system

Abstract

We provide the system. [Solution] A means of receiving inquiries from users, A means for analyzing the aforementioned query using natural language processing and classifying it into a query category, A means for distributing the aforementioned classified inquiries to the appropriate department or an automated reply message based on their category, A means for notifying the user of the status of the response and the solution method, 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 persona chatbot control method performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, 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] There is a problem that customer satisfaction decreases due to a delay in responding to inquiries from customers. In particular, when the task of distributing inquiry contents to appropriate departments is performed manually, delays and mistakes in responses are likely to occur. Also, since answers to common questions are created manually every time, waste of resources is also an issue.

Means for Solving the Problems

[0005] To solve the above problems, the present invention provides the following means. Specifically, it provides a system that includes means for receiving inquiries from users, means for analyzing the inquiries using natural language processing and classifying them into categories, means for distributing the classified inquiries to the appropriate department or an automated reply message based on the category, and means for notifying the user of the status of the response and the solution. This makes it possible to improve the efficiency and speed of inquiry handling and enhance customer satisfaction.

[0006] "User" refers to a customer or end-user who makes an inquiry using this system.

[0007] An "inquiry" refers to a question, problem report, or request that a user sends to the system.

[0008] "Means of receiving" refers to the process or device for receiving inquiry data from users.

[0009] Natural Language Processing (NLP) refers to the technology of using computers to analyze the language that humans use on a daily basis.

[0010] "Means of analysis" refers to a process or device for analyzing the content of an inquiry and extracting its constituent elements.

[0011] "Category" refers to a classification system based on the content of the inquiry.

[0012] "Means of classification" refers to a process or device for sorting analyzed query content into predetermined categories.

[0013] "Responsible department" refers to a specific department or team within the company that is responsible for handling inquiries in a particular category.

[0014] An "automatic reply message" refers to a message that automatically sends a pre-set response to an inquiry.

[0015] The "distribution means" refers to a process or device for allocating inquiry contents to corresponding departments or automatic reply messages.

[0016] The "notification means" refers to a process or device for notifying users of the response status and solution methods.

Brief Description of Drawings

[0017] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [[ID=4s4]] [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when the emotion engine is combined. [Figure 14] 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

[0018] 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.

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

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

[0021] 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.

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

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

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

[0025] [First Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0038] This invention relates to a system that efficiently processes user inquiries and routes them to the most appropriate department or automated reply message. This system enables a quick and accurate response by automating the receiving, analysis, classification, routing, and notification of inquiries.

[0039] Inquiry reception

[0040] The user fills out their inquiry in the website's contact form and clicks the submit button. The device receives the inquiry data entered by the user and sends it to the server as an HTTP POST request.

[0041] Query analysis and classification

[0042] The server analyzes the query data received from the terminal. Natural language processing (NLP) techniques are used for this analysis. The NLP engine tokenizes the query content, tags it with parts of speech, and extracts keywords and context. Based on the results of this analysis, the server determines the category of the query. For example, a query containing keywords such as "account" and "password" will be classified into the "account management" category.

[0043] Automatic distribution

[0044] The server routes categorized inquiries to the appropriate department or to an automated reply message. For example, inquiries categorized as "Account Management" are automatically forwarded to the account management team's response queue. The server can also generate automated reply emails based on the content of the inquiry. These automated reply emails contain standard answers to common questions and are sent to the user.

[0045] Notification of response status and solution

[0046] The server notifies the user of the status of their inquiry. For example, the server sends the user a status update email stating, "Your inquiry has been forwarded to the account management team. You will usually receive a response within 24 hours." Furthermore, once the issue is resolved, the server sends the user a final notification email containing the solution, completing the inquiry process.

[0047] Specific example

[0048] 1. The user enters "I forgot my account password" into the website's contact form and clicks the submit button.

[0049] 2. The terminal receives the form data entered by the user and sends an HTTP POST request to the server.

[0050] 3. The server analyzes the received query data using a natural language processing engine and extracts the keywords "account" and "password".

[0051] 4. The server categorizes the inquiry under "Account Management" and automatically forwards it to the appropriate department.

[0052] 5. The server generates an automated reply email and sends the user instructions on how to reset their password.

[0053] 6. The server notifies the user of the status of the request and sends a message stating, "You will usually receive a reply within 24 hours."

[0054] 7. The account management team will respond to user inquiries and provide specific instructions to resolve the issue.

[0055] 8. After the problem is resolved, the server will send a final notification email to the user and close the inquiry ticket.

[0056] In this way, the system based on the present invention efficiently and accurately processes user inquiries and enables a rapid response.

[0057] The following describes the processing flow.

[0058] Step 1:

[0059] The user enters their inquiry into the website's contact form and clicks the submit button.

[0060] Step 2:

[0061] The terminal collects the form data entered by the user and sends it to the server as an HTTP POST request.

[0062] Step 3:

[0063] The server parses the HTTP POST request received from the terminal and extracts the query content.

[0064] Step 4:

[0065] The server passes the query content to a natural language processing (NLP) engine, which performs tokenization, part-of-speech tagging, and dependency analysis.

[0066] Step 5:

[0067] The server extracts keywords and context from the query content based on the output of the NLP engine and determines the category of the query.

[0068] Step 6:

[0069] The server applies the appropriate processing rule based on the category of the inquiry. For example, for an inquiry categorized as "Account Management," it applies a rule to forward it to the account management team.

[0070] Step 7:

[0071] The server adds the classified query to the queue of the relevant department.

[0072] Step 8:

[0073] The server simultaneously generates an automated reply email based on the inquiry. You select a template and fill in the user's name and specific information.

[0074] Step 9:

[0075] The server sends the generated automated reply email to the user's email address.

[0076] Step 10:

[0077] The server updates the status of the inquiry and notifies the user of the response status. For example, it might send an email stating, "Your inquiry has been forwarded to the account management team. You will usually receive a response within 24 hours."

[0078] Step 11:

[0079] The relevant department (e.g., the account management team) receives the inquiry and provides specific assistance to the user. If necessary, they will request additional information from the user.

[0080] Step 12:

[0081] Once the relevant department has completed the task, the server closes the inquiry ticket and sends a resolution notification email to the user.

[0082] The above describes the specific processing flow in the system of the present invention.

[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] Traditional inquiry handling systems often lacked the ability to quickly and accurately route user inquiries to the appropriate department. This resulted in delays and inappropriate processing, leading to a poor user experience. Furthermore, the manual analysis and classification of inquiries was often time-consuming and labor-intensive. Additionally, users were not adequately notified of the status of their inquiries, causing anxiety. To address these challenges, a system is needed that automates the inquiry handling process, enabling efficient and accurate inquiry processing.

[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 users, means for analyzing the received inquiries using natural language processing and extracting keywords and context, means for determining the category of the inquiry based on the extracted keywords, means for distributing the classified inquiries to the appropriate department or an automated reply message based on the category, and means for notifying the user of the status of the response and the solution. This makes it possible to quickly and accurately analyze and classify user inquiries and automatically distribute them to the appropriate department. Furthermore, by notifying the user of the response status in a timely manner, an improvement in the user experience can be expected.

[0088] An "inquiry" refers to a question or request that a user sends to a system in order to obtain information.

[0089] "Natural language processing" refers to the technology that enables computers to understand, interpret, and generate human language, and includes processes such as tokenization of text, part-of-speech tagging, and keyword extraction.

[0090] "Analysis" refers to the process of breaking down and understanding received query data, and specifically refers to the use of natural language processing techniques.

[0091] "Keywords" refer to important words or phrases extracted from the inquiry content, and serve as crucial clues for identifying the content of the inquiry.

[0092] "Context" refers to information that helps understand the overall meaning and background of an inquiry, and primarily serves to complement the meaning of keywords.

[0093] A "category" refers to a group classified based on the analyzed inquiry content, and specifically means a particular area such as account management or technical support.

[0094] "Routing" refers to the process of assigning analyzed and classified inquiries to the appropriate department or automated response message.

[0095] A "responsible department" refers to a department or team responsible for handling inquiries categorized into a specific group.

[0096] An "automatic reply message" refers to a standardized response message that the system automatically generates and sends to the user based on the content of the inquiry.

[0097] "Notifications" refer to information sent to users to inform them of the status of their inquiry and how it has been resolved.

[0098] This invention relates to a system that efficiently processes user inquiries and routes them to the most appropriate department or automated reply message. The following describes a specific implementation of this system.

[0099] Inquiry reception

[0100] The user fills out their inquiry in the website's contact form and clicks the submit button. The device receives the inquiry data entered by the user and sends it to the server as an HTTP POST request.

[0101] Query analysis and classification

[0102] The server analyzes the query data received from the terminal. Natural language processing (NLP) techniques are used for this analysis. Specifically, Python's natural language processing libraries, such as NLTK (Natural Language Toolkit) and SpaCy, can be used. The natural language processing engine tokenizes the query content, tags it with parts of speech, and extracts keywords and context. Based on the results of this analysis, the server determines the category of the query. For example, a query containing keywords such as "account" and "password" will be classified into the "account management" category.

[0103] Automatic distribution

[0104] The server routes classified inquiries to the appropriate department or to an automated reply message. For example, inquiries classified under the "Account Management" category are automatically forwarded to the account management team's response queue. The server can also generate automated reply emails based on the inquiry content. These automated reply emails contain standard answers to common questions and are sent to the user. An SMTP server (e.g., SendGrid) can be used to generate automated reply emails.

[0105] Notification of response status and solution

[0106] The server notifies the user of the status of their inquiry. For example, the server sends the user a status update email stating, "Your inquiry has been forwarded to the account management team. You will usually receive a response within 24 hours." Furthermore, once the issue is resolved, the server sends the user a final notification email containing the solution, completing the inquiry process.

[0107] Specific example

[0108] 1. The user enters "I forgot my account password" into the website's contact form and clicks the submit button.

[0109] 2. The terminal receives the form data entered by the user and sends an HTTP POST request to the server.

[0110] 3. The server analyzes the received query data using the NLTK natural language processing engine and extracts the keywords "account" and "password".

[0111] 4. The server categorizes the inquiry under "Account Management" and automatically forwards it to the appropriate department.

[0112] 5. The server generates an automated reply email via SendGrid, sending the user instructions for resetting their password.

[0113] 6. The server notifies the user of the status of the request and sends a message stating, "You will usually receive a reply within 24 hours."

[0114] 7. The account management team will respond to user inquiries and provide specific instructions to resolve the issue.

[0115] 8. After the problem is resolved, the server will send a final notification email to the user and close the inquiry ticket.

[0116] Example of a prompt

[0117] "Please provide a step-by-step explanation of the process of a program that uses an automated sorting system to analyze user inquiries and route them to the appropriate department. For example, if a user inquires, 'I forgot my account password,' please explain the detailed processing steps involved in each process."

[0118] As a result, the system based on the present invention can process user inquiries efficiently and accurately, enabling a rapid response.

[0119] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0120] Step 1: Receiving inquiry data

[0121] The user fills out their inquiry in the website's contact form and clicks the submit button.

[0122] The terminal receives the inquiry data entered by the user and sends it to the server as an HTTP POST request.

[0123] Input: The content of the inquiry entered by the user in the form.

[0124] Output: Query data in HTTP POST request format.

[0125] Specific action: The user enters "I forgot my account password" and clicks the submit button. The device packages this data as an HTTP request and sends it to the "POST / inquiry" endpoint.

[0126] Step 2: Inquiry month analysis

[0127] The server analyzes the query data received from the terminal using a natural language processing (NLP) engine.

[0128] Input: Query data as an HTTP POST request.

[0129] Output: Analyzed keywords and contextual information.

[0130] Specific operation: The server uses natural language processing libraries (NLTK or SpaCy) to tokenize the query content, tag it with part-of-speech tags, and extract the keywords "account" and "password".

[0131] Step 3: Classifying the inquiry

[0132] The server determines the category of the query based on the extracted keywords.

[0133] Input: Analyzed keywords and contextual information.

[0134] Output: Identified query category.

[0135] Specific operation: The server categorizes inquiries into the "account management" category based on the keywords "account" and "password".

[0136] Step 4: Automatically route inquiries

[0137] The server then routes the classified inquiries to the appropriate department or to an automated reply message.

[0138] Input: Identified inquiry category.

[0139] Output: Queue or automated reply message from the relevant department.

[0140] Specific actions: The server adds inquiries categorized as "account management" to the account management team's queue. It also generates an automated reply email, creating an email outlining the "password reset procedure."

[0141] Step 5: Notifying the user of the status of the response.

[0142] The server notifies the user of the status of the inquiry.

[0143] Input: Status data.

[0144] Output: Notification email to the user.

[0145] Specific action: The server sends the user an email stating, "Your inquiry has been forwarded to the account management team. You will usually receive a response within 24 hours."

[0146] Step 6: Final notification after problem resolution

[0147] The server will send the user a final notification email containing the solution once the problem is resolved.

[0148] Input: Problem-solving data.

[0149] Output: Final notification email to the user.

[0150] Specific action: The server sends an email to the user stating "Your account password has been reset" and closes the inquiry ticket.

[0151] Through these steps, this system efficiently processes user inquiries and enables quick and accurate responses.

[0152] (Application Example 1)

[0153] 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."

[0154] The objective of this invention is to provide a system that efficiently and accurately processes user inquiries and routes them to the most appropriate department or automated reply message. In particular, it aims to improve customer satisfaction in logistics centers by providing prompt and appropriate responses to inquiries regarding delivery delays, damaged goods, etc. Furthermore, it aims to improve the efficiency and accuracy of inquiry processing by automating the analysis, classification, and notification of inquiries.

[0155] 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.

[0156] In this invention, the server includes means for receiving inquiries from users, means for analyzing inquiries using natural language processing and classifying them into categories, means for distributing the classified inquiries to the appropriate department or an automated reply message based on the category, means for notifying the user of the status of the response and the solution, means for processing inquiries about delivery status within the logistics center, means for accurately analyzing inquiries about delivery delays and damaged goods and distributing them to the appropriate department, and means for providing the user with an automated reply message regarding delivery delays and damaged goods. This enables more efficient and rapid response to inquiries in the logistics center.

[0157] A "user" is a person or organization that uses the system to make inquiries.

[0158] An "inquiry" refers to the content of a question, request, or problem report that a user provides through the system.

[0159] "Natural language processing" is a technology that enables computers to understand and analyze human language.

[0160] A "category" is a classification used to categorize inquiries based on specific themes or issues.

[0161] The "responsible department" refers to the department or person responsible for providing an appropriate response to a classified inquiry.

[0162] An "automatic reply message" is a response message that a system automatically generates based on a user's inquiry.

[0163] "Status" refers to information indicating the current status of an inquiry.

[0164] "Solution" refers to a specific response or means of resolving an inquiry.

[0165] A "logistics center" is a facility that handles the distribution, management, and related operations of goods.

[0166] "Delivery status" refers to information indicating the current progress and any issues related to the delivery of the product.

[0167] "Delivery delay" refers to a situation where delivery is delayed beyond the scheduled delivery time.

[0168] "Product damage" refers to a condition in which a product is damaged during delivery.

[0169] "Analysis" is the process by which a system examines the content of a query in detail and extracts its meaning.

[0170] "Classification" refers to dividing the analyzed query content into specific categories.

[0171] "Routing" is the process of sending classified inquiries to the appropriate department or message.

[0172] "Automatic reply" refers to a system automatically sending a response message to a user.

[0173] This invention is a system that efficiently processes user inquiries and routes them to the most appropriate department or automated reply message. In particular, it enables quick and appropriate responses to inquiries regarding delivery delays and damaged goods in logistics centers. The specific implementation of this invention will be described below in several steps.

[0174] First, the user accesses the system using a smartphone or computer and enters their inquiry. The user enters "Delivery is delayed" into the inquiry form on the website and clicks the submit button. The device receives the entered inquiry data and sends it to the server as an HTTP POST request.

[0175] The server processes the received data using a parsing module equipped with a natural language processing engine. Specifically, it uses the Python Django framework and the spaCy library to tokenize the inquiry content, tag it with parts of speech, and extract keywords. This process classifies the inquiry content into categories such as "delivery delay" or "product damage."

[0176] Next, the server automatically forwards the classified inquiries to the appropriate department. For example, an inquiry about "delivery delay" is forwarded to the delivery management team, and an inquiry about "damaged goods" is forwarded to the quality assurance team. This is done by using Django models to record the inquiry details in the database and notify the appropriate department.

[0177] The server generates an automated reply message to inform the user of the status of the response. This message is created based on a pre-configured template and sent to the user via email or in-app notification. For example, a message such as "We have received your inquiry regarding the delivery delay. We will forward it to the appropriate department." might be automatically generated.

[0178] In a specific use case at a logistics center, if a user enters "My delivery is delayed," this inquiry is categorized as "Delivery Delay." The server then generates an automated reply message stating, "We have received your inquiry regarding a delivery delay. We will forward it to the appropriate department," and notifies the user. Based on this, the appropriate department is also automatically notified.

[0179] In this way, the system can process user inquiries quickly and accurately, and streamline inquiry handling at the logistics center.

[0180] Example of a prompt:

[0181] text

[0182] It seems my package is delayed in transit. Could you please check on it?

[0183] This prompt causes the system to categorize the request as a "delivery delay," route it to the appropriate department, and send an automated reply message to the user.

[0184] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0185] Step 1:

[0186] A user enters "My delivery is delayed" into the website's contact form and clicks the submit button. The input is the user's inquiry. Based on this input, the device sends the inquiry data to the server as an HTTP POST request. The output is the HTTP POST request to the server.

[0187] Step 2:

[0188] The server analyzes the received query data. Natural language processing (NLP) techniques are used for this analysis. Specifically, the server utilizes the Python Django framework and the spaCy library to tokenize the query content, tag it with parts of speech, and extract keywords. For this purpose, the server is equipped with an NLP engine. The input is the user's query data, and the output is the extracted keywords and the tokenized query data.

[0189] Step 3:

[0190] The server categorizes the inquiry based on the analysis results. Examples of such categories include "delivery delay" and "damaged goods." In this classification step, the inquiry is assigned to the appropriate category based on the extracted keywords. The input is the analysis results obtained in step 2, and the output is the classified category.

[0191] Step 4:

[0192] The server forwards classified queries to the appropriate department. Specifically, it uses a Django model to record the query details in the database and then notifies the appropriate department. The input is classified category information and the query details, and the output is recording to the database and notifying the appropriate department.

[0193] Step 5:

[0194] The server generates an automated reply message informing the user of the status and resolution of their inquiry. This message is created based on a pre-configured template. For example, it might say, "We have received your inquiry regarding the delivery delay. We are forwarding it to the appropriate department." The input is the inquiry content and classification information, and the output is the automatically generated reply message.

[0195] Step 6:

[0196] The server sends the generated automated reply message to the user. Specifically, it sends the message to the user via the mail server or sends an in-app notification. The input is the automated reply message, and the output is the notification to the user.

[0197] For example, if a user enters "My delivery is delayed," the server categorizes this inquiry as "Delivery Delay" and forwards it to the appropriate department. An automated reply message, "We have received your inquiry regarding a delivery delay. We will forward it to the appropriate department," is then generated and sent to the user.

[0198] 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.

[0199] This invention relates to a system for efficiently processing user inquiries, and further incorporates an emotion engine that recognizes user emotions to adjust the response department or automated reply message according to those emotions. This system automates the reception, analysis (including emotion recognition), classification, sorting, and notification of inquiries, enabling flexible responses based on user emotions.

[0200] Inquiry reception

[0201] The user enters their inquiry into the website's contact form and clicks the submit button. The device collects the inquiry data entered by the user and sends it to the server as an HTTP POST request.

[0202] Inquiry analysis and sentiment recognition

[0203] The server analyzes the query data received from the terminal. This analysis uses natural language processing (NLP) technology and an emotion recognition engine. The NLP engine tokenizes the query content, tags it with parts of speech, and extracts keywords and context. Furthermore, the emotion recognition engine detects emotions (e.g., anger, sadness, joy, etc.) from the user's query content.

[0204] Inquiry classification and sentiment-based adjustment

[0205] The server categorizes inquiries based on the output of its NLP engine and emotion recognition engine. For example, inquiries containing keywords such as "account" and "password" are categorized under "account management." Next, the server adjusts the appropriate department and automated reply message based on the detected emotion. For example, if anger is detected, the inquiry is routed to a department that prioritizes handling it.

[0206] Automatic sorting and responses based on emotion

[0207] The server adds categorized inquiries to the queue of the appropriate department. The server also selects an automated reply message template based on the user's sentiment and generates a customized automated reply email. This email includes standard answers to common questions, along with wording that is sensitive to the user's feelings.

[0208] Notification of response status and solution

[0209] The server notifies the user of the status of their inquiry. For example, the server sends the user a status update email stating, "Your inquiry has been forwarded to the account management team. We will respond more quickly than usual." Furthermore, once the issue is resolved, the server sends the user a final notification email containing the solution, completing the inquiry process.

[0210] Specific example

[0211] 1. The user enters the following into the website's contact form: "I have tried to reset my account password multiple times, but I still cannot log in. I am very frustrated." and clicks the submit button.

[0212] 2. The terminal collects the form data entered by the user and sends an HTTP POST request to the server.

[0213] 3. The server analyzes the received inquiry data using NLP and an emotion recognition engine, extracting the keywords "account" and "password" and the emotion "anger."

[0214] 4. The server categorizes inquiries into "account management" and prioritizes forwarding them to the account management team based on the user's sentiment.

[0215] 5. The server generates an emotion-based automated reply email and sends it to the user, including "password reset instructions" and a promise of "prompt action."

[0216] 6. The server notifies the user of the status of the inquiry and sends a message stating, "Your inquiry will be handled with priority."

[0217] 7. The account management team will receive inquiries and provide users with prompt and specific responses.

[0218] 8. After the problem is resolved, the server will send a final notification email to the user and close the inquiry ticket.

[0219] In this way, the system based on the present invention efficiently and accurately processes user inquiries and enables flexible responses that respond to the user's emotions.

[0220] The following describes the processing flow.

[0221] Step 1:

[0222] The user enters their inquiry into the website's contact form and clicks the submit button, stating, "I have tried to reset my account password multiple times, but I still cannot log in. I am extremely frustrated."

[0223] Step 2:

[0224] The terminal collects the form data entered by the user and sends it to the server as an HTTP POST request.

[0225] Step 3:

[0226] The server parses the HTTP POST request received from the terminal and extracts the query content.

[0227] Step 4:

[0228] The server passes the query content to a natural language processing (NLP) engine, which performs tokenization, part-of-speech tagging, and dependency analysis.

[0229] Step 5:

[0230] Based on the output of the NLP engine, the server extracts keywords and context from the query content, identifying keywords such as "account," "password," and "unable to log in."

[0231] Step 6:

[0232] The server passes the user's inquiry to the sentiment recognition engine, which then detects emotions (e.g., anger) within the text.

[0233] Step 7:

[0234] The server categorizes inquiries into "account management" and, based on sentiment recognition results, flags them as inquiries requiring priority attention.

[0235] Step 8:

[0236] The server adds the categorized query to the priority queue for the account management team.

[0237] Step 9:

[0238] The server selects an appropriate template based on the inquiry content and sentiment recognition results, and generates an automated reply email. The template includes phrases such as "Password reset instructions" and "A promise of a prompt response."

[0239] Step 10:

[0240] The server sends the generated automated reply email to the user's email address.

[0241] Step 11:

[0242] The server updates the status of the inquiry and sends the user a status update email stating, "Your inquiry has been forwarded to the account management team as a priority. We will respond promptly."

[0243] Step 12:

[0244] The account management team receives inquiries and responds quickly to user issues. They provide additional information to guide users through support procedures as needed.

[0245] Step 13:

[0246] Once the issue is resolved, the server closes the inquiry ticket and sends a final notification email to the user.

[0247] The above describes the specific processing flow in the system of the present invention.

[0248] (Example 2)

[0249] 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".

[0250] Many modern systems are required to efficiently handle user inquiries, but they face the challenge of providing flexible responses that take into account user emotions. When users are frustrated or angry, a quick and appropriate response is needed, but current systems often fall short in this regard. Furthermore, routing inquiries to the appropriate department based on their content is crucial, but this process is often done manually, lacking efficiency. Therefore, there is a need for an efficient and accurate inquiry processing system that includes responses that take user emotions into account.

[0251] 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 users, means for analyzing the inquiries using natural language processing and classifying them into categories, means for detecting emotions from the content of the inquiries, means for distributing the inquiries to the appropriate department or an automated reply message based on the classification and detected emotions, and means for notifying the user of the status of the response and the solution. This enables flexible responses in accordance with the user's emotions, improving the efficiency and accuracy of inquiry processing.

[0252] A "user" refers to anyone who submits a question or problem using the contact form.

[0253] A "terminal" refers to a device used by a user (for example, a personal computer or smartphone), which has the role of collecting inquiry data and sending it to the server.

[0254] A "server" refers to a central processing unit that analyzes, classifies, distributes, and notifies query data received from terminals.

[0255] "Inquiry" refers to a question or problem that a user enters into a website's inquiry form.

[0256] "Natural language processing" refers to the technology that enables computers to understand, interpret, and generate human language.

[0257] A "category" refers to a classification group based on the content of the inquiry.

[0258] "Analysis" refers to the process of tokenizing the content of an inquiry and extracting keywords and context.

[0259] "Emotion recognition" refers to the technology that detects a user's emotions (for example, anger, sadness, joy, etc.) from the content of their inquiry.

[0260] "Routing" refers to the process of distributing inquiries to the appropriate department or automated response message based on classification and detected sentiment.

[0261] The term "responsible department" refers to the department responsible for handling inquiries in a specific category.

[0262] An "automatic reply message" refers to a standard response message that a system automatically generates and sends to the user.

[0263] "Notification" refers to the process of informing the user about the status of their inquiry and how it has been resolved.

[0264] This invention relates to a system for efficiently processing user inquiries, which, by incorporating an emotion engine that recognizes user emotions, adjusts the responding department and automated reply messages according to those emotions. This system automates the receiving, analysis (including emotion recognition), classification, sorting, and notification of inquiries, enabling flexible responses based on user emotions.

[0265] Inquiry reception

[0266] The user enters their inquiry into the website's contact form and clicks the submit button. The device sends the user's entered inquiry data to the server as an HTTP POST request. The device collects inquiries through web browsers and mobile apps and sends them to the server.

[0267] Inquiry analysis and sentiment recognition

[0268] The server analyzes the query data received from the terminal. This analysis uses natural language processing (NLP) technology and an emotion recognition engine. SpaCy and BERT can be used as the natural language processing engine. This tokenizes the query content and extracts keywords and context. Furthermore, IBM Watson® Tone Analyzer and Microsoft® Azure® Text Analytics are used as emotion recognition engines to detect emotions (e.g., anger, sadness, joy, etc.) from the user's query content.

[0269] Inquiry classification and sentiment-based adjustment

[0270] The server categorizes inquiries based on the output of its NLP engine and emotion recognition engine. For example, inquiries containing keywords such as "account" or "password" are classified under the "account management" category. Next, the server adjusts the appropriate department and automated reply message based on the detected emotion. For example, if anger is detected, the inquiry is routed to the department that should handle it first.

[0271] Automatic sorting and responses based on emotion

[0272] The server adds categorized inquiries to the queue of the appropriate department. The server also selects an automated reply message template based on the user's sentiment and generates a customized automated reply email. This email includes standard answers to common questions, along with wording that is sensitive to the user's feelings.

[0273] Notification of response status and solution

[0274] The server notifies the user of the status of their inquiry. For example, the server sends the user a status update email stating, "Your inquiry has been forwarded to the account management team. We will address it promptly." Furthermore, once the issue is resolved, the server sends the user a final notification email containing the solution, completing the inquiry process.

[0275] Specific example

[0276] 1. The user enters the following into the website's contact form: "I have tried to reset my account password multiple times, but I still cannot log in. I am very frustrated." and clicks the submit button.

[0277] 2. The terminal sends the collected inquiry data to the server as an HTTP POST request.

[0278] 3. The server uses a natural language processing engine and an emotion recognition engine to extract the keywords "account" and "password" and the emotion "anger".

[0279] 4. The server categorizes the inquiry into "Account Management" and prioritizes forwarding it to the account management team.

[0280] 5. The server generates an automated reply email tailored to the user and sends it, including wording that promises a prompt response.

[0281] 6. The server will notify the user of the status of the issue and send a final notification email once the problem has been resolved. This email will include the solution.

[0282] Example of a prompt:

[0283] A user enters the following into the website's contact form: "I have tried to reset my account password multiple times, but I still cannot log in. I am very frustrated." and clicks the submit button.

[0284] As described above, the system according to the present invention can efficiently and accurately process inquiries from users and enable flexible responses according to the emotions of the users.

[0285] The flow of the specific process in Example 2 will be described with reference to FIG. 13.

[0286] Step 1: Inquiry reception

[0287] User: Enter "I have tried to reset my account password many times but still can't log in. I'm very frustrated." in the inquiry form on the website and click the send button.

[0288] Terminal: Collect the inquiry content entered by the user as form data.

[0289] Terminal: Send this inquiry data to the server as an HTTP POST request.

[0290] Input: Inquiry content based on the inquiry form.

[0291] Output: Inquiry data converted into an HTTP POST request.

[0292] Step 2: Inquiry analysis and emotion recognition

[0293] Server: Analyze the inquiry data received from the terminal.

[0294] Server: Use a natural language processing (NLP) engine (e.g., SpaCy, BERT) to tokenize the inquiry content and extract keywords and context.

[0295] Server: Use an emotion recognition engine (e.g., IBM Watson Tone Analyzer, Microsoft Azure Text Analytics) to detect the user's emotion from the inquiry content.

[0296] Input: Inquiry data received as an HTTP POST request.

[0297] Data processing: Tokenization of inquiry content, keyword extraction, sentiment recognition.

[0298] Output: Tokenized data, extracted keywords, detected sentiment (e.g., "anger").

[0299] Step 3: Inquiry classification and adjustment based on sentiment

[0300] Server: Classify the inquiry content into categories based on the outputs of the NLP engine and the sentiment recognition engine.

[0301] Server: For example, classify an inquiry containing keywords such as "account" and "password" into the "Account management" category.

[0302] Server: Adjust the corresponding department or the auto-reply message based on the detected sentiment. For example, if anger is detected, prioritize the allocation to the department responsible for handling.

[0303] Input: Tokenized data, extracted keywords, and detected sentiment.

[0304] Data processing: Categorization of inquiry content, determination of the corresponding department based on sentiment.

[0305] Output: Classified inquiry category, determination of the corresponding department.

[0306] Step 4: Automatic allocation and reply according to sentiment

[0307] Server: Add the classified inquiry to the queue of the appropriate department for handling. For example, prioritize the allocation of inquiries in the "Account management" category to the account management team.

[0308] Server: Select an appropriate automated reply message template based on the user's emotion. Choose a template that includes wording that takes the user's emotion (in this case, "anger") into consideration.

[0309] Server: Generates an automated reply email and sends it to the user, including "password reset instructions" and a statement promising a prompt response.

[0310] Input: Classified inquiry category, department to handle, sentiment data.

[0311] Data processing: Generating automated reply messages and distributing them to the appropriate department.

[0312] Output: Automated reply email, inquiry added to the queue of the relevant department.

[0313] Step 5: Notification of response status and solution

[0314] Server: Notifies the user of the status of their inquiry. For example, it might send a status update email stating, "Your inquiry has been forwarded to the account management team. We will address it promptly."

[0315] Server: Once the issue is resolved, a final notification email containing the solution will be sent to the user, and the inquiry ticket will be closed. This email will include specific steps for resolution and suggested improvements.

[0316] Input: Feedback from the relevant department, progress of the inquiry.

[0317] Data processing: Summarizing the status and solutions, and generating notification emails.

[0318] Output: Status update email, final notification email.

[0319] The above is a detailed explanation of the processing flow of this system's program.

[0320] (Application Example 2)

[0321] 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".

[0322] Conventional inquiry handling systems have struggled to properly categorize user inquiries and distribute them to the appropriate departments. Furthermore, they often fail to respond in a way that respects user emotions, potentially leading to decreased user satisfaction. In particular, in security services, it is crucial to quickly recognize and appropriately address user anxiety and anger; therefore, the ability to recognize and reflect emotions is essential. A system is needed to solve these problems and provide flexible, emotionally sensitive responses to user inquiries.

[0323] 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.

[0324] In this invention, the server includes means for receiving inquiries from users, means for analyzing inquiries using natural language processing and classifying them into categories, means for detecting the user's emotions using an emotion recognition engine, means for assigning inquiries to the appropriate department or an automated reply message based on the category and emotions, and means for notifying the user of the response status and solution. This enables a quick and accurate response to user inquiries, as well as a flexible response that takes the user's emotions into consideration.

[0325] A "user" is a person who uses the system to make inquiries.

[0326] An "inquiry" refers to a question or problem report submitted by a user to the system.

[0327] "Natural language processing" is a technology that enables computers to understand and analyze human language.

[0328] "Analysis" is the process of breaking down input data for a specific purpose and understanding its meaning and structure.

[0329] A "category" is a classification of topics or fields that characterize the content of an inquiry.

[0330] An "emotion recognition engine" is a technology that automatically detects emotions (e.g., anger, sadness, joy, etc.) from the content of a user's inquiry.

[0331] A "response department" is a specialized department that handles inquiries related to a specific category.

[0332] An "automatic reply message" is a response message that is generated by a system and automatically sent to the user.

[0333] "Response Status" refers to status information indicating the stage of the inquiry.

[0334] A "solution" refers to a solution or answer to a problem that a user is facing.

[0335] An "inquiry management system" is a system for recording and managing received inquiries and their processing status.

[0336] "Emotional information" refers to user emotional data extracted by an emotion recognition engine.

[0337] This invention relates to a system for efficiently processing user inquiries, and further incorporates an emotion engine that recognizes user emotions to adjust the response department or automated reply message according to those emotions. This system automates the reception, analysis (including emotion recognition), classification, sorting, and notification of inquiries, enabling flexible responses based on user emotions.

[0338] Hardware and software

[0339] Smartphone: A device used by users to input and submit inquiries.

[0340] Backend server: Built using Python, it handles inquiry data analysis, sentiment recognition, categorization, distribution to the appropriate department, generation of automated reply messages, and notifications.

[0341] The NLP engine spaCy is used to tokenize the query content and extract keywords and context.

[0342] Emotion recognition engine: Detects user emotions using Google® Cloud Natural Language API or Tensorflow®.

[0343] Messaging service: Use Firebase Cloud Messaging to send notifications to users.

[0344] Detailed description of the invention

[0345] 1. Inquiry reception

[0346] The user opens the application on their smartphone, enters their inquiry into a form for security-related questions and problem reports, and clicks the submit button.

[0347] The smartphone collects data entered by the user and sends it to a backend server in the cloud via an HTTP POST request.

[0348] 2. Inquiry Analysis and Sentiment Recognition

[0349] The server analyzes the received data using spaCy's NLP engine, tokenizes the input content, and extracts keywords and context.

[0350] Use the Google Cloud Natural Language API to detect user emotions (e.g., anger, sadness, anxiety).

[0351] 3. Inquiry classification and sentiment-based adjustment

[0352] Based on the results from the NLP engine, the server categorizes the query into categories such as "system error," "unauthorized access," and "phishing scam."

[0353] Based on the results of the emotion recognition engine, inquiries with high emotion scores will be processed preferentially.

[0354] 4. Automatic sorting and responses based on emotion

[0355] The server automatically routes classified inquiries to the appropriate department. For example, reports of unauthorized access are sent directly to the security team.

[0356] It generates emotion-based reply messages and sends customized messages to users, such as "We are investigating the situation" or "We promise to respond as soon as possible."

[0357] 5. Notification of response status and resolution.

[0358] The server will notify the user of the status of the issue as it progresses, and will send a final message and close the ticket once the problem is resolved.

[0359] Specific example

[0360] 1. User behavior

[0361] The user opens the application on their smartphone, types "I received a warning about unauthorized access when I tried to log in to a new account. I'm very worried," and clicks the send button.

[0362] 2. Server processing

[0363] The received data is analyzed using spaCy's NLP engine, and keywords (e.g., "new account," "login," "unauthorized access," "warning") are extracted.

[0364] The Google Cloud Natural Language API is used to analyze emotions and detect the emotion of "worry."

[0365] Inquiries are categorized as "unauthorized access" and forwarded to the security team on a priority basis based on their high sentiment score.

[0366] An emotion-based automated reply message, "We have received your report regarding unauthorized access. We will investigate immediately and take prompt action," is generated and sent to the user.

[0367] The system notifies the user of the status of their inquiry and sends a message stating, "Your inquiry is being handled with priority."

[0368] Example of a prompt

[0369] User inquiry: "When I tried to log in to my new account, I received a warning about unauthorized access. I'm very worried."

[0370] Tokenization using an NLP engine -> Keywords: ["New account", "Login", "Unauthorized access", "Warning"]

[0371] Emotion detection by emotion recognition engine -> Emotion: "Worry"

[0372] Classification: "Unauthorized Access"

[0373] Department in charge: Security Team

[0374] Automated reply message: "We have received your report regarding unauthorized access. We will investigate immediately and take prompt action."

[0375] Notice: "Inquiries are being handled with priority."

[0376] Final message: "The issue has been resolved. Your account is secure."

[0377] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0378] Step 1:

[0379] The user opens the application on their smartphone and enters their inquiry. Specifically, the user enters "I received a warning about unauthorized access when I tried to log in to a new account. I am very worried." into the text form on the software and clicks the submit button. The input data is the inquiry (input: user's inquiry, output: HTTP POST request).

[0380] Step 2:

[0381] The terminal sends the user's input as an HTTP POST request to the cloud backend server. Specifically, it converts the input data into a JSON payload and sends it to a specific endpoint on the server (e.g., / api / report_issue) (input: user's inquiry, output: JSON payload).

[0382] Step 3:

[0383] To analyze the data received by the server, spaCy's NLP engine is first used to tokenize the query content and extract keywords and context. For example, keywords such as "new account," "login," "unauthorized access," and "warning" are extracted (input: JSON payload, output: keywords and context).

[0384] Step 4:

[0385] The server uses the Google Cloud Natural Language API or a TensorFlow sentiment recognition model to detect emotions from the user's inquiry. For example, the emotion "worried" might be detected (input: inquiry (text), output: emotion information).

[0386] Step 5:

[0387] The server classifies queries into categories such as "unauthorized access" based on the results of the NLP engine and sentiment recognition. For example, based on the keywords "new account" and "unauthorized access," it will be classified into the "unauthorized access" category (input: keywords and sentiment information, output: category).

[0388] Step 6:

[0389] The server automatically routes inquiries to the appropriate department based on their sentiment score and category. For example, if the sentiment is "concerned," it is given a high priority and sent to the security team (input: category and sentiment information, output: appropriate department).

[0390] Step 7:

[0391] The server generates an automated reply message based on sentiment information and the content of the inquiry. For example, a message such as "We have received your report regarding unauthorized access. We will investigate immediately and take prompt action." will be generated (Input: Inquiry content and sentiment information, Output: Automated reply message).

[0392] Step 8:

[0393] The server uses Firebase Cloud Messaging to send a generated automated reply message to the user. The user receives the message on their smartphone and receives a notification that "Your inquiry is being handled with priority" (Input: Automated reply message, Output: Notification to user).

[0394] Step 9:

[0395] The server periodically notifies the user of the status of the inquiry. For example, a status update message such as "Your inquiry is currently under investigation" is sent (Input: Status, Output: Status update message).

[0396] Step 10:

[0397] Once the server resolves the issue, it sends a final notification message to the user and closes the inquiry ticket. For example, a message such as "The issue has been resolved. Your account is secure." is sent (Input: Resolution information, Output: Final notification message and ticket closure).

[0398] 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.

[0399] 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.

[0400] 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.

[0401] [Second Embodiment]

[0402] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0403] 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.

[0404] 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).

[0405] 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.

[0406] 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.

[0407] 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).

[0408] 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.

[0409] 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.

[0410] 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.

[0411] 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.

[0412] 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.

[0413] 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".

[0414] This invention relates to a system that efficiently processes user inquiries and routes them to the most appropriate department or automated reply message. This system enables a quick and accurate response by automating the receiving, analysis, classification, routing, and notification of inquiries.

[0415] Inquiry reception

[0416] The user fills out their inquiry in the website's contact form and clicks the submit button. The device receives the inquiry data entered by the user and sends it to the server as an HTTP POST request.

[0417] Query analysis and classification

[0418] The server analyzes the query data received from the terminal. Natural language processing (NLP) techniques are used for this analysis. The NLP engine tokenizes the query content, tags it with parts of speech, and extracts keywords and context. Based on the results of this analysis, the server determines the category of the query. For example, a query containing keywords such as "account" and "password" will be classified into the "account management" category.

[0419] Automatic distribution

[0420] The server routes categorized inquiries to the appropriate department or to an automated reply message. For example, inquiries categorized as "Account Management" are automatically forwarded to the account management team's response queue. The server can also generate automated reply emails based on the content of the inquiry. These automated reply emails contain standard answers to common questions and are sent to the user.

[0421] Notification of response status and solution

[0422] The server notifies the user of the status of their inquiry. For example, the server sends the user a status update email stating, "Your inquiry has been forwarded to the account management team. You will usually receive a response within 24 hours." Furthermore, once the issue is resolved, the server sends the user a final notification email containing the solution, completing the inquiry process.

[0423] Specific example

[0424] 1. The user enters "I forgot my account password" into the website's contact form and clicks the submit button.

[0425] 2. The terminal receives the form data entered by the user and sends an HTTP POST request to the server.

[0426] 3. The server analyzes the received query data using a natural language processing engine and extracts the keywords "account" and "password".

[0427] 4. The server categorizes the inquiry under "Account Management" and automatically forwards it to the appropriate department.

[0428] 5. The server generates an automated reply email and sends the user instructions on how to reset their password.

[0429] 6. The server notifies the user of the status of the request and sends a message stating, "You will usually receive a reply within 24 hours."

[0430] 7. The account management team will respond to user inquiries and provide specific instructions to resolve the issue.

[0431] 8. After the problem is resolved, the server will send a final notification email to the user and close the inquiry ticket.

[0432] In this way, the system based on the present invention efficiently and accurately processes user inquiries and enables a rapid response.

[0433] The following describes the processing flow.

[0434] Step 1:

[0435] The user enters their inquiry into the website's contact form and clicks the submit button.

[0436] Step 2:

[0437] The terminal collects the form data entered by the user and sends it to the server as an HTTP POST request.

[0438] Step 3:

[0439] The server parses the HTTP POST request received from the terminal and extracts the query content.

[0440] Step 4:

[0441] The server passes the query content to a natural language processing (NLP) engine, which performs tokenization, part-of-speech tagging, and dependency analysis.

[0442] Step 5:

[0443] The server extracts keywords and context from the query content based on the output of the NLP engine and determines the category of the query.

[0444] Step 6:

[0445] The server applies the appropriate processing rule based on the category of the inquiry. For example, for an inquiry categorized as "Account Management," the server applies a rule to forward it to the account management team.

[0446] Step 7:

[0447] The server adds the classified query to the queue of the relevant department.

[0448] Step 8:

[0449] The server simultaneously generates an automated reply email based on the inquiry. You select a template and fill in the user's name and specific information.

[0450] Step 9:

[0451] The server sends the generated automated reply email to the user's email address.

[0452] Step 10:

[0453] The server updates the status of the inquiry and notifies the user of the response status. For example, it might send an email stating, "Your inquiry has been forwarded to the account management team. You will usually receive a response within 24 hours."

[0454] Step 11:

[0455] The relevant department (e.g., the account management team) receives the inquiry and provides specific assistance to the user. If necessary, they will request additional information from the user.

[0456] Step 12:

[0457] Once the relevant department has completed the task, the server closes the inquiry ticket and sends a resolution notification email to the user.

[0458] The above describes the specific processing flow in the system of the present invention.

[0459] (Example 1)

[0460] 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."

[0461] Traditional inquiry handling systems often lacked the ability to quickly and accurately route user inquiries to the appropriate department. This resulted in delays and inappropriate processing, leading to a poor user experience. Furthermore, the manual analysis and classification of inquiries was often time-consuming and labor-intensive. Additionally, users were not adequately notified of the status of their inquiries, causing anxiety. To address these challenges, a system is needed that automates the inquiry handling process, enabling efficient and accurate inquiry processing.

[0462] 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.

[0463] In this invention, the server includes means for receiving inquiries from users, means for analyzing the received inquiries using natural language processing and extracting keywords and context, means for determining the category of the inquiry based on the extracted keywords, means for distributing the classified inquiries to the appropriate department or an automated reply message based on the category, and means for notifying the user of the status of the response and the solution. This makes it possible to quickly and accurately analyze and classify user inquiries and automatically distribute them to the appropriate department. Furthermore, by notifying the user of the response status in a timely manner, an improvement in the user experience can be expected.

[0464] An "inquiry" refers to a question or request that a user sends to a system in order to obtain information.

[0465] "Natural language processing" refers to the technology that enables computers to understand, interpret, and generate human language, and includes processes such as tokenization of text, part-of-speech tagging, and keyword extraction.

[0466] "Analysis" refers to the process of breaking down and understanding received query data, and specifically refers to the use of natural language processing techniques.

[0467] "Keywords" refer to important words or phrases extracted from the inquiry content, and serve as crucial clues for identifying the content of the inquiry.

[0468] "Context" refers to information that helps understand the overall meaning and background of an inquiry, and primarily serves to complement the meaning of keywords.

[0469] A "category" refers to a group classified based on the analyzed inquiry content, and specifically means a particular area such as account management or technical support.

[0470] "Routing" refers to the process of assigning analyzed and classified inquiries to the appropriate department or automated response message.

[0471] A "responsible department" refers to a department or team responsible for handling inquiries categorized into a specific group.

[0472] An "automatic reply message" refers to a standardized response message that the system automatically generates and sends to the user based on the content of the inquiry.

[0473] "Notifications" refer to information sent to users to inform them of the status of their inquiry and how it has been resolved.

[0474] This invention relates to a system that efficiently processes user inquiries and routes them to the most appropriate department or automated reply message. The following describes a specific implementation of this system.

[0475] Inquiry reception

[0476] The user fills out their inquiry in the website's contact form and clicks the submit button. The device receives the inquiry data entered by the user and sends it to the server as an HTTP POST request.

[0477] Query analysis and classification

[0478] The server analyzes the query data received from the terminal. Natural language processing (NLP) techniques are used for this analysis. Specifically, Python's natural language processing libraries, such as NLTK (Natural Language Toolkit) and SpaCy, can be used. The natural language processing engine tokenizes the query content, tags it with parts of speech, and extracts keywords and context. Based on the results of this analysis, the server determines the category of the query. For example, a query containing keywords such as "account" and "password" will be classified into the "account management" category.

[0479] Automatic distribution

[0480] The server routes classified inquiries to the appropriate department or to an automated reply message. For example, inquiries classified under the "Account Management" category are automatically forwarded to the account management team's response queue. The server can also generate automated reply emails based on the inquiry content. These automated reply emails contain standard answers to common questions and are sent to the user. An SMTP server (e.g., SendGrid) can be used to generate automated reply emails.

[0481] Notification of response status and solution

[0482] The server notifies the user of the status of their inquiry. For example, the server sends the user a status update email stating, "Your inquiry has been forwarded to the account management team. You will usually receive a response within 24 hours." Furthermore, once the issue is resolved, the server sends the user a final notification email containing the solution, completing the inquiry process.

[0483] Specific example

[0484] 1. The user enters "I forgot my account password" into the website's contact form and clicks the submit button.

[0485] 2. The terminal receives the form data entered by the user and sends an HTTP POST request to the server.

[0486] 3. The server analyzes the received query data using the NLTK natural language processing engine and extracts the keywords "account" and "password".

[0487] 4. The server categorizes the inquiry under "Account Management" and automatically forwards it to the appropriate department.

[0488] 5. The server generates an automated reply email via SendGrid, sending the user instructions for resetting their password.

[0489] 6. The server notifies the user of the status of the request and sends a message stating, "You will usually receive a reply within 24 hours."

[0490] 7. The account management team will respond to user inquiries and provide specific instructions to resolve the issue.

[0491] 8. After the problem is resolved, the server will send a final notification email to the user and close the inquiry ticket.

[0492] Example of a prompt

[0493] "Please provide a step-by-step explanation of the process of a program that uses an automated sorting system to analyze user inquiries and route them to the appropriate department. For example, if a user inquires, 'I forgot my account password,' please explain the detailed processing steps involved in each process."

[0494] As a result, the system based on the present invention can process user inquiries efficiently and accurately, enabling a rapid response.

[0495] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0496] Step 1: Receiving inquiry data

[0497] The user fills out their inquiry in the website's contact form and clicks the submit button.

[0498] The terminal receives the inquiry data entered by the user and sends it to the server as an HTTP POST request.

[0499] Input: The content of the inquiry entered by the user in the form.

[0500] Output: Query data in HTTP POST request format.

[0501] Specific action: The user enters "I forgot my account password" and clicks the submit button. The device packages this data as an HTTP request and sends it to the "POST / inquiry" endpoint.

[0502] Step 2: Inquiry month analysis

[0503] The server analyzes the query data received from the terminal using a natural language processing (NLP) engine.

[0504] Input: Query data as an HTTP POST request.

[0505] Output: Analyzed keywords and contextual information.

[0506] Specific operation: The server uses natural language processing libraries (NLTK or SpaCy) to tokenize the query content, tag it with part-of-speech tags, and extract the keywords "account" and "password".

[0507] Step 3: Classifying the inquiry

[0508] The server determines the category of the query based on the extracted keywords.

[0509] Input: Analyzed keywords and contextual information.

[0510] Output: Identified query category.

[0511] Specific operation: The server categorizes inquiries into the "account management" category based on the keywords "account" and "password".

[0512] Step 4: Automatically route inquiries

[0513] The server then routes the classified inquiries to the appropriate department or to an automated reply message.

[0514] Input: Identified inquiry category.

[0515] Output: Queue or automated reply message from the relevant department.

[0516] Specific actions: The server adds inquiries categorized as "account management" to the account management team's queue. It also generates an automated reply email, creating an email outlining the "password reset procedure."

[0517] Step 5: Notifying the user of the status of the response.

[0518] The server notifies the user of the status of the inquiry.

[0519] Input: Status data.

[0520] Output: Notification email to the user.

[0521] Specific action: The server sends the user an email stating, "Your inquiry has been forwarded to the account management team. You will usually receive a response within 24 hours."

[0522] Step 6: Final notification after problem resolution

[0523] The server will send the user a final notification email containing the solution once the problem is resolved.

[0524] Input: Problem-solving data.

[0525] Output: Final notification email to the user.

[0526] Specific action: The server sends an email to the user stating "Your account password has been reset" and closes the inquiry ticket.

[0527] Through these steps, this system efficiently processes user inquiries and enables quick and accurate responses.

[0528] (Application Example 1)

[0529] 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."

[0530] The objective of this invention is to provide a system that efficiently and accurately processes user inquiries and routes them to the most appropriate department or automated reply message. In particular, it aims to improve customer satisfaction in logistics centers by providing prompt and appropriate responses to inquiries regarding delivery delays, damaged goods, etc. Furthermore, it aims to improve the efficiency and accuracy of inquiry processing by automating the analysis, classification, and notification of inquiries.

[0531] 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.

[0532] In this invention, the server includes means for receiving inquiries from users, means for analyzing inquiries using natural language processing and classifying them into categories, means for distributing the classified inquiries to the appropriate department or an automated reply message based on the category, means for notifying the user of the status of the response and the solution, means for processing inquiries about delivery status within the logistics center, means for accurately analyzing inquiries about delivery delays and damaged goods and distributing them to the appropriate department, and means for providing the user with an automated reply message regarding delivery delays and damaged goods. This enables more efficient and rapid response to inquiries in the logistics center.

[0533] A "user" is a person or organization that uses the system to make inquiries.

[0534] An "inquiry" refers to the content of a question, request, or problem report that a user provides through the system.

[0535] "Natural language processing" is a technology that enables computers to understand and analyze human language.

[0536] A "category" is a classification used to categorize inquiries based on specific themes or issues.

[0537] The "responsible department" refers to the department or person responsible for providing an appropriate response to a classified inquiry.

[0538] An "automatic reply message" is a response message that a system automatically generates based on a user's inquiry.

[0539] "Status" refers to information indicating the current status of an inquiry.

[0540] "Solution" refers to a specific response or means of resolving an inquiry.

[0541] A "logistics center" is a facility that handles the distribution, management, and related operations of goods.

[0542] "Delivery status" refers to information indicating the current progress and any issues related to the delivery of the product.

[0543] "Delivery delay" refers to a situation where delivery is delayed beyond the scheduled delivery time.

[0544] "Product damage" refers to a condition in which a product is damaged during delivery.

[0545] "Analysis" is the process by which a system examines the content of a query in detail and extracts its meaning.

[0546] "Classification" refers to dividing the analyzed query content into specific categories.

[0547] "Routing" is the process of sending classified inquiries to the appropriate department or message.

[0548] "Automatic reply" refers to a system automatically sending a response message to a user.

[0549] This invention is a system that efficiently processes user inquiries and routes them to the most appropriate department or automated reply message. In particular, it enables quick and appropriate responses to inquiries regarding delivery delays and damaged goods in logistics centers. The specific implementation of this invention will be described below in several steps.

[0550] First, the user accesses the system using a smartphone or computer and enters their inquiry. The user enters "Delivery is delayed" into the inquiry form on the website and clicks the submit button. The device receives the entered inquiry data and sends it to the server as an HTTP POST request.

[0551] The server processes the received data using a parsing module equipped with a natural language processing engine. Specifically, it uses the Python Django framework and the spaCy library to tokenize the inquiry content, tag it with parts of speech, and extract keywords. This process classifies the inquiry content into categories such as "delivery delay" or "product damage."

[0552] Next, the server automatically forwards the classified inquiries to the appropriate department. For example, an inquiry about "delivery delay" is forwarded to the delivery management team, and an inquiry about "damaged goods" is forwarded to the quality assurance team. This is done by using Django models to record the inquiry details in the database and notify the appropriate department.

[0553] The server generates an automated reply message to inform the user of the status of the response. This message is created based on a pre-configured template and sent to the user via email or in-app notification. For example, a message such as "We have received your inquiry regarding the delivery delay. We will forward it to the appropriate department." might be automatically generated.

[0554] In a specific use case at a logistics center, if a user enters "My delivery is delayed," this inquiry is categorized as "Delivery Delay." The server then generates an automated reply message stating, "We have received your inquiry regarding a delivery delay. We will forward it to the appropriate department," and notifies the user. Based on this, the appropriate department is also automatically notified.

[0555] In this way, the system can process user inquiries quickly and accurately, and streamline inquiry handling at the logistics center.

[0556] Example of a prompt:

[0557] text

[0558] It seems my package is delayed in transit. Could you please check on it?

[0559] This prompt causes the system to categorize the request as a "delivery delay," route it to the appropriate department, and send an automated reply message to the user.

[0560] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0561] Step 1:

[0562] A user enters "My delivery is delayed" into the website's contact form and clicks the submit button. The input is the user's inquiry. Based on this input, the device sends the inquiry data to the server as an HTTP POST request. The output is the HTTP POST request to the server.

[0563] Step 2:

[0564] The server analyzes the received query data. Natural language processing (NLP) techniques are used for this analysis. Specifically, the server utilizes the Python Django framework and the spaCy library to tokenize the query content, tag it with parts of speech, and extract keywords. For this purpose, the server is equipped with an NLP engine. The input is the user's query data, and the output is the extracted keywords and the tokenized query data.

[0565] Step 3:

[0566] The server categorizes the inquiry based on the analysis results. Examples of such categories include "delivery delay" and "damaged goods." In this classification step, the inquiry is assigned to the appropriate category based on the extracted keywords. The input is the analysis results obtained in step 2, and the output is the classified category.

[0567] Step 4:

[0568] The server forwards classified queries to the appropriate department. Specifically, it uses a Django model to record the query details in the database and then notifies the appropriate department. The input is classified category information and the query details, and the output is recording to the database and notifying the appropriate department.

[0569] Step 5:

[0570] The server generates an automated reply message informing the user of the status and resolution of their inquiry. This message is created based on a pre-configured template. For example, it might say, "We have received your inquiry regarding the delivery delay. We are forwarding it to the appropriate department." The input is the inquiry content and classification information, and the output is the automatically generated reply message.

[0571] Step 6:

[0572] The server sends the generated automated reply message to the user. Specifically, it sends the message to the user via the mail server or sends an in-app notification. The input is the automated reply message, and the output is the notification to the user.

[0573] For example, if a user enters "My delivery is delayed," the server categorizes this inquiry as "Delivery Delay" and forwards it to the appropriate department. An automated reply message, "We have received your inquiry regarding a delivery delay. We will forward it to the appropriate department," is then generated and sent to the user.

[0574] 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.

[0575] This invention relates to a system for efficiently processing user inquiries, and further incorporates an emotion engine that recognizes user emotions to adjust the response department or automated reply message according to those emotions. This system automates the reception, analysis (including emotion recognition), classification, sorting, and notification of inquiries, enabling flexible responses based on user emotions.

[0576] Inquiry reception

[0577] The user enters their inquiry into the website's contact form and clicks the submit button. The device collects the inquiry data entered by the user and sends it to the server as an HTTP POST request.

[0578] Inquiry analysis and sentiment recognition

[0579] The server analyzes the query data received from the terminal. This analysis uses natural language processing (NLP) technology and an emotion recognition engine. The NLP engine tokenizes the query content, tags it with parts of speech, and extracts keywords and context. Furthermore, the emotion recognition engine detects emotions (e.g., anger, sadness, joy, etc.) from the user's query content.

[0580] Inquiry classification and sentiment-based adjustment

[0581] The server categorizes inquiries based on the output of its NLP engine and emotion recognition engine. For example, inquiries containing keywords such as "account" and "password" are categorized under "account management." Next, the server adjusts the appropriate department and automated reply message based on the detected emotion. For example, if anger is detected, the inquiry is routed to a department that prioritizes handling it.

[0582] Automatic sorting and responses based on emotion

[0583] The server adds categorized inquiries to the queue of the appropriate department. The server also selects an automated reply message template based on the user's sentiment and generates a customized automated reply email. This email includes standard answers to common questions, along with wording that is sensitive to the user's feelings.

[0584] Notification of response status and solution

[0585] The server notifies the user of the status of their inquiry. For example, the server sends the user a status update email stating, "Your inquiry has been forwarded to the account management team. We will respond more quickly than usual." Furthermore, once the issue is resolved, the server sends the user a final notification email containing the solution, completing the inquiry process.

[0586] Specific example

[0587] 1. The user enters the following into the website's contact form: "I have tried to reset my account password multiple times, but I still cannot log in. I am very frustrated." and clicks the submit button.

[0588] 2. The terminal collects the form data entered by the user and sends an HTTP POST request to the server.

[0589] 3. The server analyzes the received inquiry data using NLP and an emotion recognition engine, extracting the keywords "account" and "password" and the emotion "anger."

[0590] 4. The server categorizes inquiries into "account management" and prioritizes forwarding them to the account management team based on the user's sentiment.

[0591] 5. The server generates an emotion-based automated reply email and sends it to the user, including "password reset instructions" and a promise of "prompt action."

[0592] 6. The server notifies the user of the status of the inquiry and sends a message stating, "Your inquiry will be handled with priority."

[0593] 7. The account management team will receive inquiries and provide users with prompt and specific responses.

[0594] 8. After the problem is resolved, the server will send a final notification email to the user and close the inquiry ticket.

[0595] In this way, the system based on the present invention efficiently and accurately processes user inquiries and enables flexible responses that respond to the user's emotions.

[0596] The following describes the processing flow.

[0597] Step 1:

[0598] The user enters their inquiry into the website's contact form and clicks the submit button, stating, "I have tried to reset my account password multiple times, but I still cannot log in. I am extremely frustrated."

[0599] Step 2:

[0600] The terminal collects the form data entered by the user and sends it to the server as an HTTP POST request.

[0601] Step 3:

[0602] The server parses the HTTP POST request received from the terminal and extracts the query content.

[0603] Step 4:

[0604] The server passes the query content to a natural language processing (NLP) engine, which performs tokenization, part-of-speech tagging, and dependency analysis.

[0605] Step 5:

[0606] Based on the output of the NLP engine, the server extracts keywords and context from the query content, identifying keywords such as "account," "password," and "unable to log in."

[0607] Step 6:

[0608] The server passes the user's inquiry to the sentiment recognition engine, which then detects emotions (e.g., anger) within the text.

[0609] Step 7:

[0610] The server categorizes inquiries into "account management" and, based on sentiment recognition results, flags them as inquiries requiring priority attention.

[0611] Step 8:

[0612] The server adds the categorized query to the priority queue for the account management team.

[0613] Step 9:

[0614] The server selects an appropriate template based on the inquiry content and sentiment recognition results, and generates an automated reply email. The template includes phrases such as "Password reset instructions" and "A promise of a prompt response."

[0615] Step 10:

[0616] The server sends the generated automated reply email to the user's email address.

[0617] Step 11:

[0618] The server updates the status of the inquiry and sends the user a status update email stating, "Your inquiry has been forwarded to the account management team as a priority. We will respond promptly."

[0619] Step 12:

[0620] The account management team receives inquiries and responds quickly to user issues. They provide additional information to guide users through support procedures as needed.

[0621] Step 13:

[0622] Once the issue is resolved, the server closes the inquiry ticket and sends a final notification email to the user.

[0623] The above describes the specific processing flow in the system of the present invention.

[0624] (Example 2)

[0625] 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".

[0626] Many modern systems are required to efficiently handle user inquiries, but they face the challenge of providing flexible responses that take into account user emotions. When users are frustrated or angry, a quick and appropriate response is needed, but current systems often fall short in this regard. Furthermore, routing inquiries to the appropriate department based on their content is crucial, but this process is often done manually, lacking efficiency. Therefore, there is a need for an efficient and accurate inquiry processing system that includes responses that take user emotions into account.

[0627] 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 users, means for analyzing the inquiries using natural language processing and classifying them into categories, means for detecting emotions from the content of the inquiries, means for distributing the inquiries to the appropriate department or an automated reply message based on the classification and detected emotions, and means for notifying the user of the status of the response and the solution. This enables flexible responses in accordance with the user's emotions, improving the efficiency and accuracy of inquiry processing.

[0628] A "user" refers to anyone who submits a question or problem using the contact form.

[0629] A "terminal" refers to a device used by a user (for example, a personal computer or smartphone), which has the role of collecting inquiry data and sending it to the server.

[0630] A "server" refers to a central processing unit that analyzes, classifies, distributes, and notifies query data received from terminals.

[0631] "Inquiry" refers to a question or problem that a user enters into a website's inquiry form.

[0632] "Natural language processing" refers to the technology that enables computers to understand, interpret, and generate human language.

[0633] A "category" refers to a classification group based on the content of the inquiry.

[0634] "Analysis" refers to the process of tokenizing the content of an inquiry and extracting keywords and context.

[0635] "Emotion recognition" refers to the technology that detects a user's emotions (for example, anger, sadness, joy, etc.) from the content of their inquiry.

[0636] "Routing" refers to the process of distributing inquiries to the appropriate department or automated response message based on classification and detected sentiment.

[0637] The term "responsible department" refers to the department responsible for handling inquiries in a specific category.

[0638] An "automatic reply message" refers to a standard response message that a system automatically generates and sends to the user.

[0639] "Notification" refers to the process of informing the user about the status of their inquiry and how it has been resolved.

[0640] This invention relates to a system for efficiently processing user inquiries, which, by incorporating an emotion engine that recognizes user emotions, adjusts the responding department and automated reply messages according to those emotions. This system automates the receiving, analysis (including emotion recognition), classification, sorting, and notification of inquiries, enabling flexible responses based on user emotions.

[0641] Inquiry reception

[0642] The user enters their inquiry into the website's contact form and clicks the submit button. The device sends the user's entered inquiry data to the server as an HTTP POST request. The device collects inquiries through web browsers and mobile apps and sends them to the server.

[0643] Inquiry analysis and sentiment recognition

[0644] The server analyzes the query data received from the terminal. This analysis uses natural language processing (NLP) techniques and an emotion recognition engine. SpaCy and BERT can be used as the natural language processing engine. This tokenizes the query content and extracts keywords and context. Furthermore, IBM Watson Tone Analyzer and Microsoft Azure Text Analytics are used as emotion recognition engines to detect emotions (e.g., anger, sadness, joy, etc.) from the user's query content.

[0645] Inquiry classification and sentiment-based adjustment

[0646] The server categorizes inquiries based on the output of its NLP engine and emotion recognition engine. For example, inquiries containing keywords such as "account" or "password" are classified under the "account management" category. Next, the server adjusts the appropriate department and automated reply message based on the detected emotion. For example, if anger is detected, the inquiry is routed to the department that should handle it first.

[0647] Automatic sorting and responses based on emotion

[0648] The server adds categorized inquiries to the queue of the appropriate department. The server also selects an automated reply message template based on the user's sentiment and generates a customized automated reply email. This email includes standard answers to common questions, along with wording that is sensitive to the user's feelings.

[0649] Notification of response status and solution

[0650] The server notifies the user of the status of their inquiry. For example, the server sends the user a status update email stating, "Your inquiry has been forwarded to the account management team. We will address it promptly." Furthermore, once the issue is resolved, the server sends the user a final notification email containing the solution, completing the inquiry process.

[0651] Specific example

[0652] 1. The user enters the following into the website's contact form: "I have tried to reset my account password multiple times, but I still cannot log in. I am very frustrated." and clicks the submit button.

[0653] 2. The terminal sends the collected inquiry data to the server as an HTTP POST request.

[0654] 3. The server uses a natural language processing engine and an emotion recognition engine to extract the keywords "account" and "password" and the emotion "anger".

[0655] 4. The server categorizes the inquiry into "Account Management" and prioritizes forwarding it to the account management team.

[0656] 5. The server generates an automated reply email tailored to the user and sends it, including wording that promises a prompt response.

[0657] 6. The server will notify the user of the status of the issue and send a final notification email once the problem has been resolved. This email will include the solution.

[0658] Example of a prompt:

[0659] A user enters the following into the website's contact form: "I have tried to reset my account password multiple times, but I still cannot log in. I am very frustrated." and clicks the submit button.

[0660] As described above, the system based on the present invention efficiently and accurately processes user inquiries and enables flexible responses that respond to the user's emotions.

[0661] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0662] Step 1: Inquiry Submission

[0663] User: Enters the following into the website's contact form: "I have tried to reset my account password multiple times, but I still cannot log in. I am very frustrated." and clicks the submit button.

[0664] Terminal: Collects user-entered inquiry content as form data.

[0665] Terminal: Send this query data to the server as an HTTP POST request.

[0666] Input: Inquiry content based on the contact form.

[0667] Output: Query data converted into an HTTP POST request.

[0668] Step 2: Inquiry Analysis and Sentiment Recognition

[0669] Server: Analyzes query data received from terminals.

[0670] Server: Uses a natural language processing (NLP) engine (e.g., SpaCy, BERT) to tokenize the query content and extract keywords and context.

[0671] Server: Uses an emotion recognition engine (e.g., IBM Watson Tone Analyzer, Microsoft Azure Text Analytics) to detect user emotions from the query content.

[0672] Input: Query data received as an HTTP POST request.

[0673] Data processing: Tokenization of inquiry content, keyword extraction, sentiment recognition.

[0674] Output: Tokenized data, extracted keywords, detected emotions (e.g., "anger").

[0675] Step 3: Inquiry classification and sentiment-based adjustment

[0676] Server: Classifies the query content into categories based on the output of the NLP engine and the emotion recognition engine.

[0677] Server: For example, queries containing keywords such as "account" and "password" are categorized under "account management".

[0678] Server: Based on detected emotions, it adjusts the appropriate department and automated response message. For example, if anger is detected, it prioritizes routing the request to the appropriate department.

[0679] Input: Tokenized data, extracted keywords, and detected sentiment.

[0680] Data processing: Categorizing inquiries and determining which department should handle them based on their emotional impact.

[0681] Output: Classified inquiry category, determination of the relevant department.

[0682] Step 4: Automatic sorting and emotionally responsive replies

[0683] Server: Adds classified inquiries to the queue of the appropriate department. For example, inquiries in the "Account Management" category are prioritized for the account management team.

[0684] Server: Select an appropriate automated reply message template based on the user's emotion. Choose a template that includes wording that takes the user's emotion (in this case, "anger") into consideration.

[0685] Server: Generates an automated reply email and sends it to the user, including "password reset instructions" and a statement promising a prompt response.

[0686] Input: Classified inquiry category, department to handle, sentiment data.

[0687] Data processing: Generating automated reply messages and distributing them to the appropriate department.

[0688] Output: Automated reply email, inquiry added to the queue of the relevant department.

[0689] Step 5: Notification of response status and solution

[0690] Server: Notifies the user of the status of their inquiry. For example, it might send a status update email stating, "Your inquiry has been forwarded to the account management team. We will address it promptly."

[0691] Server: Once the issue is resolved, a final notification email containing the solution will be sent to the user, and the inquiry ticket will be closed. This email will include specific steps for resolution and suggested improvements.

[0692] Input: Feedback from the relevant department, progress of the inquiry.

[0693] Data processing: Summarizing the status and solutions, and generating notification emails.

[0694] Output: Status update email, final notification email.

[0695] The above is a detailed explanation of the processing flow of this system's program.

[0696] (Application Example 2)

[0697] 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."

[0698] Conventional inquiry handling systems have struggled to properly categorize user inquiries and distribute them to the appropriate departments. Furthermore, they often fail to respond in a way that respects user emotions, potentially leading to decreased user satisfaction. In particular, in security services, it is crucial to quickly recognize and appropriately address user anxiety and anger; therefore, the ability to recognize and reflect emotions is essential. A system is needed to solve these problems and provide flexible, emotionally sensitive responses to user inquiries.

[0699] 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.

[0700] In this invention, the server includes means for receiving inquiries from users, means for analyzing inquiries using natural language processing and classifying them into categories, means for detecting the user's emotions using an emotion recognition engine, means for assigning inquiries to the appropriate department or an automated reply message based on the category and emotions, and means for notifying the user of the response status and solution. This enables a quick and accurate response to user inquiries, as well as a flexible response that takes the user's emotions into consideration.

[0701] A "user" is a person who uses the system to make inquiries.

[0702] An "inquiry" refers to a question or problem report submitted by a user to the system.

[0703] "Natural language processing" is a technology that enables computers to understand and analyze human language.

[0704] "Analysis" is the process of breaking down input data for a specific purpose and understanding its meaning and structure.

[0705] A "category" is a classification of topics or fields that characterize the content of an inquiry.

[0706] An "emotion recognition engine" is a technology that automatically detects emotions (e.g., anger, sadness, joy, etc.) from the content of a user's inquiry.

[0707] A "response department" is a specialized department that handles inquiries related to a specific category.

[0708] An "automatic reply message" is a response message that is generated by a system and automatically sent to the user.

[0709] "Response Status" refers to status information indicating the stage of the inquiry.

[0710] A "solution" refers to a solution or answer to a problem that a user is facing.

[0711] An "inquiry management system" is a system for recording and managing received inquiries and their processing status.

[0712] "Emotional information" refers to user emotional data extracted by an emotion recognition engine.

[0713] This invention relates to a system for efficiently processing user inquiries, and further incorporates an emotion engine that recognizes user emotions to adjust the response department or automated reply message according to those emotions. This system automates the reception, analysis (including emotion recognition), classification, sorting, and notification of inquiries, enabling flexible responses based on user emotions.

[0714] Hardware and software

[0715] Smartphone: A device used by users to input and submit inquiries.

[0716] Backend server: Built using Python, it handles inquiry data analysis, sentiment recognition, categorization, distribution to the appropriate department, generation of automated reply messages, and notifications.

[0717] The NLP engine spaCy is used to tokenize the query content and extract keywords and context.

[0718] Emotion recognition engine: Detects user emotions using Google Cloud Natural Language API or TensorFlow.

[0719] Messaging service: Use Firebase Cloud Messaging to send notifications to users.

[0720] Detailed description of the invention

[0721] 1. Inquiry reception

[0722] The user opens the application on their smartphone, enters their inquiry into a form for security-related questions and problem reports, and clicks the submit button.

[0723] The smartphone collects data entered by the user and sends it to a backend server in the cloud via an HTTP POST request.

[0724] 2. Inquiry Analysis and Sentiment Recognition

[0725] The server analyzes the received data using spaCy's NLP engine, tokenizes the input content, and extracts keywords and context.

[0726] Use the Google Cloud Natural Language API to detect user emotions (e.g., anger, sadness, anxiety).

[0727] 3. Inquiry classification and sentiment-based adjustment

[0728] Based on the results from the NLP engine, the server categorizes the query into categories such as "system error," "unauthorized access," and "phishing scam."

[0729] Based on the results of the emotion recognition engine, inquiries with high emotion scores will be processed preferentially.

[0730] 4. Automatic sorting and responses based on emotion

[0731] The server automatically routes classified inquiries to the appropriate department. For example, reports of unauthorized access are sent directly to the security team.

[0732] It generates emotion-based reply messages and sends customized messages to users, such as "We are investigating the situation" or "We promise to respond as soon as possible."

[0733] 5. Notification of response status and resolution.

[0734] The server will notify the user of the status of the issue as it progresses, and will send a final message and close the ticket once the problem is resolved.

[0735] Specific example

[0736] 1. User behavior

[0737] The user opens the application on their smartphone, types "I received a warning about unauthorized access when I tried to log in to a new account. I'm very worried," and clicks the send button.

[0738] 2. Server processing

[0739] The received data is analyzed using spaCy's NLP engine, and keywords (e.g., "new account," "login," "unauthorized access," "warning") are extracted.

[0740] The Google Cloud Natural Language API is used to analyze emotions and detect the emotion of "worry."

[0741] Inquiries are categorized as "unauthorized access" and forwarded to the security team on a priority basis based on their high sentiment score.

[0742] An emotion-based automated reply message, "We have received your report regarding unauthorized access. We will investigate immediately and take prompt action," is generated and sent to the user.

[0743] The system notifies the user of the status of their inquiry and sends a message stating, "Your inquiry is being handled with priority."

[0744] Example of a prompt

[0745] User inquiry: "When I tried to log in to my new account, I received a warning about unauthorized access. I'm very worried."

[0746] Tokenization using an NLP engine -> Keywords: ["New account", "Login", "Unauthorized access", "Warning"]

[0747] Emotion detection by emotion recognition engine -> Emotion: "Worry"

[0748] Classification: "Unauthorized Access"

[0749] Department in charge: Security Team

[0750] Automated reply message: "We have received your report regarding unauthorized access. We will investigate immediately and take prompt action."

[0751] Notice: "Inquiries are being handled with priority."

[0752] Final message: "The issue has been resolved. Your account is secure."

[0753] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0754] Step 1:

[0755] The user opens the application on their smartphone and enters their inquiry. Specifically, the user enters "I received a warning about unauthorized access when I tried to log in to a new account. I am very worried." into the text form on the software and clicks the submit button. The input data is the inquiry (input: user's inquiry, output: HTTP POST request).

[0756] Step 2:

[0757] The terminal sends the user's input as an HTTP POST request to the cloud backend server. Specifically, it converts the input data into a JSON payload and sends it to a specific endpoint on the server (e.g., / api / report_issue) (input: user's inquiry, output: JSON payload).

[0758] Step 3:

[0759] To analyze the data received by the server, spaCy's NLP engine is first used to tokenize the query content and extract keywords and context. For example, keywords such as "new account," "login," "unauthorized access," and "warning" are extracted (input: JSON payload, output: keywords and context).

[0760] Step 4:

[0761] The server uses the Google Cloud Natural Language API or a TensorFlow sentiment recognition model to detect emotions from the user's inquiry. For example, the emotion "worried" might be detected (input: inquiry (text), output: emotion information).

[0762] Step 5:

[0763] The server classifies queries into categories such as "unauthorized access" based on the results of the NLP engine and sentiment recognition. For example, based on the keywords "new account" and "unauthorized access," it will be classified into the "unauthorized access" category (input: keywords and sentiment information, output: category).

[0764] Step 6:

[0765] The server automatically routes inquiries to the appropriate department based on their sentiment score and category. For example, if the sentiment is "concerned," it is given a high priority and sent to the security team (input: category and sentiment information, output: appropriate department).

[0766] Step 7:

[0767] The server generates an automated reply message based on sentiment information and the content of the inquiry. For example, a message such as "We have received your report regarding unauthorized access. We will investigate immediately and take prompt action." will be generated (Input: Inquiry content and sentiment information, Output: Automated reply message).

[0768] Step 8:

[0769] The server uses Firebase Cloud Messaging to send a generated automated reply message to the user. The user receives the message on their smartphone and receives a notification that "Your inquiry is being handled with priority" (Input: Automated reply message, Output: Notification to user).

[0770] Step 9:

[0771] The server periodically notifies the user of the status of the inquiry. For example, a status update message such as "Your inquiry is currently under investigation" is sent (Input: Status, Output: Status update message).

[0772] Step 10:

[0773] Once the server resolves the issue, it sends a final notification message to the user and closes the inquiry ticket. For example, a message such as "The issue has been resolved. Your account is secure." is sent (Input: Resolution information, Output: Final notification message and ticket closure).

[0774] 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.

[0775] 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.

[0776] 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.

[0777] [Third Embodiment]

[0778] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0779] 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.

[0780] 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).

[0781] 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.

[0782] 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.

[0783] 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).

[0784] 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.

[0785] 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.

[0786] 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.

[0787] 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.

[0788] 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.

[0789] 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".

[0790] This invention relates to a system that efficiently processes user inquiries and routes them to the most appropriate department or automated reply message. This system enables a quick and accurate response by automating the receiving, analysis, classification, routing, and notification of inquiries.

[0791] Inquiry reception

[0792] The user fills out their inquiry in the website's contact form and clicks the submit button. The device receives the inquiry data entered by the user and sends it to the server as an HTTP POST request.

[0793] Query analysis and classification

[0794] The server analyzes the query data received from the terminal. Natural language processing (NLP) techniques are used for this analysis. The NLP engine tokenizes the query content, tags it with parts of speech, and extracts keywords and context. Based on the results of this analysis, the server determines the category of the query. For example, a query containing keywords such as "account" and "password" will be classified into the "account management" category.

[0795] Automatic distribution

[0796] The server routes categorized inquiries to the appropriate department or to an automated reply message. For example, inquiries categorized as "Account Management" are automatically forwarded to the account management team's response queue. The server can also generate automated reply emails based on the content of the inquiry. These automated reply emails contain standard answers to common questions and are sent to the user.

[0797] Notification of response status and solution

[0798] The server notifies the user of the status of their inquiry. For example, the server sends the user a status update email stating, "Your inquiry has been forwarded to the account management team. You will usually receive a response within 24 hours." Furthermore, once the issue is resolved, the server sends the user a final notification email containing the solution, completing the inquiry process.

[0799] Specific example

[0800] 1. The user enters "I forgot my account password" into the website's contact form and clicks the submit button.

[0801] 2. The terminal receives the form data entered by the user and sends an HTTP POST request to the server.

[0802] 3. The server analyzes the received query data using a natural language processing engine and extracts the keywords "account" and "password".

[0803] 4. The server categorizes the inquiry under "Account Management" and automatically forwards it to the appropriate department.

[0804] 5. The server generates an automated reply email and sends the user instructions on how to reset their password.

[0805] 6. The server notifies the user of the status of the request and sends a message stating, "You will usually receive a reply within 24 hours."

[0806] 7. The account management team will respond to user inquiries and provide specific instructions to resolve the issue.

[0807] 8. After the problem is resolved, the server will send a final notification email to the user and close the inquiry ticket.

[0808] In this way, the system based on the present invention efficiently and accurately processes user inquiries and enables a rapid response.

[0809] The following describes the processing flow.

[0810] Step 1:

[0811] The user enters their inquiry into the website's contact form and clicks the submit button.

[0812] Step 2:

[0813] The terminal collects the form data entered by the user and sends it to the server as an HTTP POST request.

[0814] Step 3:

[0815] The server parses the HTTP POST request received from the terminal and extracts the query content.

[0816] Step 4:

[0817] The server passes the query content to a natural language processing (NLP) engine, which performs tokenization, part-of-speech tagging, and dependency analysis.

[0818] Step 5:

[0819] The server extracts keywords and context from the query content based on the output of the NLP engine and determines the category of the query.

[0820] Step 6:

[0821] The server applies the appropriate processing rule based on the category of the inquiry. For example, for an inquiry categorized as "Account Management," the server applies a rule to forward it to the account management team.

[0822] Step 7:

[0823] The server adds the classified query to the queue of the relevant department.

[0824] Step 8:

[0825] The server simultaneously generates an automated reply email based on the inquiry. You select a template and fill in the user's name and specific information.

[0826] Step 9:

[0827] The server sends the generated automated reply email to the user's email address.

[0828] Step 10:

[0829] The server updates the status of the inquiry and notifies the user of the response status. For example, it might send an email stating, "Your inquiry has been forwarded to the account management team. You will usually receive a response within 24 hours."

[0830] Step 11:

[0831] The relevant department (e.g., the account management team) receives the inquiry and provides specific assistance to the user. If necessary, they will request additional information from the user.

[0832] Step 12:

[0833] Once the relevant department has completed the task, the server closes the inquiry ticket and sends a resolution notification email to the user.

[0834] The above describes the specific processing flow in the system of the present invention.

[0835] (Example 1)

[0836] 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."

[0837] Traditional inquiry handling systems often lacked the ability to quickly and accurately route user inquiries to the appropriate department. This resulted in delays and inappropriate processing, leading to a poor user experience. Furthermore, the manual analysis and classification of inquiries was often time-consuming and labor-intensive. Additionally, users were not adequately notified of the status of their inquiries, causing anxiety. To address these challenges, a system is needed that automates the inquiry handling process, enabling efficient and accurate inquiry processing.

[0838] 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.

[0839] In this invention, the server includes means for receiving inquiries from users, means for analyzing the received inquiries using natural language processing and extracting keywords and context, means for determining the category of the inquiry based on the extracted keywords, means for distributing the classified inquiries to the appropriate department or an automated reply message based on the category, and means for notifying the user of the status of the response and the solution. This makes it possible to quickly and accurately analyze and classify user inquiries and automatically distribute them to the appropriate department. Furthermore, by notifying the user of the response status in a timely manner, an improvement in the user experience can be expected.

[0840] An "inquiry" refers to a question or request that a user sends to a system in order to obtain information.

[0841] "Natural language processing" refers to the technology that enables computers to understand, interpret, and generate human language, and includes processes such as tokenization of text, part-of-speech tagging, and keyword extraction.

[0842] "Analysis" refers to the process of breaking down and understanding received query data, and specifically refers to the use of natural language processing techniques.

[0843] "Keywords" refer to important words or phrases extracted from the inquiry content, and serve as crucial clues for identifying the content of the inquiry.

[0844] "Context" refers to information that helps understand the overall meaning and background of an inquiry, and primarily serves to complement the meaning of keywords.

[0845] A "category" refers to a group classified based on the analyzed inquiry content, and specifically means a particular area such as account management or technical support.

[0846] "Routing" refers to the process of assigning analyzed and classified inquiries to the appropriate department or automated response message.

[0847] A "responsible department" refers to a department or team responsible for handling inquiries categorized into a specific group.

[0848] An "automatic reply message" refers to a standardized response message that the system automatically generates and sends to the user based on the content of the inquiry.

[0849] "Notifications" refer to information sent to users to inform them of the status of their inquiry and how it has been resolved.

[0850] This invention relates to a system that efficiently processes user inquiries and routes them to the most appropriate department or automated reply message. The following describes a specific implementation of this system.

[0851] Inquiry reception

[0852] The user fills out their inquiry in the website's contact form and clicks the submit button. The device receives the inquiry data entered by the user and sends it to the server as an HTTP POST request.

[0853] Query analysis and classification

[0854] The server analyzes the query data received from the terminal. Natural language processing (NLP) techniques are used for this analysis. Specifically, Python's natural language processing libraries, such as NLTK (Natural Language Toolkit) and SpaCy, can be used. The natural language processing engine tokenizes the query content, tags it with parts of speech, and extracts keywords and context. Based on the results of this analysis, the server determines the category of the query. For example, a query containing keywords such as "account" and "password" will be classified into the "account management" category.

[0855] Automatic distribution

[0856] The server routes classified inquiries to the appropriate department or to an automated reply message. For example, inquiries classified under the "Account Management" category are automatically forwarded to the account management team's response queue. The server can also generate automated reply emails based on the inquiry content. These automated reply emails contain standard answers to common questions and are sent to the user. An SMTP server (e.g., SendGrid) can be used to generate automated reply emails.

[0857] Notification of response status and solution

[0858] The server notifies the user of the status of their inquiry. For example, the server sends the user a status update email stating, "Your inquiry has been forwarded to the account management team. You will usually receive a response within 24 hours." Furthermore, once the issue is resolved, the server sends the user a final notification email containing the solution, completing the inquiry process.

[0859] Specific example

[0860] 1. The user enters "I forgot my account password" into the website's contact form and clicks the submit button.

[0861] 2. The terminal receives the form data entered by the user and sends an HTTP POST request to the server.

[0862] 3. The server analyzes the received query data using the NLTK natural language processing engine and extracts the keywords "account" and "password".

[0863] 4. The server categorizes the inquiry under "Account Management" and automatically forwards it to the appropriate department.

[0864] 5. The server generates an automated reply email via SendGrid, sending the user instructions for resetting their password.

[0865] 6. The server notifies the user of the status of the request and sends a message stating, "You will usually receive a reply within 24 hours."

[0866] 7. The account management team will respond to user inquiries and provide specific instructions to resolve the issue.

[0867] 8. After the problem is resolved, the server will send a final notification email to the user and close the inquiry ticket.

[0868] Example of a prompt

[0869] "Please provide a step-by-step explanation of the process of a program that uses an automated sorting system to analyze user inquiries and route them to the appropriate department. For example, if a user inquires, 'I forgot my account password,' please explain the detailed processing steps involved in each process."

[0870] As a result, the system based on the present invention can process user inquiries efficiently and accurately, enabling a rapid response.

[0871] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0872] Step 1: Receiving inquiry data

[0873] The user fills out their inquiry in the website's contact form and clicks the submit button.

[0874] The terminal receives the inquiry data entered by the user and sends it to the server as an HTTP POST request.

[0875] Input: The content of the inquiry entered by the user in the form.

[0876] Output: Query data in HTTP POST request format.

[0877] Specific action: The user enters "I forgot my account password" and clicks the submit button. The device packages this data as an HTTP request and sends it to the "POST / inquiry" endpoint.

[0878] Step 2: Inquiry month analysis

[0879] The server analyzes the query data received from the terminal using a natural language processing (NLP) engine.

[0880] Input: Query data as an HTTP POST request.

[0881] Output: Analyzed keywords and contextual information.

[0882] Specific operation: The server uses natural language processing libraries (NLTK or SpaCy) to tokenize the query content, tag it with part-of-speech tags, and extract the keywords "account" and "password".

[0883] Step 3: Classifying the inquiry

[0884] The server determines the category of the query based on the extracted keywords.

[0885] Input: Analyzed keywords and contextual information.

[0886] Output: Identified query category.

[0887] Specific operation: The server categorizes inquiries into the "account management" category based on the keywords "account" and "password".

[0888] Step 4: Automatically route inquiries

[0889] The server then routes the classified inquiries to the appropriate department or to an automated reply message.

[0890] Input: Identified inquiry category.

[0891] Output: Queue or automated reply message from the relevant department.

[0892] Specific actions: The server adds inquiries categorized as "account management" to the account management team's queue. It also generates an automated reply email, creating an email outlining the "password reset procedure."

[0893] Step 5: Notifying the user of the status of the response.

[0894] The server notifies the user of the status of the inquiry.

[0895] Input: Status data.

[0896] Output: Notification email to the user.

[0897] Specific action: The server sends the user an email stating, "Your inquiry has been forwarded to the account management team. You will usually receive a response within 24 hours."

[0898] Step 6: Final notification after problem resolution

[0899] The server will send the user a final notification email containing the solution once the problem is resolved.

[0900] Input: Problem-solving data.

[0901] Output: Final notification email to the user.

[0902] Specific action: The server sends an email to the user stating "Your account password has been reset" and closes the inquiry ticket.

[0903] Through these steps, this system efficiently processes user inquiries and enables quick and accurate responses.

[0904] (Application Example 1)

[0905] 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."

[0906] The objective of this invention is to provide a system that efficiently and accurately processes user inquiries and routes them to the most appropriate department or automated reply message. In particular, it aims to improve customer satisfaction in logistics centers by providing prompt and appropriate responses to inquiries regarding delivery delays, damaged goods, etc. Furthermore, it aims to improve the efficiency and accuracy of inquiry processing by automating the analysis, classification, and notification of inquiries.

[0907] 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.

[0908] In this invention, the server includes means for receiving inquiries from users, means for analyzing inquiries using natural language processing and classifying them into categories, means for distributing the classified inquiries to the appropriate department or an automated reply message based on the category, means for notifying the user of the status of the response and the solution, means for processing inquiries about delivery status within the logistics center, means for accurately analyzing inquiries about delivery delays and damaged goods and distributing them to the appropriate department, and means for providing the user with an automated reply message regarding delivery delays and damaged goods. This enables more efficient and rapid response to inquiries in the logistics center.

[0909] A "user" is a person or organization that uses the system to make inquiries.

[0910] An "inquiry" refers to the content of a question, request, or problem report that a user provides through the system.

[0911] "Natural language processing" is a technology that enables computers to understand and analyze human language.

[0912] A "category" is a classification used to categorize inquiries based on specific themes or issues.

[0913] The "responsible department" refers to the department or person responsible for providing an appropriate response to a classified inquiry.

[0914] An "automatic reply message" is a response message that a system automatically generates based on a user's inquiry.

[0915] "Status" refers to information indicating the current status of an inquiry.

[0916] "Solution" refers to a specific response or means of resolving an inquiry.

[0917] A "logistics center" is a facility that handles the distribution, management, and related operations of goods.

[0918] "Delivery status" refers to information indicating the current progress and any issues related to the delivery of the product.

[0919] "Delivery delay" refers to a situation where delivery is delayed beyond the scheduled delivery time.

[0920] "Product damage" refers to a condition in which a product is damaged during delivery.

[0921] "Analysis" is the process by which a system examines the content of a query in detail and extracts its meaning.

[0922] "Classification" refers to dividing the analyzed query content into specific categories.

[0923] "Routing" is the process of sending classified inquiries to the appropriate department or message.

[0924] "Automatic reply" refers to a system automatically sending a response message to a user.

[0925] This invention is a system that efficiently processes user inquiries and routes them to the most appropriate department or automated reply message. In particular, it enables quick and appropriate responses to inquiries regarding delivery delays and damaged goods in logistics centers. The specific implementation of this invention will be described below in several steps.

[0926] First, the user accesses the system using a smartphone or computer and enters their inquiry. The user enters "Delivery is delayed" into the inquiry form on the website and clicks the submit button. The device receives the entered inquiry data and sends it to the server as an HTTP POST request.

[0927] The server processes the received data using a parsing module equipped with a natural language processing engine. Specifically, it uses the Python Django framework and the spaCy library to tokenize the inquiry content, tag it with parts of speech, and extract keywords. This process classifies the inquiry content into categories such as "delivery delay" or "product damage."

[0928] Next, the server automatically forwards the classified inquiries to the appropriate department. For example, an inquiry about "delivery delay" is forwarded to the delivery management team, and an inquiry about "damaged goods" is forwarded to the quality assurance team. This is done by using Django models to record the inquiry details in the database and notify the appropriate department.

[0929] The server generates an automated reply message to inform the user of the status of the response. This message is created based on a pre-configured template and sent to the user via email or in-app notification. For example, a message such as "We have received your inquiry regarding the delivery delay. We will forward it to the appropriate department." might be automatically generated.

[0930] In a specific use case at a logistics center, if a user enters "My delivery is delayed," this inquiry is categorized as "Delivery Delay." The server then generates an automated reply message stating, "We have received your inquiry regarding a delivery delay. We will forward it to the appropriate department," and notifies the user. Based on this, the appropriate department is also automatically notified.

[0931] In this way, the system can process user inquiries quickly and accurately, and streamline inquiry handling at the logistics center.

[0932] Example of a prompt:

[0933] text

[0934] It seems my package is delayed in transit. Could you please check on it?

[0935] This prompt causes the system to categorize the request as a "delivery delay," route it to the appropriate department, and send an automated reply message to the user.

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

[0937] Step 1:

[0938] A user enters "My delivery is delayed" into the website's contact form and clicks the submit button. The input is the user's inquiry. Based on this input, the device sends the inquiry data to the server as an HTTP POST request. The output is the HTTP POST request to the server.

[0939] Step 2:

[0940] The server analyzes the received query data. Natural language processing (NLP) techniques are used for this analysis. Specifically, the server utilizes the Python Django framework and the spaCy library to tokenize the query content, tag it with parts of speech, and extract keywords. For this purpose, the server is equipped with an NLP engine. The input is the user's query data, and the output is the extracted keywords and the tokenized query data.

[0941] Step 3:

[0942] The server categorizes the inquiry based on the analysis results. Examples of such categories include "delivery delay" and "damaged goods." In this classification step, the inquiry is assigned to the appropriate category based on the extracted keywords. The input is the analysis results obtained in step 2, and the output is the classified category.

[0943] Step 4:

[0944] The server forwards classified queries to the appropriate department. Specifically, it uses a Django model to record the query details in the database and then notifies the appropriate department. The input is classified category information and the query details, and the output is recording to the database and notifying the appropriate department.

[0945] Step 5:

[0946] The server generates an automated reply message informing the user of the status and resolution of their inquiry. This message is created based on a pre-configured template. For example, it might say, "We have received your inquiry regarding the delivery delay. We are forwarding it to the appropriate department." The input is the inquiry content and classification information, and the output is the automatically generated reply message.

[0947] Step 6:

[0948] The server sends the generated automated reply message to the user. Specifically, it sends the message to the user via the mail server or sends an in-app notification. The input is the automated reply message, and the output is the notification to the user.

[0949] For example, if a user enters "My delivery is delayed," the server categorizes this inquiry as "Delivery Delay" and forwards it to the appropriate department. An automated reply message, "We have received your inquiry regarding a delivery delay. We will forward it to the appropriate department," is then generated and sent to the user.

[0950] 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.

[0951] This invention relates to a system for efficiently processing user inquiries, and further incorporates an emotion engine that recognizes user emotions to adjust the response department or automated reply message according to those emotions. This system automates the reception, analysis (including emotion recognition), classification, sorting, and notification of inquiries, enabling flexible responses based on user emotions.

[0952] Inquiry reception

[0953] The user enters their inquiry into the website's contact form and clicks the submit button. The device collects the inquiry data entered by the user and sends it to the server as an HTTP POST request.

[0954] Inquiry analysis and sentiment recognition

[0955] The server analyzes the query data received from the terminal. This analysis uses natural language processing (NLP) technology and an emotion recognition engine. The NLP engine tokenizes the query content, tags it with parts of speech, and extracts keywords and context. Furthermore, the emotion recognition engine detects emotions (e.g., anger, sadness, joy, etc.) from the user's query content.

[0956] Inquiry classification and sentiment-based adjustment

[0957] The server categorizes inquiries based on the output of its NLP engine and emotion recognition engine. For example, inquiries containing keywords such as "account" and "password" are categorized under "account management." Next, the server adjusts the appropriate department and automated reply message based on the detected emotion. For example, if anger is detected, the inquiry is routed to a department that prioritizes handling it.

[0958] Automatic sorting and responses based on emotion

[0959] The server adds categorized inquiries to the queue of the appropriate department. The server also selects an automated reply message template based on the user's sentiment and generates a customized automated reply email. This email includes standard answers to common questions, along with wording that is sensitive to the user's feelings.

[0960] Notification of response status and solution

[0961] The server notifies the user of the status of their inquiry. For example, the server sends the user a status update email stating, "Your inquiry has been forwarded to the account management team. We will respond more quickly than usual." Furthermore, once the issue is resolved, the server sends the user a final notification email containing the solution, completing the inquiry process.

[0962] Specific example

[0963] 1. The user enters the following into the website's contact form: "I have tried to reset my account password multiple times, but I still cannot log in. I am very frustrated." and clicks the submit button.

[0964] 2. The terminal collects the form data entered by the user and sends an HTTP POST request to the server.

[0965] 3. The server analyzes the received inquiry data using NLP and an emotion recognition engine, extracting the keywords "account" and "password" and the emotion "anger."

[0966] 4. The server categorizes inquiries into "account management" and prioritizes forwarding them to the account management team based on the user's sentiment.

[0967] 5. The server generates an automated reply email based on emotion and sends it to the user, including "password reset instructions" and a promise of "prompt action."

[0968] 6. The server notifies the user of the status of the inquiry and sends a message stating, "Your inquiry will be handled with priority."

[0969] 7. The account management team will receive inquiries and provide users with prompt and specific responses.

[0970] 8. After the problem is resolved, the server will send a final notification email to the user and close the inquiry ticket.

[0971] In this way, the system based on the present invention efficiently and accurately processes user inquiries and enables flexible responses that respond to the user's emotions.

[0972] The following describes the processing flow.

[0973] Step 1:

[0974] The user enters their inquiry into the website's contact form and clicks the submit button, stating, "I have tried to reset my account password multiple times, but I still cannot log in. I am extremely frustrated."

[0975] Step 2:

[0976] The terminal collects the form data entered by the user and sends it to the server as an HTTP POST request.

[0977] Step 3:

[0978] The server parses the HTTP POST request received from the terminal and extracts the query content.

[0979] Step 4:

[0980] The server passes the query content to a natural language processing (NLP) engine, which performs tokenization, part-of-speech tagging, and dependency analysis.

[0981] Step 5:

[0982] Based on the output of the NLP engine, the server extracts keywords and context from the query content, identifying keywords such as "account," "password," and "unable to log in."

[0983] Step 6:

[0984] The server passes the user's inquiry to the sentiment recognition engine, which then detects emotions (e.g., anger) within the text.

[0985] Step 7:

[0986] The server categorizes inquiries into "account management" and flags them as inquiries requiring priority attention based on sentiment recognition results.

[0987] Step 8:

[0988] The server adds the categorized query to the priority queue for the account management team.

[0989] Step 9:

[0990] The server selects an appropriate template based on the inquiry content and sentiment recognition results, and generates an automated reply email. The template includes phrases such as "Password reset instructions" and "A promise of a prompt response."

[0991] Step 10:

[0992] The server sends the generated automated reply email to the user's email address.

[0993] Step 11:

[0994] The server updates the status of the inquiry and sends the user a status update email stating, "Your inquiry has been forwarded to the account management team as a priority. We will respond promptly."

[0995] Step 12:

[0996] The account management team receives inquiries and responds quickly to user issues. They provide additional information to guide users through support procedures as needed.

[0997] Step 13:

[0998] Once the issue is resolved, the server closes the inquiry ticket and sends a final notification email to the user.

[0999] The above describes the specific processing flow in the system of the present invention.

[1000] (Example 2)

[1001] 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."

[1002] Many modern systems are required to efficiently handle user inquiries, but they face the challenge of providing flexible responses that take into account user emotions. When users are frustrated or angry, a quick and appropriate response is needed, but current systems often fall short in this regard. Furthermore, routing inquiries to the appropriate department based on their content is crucial, but this process is often done manually, lacking efficiency. Therefore, there is a need for an efficient and accurate inquiry processing system that includes responses that take user emotions into account.

[1003] 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 users, means for analyzing the inquiries using natural language processing and classifying them into categories, means for detecting emotions from the content of the inquiries, means for distributing the inquiries to the appropriate department or an automated reply message based on the classification and detected emotions, and means for notifying the user of the status of the response and the solution. This enables flexible responses in accordance with the user's emotions, improving the efficiency and accuracy of inquiry processing.

[1004] A "user" refers to anyone who submits a question or problem using the contact form.

[1005] A "terminal" refers to a device used by a user (for example, a personal computer or smartphone), which has the role of collecting inquiry data and sending it to the server.

[1006] A "server" refers to a central processing unit that analyzes, classifies, distributes, and notifies query data received from terminals.

[1007] "Inquiry" refers to a question or problem that a user enters into a website's inquiry form.

[1008] "Natural language processing" refers to the technology that enables computers to understand, interpret, and generate human language.

[1009] A "category" refers to a classification group based on the content of the inquiry.

[1010] "Analysis" refers to the process of tokenizing the content of an inquiry and extracting keywords and context.

[1011] "Emotion recognition" refers to the technology that detects a user's emotions (for example, anger, sadness, joy, etc.) from the content of their inquiry.

[1012] "Routing" refers to the process of distributing inquiries to the appropriate department or automated response message based on classification and detected sentiment.

[1013] The term "responsible department" refers to the department responsible for handling inquiries within a specific category.

[1014] An "automatic reply message" refers to a standard response message that a system automatically generates and sends to the user.

[1015] "Notification" refers to the process of informing the user about the status of their inquiry and how it has been resolved.

[1016] This invention relates to a system for efficiently processing user inquiries, which, by incorporating an emotion engine that recognizes user emotions, adjusts the responding department and automated reply messages according to those emotions. This system automates the receiving, analysis (including emotion recognition), classification, sorting, and notification of inquiries, enabling flexible responses based on user emotions.

[1017] Inquiry reception

[1018] The user enters their inquiry into the website's contact form and clicks the submit button. The device sends the user's entered inquiry data to the server as an HTTP POST request. The device collects inquiries through web browsers and mobile apps and sends them to the server.

[1019] Inquiry analysis and sentiment recognition

[1020] The server analyzes the query data received from the terminal. This analysis uses natural language processing (NLP) techniques and an emotion recognition engine. SpaCy and BERT can be used as the natural language processing engine. This tokenizes the query content and extracts keywords and context. Furthermore, IBM Watson Tone Analyzer and Microsoft Azure Text Analytics are used as emotion recognition engines to detect emotions (e.g., anger, sadness, joy, etc.) from the user's query content.

[1021] Inquiry classification and sentiment-based adjustment

[1022] The server categorizes inquiries based on the output of its NLP engine and emotion recognition engine. For example, inquiries containing keywords such as "account" or "password" are classified under the "account management" category. Next, the server adjusts the appropriate department and automated reply message based on the detected emotion. For example, if anger is detected, the inquiry is routed to the department that should handle it first.

[1023] Automatic sorting and responses based on emotion

[1024] The server adds categorized inquiries to the queue of the appropriate department. The server also selects an automated reply message template based on the user's sentiment and generates a customized automated reply email. This email includes standard answers to common questions, along with wording that is sensitive to the user's feelings.

[1025] Notification of response status and solution

[1026] The server notifies the user of the status of their inquiry. For example, the server sends the user a status update email stating, "Your inquiry has been forwarded to the account management team. We will address it promptly." Furthermore, once the issue is resolved, the server sends the user a final notification email containing the solution, completing the inquiry process.

[1027] Specific example

[1028] 1. The user enters the following into the website's contact form: "I have tried to reset my account password multiple times, but I still cannot log in. I am very frustrated." and clicks the submit button.

[1029] 2. The terminal sends the collected inquiry data to the server as an HTTP POST request.

[1030] 3. The server uses a natural language processing engine and an emotion recognition engine to extract the keywords "account" and "password" and the emotion "anger".

[1031] 4. The server categorizes the inquiry into "Account Management" and prioritizes forwarding it to the account management team.

[1032] 5. The server generates an automated reply email tailored to the user and sends it, including wording that promises a prompt response.

[1033] 6. The server will notify the user of the status of the issue and send a final notification email once the problem has been resolved. This email will include the solution.

[1034] Example of a prompt:

[1035] A user enters the following into the website's contact form: "I have tried to reset my account password multiple times, but I still cannot log in. I am very frustrated." and clicks the submit button.

[1036] As described above, the system based on the present invention efficiently and accurately processes user inquiries and enables flexible responses that respond to the user's emotions.

[1037] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1038] Step 1: Inquiry Submission

[1039] User: Enters the following into the website's contact form: "I have tried to reset my account password multiple times, but I still cannot log in. I am very frustrated." and clicks the submit button.

[1040] Terminal: Collects user-entered inquiry content as form data.

[1041] Terminal: Send this query data to the server as an HTTP POST request.

[1042] Input: Inquiry content based on the contact form.

[1043] Output: Query data converted into an HTTP POST request.

[1044] Step 2: Inquiry Analysis and Sentiment Recognition

[1045] Server: Analyzes query data received from terminals.

[1046] Server: Uses a natural language processing (NLP) engine (e.g., SpaCy, BERT) to tokenize the query content and extract keywords and context.

[1047] Server: Uses an emotion recognition engine (e.g., IBM Watson Tone Analyzer, Microsoft Azure Text Analytics) to detect user emotions from the query content.

[1048] Input: Query data received as an HTTP POST request.

[1049] Data processing: Tokenization of inquiry content, keyword extraction, sentiment recognition.

[1050] Output: Tokenized data, extracted keywords, detected emotions (e.g., "anger").

[1051] Step 3: Inquiry classification and sentiment-based adjustment

[1052] Server: Classifies the query content into categories based on the output of the NLP engine and the emotion recognition engine.

[1053] Server: For example, queries containing keywords such as "account" and "password" are categorized under "account management".

[1054] Server: Based on detected emotions, it adjusts the appropriate department and automated response message. For example, if anger is detected, it prioritizes routing the request to the appropriate department.

[1055] Input: Tokenized data, extracted keywords, and detected sentiment.

[1056] Data processing: Categorizing inquiries and determining which department should handle them based on their emotional impact.

[1057] Output: Classified inquiry category, determination of the relevant department.

[1058] Step 4: Automatic sorting and emotionally responsive replies

[1059] Server: Adds classified inquiries to the queue of the appropriate department. For example, inquiries in the "Account Management" category are prioritized for the account management team.

[1060] Server: Select an appropriate automated reply message template based on the user's emotion. Choose a template that includes wording that takes the user's emotion (in this case, "anger") into consideration.

[1061] Server: Generates an automated reply email and sends it to the user, including "password reset instructions" and a statement promising a prompt response.

[1062] Input: Classified inquiry category, department to handle, sentiment data.

[1063] Data processing: Generating automated reply messages and distributing them to the appropriate department.

[1064] Output: Automated reply email, inquiry added to the queue of the relevant department.

[1065] Step 5: Notification of response status and solution

[1066] Server: Notifies the user of the status of their inquiry. For example, it might send a status update email stating, "Your inquiry has been forwarded to the account management team. We will address it promptly."

[1067] Server: Once the issue is resolved, a final notification email containing the solution will be sent to the user, and the inquiry ticket will be closed. This email will include specific steps for resolution and suggested improvements.

[1068] Input: Feedback from the relevant department, progress of the inquiry.

[1069] Data processing: Summarizing the status and solutions, and generating notification emails.

[1070] Output: Status update email, final notification email.

[1071] The above is a detailed explanation of the processing flow of this system's program.

[1072] (Application Example 2)

[1073] 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."

[1074] Conventional inquiry handling systems have struggled to properly categorize user inquiries and distribute them to the appropriate departments. Furthermore, they often fail to respond in a way that respects user emotions, potentially leading to decreased user satisfaction. In particular, in security services, it is crucial to quickly recognize and appropriately address user anxiety and anger; therefore, the ability to recognize and reflect emotions is essential. A system is needed to solve these problems and provide flexible, emotionally sensitive responses to user inquiries.

[1075] 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.

[1076] In this invention, the server includes means for receiving inquiries from users, means for analyzing inquiries using natural language processing and classifying them into categories, means for detecting the user's emotions using an emotion recognition engine, means for assigning inquiries to the appropriate department or an automated reply message based on the category and emotions, and means for notifying the user of the response status and solution. This enables a quick and accurate response to user inquiries, as well as a flexible response that takes the user's emotions into consideration.

[1077] A "user" is a person who uses the system to make inquiries.

[1078] An "inquiry" refers to a question or problem report submitted by a user to the system.

[1079] "Natural language processing" is a technology that enables computers to understand and analyze human language.

[1080] "Analysis" is the process of breaking down input data for a specific purpose and understanding its meaning and structure.

[1081] A "category" is a classification of topics or fields that characterize the content of an inquiry.

[1082] An "emotion recognition engine" is a technology that automatically detects emotions (e.g., anger, sadness, joy, etc.) from the content of a user's inquiry.

[1083] A "response department" is a specialized department that handles inquiries related to a specific category.

[1084] An "automatic reply message" is a response message that is generated by a system and automatically sent to the user.

[1085] "Response Status" refers to status information indicating the stage of the inquiry.

[1086] A "solution" refers to a solution or answer to a problem that a user is facing.

[1087] An "inquiry management system" is a system for recording and managing received inquiries and their processing status.

[1088] "Emotional information" refers to user emotional data extracted by an emotion recognition engine.

[1089] This invention relates to a system for efficiently processing user inquiries, and further incorporates an emotion engine that recognizes user emotions to adjust the response department or automated reply message according to those emotions. This system automates the reception, analysis (including emotion recognition), classification, sorting, and notification of inquiries, enabling flexible responses based on user emotions.

[1090] Hardware and software

[1091] Smartphone: A device used by users to input and submit inquiries.

[1092] Backend server: Built using Python, it handles inquiry data analysis, sentiment recognition, categorization, distribution to the appropriate department, generation of automated reply messages, and notifications.

[1093] The NLP engine spaCy is used to tokenize the query content and extract keywords and context.

[1094] Emotion recognition engine: Detects user emotions using Google Cloud Natural Language API or TensorFlow.

[1095] Messaging service: Use Firebase Cloud Messaging to send notifications to users.

[1096] Detailed description of the invention

[1097] 1. Inquiry reception

[1098] The user opens the application on their smartphone, enters their inquiry into a form for security-related questions and problem reports, and clicks the submit button.

[1099] The smartphone collects data entered by the user and sends it to a backend server in the cloud via an HTTP POST request.

[1100] 2. Inquiry Analysis and Sentiment Recognition

[1101] The server analyzes the received data using spaCy's NLP engine, tokenizes the input content, and extracts keywords and context.

[1102] Use the Google Cloud Natural Language API to detect user emotions (e.g., anger, sadness, anxiety).

[1103] 3. Inquiry classification and sentiment-based adjustment

[1104] Based on the results from the NLP engine, the server categorizes the query into categories such as "system error," "unauthorized access," and "phishing scam."

[1105] Based on the results of the emotion recognition engine, inquiries with high emotion scores will be processed preferentially.

[1106] 4. Automatic sorting and responses based on emotion

[1107] The server automatically routes classified inquiries to the appropriate department. For example, reports of unauthorized access are sent directly to the security team.

[1108] It generates emotion-based reply messages and sends customized messages to users, such as "We are investigating the situation" or "We promise to respond as soon as possible."

[1109] 5. Notification of response status and resolution.

[1110] The server will notify the user of the status of the issue as it progresses, and will send a final message and close the ticket once the problem is resolved.

[1111] Specific example

[1112] 1. User behavior

[1113] The user opens the application on their smartphone, types "I received a warning about unauthorized access when I tried to log in to a new account. I'm very worried," and clicks the send button.

[1114] 2. Server processing

[1115] The received data is analyzed using spaCy's NLP engine, and keywords (e.g., "new account," "login," "unauthorized access," "warning") are extracted.

[1116] The Google Cloud Natural Language API is used to analyze emotions and detect the emotion of "worry."

[1117] Inquiries are categorized as "unauthorized access" and forwarded to the security team on a priority basis based on their high sentiment score.

[1118] An emotion-based automated reply message, "We have received your report regarding unauthorized access. We will investigate immediately and take prompt action," is generated and sent to the user.

[1119] The system notifies the user of the status of their inquiry and sends a message stating, "Your inquiry is being handled with priority."

[1120] Example of a prompt

[1121] User inquiry: "When I tried to log in to my new account, I received a warning about unauthorized access. I'm very worried."

[1122] Tokenization using an NLP engine -> Keywords: ["New account", "Login", "Unauthorized access", "Warning"]

[1123] Emotion detection by emotion recognition engine -> Emotion: "Worry"

[1124] Classification: "Unauthorized Access"

[1125] Department in charge: Security Team

[1126] Automated reply message: "We have received your report regarding unauthorized access. We will investigate immediately and take prompt action."

[1127] Notice: "Inquiries are being handled with priority."

[1128] Final message: "The issue has been resolved. Your account is secure."

[1129] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1130] Step 1:

[1131] The user opens the application on their smartphone and enters their inquiry. Specifically, the user enters "I received a warning about unauthorized access when I tried to log in to a new account. I am very worried." into the text form on the software and clicks the submit button. The input data is the inquiry (input: user's inquiry, output: HTTP POST request).

[1132] Step 2:

[1133] The terminal sends the user's input as an HTTP POST request to the cloud backend server. Specifically, it converts the input data into a JSON payload and sends it to a specific endpoint on the server (e.g., / api / report_issue) (input: user's inquiry, output: JSON payload).

[1134] Step 3:

[1135] To analyze the data received by the server, spaCy's NLP engine is first used to tokenize the query content and extract keywords and context. For example, keywords such as "new account," "login," "unauthorized access," and "warning" are extracted (input: JSON payload, output: keywords and context).

[1136] Step 4:

[1137] The server uses the Google Cloud Natural Language API or a TensorFlow sentiment recognition model to detect emotions from the user's inquiry. For example, the emotion "worried" might be detected (input: inquiry (text), output: emotion information).

[1138] Step 5:

[1139] The server classifies queries into categories such as "unauthorized access" based on the results of the NLP engine and sentiment recognition. For example, based on the keywords "new account" and "unauthorized access," it will be classified into the "unauthorized access" category (input: keywords and sentiment information, output: category).

[1140] Step 6:

[1141] The server automatically routes inquiries to the appropriate department based on their sentiment score and category. For example, if the sentiment is "concerned," it is given a high priority and sent to the security team (input: category and sentiment information, output: appropriate department).

[1142] Step 7:

[1143] The server generates an automated reply message based on sentiment information and the content of the inquiry. For example, a message such as "We have received your report regarding unauthorized access. We will investigate immediately and take prompt action." will be generated (Input: Inquiry content and sentiment information, Output: Automated reply message).

[1144] Step 8:

[1145] The server uses Firebase Cloud Messaging to send a generated automated reply message to the user. The user receives the message on their smartphone and receives a notification that "Your inquiry is being handled with priority" (Input: Automated reply message, Output: Notification to user).

[1146] Step 9:

[1147] The server periodically notifies the user of the status of the inquiry. For example, a status update message such as "Your inquiry is currently under investigation" is sent (Input: Status, Output: Status update message).

[1148] Step 10:

[1149] Once the server resolves the issue, it sends a final notification message to the user and closes the inquiry ticket. For example, a message such as "The issue has been resolved. Your account is secure." is sent (Input: Resolution information, Output: Final notification message and ticket closure).

[1150] 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.

[1151] 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.

[1152] 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.

[1153] [Fourth Embodiment]

[1154] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1155] 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.

[1156] 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).

[1157] 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.

[1158] 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.

[1159] 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).

[1160] 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.

[1161] 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.

[1162] 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.

[1163] 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.

[1164] 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.

[1165] 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.

[1166] 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".

[1167] This invention relates to a system that efficiently processes user inquiries and routes them to the most appropriate department or automated reply message. This system enables a quick and accurate response by automating the receiving, analysis, classification, routing, and notification of inquiries.

[1168] Inquiry reception

[1169] The user fills out their inquiry in the website's contact form and clicks the submit button. The device receives the inquiry data entered by the user and sends it to the server as an HTTP POST request.

[1170] Query analysis and classification

[1171] The server analyzes the query data received from the terminal. Natural language processing (NLP) techniques are used for this analysis. The NLP engine tokenizes the query content, tags it with parts of speech, and extracts keywords and context. Based on the results of this analysis, the server determines the category of the query. For example, a query containing keywords such as "account" and "password" will be classified into the "account management" category.

[1172] Automatic distribution

[1173] The server routes categorized inquiries to the appropriate department or to an automated reply message. For example, inquiries categorized as "Account Management" are automatically forwarded to the account management team's response queue. The server can also generate automated reply emails based on the content of the inquiry. These automated reply emails contain standard answers to common questions and are sent to the user.

[1174] Notification of response status and solution

[1175] The server notifies the user of the status of their inquiry. For example, the server sends the user a status update email stating, "Your inquiry has been forwarded to the account management team. You will usually receive a response within 24 hours." Furthermore, once the issue is resolved, the server sends the user a final notification email containing the solution, completing the inquiry process.

[1176] Specific example

[1177] 1. The user enters "I forgot my account password" into the website's contact form and clicks the submit button.

[1178] 2. The terminal receives the form data entered by the user and sends an HTTP POST request to the server.

[1179] 3. The server analyzes the received query data using a natural language processing engine and extracts the keywords "account" and "password".

[1180] 4. The server categorizes the inquiry under "Account Management" and automatically forwards it to the appropriate department.

[1181] 5. The server generates an automated reply email and sends the user instructions on how to reset their password.

[1182] 6. The server notifies the user of the status of the request and sends a message stating, "You will usually receive a reply within 24 hours."

[1183] 7. The account management team will respond to user inquiries and provide specific instructions to resolve the issue.

[1184] 8. After the problem is resolved, the server will send a final notification email to the user and close the inquiry ticket.

[1185] In this way, the system based on the present invention efficiently and accurately processes user inquiries and enables a rapid response.

[1186] The following describes the processing flow.

[1187] Step 1:

[1188] The user enters their inquiry into the website's contact form and clicks the submit button.

[1189] Step 2:

[1190] The terminal collects the form data entered by the user and sends it to the server as an HTTP POST request.

[1191] Step 3:

[1192] The server parses the HTTP POST request received from the terminal and extracts the query content.

[1193] Step 4:

[1194] The server passes the query content to a natural language processing (NLP) engine, which performs tokenization, part-of-speech tagging, and dependency analysis.

[1195] Step 5:

[1196] The server extracts keywords and context from the query content based on the output of the NLP engine and determines the category of the query.

[1197] Step 6:

[1198] The server applies the appropriate processing rule based on the category of the inquiry. For example, for an inquiry categorized as "Account Management," the server applies a rule to forward it to the account management team.

[1199] Step 7:

[1200] The server adds the classified query to the queue of the relevant department.

[1201] Step 8:

[1202] The server simultaneously generates an automated reply email based on the inquiry. You select a template and fill in the user's name and specific information.

[1203] Step 9:

[1204] The server sends the generated automated reply email to the user's email address.

[1205] Step 10:

[1206] The server updates the status of the inquiry and notifies the user of the response status. For example, it might send an email stating, "Your inquiry has been forwarded to the account management team. You will usually receive a response within 24 hours."

[1207] Step 11:

[1208] The relevant department (e.g., the account management team) receives the inquiry and provides specific assistance to the user. If necessary, they will request additional information from the user.

[1209] Step 12:

[1210] Once the relevant department has completed the task, the server closes the inquiry ticket and sends a resolution notification email to the user.

[1211] The above describes the specific processing flow in the system of the present invention.

[1212] (Example 1)

[1213] 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".

[1214] Traditional inquiry handling systems often lacked the ability to quickly and accurately route user inquiries to the appropriate department. This resulted in delays and inappropriate processing, leading to a poor user experience. Furthermore, the manual analysis and classification of inquiries was often time-consuming and labor-intensive. Additionally, users were not adequately notified of the status of their inquiries, causing anxiety. To address these challenges, a system is needed that automates the inquiry handling process, enabling efficient and accurate inquiry processing.

[1215] 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.

[1216] In this invention, the server includes means for receiving inquiries from users, means for analyzing the received inquiries using natural language processing and extracting keywords and context, means for determining the category of the inquiry based on the extracted keywords, means for distributing the classified inquiries to the appropriate department or an automated reply message based on the category, and means for notifying the user of the status of the response and the solution. This makes it possible to quickly and accurately analyze and classify user inquiries and automatically distribute them to the appropriate department. Furthermore, by notifying the user of the response status in a timely manner, an improvement in the user experience can be expected.

[1217] An "inquiry" refers to a question or request that a user sends to a system in order to obtain information.

[1218] "Natural language processing" refers to the technology that enables computers to understand, interpret, and generate human language, and includes processes such as tokenization of text, part-of-speech tagging, and keyword extraction.

[1219] "Analysis" refers to the process of breaking down and understanding received query data, and specifically refers to the use of natural language processing techniques.

[1220] "Keywords" refer to important words or phrases extracted from the inquiry content, and serve as crucial clues for identifying the content of the inquiry.

[1221] "Context" refers to information that helps understand the overall meaning and background of an inquiry, and primarily serves to complement the meaning of keywords.

[1222] A "category" refers to a group classified based on the analyzed inquiry content, and specifically means a particular area such as account management or technical support.

[1223] "Routing" refers to the process of assigning analyzed and classified inquiries to the appropriate department or automated response message.

[1224] A "responsible department" refers to a department or team responsible for handling inquiries categorized into a specific group.

[1225] An "automatic reply message" refers to a standardized response message that the system automatically generates and sends to the user based on the content of the inquiry.

[1226] "Notifications" refer to information sent to users to inform them of the status of their inquiry and how it has been resolved.

[1227] This invention relates to a system that efficiently processes user inquiries and routes them to the most appropriate department or automated reply message. The following describes a specific implementation of this system.

[1228] Inquiry reception

[1229] The user fills out their inquiry in the website's contact form and clicks the submit button. The device receives the inquiry data entered by the user and sends it to the server as an HTTP POST request.

[1230] Query analysis and classification

[1231] The server analyzes the query data received from the terminal. Natural language processing (NLP) techniques are used for this analysis. Specifically, Python's natural language processing libraries, such as NLTK (Natural Language Toolkit) and SpaCy, can be used. The natural language processing engine tokenizes the query content, tags it with parts of speech, and extracts keywords and context. Based on the results of this analysis, the server determines the category of the query. For example, a query containing keywords such as "account" and "password" will be classified into the "account management" category.

[1232] Automatic distribution

[1233] The server routes classified inquiries to the appropriate department or to an automated reply message. For example, inquiries classified under the "Account Management" category are automatically forwarded to the account management team's response queue. The server can also generate automated reply emails based on the inquiry content. These automated reply emails contain standard answers to common questions and are sent to the user. An SMTP server (e.g., SendGrid) can be used to generate automated reply emails.

[1234] Notification of response status and solution

[1235] The server notifies the user of the status of their inquiry. For example, the server sends the user a status update email stating, "Your inquiry has been forwarded to the account management team. You will usually receive a response within 24 hours." Furthermore, once the issue is resolved, the server sends the user a final notification email containing the solution, completing the inquiry process.

[1236] Specific example

[1237] 1. The user enters "I forgot my account password" into the website's contact form and clicks the submit button.

[1238] 2. The terminal receives the form data entered by the user and sends an HTTP POST request to the server.

[1239] 3. The server analyzes the received query data using the NLTK natural language processing engine and extracts the keywords "account" and "password".

[1240] 4. The server categorizes the inquiry under "Account Management" and automatically forwards it to the appropriate department.

[1241] 5. The server generates an automated reply email via SendGrid, sending the user instructions for resetting their password.

[1242] 6. The server notifies the user of the status of the request and sends a message stating, "You will usually receive a reply within 24 hours."

[1243] 7. The account management team will respond to user inquiries and provide specific instructions to resolve the issue.

[1244] 8. After the problem is resolved, the server will send a final notification email to the user and close the inquiry ticket.

[1245] Example of a prompt

[1246] "Please provide a step-by-step explanation of the process of a program that uses an automated sorting system to analyze user inquiries and route them to the appropriate department. For example, if a user inquires, 'I forgot my account password,' please explain the detailed processing steps involved in each process."

[1247] As a result, the system based on the present invention can process user inquiries efficiently and accurately, enabling a rapid response.

[1248] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1249] Step 1: Receiving inquiry data

[1250] The user fills out their inquiry in the website's contact form and clicks the submit button.

[1251] The terminal receives the inquiry data entered by the user and sends it to the server as an HTTP POST request.

[1252] Input: The content of the inquiry entered by the user in the form.

[1253] Output: Query data in HTTP POST request format.

[1254] Specific action: The user enters "I forgot my account password" and clicks the submit button. The device packages this data as an HTTP request and sends it to the "POST / inquiry" endpoint.

[1255] Step 2: Inquiry month analysis

[1256] The server analyzes the query data received from the terminal using a natural language processing (NLP) engine.

[1257] Input: Query data as an HTTP POST request.

[1258] Output: Analyzed keywords and contextual information.

[1259] Specific operation: The server uses natural language processing libraries (NLTK or SpaCy) to tokenize the query content, tag it with part-of-speech tags, and extract the keywords "account" and "password".

[1260] Step 3: Classifying the inquiry

[1261] The server determines the category of the query based on the extracted keywords.

[1262] Input: Analyzed keywords and contextual information.

[1263] Output: Identified query category.

[1264] Specific operation: The server categorizes inquiries into the "account management" category based on the keywords "account" and "password".

[1265] Step 4: Automatically route inquiries

[1266] The server then routes the classified inquiries to the appropriate department or to an automated reply message.

[1267] Input: Identified inquiry category.

[1268] Output: Queue or automated reply message from the relevant department.

[1269] Specific actions: The server adds inquiries categorized as "account management" to the account management team's queue. It also generates an automated reply email, creating an email outlining the "password reset procedure."

[1270] Step 5: Notifying the user of the status of the response.

[1271] The server notifies the user of the status of the inquiry.

[1272] Input: Status data.

[1273] Output: Notification email to the user.

[1274] Specific action: The server sends the user an email stating, "Your inquiry has been forwarded to the account management team. You will usually receive a response within 24 hours."

[1275] Step 6: Final notification after problem resolution

[1276] The server will send the user a final notification email containing the solution once the problem is resolved.

[1277] Input: Problem-solving data.

[1278] Output: Final notification email to the user.

[1279] Specific action: The server sends an email to the user stating "Your account password has been reset" and closes the inquiry ticket.

[1280] Through these steps, this system efficiently processes user inquiries and enables quick and accurate responses.

[1281] (Application Example 1)

[1282] 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".

[1283] The objective of this invention is to provide a system that efficiently and accurately processes user inquiries and routes them to the most appropriate department or automated reply message. In particular, it aims to improve customer satisfaction in logistics centers by providing prompt and appropriate responses to inquiries regarding delivery delays, damaged goods, etc. Furthermore, it aims to improve the efficiency and accuracy of inquiry processing by automating the analysis, classification, and notification of inquiries.

[1284] 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.

[1285] In this invention, the server includes means for receiving inquiries from users, means for analyzing inquiries using natural language processing and classifying them into categories, means for distributing the classified inquiries to the appropriate department or an automated reply message based on the category, means for notifying the user of the status of the response and the solution, means for processing inquiries about delivery status within the logistics center, means for accurately analyzing inquiries about delivery delays and damaged goods and distributing them to the appropriate department, and means for providing the user with an automated reply message regarding delivery delays and damaged goods. This enables more efficient and rapid response to inquiries in the logistics center.

[1286] A "user" is a person or organization that uses the system to make inquiries.

[1287] An "inquiry" refers to the content of a question, request, or problem report that a user provides through the system.

[1288] "Natural language processing" is a technology that enables computers to understand and analyze human language.

[1289] A "category" is a classification used to categorize inquiries based on specific themes or issues.

[1290] The "responsible department" refers to the department or person responsible for providing an appropriate response to a classified inquiry.

[1291] An "automatic reply message" is a response message that a system automatically generates based on a user's inquiry.

[1292] "Status" refers to information indicating the current status of an inquiry.

[1293] "Solution" refers to a specific response or means of resolving an inquiry.

[1294] A "logistics center" is a facility that handles the distribution, management, and related operations of goods.

[1295] "Delivery status" refers to information indicating the current progress and any issues related to the delivery of the product.

[1296] "Delivery delay" refers to a situation where delivery is delayed beyond the scheduled delivery time.

[1297] "Product damage" refers to a condition in which a product is damaged during delivery.

[1298] "Analysis" is the process by which a system examines the content of a query in detail and extracts its meaning.

[1299] "Classification" refers to dividing the analyzed query content into specific categories.

[1300] "Routing" is the process of sending classified inquiries to the appropriate department or message.

[1301] "Automatic reply" refers to a system automatically sending a response message to a user.

[1302] This invention is a system that efficiently processes user inquiries and routes them to the most appropriate department or automated reply message. In particular, it enables quick and appropriate responses to inquiries regarding delivery delays and damaged goods in logistics centers. The specific implementation of this invention will be described below in several steps.

[1303] First, the user accesses the system using a smartphone or computer and enters their inquiry. The user enters "Delivery is delayed" into the inquiry form on the website and clicks the submit button. The device receives the entered inquiry data and sends it to the server as an HTTP POST request.

[1304] The server processes the received data using a parsing module equipped with a natural language processing engine. Specifically, it uses the Python Django framework and the spaCy library to tokenize the inquiry content, tag it with parts of speech, and extract keywords. This process classifies the inquiry content into categories such as "delivery delay" or "product damage."

[1305] Next, the server automatically forwards the classified inquiries to the appropriate department. For example, an inquiry about "delivery delay" is forwarded to the delivery management team, and an inquiry about "damaged goods" is forwarded to the quality assurance team. This is done by using Django models to record the inquiry details in the database and notify the appropriate department.

[1306] The server generates an automated reply message to inform the user of the status of the response. This message is created based on a pre-configured template and sent to the user via email or in-app notification. For example, a message such as "We have received your inquiry regarding the delivery delay. We will forward it to the appropriate department." might be automatically generated.

[1307] In a specific use case at a logistics center, if a user enters "My delivery is delayed," this inquiry is categorized as "Delivery Delay." The server then generates an automated reply message stating, "We have received your inquiry regarding a delivery delay. We will forward it to the appropriate department," and notifies the user. Based on this, the appropriate department is also automatically notified.

[1308] In this way, the system can process user inquiries quickly and accurately, and streamline inquiry handling at the logistics center.

[1309] Example of a prompt:

[1310] text

[1311] It seems my package is delayed in transit. Could you please check on it?

[1312] This prompt causes the system to categorize the request as a "delivery delay," route it to the appropriate department, and send an automated reply message to the user.

[1313] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1314] Step 1:

[1315] A user enters "My delivery is delayed" into the website's contact form and clicks the submit button. The input is the user's inquiry. Based on this input, the device sends the inquiry data to the server as an HTTP POST request. The output is the HTTP POST request to the server.

[1316] Step 2:

[1317] The server analyzes the received query data. Natural language processing (NLP) techniques are used for this analysis. Specifically, the server utilizes the Python Django framework and the spaCy library to tokenize the query content, tag it with parts of speech, and extract keywords. For this purpose, the server is equipped with an NLP engine. The input is the user's query data, and the output is the extracted keywords and the tokenized query data.

[1318] Step 3:

[1319] The server categorizes the inquiry based on the analysis results. Examples of such categories include "delivery delay" and "damaged goods." In this classification step, the inquiry is assigned to the appropriate category based on the extracted keywords. The input is the analysis results obtained in step 2, and the output is the classified category.

[1320] Step 4:

[1321] The server forwards classified queries to the appropriate department. Specifically, it uses a Django model to record the query details in the database and then notifies the appropriate department. The input is classified category information and the query details, and the output is recording to the database and notifying the appropriate department.

[1322] Step 5:

[1323] The server generates an automated reply message informing the user of the status and resolution of their inquiry. This message is created based on a pre-configured template. For example, it might say, "We have received your inquiry regarding the delivery delay. We are forwarding it to the appropriate department." The input is the inquiry content and classification information, and the output is the automatically generated reply message.

[1324] Step 6:

[1325] The server sends the generated automated reply message to the user. Specifically, it sends the message to the user via the mail server or sends an in-app notification. The input is the automated reply message, and the output is the notification to the user.

[1326] For example, if a user enters "My delivery is delayed," the server categorizes this inquiry as "Delivery Delay" and forwards it to the appropriate department. An automated reply message, "We have received your inquiry regarding a delivery delay. We will forward it to the appropriate department," is then generated and sent to the user.

[1327] 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.

[1328] This invention relates to a system for efficiently processing user inquiries, and further incorporates an emotion engine that recognizes user emotions to adjust the response department or automated reply message according to those emotions. This system automates the reception, analysis (including emotion recognition), classification, sorting, and notification of inquiries, enabling flexible responses based on user emotions.

[1329] Inquiry reception

[1330] The user enters their inquiry into the website's contact form and clicks the submit button. The device collects the inquiry data entered by the user and sends it to the server as an HTTP POST request.

[1331] Inquiry analysis and sentiment recognition

[1332] The server analyzes the query data received from the terminal. This analysis uses natural language processing (NLP) technology and an emotion recognition engine. The NLP engine tokenizes the query content, tags it with parts of speech, and extracts keywords and context. Furthermore, the emotion recognition engine detects emotions (e.g., anger, sadness, joy, etc.) from the user's query content.

[1333] Inquiry classification and sentiment-based adjustment

[1334] The server categorizes inquiries based on the output of its NLP engine and emotion recognition engine. For example, inquiries containing keywords such as "account" and "password" are categorized under "account management." Next, the server adjusts the appropriate department and automated reply message based on the detected emotion. For example, if anger is detected, the inquiry is routed to a department that prioritizes handling it.

[1335] Automatic sorting and responses based on emotion

[1336] The server adds categorized inquiries to the queue of the appropriate department. The server also selects an automated reply message template based on the user's sentiment and generates a customized automated reply email. This email includes standard answers to common questions, along with wording that is sensitive to the user's feelings.

[1337] Notification of response status and solution

[1338] The server notifies the user of the status of their inquiry. For example, the server sends the user a status update email stating, "Your inquiry has been forwarded to the account management team. We will respond more quickly than usual." Furthermore, once the issue is resolved, the server sends the user a final notification email containing the solution, completing the inquiry process.

[1339] Specific example

[1340] 1. The user enters the following into the website's contact form: "I have tried to reset my account password multiple times, but I still cannot log in. I am very frustrated." and clicks the submit button.

[1341] 2. The terminal collects the form data entered by the user and sends an HTTP POST request to the server.

[1342] 3. The server analyzes the received inquiry data using NLP and an emotion recognition engine, extracting the keywords "account" and "password" and the emotion "anger."

[1343] 4. The server categorizes inquiries into "account management" and prioritizes forwarding them to the account management team based on the user's sentiment.

[1344] 5. The server generates an automated reply email based on emotion and sends it to the user, including "password reset instructions" and a promise of "prompt action."

[1345] 6. The server notifies the user of the status of the inquiry and sends a message stating, "Your inquiry will be handled with priority."

[1346] 7. The account management team will receive inquiries and provide users with prompt and specific responses.

[1347] 8. After the problem is resolved, the server will send a final notification email to the user and close the inquiry ticket.

[1348] In this way, the system based on the present invention efficiently and accurately processes user inquiries and enables flexible responses that respond to the user's emotions.

[1349] The following describes the processing flow.

[1350] Step 1:

[1351] The user enters their inquiry into the website's contact form and clicks the submit button, stating, "I have tried to reset my account password multiple times, but I still cannot log in. I am extremely frustrated."

[1352] Step 2:

[1353] The terminal collects the form data entered by the user and sends it to the server as an HTTP POST request.

[1354] Step 3:

[1355] The server parses the HTTP POST request received from the terminal and extracts the query content.

[1356] Step 4:

[1357] The server passes the query content to a natural language processing (NLP) engine, which performs tokenization, part-of-speech tagging, and dependency analysis.

[1358] Step 5:

[1359] Based on the output of the NLP engine, the server extracts keywords and context from the query content, identifying keywords such as "account," "password," and "unable to log in."

[1360] Step 6:

[1361] The server passes the user's inquiry to the sentiment recognition engine, which then detects emotions (e.g., anger) within the text.

[1362] Step 7:

[1363] The server categorizes inquiries into "account management" and flags them as inquiries requiring priority attention based on sentiment recognition results.

[1364] Step 8:

[1365] The server adds the categorized query to the priority queue for the account management team.

[1366] Step 9:

[1367] The server selects an appropriate template based on the inquiry content and sentiment recognition results, and generates an automated reply email. The template includes phrases such as "Password reset instructions" and "A promise of a prompt response."

[1368] Step 10:

[1369] The server sends the generated automated reply email to the user's email address.

[1370] Step 11:

[1371] The server updates the status of the inquiry and sends the user a status update email stating, "Your inquiry has been forwarded to the account management team as a priority. We will respond promptly."

[1372] Step 12:

[1373] The account management team receives inquiries and responds quickly to user issues. They provide additional information to guide users through support procedures as needed.

[1374] Step 13:

[1375] Once the issue is resolved, the server closes the inquiry ticket and sends a final notification email to the user.

[1376] The above describes the specific processing flow in the system of the present invention.

[1377] (Example 2)

[1378] 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".

[1379] Many modern systems are required to efficiently handle user inquiries, but they face the challenge of providing flexible responses that take into account user emotions. When users are frustrated or angry, a quick and appropriate response is needed, but current systems often fall short in this regard. Furthermore, routing inquiries to the appropriate department based on their content is crucial, but this process is often done manually, lacking efficiency. Therefore, there is a need for an efficient and accurate inquiry processing system that includes responses that take user emotions into account.

[1380] 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 users, means for analyzing the inquiries using natural language processing and classifying them into categories, means for detecting emotions from the content of the inquiries, means for distributing the inquiries to the appropriate department or an automated reply message based on the classification and detected emotions, and means for notifying the user of the status of the response and the solution. This enables flexible responses in accordance with the user's emotions, improving the efficiency and accuracy of inquiry processing.

[1381] A "user" refers to anyone who submits a question or problem using the contact form.

[1382] A "terminal" refers to a device used by a user (for example, a personal computer or smartphone), which has the role of collecting inquiry data and sending it to the server.

[1383] A "server" refers to a central processing unit that analyzes, classifies, distributes, and notifies query data received from terminals.

[1384] "Inquiry" refers to a question or problem that a user enters into a website's inquiry form.

[1385] "Natural language processing" refers to the technology that enables computers to understand, interpret, and generate human language.

[1386] A "category" refers to a classification group based on the content of the inquiry.

[1387] "Analysis" refers to the process of tokenizing the content of an inquiry and extracting keywords and context.

[1388] "Emotion recognition" refers to the technology that detects a user's emotions (for example, anger, sadness, joy, etc.) from the content of their inquiry.

[1389] "Routing" refers to the process of distributing inquiries to the appropriate department or automated response message based on classification and detected sentiment.

[1390] The term "responsible department" refers to the department responsible for handling inquiries within a specific category.

[1391] An "automatic reply message" refers to a standard response message that a system automatically generates and sends to the user.

[1392] "Notification" refers to the process of informing the user about the status of their inquiry and how it has been resolved.

[1393] This invention relates to a system for efficiently processing user inquiries, which, by incorporating an emotion engine that recognizes user emotions, adjusts the responding department and automated reply messages according to those emotions. This system automates the receiving, analysis (including emotion recognition), classification, sorting, and notification of inquiries, enabling flexible responses based on user emotions.

[1394] Inquiry reception

[1395] The user enters their inquiry into the website's contact form and clicks the submit button. The device sends the user's entered inquiry data to the server as an HTTP POST request. The device collects inquiries through web browsers and mobile apps and sends them to the server.

[1396] Inquiry analysis and sentiment recognition

[1397] The server analyzes the query data received from the terminal. This analysis uses natural language processing (NLP) techniques and an emotion recognition engine. SpaCy and BERT can be used as the natural language processing engine. This tokenizes the query content and extracts keywords and context. Furthermore, IBM Watson Tone Analyzer and Microsoft Azure Text Analytics are used as emotion recognition engines to detect emotions (e.g., anger, sadness, joy, etc.) from the user's query content.

[1398] Inquiry classification and sentiment-based adjustment

[1399] The server categorizes inquiries based on the output of its NLP engine and emotion recognition engine. For example, inquiries containing keywords such as "account" or "password" are classified under the "account management" category. Next, the server adjusts the appropriate department and automated reply message based on the detected emotion. For example, if anger is detected, the inquiry is routed to the department that should handle it first.

[1400] Automatic sorting and responses based on emotion

[1401] The server adds categorized inquiries to the queue of the appropriate department. The server also selects an automated reply message template based on the user's sentiment and generates a customized automated reply email. This email includes standard answers to common questions, along with wording that is sensitive to the user's feelings.

[1402] Notification of response status and solution

[1403] The server notifies the user of the status of their inquiry. For example, the server sends the user a status update email stating, "Your inquiry has been forwarded to the account management team. We will address it promptly." Furthermore, once the issue is resolved, the server sends the user a final notification email containing the solution, completing the inquiry process.

[1404] Specific example

[1405] 1. The user enters the following into the website's contact form: "I have tried to reset my account password multiple times, but I still cannot log in. I am very frustrated." and clicks the submit button.

[1406] 2. The terminal sends the collected inquiry data to the server as an HTTP POST request.

[1407] 3. The server uses a natural language processing engine and an emotion recognition engine to extract the keywords "account" and "password" and the emotion "anger".

[1408] 4. The server categorizes the inquiry into "Account Management" and prioritizes forwarding it to the account management team.

[1409] 5. The server generates an automated reply email tailored to the user and sends it, including wording that promises a prompt response.

[1410] 6. The server will notify the user of the status of the issue and send a final notification email once the problem has been resolved. This email will include the solution.

[1411] Example of a prompt:

[1412] A user enters the following into the website's contact form: "I have tried to reset my account password multiple times, but I still cannot log in. I am very frustrated." and clicks the submit button.

[1413] As described above, the system based on the present invention efficiently and accurately processes user inquiries and enables flexible responses that respond to the user's emotions.

[1414] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1415] Step 1: Inquiry Submission

[1416] User: Enters the following into the website's contact form: "I have tried to reset my account password multiple times, but I still cannot log in. I am very frustrated." and clicks the submit button.

[1417] Terminal: Collects user-entered inquiry content as form data.

[1418] Terminal: Send this query data to the server as an HTTP POST request.

[1419] Input: Inquiry content based on the contact form.

[1420] Output: Query data converted into an HTTP POST request.

[1421] Step 2: Inquiry Analysis and Sentiment Recognition

[1422] Server: Analyzes query data received from terminals.

[1423] Server: Uses a natural language processing (NLP) engine (e.g., SpaCy, BERT) to tokenize the query content and extract keywords and context.

[1424] Server: Uses an emotion recognition engine (e.g., IBM Watson Tone Analyzer, Microsoft Azure Text Analytics) to detect user emotions from the query content.

[1425] Input: Query data received as an HTTP POST request.

[1426] Data processing: Tokenization of inquiry content, keyword extraction, sentiment recognition.

[1427] Output: Tokenized data, extracted keywords, detected emotions (e.g., "anger").

[1428] Step 3: Inquiry classification and sentiment-based adjustment

[1429] Server: Classifies the query content into categories based on the output of the NLP engine and the emotion recognition engine.

[1430] Server: For example, queries containing keywords such as "account" and "password" are categorized under "account management".

[1431] Server: Based on detected emotions, it adjusts the appropriate department and automated response message. For example, if anger is detected, it prioritizes routing the request to the appropriate department.

[1432] Input: Tokenized data, extracted keywords, and detected sentiment.

[1433] Data processing: Categorizing inquiries and determining which department should handle them based on their emotional impact.

[1434] Output: Classified inquiry category, determination of the relevant department.

[1435] Step 4: Automatic sorting and emotionally responsive replies

[1436] Server: Adds classified inquiries to the queue of the appropriate department. For example, inquiries in the "Account Management" category are prioritized for the account management team.

[1437] Server: Select an appropriate automated reply message template based on the user's emotion. Choose a template that includes wording that takes the user's emotion (in this case, "anger") into consideration.

[1438] Server: Generates an automated reply email and sends it to the user, including "password reset instructions" and a statement promising a prompt response.

[1439] Input: Classified inquiry category, department to handle, sentiment data.

[1440] Data processing: Generating automated reply messages and distributing them to the appropriate department.

[1441] Output: Automated reply email, inquiry added to the queue of the relevant department.

[1442] Step 5: Notification of response status and solution

[1443] Server: Notifies the user of the status of their inquiry. For example, it might send a status update email stating, "Your inquiry has been forwarded to the account management team. We will address it promptly."

[1444] Server: Once the issue is resolved, a final notification email containing the solution will be sent to the user, and the inquiry ticket will be closed. This email will include specific steps for resolution and suggested improvements.

[1445] Input: Feedback from the relevant department, progress of the inquiry.

[1446] Data processing: Summarizing the status and solutions, and generating notification emails.

[1447] Output: Status update email, final notification email.

[1448] The above is a detailed explanation of the processing flow of this system's program.

[1449] (Application Example 2)

[1450] 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".

[1451] Conventional inquiry handling systems have struggled to properly categorize user inquiries and distribute them to the appropriate departments. Furthermore, they often fail to respond in a way that respects user emotions, potentially leading to decreased user satisfaction. In particular, in security services, it is crucial to quickly recognize and appropriately address user anxiety and anger; therefore, the ability to recognize and reflect emotions is essential. A system is needed to solve these problems and provide flexible, emotionally sensitive responses to user inquiries.

[1452] 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.

[1453] In this invention, the server includes means for receiving inquiries from users, means for analyzing inquiries using natural language processing and classifying them into categories, means for detecting the user's emotions using an emotion recognition engine, means for assigning inquiries to the appropriate department or an automated reply message based on the category and emotions, and means for notifying the user of the response status and solution. This enables a quick and accurate response to user inquiries, as well as a flexible response that takes the user's emotions into consideration.

[1454] A "user" is a person who uses the system to make inquiries.

[1455] An "inquiry" refers to a question or problem report submitted by a user to the system.

[1456] "Natural language processing" is a technology that enables computers to understand and analyze human language.

[1457] "Analysis" is the process of breaking down input data for a specific purpose and understanding its meaning and structure.

[1458] A "category" is a classification of topics or fields that characterize the content of an inquiry.

[1459] An "emotion recognition engine" is a technology that automatically detects emotions (e.g., anger, sadness, joy, etc.) from the content of a user's inquiry.

[1460] A "response department" is a specialized department that handles inquiries related to a specific category.

[1461] An "automatic reply message" is a response message that is generated by a system and automatically sent to the user.

[1462] "Response Status" refers to status information indicating the stage of the inquiry.

[1463] A "solution" refers to a solution or answer to a problem that a user is facing.

[1464] An "inquiry management system" is a system for recording and managing received inquiries and their processing status.

[1465] "Emotional information" refers to user emotional data extracted by an emotion recognition engine.

[1466] This invention relates to a system for efficiently processing user inquiries, and further incorporates an emotion engine that recognizes user emotions to adjust the response department or automated reply message according to those emotions. This system automates the reception, analysis (including emotion recognition), classification, sorting, and notification of inquiries, enabling flexible responses based on user emotions.

[1467] Hardware and software

[1468] Smartphone: A device used by users to input and submit inquiries.

[1469] Backend server: Built using Python, it handles inquiry data analysis, sentiment recognition, categorization, distribution to the appropriate department, generation of automated reply messages, and notifications.

[1470] The NLP engine spaCy is used to tokenize the query content and extract keywords and context.

[1471] Emotion recognition engine: Detects user emotions using Google Cloud Natural Language API or TensorFlow.

[1472] Messaging service: Use Firebase Cloud Messaging to send notifications to users.

[1473] Detailed description of the invention

[1474] 1. Inquiry reception

[1475] The user opens the application on their smartphone, enters their inquiry into a form for security-related questions and problem reports, and clicks the submit button.

[1476] The smartphone collects data entered by the user and sends it to a backend server in the cloud via an HTTP POST request.

[1477] 2. Inquiry Analysis and Sentiment Recognition

[1478] The server analyzes the received data using spaCy's NLP engine, tokenizes the input content, and extracts keywords and context.

[1479] Use the Google Cloud Natural Language API to detect user emotions (e.g., anger, sadness, anxiety).

[1480] 3. Inquiry classification and sentiment-based adjustment

[1481] Based on the results from the NLP engine, the server categorizes the query into categories such as "system error," "unauthorized access," and "phishing scam."

[1482] Based on the results of the emotion recognition engine, inquiries with high emotion scores will be processed preferentially.

[1483] 4. Automatic sorting and responses based on emotion

[1484] The server automatically routes classified inquiries to the appropriate department. For example, reports of unauthorized access are sent directly to the security team.

[1485] It generates emotion-based reply messages and sends customized messages to users, such as "We are investigating the situation" or "We promise to respond as soon as possible."

[1486] 5. Notification of response status and resolution.

[1487] The server will notify the user of the status of the issue as it progresses, and will send a final message and close the ticket once the problem is resolved.

[1488] Specific example

[1489] 1. User behavior

[1490] The user opens the application on their smartphone, types "I received a warning about unauthorized access when I tried to log in to a new account. I'm very worried," and clicks the send button.

[1491] 2. Server processing

[1492] The received data is analyzed using spaCy's NLP engine, and keywords (e.g., "new account," "login," "unauthorized access," "warning") are extracted.

[1493] The Google Cloud Natural Language API is used to analyze emotions and detect the emotion of "worry."

[1494] Inquiries are categorized as "unauthorized access" and forwarded to the security team on a priority basis based on their high sentiment score.

[1495] An emotion-based automated reply message, "We have received your report regarding unauthorized access. We will investigate immediately and take prompt action," is generated and sent to the user.

[1496] The system notifies the user of the status of their inquiry and sends a message stating, "Your inquiry is being handled with priority."

[1497] Example of a prompt

[1498] User inquiry: "When I tried to log in to my new account, I received a warning about unauthorized access. I'm very worried."

[1499] Tokenization using an NLP engine -> Keywords: ["New account", "Login", "Unauthorized access", "Warning"]

[1500] Emotion detection by emotion recognition engine -> Emotion: "Worry"

[1501] Classification: "Unauthorized Access"

[1502] Department in charge: Security Team

[1503] Automated reply message: "We have received your report regarding unauthorized access. We will investigate immediately and take prompt action."

[1504] Notice: "Inquiries are being handled with priority."

[1505] Final message: "The issue has been resolved. Your account is secure."

[1506] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1507] Step 1:

[1508] The user opens the application on their smartphone and enters their inquiry. Specifically, the user enters "I received a warning about unauthorized access when I tried to log in to a new account. I am very worried." into the text form on the software and clicks the submit button. The input data is the inquiry (input: user's inquiry, output: HTTP POST request).

[1509] Step 2:

[1510] The terminal sends the user's input as an HTTP POST request to the cloud backend server. Specifically, it converts the input data into a JSON payload and sends it to a specific endpoint on the server (e.g., / api / report_issue) (input: user's inquiry, output: JSON payload).

[1511] Step 3:

[1512] To analyze the data received by the server, spaCy's NLP engine is first used to tokenize the query content and extract keywords and context. For example, keywords such as "new account," "login," "unauthorized access," and "warning" are extracted (input: JSON payload, output: keywords and context).

[1513] Step 4:

[1514] The server uses the Google Cloud Natural Language API or a TensorFlow sentiment recognition model to detect emotions from the user's inquiry. For example, the emotion "worried" might be detected (input: inquiry (text), output: emotion information).

[1515] Step 5:

[1516] The server classifies queries into categories such as "unauthorized access" based on the results of the NLP engine and sentiment recognition. For example, based on the keywords "new account" and "unauthorized access," it will be classified into the "unauthorized access" category (input: keywords and sentiment information, output: category).

[1517] Step 6:

[1518] The server automatically routes inquiries to the appropriate department based on their sentiment score and category. For example, if the sentiment is "concerned," it is given a high priority and sent to the security team (input: category and sentiment information, output: appropriate department).

[1519] Step 7:

[1520] The server generates an automated reply message based on sentiment information and the content of the inquiry. For example, a message such as "We have received your report regarding unauthorized access. We will investigate immediately and take prompt action." will be generated (Input: Inquiry content and sentiment information, Output: Automated reply message).

[1521] Step 8:

[1522] The server uses Firebase Cloud Messaging to send a generated automated reply message to the user. The user receives the message on their smartphone and receives a notification that "Your inquiry is being handled with priority" (Input: Automated reply message, Output: Notification to user).

[1523] Step 9:

[1524] The server periodically notifies the user of the status of the inquiry. For example, a status update message such as "Your inquiry is currently under investigation" is sent (Input: Status, Output: Status update message).

[1525] Step 10:

[1526] Once the server resolves the issue, it sends a final notification message to the user and closes the inquiry ticket. For example, a message such as "The issue has been resolved. Your account is secure." is sent (Input: Resolution information, Output: Final notification message and ticket closure).

[1527] 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.

[1528] 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.

[1529] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1530] 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.

[1531] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1532] 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.

[1533] 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.

[1534] 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.

[1535] 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."

[1536] 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.

[1537] 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.

[1538] 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.

[1539] 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.

[1540] 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.

[1541] 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.

[1542] 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.

[1543] 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.

[1544] 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.

[1545] 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.

[1546] 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.

[1547] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[1548] The following is further disclosed regarding the embodiments described above.

[1549] (Claim 1)

[1550] A means of receiving inquiries from users,

[1551] A means for analyzing the aforementioned query using natural language processing and classifying it into a query category,

[1552] A means for distributing the aforementioned classified inquiries to the appropriate department or an automated reply message based on their category,

[1553] A means for notifying the user of the status of the response and the solution method,

[1554] A system that includes this.

[1555] (Claim 2)

[1556] The system according to claim 1, further comprising means for recording the content of the inquiry in an inquiry management system when forwarding the inquiry to the relevant department.

[1557] (Claim 3)

[1558] The system according to claim 1, further comprising means for generating an automated reply email based on the content of the inquiry and sending it to the user.

[1559] "Example 1"

[1560] (Claim 1)

[1561] A means of receiving inquiries from users,

[1562] A method for analyzing received inquiries using natural language processing to extract keywords and context,

[1563] A means for determining the category of an inquiry based on extracted keywords,

[1564] A means for distributing the aforementioned classified inquiries to the appropriate department or an automated reply message based on their category,

[1565] A means of notifying the user of the status and solution,

[1566] A system that includes this.

[1567] (Claim 2)

[1568] The system according to claim 1, further comprising means for recording the content of the inquiry in an inquiry management system when forwarding the inquiry to the relevant department.

[1569] (Claim 3)

[1570] The system according to claim 1, further comprising means for generating an automated reply email based on the content of the inquiry and sending it to the user.

[1571] "Application Example 1"

[1572] (Claim 1)

[1573] A means of receiving inquiries from users,

[1574] A means for analyzing the aforementioned query using natural language processing and classifying it into a query category,

[1575] A means for distributing the aforementioned classified inquiries to the appropriate department or an automated reply message based on their category,

[1576] A means for notifying the user of the status of the response and the solution method,

[1577] A means of handling inquiries about delivery status within the logistics center,

[1578] A means to accurately analyze inquiries about delivery delays and damaged goods and route them to the appropriate department,

[1579] A means of providing the user with an automated reply message regarding delivery delays or product damage,

[1580] A system that includes this.

[1581] (Claim 2)

[1582] The system according to claim 1, further comprising means for recording the content of the inquiry in an inquiry management system when forwarding the inquiry to the relevant department.

[1583] (Claim 3)

[1584] The system according to claim 1, further comprising means for generating an automated reply email based on the content of the inquiry and sending it to the user.

[1585] "Example 2 of combining an emotion engine"

[1586] (Claim 1)

[1587] A means of receiving inquiries from users,

[1588] A means for analyzing the aforementioned query using natural language processing and classifying it into a query category,

[1589] A means for detecting emotions from the aforementioned inquiry content,

[1590] A means for routing inquiries to the appropriate department or an automated reply message based on the aforementioned classification and detected emotions,

[1591] A means for notifying the user of the status of the response and the solution method,

[1592] A system that includes this.

[1593] (Claim 2)

[1594] The system according to claim 1, further comprising means for recording the content of the inquiry in an inquiry management system when forwarding the inquiry to the relevant department.

[1595] (Claim 3)

[1596] The system according to claim 1, further comprising means for generating and sending an automated reply email to the user based on the content of the inquiry and the detected emotions.

[1597] "Application example 2 when combining with an emotional engine"

[1598] (Claim 1)

[1599] A means of receiving inquiries from users,

[1600] A means for analyzing the aforementioned query using natural language processing and classifying it into a query category,

[1601] A means for detecting a user's emotions using an emotion recognition engine,

[1602] A means of assigning the recipient to the appropriate department or to an automated reply message based on the aforementioned category and emotion,

[1603] A means for notifying the user of the status of the response and the solution method,

[1604] A system that includes this.

[1605] (Claim 2)

[1606] The system according to claim 1, further comprising means for recording the content of the inquiry and sentiment information in the inquiry management system when forwarding the inquiry to the relevant department.

[1607] (Claim 3)

[1608] The system according to claim 1, further comprising means for generating an automated reply message based on the aforementioned inquiry content and sentiment information and sending it to the user. [Explanation of symbols]

[1609] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of receiving inquiries from users, A means for analyzing the aforementioned query using natural language processing and classifying it into a query category, A means for distributing the aforementioned classified inquiries to the appropriate department or an automated reply message based on their category, A means for notifying the user of the status of the response and the solution method, A system that includes this.

2. The system according to claim 1, further comprising means for recording the content of the inquiry in an inquiry management system when forwarding the inquiry to the relevant department.

3. The system according to claim 1, further comprising means for generating an automatic reply email based on the content of the inquiry and sending it to the user.

Images