System

Abstract

A system is provided.SOLUTION: The system includes a means for providing an interface for inputting an inquiry content, a means for transmitting the inquiry content to a server, a means for analyzing the received inquiry content and extracting a main keyword and an intention, a means for generating a related sample wording based on the extracted keyword and the intention, and a means for displaying the generated sample wording.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] In current call center operations, training new operators requires a great deal of time and effort, making it difficult to provide standardized responses. Furthermore, the time required to promptly respond to user inquiries tends to be long. This leads to problems such as reduced user satisfaction and operational efficiency. The present invention aims to provide a system that reduces the time required for training new operators and shortens response times, thereby improving operational efficiency. [Means for solving the problem]

[0005] The present invention solves the above problems by the following means. First, it includes a means for providing an interface for a user to input inquiry content. Next, it includes a means for transmitting the inquiry content to a server, and the server analyzes the received inquiry content. The analysis is performed using a natural language processing algorithm to extract main keywords and intent. It includes a means for generating related sample phrases based on the extracted keywords and intent, and sending these to the terminal for display. Furthermore, it provides appropriate sample phrases by using a means for searching for response templates from a database in the server. This enables quick and appropriate responses, and even new operators can provide high-quality responses.

[0006] The "interface for inputting inquiry details" refers to a means for providing a screen or form that a user uses to input inquiry details.

[0007] The "means for transmitting the contents of the inquiry to the server" refers to a means including a function and a protocol for transmitting the contents of the input inquiry to the server.

[0008] "Means for analyzing the content of the received inquiry and extracting the main keywords and intent" refers to a function that analyzes the content of the inquiry received by the server using algorithms such as natural language processing, and identifies the main keywords and the user's intent.

[0009] The "means for generating relevant sample phrases based on the extracted keywords and intent" is a function for searching a database for and generating appropriate response phrases based on the analyzed keywords and intent.

[0010] The "means for displaying the generated sample text" is a function for displaying the generated sample text on the terminal so that the user can check it.

[0011] A "database" is a searchable data storage system that stores response templates and related information corresponding to inquiries.

[0012] "Natural language processing algorithm" is a general term for algorithms and methods for analyzing text data and understanding its meaning and intent. [Brief explanation of the drawings]

[0013] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0014] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0017] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0018] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0019] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0021] [First embodiment]

[0022] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0023] 1, a 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.

[0024] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0026] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the 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.

[0027] 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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0029] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

[0031] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0033] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0034] The present invention relates to a call center support system that promptly proposes appropriate sample phrases in response to user inquiries. The system includes a program that analyzes the content of a user's inquiry and generates and displays appropriate response phrases.

[0035] System configuration and functions

[0036] User query input

[0037] The terminal provides an interface for the user to input the inquiry details. This interface is composed of a form that includes a text box for inputting the inquiry details and a send button. When the user inputs the inquiry details and presses the send button, the input details are sent to the server.

[0038] Sending and analyzing inquiries

[0039] The server receives the inquiry sent from the device and temporarily stores it. It then uses a natural language processing (NLP) algorithm to analyze the text of the inquiry. This analysis extracts key keywords and the user's intent. For example, keywords such as "bill," "not received," and "what should I do" are extracted.

[0040] Generating sample text based on inquiry content

[0041] The server searches an internal database for relevant response templates based on the extracted keywords and intent. The database contains multiple response templates for various inquiries. When a suitable template is found, the server generates a sample message based on it. For example, the message generated might be, "Dear customer, I understand you haven't received this month's invoice yet. I'm sorry. Could you please tell me your address and registered phone number for confirmation?"

[0042] Viewing and Using Sample Wording

[0043] The generated sample text is sent from the server to the terminal. The terminal displays this sample text to the user. The user can check the displayed sample text and make fine adjustments as necessary, or use it as is. The text that has been finalized as the final response text is sent by the user by pressing the send button.

[0044] Specific examples

[0045] A specific example will be explained below in which a user inquires, "I haven't received this month's invoice yet. What should I do?"

[0046] 1. User query input

[0047] The terminal displays a form for the user to input the inquiry.

[0048] The user enters the inquiry content in the text box and presses the send button.

[0049] 2. Sending and analyzing inquiries

[0050] The terminal transmits the input inquiry to the server.

[0051] The server analyzes the received query using a natural language processing algorithm.

[0052] As a result of the analysis, the keywords and intents extracted are "invoice," "not received," and "what should I do."

[0053] 3. Generating sample text based on inquiry content

[0054] The server searches for an appropriate template from a database based on the extracted keywords and intent.

[0055] The server generates a sample message: "Sir, I understand that you haven't received this month's invoice yet. I'm sorry. To confirm, could you please tell me your address and registered phone number?"

[0056] 4. Displaying and Using Sample Wording

[0057] The terminal displays the generated sample text to the user.

[0058] The user can fine-tune the displayed sample text as needed and then press the send button to send it as the final response text.

[0059] This system allows even new operators to respond quickly and appropriately, shortening user waiting times and improving work efficiency.

[0060] The processing flow will be explained below.

[0061] Step 1:

[0062] The terminal displays an interface (such as a text box and a send button) for the user to input the inquiry content.

[0063] Step 2:

[0064] The user enters the inquiry (e.g., "I haven't received this month's invoice yet. What should I do?") into the terminal interface and presses the send button.

[0065] Step 3:

[0066] The device sends the entered query to the server using a protocol such as an HTTP request or WebSocket.

[0067] Step 4:

[0068] The server temporarily stores the inquiry received from the terminal and invokes a natural language processing algorithm.

[0069] Step 5:

[0070] The server uses natural language processing algorithms to analyze the text of the inquiry, extracting key keywords (e.g., "bill," "not received," "what should I do") and the user's intent.

[0071] Step 6:

[0072] The server searches for relevant response templates from a database that stores past inquiries and response phrases based on the keywords and intent extracted from the analysis results.

[0073] Step 7:

[0074] The server selects the most suitable response template and generates a sample message based on that template, such as, "Dear customer, I understand that you have not yet received this month's invoice. We are sorry. To confirm, could you please tell us your address and registered phone number?"

[0075] Step 8:

[0076] The server transmits the generated sample text to the terminal.

[0077] Step 9:

[0078] The terminal displays the received sample text to the user, who can refer to the displayed sample text and make fine adjustments as necessary.

[0079] Step 10:

[0080] The user checks the sample text for fine tuning or as is, and presses the send button to confirm it as the final response text.

[0081] Example 1

[0082] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0083] Modern call center operations require quick and appropriate responses to user inquiries, but this is often difficult for new operators and inexperienced staff. There is also a need to reduce response times and improve operational efficiency. Conventional systems have difficulty effectively providing appropriate responses based on user inquiries.

[0084] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0085] In this invention, the server includes a means for analyzing the content of the inquiry using a natural language processing algorithm and extracting key keywords and intent, a means for generating related sample phrases from an internal database using a generative AI model based on the extracted keywords and intent, and a means for using a prompt sentence as an input sentence to the generative AI model, thereby enabling the generation and display of a prompt and appropriate response sentence.

[0086] A "terminal" is a device through which a user inputs their inquiry and communicates with the server, and generally refers to a PC or smartphone.

[0087] "Interface" refers to the screen and input form that users use to interact with the system via their terminal, and includes a text box for entering inquiry details and a send button.

[0088] A "server" is a computer system that receives, stores, analyzes inquiries sent by users, and generates appropriate sample text.

[0089] A "natural language processing algorithm" is a technology for analyzing text data, extracting elements, and understanding meaning, and typical examples use software libraries such as "NLTK" and "spaCy."

[0090] "Keywords" refer to the most important words and expressions extracted from the user's inquiry.

[0091] "Intent" refers to what the user is seeking through their inquiry, their purpose or desire.

[0092] The "internal database" is an information resource that stores response templates for various inquiries and is used to generate sample phrases.

[0093] A "generative AI model" is a model that uses artificial intelligence technology to automatically generate appropriate sample phrases, generating responses using specific prompt phrases as input.

[0094] A "prompt" is a text sentence that indicates specific conditions or questions to the generative AI model, and serves as the basis for generating a response.

[0095] The present invention relates to a call center operation support system that responds quickly and appropriately to user inquiries. This system analyzes the content of user inquiries, generates related sample phrases, and displays them to the user, thereby improving work efficiency.

[0096] Components and Functions

[0097] User query input

[0098] The user inputs the inquiry using a terminal (e.g., a PC or smartphone). An interface for inputting the inquiry is displayed on this terminal. The interface includes a text box and a send button. When the user inputs the inquiry and presses the send button, the inquiry is sent to the server.

[0099] Sending and analyzing inquiries

[0100] The terminal sends the inquiry content entered by the user to the server using an HTTP request.

[0101] The server temporarily stores the query received from the device and then analyzes it using a natural language processing (NLP) algorithm. This analysis process uses Python's "NLTK" or "spaCy." The server then extracts important keywords and the user's intent.

[0102] Generating sample phrases based on extracted keywords and intent

[0103] The server searches for relevant response templates from its internal database based on the extracted keywords and intent. Once a suitable template is found, the server uses a "generative AI model" to generate the optimal sample phrase. An example prompt phrase is "I haven't received this month's invoice yet, what should I do?" The generated sample phrase is "Sir, I understand you haven't received this month's invoice yet. I'm sorry. Could you please tell me your address and registered phone number for verification?"

[0104] Viewing and Using Sample Wording

[0105] The server sends the generated sample text to the terminal. The terminal uses HTML and JavaScript (registered trademark) to display this sample text to the user. The user can check the displayed sample text and make fine adjustments as necessary. If the user wants to use it as is, they can simply press the send button to confirm it as the final response text.

[0106] Specific examples

[0107] When a user inquires, "I haven't received this month's invoice yet, what should I do?", the system operates as follows:

[0108] 1. The user enters the inquiry details into the form on the device and presses the send button.

[0109] 2. The device sends the input to the server.

[0110] 3. The server analyzes the received content using a natural language processing algorithm and extracts the keywords "invoice," "not received," and "what should I do."

[0111] 4. The server searches the database for relevant templates and generates sample text using a generative AI model.

[0112] 5. The server sends the generated sample text to the terminal, which displays it to the user.

[0113] 6. The user checks and adjusts the sample text, then finalizes and sends the final response.

[0114] This system allows even new operators to respond quickly and appropriately, shortening user waiting times and improving work efficiency.

[0115] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0116] Step 1: User query input

[0117] The user inputs the inquiry into the terminal interface and presses the send button. This interface includes a text box for inputting the inquiry and a send button.

[0118] Input: Text data of the inquiry entered by the user

[0119] Output: Form data for sending inquiry content from the terminal to the server

[0120] Step 2: Submit your inquiry

[0121] The terminal sends the query entered by the user to the server, using an HTTP request to send the data.

[0122] Input: Text data of the inquiry entered by the user

[0123] Output: HTTP request data received by the server

[0124] Step 3: Receiving and temporarily saving your inquiry

[0125] The server receives the inquiry sent from the terminal and temporarily stores it.

[0126] Input: HTTP request data sent from the terminal

[0127] Output: Text data of the temporarily saved inquiry

[0128] Step 4: Analyzing the inquiry

[0129] The server analyzes the stored query using natural language processing (NLP) algorithms, such as NLTK and spaCy. As a result of the analysis, key keywords and user intent are extracted.

[0130] Input: Text data of the inquiry that was temporarily saved

[0131] Data processing: Analysis using natural language processing algorithms and keyword extraction

[0132] Output: Extracted main keywords and user intent

[0133] Step 5: Generate sample text

[0134] The server searches for relevant response templates from its internal database based on the extracted keywords and intent. Once a suitable template is found, the server uses a generative AI model to generate sample prompts. An example prompt is, "I haven't received my monthly bill yet. What should I do?"

[0135] Input: Extracted keywords and user intent

[0136] Data processing: Search for templates from an internal database and generate sample text using a generative AI model

[0137] Output: Generated sample text

[0138] Step 6: Submit and view sample text

[0139] The server sends the generated sample text to the terminal.

[0140] The device displays the received sample text to the user using HTML and JavaScript.

[0141] Input: Generated sample text

[0142] Output: Screen (interface) showing sample text

[0143] Step 7: Review and adjust user responses

[0144] The user checks the displayed sample text, makes minor adjustments as necessary, and presses the send button again to confirm the final response text after adjustments.

[0145] Input: Sample text displayed

[0146] Output: Final response sentence adjusted by the user

[0147] Step 8: Sending a Final Response

[0148] The terminal sends the adjusted final response to the server or other relevant departments.

[0149] Input: Adjusted final response

[0150] Output: The final response received by the server

[0151] (Application example 1)

[0152] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0153] In conventional call center operations, responses to user inquiries depended heavily on the experience and ability of the operator, and new operators were often slow to respond or unable to provide appropriate responses. This also created problems such as long wait times for users to receive appropriate responses. This resulted in a poor customer experience and a decline in operational efficiency.

[0154] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0155] In this invention, the server includes means for providing an interface for inputting inquiry content, means for transmitting the inquiry content, means for analyzing the received inquiry content and extracting main keywords and intent, means for generating related sample phrases based on the extracted keywords and intent, means for displaying the generated sample phrases, and means for the user to fine-tune and transmit a final response, thereby enabling prompt and appropriate response phrases to be presented.

[0156] The "means for providing an interface for inputting inquiry details" refers to a device or program that provides a format or screen for the user to input inquiry details.

[0157] The "means for transmitting the inquiry content to the server" refers to a device or program for transmitting the inquiry content input by the user to the server via the network.

[0158] "Means for analyzing the content of the received inquiry and extracting key keywords and intent" refers to a device or program that uses natural language processing technology to analyze the content of the inquiry sent to the server and identify important words and the user's intent from within it.

[0159] The "means for generating relevant sample phrases based on the extracted keywords and intent" refers to a device or program that generates appropriate response phrases based on the extracted keywords and the user's intent.

[0160] The "means for displaying the generated sample message" refers to a device or program that visually presents the generated response message to the user.

[0161] The "means for the user to fine-tune and send the final response" refers to a device or program that allows the user to fine-tune the sample wording provided and then send it as the final response.

[0162] The "means for searching a database for a response template" refers to a device or program that searches a database for a response template related to the content of the inquiry.

[0163] "Natural language processing algorithms" are a series of algorithms that allow computers to understand, generate, and analyze natural human language.

[0164] The system for implementing this invention includes a series of processes for allowing users to input inquiry content and provide quick and appropriate sample phrases. This system mainly consists of the following components:

[0165] 1. User query input

[0166] The user inputs the inquiry details through the smartphone application. The interface includes a text box and a send button, and when the user inputs the inquiry details and presses the send button, the details are sent to the server.

[0167] 2. Sending and analyzing inquiries

[0168] The query sent from the device is received by the server and temporarily stored. The server then uses natural language processing (NLP) algorithms to analyze the text of the query. The analysis extracts key keywords and the user's intent. NLP libraries such as spaCy are used in this process.

[0169] 3. Generating sample text based on inquiry content

[0170] The server searches its internal database for relevant response templates based on the extracted keywords and intent. Once a suitable template is found, a sample response is generated. This response template is randomly selected from a set of pre-defined templates.

[0171] 4. Displaying and Using Sample Wording

[0172] The generated sample text is sent back to the terminal and displayed to the user, who can then fine-tune the displayed sample text as needed and send the final response text.

[0173] This system allows even new operators to respond quickly and appropriately, shortening user waiting times and maintaining consistency in responses, improving operational efficiency.

[0174] Specific examples

[0175] Consider the case where a user types "I haven't received my bill this month yet, what should I do?" into a smartphone application. When the user presses the send button, the text is sent to the server. The server uses NLP to analyze the text and extract the keywords "bill," "not received," and "what should I do." Based on this, a relevant response template is searched for in the database and a sample response is generated: "Sir, I understand you haven't received your bill this month yet. I'm sorry. Could you please tell me your address and registered phone number for confirmation?" This response is displayed on the user's device, and the user can fine-tune it as needed and send it as the final response.

[0176] Example prompts to input to the generative AI model

[0177] Please enter the content of your inquiry. For example, if you enter "I haven't received this month's invoice yet, what's going on?", sample text that will promptly respond to this content will be displayed.

[0178] In this way, the system of the present invention simultaneously improves the efficiency of inquiry response work and user satisfaction.

[0179] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0180] Step 1:

[0181] The user inputs the inquiry using the smartphone interface.

[0182] Specific operation: The user enters an inquiry such as "I haven't received this month's bill yet. What should I do?" into the text box on their smartphone and presses the send button.

[0183] Input: The text of the inquiry.

[0184] Output: The data sent to the server based on the query entered.

[0185] Step 2:

[0186] The terminal sends the inquiry to the server.

[0187] Specific operation: The entered text data is sent to the server via the network, typically using an HTTP POST request.

[0188] Input: The query entered by the user.

[0189] Output: The server receives the query and begins processing it.

[0190] Step 3:

[0191] The server analyzes the received query and extracts the main keywords and the user's intent.

[0192] What it does: The server uses NLP algorithms (e.g., spaCy) to analyze the text and extract important keywords such as nouns and verbs, as well as the user's intent.

[0193] Input: Text data of the inquiry.

[0194] Output: Extracted keywords and user intent (e.g., "invoice," "not received," "what should I do?").

[0195] Step 4:

[0196] The server generates relevant sample text based on the extracted keywords and intent.

[0197] Specific operation: Based on the extracted keywords, the server searches for an appropriate response template from its internal database and uses that template to generate sample phrases. The generated sample phrases may be selected randomly.

[0198] Input: Extracted keywords and intent.

[0199] Output: Generated sample text (e.g., "Dear customer, I understand you haven't received this month's invoice yet. Could you please provide your address and registered phone number so we can verify this?").

[0200] Step 5:

[0201] The server sends the generated sample text to the terminal.

[0202] Specific operation: The generated sample text is sent back to the user's device via the network using an HTTP response.

[0203] Input: Generated sample text.

[0204] Output: A sample message that will be displayed on the user's device.

[0205] Step 6:

[0206] The user reviews the sample wording, makes any necessary adjustments, and submits the final response.

[0207] Specific operation: The user checks the displayed sample text, fine-tunes it using a text editor if necessary, and presses the send button to finalize the response text.

[0208] Input: Sample text and user tweaks.

[0209] Output: The data that will be sent as the final response.

[0210] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0211] The present invention relates to a call center support system that promptly proposes appropriate sample phrases in response to user inquiries. This system analyzes the content of the user's inquiry, generates and displays appropriate response phrases, and also includes a means for recognizing the user's emotions and reflecting them in the response template.

[0212] System configuration and functions

[0213] User query input

[0214] The terminal provides an interface for the user to input the inquiry details. This interface is composed of a form that includes a text box for inputting the inquiry details and a send button. When the user inputs the inquiry details and presses the send button, the input details are sent to the server.

[0215] Sending and analyzing inquiries

[0216] The server receives and temporarily stores the query sent from the device, then uses natural language processing (NLP) algorithms to analyze the text of the query, extracting key keywords and the user's intent.

[0217] Emotion recognition by emotion engine

[0218] The server uses an emotion engine to analyze the user's emotions from the text of the inquiry, recognizing, for example, emotional states such as anger, confusion, and sadness, thereby gaining a deeper understanding of the context and urgency of the inquiry.

[0219] Generating sample text based on inquiry content

[0220] The server searches for relevant response templates from its internal database based on the analyzed keywords and intent, as well as the results of the emotion engine. The database contains multiple response templates corresponding to various inquiry contents. For example, if the emotion is "anger," a more polite template that includes an apology is selected. The server generates sample text based on these templates.

[0221] Viewing and Using Sample Wording

[0222] The generated sample text is sent from the server to the terminal. The terminal displays this sample text to the user. The user can check the displayed sample text and make fine adjustments as necessary, or use it as is. The text that has been finalized as the final response text is sent by the user by pressing the send button.

[0223] Specific examples

[0224] A specific example will be described in which a user makes an inquiry such as, "I haven't received this month's bill yet. What should I do? I'm really in trouble."

[0225] 1. User query input

[0226] The terminal displays a form for the user to input the inquiry.

[0227] The user enters the inquiry content in the text box and presses the send button.

[0228] 2. Sending and analyzing inquiries

[0229] The terminal transmits the input inquiry to the server.

[0230] The server analyzes the received query using a natural language processing algorithm.

[0231] As a result of the analysis, the keywords and intents extracted are "invoice," "not received," and "what should I do."

[0232] 3. Emotion Recognition by Emotion Engine

[0233] The server analyzes the user's emotions from the text of the inquiry. For example, the emotion "confused" is recognized.

[0234] 4. Generating sample text based on inquiry content

[0235] The server searches for an appropriate template from the database based on the extracted keywords, intent, and the results of the emotion engine.

[0236] The server generates a sample message that reads, "Dear customer, we are very sorry for the inconvenience. We understand that you have not yet received your monthly bill. Could you please provide us with your address and registered phone number so we can verify this?"

[0237] 5. Viewing and Using Sample Wording

[0238] The terminal displays the generated sample text to the user.

[0239] The user can fine-tune the displayed sample text as needed and then press the send button to send it as the final response text.

[0240] This system enables appropriate responses that take into account the user's emotions, allowing even new operators to provide high-quality service.

[0241] The processing flow will be explained below.

[0242] Step 1:

[0243] The terminal displays an interface (such as a text box and a send button) for the user to input the inquiry content.

[0244] Step 2:

[0245] The user enters the inquiry into the terminal interface (e.g., "I haven't received this month's invoice yet. What should I do? I'm really worried.") and presses the send button.

[0246] Step 3:

[0247] The device sends the entered query to the server using a protocol such as an HTTP request or WebSocket.

[0248] Step 4:

[0249] The server temporarily stores the inquiry received from the terminal and invokes a natural language processing algorithm.

[0250] Step 5:

[0251] The server uses natural language processing algorithms to analyze the text of the inquiry, extracting key keywords (e.g., "bill," "not received," "what should I do," "I'm having trouble") and the user's intent.

[0252] Step 6:

[0253] The server uses an emotion engine to analyze the user's emotion from the text of the inquiry. For example, the emotion "confusion" is recognized from the part "I'm in trouble."

[0254] Step 7:

[0255] The server searches a database for relevant response templates based on the analysis results (keywords and emotions). The database contains multiple response templates corresponding to various inquiry contents. In particular, considering that the emotion is "confusion," the server selects a template that is more polite and shows empathy.

[0256] Step 8:

[0257] The server generates a sample message based on the most suitable template, such as "Dear customer, we apologize for the inconvenience. We understand that you have not yet received this month's invoice. To confirm, could you please provide us with your address and registered phone number?"

[0258] Step 9:

[0259] The server transmits the generated sample text to the terminal.

[0260] Step 10:

[0261] The terminal displays the received sample text to the user, who can then check the displayed sample text and make fine adjustments as necessary.

[0262] Step 11:

[0263] The user checks the sample text for fine tuning or leaves it as is, and then presses the send button to send it as the final response text.

[0264] Example 2

[0265] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0266] In conventional call center operations, providing prompt and appropriate responses to user inquiries has been a challenge. It is particularly difficult for new operators to generate appropriate responses to inquiries. Furthermore, there is a lack of means to automatically generate responses that take the user's emotions into consideration, which results in inconsistent response quality and lower customer satisfaction.

[0267] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for analyzing the content of the inquiry and extracting main keywords and intention, means for using an emotion engine for analyzing the user's emotions, and means for searching a database for a response template based on the extracted keywords, intention, and emotion analysis. This makes it possible to quickly generate and display appropriate sample phrases, allowing even new operators to provide high-quality responses.

[0268] The "interface for inputting inquiry details" is an interface that allows a user to input inquiry details via a text box, a send button, etc., and send the details to the server.

[0269] The "means for sending the inquiry content to the server" is a function for sending the inquiry content entered by the user to the server using a protocol such as HTTP or HTTPS.

[0270] "Means of analyzing the content of the received inquiry and extracting key keywords and intent" refers to the function of analyzing the text data received by the server using a natural language processing algorithm to identify and extract important keywords and the user's intent.

[0271] The "means for generating relevant sample phrases" is a function that generates appropriate response phrases from templates based on the analyzed keywords and intent.

[0272] The "means for using an emotion engine to analyze user emotions" is a function that uses an engine to analyze emotions (e.g., anger, confusion, sadness, etc.) from the user's inquiry text and quantify or categorize them.

[0273] "Means for searching for response templates from a database" refers to a function that searches for and retrieves appropriate response templates stored in a database based on the results of extracted keywords, intent, and sentiment analysis.

[0274] The "means for displaying the generated sample text" is a function for displaying the sample text sent from the server on the interface of the terminal, and visually presenting it to the user.

[0275] The present invention relates to a call center support system that promptly proposes appropriate sample phrases in response to user inquiries. This system analyzes the content of the user's inquiry, generates and displays appropriate response phrases, and also includes a means for recognizing the user's emotions and reflecting them in the response template.

[0276] User query input

[0277] The terminal provides an interface for the user to input the inquiry details. The interface is constructed using HTML and JavaScript, and provides a form including a text box and a submit button. The user enters the inquiry details in the text box and presses the submit button, which sends the input details from the terminal to the server.

[0278] Sending and analyzing inquiries

[0279] The device sends the entered query to the server using HTTP or HTTPS. The server stores the received query in a database or temporary memory. Examples of storage technologies include MySQL (registered trademark) and Redis. The server then analyzes the query using natural language processing (NLP) algorithms such as Python's NLTK or SpaCy to extract key keywords and the user's intent.

[0280] Emotion recognition by emotion engine

[0281] The server uses an emotion engine, such as IBM Watson® Tone Analyzer or Microsoft® Text Analytics, to analyze the user's emotion from the text of the query. Using these tools, the server recognizes the emotion in the text (e.g., anger, confusion, sadness) and quantifies the emotional state.

[0282] Generating sample text based on inquiry content

[0283] The server searches for relevant response templates from an internal database based on the analyzed keywords, intent, and emotion engine results. The database contains multiple response templates corresponding to various inquiry contents. Using a database query system, it is possible to quickly search for the optimal template according to the user's emotion and inquiry content. Based on the searched template, the server generates sample text using a template engine such as Jinja2 or Handlebars.

[0284] Viewing and Using Sample Wording

[0285] The generated sample text is sent from the server to the device as an HTTP response. The device displays this sample text to the user using HTML and JavaScript. The user can check the displayed sample text and make fine adjustments as needed, or use it as is. Once the text is finalized, the user presses the send button to send the final response text.

[0286] Examples of concrete examples and prompts

[0287] For example, a specific case will be described in which a user makes an inquiry such as, "I haven't received this month's bill yet. What should I do? I'm really in trouble."

[0288] The user enters "I haven't received this month's bill yet. What should I do? I'm really worried." in the text box and presses the submit button.

[0289] The terminal sends the query to the server, which then analyzes the received query using a natural language processing algorithm.

[0290] As a result of the analysis, the keywords "bill," "not received," and "what should I do" as well as the user's emotion of "confusion" are extracted.

[0291] Using this information, the server searches a database for an appropriate response template and generates a sample message like this: "Dear customer, we apologize for the inconvenience. We understand that you have not yet received your monthly bill. Could you please provide us with your address and registered phone number so we can verify this?"

[0292] The generated sample text is sent to the terminal, which displays it to the user. The user can check the displayed text, make any necessary adjustments, and then press the send button to send the finalized response text.

[0293] An example of a prompt is as follows:

[0294] "User's question: I haven't received my invoice for this month yet, what should I do? I'm really worried.

[0295] Analysis results: Keywords: bill, not received, what to do. Emotions: confusion.

[0296] Please generate a sample response for this."

[0297] This series of processes makes it possible to provide a quick and appropriate response that takes into account the user's feelings, improving the efficiency and quality of call center operations.

[0298] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0299] Step 1: User query input

[0300] The terminal displays an input interface for the user. This interface is a form with a text box and a submit button. The screen is designed to be simple so that the user can easily enter their inquiry.

[0301] User input: The user enters the inquiry "I haven't received this month's invoice yet, what should I do?" into the text box and presses the send button. The input format is text-based.

[0302] Input and Output: The input is the query entered by the user, and the output is the query data ready to be sent.

[0303] Step 2: Submit your inquiry

[0304] The terminal sends the entered query to the server using the HTTP or HTTPS protocol, with the data being sent in JSON format.

[0305] Input and output: The input is the query entered by the user, and the output is a notification of completion of transmission to the server.

[0306] Step 3: Receiving and storing your inquiry

[0307] The server receives the inquiry sent from the terminal and temporarily stores it in a database (e.g., MySQL or Redis).

[0308] Input and output: The input is the query content sent from the terminal, and the output is the query data stored in the database.

[0309] Specific operation: The server receives the HTTP request and saves the query in the database.

[0310] Step 4: Text Analysis

[0311] The server analyzes the received queries using natural language processing (NLP) algorithms, specifically Python's NLTK or SpaCy.

[0312] Input and Output: The input is the stored query content, and the output is a set of parsed keywords and intents.

[0313] Specific operation: A program is run to tokenize the query and extract key keywords and user intent.

[0314] Step 5: Sentiment Analysis

[0315] The server uses an emotion engine to analyze the user's emotions from the text of the inquiry, specifically using IBM Watson Tone Analyzer and Microsoft Text Analytics.

[0316] Input and Output: The input is the text of the query, and the output is the analyzed emotion data (e.g., anger, confusion, sadness, etc.).

[0317] What it does: The emotion engine analyzes the text and quantifies or categorizes the user's emotion.

[0318] Step 6: Find the response template

[0319] The server searches a database for an appropriate response template based on the extracted keywords and the results of the intent and sentiment analysis.

[0320] Input and Output: The input is the extracted keywords, intent, and emotion data, and the output is the response template.

[0321] What it does: Runs a database query to find the best response template.

[0322] Step 7: Generate sample text

[0323] The server generates sample text based on the retrieved response template using a template engine (e.g., Jinja2 or Handlebars).

[0324] Input and Output: The input is the response template and the parsed results, and the output is the generated sample text.

[0325] Specific behavior: Dynamically generate sample text using a template engine.

[0326] Step 8: Submit and view sample text

[0327] The server sends the generated sample text to the terminal in the form of an HTTP response.

[0328] The device displays the received sample text to the user using HTML and JavaScript.

[0329] Input and Output: The input is the generated sample text, and the output is the display to the user.

[0330] Specific behavior: The device displays sample text in the text area for the user to review and adjust.

[0331] Step 9: User confirmation, adjustments and final submission

[0332] The user can check the sample text displayed and make any necessary adjustments. Once the adjustments are complete, the user presses the send button to send the final response text.

[0333] Input and Output: The input is the displayed sample text, the user's adjustments, and the output is the final response text.

[0334] Specific operation: The user checks and adjusts the sample text, and then sends the final response text to the server.

[0335] (Application example 2)

[0336] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0337] Modern inquiry response systems are required to provide prompt and appropriate responses that take user emotions into consideration. However, conventional systems lack the ability to automatically generate responses that reflect user emotions, resulting in low response quality and reduced user satisfaction. In particular, in the security field, where emergency response is required, prompt and appropriate responses are essential, and such issues can have a serious impact.

[0338] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0339] In this invention, the server includes means for providing an interface for inputting inquiry content, means for transmitting the inquiry content to the server, means for analyzing the received inquiry content and extracting main keywords and intent, means for analyzing the user's emotions, means for generating a response message based on the analyzed keywords, intent, and emotion, means for displaying the generated response message, and means for providing an interface for the user to check and fine-tune the generated response message. This enables a quick and appropriate response that reflects the user's emotions, making it possible to achieve high user satisfaction, particularly in emergency responses in the security field.

[0340] The "interface for inputting inquiry content" is a device that provides an input form for the user to input the inquiry content in text format.

[0341] The "means for transmitting the inquiry content to the server" refers to a device or software that has the function of transmitting the inquiry content entered by the user to the server via the network.

[0342] "Means for analyzing the content of the received inquiry and extracting key keywords and intent" refers to an algorithm or system that analyzes the received text data and extracts important keywords and the user's intent from it.

[0343] A "means for analyzing user emotions" is an algorithm or system that analyzes user input and recognizes the underlying emotion (e.g., anger, confusion, fear, etc.).

[0344] The "means for generating a response sentence based on the analyzed keywords, intention, and emotion" refers to a device or software that automatically generates an appropriate response sentence based on the extracted keywords, intention, and the user's emotion.

[0345] The "means for displaying the generated response message" refers to a device or software that has a screen or display for visually displaying the generated response message to the user.

[0346] "Means for providing an interface for a user to check and fine-tune the generated response text" refers to a device or software that provides an input interface for a user to check the generated response text and edit or modify it as necessary.

[0347] The present invention relates to a system for generating prompt and appropriate answers to user inquiries. Specific embodiments of the system will be described below.

[0348] First, the user inputs the inquiry using the terminal. The interface provided by the terminal consists of a text box and a send button, and has the function of sending the inquiry input by the user to the server. The inquiry is temporarily saved by the server.

[0349] The server then receives the query and analyzes it using natural language processing (NLP) algorithms. During the analysis, key keywords and user intent are extracted from the query. NLP models such as the Transformers library are used for this analysis.

[0350] At the same time, the server uses an emotion recognition engine to analyze the user's emotions from the query content, for example, accurately recognizing emotions such as anger, confusion, and fear in the text. The emotion recognition algorithm used at this stage provides a deeper understanding based on the user's text.

[0351] The server then searches for relevant response templates from its internal database based on the analyzed keywords, intent, and emotions, and generates appropriate responses based on these templates. The generated responses are designed to be appropriate and reflect the user's emotional state.

[0352] The generated response is then sent to the terminal and displayed to the user, who can review the displayed response and make any necessary adjustments. After making the adjustments, the user can then send the final response.

[0353] The configuration of this system will be explained using a concrete example. When a user makes a query such as "A suspicious person has appeared in my house. I'm really scared. What should I do?", the server receives this text and uses an NLP algorithm to extract the keywords and intent of "suspicious person," "house," "scary," and "what should I do." At the same time, the emotion recognition engine recognizes the user's emotion as "fear."

[0354] Based on this, the server generates a response message saying, "We will respond quickly to make you feel safe. Could you please tell us more about the situation?" This response message is sent to the device and displayed to the user. The user can check the displayed response message and modify it if necessary, and it is then sent.

[0355] Examples of prompts include:

[0356] "There's a suspicious person in my house. I'm really scared. What should I do?"

[0357] In this way, it is possible to generate a quick and appropriate response that takes into account the user's emotions. This system is expected to improve emergency response, especially in the security field, and increase user satisfaction.

[0358] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0359] Step 1:

[0360] The user inputs the inquiry using the terminal.

[0361] Input: Text of inquiry (e.g., "A suspicious person has appeared in my house. I'm really scared. What should I do?")

[0362] Output: The status of preparation for sending the query from the terminal to the server

[0363] Specific operation: The user enters the inquiry content in text format into the input form on the terminal and presses the send button. The terminal temporarily stores this content and generates a signal to send it to the server.

[0364] Step 2:

[0365] The terminal sends the inquiry to the server.

[0366] Input: The inquiry content entered by the user and pressed the send button

[0367] Output: The query arrives at the server and is saved.

[0368] Specific operation: The terminal sends the query entered by the user to the server via the network. The server temporarily stores the received data and prepares it for subsequent analysis.

[0369] Step 3:

[0370] The server analyzes the query received using a natural language processing algorithm.

[0371] Input: Text data of saved inquiry details

[0372] Output: Extracted main keywords and user intent

[0373] How it works: The server uses the "Transformers" library to analyze the query text and extract key keywords (e.g., "suspicious person," "house," "scary") and the user's intent (e.g., "asking for help").

[0374] Step 4:

[0375] The server uses an emotion recognition engine to analyze the emotion of the query.

[0376] Input: Text data of inquiry content

[0377] Output: Perceived emotional state (e.g., "fear")

[0378] How it works: The server uses an emotion recognition algorithm to analyze the emotions in the user's input text. The emotion recognition engine determines emotions such as anger, confusion, or fear from the context and wording of the text.

[0379] Step 5:

[0380] The server generates a response based on the analyzed keywords, intent, and sentiment.

[0381] Input: Parsed keyword, intent, and sentiment data

[0382] Output: Generated response (e.g., "We will act quickly to make you feel safe. Can you tell us more about the situation?")

[0383] What it does: The server searches for an appropriate response template from its internal database and generates the text using a generative AI model based on the parsed data.

[0384] Step 6:

[0385] The server sends the generated response text to the terminal, which displays it to the user.

[0386] Input: Generated response text

[0387] Output: The response text displayed to the user

[0388] Specific operation: The server sends the generated response text to the terminal via the network, and the terminal displays the response text on the user's screen.

[0389] Step 7:

[0390] The user checks the displayed response text and makes minor adjustments as necessary.

[0391] Input: Displayed response text

[0392] Output: Final response text

[0393] Specific operation: The user checks the response displayed on the terminal, edits or corrects the text as necessary, and then presses the send button to finalize the response.

[0394] This series of processing steps enables the generation of a quick and appropriate response that reflects the user's feelings.

[0395] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0396] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0397] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0398] [Second embodiment]

[0399] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0400] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0401] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0402] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0403] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0404] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0405] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0406] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0407] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0408] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0409] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0410] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0411] The present invention relates to a call center support system that promptly proposes appropriate sample phrases in response to user inquiries. The system includes a program that analyzes the content of a user's inquiry and generates and displays appropriate response phrases.

[0412] System configuration and functions

[0413] User query input

[0414] The terminal provides an interface for the user to input the inquiry details. This interface is composed of a form that includes a text box for inputting the inquiry details and a send button. When the user inputs the inquiry details and presses the send button, the input details are sent to the server.

[0415] Sending and analyzing inquiries

[0416] The server receives the inquiry sent from the device and temporarily stores it. It then uses a natural language processing (NLP) algorithm to analyze the text of the inquiry. This analysis extracts key keywords and the user's intent. For example, keywords such as "bill," "not received," and "what should I do" are extracted.

[0417] Generating sample text based on inquiry content

[0418] The server searches an internal database for relevant response templates based on the extracted keywords and intent. The database contains multiple response templates for various inquiries. When a suitable template is found, the server generates a sample message based on it. For example, the message generated might be, "Dear customer, I understand you haven't received this month's invoice yet. I'm sorry. Could you please tell me your address and registered phone number for confirmation?"

[0419] Viewing and Using Sample Wording

[0420] The generated sample text is sent from the server to the terminal. The terminal displays this sample text to the user. The user can check the displayed sample text and make fine adjustments as necessary, or use it as is. The text that has been finalized as the final response text is sent by the user by pressing the send button.

[0421] Specific examples

[0422] A specific example will be explained below in which a user inquires, "I haven't received this month's invoice yet. What should I do?"

[0423] 1. User query input

[0424] The terminal displays a form for the user to input the inquiry.

[0425] The user enters the inquiry content in the text box and presses the send button.

[0426] 2. Sending and analyzing inquiries

[0427] The terminal transmits the input inquiry to the server.

[0428] The server analyzes the received query using a natural language processing algorithm.

[0429] As a result of the analysis, the keywords and intents extracted are "invoice," "not received," and "what should I do."

[0430] 3. Generating sample text based on inquiry content

[0431] The server searches for an appropriate template from a database based on the extracted keywords and intent.

[0432] The server generates a sample message: "Sir, I understand that you haven't received this month's invoice yet. I'm sorry. To confirm, could you please tell me your address and registered phone number?"

[0433] 4. Displaying and Using Sample Wording

[0434] The terminal displays the generated sample text to the user.

[0435] The user can fine-tune the displayed sample text as needed and then press the send button to send it as the final response text.

[0436] This system allows even new operators to respond quickly and appropriately, shortening user waiting times and improving work efficiency.

[0437] The processing flow will be explained below.

[0438] Step 1:

[0439] The terminal displays an interface (such as a text box and a send button) for the user to input the inquiry content.

[0440] Step 2:

[0441] The user enters the inquiry (e.g., "I haven't received this month's invoice yet. What should I do?") into the terminal interface and presses the send button.

[0442] Step 3:

[0443] The device sends the entered query to the server using a protocol such as an HTTP request or WebSocket.

[0444] Step 4:

[0445] The server temporarily stores the inquiry received from the terminal and invokes a natural language processing algorithm.

[0446] Step 5:

[0447] The server uses natural language processing algorithms to analyze the text of the inquiry, extracting key keywords (e.g., "bill," "not received," "what should I do") and the user's intent.

[0448] Step 6:

[0449] The server searches for relevant response templates from a database that stores past inquiries and response phrases based on the keywords and intent extracted from the analysis results.

[0450] Step 7:

[0451] The server selects the most suitable response template and generates a sample message based on that template, such as, "Dear customer, I understand that you have not yet received this month's invoice. We are sorry. To confirm, could you please tell us your address and registered phone number?"

[0452] Step 8:

[0453] The server transmits the generated sample text to the terminal.

[0454] Step 9:

[0455] The terminal displays the received sample text to the user, who can refer to the displayed sample text and make fine adjustments as necessary.

[0456] Step 10:

[0457] The user checks the sample text for fine tuning or as is, and presses the send button to confirm it as the final response text.

[0458] Example 1

[0459] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0460] Modern call center operations require quick and appropriate responses to user inquiries, but this is often difficult for new operators and inexperienced staff. There is also a need to reduce response times and improve operational efficiency. Conventional systems have difficulty effectively providing appropriate responses based on user inquiries.

[0461] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0462] In this invention, the server includes a means for analyzing the content of the inquiry using a natural language processing algorithm and extracting key keywords and intent, a means for generating related sample phrases from an internal database using a generative AI model based on the extracted keywords and intent, and a means for using a prompt sentence as an input sentence to the generative AI model, thereby enabling the generation and display of a prompt and appropriate response sentence.

[0463] A "terminal" is a device through which a user inputs their inquiry and communicates with the server, and generally refers to a PC or smartphone.

[0464] "Interface" refers to the screen and input form that users use to interact with the system via their terminal, and includes a text box for entering inquiry details and a send button.

[0465] A "server" is a computer system that receives, stores, analyzes inquiries sent by users, and generates appropriate sample text.

[0466] A "natural language processing algorithm" is a technology for analyzing text data, extracting elements, and understanding meaning, and typical examples use software libraries such as "NLTK" and "spaCy."

[0467] "Keywords" refer to the most important words and expressions extracted from the user's inquiry.

[0468] "Intent" refers to what the user is seeking through their inquiry, their purpose or desire.

[0469] The "internal database" is an information resource that stores response templates for various inquiries and is used to generate sample phrases.

[0470] A "generative AI model" is a model that uses artificial intelligence technology to automatically generate appropriate sample phrases, generating responses using specific prompt phrases as input.

[0471] A "prompt" is a text sentence that indicates specific conditions or questions to the generative AI model, and serves as the basis for generating a response.

[0472] The present invention relates to a call center operation support system that responds quickly and appropriately to user inquiries. This system analyzes the content of user inquiries, generates related sample phrases, and displays them to the user, thereby improving work efficiency.

[0473] Components and Functions

[0474] User query input

[0475] The user inputs the inquiry using a terminal (e.g., a PC or smartphone). An interface for inputting the inquiry is displayed on this terminal. The interface includes a text box and a send button. When the user inputs the inquiry and presses the send button, the inquiry is sent to the server.

[0476] Sending and analyzing inquiries

[0477] The terminal sends the inquiry content entered by the user to the server using an HTTP request.

[0478] The server temporarily stores the query received from the device and then analyzes it using a natural language processing (NLP) algorithm. This analysis process uses Python's "NLTK" or "spaCy." The server then extracts important keywords and the user's intent.

[0479] Generating sample phrases based on extracted keywords and intent

[0480] The server searches for relevant response templates from its internal database based on the extracted keywords and intent. Once a suitable template is found, the server uses a "generative AI model" to generate the optimal sample phrase. An example prompt phrase is "I haven't received this month's invoice yet, what should I do?" The generated sample phrase is "Sir, I understand you haven't received this month's invoice yet. I'm sorry. Could you please tell me your address and registered phone number for verification?"

[0481] Viewing and Using Sample Wording

[0482] The server sends the generated sample text to the terminal. The terminal uses HTML and JavaScript to display this sample text to the user. The user can check the displayed sample text and make fine adjustments as necessary. If they wish to use it as is, they can simply press the send button to confirm it as the final response text.

[0483] Specific examples

[0484] When a user inquires, "I haven't received this month's invoice yet, what should I do?", the system operates as follows:

[0485] 1. The user enters the inquiry details into the form on the device and presses the send button.

[0486] 2. The device sends the input to the server.

[0487] 3. The server analyzes the received content using a natural language processing algorithm and extracts the keywords "invoice," "not received," and "what should I do."

[0488] 4. The server searches the database for relevant templates and generates sample text using a generative AI model.

[0489] 5. The server sends the generated sample text to the terminal, which displays it to the user.

[0490] 6. The user checks and adjusts the sample text, then finalizes and sends the final response.

[0491] This system allows even new operators to respond quickly and appropriately, shortening user waiting times and improving work efficiency.

[0492] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0493] Step 1: User query input

[0494] The user inputs the inquiry into the terminal interface and presses the send button. This interface includes a text box for inputting the inquiry and a send button.

[0495] Input: Text data of the inquiry entered by the user

[0496] Output: Form data for sending inquiry content from the terminal to the server

[0497] Step 2: Submit your inquiry

[0498] The terminal sends the query entered by the user to the server, using an HTTP request to send the data.

[0499] Input: Text data of the inquiry entered by the user

[0500] Output: HTTP request data received by the server

[0501] Step 3: Receiving and temporarily saving your inquiry

[0502] The server receives the inquiry sent from the terminal and temporarily stores it.

[0503] Input: HTTP request data sent from the terminal

[0504] Output: Text data of the temporarily saved inquiry

[0505] Step 4: Analyzing the inquiry

[0506] The server analyzes the stored query using natural language processing (NLP) algorithms, such as NLTK and spaCy. As a result of the analysis, key keywords and user intent are extracted.

[0507] Input: Text data of the inquiry that was temporarily saved

[0508] Data processing: Analysis using natural language processing algorithms and keyword extraction

[0509] Output: Extracted main keywords and user intent

[0510] Step 5: Generate sample text

[0511] The server searches for relevant response templates from its internal database based on the extracted keywords and intent. Once a suitable template is found, the server uses a generative AI model to generate sample prompts. An example prompt is, "I haven't received my monthly bill yet. What should I do?"

[0512] Input: Extracted keywords and user intent

[0513] Data processing: Search for templates from an internal database and generate sample text using a generative AI model

[0514] Output: Generated sample text

[0515] Step 6: Submit and view sample text

[0516] The server sends the generated sample text to the terminal.

[0517] The device displays the received sample text to the user using HTML and JavaScript.

[0518] Input: Generated sample text

[0519] Output: Screen (interface) showing sample text

[0520] Step 7: Review and adjust user responses

[0521] The user checks the displayed sample text, makes minor adjustments as necessary, and presses the send button again to confirm the final response text after adjustments.

[0522] Input: Sample text displayed

[0523] Output: Final response sentence adjusted by the user

[0524] Step 8: Sending a Final Response

[0525] The terminal sends the adjusted final response to the server or other relevant departments.

[0526] Input: Adjusted final response

[0527] Output: The final response received by the server

[0528] (Application example 1)

[0529] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0530] In conventional call center operations, responses to user inquiries depended heavily on the experience and ability of the operator, and new operators were often slow to respond or unable to provide appropriate responses. This also created problems such as long wait times for users to receive appropriate responses. This resulted in a poor customer experience and a decline in operational efficiency.

[0531] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0532] In this invention, the server includes means for providing an interface for inputting inquiry content, means for transmitting the inquiry content, means for analyzing the received inquiry content and extracting main keywords and intent, means for generating related sample phrases based on the extracted keywords and intent, means for displaying the generated sample phrases, and means for the user to fine-tune and transmit a final response, thereby enabling prompt and appropriate response phrases to be presented.

[0533] The "means for providing an interface for inputting inquiry details" refers to a device or program that provides a format or screen for the user to input inquiry details.

[0534] The "means for transmitting the inquiry content to the server" refers to a device or program for transmitting the inquiry content input by the user to the server via the network.

[0535] "Means for analyzing the content of the received inquiry and extracting key keywords and intent" refers to a device or program that uses natural language processing technology to analyze the content of the inquiry sent to the server and identify important words and the user's intent from within it.

[0536] The "means for generating relevant sample phrases based on the extracted keywords and intent" refers to a device or program that generates appropriate response phrases based on the extracted keywords and the user's intent.

[0537] The "means for displaying the generated sample message" refers to a device or program that visually presents the generated response message to the user.

[0538] The "means for the user to fine-tune and send the final response" refers to a device or program that allows the user to fine-tune the sample wording provided and then send it as the final response.

[0539] The "means for searching a database for a response template" refers to a device or program that searches a database for a response template related to the content of the inquiry.

[0540] "Natural language processing algorithms" are a series of algorithms that allow computers to understand, generate, and analyze natural human language.

[0541] The system for implementing this invention includes a series of processes for allowing users to input inquiry content and provide quick and appropriate sample phrases. This system mainly consists of the following components:

[0542] 1. User query input

[0543] The user inputs the inquiry details through the smartphone application. The interface includes a text box and a send button, and when the user inputs the inquiry details and presses the send button, the details are sent to the server.

[0544] 2. Sending and analyzing inquiries

[0545] The query sent from the device is received by the server and temporarily stored. The server then uses natural language processing (NLP) algorithms to analyze the text of the query. The analysis extracts key keywords and the user's intent. NLP libraries such as spaCy are used in this process.

[0546] 3. Generating sample text based on inquiry content

[0547] The server searches its internal database for relevant response templates based on the extracted keywords and intent. Once a suitable template is found, a sample response is generated. This response template is randomly selected from a set of pre-defined templates.

[0548] 4. Displaying and Using Sample Wording

[0549] The generated sample text is sent back to the terminal and displayed to the user, who can then fine-tune the displayed sample text as needed and send the final response text.

[0550] This system allows even new operators to respond quickly and appropriately, shortening user waiting times and maintaining consistency in responses, improving operational efficiency.

[0551] Specific examples

[0552] Consider the case where a user types "I haven't received my bill this month yet, what should I do?" into a smartphone application. When the user presses the send button, the text is sent to the server. The server uses NLP to analyze the text and extract the keywords "bill," "not received," and "what should I do." Based on this, a relevant response template is searched for in the database and a sample response is generated: "Sir, I understand you haven't received your bill this month yet. I'm sorry. Could you please tell me your address and registered phone number for confirmation?" This response is displayed on the user's device, and the user can fine-tune it as needed and send it as the final response.

[0553] Example prompts to input to the generative AI model

[0554] Please enter the content of your inquiry. For example, if you enter "I haven't received this month's invoice yet, what's going on?", sample text that will promptly respond to this content will be displayed.

[0555] In this way, the system of the present invention simultaneously improves the efficiency of inquiry response work and user satisfaction.

[0556] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0557] Step 1:

[0558] The user inputs the inquiry using the smartphone interface.

[0559] Specific operation: The user enters an inquiry such as "I haven't received this month's bill yet. What should I do?" into the text box on their smartphone and presses the send button.

[0560] Input: The text of the inquiry.

[0561] Output: The data sent to the server based on the query entered.

[0562] Step 2:

[0563] The terminal sends the inquiry to the server.

[0564] Specific operation: The entered text data is sent to the server via the network, typically using an HTTP POST request.

[0565] Input: The query entered by the user.

[0566] Output: The server receives the query and begins processing it.

[0567] Step 3:

[0568] The server analyzes the received query and extracts the main keywords and the user's intent.

[0569] What it does: The server uses NLP algorithms (e.g., spaCy) to analyze the text and extract important keywords such as nouns and verbs, as well as the user's intent.

[0570] Input: Text data of the inquiry.

[0571] Output: Extracted keywords and user intent (e.g., "invoice," "not received," "what should I do?").

[0572] Step 4:

[0573] The server generates relevant sample text based on the extracted keywords and intent.

[0574] Specific operation: Based on the extracted keywords, the server searches for an appropriate response template from its internal database and uses that template to generate sample phrases. The generated sample phrases may be selected randomly.

[0575] Input: Extracted keywords and intent.

[0576] Output: Generated sample text (e.g., "Dear customer, I understand you haven't received this month's invoice yet. Could you please provide your address and registered phone number so we can verify this?").

[0577] Step 5:

[0578] The server sends the generated sample text to the terminal.

[0579] Specific operation: The generated sample text is sent back to the user's device via the network using an HTTP response.

[0580] Input: Generated sample text.

[0581] Output: A sample message that will be displayed on the user's device.

[0582] Step 6:

[0583] The user reviews the sample wording, makes any necessary adjustments, and submits the final response.

[0584] Specific operation: The user checks the displayed sample text, fine-tunes it using a text editor if necessary, and presses the send button to finalize the response text.

[0585] Input: Sample text and user tweaks.

[0586] Output: The data that will be sent as the final response.

[0587] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0588] The present invention relates to a call center support system that promptly proposes appropriate sample phrases in response to user inquiries. This system analyzes the content of the user's inquiry, generates and displays appropriate response phrases, and also includes a means for recognizing the user's emotions and reflecting them in the response template.

[0589] System configuration and functions

[0590] User query input

[0591] The terminal provides an interface for the user to input the inquiry details. This interface is composed of a form that includes a text box for inputting the inquiry details and a send button. When the user inputs the inquiry details and presses the send button, the input details are sent to the server.

[0592] Sending and analyzing inquiries

[0593] The server receives and temporarily stores the query sent from the device, then uses natural language processing (NLP) algorithms to analyze the text of the query, extracting key keywords and the user's intent.

[0594] Emotion recognition by emotion engine

[0595] The server uses an emotion engine to analyze the user's emotions from the text of the inquiry, recognizing, for example, emotional states such as anger, confusion, and sadness, thereby gaining a deeper understanding of the context and urgency of the inquiry.

[0596] Generating sample text based on inquiry content

[0597] The server searches for relevant response templates from its internal database based on the analyzed keywords and intent, as well as the results of the emotion engine. The database contains multiple response templates corresponding to various inquiry contents. For example, if the emotion is "anger," a more polite template that includes an apology is selected. The server generates sample text based on these templates.

[0598] Viewing and Using Sample Wording

[0599] The generated sample text is sent from the server to the terminal. The terminal displays this sample text to the user. The user can check the displayed sample text and make fine adjustments as necessary, or use it as is. The text that has been finalized as the final response text is sent by the user by pressing the send button.

[0600] Specific examples

[0601] A specific example will be described in which a user makes an inquiry such as, "I haven't received this month's bill yet. What should I do? I'm really in trouble."

[0602] 1. User query input

[0603] The terminal displays a form for the user to input the inquiry.

[0604] The user enters the inquiry content in the text box and presses the send button.

[0605] 2. Sending and analyzing inquiries

[0606] The terminal transmits the input inquiry to the server.

[0607] The server analyzes the received query using a natural language processing algorithm.

[0608] As a result of the analysis, the keywords and intents extracted are "invoice," "not received," and "what should I do."

[0609] 3. Emotion Recognition by Emotion Engine

[0610] The server analyzes the user's emotions from the text of the inquiry. For example, the emotion "confused" is recognized.

[0611] 4. Generating sample text based on inquiry content

[0612] The server searches for an appropriate template from the database based on the extracted keywords, intent, and the results of the emotion engine.

[0613] The server generates a sample message that reads, "Dear customer, we are very sorry for the inconvenience. We understand that you have not yet received your monthly bill. Could you please provide us with your address and registered phone number so we can verify this?"

[0614] 5. Viewing and Using Sample Wording

[0615] The terminal displays the generated sample text to the user.

[0616] The user can fine-tune the displayed sample text as needed and then press the send button to send it as the final response text.

[0617] This system enables appropriate responses that take into account the user's emotions, allowing even new operators to provide high-quality service.

[0618] The processing flow will be explained below.

[0619] Step 1:

[0620] The terminal displays an interface (such as a text box and a send button) for the user to input the inquiry content.

[0621] Step 2:

[0622] The user enters the inquiry into the terminal interface (e.g., "I haven't received this month's invoice yet. What should I do? I'm really worried.") and presses the send button.

[0623] Step 3:

[0624] The device sends the entered query to the server using a protocol such as an HTTP request or WebSocket.

[0625] Step 4:

[0626] The server temporarily stores the inquiry received from the terminal and invokes a natural language processing algorithm.

[0627] Step 5:

[0628] The server uses natural language processing algorithms to analyze the text of the inquiry, extracting key keywords (e.g., "bill," "not received," "what should I do," "I'm having trouble") and the user's intent.

[0629] Step 6:

[0630] The server uses an emotion engine to analyze the user's emotion from the text of the inquiry. For example, the emotion "confusion" is recognized from the part "I'm in trouble."

[0631] Step 7:

[0632] The server searches a database for relevant response templates based on the analysis results (keywords and emotions). The database contains multiple response templates corresponding to various inquiry contents. In particular, considering that the emotion is "confusion," the server selects a template that is more polite and shows empathy.

[0633] Step 8:

[0634] The server generates a sample message based on the most suitable template, such as "Dear customer, we apologize for the inconvenience. We understand that you have not yet received this month's invoice. To confirm, could you please provide us with your address and registered phone number?"

[0635] Step 9:

[0636] The server transmits the generated sample text to the terminal.

[0637] Step 10:

[0638] The terminal displays the received sample text to the user, who can then check the displayed sample text and make fine adjustments as necessary.

[0639] Step 11:

[0640] The user checks the sample text for fine tuning or leaves it as is, and then presses the send button to send it as the final response text.

[0641] Example 2

[0642] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0643] In conventional call center operations, providing prompt and appropriate responses to user inquiries has been a challenge. It is particularly difficult for new operators to generate appropriate responses to inquiries. Furthermore, there is a lack of means to automatically generate responses that take the user's emotions into consideration, which results in inconsistent response quality and lower customer satisfaction.

[0644] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for analyzing the content of the inquiry and extracting main keywords and intention, means for using an emotion engine for analyzing the user's emotions, and means for searching a database for a response template based on the extracted keywords, intention, and emotion analysis. This makes it possible to quickly generate and display appropriate sample phrases, allowing even new operators to provide high-quality responses.

[0645] The "interface for inputting inquiry details" is an interface that allows a user to input inquiry details via a text box, a send button, etc., and send the details to the server.

[0646] The "means for sending the inquiry content to the server" is a function for sending the inquiry content entered by the user to the server using a protocol such as HTTP or HTTPS.

[0647] "Means of analyzing the content of the received inquiry and extracting key keywords and intent" refers to the function of analyzing the text data received by the server using a natural language processing algorithm to identify and extract important keywords and the user's intent.

[0648] The "means for generating relevant sample phrases" is a function that generates appropriate response phrases from templates based on the analyzed keywords and intent.

[0649] The "means for using an emotion engine to analyze user emotions" is a function that uses an engine to analyze emotions (e.g., anger, confusion, sadness, etc.) from the user's inquiry text and quantify or categorize them.

[0650] "Means for searching for response templates from a database" refers to a function that searches for and retrieves appropriate response templates stored in a database based on the results of extracted keywords, intent, and sentiment analysis.

[0651] The "means for displaying the generated sample text" is a function for displaying the sample text sent from the server on the interface of the terminal, and visually presenting it to the user.

[0652] The present invention relates to a call center support system that promptly proposes appropriate sample phrases in response to user inquiries. This system analyzes the content of the user's inquiry, generates and displays appropriate response phrases, and also includes a means for recognizing the user's emotions and reflecting them in the response template.

[0653] User query input

[0654] The terminal provides an interface for the user to input the inquiry details. The interface is constructed using HTML and JavaScript, and provides a form including a text box and a submit button. The user enters the inquiry details in the text box and presses the submit button, which sends the input details from the terminal to the server.

[0655] Sending and analyzing inquiries

[0656] The device sends the entered query to the server using HTTP or HTTPS. The server stores the received query in a database or temporary memory. Storage technologies include MySQL and Redis. The server then analyzes the query using natural language processing (NLP) algorithms such as Python's NLTK or SpaCy to extract key keywords and the user's intent.

[0657] Emotion recognition by emotion engine

[0658] The server uses an emotion engine, such as IBM Watson Tone Analyzer or Microsoft Text Analytics, to analyze the user's emotion from the text of the query. Using these tools, the server recognizes the emotion in the text (e.g., anger, confusion, sadness) and quantifies the emotional state.

[0659] Generating sample text based on inquiry content

[0660] The server searches for relevant response templates from an internal database based on the analyzed keywords, intent, and emotion engine results. The database contains multiple response templates corresponding to various inquiry contents. Using a database query system, it is possible to quickly search for the optimal template according to the user's emotion and inquiry content. Based on the searched template, the server generates sample text using a template engine such as Jinja2 or Handlebars.

[0661] Viewing and Using Sample Wording

[0662] The generated sample text is sent from the server to the device as an HTTP response. The device displays this sample text to the user using HTML and JavaScript. The user can check the displayed sample text and make fine adjustments as needed, or use it as is. Once the text is finalized, the user presses the send button to send the final response text.

[0663] Examples of concrete examples and prompts

[0664] For example, a specific case will be described in which a user makes an inquiry such as, "I haven't received this month's bill yet. What should I do? I'm really in trouble."

[0665] The user enters "I haven't received this month's bill yet. What should I do? I'm really worried." in the text box and presses the submit button.

[0666] The terminal sends the query to the server, which then analyzes the received query using a natural language processing algorithm.

[0667] As a result of the analysis, the keywords "bill," "not received," and "what should I do" as well as the user's emotion of "confusion" are extracted.

[0668] Using this information, the server searches a database for an appropriate response template and generates a sample message like this: "Dear customer, we apologize for the inconvenience. We understand that you have not yet received your monthly bill. Could you please provide us with your address and registered phone number so we can verify this?"

[0669] The generated sample text is sent to the terminal, which displays it to the user. The user can check the displayed text, make any necessary adjustments, and then press the send button to send the finalized response text.

[0670] An example of a prompt is as follows:

[0671] "User's question: I haven't received my invoice for this month yet, what should I do? I'm really worried.

[0672] Analysis results: Keywords: bill, not received, what to do. Emotions: confusion.

[0673] Please generate a sample response for this."

[0674] This series of processes makes it possible to provide a quick and appropriate response that takes into account the user's feelings, improving the efficiency and quality of call center operations.

[0675] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0676] Step 1: User query input

[0677] The terminal displays an input interface for the user. This interface is a form with a text box and a submit button. The screen is designed to be simple so that the user can easily enter their inquiry.

[0678] User input: The user enters the inquiry "I haven't received this month's invoice yet, what should I do?" into the text box and presses the send button. The input format is text-based.

[0679] Input and Output: The input is the query entered by the user, and the output is the query data ready to be sent.

[0680] Step 2: Submit your inquiry

[0681] The terminal sends the entered query to the server using the HTTP or HTTPS protocol, with the data being sent in JSON format.

[0682] Input and output: The input is the query entered by the user, and the output is a notification of completion of transmission to the server.

[0683] Step 3: Receiving and storing your inquiry

[0684] The server receives the inquiry sent from the terminal and temporarily stores it in a database (e.g., MySQL or Redis).

[0685] Input and output: The input is the query content sent from the terminal, and the output is the query data stored in the database.

[0686] Specific operation: The server receives the HTTP request and saves the query in the database.

[0687] Step 4: Text Analysis

[0688] The server analyzes the received queries using natural language processing (NLP) algorithms, specifically Python's NLTK or SpaCy.

[0689] Input and Output: The input is the stored query content, and the output is a set of parsed keywords and intents.

[0690] Specific operation: A program is run to tokenize the query and extract key keywords and user intent.

[0691] Step 5: Sentiment Analysis

[0692] The server uses an emotion engine to analyze the user's emotions from the text of the inquiry, specifically using IBM Watson Tone Analyzer and Microsoft Text Analytics.

[0693] Input and Output: The input is the text of the query, and the output is the analyzed emotion data (e.g., anger, confusion, sadness, etc.).

[0694] What it does: The emotion engine analyzes the text and quantifies or categorizes the user's emotion.

[0695] Step 6: Find the response template

[0696] The server searches a database for an appropriate response template based on the extracted keywords and the results of the intent and sentiment analysis.

[0697] Input and Output: The input is the extracted keywords, intent, and emotion data, and the output is the response template.

[0698] What it does: Runs a database query to find the best response template.

[0699] Step 7: Generate sample text

[0700] The server generates sample text based on the retrieved response template using a template engine (e.g., Jinja2 or Handlebars).

[0701] Input and Output: The input is the response template and the parsed results, and the output is the generated sample text.

[0702] Specific behavior: Dynamically generate sample text using a template engine.

[0703] Step 8: Submit and view sample text

[0704] The server sends the generated sample text to the terminal in the form of an HTTP response.

[0705] The device displays the received sample text to the user using HTML and JavaScript.

[0706] Input and Output: The input is the generated sample text, and the output is the display to the user.

[0707] Specific behavior: The device displays sample text in the text area for the user to review and adjust.

[0708] Step 9: User confirmation, adjustments and final submission

[0709] The user can check the sample text displayed and make any necessary adjustments. Once the adjustments are complete, the user presses the send button to send the final response text.

[0710] Input and Output: The input is the displayed sample text, the user's adjustments, and the output is the final response text.

[0711] Specific operation: The user checks and adjusts the sample text, and then sends the final response text to the server.

[0712] (Application example 2)

[0713] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0714] Modern inquiry response systems are required to provide prompt and appropriate responses that take user emotions into consideration. However, conventional systems lack the ability to automatically generate responses that reflect user emotions, resulting in low response quality and reduced user satisfaction. In particular, in the security field, where emergency response is required, prompt and appropriate responses are essential, and such issues can have a serious impact.

[0715] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0716] In this invention, the server includes means for providing an interface for inputting inquiry content, means for transmitting the inquiry content to the server, means for analyzing the received inquiry content and extracting main keywords and intent, means for analyzing the user's emotions, means for generating a response message based on the analyzed keywords, intent, and emotion, means for displaying the generated response message, and means for providing an interface for the user to check and fine-tune the generated response message. This enables a quick and appropriate response that reflects the user's emotions, making it possible to achieve high user satisfaction, particularly in emergency responses in the security field.

[0717] The "interface for inputting inquiry content" is a device that provides an input form for the user to input the inquiry content in text format.

[0718] The "means for transmitting the inquiry content to the server" refers to a device or software that has the function of transmitting the inquiry content entered by the user to the server via the network.

[0719] "Means for analyzing the content of the received inquiry and extracting key keywords and intent" refers to an algorithm or system that analyzes the received text data and extracts important keywords and the user's intent from it.

[0720] A "means for analyzing user emotions" is an algorithm or system that analyzes user input and recognizes the underlying emotion (e.g., anger, confusion, fear, etc.).

[0721] The "means for generating a response sentence based on the analyzed keywords, intention, and emotion" refers to a device or software that automatically generates an appropriate response sentence based on the extracted keywords, intention, and the user's emotion.

[0722] The "means for displaying the generated response message" refers to a device or software that has a screen or display for visually displaying the generated response message to the user.

[0723] "Means for providing an interface for a user to check and fine-tune the generated response text" refers to a device or software that provides an input interface for a user to check the generated response text and edit or modify it as necessary.

[0724] The present invention relates to a system for generating prompt and appropriate answers to user inquiries. Specific embodiments of the system will be described below.

[0725] First, the user inputs the inquiry using the terminal. The interface provided by the terminal consists of a text box and a send button, and has the function of sending the inquiry input by the user to the server. The inquiry is temporarily saved by the server.

[0726] The server then receives the query and analyzes it using natural language processing (NLP) algorithms. During the analysis, key keywords and user intent are extracted from the query. NLP models such as the Transformers library are used for this analysis.

[0727] At the same time, the server uses an emotion recognition engine to analyze the user's emotions from the query content, for example, accurately recognizing emotions such as anger, confusion, and fear in the text. The emotion recognition algorithm used at this stage provides a deeper understanding based on the user's text.

[0728] The server then searches for relevant response templates from its internal database based on the analyzed keywords, intent, and emotions, and generates appropriate responses based on these templates. The generated responses are designed to be appropriate and reflect the user's emotional state.

[0729] The generated response is then sent to the terminal and displayed to the user, who can review the displayed response and make any necessary adjustments. After making the adjustments, the user can then send the final response.

[0730] The configuration of this system will be explained using a concrete example. When a user makes a query such as "A suspicious person has appeared in my house. I'm really scared. What should I do?", the server receives this text and uses an NLP algorithm to extract the keywords and intent of "suspicious person," "house," "scary," and "what should I do." At the same time, the emotion recognition engine recognizes the user's emotion as "fear."

[0731] Based on this, the server generates a response message saying, "We will respond quickly to make you feel safe. Could you please tell us more about the situation?" This response message is sent to the device and displayed to the user. The user can check the displayed response message and modify it if necessary, and it is then sent.

[0732] Examples of prompts include:

[0733] "There's a suspicious person in my house. I'm really scared. What should I do?"

[0734] In this way, it is possible to generate a quick and appropriate response that takes into account the user's emotions. This system is expected to improve emergency response, especially in the security field, and increase user satisfaction.

[0735] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0736] Step 1:

[0737] The user inputs the inquiry using the terminal.

[0738] Input: Text of inquiry (e.g., "A suspicious person has appeared in my house. I'm really scared. What should I do?")

[0739] Output: The status of preparation for sending the query from the terminal to the server

[0740] Specific operation: The user enters the inquiry content in text format into the input form on the terminal and presses the send button. The terminal temporarily stores this content and generates a signal to send it to the server.

[0741] Step 2:

[0742] The terminal sends the inquiry to the server.

[0743] Input: The inquiry content entered by the user and pressed the send button

[0744] Output: The query arrives at the server and is saved.

[0745] Specific operation: The terminal sends the query entered by the user to the server via the network. The server temporarily stores the received data and prepares it for subsequent analysis.

[0746] Step 3:

[0747] The server analyzes the query received using a natural language processing algorithm.

[0748] Input: Text data of saved inquiry details

[0749] Output: Extracted main keywords and user intent

[0750] How it works: The server uses the "Transformers" library to analyze the query text and extract key keywords (e.g., "suspicious person," "house," "scary") and the user's intent (e.g., "asking for help").

[0751] Step 4:

[0752] The server uses an emotion recognition engine to analyze the emotion of the query.

[0753] Input: Text data of inquiry content

[0754] Output: Perceived emotional state (e.g., "fear")

[0755] How it works: The server uses an emotion recognition algorithm to analyze the emotions in the user's input text. The emotion recognition engine determines emotions such as anger, confusion, or fear from the context and wording of the text.

[0756] Step 5:

[0757] The server generates a response based on the analyzed keywords, intent, and sentiment.

[0758] Input: Parsed keyword, intent, and sentiment data

[0759] Output: Generated response (e.g., "We will act quickly to make you feel safe. Can you tell us more about the situation?")

[0760] What it does: The server searches for an appropriate response template from its internal database and generates the text using a generative AI model based on the parsed data.

[0761] Step 6:

[0762] The server sends the generated response text to the terminal, which displays it to the user.

[0763] Input: Generated response text

[0764] Output: The response text displayed to the user

[0765] Specific operation: The server sends the generated response text to the terminal via the network, and the terminal displays the response text on the user's screen.

[0766] Step 7:

[0767] The user checks the displayed response text and makes minor adjustments as necessary.

[0768] Input: Displayed response text

[0769] Output: Final response text

[0770] Specific operation: The user checks the response displayed on the terminal, edits or corrects the text as necessary, and then presses the send button to finalize the response.

[0771] This series of processing steps enables the generation of a quick and appropriate response that reflects the user's feelings.

[0772] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0773] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0774] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0775] [Third embodiment]

[0776] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0777] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0778] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0779] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0780] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0781] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0782] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0783] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0784] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0785] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0786] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0787] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0788] The present invention relates to a call center support system that promptly proposes appropriate sample phrases in response to user inquiries. The system includes a program that analyzes the content of a user's inquiry and generates and displays appropriate response phrases.

[0789] System configuration and functions

[0790] User query input

[0791] The terminal provides an interface for the user to input the inquiry details. This interface is composed of a form that includes a text box for inputting the inquiry details and a send button. When the user inputs the inquiry details and presses the send button, the input details are sent to the server.

[0792] Sending and analyzing inquiries

[0793] The server receives the inquiry sent from the device and temporarily stores it. It then uses a natural language processing (NLP) algorithm to analyze the text of the inquiry. This analysis extracts key keywords and the user's intent. For example, keywords such as "bill," "not received," and "what should I do" are extracted.

[0794] Generating sample text based on inquiry content

[0795] The server searches an internal database for relevant response templates based on the extracted keywords and intent. The database contains multiple response templates for various inquiries. When a suitable template is found, the server generates a sample message based on it. For example, the message generated might be, "Dear customer, I understand you haven't received this month's invoice yet. I'm sorry. Could you please tell me your address and registered phone number for confirmation?"

[0796] Viewing and Using Sample Wording

[0797] The generated sample text is sent from the server to the terminal. The terminal displays this sample text to the user. The user can check the displayed sample text and make fine adjustments as necessary, or use it as is. The text that has been finalized as the final response text is sent by the user by pressing the send button.

[0798] Specific examples

[0799] A specific example will be explained below in which a user inquires, "I haven't received this month's invoice yet. What should I do?"

[0800] 1. User query input

[0801] The terminal displays a form for the user to input the inquiry.

[0802] The user enters the inquiry content in the text box and presses the send button.

[0803] 2. Sending and analyzing inquiries

[0804] The terminal transmits the input inquiry to the server.

[0805] The server analyzes the received query using a natural language processing algorithm.

[0806] As a result of the analysis, the keywords and intents extracted are "invoice," "not received," and "what should I do."

[0807] 3. Generating sample text based on inquiry content

[0808] The server searches for an appropriate template from a database based on the extracted keywords and intent.

[0809] The server generates a sample message: "Sir, I understand that you haven't received this month's invoice yet. I'm sorry. To confirm, could you please tell me your address and registered phone number?"

[0810] 4. Displaying and Using Sample Wording

[0811] The terminal displays the generated sample text to the user.

[0812] The user can fine-tune the displayed sample text as needed and then press the send button to send it as the final response text.

[0813] This system allows even new operators to respond quickly and appropriately, shortening user waiting times and improving work efficiency.

[0814] The processing flow will be explained below.

[0815] Step 1:

[0816] The terminal displays an interface (such as a text box and a send button) for the user to input the inquiry content.

[0817] Step 2:

[0818] The user enters the inquiry (e.g., "I haven't received this month's invoice yet. What should I do?") into the terminal interface and presses the send button.

[0819] Step 3:

[0820] The device sends the entered query to the server using a protocol such as an HTTP request or WebSocket.

[0821] Step 4:

[0822] The server temporarily stores the inquiry received from the terminal and invokes a natural language processing algorithm.

[0823] Step 5:

[0824] The server uses natural language processing algorithms to analyze the text of the inquiry, extracting key keywords (e.g., "bill," "not received," "what should I do") and the user's intent.

[0825] Step 6:

[0826] The server searches for relevant response templates from a database that stores past inquiries and response phrases based on the keywords and intent extracted from the analysis results.

[0827] Step 7:

[0828] The server selects the most suitable response template and generates a sample message based on that template, such as, "Dear customer, I understand that you have not yet received this month's invoice. We are sorry. To confirm, could you please tell us your address and registered phone number?"

[0829] Step 8:

[0830] The server transmits the generated sample text to the terminal.

[0831] Step 9:

[0832] The terminal displays the received sample text to the user, who can refer to the displayed sample text and make fine adjustments as necessary.

[0833] Step 10:

[0834] The user checks the sample text for fine tuning or as is, and presses the send button to confirm it as the final response text.

[0835] Example 1

[0836] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0837] Modern call center operations require quick and appropriate responses to user inquiries, but this is often difficult for new operators and inexperienced staff. There is also a need to reduce response times and improve operational efficiency. Conventional systems have difficulty effectively providing appropriate responses based on user inquiries.

[0838] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0839] In this invention, the server includes a means for analyzing the content of the inquiry using a natural language processing algorithm and extracting key keywords and intent, a means for generating related sample phrases from an internal database using a generative AI model based on the extracted keywords and intent, and a means for using a prompt sentence as an input sentence to the generative AI model, thereby enabling the generation and display of a prompt and appropriate response sentence.

[0840] A "terminal" is a device through which a user inputs their inquiry and communicates with the server, and generally refers to a PC or smartphone.

[0841] "Interface" refers to the screen and input form that users use to interact with the system via their terminal, and includes a text box for entering inquiry details and a send button.

[0842] A "server" is a computer system that receives, stores, analyzes inquiries sent by users, and generates appropriate sample text.

[0843] A "natural language processing algorithm" is a technology for analyzing text data, extracting elements, and understanding meaning, and typical examples use software libraries such as "NLTK" and "spaCy."

[0844] "Keywords" refer to the most important words and expressions extracted from the user's inquiry.

[0845] "Intent" refers to what the user is seeking through their inquiry, their purpose or desire.

[0846] The "internal database" is an information resource that stores response templates for various inquiries and is used to generate sample phrases.

[0847] A "generative AI model" is a model that uses artificial intelligence technology to automatically generate appropriate sample phrases, generating responses using specific prompt phrases as input.

[0848] A "prompt" is a text sentence that indicates specific conditions or questions to the generative AI model, and serves as the basis for generating a response.

[0849] The present invention relates to a call center operation support system that responds quickly and appropriately to user inquiries. This system analyzes the content of user inquiries, generates related sample phrases, and displays them to the user, thereby improving work efficiency.

[0850] Components and Functions

[0851] User query input

[0852] The user inputs the inquiry using a terminal (e.g., a PC or smartphone). An interface for inputting the inquiry is displayed on this terminal. The interface includes a text box and a send button. When the user inputs the inquiry and presses the send button, the inquiry is sent to the server.

[0853] Sending and analyzing inquiries

[0854] The terminal sends the inquiry content entered by the user to the server using an HTTP request.

[0855] The server temporarily stores the query received from the device and then analyzes it using a natural language processing (NLP) algorithm. This analysis process uses Python's "NLTK" or "spaCy." The server then extracts important keywords and the user's intent.

[0856] Generating sample phrases based on extracted keywords and intent

[0857] The server searches for relevant response templates from its internal database based on the extracted keywords and intent. Once a suitable template is found, the server uses a "generative AI model" to generate the optimal sample phrase. An example prompt phrase is "I haven't received this month's invoice yet, what should I do?" The generated sample phrase is "Sir, I understand you haven't received this month's invoice yet. I'm sorry. Could you please tell me your address and registered phone number for verification?"

[0858] Viewing and Using Sample Wording

[0859] The server sends the generated sample text to the terminal. The terminal uses HTML and JavaScript to display this sample text to the user. The user can check the displayed sample text and make fine adjustments as necessary. If they wish to use it as is, they can simply press the send button to confirm it as the final response text.

[0860] Specific examples

[0861] When a user inquires, "I haven't received this month's invoice yet, what should I do?", the system operates as follows:

[0862] 1. The user enters the inquiry details into the form on the device and presses the send button.

[0863] 2. The device sends the input to the server.

[0864] 3. The server analyzes the received content using a natural language processing algorithm and extracts the keywords "invoice," "not received," and "what should I do."

[0865] 4. The server searches the database for relevant templates and generates sample text using a generative AI model.

[0866] 5. The server sends the generated sample text to the terminal, which displays it to the user.

[0867] 6. The user checks and adjusts the sample text, then finalizes and sends the final response.

[0868] This system allows even new operators to respond quickly and appropriately, shortening user waiting times and improving work efficiency.

[0869] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0870] Step 1: User query input

[0871] The user inputs the inquiry into the terminal interface and presses the send button. This interface includes a text box for inputting the inquiry and a send button.

[0872] Input: Text data of the inquiry entered by the user

[0873] Output: Form data for sending inquiry content from the terminal to the server

[0874] Step 2: Submit your inquiry

[0875] The terminal sends the query entered by the user to the server, using an HTTP request to send the data.

[0876] Input: Text data of the inquiry entered by the user

[0877] Output: HTTP request data received by the server

[0878] Step 3: Receiving and temporarily saving your inquiry

[0879] The server receives the inquiry sent from the terminal and temporarily stores it.

[0880] Input: HTTP request data sent from the terminal

[0881] Output: Text data of the temporarily saved inquiry

[0882] Step 4: Analyzing the inquiry

[0883] The server analyzes the stored query using natural language processing (NLP) algorithms, such as NLTK and spaCy. As a result of the analysis, key keywords and user intent are extracted.

[0884] Input: Text data of the inquiry that was temporarily saved

[0885] Data processing: Analysis using natural language processing algorithms and keyword extraction

[0886] Output: Extracted main keywords and user intent

[0887] Step 5: Generate sample text

[0888] The server searches for relevant response templates from its internal database based on the extracted keywords and intent. Once a suitable template is found, the server uses a generative AI model to generate sample prompts. An example prompt is, "I haven't received my monthly bill yet. What should I do?"

[0889] Input: Extracted keywords and user intent

[0890] Data processing: Search for templates from an internal database and generate sample text using a generative AI model

[0891] Output: Generated sample text

[0892] Step 6: Submit and view sample text

[0893] The server sends the generated sample text to the terminal.

[0894] The device displays the received sample text to the user using HTML and JavaScript.

[0895] Input: Generated sample text

[0896] Output: Screen (interface) showing sample text

[0897] Step 7: Review and adjust user responses

[0898] The user checks the displayed sample text, makes minor adjustments as necessary, and presses the send button again to confirm the final response text after adjustments.

[0899] Input: Sample text displayed

[0900] Output: Final response sentence adjusted by the user

[0901] Step 8: Sending a Final Response

[0902] The terminal sends the adjusted final response to the server or other relevant departments.

[0903] Input: Adjusted final response

[0904] Output: The final response received by the server

[0905] (Application example 1)

[0906] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0907] In conventional call center operations, responses to user inquiries depended heavily on the experience and ability of the operator, and new operators were often slow to respond or unable to provide appropriate responses. This also created problems such as long wait times for users to receive appropriate responses. This resulted in a poor customer experience and a decline in operational efficiency.

[0908] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0909] In this invention, the server includes means for providing an interface for inputting inquiry content, means for transmitting the inquiry content, means for analyzing the received inquiry content and extracting main keywords and intent, means for generating related sample phrases based on the extracted keywords and intent, means for displaying the generated sample phrases, and means for the user to fine-tune and transmit a final response, thereby enabling prompt and appropriate response phrases to be presented.

[0910] The "means for providing an interface for inputting inquiry details" refers to a device or program that provides a format or screen for the user to input inquiry details.

[0911] The "means for transmitting the inquiry content to the server" refers to a device or program for transmitting the inquiry content input by the user to the server via the network.

[0912] "Means for analyzing the content of the received inquiry and extracting key keywords and intent" refers to a device or program that uses natural language processing technology to analyze the content of the inquiry sent to the server and identify important words and the user's intent from within it.

[0913] The "means for generating relevant sample phrases based on the extracted keywords and intent" refers to a device or program that generates appropriate response phrases based on the extracted keywords and the user's intent.

[0914] The "means for displaying the generated sample message" refers to a device or program that visually presents the generated response message to the user.

[0915] The "means for the user to fine-tune and send the final response" refers to a device or program that allows the user to fine-tune the sample wording provided and then send it as the final response.

[0916] The "means for searching a database for a response template" refers to a device or program that searches a database for a response template related to the content of the inquiry.

[0917] "Natural language processing algorithms" are a series of algorithms that allow computers to understand, generate, and analyze natural human language.

[0918] The system for implementing this invention includes a series of processes for allowing users to input inquiry content and provide quick and appropriate sample phrases. This system mainly consists of the following components:

[0919] 1. User query input

[0920] The user inputs the inquiry details through the smartphone application. The interface includes a text box and a send button, and when the user inputs the inquiry details and presses the send button, the details are sent to the server.

[0921] 2. Sending and analyzing inquiries

[0922] The query sent from the device is received by the server and temporarily stored. The server then uses natural language processing (NLP) algorithms to analyze the text of the query. The analysis extracts key keywords and the user's intent. NLP libraries such as spaCy are used in this process.

[0923] 3. Generating sample text based on inquiry content

[0924] The server searches its internal database for relevant response templates based on the extracted keywords and intent. Once a suitable template is found, a sample response is generated. This response template is randomly selected from a set of pre-defined templates.

[0925] 4. Displaying and Using Sample Wording

[0926] The generated sample text is sent back to the terminal and displayed to the user, who can then fine-tune the displayed sample text as needed and send the final response text.

[0927] This system allows even new operators to respond quickly and appropriately, shortening user waiting times and maintaining consistency in responses, improving operational efficiency.

[0928] Specific examples

[0929] Consider the case where a user types "I haven't received my bill this month yet, what should I do?" into a smartphone application. When the user presses the send button, the text is sent to the server. The server uses NLP to analyze the text and extract the keywords "bill," "not received," and "what should I do." Based on this, a relevant response template is searched for in the database and a sample response is generated: "Sir, I understand you haven't received your bill this month yet. I'm sorry. Could you please tell me your address and registered phone number for confirmation?" This response is displayed on the user's device, and the user can fine-tune it as needed and send it as the final response.

[0930] Example prompts to input to the generative AI model

[0931] Please enter the content of your inquiry. For example, if you enter "I haven't received this month's invoice yet, what's going on?", sample text that will promptly respond to this content will be displayed.

[0932] In this way, the system of the present invention simultaneously improves the efficiency of inquiry response work and user satisfaction.

[0933] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0934] Step 1:

[0935] The user inputs the inquiry using the smartphone interface.

[0936] Specific operation: The user enters an inquiry such as "I haven't received this month's bill yet. What should I do?" into the text box on their smartphone and presses the send button.

[0937] Input: The text of the inquiry.

[0938] Output: The data sent to the server based on the query entered.

[0939] Step 2:

[0940] The terminal sends the inquiry to the server.

[0941] Specific operation: The entered text data is sent to the server via the network, typically using an HTTP POST request.

[0942] Input: The query entered by the user.

[0943] Output: The server receives the query and begins processing it.

[0944] Step 3:

[0945] The server analyzes the received query and extracts the main keywords and the user's intent.

[0946] What it does: The server uses NLP algorithms (e.g., spaCy) to analyze the text and extract important keywords such as nouns and verbs, as well as the user's intent.

[0947] Input: Text data of the inquiry.

[0948] Output: Extracted keywords and user intent (e.g., "invoice," "not received," "what should I do?").

[0949] Step 4:

[0950] The server generates relevant sample text based on the extracted keywords and intent.

[0951] Specific operation: Based on the extracted keywords, the server searches for an appropriate response template from its internal database and uses that template to generate sample phrases. The generated sample phrases may be selected randomly.

[0952] Input: Extracted keywords and intent.

[0953] Output: Generated sample text (e.g., "Dear customer, I understand you haven't received this month's invoice yet. Could you please provide your address and registered phone number so we can verify this?").

[0954] Step 5:

[0955] The server sends the generated sample text to the terminal.

[0956] Specific operation: The generated sample text is sent back to the user's device via the network using an HTTP response.

[0957] Input: Generated sample text.

[0958] Output: A sample message that will be displayed on the user's device.

[0959] Step 6:

[0960] The user reviews the sample wording, makes any necessary adjustments, and submits the final response.

[0961] Specific operation: The user checks the displayed sample text, fine-tunes it using a text editor if necessary, and presses the send button to finalize the response text.

[0962] Input: Sample text and user tweaks.

[0963] Output: The data that will be sent as the final response.

[0964] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0965] The present invention relates to a call center support system that promptly proposes appropriate sample phrases in response to user inquiries. This system analyzes the content of the user's inquiry, generates and displays appropriate response phrases, and also includes a means for recognizing the user's emotions and reflecting them in the response template.

[0966] System configuration and functions

[0967] User query input

[0968] The terminal provides an interface for the user to input the inquiry details. This interface is composed of a form that includes a text box for inputting the inquiry details and a send button. When the user inputs the inquiry details and presses the send button, the input details are sent to the server.

[0969] Sending and analyzing inquiries

[0970] The server receives and temporarily stores the query sent from the device, then uses natural language processing (NLP) algorithms to analyze the text of the query, extracting key keywords and the user's intent.

[0971] Emotion recognition by emotion engine

[0972] The server uses an emotion engine to analyze the user's emotions from the text of the inquiry, recognizing, for example, emotional states such as anger, confusion, and sadness, thereby gaining a deeper understanding of the context and urgency of the inquiry.

[0973] Generating sample text based on inquiry content

[0974] The server searches for relevant response templates from its internal database based on the analyzed keywords and intent, as well as the results of the emotion engine. The database contains multiple response templates corresponding to various inquiry contents. For example, if the emotion is "anger," a more polite template that includes an apology is selected. The server generates sample text based on these templates.

[0975] Viewing and Using Sample Wording

[0976] The generated sample text is sent from the server to the terminal. The terminal displays this sample text to the user. The user can check the displayed sample text and make fine adjustments as necessary, or use it as is. The text that has been finalized as the final response text is sent by the user by pressing the send button.

[0977] Specific examples

[0978] A specific example will be described in which a user makes an inquiry such as, "I haven't received this month's bill yet. What should I do? I'm really in trouble."

[0979] 1. User query input

[0980] The terminal displays a form for the user to input the inquiry.

[0981] The user enters the inquiry content in the text box and presses the send button.

[0982] 2. Sending and analyzing inquiries

[0983] The terminal transmits the input inquiry to the server.

[0984] The server analyzes the received query using a natural language processing algorithm.

[0985] As a result of the analysis, the keywords and intents extracted are "invoice," "not received," and "what should I do."

[0986] 3. Emotion Recognition by Emotion Engine

[0987] The server analyzes the user's emotions from the text of the inquiry. For example, the emotion "confused" is recognized.

[0988] 4. Generating sample text based on inquiry content

[0989] The server searches for an appropriate template from the database based on the extracted keywords, intent, and the results of the emotion engine.

[0990] The server generates a sample message that reads, "Dear customer, we are very sorry for the inconvenience. We understand that you have not yet received your monthly bill. Could you please provide us with your address and registered phone number so we can verify this?"

[0991] 5. Viewing and Using Sample Wording

[0992] The terminal displays the generated sample text to the user.

[0993] The user can fine-tune the displayed sample text as needed and then press the send button to send it as the final response text.

[0994] This system enables appropriate responses that take into account the user's emotions, allowing even new operators to provide high-quality service.

[0995] The processing flow will be explained below.

[0996] Step 1:

[0997] The terminal displays an interface (such as a text box and a send button) for the user to input the inquiry content.

[0998] Step 2:

[0999] The user enters the inquiry into the terminal interface (e.g., "I haven't received this month's invoice yet. What should I do? I'm really worried.") and presses the send button.

[1000] Step 3:

[1001] The device sends the entered query to the server using a protocol such as an HTTP request or WebSocket.

[1002] Step 4:

[1003] The server temporarily stores the inquiry received from the terminal and invokes a natural language processing algorithm.

[1004] Step 5:

[1005] The server uses natural language processing algorithms to analyze the text of the inquiry, extracting key keywords (e.g., "bill," "not received," "what should I do," "I'm having trouble") and the user's intent.

[1006] Step 6:

[1007] The server uses an emotion engine to analyze the user's emotion from the text of the inquiry. For example, the emotion "confusion" is recognized from the part "I'm in trouble."

[1008] Step 7:

[1009] The server searches a database for relevant response templates based on the analysis results (keywords and emotions). The database contains multiple response templates corresponding to various inquiry contents. In particular, considering that the emotion is "confusion," the server selects a template that is more polite and shows empathy.

[1010] Step 8:

[1011] The server generates a sample message based on the most suitable template, such as "Dear customer, we apologize for the inconvenience. We understand that you have not yet received this month's invoice. To confirm, could you please provide us with your address and registered phone number?"

[1012] Step 9:

[1013] The server transmits the generated sample text to the terminal.

[1014] Step 10:

[1015] The terminal displays the received sample text to the user, who can then check the displayed sample text and make fine adjustments as necessary.

[1016] Step 11:

[1017] The user checks the sample text for fine tuning or leaves it as is, and then presses the send button to send it as the final response text.

[1018] Example 2

[1019] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1020] In conventional call center operations, providing prompt and appropriate responses to user inquiries has been a challenge. It is particularly difficult for new operators to generate appropriate responses to inquiries. Furthermore, there is a lack of means to automatically generate responses that take the user's emotions into consideration, which results in inconsistent response quality and lower customer satisfaction.

[1021] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for analyzing the content of the inquiry and extracting main keywords and intention, means for using an emotion engine for analyzing the user's emotions, and means for searching a database for a response template based on the extracted keywords, intention, and emotion analysis. This makes it possible to quickly generate and display appropriate sample phrases, allowing even new operators to provide high-quality responses.

[1022] The "interface for inputting inquiry details" is an interface that allows a user to input inquiry details via a text box, a send button, etc., and send the details to the server.

[1023] The "means for sending the inquiry content to the server" is a function for sending the inquiry content entered by the user to the server using a protocol such as HTTP or HTTPS.

[1024] "Means of analyzing the content of the received inquiry and extracting key keywords and intent" refers to the function of analyzing the text data received by the server using a natural language processing algorithm to identify and extract important keywords and the user's intent.

[1025] The "means for generating relevant sample phrases" is a function that generates appropriate response phrases from templates based on the analyzed keywords and intent.

[1026] The "means for using an emotion engine to analyze user emotions" is a function that uses an engine to analyze emotions (e.g., anger, confusion, sadness, etc.) from the user's inquiry text and quantify or categorize them.

[1027] "Means for searching for response templates from a database" refers to a function that searches for and retrieves appropriate response templates stored in a database based on the results of extracted keywords, intent, and sentiment analysis.

[1028] The "means for displaying the generated sample text" is a function for displaying the sample text sent from the server on the interface of the terminal, and visually presenting it to the user.

[1029] The present invention relates to a call center support system that promptly proposes appropriate sample phrases in response to user inquiries. This system analyzes the content of the user's inquiry, generates and displays appropriate response phrases, and also includes a means for recognizing the user's emotions and reflecting them in the response template.

[1030] User query input

[1031] The terminal provides an interface for the user to input the inquiry details. The interface is constructed using HTML and JavaScript, and provides a form including a text box and a submit button. The user enters the inquiry details in the text box and presses the submit button, which sends the input details from the terminal to the server.

[1032] Sending and analyzing inquiries

[1033] The device sends the entered query to the server using HTTP or HTTPS. The server stores the received query in a database or temporary memory. Storage technologies include MySQL and Redis. The server then analyzes the query using natural language processing (NLP) algorithms such as Python's NLTK or SpaCy to extract key keywords and the user's intent.

[1034] Emotion recognition by emotion engine

[1035] The server uses an emotion engine, such as IBM Watson Tone Analyzer or Microsoft Text Analytics, to analyze the user's emotion from the text of the query. Using these tools, the server recognizes the emotion in the text (e.g., anger, confusion, sadness) and quantifies the emotional state.

[1036] Generating sample text based on inquiry content

[1037] The server searches for relevant response templates from an internal database based on the analyzed keywords, intent, and emotion engine results. The database contains multiple response templates corresponding to various inquiry contents. Using a database query system, it is possible to quickly search for the optimal template according to the user's emotion and inquiry content. Based on the searched template, the server generates sample text using a template engine such as Jinja2 or Handlebars.

[1038] Viewing and Using Sample Wording

[1039] The generated sample text is sent from the server to the device as an HTTP response. The device displays this sample text to the user using HTML and JavaScript. The user can check the displayed sample text and make fine adjustments as needed, or use it as is. Once the text is finalized, the user presses the send button to send the final response text.

[1040] Examples of concrete examples and prompts

[1041] For example, a specific case will be described in which a user makes an inquiry such as, "I haven't received this month's bill yet. What should I do? I'm really in trouble."

[1042] The user enters "I haven't received this month's bill yet. What should I do? I'm really worried." in the text box and presses the submit button.

[1043] The terminal sends the query to the server, which then analyzes the received query using a natural language processing algorithm.

[1044] As a result of the analysis, the keywords "bill," "not received," and "what should I do" as well as the user's emotion of "confusion" are extracted.

[1045] Using this information, the server searches a database for an appropriate response template and generates a sample message like this: "Dear customer, we apologize for the inconvenience. We understand that you have not yet received your monthly bill. Could you please provide us with your address and registered phone number so we can verify this?"

[1046] The generated sample text is sent to the terminal, which displays it to the user. The user can check the displayed text, make any necessary adjustments, and then press the send button to send the finalized response text.

[1047] An example of a prompt is as follows:

[1048] "User's question: I haven't received my invoice for this month yet, what should I do? I'm really worried.

[1049] Analysis results: Keywords: bill, not received, what to do. Emotions: confusion.

[1050] Please generate a sample response for this."

[1051] This series of processes makes it possible to provide a quick and appropriate response that takes into account the user's feelings, improving the efficiency and quality of call center operations.

[1052] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1053] Step 1: User query input

[1054] The terminal displays an input interface for the user. This interface is a form with a text box and a submit button. The screen is designed to be simple so that the user can easily enter their inquiry.

[1055] User input: The user enters the inquiry "I haven't received this month's invoice yet, what should I do?" into the text box and presses the send button. The input format is text-based.

[1056] Input and Output: The input is the query entered by the user, and the output is the query data ready to be sent.

[1057] Step 2: Submit your inquiry

[1058] The terminal sends the entered query to the server using the HTTP or HTTPS protocol, with the data being sent in JSON format.

[1059] Input and output: The input is the query entered by the user, and the output is a notification of completion of transmission to the server.

[1060] Step 3: Receiving and storing your inquiry

[1061] The server receives the inquiry sent from the terminal and temporarily stores it in a database (e.g., MySQL or Redis).

[1062] Input and output: The input is the query content sent from the terminal, and the output is the query data stored in the database.

[1063] Specific operation: The server receives the HTTP request and saves the query in the database.

[1064] Step 4: Text Analysis

[1065] The server analyzes the received queries using natural language processing (NLP) algorithms, specifically Python's NLTK or SpaCy.

[1066] Input and Output: The input is the stored query content, and the output is a set of parsed keywords and intents.

[1067] Specific operation: A program is run to tokenize the query and extract key keywords and user intent.

[1068] Step 5: Sentiment Analysis

[1069] The server uses an emotion engine to analyze the user's emotions from the text of the inquiry, specifically using IBM Watson Tone Analyzer and Microsoft Text Analytics.

[1070] Input and Output: The input is the text of the query, and the output is the analyzed emotion data (e.g., anger, confusion, sadness, etc.).

[1071] What it does: The emotion engine analyzes the text and quantifies or categorizes the user's emotion.

[1072] Step 6: Find the response template

[1073] The server searches a database for an appropriate response template based on the extracted keywords and the results of the intent and sentiment analysis.

[1074] Input and Output: The input is the extracted keywords, intent, and emotion data, and the output is the response template.

[1075] What it does: Runs a database query to find the best response template.

[1076] Step 7: Generate sample text

[1077] The server generates sample text based on the retrieved response template using a template engine (e.g., Jinja2 or Handlebars).

[1078] Input and Output: The input is the response template and the parsed results, and the output is the generated sample text.

[1079] Specific behavior: Dynamically generate sample text using a template engine.

[1080] Step 8: Submit and view sample text

[1081] The server sends the generated sample text to the terminal in the form of an HTTP response.

[1082] The device displays the received sample text to the user using HTML and JavaScript.

[1083] Input and Output: The input is the generated sample text, and the output is the display to the user.

[1084] Specific behavior: The device displays sample text in the text area for the user to review and adjust.

[1085] Step 9: User confirmation, adjustments and final submission

[1086] The user can check the sample text displayed and make any necessary adjustments. Once the adjustments are complete, the user presses the send button to send the final response text.

[1087] Input and Output: The input is the displayed sample text, the user's adjustments, and the output is the final response text.

[1088] Specific operation: The user checks and adjusts the sample text, and then sends the final response text to the server.

[1089] (Application example 2)

[1090] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1091] Modern inquiry response systems are required to provide prompt and appropriate responses that take user emotions into consideration. However, conventional systems lack the ability to automatically generate responses that reflect user emotions, resulting in low response quality and reduced user satisfaction. In particular, in the security field, where emergency response is required, prompt and appropriate responses are essential, and such issues can have a serious impact.

[1092] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1093] In this invention, the server includes means for providing an interface for inputting inquiry content, means for transmitting the inquiry content to the server, means for analyzing the received inquiry content and extracting main keywords and intent, means for analyzing the user's emotions, means for generating a response message based on the analyzed keywords, intent, and emotion, means for displaying the generated response message, and means for providing an interface for the user to check and fine-tune the generated response message. This enables a quick and appropriate response that reflects the user's emotions, making it possible to achieve high user satisfaction, particularly in emergency responses in the security field.

[1094] The "interface for inputting inquiry content" is a device that provides an input form for the user to input the inquiry content in text format.

[1095] The "means for transmitting the inquiry content to the server" refers to a device or software that has the function of transmitting the inquiry content entered by the user to the server via the network.

[1096] "Means for analyzing the content of the received inquiry and extracting key keywords and intent" refers to an algorithm or system that analyzes the received text data and extracts important keywords and the user's intent from it.

[1097] A "means for analyzing user emotions" is an algorithm or system that analyzes user input and recognizes the underlying emotion (e.g., anger, confusion, fear, etc.).

[1098] The "means for generating a response sentence based on the analyzed keywords, intention, and emotion" refers to a device or software that automatically generates an appropriate response sentence based on the extracted keywords, intention, and the user's emotion.

[1099] The "means for displaying the generated response message" refers to a device or software that has a screen or display for visually displaying the generated response message to the user.

[1100] "Means for providing an interface for a user to check and fine-tune the generated response text" refers to a device or software that provides an input interface for a user to check the generated response text and edit or modify it as necessary.

[1101] The present invention relates to a system for generating prompt and appropriate answers to user inquiries. Specific embodiments of the system will be described below.

[1102] First, the user inputs the inquiry using the terminal. The interface provided by the terminal consists of a text box and a send button, and has the function of sending the inquiry input by the user to the server. The inquiry is temporarily saved by the server.

[1103] The server then receives the query and analyzes it using natural language processing (NLP) algorithms. During the analysis, key keywords and user intent are extracted from the query. NLP models such as the Transformers library are used for this analysis.

[1104] At the same time, the server uses an emotion recognition engine to analyze the user's emotions from the query content, for example, accurately recognizing emotions such as anger, confusion, and fear in the text. The emotion recognition algorithm used at this stage provides a deeper understanding based on the user's text.

[1105] The server then searches for relevant response templates from its internal database based on the analyzed keywords, intent, and emotions, and generates appropriate responses based on these templates. The generated responses are designed to be appropriate and reflect the user's emotional state.

[1106] The generated response is then sent to the terminal and displayed to the user, who can review the displayed response and make any necessary adjustments. After making the adjustments, the user can then send the final response.

[1107] The configuration of this system will be explained using a concrete example. When a user makes a query such as "A suspicious person has appeared in my house. I'm really scared. What should I do?", the server receives this text and uses an NLP algorithm to extract the keywords and intent of "suspicious person," "house," "scary," and "what should I do." At the same time, the emotion recognition engine recognizes the user's emotion as "fear."

[1108] Based on this, the server generates a response message saying, "We will respond quickly to make you feel safe. Could you please tell us more about the situation?" This response message is sent to the device and displayed to the user. The user can check the displayed response message and modify it if necessary, and it is then sent.

[1109] Examples of prompts include:

[1110] "There's a suspicious person in my house. I'm really scared. What should I do?"

[1111] In this way, it is possible to generate a quick and appropriate response that takes into account the user's emotions. This system is expected to improve emergency response, especially in the security field, and increase user satisfaction.

[1112] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1113] Step 1:

[1114] The user inputs the inquiry using the terminal.

[1115] Input: Text of inquiry (e.g., "A suspicious person has appeared in my house. I'm really scared. What should I do?")

[1116] Output: The status of preparation for sending the query from the terminal to the server

[1117] Specific operation: The user enters the inquiry content in text format into the input form on the terminal and presses the send button. The terminal temporarily stores this content and generates a signal to send it to the server.

[1118] Step 2:

[1119] The terminal sends the inquiry to the server.

[1120] Input: The inquiry content entered by the user and pressed the send button

[1121] Output: The query arrives at the server and is saved.

[1122] Specific operation: The terminal sends the query entered by the user to the server via the network. The server temporarily stores the received data and prepares it for subsequent analysis.

[1123] Step 3:

[1124] The server analyzes the query received using a natural language processing algorithm.

[1125] Input: Text data of saved inquiry details

[1126] Output: Extracted main keywords and user intent

[1127] How it works: The server uses the "Transformers" library to analyze the query text and extract key keywords (e.g., "suspicious person," "house," "scary") and the user's intent (e.g., "asking for help").

[1128] Step 4:

[1129] The server uses an emotion recognition engine to analyze the emotion of the query.

[1130] Input: Text data of inquiry content

[1131] Output: Perceived emotional state (e.g., "fear")

[1132] How it works: The server uses an emotion recognition algorithm to analyze the emotions in the user's input text. The emotion recognition engine determines emotions such as anger, confusion, or fear from the context and wording of the text.

[1133] Step 5:

[1134] The server generates a response based on the analyzed keywords, intent, and sentiment.

[1135] Input: Parsed keyword, intent, and sentiment data

[1136] Output: Generated response (e.g., "We will act quickly to make you feel safe. Can you tell us more about the situation?")

[1137] What it does: The server searches for an appropriate response template from its internal database and generates the text using a generative AI model based on the parsed data.

[1138] Step 6:

[1139] The server sends the generated response text to the terminal, which displays it to the user.

[1140] Input: Generated response text

[1141] Output: The response text displayed to the user

[1142] Specific operation: The server sends the generated response text to the terminal via the network, and the terminal displays the response text on the user's screen.

[1143] Step 7:

[1144] The user checks the displayed response text and makes minor adjustments as necessary.

[1145] Input: Displayed response text

[1146] Output: Final response text

[1147] Specific operation: The user checks the response displayed on the terminal, edits or corrects the text as necessary, and then presses the send button to finalize the response.

[1148] This series of processing steps enables the generation of a quick and appropriate response that reflects the user's feelings.

[1149] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1150] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1151] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1152] [Fourth embodiment]

[1153] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1154] 7, a 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.

[1155] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1156] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1157] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1158] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1159] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1160] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1161] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1162] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1163] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1164] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1165] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1166] The present invention relates to a call center support system that promptly proposes appropriate sample phrases in response to user inquiries. The system includes a program that analyzes the content of a user's inquiry and generates and displays appropriate response phrases.

[1167] System configuration and functions

[1168] User query input

[1169] The terminal provides an interface for the user to input the inquiry details. This interface is composed of a form that includes a text box for inputting the inquiry details and a send button. When the user inputs the inquiry details and presses the send button, the input details are sent to the server.

[1170] Sending and analyzing inquiries

[1171] The server receives the inquiry sent from the device and temporarily stores it. It then uses a natural language processing (NLP) algorithm to analyze the text of the inquiry. This analysis extracts key keywords and the user's intent. For example, keywords such as "bill," "not received," and "what should I do" are extracted.

[1172] Generating sample text based on inquiry content

[1173] The server searches an internal database for relevant response templates based on the extracted keywords and intent. The database contains multiple response templates for various inquiries. When a suitable template is found, the server generates a sample message based on it. For example, the message generated might be, "Dear customer, I understand you haven't received this month's invoice yet. I'm sorry. Could you please tell me your address and registered phone number for confirmation?"

[1174] Viewing and Using Sample Wording

[1175] The generated sample text is sent from the server to the terminal. The terminal displays this sample text to the user. The user can check the displayed sample text and make fine adjustments as necessary, or use it as is. The text that has been finalized as the final response text is sent by the user by pressing the send button.

[1176] Specific examples

[1177] A specific example will be explained below in which a user inquires, "I haven't received this month's invoice yet. What should I do?"

[1178] 1. User query input

[1179] The terminal displays a form for the user to input the inquiry.

[1180] The user enters the inquiry content in the text box and presses the send button.

[1181] 2. Sending and analyzing inquiries

[1182] The terminal transmits the input inquiry to the server.

[1183] The server analyzes the received query using a natural language processing algorithm.

[1184] As a result of the analysis, the keywords and intents extracted are "invoice," "not received," and "what should I do."

[1185] 3. Generating sample text based on inquiry content

[1186] The server searches for an appropriate template from a database based on the extracted keywords and intent.

[1187] The server generates a sample message: "Sir, I understand that you haven't received this month's invoice yet. I'm sorry. To confirm, could you please tell me your address and registered phone number?"

[1188] 4. Displaying and Using Sample Wording

[1189] The terminal displays the generated sample text to the user.

[1190] The user can fine-tune the displayed sample text as needed and then press the send button to send it as the final response text.

[1191] This system allows even new operators to respond quickly and appropriately, shortening user waiting times and improving work efficiency.

[1192] The processing flow will be explained below.

[1193] Step 1:

[1194] The terminal displays an interface (such as a text box and a send button) for the user to input the inquiry content.

[1195] Step 2:

[1196] The user enters the inquiry (e.g., "I haven't received this month's invoice yet. What should I do?") into the terminal interface and presses the send button.

[1197] Step 3:

[1198] The device sends the entered query to the server using a protocol such as an HTTP request or WebSocket.

[1199] Step 4:

[1200] The server temporarily stores the inquiry received from the terminal and invokes a natural language processing algorithm.

[1201] Step 5:

[1202] The server uses natural language processing algorithms to analyze the text of the inquiry, extracting key keywords (e.g., "bill," "not received," "what should I do") and the user's intent.

[1203] Step 6:

[1204] The server searches for relevant response templates from a database that stores past inquiries and response phrases based on the keywords and intent extracted from the analysis results.

[1205] Step 7:

[1206] The server selects the most suitable response template and generates a sample message based on that template, such as, "Dear customer, I understand that you have not yet received this month's invoice. We are sorry. To confirm, could you please tell us your address and registered phone number?"

[1207] Step 8:

[1208] The server transmits the generated sample text to the terminal.

[1209] Step 9:

[1210] The terminal displays the received sample text to the user, who can refer to the displayed sample text and make fine adjustments as necessary.

[1211] Step 10:

[1212] The user checks the sample text for fine tuning or as is, and presses the send button to confirm it as the final response text.

[1213] Example 1

[1214] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1215] Modern call center operations require quick and appropriate responses to user inquiries, but this is often difficult for new operators and inexperienced staff. There is also a need to reduce response times and improve operational efficiency. Conventional systems have difficulty effectively providing appropriate responses based on user inquiries.

[1216] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1217] In this invention, the server includes a means for analyzing the content of the inquiry using a natural language processing algorithm and extracting key keywords and intent, a means for generating related sample phrases from an internal database using a generative AI model based on the extracted keywords and intent, and a means for using a prompt sentence as an input sentence to the generative AI model, thereby enabling the generation and display of a prompt and appropriate response sentence.

[1218] A "terminal" is a device through which a user inputs their inquiry and communicates with the server, and generally refers to a PC or smartphone.

[1219] "Interface" refers to the screen and input form that users use to interact with the system via their terminal, and includes a text box for entering inquiry details and a send button.

[1220] A "server" is a computer system that receives, stores, analyzes inquiries sent by users, and generates appropriate sample text.

[1221] A "natural language processing algorithm" is a technology for analyzing text data, extracting elements, and understanding meaning, and typical examples use software libraries such as "NLTK" and "spaCy."

[1222] "Keywords" refer to the most important words and expressions extracted from the user's inquiry.

[1223] "Intent" refers to what the user is seeking through their inquiry, their purpose or desire.

[1224] The "internal database" is an information resource that stores response templates for various inquiries and is used to generate sample phrases.

[1225] A "generative AI model" is a model that uses artificial intelligence technology to automatically generate appropriate sample phrases, generating responses using specific prompt phrases as input.

[1226] A "prompt" is a text sentence that indicates specific conditions or questions to the generative AI model, and serves as the basis for generating a response.

[1227] The present invention relates to a call center operation support system that responds quickly and appropriately to user inquiries. This system analyzes the content of user inquiries, generates related sample phrases, and displays them to the user, thereby improving work efficiency.

[1228] Components and Functions

[1229] User query input

[1230] The user inputs the inquiry using a terminal (e.g., a PC or smartphone). An interface for inputting the inquiry is displayed on this terminal. The interface includes a text box and a send button. When the user inputs the inquiry and presses the send button, the inquiry is sent to the server.

[1231] Sending and analyzing inquiries

[1232] The terminal sends the inquiry content entered by the user to the server using an HTTP request.

[1233] The server temporarily stores the query received from the device and then analyzes it using a natural language processing (NLP) algorithm. This analysis process uses Python's "NLTK" or "spaCy." The server then extracts important keywords and the user's intent.

[1234] Generating sample phrases based on extracted keywords and intent

[1235] The server searches for relevant response templates from its internal database based on the extracted keywords and intent. Once a suitable template is found, the server uses a "generative AI model" to generate the optimal sample phrase. An example prompt phrase is "I haven't received this month's invoice yet, what should I do?" The generated sample phrase is "Sir, I understand you haven't received this month's invoice yet. I'm sorry. Could you please tell me your address and registered phone number for verification?"

[1236] Viewing and Using Sample Wording

[1237] The server sends the generated sample text to the terminal. The terminal uses HTML and JavaScript to display this sample text to the user. The user can check the displayed sample text and make fine adjustments as necessary. If they wish to use it as is, they can simply press the send button to confirm it as the final response text.

[1238] Specific examples

[1239] When a user inquires, "I haven't received this month's invoice yet, what should I do?", the system operates as follows:

[1240] 1. The user enters the inquiry details into the form on the device and presses the send button.

[1241] 2. The device sends the input to the server.

[1242] 3. The server analyzes the received content using a natural language processing algorithm and extracts the keywords "invoice," "not received," and "what should I do."

[1243] 4. The server searches the database for relevant templates and generates sample text using a generative AI model.

[1244] 5. The server sends the generated sample text to the terminal, which displays it to the user.

[1245] 6. The user checks and adjusts the sample text, then finalizes and sends the final response.

[1246] This system allows even new operators to respond quickly and appropriately, shortening user waiting times and improving work efficiency.

[1247] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1248] Step 1: User query input

[1249] The user inputs the inquiry into the terminal interface and presses the send button. This interface includes a text box for inputting the inquiry and a send button.

[1250] Input: Text data of the inquiry entered by the user

[1251] Output: Form data for sending inquiry content from the terminal to the server

[1252] Step 2: Submit your inquiry

[1253] The terminal sends the query entered by the user to the server, using an HTTP request to send the data.

[1254] Input: Text data of the inquiry entered by the user

[1255] Output: HTTP request data received by the server

[1256] Step 3: Receiving and temporarily saving your inquiry

[1257] The server receives the inquiry sent from the terminal and temporarily stores it.

[1258] Input: HTTP request data sent from the terminal

[1259] Output: Text data of the temporarily saved inquiry

[1260] Step 4: Analyzing the inquiry

[1261] The server analyzes the stored query using natural language processing (NLP) algorithms, such as NLTK and spaCy. As a result of the analysis, key keywords and user intent are extracted.

[1262] Input: Text data of the inquiry that was temporarily saved

[1263] Data processing: Analysis using natural language processing algorithms and keyword extraction

[1264] Output: Extracted main keywords and user intent

[1265] Step 5: Generate sample text

[1266] The server searches for relevant response templates from its internal database based on the extracted keywords and intent. Once a suitable template is found, the server uses a generative AI model to generate sample prompts. An example prompt is, "I haven't received my monthly bill yet. What should I do?"

[1267] Input: Extracted keywords and user intent

[1268] Data processing: Search for templates from an internal database and generate sample text using a generative AI model

[1269] Output: Generated sample text

[1270] Step 6: Submit and view sample text

[1271] The server sends the generated sample text to the terminal.

[1272] The device displays the received sample text to the user using HTML and JavaScript.

[1273] Input: Generated sample text

[1274] Output: Screen (interface) showing sample text

[1275] Step 7: Review and adjust user responses

[1276] The user checks the displayed sample text, makes minor adjustments as necessary, and presses the send button again to confirm the final response text after adjustments.

[1277] Input: Sample text displayed

[1278] Output: Final response sentence adjusted by the user

[1279] Step 8: Sending a Final Response

[1280] The terminal sends the adjusted final response to the server or other relevant departments.

[1281] Input: Adjusted final response

[1282] Output: The final response received by the server

[1283] (Application example 1)

[1284] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1285] In conventional call center operations, responses to user inquiries depended heavily on the experience and ability of the operator, and new operators were often slow to respond or unable to provide appropriate responses. This also created problems such as long wait times for users to receive appropriate responses. This resulted in a poor customer experience and a decline in operational efficiency.

[1286] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1287] In this invention, the server includes means for providing an interface for inputting inquiry content, means for transmitting the inquiry content, means for analyzing the received inquiry content and extracting main keywords and intent, means for generating related sample phrases based on the extracted keywords and intent, means for displaying the generated sample phrases, and means for the user to fine-tune and transmit a final response, thereby enabling prompt and appropriate response phrases to be presented.

[1288] The "means for providing an interface for inputting inquiry details" refers to a device or program that provides a format or screen for the user to input inquiry details.

[1289] The "means for transmitting the inquiry content to the server" refers to a device or program for transmitting the inquiry content input by the user to the server via the network.

[1290] "Means for analyzing the content of the received inquiry and extracting key keywords and intent" refers to a device or program that uses natural language processing technology to analyze the content of the inquiry sent to the server and identify important words and the user's intent from within it.

[1291] The "means for generating relevant sample phrases based on the extracted keywords and intent" refers to a device or program that generates appropriate response phrases based on the extracted keywords and the user's intent.

[1292] The "means for displaying the generated sample message" refers to a device or program that visually presents the generated response message to the user.

[1293] The "means for the user to fine-tune and send the final response" refers to a device or program that allows the user to fine-tune the sample wording provided and then send it as the final response.

[1294] The "means for searching a database for a response template" refers to a device or program that searches a database for a response template related to the content of the inquiry.

[1295] "Natural language processing algorithms" are a series of algorithms that allow computers to understand, generate, and analyze natural human language.

[1296] The system for implementing this invention includes a series of processes for allowing users to input inquiry content and provide quick and appropriate sample phrases. This system mainly consists of the following components:

[1297] 1. User query input

[1298] The user inputs the inquiry details through the smartphone application. The interface includes a text box and a send button, and when the user inputs the inquiry details and presses the send button, the details are sent to the server.

[1299] 2. Sending and analyzing inquiries

[1300] The query sent from the device is received by the server and temporarily stored. The server then uses natural language processing (NLP) algorithms to analyze the text of the query. The analysis extracts key keywords and the user's intent. NLP libraries such as spaCy are used in this process.

[1301] 3. Generating sample text based on inquiry content

[1302] The server searches its internal database for relevant response templates based on the extracted keywords and intent. Once a suitable template is found, a sample response is generated. This response template is randomly selected from a set of pre-defined templates.

[1303] 4. Displaying and Using Sample Wording

[1304] The generated sample text is sent back to the terminal and displayed to the user, who can then fine-tune the displayed sample text as needed and send the final response text.

[1305] This system allows even new operators to respond quickly and appropriately, shortening user waiting times and maintaining consistency in responses, improving operational efficiency.

[1306] Specific examples

[1307] Consider the case where a user types "I haven't received my bill this month yet, what should I do?" into a smartphone application. When the user presses the send button, the text is sent to the server. The server uses NLP to analyze the text and extract the keywords "bill," "not received," and "what should I do." Based on this, a relevant response template is searched for in the database and a sample response is generated: "Sir, I understand you haven't received your bill this month yet. I'm sorry. Could you please tell me your address and registered phone number for confirmation?" This response is displayed on the user's device, and the user can fine-tune it as needed and send it as the final response.

[1308] Example prompts to input to the generative AI model

[1309] Please enter the content of your inquiry. For example, if you enter "I haven't received this month's invoice yet, what's going on?", sample text that will promptly respond to this content will be displayed.

[1310] In this way, the system of the present invention simultaneously improves the efficiency of inquiry response work and user satisfaction.

[1311] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1312] Step 1:

[1313] The user inputs the inquiry using the smartphone interface.

[1314] Specific operation: The user enters an inquiry such as "I haven't received this month's bill yet. What should I do?" into the text box on their smartphone and presses the send button.

[1315] Input: The text of the inquiry.

[1316] Output: The data sent to the server based on the query entered.

[1317] Step 2:

[1318] The terminal sends the inquiry to the server.

[1319] Specific operation: The entered text data is sent to the server via the network, typically using an HTTP POST request.

[1320] Input: The query entered by the user.

[1321] Output: The server receives the query and begins processing it.

[1322] Step 3:

[1323] The server analyzes the received query and extracts the main keywords and the user's intent.

[1324] What it does: The server uses NLP algorithms (e.g., spaCy) to analyze the text and extract important keywords such as nouns and verbs, as well as the user's intent.

[1325] Input: Text data of the inquiry.

[1326] Output: Extracted keywords and user intent (e.g., "invoice," "not received," "what should I do?").

[1327] Step 4:

[1328] The server generates relevant sample text based on the extracted keywords and intent.

[1329] Specific operation: Based on the extracted keywords, the server searches for an appropriate response template from its internal database and uses that template to generate sample phrases. The generated sample phrases may be selected randomly.

[1330] Input: Extracted keywords and intent.

[1331] Output: Generated sample text (e.g., "Dear customer, I understand you haven't received this month's invoice yet. Could you please provide your address and registered phone number so we can verify this?").

[1332] Step 5:

[1333] The server sends the generated sample text to the terminal.

[1334] Specific operation: The generated sample text is sent back to the user's device via the network using an HTTP response.

[1335] Input: Generated sample text.

[1336] Output: A sample message that will be displayed on the user's device.

[1337] Step 6:

[1338] The user reviews the sample wording, makes any necessary adjustments, and submits the final response.

[1339] Specific operation: The user checks the displayed sample text, fine-tunes it using a text editor if necessary, and presses the send button to finalize the response text.

[1340] Input: Sample text and user tweaks.

[1341] Output: The data that will be sent as the final response.

[1342] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1343] The present invention relates to a call center support system that promptly proposes appropriate sample phrases in response to user inquiries. This system analyzes the content of the user's inquiry, generates and displays appropriate response phrases, and also includes a means for recognizing the user's emotions and reflecting them in the response template.

[1344] System configuration and functions

[1345] User query input

[1346] The terminal provides an interface for the user to input the inquiry details. This interface is composed of a form that includes a text box for inputting the inquiry details and a send button. When the user inputs the inquiry details and presses the send button, the input details are sent to the server.

[1347] Sending and analyzing inquiries

[1348] The server receives and temporarily stores the query sent from the device, then uses natural language processing (NLP) algorithms to analyze the text of the query, extracting key keywords and the user's intent.

[1349] Emotion recognition by emotion engine

[1350] The server uses an emotion engine to analyze the user's emotions from the text of the inquiry, recognizing, for example, emotional states such as anger, confusion, and sadness, thereby gaining a deeper understanding of the context and urgency of the inquiry.

[1351] Generating sample text based on inquiry content

[1352] The server searches for relevant response templates from its internal database based on the analyzed keywords and intent, as well as the results of the emotion engine. The database contains multiple response templates corresponding to various inquiry contents. For example, if the emotion is "anger," a more polite template that includes an apology is selected. The server generates sample text based on these templates.

[1353] Viewing and Using Sample Wording

[1354] The generated sample text is sent from the server to the terminal. The terminal displays this sample text to the user. The user can check the displayed sample text and make fine adjustments as necessary, or use it as is. The text that has been finalized as the final response text is sent by the user by pressing the send button.

[1355] Specific examples

[1356] A specific example will be described in which a user makes an inquiry such as, "I haven't received this month's bill yet. What should I do? I'm really in trouble."

[1357] 1. User query input

[1358] The terminal displays a form for the user to input the inquiry.

[1359] The user enters the inquiry content in the text box and presses the send button.

[1360] 2. Sending and analyzing inquiries

[1361] The terminal transmits the input inquiry to the server.

[1362] The server analyzes the received query using a natural language processing algorithm.

[1363] As a result of the analysis, the keywords and intents extracted are "invoice," "not received," and "what should I do."

[1364] 3. Emotion Recognition by Emotion Engine

[1365] The server analyzes the user's emotions from the text of the inquiry. For example, the emotion "confused" is recognized.

[1366] 4. Generating sample text based on inquiry content

[1367] The server searches for an appropriate template from the database based on the extracted keywords, intent, and the results of the emotion engine.

[1368] The server generates a sample message that reads, "Dear customer, we are very sorry for the inconvenience. We understand that you have not yet received your monthly bill. Could you please provide us with your address and registered phone number so we can verify this?"

[1369] 5. Viewing and Using Sample Wording

[1370] The terminal displays the generated sample text to the user.

[1371] The user can fine-tune the displayed sample text as needed and then press the send button to send it as the final response text.

[1372] This system enables appropriate responses that take into account the user's emotions, allowing even new operators to provide high-quality service.

[1373] The processing flow will be explained below.

[1374] Step 1:

[1375] The terminal displays an interface (such as a text box and a send button) for the user to input the inquiry content.

[1376] Step 2:

[1377] The user enters the inquiry into the terminal interface (e.g., "I haven't received this month's invoice yet. What should I do? I'm really worried.") and presses the send button.

[1378] Step 3:

[1379] The device sends the entered query to the server using a protocol such as an HTTP request or WebSocket.

[1380] Step 4:

[1381] The server temporarily stores the inquiry received from the terminal and invokes a natural language processing algorithm.

[1382] Step 5:

[1383] The server uses natural language processing algorithms to analyze the text of the inquiry, extracting key keywords (e.g., "bill," "not received," "what should I do," "I'm having trouble") and the user's intent.

[1384] Step 6:

[1385] The server uses an emotion engine to analyze the user's emotion from the text of the inquiry. For example, the emotion "confusion" is recognized from the part "I'm in trouble."

[1386] Step 7:

[1387] The server searches a database for relevant response templates based on the analysis results (keywords and emotions). The database contains multiple response templates corresponding to various inquiry contents. In particular, considering that the emotion is "confusion," the server selects a template that is more polite and shows empathy.

[1388] Step 8:

[1389] The server generates a sample message based on the most suitable template, such as "Dear customer, we apologize for the inconvenience. We understand that you have not yet received this month's invoice. To confirm, could you please provide us with your address and registered phone number?"

[1390] Step 9:

[1391] The server transmits the generated sample text to the terminal.

[1392] Step 10:

[1393] The terminal displays the received sample text to the user, who can then check the displayed sample text and make fine adjustments as necessary.

[1394] Step 11:

[1395] The user checks the sample text for fine tuning or leaves it as is, and then presses the send button to send it as the final response text.

[1396] Example 2

[1397] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1398] In conventional call center operations, providing prompt and appropriate responses to user inquiries has been a challenge. It is particularly difficult for new operators to generate appropriate responses to inquiries. Furthermore, there is a lack of means to automatically generate responses that take the user's emotions into consideration, which results in inconsistent response quality and lower customer satisfaction.

[1399] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for analyzing the content of the inquiry and extracting main keywords and intention, means for using an emotion engine for analyzing the user's emotions, and means for searching a database for a response template based on the extracted keywords, intention, and emotion analysis. This makes it possible to quickly generate and display appropriate sample phrases, allowing even new operators to provide high-quality responses.

[1400] The "interface for inputting inquiry details" is an interface that allows a user to input inquiry details via a text box, a send button, etc., and send the details to the server.

[1401] The "means for sending the inquiry content to the server" is a function for sending the inquiry content entered by the user to the server using a protocol such as HTTP or HTTPS.

[1402] "Means of analyzing the content of the received inquiry and extracting key keywords and intent" refers to the function of analyzing the text data received by the server using a natural language processing algorithm to identify and extract important keywords and the user's intent.

[1403] The "means for generating relevant sample phrases" is a function that generates appropriate response phrases from templates based on the analyzed keywords and intent.

[1404] The "means for using an emotion engine to analyze user emotions" is a function that uses an engine to analyze emotions (e.g., anger, confusion, sadness, etc.) from the user's inquiry text and quantify or categorize them.

[1405] "Means for searching for response templates from a database" refers to a function that searches for and retrieves appropriate response templates stored in a database based on the results of extracted keywords, intent, and sentiment analysis.

[1406] The "means for displaying the generated sample text" is a function for displaying the sample text sent from the server on the interface of the terminal, and visually presenting it to the user.

[1407] The present invention relates to a call center support system that promptly proposes appropriate sample phrases in response to user inquiries. This system analyzes the content of the user's inquiry, generates and displays appropriate response phrases, and also includes a means for recognizing the user's emotions and reflecting them in the response template.

[1408] User query input

[1409] The terminal provides an interface for the user to input the inquiry details. The interface is constructed using HTML and JavaScript, and provides a form including a text box and a submit button. The user enters the inquiry details in the text box and presses the submit button, which sends the input details from the terminal to the server.

[1410] Sending and analyzing inquiries

[1411] The device sends the entered query to the server using HTTP or HTTPS. The server stores the received query in a database or temporary memory. Storage technologies include MySQL and Redis. The server then analyzes the query using natural language processing (NLP) algorithms such as Python's NLTK or SpaCy to extract key keywords and the user's intent.

[1412] Emotion recognition by emotion engine

[1413] The server uses an emotion engine, such as IBM Watson Tone Analyzer or Microsoft Text Analytics, to analyze the user's emotion from the text of the query. Using these tools, the server recognizes the emotion in the text (e.g., anger, confusion, sadness) and quantifies the emotional state.

[1414] Generating sample text based on inquiry content

[1415] The server searches for relevant response templates from an internal database based on the analyzed keywords, intent, and emotion engine results. The database contains multiple response templates corresponding to various inquiry contents. Using a database query system, it is possible to quickly search for the optimal template according to the user's emotion and inquiry content. Based on the searched template, the server generates sample text using a template engine such as Jinja2 or Handlebars.

[1416] Viewing and Using Sample Wording

[1417] The generated sample text is sent from the server to the device as an HTTP response. The device displays this sample text to the user using HTML and JavaScript. The user can check the displayed sample text and make fine adjustments as needed, or use it as is. Once the text is finalized, the user presses the send button to send the final response text.

[1418] Examples of concrete examples and prompts

[1419] For example, a specific case will be described in which a user makes an inquiry such as, "I haven't received this month's bill yet. What should I do? I'm really in trouble."

[1420] The user enters "I haven't received this month's bill yet. What should I do? I'm really worried." in the text box and presses the submit button.

[1421] The terminal sends the query to the server, which then analyzes the received query using a natural language processing algorithm.

[1422] As a result of the analysis, the keywords "bill," "not received," and "what should I do" as well as the user's emotion of "confusion" are extracted.

[1423] Using this information, the server searches a database for an appropriate response template and generates a sample message like this: "Dear customer, we apologize for the inconvenience. We understand that you have not yet received your monthly bill. Could you please provide us with your address and registered phone number so we can verify this?"

[1424] The generated sample text is sent to the terminal, which displays it to the user. The user can check the displayed text, make any necessary adjustments, and then press the send button to send the finalized response text.

[1425] An example of a prompt is as follows:

[1426] "User's question: I haven't received my invoice for this month yet, what should I do? I'm really worried.

[1427] Analysis results: Keywords: bill, not received, what to do. Emotions: confusion.

[1428] Please generate a sample response for this."

[1429] This series of processes makes it possible to provide a quick and appropriate response that takes into account the user's feelings, improving the efficiency and quality of call center operations.

[1430] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1431] Step 1: User query input

[1432] The terminal displays an input interface for the user. This interface is a form with a text box and a submit button. The screen is designed to be simple so that the user can easily enter their inquiry.

[1433] User input: The user enters the inquiry "I haven't received this month's invoice yet, what should I do?" into the text box and presses the send button. The input format is text-based.

[1434] Input and Output: The input is the query entered by the user, and the output is the query data ready to be sent.

[1435] Step 2: Submit your inquiry

[1436] The terminal sends the entered query to the server using the HTTP or HTTPS protocol, with the data being sent in JSON format.

[1437] Input and output: The input is the query entered by the user, and the output is a notification of completion of transmission to the server.

[1438] Step 3: Receiving and storing your inquiry

[1439] The server receives the inquiry sent from the terminal and temporarily stores it in a database (e.g., MySQL or Redis).

[1440] Input and output: The input is the query content sent from the terminal, and the output is the query data stored in the database.

[1441] Specific operation: The server receives the HTTP request and saves the query in the database.

[1442] Step 4: Text Analysis

[1443] The server analyzes the received queries using natural language processing (NLP) algorithms, specifically Python's NLTK or SpaCy.

[1444] Input and Output: The input is the stored query content, and the output is a set of parsed keywords and intents.

[1445] Specific operation: A program is run to tokenize the query and extract key keywords and user intent.

[1446] Step 5: Sentiment Analysis

[1447] The server uses an emotion engine to analyze the user's emotions from the text of the inquiry, specifically using IBM Watson Tone Analyzer and Microsoft Text Analytics.

[1448] Input and Output: The input is the text of the query, and the output is the analyzed emotion data (e.g., anger, confusion, sadness, etc.).

[1449] What it does: The emotion engine analyzes the text and quantifies or categorizes the user's emotion.

[1450] Step 6: Find the response template

[1451] The server searches a database for an appropriate response template based on the extracted keywords and the results of the intent and sentiment analysis.

[1452] Input and Output: The input is the extracted keywords, intent, and emotion data, and the output is the response template.

[1453] What it does: Runs a database query to find the best response template.

[1454] Step 7: Generate sample text

[1455] The server generates sample text based on the retrieved response template using a template engine (e.g., Jinja2 or Handlebars).

[1456] Input and Output: The input is the response template and the parsed results, and the output is the generated sample text.

[1457] Specific behavior: Dynamically generate sample text using a template engine.

[1458] Step 8: Submit and view sample text

[1459] The server sends the generated sample text to the terminal in the form of an HTTP response.

[1460] The device displays the received sample text to the user using HTML and JavaScript.

[1461] Input and Output: The input is the generated sample text, and the output is the display to the user.

[1462] Specific behavior: The device displays sample text in the text area for the user to review and adjust.

[1463] Step 9: User confirmation, adjustments and final submission

[1464] The user can check the sample text displayed and make any necessary adjustments. Once the adjustments are complete, the user presses the send button to send the final response text.

[1465] Input and Output: The input is the displayed sample text, the user's adjustments, and the output is the final response text.

[1466] Specific operation: The user checks and adjusts the sample text, and then sends the final response text to the server.

[1467] (Application example 2)

[1468] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1469] Modern inquiry response systems are required to provide prompt and appropriate responses that take user emotions into consideration. However, conventional systems lack the ability to automatically generate responses that reflect user emotions, resulting in low response quality and reduced user satisfaction. In particular, in the security field, where emergency response is required, prompt and appropriate responses are essential, and such issues can have a serious impact.

[1470] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1471] In this invention, the server includes means for providing an interface for inputting inquiry content, means for transmitting the inquiry content to the server, means for analyzing the received inquiry content and extracting main keywords and intent, means for analyzing the user's emotions, means for generating a response message based on the analyzed keywords, intent, and emotion, means for displaying the generated response message, and means for providing an interface for the user to check and fine-tune the generated response message. This enables a quick and appropriate response that reflects the user's emotions, making it possible to achieve high user satisfaction, particularly in emergency responses in the security field.

[1472] The "interface for inputting inquiry content" is a device that provides an input form for the user to input the inquiry content in text format.

[1473] The "means for transmitting the inquiry content to the server" refers to a device or software that has the function of transmitting the inquiry content entered by the user to the server via the network.

[1474] "Means for analyzing the content of the received inquiry and extracting key keywords and intent" refers to an algorithm or system that analyzes the received text data and extracts important keywords and the user's intent from it.

[1475] A "means for analyzing user emotions" is an algorithm or system that analyzes user input and recognizes the underlying emotion (e.g., anger, confusion, fear, etc.).

[1476] The "means for generating a response sentence based on the analyzed keywords, intention, and emotion" refers to a device or software that automatically generates an appropriate response sentence based on the extracted keywords, intention, and the user's emotion.

[1477] The "means for displaying the generated response message" refers to a device or software that has a screen or display for visually displaying the generated response message to the user.

[1478] "Means for providing an interface for a user to check and fine-tune the generated response text" refers to a device or software that provides an input interface for a user to check the generated response text and edit or modify it as necessary.

[1479] The present invention relates to a system for generating prompt and appropriate answers to user inquiries. Specific embodiments of the system will be described below.

[1480] First, the user inputs the inquiry using the terminal. The interface provided by the terminal consists of a text box and a send button, and has the function of sending the inquiry input by the user to the server. The inquiry is temporarily saved by the server.

[1481] The server then receives the query and analyzes it using natural language processing (NLP) algorithms. During the analysis, key keywords and user intent are extracted from the query. NLP models such as the Transformers library are used for this analysis.

[1482] At the same time, the server uses an emotion recognition engine to analyze the user's emotions from the query content, for example, accurately recognizing emotions such as anger, confusion, and fear in the text. The emotion recognition algorithm used at this stage provides a deeper understanding based on the user's text.

[1483] The server then searches for relevant response templates from its internal database based on the analyzed keywords, intent, and emotions, and generates appropriate responses based on these templates. The generated responses are designed to be appropriate and reflect the user's emotional state.

[1484] The generated response is then sent to the terminal and displayed to the user, who can review the displayed response and make any necessary adjustments. After making the adjustments, the user can then send the final response.

[1485] The configuration of this system will be explained using a concrete example. When a user makes a query such as "A suspicious person has appeared in my house. I'm really scared. What should I do?", the server receives this text and uses an NLP algorithm to extract the keywords and intent of "suspicious person," "house," "scary," and "what should I do." At the same time, the emotion recognition engine recognizes the user's emotion as "fear."

[1486] Based on this, the server generates a response message saying, "We will respond quickly to make you feel safe. Could you please tell us more about the situation?" This response message is sent to the device and displayed to the user. The user can check the displayed response message and modify it if necessary, and it is then sent.

[1487] Examples of prompts include:

[1488] "There's a suspicious person in my house. I'm really scared. What should I do?"

[1489] In this way, it is possible to generate a quick and appropriate response that takes into account the user's emotions. This system is expected to improve emergency response, especially in the security field, and increase user satisfaction.

[1490] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1491] Step 1:

[1492] The user inputs the inquiry using the terminal.

[1493] Input: Text of inquiry (e.g., "A suspicious person has appeared in my house. I'm really scared. What should I do?")

[1494] Output: The status of preparation for sending the query from the terminal to the server

[1495] Specific operation: The user enters the inquiry content in text format into the input form on the terminal and presses the send button. The terminal temporarily stores this content and generates a signal to send it to the server.

[1496] Step 2:

[1497] The terminal sends the inquiry to the server.

[1498] Input: The inquiry content entered by the user and pressed the send button

[1499] Output: The query arrives at the server and is saved.

[1500] Specific operation: The terminal sends the query entered by the user to the server via the network. The server temporarily stores the received data and prepares it for subsequent analysis.

[1501] Step 3:

[1502] The server analyzes the query received using a natural language processing algorithm.

[1503] Input: Text data of saved inquiry details

[1504] Output: Extracted main keywords and user intent

[1505] How it works: The server uses the "Transformers" library to analyze the query text and extract key keywords (e.g., "suspicious person," "house," "scary") and the user's intent (e.g., "asking for help").

[1506] Step 4:

[1507] The server uses an emotion recognition engine to analyze the emotion of the query.

[1508] Input: Text data of inquiry content

[1509] Output: Perceived emotional state (e.g., "fear")

[1510] How it works: The server uses an emotion recognition algorithm to analyze the emotions in the user's input text. The emotion recognition engine determines emotions such as anger, confusion, or fear from the context and wording of the text.

[1511] Step 5:

[1512] The server generates a response based on the analyzed keywords, intent, and sentiment.

[1513] Input: Parsed keyword, intent, and sentiment data

[1514] Output: Generated response (e.g., "We will act quickly to make you feel safe. Can you tell us more about the situation?")

[1515] What it does: The server searches for an appropriate response template from its internal database and generates the text using a generative AI model based on the parsed data.

[1516] Step 6:

[1517] The server sends the generated response text to the terminal, which displays it to the user.

[1518] Input: Generated response text

[1519] Output: The response text displayed to the user

[1520] Specific operation: The server sends the generated response text to the terminal via the network, and the terminal displays the response text on the user's screen.

[1521] Step 7:

[1522] The user checks the displayed response text and makes minor adjustments as necessary.

[1523] Input: Displayed response text

[1524] Output: Final response text

[1525] Specific operation: The user checks the response displayed on the terminal, edits or corrects the text as necessary, and then presses the send button to finalize the response.

[1526] This series of processing steps enables the generation of a quick and appropriate response that reflects the user's feelings.

[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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1528] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice 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 the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1530] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1531] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1532] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1533] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1534] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1535] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences 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 ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1537] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1538] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1539] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with 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] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1542] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1543] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific processing may be a single processor.

[1544] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1545] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1546] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1547] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1548] The following is further disclosed regarding the above embodiment.

[1549] (Claim 1)

[1550] means for providing an interface for inputting inquiry content;

[1551] means for transmitting the query to a server;

[1552] A means for analyzing the content of the received inquiry and extracting key keywords and intent;

[1553] A means for generating relevant sample phrases based on the extracted keywords and intent;

[1554] a means for displaying the generated sample text;

[1555] A system including:

[1556] (Claim 2)

[1557] 10. The system of claim 1, further comprising: means for retrieving a response template from a database based on the extracted keywords and intent.

[1558] (Claim 3)

[1559] 10. The system of claim 1, further comprising means for analyzing query content using a natural language processing algorithm.

[1560] "Example 1"

[1561] (Claim 1)

[1562] means for providing an interface displayed on a terminal for inputting a query;

[1563] means for transmitting the query to a server;

[1564] A means for analyzing the received inquiry content using a natural language processing algorithm and extracting key keywords and intent;

[1565] A means for generating relevant sample phrases from an internal database using a generative AI model based on the extracted keywords and intent;

[1566] A means for displaying the generated sample text on a terminal;

[1567] means for providing an interface for a user to adjust the final response sentence;

[1568] means for transmitting a tailored final response;

[1569] A system including:

[1570] (Claim 2)

[1571] 10. The system of claim 1, further comprising: means for retrieving a response template from a database based on the extracted keywords and intent.

[1572] (Claim 3)

[1573] 10. The system of claim 1, further comprising: means for using a prompt sentence as an input sentence to the generative AI model.

[1574] "Application Example 1"

[1575] (Claim 1)

[1576] means for providing an interface for inputting inquiry content;

[1577] means for transmitting the query to a server;

[1578] A means for analyzing the content of the received inquiry and extracting key keywords and intent;

[1579] A means for generating relevant sample phrases based on the extracted keywords and intent;

[1580] a means for displaying the generated sample text;

[1581] a means for the user to fine-tune and submit the final response;

[1582] A system including:

[1583] (Claim 2)

[1584] 10. The system of claim 1, further comprising: means for retrieving a response template from a database based on the extracted keywords and intent.

[1585] (Claim 3)

[1586] 10. The system of claim 1, further comprising means for analyzing query content using a natural language processing algorithm.

[1587] "Example 2: Combining Emotion Engines"

[1588] (Claim 1)

[1589] means for providing an interface for inputting inquiry content;

[1590] means for transmitting the query to a server;

[1591] A means for analyzing the content of the received inquiry and extracting key keywords and intent;

[1592] A means for generating relevant sample phrases based on the extracted keywords and intent;

[1593] means for using an emotion engine to analyze the emotion of a user;

[1594] a means for displaying the generated sample text;

[1595] A system including:

[1596] (Claim 2)

[1597] 10. The system of claim 1, further comprising means for retrieving a response template from a database based on the extracted keywords and intent and sentiment analysis.

[1598] (Claim 3)

[1599] 10. The system of claim 1, further comprising means for analyzing query content using a natural language processing algorithm.

[1600] "Application example 2 when combining emotion engines"

[1601] (Claim 1)

[1602] means for providing an interface for inputting inquiry content;

[1603] means for transmitting the query to a server;

[1604] A means for analyzing the content of the received inquiry and extracting key keywords and intent;

[1605] A means for generating relevant sample phrases based on the extracted keywords and intent;

[1606] means for analyzing user emotions;

[1607] A means for generating a response based on the analyzed keywords and the intent and sentiment;

[1608] means for displaying the generated response text;

[1609] A system including:

[1610] (Claim 2)

[1611] 10. The system of claim 1, further comprising means for providing an interface for a user to review and fine-tune the generated response wording.

[1612] (Claim 3)

[1613] 10. The system of claim 1, further comprising means for analyzing query content using a natural language processing algorithm. [Explanation of symbols]

[1614] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for providing an interface for inputting inquiry content; means for transmitting the query to a server; A means for analyzing the content of the received inquiry and extracting key keywords and intent; A means for generating relevant sample phrases based on the extracted keywords and intent; a means for displaying the generated sample text; A system including:

2. 10. The system of claim 1, further comprising: means for retrieving a response template from a database based on the extracted keywords and intent.

3. The system of claim 1 further comprising means for analyzing query content using a natural language processing algorithm.

Images