotion engine to recognize the user's emotions from text and audio data, and reflects that emotional state in the analysis results.

[1078] 4. Generating automated responses:

[1079] Based on the analysis results and emotion recognition results, the server refers to the FAQ database to generate an appropriate automated response and provides it to the user. The response is expressed in a friendly manner that matches the user's emotional state.

[1080] 5. Escalation:

[1081] If the automated response is insufficient, the server will re-evaluate the inquiry and route it to the appropriate person or department.

[1082] 6. Recording and sharing of interaction history:

[1083] The server records all inquiry handling history in a database, making it accessible to all operators.

[1084] Hardware and software to be used

[1085] 1. Hardware:

[1086] Smartphones, tablets, and servers (including multiple servers for running the inquiry management system).

[1087] 2. Software:

[1088] Python programming language, TextBlob library for sentiment analysis, FAQ database, and libraries for natural language processing.

[1089] Specific example

[1090] For example, if a user makes a request through a smartphone application saying, "I'm tired today, so I'd like to listen to some relaxing music," the server receives the request and extracts it as text data. Then, using natural language processing technology, the request is analyzed, and the main keywords "relax" and "music" are extracted. Furthermore, an emotion engine is used to recognize the user's emotional state of being "tired." Based on this information, the server automatically generates and provides a "relaxing music playlist."

[1091] Example of a prompt

[1092] If a user inputs "Please recommend some relaxing music," an example of the input prompt text for the generating AI model would be as follows:

[1093] "Users are looking for relaxation. Please suggest some relaxing music."

[1094] Thus, the present invention centrally manages inquiries from various channels and incorporates emotion recognition technology to quickly provide appropriate automated responses tailored to the user's emotional state. This reduces the workload of operators while improving user satisfaction.

[1095] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1096] Step 1:

[1097] Inquiry received

[1098] Users input and submit their inquiries via smartphones, email, phone, chatbots, etc. The server receives inquiries from these various channels. The input data may be in text or audio format. For example, a user might send "I want to listen to relaxing music" via a smartphone application.

[1099] Step 2:

[1100] Extraction of inquiry content

[1101] The server extracts the received query content as text data. This process also includes converting audio data to text. If audio data is present, it is converted to text format and passed on to the next step.

[1102] Step 3:

[1103] Analysis using natural language processing

[1104] The server analyzes text data using natural language processing techniques. Specifically, it analyzes the text data to extract key keywords and intent. For example, the keywords "relax" and "music" might be extracted. The input is text data, and the output is the analyzed keyword data.

[1105] Step 4:

[1106] emotion recognition

[1107] The server uses an emotion engine to recognize the user's emotions from text data. Here, it classifies and identifies emotions as positive, negative, or neutral. For example, it might recognize the negative emotion "tired" from the user's text. The input is keyword data, and the output is the user's emotional state.

[1108] Step 5:

[1109] Generating an automated response

[1110] The server generates an appropriate automated response by referencing the FAQ database and pre-configured response patterns based on the analysis results and emotion recognition results. For example, it might generate a response offering a "relaxing music playlist." The input is keyword data and emotion state, and the output is the generated automated response.

[1111] Step 6:

[1112] Judgment and handling of escalation

[1113] The server evaluates the generated automated response, and if it determines the response is insufficient, it routes the inquiry to the appropriate person or department. For example, complex requests are escalated to specialized support staff. The input is the automated response, and the output is the escalated inquiry.

[1114] Step 7:

[1115] Providing a response

[1116] The server sends a generated automated response to the user. The user receives the response through a smartphone application or the channel used. For example, a generated playlist is provided to the user. The input is the generated response, and the output is the response sent to the user.

[1117] Step 8:

[1118] Recording and sharing of inquiry response history

[1119] The server records all inquiries and their responses in a database. This record is accessible to all operators and is used as reference material to ensure consistent responses. Input is the response content, and output is the record stored in the database.

[1120] 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.

[1121] 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.

[1122] 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.

[1123] [Fourth Embodiment]

[1124] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1125] 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.

[1126] 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).

[1127] 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.

[1128] 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.

[1129] 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).

[1130] 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.

[1131] 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.

[1132] 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.

[1133] 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.

[1134] 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.

[1135] 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.

[1136] 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".

[1137] This invention relates to an inquiry management system that centrally manages inquiries received by a company from various channels and performs automated responses and escalations. Specific embodiments for carrying out this invention are described below.

[1138] This system receives inquiries from various channels, analyzes their content, and provides automated responses. Furthermore, if the automated response is insufficient, it routes the inquiry to the appropriate person in charge. In addition, inquiry handling history is recorded in a database and shared among operators to prevent duplicate responses and reduce workload.

[1139] System Overview

[1140] 1. Receiving an inquiry

[1141] The server receives user inquiries through multiple channels, including email, phone, and chatbots.

[1142] 2. Analysis of the inquiry content

[1143] The server extracts the received query content as text data and analyzes it using natural language processing techniques.

[1144] 3. Generating automated responses

[1145] Based on the analysis results, the server refers to the FAQ database to generate an appropriate automated response and provides it to the user.

[1146] 4. Escalation

[1147] If the server's automated response is insufficient, it will forward the inquiry to the appropriate person in charge.

[1148] 5. Recording and sharing of support history

[1149] The server records all inquiry handling history in a database, making it accessible to all operators.

[1150] Detailed processing flow

[1151] Inquiry received

[1152] The server receives user inquiries through multiple channels, such as email, phone, and chatbot. For example, if a user sends an email asking "How do I return a product?", the server will receive that email.

[1153] Analysis of inquiry content

[1154] The server converts the received inquiry into text data format. Next, this inquiry is analyzed using natural language processing techniques to extract key keywords and intent. Here, key keywords such as "return" and "method" are extracted.

[1155] Generating an automated response

[1156] The server searches the FAQ database based on the extracted keywords to find the most suitable answer. For example, if an FAQ exists regarding "how to return a product," it generates an automated response based on that answer. This automated response is then provided to the user.

[1157] escalation

[1158] If the automated response is insufficient, the server re-evaluates the inquiry and routes it to the appropriate person or department. For example, if an inquiry concerns complex return conditions or a specific case, the server will forward the information to the relevant customer support department.

[1159] Recording and sharing of support history

[1160] The server records all inquiries and their responses in a database. This database is accessible to all operators, enabling quick and consistent responses by referring to past inquiry history.

[1161] Specific example

[1162] For example, if a user sends an email inquiry asking "How do I return a product?", this inquiry is received by the server. The server extracts the inquiry as text data and uses natural language processing technology to extract the keywords "return" and "method". The server then searches the FAQ database for answers regarding "how to return a product," generates an automated response, and sends it back to the user. If the user inquires about more detailed conditions, the information is forwarded to the appropriate department, and the response history is recorded and shared in the database.

[1163] In this way, this system centrally manages inquiries from various channels and provides appropriate responses quickly, thereby reducing the workload of operators while improving customer satisfaction.

[1164] The following describes the processing flow.

[1165] Step 1:

[1166] The server receives user inquiries through various channels, including email, telephone, and chatbots. For email, the server checks for new emails from the mail server using the IMAP protocol. For chatbots, the server receives new messages via WebSocket. For telephone calls, the server obtains incoming call information using SIP (Session Initiation Protocol).

[1167] Step 2:

[1168] The server extracts the received inquiry content as text data. Text is extracted from the body of emails and chat messages, and in the case of telephone inquiries, a speech recognition system is used to convert the speech into text.

[1169] Step 3:

[1170] The server extracts text data and passes it to a natural language processing engine for semantic analysis and keyword extraction of the query. Specifically, the server sends text data to a natural language processing API for keyword and intent analysis.

[1171] Step 4:

[1172] The server searches the FAQ database based on the analysis results. It queries the FAQ database based on keywords and phrases to retrieve the most relevant answers.

[1173] Step 5:

[1174] The server generates an automated response based on the answers it receives. The generated automated response is converted to an adaptive format and organized into a format that is provided to the user.

[1175] Step 6:

[1176] The server sends an automated response to the user. In the case of email, the server sends the reply email using the SMTP protocol. In the case of a chatbot, the server sends the message using WebSocket.

[1177] Step 7:

[1178] If the server's automated response is insufficient, it will determine whether to escalate the inquiry to a responsible person. Based on the analysis results, an escalation flag will be set, and the appropriate person or department will be determined.

[1179] Step 8:

[1180] The server routes the inquiry to the appropriate person. Based on the content and category of the escalated inquiry, it refers to a list of tasks that the person can handle. Once a suitable person is determined, a notification is sent.

[1181] Step 9:

[1182] The server records all inquiries and their responses in a database. Detailed information, including inquiry content, automated responses, and the actions taken by the assigned staff member in case of escalation, is stored in the database.

[1183] Step 10:

[1184] The server sends a survey form or rating template to the user to collect feedback after handling their inquiry. The collected feedback information is stored in a database and analyzed to help improve the quality of service.

[1185] (Example 1)

[1186] 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".

[1187] In modern society, it is crucial for companies to efficiently and quickly handle inquiries received from various channels. However, if automated responses are insufficient or if the sharing of response history is not done properly, customer satisfaction may decline and the burden on operators may increase. To solve these problems, a system is needed that accurately analyzes inquiry content, provides appropriate responses, and efficiently manages and shares response history.

[1188] 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.

[1189] In this invention, the server includes means for receiving inquiries from various channels, means for analyzing the received inquiries using natural language processing, means for generating automatic responses based on the analysis results, means for routing inquiries to appropriate personnel if the automatic response is insufficient, means for recording and sharing inquiry handling history, means for evaluating and escalating inquiry content, means for analyzing inquiry content using a natural language processing library, means including an evaluation algorithm for evaluating the effectiveness of automatic responses, and means for providing a management screen and making the inquiry history accessible. This enables centralized management of inquiries from various channels, prompt provision of appropriate responses, reduction of operator workload, and improvement of customer satisfaction.

[1190] An "inquiry" refers to information that a user sends to a company to request information or support.

[1191] A "channel" refers to the medium or method that a user uses to send an inquiry to a company.

[1192] A "server" refers to a computer system that receives, analyzes, generates automated responses to, escalates, and records and shares response history.

[1193] "Natural language processing" refers to the technology that enables computers to understand and process human language.

[1194] "Automated response" refers to a system where a computer automatically generates and provides answers based on the content of an inquiry.

[1195] "Escalation" refers to the process of transferring an inquiry to a human representative when the automated response is insufficient or inappropriate.

[1196] "Analysis" refers to the process of understanding the content of an inquiry using natural language processing technology and extracting important keywords and intents.

[1197] An "FAQ database" refers to a database that compiles frequently asked questions and their answers.

[1198] A "database" refers to a system for organizing and storing digital information.

[1199] An "evaluation algorithm" refers to a mathematical method used to assess the effectiveness of automated responses.

[1200] The term "administration screen" refers to an interface used by operators to manage the system and view inquiry history.

[1201] This invention relates to an inquiry management system that centrally manages inquiries received by a company from various channels and performs automated responses and escalations. Specific embodiments for carrying out this invention are described below.

[1202] This system operates server-centric, receiving inquiries from various channels, analyzing their content, and providing automated responses. Furthermore, if the automated response is insufficient, it routes the inquiry to the appropriate person. In addition, inquiry handling history is recorded in a database and shared among operators to prevent duplicate responses and reduce workload.

[1203] Hardware and software to be used

[1204] The server is the main component and uses the following hardware and software:

[1205] Hardware: Server machines, database servers

[1206] Software: Email receiving servers (e.g., SMTP servers), natural language processing libraries (e.g., spaCy, NLTK), database management systems (e.g., MySQL, PostgreSQL), web application frameworks for administration panels (e.g., Django, Flask)

[1207] System Overview

[1208] This system has the following functions:

[1209] 1. Receiving inquiries: The server receives inquiries from users through multiple channels, such as email, telephone, and chatbots.

[1210] 2. Analysis of the inquiry content: The server extracts the received inquiry content as text data and analyzes it using natural language processing technology.

[1211] 3. Generation of automated responses: Based on the analysis results, the server generates an appropriate automated response by referring to the FAQ database and provides it to the user.

[1212] 4. Escalation: If the server's automated response is insufficient, it will forward the inquiry to the appropriate person in charge.

[1213] 5. Recording and sharing of response history: The server records all inquiry response history in a database and makes it accessible to all operators.

[1214] Specific examples of receiving inquiries

[1215] A user sends an email message saying, "Please tell me how to return an item." The server receives this message via the email receiving server and stores it in the inquiry database.

[1216] Specific examples of analyzing inquiry content

[1217] The server extracts the body of the received email as text data and uses a natural language processing library to identify the keywords "return" and "method." The server then uses these keywords to understand the user's intent.

[1218] Specific examples of automated response generation

[1219] The server queries the FAQ database to retrieve answers regarding "how to return a product." Then, based on the retrieved answers, the server generates an automated response message, which is sent to the user, for example, via email.

[1220] Specific examples of escalation

[1221] If the automated response is insufficient, the server will receive a reply from the user stating that they would like to know more specific return conditions. In this case, the server will re-analyze the inquiry and escalate it to the appropriate person in charge.

[1222] Examples of recording and sharing support history

[1223] The server stores all inquiries and their responses in a database. Furthermore, all operators can access past inquiry history through a web-based management screen. For example, an operator can log into the management screen and search for past inquiries related to "returns."

[1224] Example of a prompt

[1225] The following is an example of an input prompt statement for a specific generative AI model:

[1226] "We have an inquiry regarding the return process for a product. Please extract keywords to generate an automated response."

[1227] "If the automated response is insufficient, please escalate the issue to the appropriate person."

[1228] Thus, this system provides a set of functions to efficiently and effectively process inquiries and improve customer satisfaction.

[1229] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1230] Step 1:

[1231] Inquiry received

[1232] The server receives user inquiries through multiple channels, such as email, phone, and chatbot. For example, if a user sends an email asking "How do I return this item?", the server's email receiving server receives the email. In this case, the input is the user's inquiry message, and the output is the received inquiry data.

[1233] Specific actions:

[1234] The server receives emails via an email receiving server (e.g., an SMTP server).

[1235] The received message is saved to the query database.

[1236] Step 2:

[1237] Analysis of inquiry content

[1238] The server extracts the received query content as text data and analyzes it using natural language processing techniques. The input is the received query data, and the output is the analyzed keywords and intent.

[1239] Specific actions:

[1240] The server extracts the body of the received message as text data.

[1241] We use natural language processing libraries (e.g., spaCy, NLTK) to extract key keywords and intent. For example, we identify the keywords "return" and "method".

[1242] Step 3:

[1243] Generating an automated response

[1244] The server generates an appropriate automated response based on the analysis results, referencing the FAQ database, and provides it to the user. The input in this process consists of the analyzed keywords and intent, while the output is the generated automated response message.

[1245] Specific actions:

[1246] The server searches the FAQ database based on the analyzed keywords.

[1247] Retrieve relevant answers and generate automated response messages. For example, generate an automated response based on FAQ answers regarding "how to return a product."

[1248] The generated automated response message is provided to the user via email or other means.

[1249] Step 4:

[1250] escalation

[1251] If the automated response is insufficient, the server will forward the inquiry to the appropriate person in charge. The input at this time is the user's follow-up inquiry or feedback on the automated response, and the output is the inquiry data that will be passed on to the person in charge.

[1252] Specific actions:

[1253] The server runs an evaluation algorithm to assess the effectiveness of the automated response. For example, if the user makes another inquiry or if the user's feedback is negative, the server may determine that the automated response was insufficient.

[1254] Analyze the inquiry and forward it to the appropriate person in charge. Send a notification to the person in charge.

[1255] Step 5:

[1256] Recording and sharing of support history

[1257] The server records all inquiry handling history in a database, making it accessible to all operators. The input consists of processed inquiry data and its response result, while the output is the recorded handling history.

[1258] Specific actions:

[1259] The server saves each query, its response, and the escalation details to a database management system (e.g., MySQL, PostgreSQL).

[1260] The server provides an administration screen for operators, allowing them to view past inquiry history. Operators log in to the administration screen and search and display history using specific keywords or dates.

[1261] Step 6:

[1262] Evaluation of the effectiveness of automated responses

[1263] The server continuously evaluates the effectiveness of the generated automated responses and uses this as a criterion for escalation decisions. The inputs at this stage are user feedback and follow-up query data regarding the generated automated responses, while the output is the escalation decision result and the improved automated response message.

[1264] Specific actions:

[1265] The server collects user feedback data and information on whether or not the user has made a follow-up inquiry.

[1266] The evaluation algorithm is executed to assess the effectiveness of the automated response.

[1267] If escalation is deemed necessary, the inquiry will be re-analyzed and handed over to the appropriate person.

[1268] (Application Example 1)

[1269] 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".

[1270] In recent years, with the spread of online shopping, the importance of customer support in virtual stores has increased. However, customer inquiries come from a variety of channels, which can lead to a loss of consistency and speed in responses. Furthermore, if appropriate automated responses are not provided, escalation becomes necessary, and efficient inquiry management is required. This invention aims to solve these problems by providing a system that can respond to customer inquiries quickly and consistently in virtual stores.

[1271] 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.

[1272] In this invention, the server includes means for receiving inquiries from various channels, means for analyzing the received inquiries using natural language processing, means for proposing an automated response based on the analysis results, means for routing inquiries to the appropriate person in case the automated response is insufficient, means for recording and sharing the inquiry handling history, means for receiving and analyzing user inquiries in real time within the virtual store, and means for creating an appropriate automated response using a generative AI model. This enables a rapid and consistent response to customer inquiries within the virtual store, and is expected to improve the efficiency of customer support and enhance customer satisfaction.

[1273] "Means of receiving inquiries from diverse channels" refers to a system for receiving customer inquiries through multiple communication methods, such as email, telephone, chatbots, and in-virtual store chats.

[1274] "Analysis means for natural language processing received inquiries" refers to a function that uses natural language processing technology to analyze the content of inquiries as text data and extract key keywords and intents.

[1275] "Means of proposing automated responses based on analysis results" refers to a function that generates the optimal automated response by referring to an appropriate FAQ database based on the analyzed keywords and intent.

[1276] "Means for routing inquiries to the appropriate person in case of insufficient automated responses" refers to a function that forwards inquiries to the appropriate person or department when the generated automated response is inadequate to the customer's inquiry.

[1277] "Means for recording and sharing inquiry response history" refers to a function that records all inquiries and their responses in a database, making this information accessible to all operators, thereby sharing past response history and preventing duplicate responses.

[1278] "A means of receiving and analyzing user inquiries in real time within a virtual store" refers to a function that receives inquiries made by users within a virtual store in real time, analyzes their content immediately, and responds to them promptly.

[1279] "Means for creating appropriate automated responses using a generative AI model" refers to a function that uses an AI model to generate the optimal automated response based on the analyzed inquiry content and provide it to the user.

[1280] This invention provides a system for centrally managing inquiries from various channels in a virtual store and enabling automated responses and escalation. The system includes a series of processes for receiving inquiries, analyzing them, generating responses, and escalating them as necessary.

[1281] System Configuration

[1282] This system is implemented using the following main components:

[1283] 1. Inquiry receiving server

[1284] Inquiries are received through multiple channels, including email, phone, chatbots, and in-virtual store chats. Received inquiries are converted into a format that can be processed as text data.

[1285] 2. Natural Language Processing (NLP) Analysis Module

[1286] This module analyzes received inquiries and extracts key keywords and intents. Specifically, it extracts important keywords through text analysis using natural language processing techniques.

[1287] 3. Generating AI Module

[1288] Based on the analyzed keywords, the system consults the FAQ database and generates an appropriate automated response. The generated response is then sent to the user.

[1289] 4. Escalation Module

[1290] If the automated response is insufficient, this module will re-evaluate the inquiry and route it to the appropriate person or department.

[1291] 5. Inquiry Response History Database

[1292] This is a database that records all inquiries and their responses. All operators can access this database, enabling consistent responses by referring to past inquiry history.

[1293] System processing flow

[1294] When a user submits an inquiry within the virtual store, the inquiry is received by a receiving server. The receiving server processes the inquiry as text data and forwards it to an NLP analysis module. The NLP analysis module extracts the main keywords of the inquiry and passes them on to a generation AI module. The generation AI module selects the most appropriate answer from the FAQ database and generates a response. If the generated response is insufficient, an escalation module routes the inquiry to the appropriate person or department. All inquiries and their responses are recorded in an inquiry response history database and used for future inquiry handling.

[1295] Technologies used and specific examples

[1296] Hardware: Servers, cloud storage

[1297] Software: AIChatbot, TextAnalyzer, DatabaseConnector, FAQ

[1298] For example, if a user sends a chat message in a virtual store asking "How do I return an item?", this inquiry is received by the receiving server. TextAnalyzer extracts the keywords "return" and "how," and uses a generative AI model to search for FAQs related to "how to return an item." As a result, an appropriate automated response is provided to the user.

[1299] Example of a prompt

[1300] "Please tell me how to return an item."

[1301] "I'd like to know the reason for the delivery delay."

[1302] "I would like to change the size of the product."

[1303] "I have a question about a specific product."

[1304] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1305] Step 1:

[1306] Users make inquiries within the virtual store. For example, a user might use the chat function to send a message saying, "How do I return an item?" This message becomes input into the system.

[1307] Step 2:

[1308] The server receives inquiries from users. The processing flow involves receiving inquiries via various channels such as email, telephone, chatbot, and in-virtual store chat, and converting them into text data format. The received inquiry text becomes the input for the next step.

[1309] Step 3:

[1310] The server's natural language processing (NLP) analysis module analyzes the received query. In this step, TextAnalyzer is used to extract key keywords and intent from the text data. For example, keywords such as "return" and "method" are extracted. The extracted keywords become the input for the next step.

[1311] Step 4:

[1312] The server's generation AI module generates an automated response based on keywords from the NLP analysis module. In this step, the generation AI model is used to search for appropriate answers in the FAQ database and create a response message using natural language generation technology. For example, it retrieves an answer regarding "how to return a product" from the FAQ and generates a response such as "Details on how to return a product are as follows:...". The generated automated response becomes the input for the next step.

[1313] Step 5:

[1314] The server sends an automated response to the user. The response message is then sent to the user's chat. The user receives the automated response and obtains a solution to their inquiry. This response serves as input for the next step.

[1315] Step 6:

[1316] If the server's automated response is insufficient, it forwards the inquiry to the escalation module. The escalation module re-evaluates the generated automated response if it determines that the automated response is insufficient based on certain criteria, and routes the inquiry to the appropriate person or department. For example, if an exception to the return procedure is required, it will be forwarded to the customer support team. The assigned person's information becomes the input for the next step.

[1317] Step 7:

[1318] The server's inquiry response history database module records all inquiries and their responses in the database. This includes the inquiry reception time, content, analysis results, automated response content, and escalation history. This allows operators to refer to past inquiry history. The recorded data is used for future inquiry handling.

[1319] The above are the specific processing steps.

[1320] 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.

[1321] This invention relates to an inquiry management system that centrally manages inquiries received by a company from various channels, and performs automated responses, escalation, and sentiment recognition using an emotion engine. Specific embodiments for carrying out this invention are described below.

[1322] This system receives user inquiries from various channels, analyzes their content, and uses an emotion engine to recognize the user's emotions, providing appropriate responses based on those emotions. If the automated response is insufficient, it forwards the inquiry to the appropriate person in charge. Inquiry handling history is also recorded in a database and can be shared among operators.

[1323] System Overview

[1324] 1. Receiving an inquiry

[1325] The server receives user inquiries through various channels, including email, phone, and chatbots.

[1326] 2. Analysis of the inquiry content

[1327] The server extracts the received query content as text data and analyzes it using natural language processing techniques.

[1328] 3. Emotion recognition

[1329] The server uses an emotion engine to recognize the user's emotions from text and audio data and reflects them in the analysis results.

[1330] 4. Generating automated responses

[1331] The server generates an appropriate automated response based on the analysis results and sentiment recognition results, referencing the FAQ database, and provides it to the user.

[1332] 5. Escalation

[1333] If the server's automated response is insufficient, it will forward the inquiry to the appropriate person in charge.

[1334] 6. Recording and sharing of support history

[1335] The server records all inquiry handling history in a database, making it accessible to all operators.

[1336] Detailed processing flow

[1337] Inquiry received

[1338] The server receives user inquiries through various channels such as email, phone, and chatbots. For example, if a user sends an email asking "How do I return a product?", the server will receive that email.

[1339] Analysis of inquiry content

[1340] The server converts the received inquiry into text data format. Next, this inquiry is analyzed using natural language processing techniques to extract key keywords and intent. Here, key keywords such as "return" and "method" are extracted.

[1341] emotion recognition

[1342] The server uses an emotion engine to recognize user emotions from text and audio data. For example, it analyzes the user's emotions, such as "angry" or "troubled," from text and recognizes their emotional state. The recognition results are fed back to the analysis system and used to adjust the response.

[1343] Generating an automated response

[1344] The server searches the FAQ database based on the analysis results and sentiment recognition results to find the most appropriate answer. For example, if there is an FAQ about "how to return a product," it generates an automated response based on the content of that FAQ. This automated response is then provided to the user. For example, if the user is in a state of "anxiety," a more helpful response will be generated.

[1345] escalation

[1346] If the automated response is insufficient, the server re-evaluates the inquiry and routes it to the appropriate person or department. For example, if an inquiry concerns complex return conditions or a specific case, the server will forward the information to the relevant customer support department.

[1347] Recording and sharing of support history

[1348] The server records all inquiries and their responses in a database. This database is accessible to all operators, enabling quick and consistent responses by referring to past inquiry history.

[1349] Specific example

[1350] For example, if a user sends an email inquiry asking "How do I return a product?", the server receives the inquiry. The server analyzes the content using natural language processing and recognizes the user's emotions using an emotion engine. As a result of the analysis, keywords such as "return" and "how" are extracted, and the emotion engine detects that the user is "confused." Based on this information, the server generates a more helpful automated response and sends it back to the user. If necessary, the server escalates the inquiry to a specialist and records the entire response history in a database to ensure consistent service.

[1351] In this way, this system centrally manages inquiries from various channels and incorporates sentiment recognition technology to provide more appropriate responses quickly. This makes it possible to reduce the workload of operators while improving customer satisfaction.

[1352] The following describes the processing flow.

[1353] Step 1:

[1354] The server receives user inquiries through various channels, including email, telephone, and chatbots. For email, the server retrieves new emails from the mail server using the IMAP protocol. For chatbots, the server receives new messages via WebSocket. For telephone calls, the server retrieves incoming call information using the SIP protocol.

[1355] Step 2:

[1356] The server extracts the content of the received inquiry as text data. For emails and chat messages, text is extracted from the body, and for phone calls, a speech recognition system is used to convert the speech into text.

[1357] Step 3:

[1358] The server extracts text data and passes it to a natural language processing engine for semantic analysis and keyword extraction of the query. Specifically, the server sends text data to a natural language processing API, and keywords and intent are obtained as analysis results.

[1359] Step 4:

[1360] The server passes text data to the emotion engine to analyze the user's emotions. The emotion engine performs the analysis and detects emotions such as "joy," "anger," and "sadness." The detected emotion data is returned to the server and fed back into the analysis system.

[1361] Step 5:

[1362] The server searches the FAQ database based on the analysis results and sentiment recognition results. The server retrieves the most relevant answers from the FAQ database based on keywords and detected sentiments.

[1363] Step 6:

[1364] The server generates an automated response based on answers retrieved from the FAQ database, and adjusts the response content while also taking into account the emotion recognition results. For example, if the server detects that the user is "angry," it generates a response that includes an apology. This response is then formatted appropriately and sent to the user.

[1365] Step 7:

[1366] The server sends an automated response to the user. If it's email, the server sends the reply using the SMTP protocol. If it's a chatbot, the server sends the message using WebSocket.

[1367] Step 8:

[1368] If the server determines that its automated response is insufficient, it will escalate the inquiry to a relevant person. Based on the analysis results and sentiment recognition results, the appropriate person or department will be selected, an escalation flag will be set, and a notification will be sent.

[1369] Step 9:

[1370] The server routes the inquiry to the appropriate person in charge. The escalated inquiry is compared to a list of tasks that the person in charge can handle, and a notification is sent once a suitable person is determined.

[1371] Step 10:

[1372] The server records all inquiries and their responses in a database. Detailed information such as the inquiry content, automated responses, the actions taken by the assigned staff during escalation, and the user's emotional state are stored in the database.

[1373] Step 11:

[1374] After handling an inquiry, the server sends a survey form or rating template to the user to collect feedback. The collected feedback information is stored in a database and used to improve the quality of future support.

[1375] (Example 2)

[1376] 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".

[1377] A key challenge for companies is to centrally manage inquiries received from various channels and respond quickly and appropriately. In particular, accurately recognizing user emotions and generating responses based on them is crucial for improving customer satisfaction, and it is also necessary to quickly escalate issues to the appropriate personnel when automated responses are insufficient.

[1378] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving inquiries from various channels, means for analyzing the received inquiries using natural language processing technology, means for generating an automated response based on the analysis results and sentiment recognition by the sentiment engine, means for routing inquiries to the appropriate person in charge if the automated response is insufficient, and means for recording and sharing the inquiry handling history. This enables companies to centrally manage inquiries from various channels and quickly provide appropriate responses that take into account the user's emotions.

[1379] An "inquiry" is a question or request that a user sends to a company or organization to seek information.

[1380] A "channel" refers to a means of communication used for sending and receiving inquiries and information, and specifically includes email, telephone, and chatbots.

[1381] "Natural language processing technology" is the technology that understands, interprets, and generates human language on a computer.

[1382] "Analysis means" refers to the techniques and methods used to analyze received inquiries and understand their content and intent.

[1383] An "emotion engine" is a system or technology that recognizes a user's emotional state from text data or audio data.

[1384] "Automatic response" refers to a function in which a system automatically provides pre-set answers to user inquiries.

[1385] An "FAQ database" is a database that compiles frequently asked questions and their answers.

[1386] "Escalation" is the process of transferring an inquiry to the appropriate person or department when the initial response is insufficient.

[1387] A "person in charge" refers to the individual or department responsible for handling an escalated inquiry.

[1388] "Response history" refers to data that records each inquiry and the details of the response to it.

[1389] "Sharing methods" refer to systems or methods that enable multiple operators or staff members to view and use the service history.

[1390] This invention relates to an inquiry management system that centrally manages inquiries received by a company from various channels, and performs automated responses, escalation, and sentiment recognition. This system receives user inquiries from various channels, analyzes their content, recognizes the user's emotions using a sentiment engine, and provides an appropriate response based on that. Furthermore, if the automated response is insufficient, it routes the inquiry to the appropriate person. Inquiry handling history is also recorded in a database and can be shared among operators.

[1391] Specifically, the system is configured as follows:

[1392] Inquiry received

[1393] The server receives user inquiries through various channels, including email, phone, and chatbots. This receiving process includes capturing voice data and parsing text messages. For example, if a user types "How do I return this item?" into the chatbot, the server receives the message immediately.

[1394] Analysis of inquiry content

[1395] The server converts the received inquiry into text data. For voice input, speech recognition technology is used for this purpose. Next, the server analyzes the inquiry using a natural language processing (NLP) engine to extract key keywords and context. For example, keywords such as "return" and "method" are identified.

[1396] emotion recognition

[1397] The server uses an emotion engine to recognize the user's emotions from text and audio data. For example, an NLP engine analyzes emotions such as "confused" or "angry." The results of the emotion recognition are fed back into the analysis results and used to adjust the response.

[1398] Generating an automated response

[1399] The server uses the analysis results and sentiment recognition results to refer to the FAQ database and generate the most appropriate answer. For example, if an FAQ about "how to return a product" exists in the database, the server will generate an automated response based on that information. If the sentiment engine recognizes that the user is "confused," the server will generate a response using more helpful and polite language.

[1400] escalation

[1401] If the automated response is insufficient, the server re-evaluates the inquiry and routes it to the appropriate person or department. For example, if the process is complex and cannot be handled by the FAQ, the server escalates the matter to the customer support department. This ensures that the right person can respond quickly.

[1402] Recording and sharing of support history

[1403] The server records all inquiries and their responses in a database. This database is accessible to all operators, enabling them to provide fast and consistent service based on past response history.

[1404] Specific example

[1405] For example, if a user sends an email inquiry asking "How do I return a product?", the server receives the email. The server analyzes the email content using natural language processing technology and extracts the main keywords "return" and "how to return". At the same time, the sentiment engine recognizes that the user is "confused". Based on the analysis results and sentiment state, the server generates an automated response in a friendly tone and sends it back to the user. If necessary, the server escalates the inquiry to a specialist and records the entire response history in a database for future reference.

[1406] Example of a prompt

[1407] The following is an example of how inputting the following prompt into the AI ​​model can produce an appropriate response:

[1408] "A user is confused about how to return a product. How can we automatically generate a helpful response in this case?"

[1409] "A user contacted us via chatbot regarding a product return, but the emotion engine detected anger. What is the appropriate response in this case?"

[1410] In this way, this system centrally manages inquiries from various channels and incorporates sentiment recognition technology to provide more appropriate responses quickly. This makes it possible to reduce operator workload while improving customer satisfaction.

[1411] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1412] Step 1: Receiving an inquiry

[1413] The server receives user inquiries through various channels, such as email, phone, and chatbots. For example, if a user enters "How do I return a product?" into the chatbot, that message is sent to the server. The server then internally records the received message in its data store. The input is the inquiry content, and the output is the received inquiry data.

[1414] Step 2: Analyzing the inquiry content

[1415] The server converts the received inquiry into text data format. In the case of voice input, the server uses speech recognition technology. For example, if a user makes an inquiry by phone, the server converts the voice data into text and then analyzes that text data. Next, the server uses a natural language processing (NLP) engine to analyze the inquiry and extract key keywords and context. For example, keywords such as "return" and "method" are identified. The input is text data or voice data, and the output is the analyzed keyword and context data.

[1416] Step 3: Emotion Recognition

[1417] The server uses an emotion engine to recognize the user's emotions from text and audio data. For example, the NLP engine can detect emotions such as "confused" or "angry" from the user's message. This information is then fed back into subsequent response generation. The input is the parsed text data, and the output is the emotion recognition result.

[1418] Step 4: Generating an automated response

[1419] The server references the FAQ database based on analysis results and sentiment recognition results to generate the most appropriate answer. For example, if an FAQ about "how to return a product" exists in the database, it will generate an automated response based on that information. If the sentiment engine determines that the user is "confused," a more helpful and easy-to-understand response will be generated. The input is the FAQ database and sentiment recognition results, and the output is an automated response message.

[1420] Step 5: Escalation

[1421] If the automated response is insufficient, the server re-evaluates the inquiry and routes it to the appropriate person or department. For example, if the process is complex and cannot be resolved through FAQs, the server escalates the inquiry to the customer support department. In this process, the person in charge is notified of the inquiry and its status. The input is the inquiry and the result of the automated response suitability evaluation, and the output is the contact person to whom the inquiry has been escalated.

[1422] Step 6: Record and share the history of interactions

[1423] The server records all inquiries and their responses in a database. This database is accessible to all operators and is used to provide fast and consistent service based on past response history. For example, if a similar inquiry has occurred in the past, the response time can be reduced by referring to that history. Inputs include inquiry content, response content, and escalation history, while output is the recorded response history data.

[1424] (Application Example 2)

[1425] 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".

[1426] Traditional inquiry management systems struggle to centrally manage inquiries received from various channels, and in particular, they have difficulty providing appropriate responses tailored to the user's emotional state. Furthermore, they lack adequate mechanisms for analyzing inquiry content, generating automated responses, and then routing inquiries to the appropriate personnel if the automated responses are insufficient. This results in problems such as a reduced user experience and increased response times.

[1427] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1428] In this invention, the server includes means for receiving inquiries from various channels, means for analyzing the received inquiries using natural language processing, means for proposing an automated response based on the analysis results, means for recognizing the user's emotions and generating an appropriate automated response based on the results, means for routing inquiries to the appropriate person in charge if the automated response is insufficient, and means for recording and sharing the inquiry handling history. This enables centralized management of inquiries from various channels and allows for the rapid provision of more appropriate responses by incorporating emotion recognition technology.

[1429] "Means of receiving inquiries from diverse channels" refers to a system for receiving inquiries from different communication methods such as email, telephone, chatbots, and smartphone applications.

[1430] "Analysis means for natural language processing received inquiries" refers to the process of converting the received inquiry content into text data, analyzing the content using natural language processing techniques, and extracting key keywords and intents.

[1431] "Means for proposing automated responses based on analysis results" refers to a system that automatically generates and proposes appropriate responses based on the analyzed inquiry content and the results of sentiment recognition.

[1432] "Means for recognizing user emotions and generating appropriate automated responses based on the results" refers to a technology that uses an emotion engine to identify the user's emotional state and generates the optimal response accordingly.

[1433] "A means of routing inquiries to the appropriate person when automated responses are insufficient" refers to a function that re-evaluates inquiries that cannot be resolved by automated responses and routes them to the appropriate person or department with the necessary expertise.

[1434] "Means for recording and sharing inquiry response history" refers to a system that stores all inquiries and their responses in a database and shares them in a way that all operators can access.

[1435] An "emotion engine" is a technology that analyzes a user's emotional state from text and audio data, recognizing and classifying emotions such as positive, negative, and neutral.

[1436] A "smartphone application" is software that runs on a smartphone or tablet and interacts directly with the user through an interface.

[1437] This invention relates to an inquiry management system that centrally manages inquiries received by a company from various channels, and performs automated responses, escalation, and sentiment recognition using an sentiment engine. Specific embodiments for carrying out this invention are described below.

[1438] System Overview

[1439] This system has the following main features:

[1440] 1. Receiving an inquiry:

[1441] The server receives user inquiries through various channels, including email, telephone, chatbots, and smartphone applications.

[1442] 2. Analysis of the inquiry content:

[1443] The server extracts the received inquiry content as text data, analyzes it using natural language processing techniques, and extracts key keywords and intent.

[1444] 3. Emotion recognition:

[1445] The server uses an emotion engine to recognize the user's emotions from text and audio data, and reflects that emotional state in the analysis results.

[1446] 4. Generating automated responses:

[1447] Based on the analysis results and emotion recognition results, the server refers to the FAQ database to generate an appropriate automated response and provides it to the user. The response is expressed in a friendly manner that matches the user's emotional state.

[1448] 5. Escalation:

[1449] If the automated response is insufficient, the server will re-evaluate the inquiry and route it to the appropriate person or department.

[1450] 6. Recording and sharing of interaction history:

[1451] The server records all inquiry handling history in a database, making it accessible to all operators.

[1452] Hardware and software to be used

[1453] 1. Hardware:

[1454] Smartphones, tablets, and servers (including multiple servers for running the inquiry management system).

[1455] 2. Software:

[1456] Python programming language, TextBlob library for sentiment analysis, FAQ database, and libraries for natural language processing.

[1457] Specific example

[1458] For example, if a user makes a request through a smartphone application saying, "I'm tired today, so I'd like to listen to some relaxing music," the server receives the request and extracts it as text data. Then, using natural language processing technology, the request is analyzed, and the main keywords "relax" and "music" are extracted. Furthermore, an emotion engine is used to recognize the user's emotional state of being "tired." Based on this information, the server automatically generates and provides a "relaxing music playlist."

[1459] Example of a prompt

[1460] If a user inputs "Please recommend some relaxing music," an example of the input prompt text for the generating AI model would be as follows:

[1461] "Users are looking for relaxation. Please suggest some relaxing music."

[1462] Thus, the present invention centrally manages inquiries from various channels and incorporates emotion recognition technology to quickly provide appropriate automated responses tailored to the user's emotional state. This reduces the workload of operators while improving user satisfaction.

[1463] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1464] Step 1:

[1465] Inquiry received

[1466] Users input and submit their inquiries via smartphones, email, phone, chatbots, etc. The server receives inquiries from these various channels. The input data may be in text or audio format. For example, a user might send "I want to listen to relaxing music" via a smartphone application.

[1467] Step 2:

[1468] Extraction of inquiry content

[1469] The server extracts the received query content as text data. This process also includes converting audio data to text. If audio data is present, it is converted to text format and passed on to the next step.

[1470] Step 3:

[1471] Analysis using natural language processing

[1472] The server analyzes text data using natural language processing techniques. Specifically, it analyzes the text data to extract key keywords and intent. For example, the keywords "relax" and "music" might be extracted. The input is text data, and the output is the analyzed keyword data.

[1473] Step 4:

[1474] emotion recognition

[1475] The server uses an emotion engine to recognize the user's emotions from text data. Here, it classifies and identifies emotions as positive, negative, or neutral. For example, it might recognize the negative emotion "tired" from the user's text. The input is keyword data, and the output is the user's emotional state.

[1476] Step 5:

[1477] Generating an automated response

[1478] The server generates an appropriate automated response by referencing the FAQ database and pre-configured response patterns based on the analysis results and emotion recognition results. For example, it might generate a response offering a "relaxing music playlist." The input is keyword data and emotion state, and the output is the generated automated response.

[1479] Step 6:

[1480] Judgment and handling of escalation

[1481] The server evaluates the generated automated response, and if it determines the response is insufficient, it routes the inquiry to the appropriate person or department. For example, complex requests are escalated to specialized support staff. The input is the automated response, and the output is the escalated inquiry.

[1482] Step 7:

[1483] Providing a response

[1484] The server sends a generated automated response to the user. The user receives the response through a smartphone application or the channel used. For example, a generated playlist is provided to the user. The input is the generated response, and the output is the response sent to the user.

[1485] Step 8:

[1486] Recording and sharing of inquiry response history

[1487] The server records all inquiries and their responses in a database. This record is accessible to all operators and is used as reference material to ensure consistent responses. Input is the response content, and output is the record stored in the database.

[1488] 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.

[1489] 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.

[1490] 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.

[1491] 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.

[1492] 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. In the upper and lower directions of the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. Also, the upper side of the concentric circles is where "pleasant" emotions are located, and the lower side is where "unpleasant" emotions are located. In this way, 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.

[1493] 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.

[1494] 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.

[1495] 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.

[1496] 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."

[1497] 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.

[1498] 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.

[1499] 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.

[1500] 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.

[1501] 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.

[1502] 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.

[1503] 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.

[1504] 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.

[1505] 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.

[1506] 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.

[1507] 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.

[1508] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[1509] The following is further disclosed regarding the embodiments described above.

[1510] (Claim 1)

[1511] Means of receiving inquiries from various channels,

[1512] An analysis means for processing received queries using natural language,

[1513] A means of proposing an automated response based on the analysis results,

[1514] A means of routing inquiries to the appropriate person in case the automated response is insufficient,

[1515] A means of recording and sharing the history of inquiries,

[1516] A system that includes this.

[1517] (Claim 2)

[1518] The system according to claim 1, wherein the inquiry receiving channels consist of email, telephone, and chatbot.

[1519] (Claim 3)

[1520] The system according to claim 1, wherein the analysis means performs semantic analysis of the query content and keyword extraction using natural language processing technology.

[1521] "Example 1"

[1522] (Claim 1)

[1523] Means of receiving inquiries from various channels,

[1524] An analysis means for processing received queries using natural language,

[1525] A means for generating an automated response based on the analysis results,

[1526] A means of routing inquiries to the appropriate person in case the automated response is insufficient,

[1527] A means of recording and sharing the history of inquiries,

[1528] A means of evaluating and escalating inquiries,

[1529] A means of analyzing query content using a natural language processing library,

[1530] A means including an evaluation algorithm for evaluating the effectiveness of automated responses,

[1531] A means to provide an administration screen and make the inquiry history accessible,

[1532] A system that includes this.

[1533] (Claim 2)

[1534] The system according to claim 1, wherein the inquiry receiving channels consist of email, telephone, and chatbot.

[1535] (Claim 3)

[1536] The system according to claim 1, wherein the analysis means performs semantic analysis of the query content and keyword extraction using natural language processing technology.

[1537] "Application Example 1"

[1538] (Claim 1)

[1539] Means of receiving inquiries from various channels,

[1540] An analysis means for processing received queries using natural language,

[1541] A means of proposing an automated response based on the analysis results,

[1542] A means of routing inquiries to the appropriate person in case the automated response is insufficient,

[1543] A means of recording and sharing the history of inquiries,

[1544] A means of receiving and analyzing user inquiries in real time within a virtual store,

[1545] A means of creating appropriate automated responses using a generative AI model,

[1546] A system that includes this.

[1547] (Claim 2)

[1548] The system according to claim 1, wherein the inquiry receiving channels consist of email, telephone, chatbot, and chat within a virtual store.

[1549] (Claim 3)

[1550] The system according to claim 1, wherein the analysis means uses natural language processing technology to perform semantic analysis and keyword extraction of the inquiry content, and generates an automated response using a generative AI model.

[1551] "Example 2 of combining an emotion engine"

[1552] (Claim 1)

[1553] Means of receiving inquiries from various channels,

[1554] A means of analyzing received queries using natural language processing techniques,

[1555] A means for generating an automated response based on the analysis results and emotion recognition by the emotion engine,

[1556] A means of routing inquiries to the appropriate person in case the automated response is insufficient,

[1557] A means of recording and sharing the history of inquiries,

[1558] A system that includes this.

[1559] (Claim 2)

[1560] The system according to claim 1, wherein the inquiry receiving channels consist of email, telephone, and chatbot.

[1561] (Claim 3)

[1562] The system according to claim 1, wherein the analysis means uses natural language processing technology to perform semantic analysis and keyword extraction of the inquiry content, and performs emotion recognition using an emotion engine.

[1563] "Application example 2 when combining with an emotional engine"

[1564] (Claim 1)

[1565] Means of receiving inquiries from various channels,

[1566] An analysis means for processing received queries using natural language,

[1567] A means of proposing an automated response based on the analysis results,

[1568] A means for recognizing user emotions and generating appropriate automated responses based on those emotions,

[1569] A means of routing inquiries to the appropriate person in case the automated response is insufficient,

[1570] A means of recording and sharing the history of inquiries,

[1571] A system that includes this.

[1572] (Claim 2)

[1573] The system according to claim 1, wherein the inquiry receiving channels consist of email, telephone, chatbot, and smartphone application.

[1574] (Claim 3)

[1575] The system according to claim 1, wherein the analysis means uses natural language processing technology to perform semantic analysis and keyword extraction of the inquiry content, and uses an emotion engine for emotion recognition. [Explanation of symbols]

[1576] 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. Means of receiving inquiries from various channels, An analysis means for processing received queries using natural language, A means of proposing an automated response based on the analysis results, A means of routing inquiries to the appropriate person in case the automated response is insufficient, A means of recording and sharing the history of inquiries, A system that includes this.

2. The system according to claim 1, wherein the inquiry receiving channels consist of email, telephone, and chatbot.

3. The system according to claim 1, wherein the analysis means performs semantic analysis of the query content and keyword extraction using natural language processing technology.

Images