system

Abstract

Provide a system. 【Solution means】 Means for inputting a request content, Means for analyzing the request content and generating candidate answers, Means for selecting an answer from the generated candidate answers, Means for editing the selected answer, Means for generating proposals and information of additional services according to the enterprise scale and business type, Means for editing the proposals and information of the additional services, A system including means for transmitting the answer and the proposals and information of the additional services is provided.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a modern business environment, quickly and accurately responding to inquiries from customers is an important factor that affects a company's competitiveness. However, it is difficult for a person in charge to quickly generate an appropriate answer and further include an optimal service proposal in the answer for various requests from customers. In addition, it is not easy to provide proactive responses according to different scales and business types for each customer. In such a situation, there is a demand for a system that realizes the quickening and standardization of customer response and improves customer satisfaction and a company's sales.

Means for Solving the Problems

[0005] In order to solve the above problems, the present invention provides the following means.

[0006] The system includes means for inputting the request details, means for analyzing the request details and generating appropriate response candidates, means for selecting a response from the generated response candidates, means for editing the selected response, means for generating proposals and information for additional services tailored to the company size and type of business, means for editing the proposals and information for additional services, and means for transmitting the response and the proposals and information for additional services. This system achieves rapid and appropriate customer service by analyzing the request details using natural language processing technology, generating response candidates using a machine learning model, and referencing customer profiles when generating proposals tailored to the company size and type of business.

[0007] "Request details" refers to information that indicates customer inquiries, requests, problems, etc.

[0008] "Means of input" refers to the interface and devices that users use to input their requests into the system.

[0009] "Means of analysis" refers to a module that includes natural language processing technology for processing the input request content and understanding its meaning.

[0010] "Means for generating candidate answers" refers to algorithms and methods for generating appropriate response sentences based on the analyzed request content.

[0011] "Means for selecting an answer" refers to a user interface and method for selecting the best answer from multiple generated answer candidates.

[0012] "Means of editing" refers to a text editing interface that allows users to modify or change selected answers and additional information as needed.

[0013] "Means for generating proposals and information on additional services" refers to algorithms and technologies for generating proposals and additional information tailored to the size and type of business of the company.

[0014] "Means of transmission" refers to the methods and infrastructure for sending the final edited and confirmed responses and suggestions to customers via email, chat, or other means.

[0015] "Natural language processing technology" is a technology that enables computers to understand, interpret, and process human language.

[0016] A "machine learning model" is an algorithm and technology that learns patterns from vast amounts of data and automatically makes predictions and decisions.

[0017] A "customer profile" is information that includes the size of the customer's company, its business type, and its past purchase history. [Brief explanation of the drawing]

[0018] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] Shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0019] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0020] First, the terms used in the following description will be explained.

[0021] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0022] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0023] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0024] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0025] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0026] [First Embodiment]

[0027] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0028] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0029] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0030] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0031] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0032] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0033] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0034] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0036] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0037] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0038] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0039] The embodiments for carrying out this invention will now be described. The system of the invention begins by providing a terminal with an interface for the user to input the details of a customer's request. The request details entered into the terminal are transmitted to a server.

[0040] The server analyzes the received request using natural language processing techniques. This analysis step involves tokenizing and grammatically analyzing the request to extract important keywords and phrases. For example, a request like "My product delivery is delayed. Please tell me the status" is broken down into keywords such as "delivery," "delay," and "status."

[0041] Next, the server generates appropriate answer candidates based on the analyzed keywords and request details. This involves referencing internal databases and FAQ documents, and utilizing a machine learning model. This machine learning model learns from past responses to similar inquiries, enabling it to generate the most appropriate answer. For example, it might generate answers such as "There is a temporary problem with the delivery service" and "The reason for the delay in product delivery is insufficient stock."

[0042] The generated response options are displayed on the user's device. The user selects the most appropriate response from these options. After selection, the user can edit the response. For example, the response "There is a temporary problem with the delivery service" can be edited to "We apologize for the delay in delivery. There is currently a temporary problem with the delivery service."

[0043] Subsequently, the server generates suggestions and information for additional services tailored to the company's size and business type. In this step, it refers to the customer profile and makes optimal suggestions based on past purchase history and company characteristics. For example, it might generate a suggestion such as, "We'll provide you with a 20% discount coupon that you can use on your next order."

[0044] The generated additional service suggestions and information are also presented on the user's device, allowing the user to review and edit them as needed. For example, it is possible to change a "20% discount coupon" to a "30% discount coupon."

[0045] Finally, the user sends the edited response and additional suggestions to the customer. This sending process uses communication methods such as email or chat, which the server uses. For example, it might say, "We apologize for the delay in delivery. We are currently experiencing a temporary issue with our delivery service. As an apology, we are offering a 30% discount coupon that can be used on your next order."

[0046] In this way, the system of the present invention enables prompt and appropriate customer service, thereby improving customer satisfaction and sales.

[0047] The following describes the processing flow.

[0048] Step 1:

[0049] The user enters their request into the terminal. For example, they might enter a request such as, "My product delivery is delayed. Please tell me the status." This input is done through the interface on the terminal.

[0050] Step 2:

[0051] The terminal sends the request details entered by the user to the server. This transmission is done via an API and uses a secure communication protocol.

[0052] Step 3:

[0053] The server analyzes the received request using natural language processing techniques. Specifically, it breaks down the request into tokens, performs grammatical analysis, and extracts keywords and important phrases. For example, it identifies keywords such as "delivery," "delay," and "situation."

[0054] Step 4:

[0055] Based on the keywords analyzed by the server, it generates appropriate answer candidates. In this process, the server refers to an internal database and FAQ documents and uses a machine learning model to generate answer candidates. Examples of generated answers include "The reason for the delay in product delivery is insufficient stock" and "There is a temporary problem with the delivery service."

[0056] Step 5:

[0057] The server sends the generated answer candidates to the terminal. The terminal receives them and displays them in the user interface. The user reviews the multiple answer candidates presented.

[0058] Step 6:

[0059] The user selects the answer they deem most appropriate on their device. After selecting, the user can edit the selected answer as needed. For example, they might edit the answer "There is a temporary problem with our delivery service" to "We apologize for the delay in delivery. There is currently a temporary problem with our delivery service."

[0060] Step 7:

[0061] The server receives the edited response and, referencing the customer profile, generates additional service suggestions and information tailored to the company size and type. For example, if the customer is a small business, it might generate a suggestion such as, "We'll give you a 20% discount coupon for your next order."

[0062] Step 8:

[0063] The server sends additional suggestions and information it generates to the user's terminal, where the user can review and edit them. For example, a "20% discount coupon" can be changed to a "30% discount coupon."

[0064] Step 9:

[0065] The user sends their final edited response and additional suggestions to the server via their device. The server receives this and sends the final response to the customer via email, chat, or other means. For example, it might say, "We apologize for the delay in delivery. We are currently experiencing a temporary issue with our delivery service. As an apology, we are offering a 30% discount coupon for your next order."

[0066] In this way, the system enables quick and appropriate customer service, contributing to increased customer satisfaction and improved company sales.

[0067] (Example 1)

[0068] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0069] In today's business environment, responding quickly and appropriately to a wide range of customer inquiries is crucial for improving customer satisfaction and maintaining a company's competitiveness. However, efficiently handling a large volume of inquiries requires an automated response system utilizing advanced natural language processing technology and machine learning models. Furthermore, providing proposals and services tailored to individual customer needs necessitates a flexible system based on the company's size, industry, and customer profile. Developing a system that meets these diverse requirements remains challenging, and many companies have yet to implement one effectively.

[0070] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0071] In this invention, the server includes means for inputting the request details, means for analyzing the request details and generating appropriate response candidates, means for selecting a response from the generated response candidates, means for editing the selected response, means for generating suggestions and information on additional services according to the size and type of business, means for editing the suggestions and information on additional services, and means for transmitting the response and the suggestions and information on additional services. This enables prompt and appropriate customer service.

[0072] "Request details" refers to information about inquiries and requests received by the user from customers.

[0073] "Means of input" refers to the interface or device used by the user to input the details of their request into the system, as well as the method of operating it.

[0074] "Means of analysis" refers to the process and techniques used to analyze the received request using language processing technology and extract the necessary information.

[0075] "Response candidates" refer to several appropriate response options generated based on the analyzed request.

[0076] "Means of selection" refers to the interface or method that allows the user to choose the most suitable response from among the generated candidate responses.

[0077] "Means of editing" refer to tools and functions that allow users to modify or supplement selected responses as appropriate.

[0078] "Proposal for additional services" refers to additional services or offers provided based on customer needs, company size, and business type.

[0079] "Means of generating information" refers to processes and technologies for automatically creating suggestions for additional services and other related information.

[0080] "Means of transmission" refers to the means or methods of communication used to deliver the final edited response or additional service suggestions to the customer.

[0081] "Natural language processing technology" refers to the technology used by computers to understand and analyze natural language and extract relevant information.

[0082] A "machine learning model" is an algorithm that learns patterns based on past data and uses that knowledge to perform inferences and predictions on new data.

[0083] A "customer profile" refers to detailed information about individual customers, such as their past purchase history and behavioral data.

[0084] The system according to this invention provides a comprehensive solution for responding quickly and appropriately to customer inquiries. Specific embodiments of this system are described below.

[0085] First, a terminal is provided that offers an interface for users to input the details of requests received from customers. This interface is built as a web application based on HTML and JavaScript (registered trademark). Through this interface, users input the details of the request in text format. For example, "The delivery of the product is delayed. Please let me know the status."

[0086] The request details entered on the terminal are sent to the server via the internet. The HTTPS protocol is used for this communication, ensuring secure data transfer. Specifically, an Ajax request is generated, and data is sent in JSON format, as shown below.

[0087] json

[0088] {

[0089] "request": "My order is delayed. Please tell me the status."

[0090] }

[0091] The request content that reaches the server is analyzed using natural language processing (NLP) technology. This analysis uses spaCy, a Python NLP library, to tokenize the request content, perform grammatical analysis, and extract important keywords. For example, when tokenizing "My product delivery is delayed. Please tell me the status," the tokens would be "product," "delivery," "delay," "status," and "tell me."

[0092] Next, the server generates appropriate response candidates based on the analyzed keywords and request details. At this stage, it refers to internal databases and FAQ documents, and uses machine learning models. Specifically, it uses machine learning libraries such as TENSORFLOW® and scikit-learn, and models trained on historical data generate the optimal response. Examples of generated responses include "There is a temporary problem with the delivery service" and "The reason for the delay in product delivery is insufficient stock."

[0093] Once answer suggestions are generated, the server sends them to the user's device. The user reviews the suggested answers on their device and selects the most appropriate one. Furthermore, the user can edit their selected answer. For example, they can change the answer "There is a temporary problem with the delivery service" to "We apologize for the delay in delivery. There is currently a temporary problem with the delivery service."

[0094] In addition, the server generates suggestions for additional services tailored to the company's size and business type. This suggestion generation is performed by retrieving data from CRM systems such as Salesforce, based on customer profiles and past purchase history. Specific examples of suggestions include, "We'll provide you with a 20% discount coupon for your next order." Users can also edit the generated additional suggestions.

[0095] Finally, the user sends the edited response and additional suggestions to the customer. This sending process utilizes email and chat tool APIs. For example, the SendGrid API might be used to send a final message like the following:

[0096] "We sincerely apologize for the delay in delivery. We are currently experiencing a temporary issue with our delivery service. As an apology, we are offering a 30% discount coupon that can be used on your next order."

[0097] This system allows users to respond quickly and accurately, leading to increased customer satisfaction and sales.

[0098] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0099] Step 1:

[0100] The user enters customer requests using their device. The interface is built as a web application, and the user enters the request details into a text box. For example, they might enter, "The product delivery is delayed. Please let me know the status."

[0101] Step 2:

[0102] The terminal sends the entered request details to the server. HTTPS protocol is used for communication, and an Ajax request is generated. The input is in text format and is converted to JSON format upon transmission. Specific request example:

[0103] json

[0104] {

[0105] "request": "My order is delayed. Please tell me the status."

[0106] }

[0107] The output is the data packet sent to the server.

[0108] Step 3:

[0109] The server analyzes the received request using natural language processing techniques. The library used is spaCy in Python, which performs tokenization and grammatical analysis. The input is the request content in JSON format, and the output is extracted keywords. For example, if the input sentence "The delivery of my product is delayed. Please tell me the status" is analyzed, the output will be tokenized as "product", "delivery", "delay", "status", and "tell me".

[0110] Step 4:

[0111] The server generates appropriate answer candidates based on the analyzed keywords and request details. It references an internal database and FAQ documentation and runs a machine learning model using TensorFlow. The input is tokenized keywords, and the output is multiple answer candidates. For example, it might generate answers such as "There is a temporary problem with the delivery service" or "The reason for the delay in product delivery is insufficient stock."

[0112] Step 5:

[0113] The server sends the generated answer suggestions to the user's device. The user's device displays the answer suggestions and provides a confirmation UI. The input is the answer suggestion data, and the output is the confirmation screen the user can view. Specific UI example:

[0114] Option 1: "There is a temporary issue with our delivery service."

[0115] Option 2: "The reason for the delay in product delivery is a shortage of stock."

[0116] Step 6:

[0117] The user selects the most suitable answer from a list of options and edits it. Selection is done on the UI, and editing is done using a text box. The input is the answer options, and the output is the final edited response. For example, "There is a temporary problem with our delivery service" can be edited to "We apologize for the delay in delivery. There is currently a temporary problem with our delivery service."

[0118] Step 7:

[0119] The server generates additional service suggestions tailored to the company's size and business type. This step involves retrieving customer profiles and past purchase history from CRM systems such as Salesforce. The input is customer profile data, and the output is additional service suggestions. A specific example suggestion: "We offer a 20% discount coupon for your next order."

[0120] Step 8:

[0121] The user reviews the generated additional service suggestions and edits them as needed. The input is the suggestion data, and the output is the edited suggestion. For example, it is possible to change "20% discount coupon" to "30% discount coupon".

[0122] Step 9:

[0123] The user edits the response and additional suggestions, which are then sent to the customer as the final message. This sending process uses email service APIs such as SendGrid. The input is the edited response and additional suggestions, and the output is the final message sent to the customer. For example, a message such as, "We apologize for the delay in delivery. We are currently experiencing a temporary issue with our delivery service. As an apology, we are offering a 30% discount coupon for your next order," might be sent.

[0124] By following these steps, users can respond quickly and accurately, leading to increased customer satisfaction and sales.

[0125] (Application Example 1)

[0126] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0127] Modern content delivery services require prompt and appropriate responses to user problems and requests. However, previous systems had drawbacks, such as low efficiency, as they required a lot of manual work to analyze user requests, generate appropriate responses, and propose services tailored to the size and type of company. Furthermore, the lack of a good user interface and the difficulty in effectively utilizing natural language processing technology limited the improvement of user satisfaction.

[0128] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0129] In this invention, the server includes means for inputting the request content, means for analyzing the request content and generating appropriate answer candidates, means for selecting an answer from the generated answer candidates, means for editing the selected answer, means for generating suggestions and information on additional services according to the size and type of business, means for editing the suggestions and information on additional services, means for transmitting the answer and the suggestions and information on additional services, means for providing a user interface for inputting the request content and displaying and editing the answer, means for analyzing the request content using natural language processing technology and generating an appropriate answer by referring to specific documents or databases based on the analysis results, means for using a generation AI model to generate the answer, and means for displaying prompt sentences on the user interface to prompt user input. This enables efficient and automated user support.

[0130] "Request details" refers to the description of the problem or request entered by the user.

[0131] "Analysis" refers to the process of tokenizing and grammatically analyzing the request content entered by the user.

[0132] "Possible responses" are a selection of appropriate responses to the user's request.

[0133] A "user interface" is an interface through which users input their requests and view and edit analysis results and responses.

[0134] "Natural language processing technology" is a technology that analyzes user input and enables computers to understand language that humans speak naturally.

[0135] A "generative AI model" is an artificial intelligence algorithm that learns from past data and generates appropriate responses to user requests.

[0136] A "prompt message" is a sample sentence or input guidance displayed to encourage user input.

[0137] "Additional service proposals" refer to special services or promotions that are suggested based on the company's size, business type, and customer profile.

[0138] A "database" is a system that manages a collection of information, and it is used by the system to understand the content of a request.

[0139] "Editing" is the process of modifying or changing the generated answers or suggested additional services.

[0140] "Sending" refers to the act of sending a final response or proposal to the user or customer.

[0141] The embodiments for carrying out this invention will be described in detail. This system is for automating and streamlining user support in content distribution services. It is composed of the following roles: server, terminal, and user.

[0142] The server first provides a means for inputting the request details. This is an interface where the user inputs problems and requests, and it is embedded in devices such as smartphones, smart glasses, and robots using HTML, CSS, and JavaScript. The input data from this interface is sent to the server via an API.

[0143] Next, the server analyzes the received request using natural language processing technology (such as spaCy or NLTK). This involves tokenizing the request, performing grammatical analysis, and then extracting important keywords and phrases. For example, if the request is "the streaming stops midway," keywords such as "streaming," "midway," and "stop" will be extracted.

[0144] Subsequently, the server uses a generative AI model (e.g., TensorFlow) to generate candidate answers based on the analysis results. These models learn from past data and generate the best possible answers to the user's questions. For example, they might generate answers such as "Please check your network connection" or "Please update to the latest app version."

[0145] The generated response suggestions are sent from the server to the user interface. The user interface provides a means for the user to select a response suggestion and edit it as needed. For example, a text area can be used to allow the user to change the response "Please check your network connection" to "Could you please check your network connection?".

[0146] The server also generates suggestions and information for additional services tailored to the size and type of business. This is done by referencing customer profiles (such as viewing and purchase history). For example, suggestions such as "a 10% discount coupon for your next visit" may be generated. These suggestions are also displayed in the user interface and can be edited by the user.

[0147] Finally, the user's edited response and suggestions for additional services are sent from the server to the customer. This transmission is done using communication methods such as email or chat. For example, a message might be sent in the form of, "Thank you for letting us know about the issue with streaming stopping midway. We are currently asking you to check your network connection. You can also use a 10% discount coupon for your next order."

[0148] Examples of prompt messages used include the following:

[0149] "The streaming stops midway."

[0150] "I can't find the content I'm looking for."

[0151] "Please tell me how to use the app."

[0152] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0153] Step 1:

[0154] The terminal provides an interface for the user to input their request. The user enters the problem or request in the input field. The input data is sent to the server via the API in JSON format. For example, the user might enter "The streaming stops midway."

[0155] Step 2:

[0156] The server analyzes the received request using natural language processing techniques (e.g., spaCy or NLTK). Specifically, it tokenizes the input text, performs grammatical analysis, and extracts important keywords and phrases. In this case, the input data "streaming stops midway" is tokenized into "streaming," "midway," and "stop."

[0157] Step 3:

[0158] The server references databases and FAQ documents based on the analysis results and generates answer candidates using a generative AI model (e.g., TensorFlow). For example, it might generate answers such as "Please check your network connection" or "Please update to the latest app version."

[0159] Step 4:

[0160] The server sends the generated answer suggestions to the user interface. The user interface displays the answer suggestions to the user. At this time, the user interface displays a prompt message to encourage user feedback and editing. For example, the answer suggestion "Please check your network connection" might be displayed in the text area.

[0161] Step 5:

[0162] The user selects the most appropriate answer from the displayed options and edits it as needed. The edited answer is then sent back to the server. For example, "Please check your network connection" can be edited to "Could you please check your network connection?".

[0163] Step 6:

[0164] The server generates additional service suggestions based on the company's size and business type. To do this, it refers to customer profiles (such as viewing and purchase history) to determine appropriate suggestions. For example, it might generate a suggestion such as "a 10% discount coupon for your next visit."

[0165] Step 7:

[0166] The server sends the generated additional service suggestions to the user interface. The user interface displays them and allows the user to edit them. For example, the displayed "10% discount coupon" can be changed to a "15% discount coupon".

[0167] Step 8:

[0168] The user then reviews the edited response and any suggested additional services and sends them to the customer. The server then sends the reviewed information to the customer via email, chat, or other means of communication. For example, it might say, "Thank you for letting us know about the issue with the streaming stopping midway. We are currently asking you to check your network connection. You can also use a 10% discount coupon for your next order."

[0169] This series of processes allows users to respond to customers quickly and effectively.

[0170] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0171] The embodiments for carrying out the present invention will be described in detail. This invention combines a system that takes a request as input, analyzes it, generates appropriate response candidates, and also provides suggestions and information on additional services tailored to the size and type of company with an emotion engine that recognizes the user's emotions.

[0172] First, the user enters their request into the device. For example, they might enter, "My delivery is delayed. Please tell me the status." During this input process, the device uses its built-in emotion engine to recognize the user's emotions. This emotion information is extracted through voice and text analysis.

[0173] Next, the terminal sends emotional information along with the request to the server. The server analyzes the received request using natural language processing technology to understand its meaning and extract important keywords and phrases. For example, it identifies keywords such as "delivery," "delay," and "situation."

[0174] Based on the analysis results, the server uses a machine learning model to generate appropriate response candidates. This generation process also takes into account the user's sentiment information. For example, if sentiment data indicates the user is dissatisfied, responses that include an apology will be prioritized. For instance, a response such as "We are experiencing a temporary problem with our delivery service. We sincerely apologize" might be generated.

[0175] The server generates suggested responses, which are sent to the terminal and presented to the user. The user selects the most suitable response from the presented options and edits it as needed. For example, they might edit it to include specific wording such as, "We apologize for the delay in delivery. We are currently experiencing a temporary issue with our delivery service."

[0176] Next, the server generates additional service suggestions and information based on the customer profile, tailored to the company size and type of business. Sentimental information is also considered in this suggestion generation process, ensuring that the most appropriate suggestions are made in response to the user's emotions. For example, if the user appears very dissatisfied, a suggestion such as "We offer a 30% discount coupon for your next order" will be generated.

[0177] The generated additional suggestions and information are also sent to the user's device, where the user can review and edit them as needed. For example, it is possible to change a "30% discount coupon" to a "40% discount coupon."

[0178] Finally, the user sends their edited response and additional suggestions to the server via their device. The server receives this and sends the final response to the customer via email, chat, or other means. For example, it might say, "We apologize for the delay in delivery. We are currently experiencing a temporary issue with our delivery service. As an apology, we are offering a 40% discount coupon that can be used on your next order."

[0179] Thus, by combining the system of the present invention with an emotion engine, it is possible to achieve prompt and appropriate customer service that takes customer emotions into consideration, thereby improving customer satisfaction and corporate sales.

[0180] The following describes the processing flow.

[0181] Step 1:

[0182] The user enters their request into the terminal. The input interface of the terminal will contain a request such as, "My product delivery is delayed. Please tell me the status." The terminal is also equipped with an emotion engine that recognizes the user's emotions during input through voice and facial expression analysis. It also analyzes emotions from text input.

[0183] Step 2:

[0184] The terminal sends the entered request details and emotional information to the server. This data is transmitted using a secure communication protocol, ensuring data security.

[0185] Step 3:

[0186] The server analyzes the received request using natural language processing technology. Specifically, it breaks down the input request into tokens and analyzes its grammatical structure. It extracts important keywords and phrases and identifies elements such as "delivery," "delay," and "situation."

[0187] Step 4:

[0188] The server generates appropriate response options based on the analyzed request content and sentiment information. This process references internal databases and FAQ documents. For example, if dissatisfaction is detected, a response option including an apology, such as "We are experiencing a temporary problem with our delivery service. We sincerely apologize," will be generated.

[0189] Step 5:

[0190] The server sends the generated answer candidates to the terminal. The terminal displays the received answer candidates in the user interface, presenting the user with multiple answer options.

[0191] Step 6:

[0192] The user selects the most suitable answer from the suggested answers displayed on their device. After selection, they can edit the selected answer as needed. For example, they can change the answer "There is a temporary problem with our delivery service" to a more specific wording such as "We apologize for the delay in delivery. There is currently a temporary problem with our delivery service."

[0193] Step 7:

[0194] The server receives the user's edited responses and, referencing the customer profile, generates additional service suggestions and information tailored to the company's size and business type. Sentimental information is also considered, ensuring that the most appropriate suggestions are made based on the user's emotions. For example, if the user appears very dissatisfied, additional suggestions including a perk such as "We'll provide you with a 30% discount coupon for your next order" are generated.

[0195] Step 8:

[0196] The server sends additional suggestions and information it generates to the user's terminal, where the user can review and edit them. For example, the user can edit an additional suggestion, such as changing a "30% discount coupon" to a "40% discount coupon."

[0197] Step 9:

[0198] The user sends their final edited response and additional suggestions to the server via their device. The server receives this and sends the final response to the customer via a communication method such as email or chat. For example, the customer might receive a message such as, "We apologize for the delay in delivery. We are currently experiencing a temporary issue with our delivery service. As an apology, we are offering a 40% discount coupon that can be used on your next order."

[0199] In this way, by combining an emotion engine, the system provides quick and appropriate responses that take customer emotions into account, resulting in increased customer satisfaction and improved company sales.

[0200] (Example 2)

[0201] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0202] Traditional customer service systems simply process customer requests without considering customer emotions. This makes it difficult to achieve sufficient customer satisfaction, hindering the company's ability to build trust and increase sales.

[0203] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for analyzing the request content and generating appropriate response candidates, means for recognizing the user's emotions, and means for generating response candidates while considering the emotional information. This enables a quick and appropriate response that takes into account the customer's emotions, thereby improving customer satisfaction and enhancing the company's credibility.

[0204] "Request details" refer to the information and requirements that the user enters into the system.

[0205] "Emotional information" refers to data obtained by analyzing a user's emotions and feelings.

[0206] "Natural language processing technology" is a technology that analyzes text data and helps it understand meaning and context.

[0207] A "machine learning model" is an algorithm or framework that learns from data and performs predictions and classifications.

[0208] "Possible responses" refer to appropriate replies or suggested actions in response to a request.

[0209] "Company size and type" refers to the size of a company (for example, a small or medium-sized enterprise, or a large corporation) and its business operations.

[0210] A "customer profile" is data that records a customer's personal information, purchase history, preferences, and other details.

[0211] A "proposal for additional services" refers to a proposal for additional services or benefits that a company can offer.

[0212] A "system" is a set of devices or programs designed to achieve a specific purpose.

[0213] A "user" is an individual or organization that uses the system to input request details.

[0214] A "server" is the central device of a system, responsible for processing and managing data.

[0215] Modes for carrying out the invention

[0216] The system of the present invention analyzes the user's request, generates appropriate response candidates that take emotional information into consideration, and proposes additional services tailored to the size and type of business. The embodiments for carrying out the present invention are described in detail below.

[0217] System Configuration

[0218] This system broadly includes the following main components:

[0219] A means (terminal) for entering request details.

[0220] A means of recognizing user emotions (emotion engine)

[0221] A method (server) for analyzing request content using natural language processing technology.

[0222] A method (server) for generating answer candidates using a machine learning model.

[0223] A server for generating proposals for additional services tailored to the size and type of business.

[0224] Means for transmitting and receiving various types of data (terminals, servers)

[0225] Hardware and software configuration

[0226] The following hardware and software will be used to implement this system.

[0227] Terminal: A device used by users to input request details. This includes personal computers and smartphones.

[0228] Emotion engine: Software used to recognize user emotions. Examples include IBM Watson® Tone Analyzer and Microsoft® Text Analytics.

[0229] Server: A device that analyzes the request content and generates answer candidates and additional service suggestions. It can use Google® Cloud Natural Language API to implement natural language processing technology and OpenAI® GPT series for answer candidate generation.

[0230] Communication method: Internet connection for data transmission between terminal and server.

[0231] Data processing and data calculation

[0232] The operation of this system follows the steps below.

[0233] 1. Enter the request details and emotional information:

[0234] The user enters their request details into their device. During this process, an emotion engine is used to analyze and recognize the user's emotional information.

[0235] 2. Sending data:

[0236] The device sends the request details and sentiment information to the server. This data is transmitted securely using a standard communication protocol (e.g., HTTPS).

[0237] 3. Analysis using natural language processing:

[0238] The server analyzes the received request using natural language processing technology and extracts important keywords and phrases.

[0239] 4. Generating answer candidates:

[0240] Based on the analyzed keywords and sentiment information, the server uses a machine learning model (e.g., OpenAI's GPT series) to generate appropriate response candidates. The generated response candidates take the user's sentiment into account; for example, if the user expresses dissatisfaction, a response including an apology will be provided.

[0241] 5. Generating proposals for additional services:

[0242] Based on the company profile, the server generates suggestions and information for additional services tailored to the company's size and business type. Sentimental information is also taken into consideration; for example, if a user is highly dissatisfied, a suggestion such as "We will provide you with a 30% discount coupon that you can use on your next order" will be generated.

[0243] Specific examples and prompt statements

[0244] To illustrate the specific operation, the following are examples of concrete actions and prompt statements.

[0245] Specific example:

[0246] User input: "My order is delayed. Please tell me the status."

[0247] Emotion engine's recognition result: "Dissatisfaction"

[0248] Keyword extraction using natural language processing: "delivery," "delay," "situation"

[0249] Suggested response: "We are experiencing a temporary issue with our delivery service. We sincerely apologize."

[0250] Example of a prompt:

[0251] "Your delivery is delayed. Please let me know the status."

[0252] "There is an error in the invoice. Please check it."

[0253] "My ordered item hasn't arrived yet. What's going on?"

[0254] "The service wasn't what I expected. Why?"

[0255] Based on the above explanation, this system can provide prompt and appropriate customer service that takes user emotions into consideration, thereby improving customer satisfaction, corporate credibility, and sales.

[0256] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0257] Step 1:

[0258] The user enters their request into the terminal. For example, they might enter, "My product delivery is delayed. Please tell me the status." This input data becomes the starting point for the system's processing.

[0259] Step 2:

[0260] The terminal uses an emotion engine to recognize the user's emotions based on the input request. Examples of emotion engines used include IBM Watson Tone Analyzer and Microsoft Text Analytics. At this stage, the request content is passed to the emotion engine as input data, and emotion information such as "dissatisfied" is obtained as output.

[0261] Step 3:

[0262] The terminal sends the entered request details and recognized emotion information to the server. The data is sent, for example, via the HTTPS protocol. The input data consists of the request details and emotion information, and the output is the transmission of data to the server.

[0263] Step 4:

[0264] The server analyzes the received request using natural language processing technology. One example of this technology is the Google Cloud Natural Language API. The input data is the request content, and the output is important keywords and phrases (e.g., "delivery," "delay," "status").

[0265] Step 5:

[0266] The server uses the analyzed keywords and sentiment information to generate appropriate response candidates using a machine learning model (e.g., OpenAI's GPT series). The input data consists of keywords and sentiment information, and the output is the generated response candidates (e.g., "We are experiencing a temporary problem with our delivery service. We sincerely apologize.").

[0267] Step 6:

[0268] The server sends the generated answer candidates to the terminal. The input data is the answer candidates, and the output is the transmission of data to the terminal.

[0269] Step 7:

[0270] The user reviews the suggested answers presented on their device and edits them as needed. The input data is the presented answer candidates, and the output is the user's final edited answer (e.g., "We apologize for the delay in delivery. We are currently experiencing a temporary issue with our delivery service.").

[0271] Step 8:

[0272] After the server receives the edited response, it generates additional service suggestions tailored to the company size and type based on the customer profile. The input data is the edited response and customer profile, and the output is the generated additional suggestion (e.g., "We'll give you a 30% discount coupon for your next order").

[0273] Step 9:

[0274] The server sends the generated additional suggestions to the terminal and presents them to the user. The input data is the additional suggestions, and the output is the data transmission to the terminal.

[0275] Step 10:

[0276] Users can review the presented additional suggestions and edit them as needed. The input data is the presented additional suggestions, and the output is the final suggestion edited by the user (e.g., "40% discount coupon").

[0277] Step 11:

[0278] The user submits their final edited response and suggestions to the server. The input data is the final response and suggestions, and the output is the data submission to the server.

[0279] Step 12:

[0280] The server sends the final response to the customer. The final response is delivered to the customer via communication methods such as email or chat. The input data is the final response and proposal, and the output is what is sent to the customer. For example, it might say, "We apologize for the delay in delivery. We are currently experiencing a temporary problem with our delivery service. As an apology, we are offering a 40% discount coupon that can be used on your next order."

[0281] (Application Example 2)

[0282] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0283] In the conventional customer support system, there was a limit in generating an appropriate response to the request content, and there was a problem that it was particularly difficult to respond according to the user's emotions. Also, it was difficult to provide appropriate additional proposals and information, and there was a lack of means to improve customer satisfaction. As a result, customer dissatisfaction accumulated, which could have a negative impact on the company's sales and brand image.

[0284] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0285] In this invention, the server includes means for inputting the request content, means for recognizing the user's emotion based on the request content, means for analyzing the request content and generating appropriate answer candidates, means for selecting an answer from the generated answer candidates, means for editing the selected answer, means for generating additional proposals and information according to the company scale and business type, means for editing the additional proposals and information, and means for transmitting the answer and the additional proposals and information. Thereby, it becomes possible to quickly and appropriately respond to customers according to the user's emotions, and it becomes possible to improve customer satisfaction and the company's sales.

[0286] The "request content" refers to the information that the user requests regarding the service or product and the requests for problem-solving.

[0287] The "means for recognizing emotion" refers to a technology having a function of analyzing an emotional state from the user's input content and determining a specific emotion (such as joy, anger, sadness, etc.).

[0288] The "means for generating answer candidates" refers to an analysis engine or algorithm used to list a plurality of appropriate responses to the request content.

[0289] The "means for selecting an answer" refers to an interface or function for selecting the most appropriate one from the generated answer candidates.

[0290] "Means for editing answers" refers to a function that allows users to modify or change selected answers as appropriate.

[0291] "Means for generating additional suggestions and information" refers to analytical engines and algorithms for generating and providing services and information tailored to the size and type of business of the company.

[0292] "Means for editing additional suggestions and information" refers to functions that allow users to modify or change generated additional suggestions and information as needed.

[0293] "Means of transmission" refers to communication functions used to convey generated responses and additional suggestions to users and customers.

[0294] "Natural language processing technology" refers to technologies that understand and analyze human language and perform appropriate information processing based on that understanding.

[0295] A "machine learning model" refers to artificial intelligence technology that learns from large amounts of data to solve problems and make predictions.

[0296] A "customer profile" refers to a database that includes customer behavior history and attribute information.

[0297] "Food delivery" refers to a service that delivers food and beverages to a specific location.

[0298] This invention is a system that provides prompt and appropriate customer service in the food delivery field, taking into account the user's emotions. As mentioned above, this system handles the input of the request, recognition of emotions, generation of appropriate response candidates, and generation of additional suggestions and information.

[0299] Specifically, the process begins with the user entering their request using a smartphone or other device, and the system receiving this information. For example, the user might enter, "My pizza order is late and I'm getting frustrated. Please tell me what's happening." Based on this request, the system's emotion recognition engine analyzes the user's emotions and extracts emotional information.

[0300] The analyzed sentiment information and request details are sent to the server. The server uses natural language processing techniques to analyze the request details and extract key keywords. This process utilizes the Python TextBlob library. For example, keywords such as "order," "pizza," "delay," and "situation" are identified.

[0301] Next, the server uses Hugging Face's sentiment analysis model to analyze the user's emotional information. After identifying the emotion, the server uses a machine learning model to generate appropriate response candidates. In this process, the user's emotional information is given special consideration, resulting in responses such as, "We apologize for the delay in delivery. We are currently investigating the situation."

[0302] The suggested answers are sent to the user's device, where they can review and edit them as needed. This editing function allows users to modify the suggested answers as appropriate and optimize them for submission.

[0303] Subsequently, the server generates additional suggestions tailored to the company size and industry based on the customer profile and user sentiment information. This may include information such as, "We offer a 30% discount coupon that can be used on your next order."

[0304] The generated additional suggestions and information are sent back to the user's device, where the user reviews and edits them as needed. The final response and additional suggestions are then sent to the customer via the server.

[0305] In summary, this system effectively combines an emotion recognition engine, natural language processing, and a machine learning model to quickly provide responses that meet customer needs and improve customer satisfaction. The main hardware and software used include Python, TextBlob, Hugging Face Transformers, smartphones, etc.

[0306] Specific examples of prompt sentences include:

[0307] "The pizza order is late. Please let me know the situation."

[0308] "Two hours have passed since I placed the order, but it hasn't arrived yet. Why?"

[0309] "If the delivery is delayed, I would like to be informed."

[0310] As described above, the system of the present invention aims to realize responses that take into account the emotions of customers and improve the quality of customer service in the food delivery field.

[0311] The flow of the specific process in Application Example 2 will be described using FIG. 14.

[0312] Step 1:

[0313] The user inputs the request content using a terminal such as a smartphone. The input content describes the problem or request in text or voice format. For example, the content "I'm frustrated because the ordered pizza is late. Please let me know the situation." is input.

[0314] Input: User request content (text or voice)

[0315] Output: Input request content

[0316] Step 2:

[0317] The terminal receives the input request and analyzes the user's emotions using an emotion recognition engine. This analysis employs algorithms that extract emotions from voice and text. For example, the emotion "irritated" might be identified.

[0318] Input: User's request (text or voice)

[0319] Output: Analyzed sentiment information

[0320] Step 3:

[0321] The terminal sends the analyzed sentiment information and request details to the server. The server analyzes the request details using natural language processing techniques and extracts important keywords and phrases. For example, keywords such as "order," "pizza," and "delay" may be identified.

[0322] Input: Request details and emotional information

[0323] Output: Analyzed keywords and phrases

[0324] Step 4:

[0325] The server generates appropriate response candidates based on keywords and sentiment information analyzed using a machine learning model. Sentiment information is given particular consideration, and responses including apologies are prioritized if dissatisfaction is strong. For example, a response such as "We apologize for the delay in delivery. We are currently investigating the situation" might be generated.

[0326] Input: Analyzed keywords and sentiment information

[0327] Output: Generated answer candidates

[0328] Step 5:

[0329] The server sends the generated response options to the terminal. The user reviews the suggested responses and modifies / edits them as needed. For example, they might edit them to include more specific wording, such as "We are currently checking the delivery status."

[0330] Input: Generated answer suggestions

[0331] Output: User-edited response

[0332] Step 6:

[0333] Next, the server generates additional suggestions and information tailored to the company size and type, based on customer profiles and user sentiment information. For example, it might generate a suggestion such as, "We'll give you a 30% discount coupon for your next order."

[0334] Input: Customer profile and sentiment information

[0335] Output: Generated additional suggestions and information

[0336] Step 7:

[0337] The server sends the generated additional suggestions and information to the terminal, where the user reviews and edits them as needed. For example, they might change "30% discount coupon" to "40% discount coupon."

[0338] Input: Generated additional suggestions and information

[0339] Output: Additional suggestions and information edited by the user.

[0340] Step 8:

[0341] Finally, the user's edited response and additional suggestions are sent to the server, which receives them and forwards them to the customer via email, chat, or other methods. For example, a message might be sent saying, "We apologize for the delay in delivery. We are currently experiencing a temporary issue with our delivery service. As an apology, we will provide you with a 40% discount coupon for your next order."

[0342] Input: User-edited answers and additional suggestions

[0343] Output: Final response and additional suggestions (to be sent to the customer)

[0344] Through the steps outlined above, prompt and appropriate customer service that takes user emotions into consideration is achieved.

[0345] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0346] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0347] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0348] [Second Embodiment]

[0349] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0350] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0351] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0352] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0353] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0354] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0355] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0356] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0357] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0358] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0359] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0360] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0361] The embodiments for carrying out this invention will now be described. The system of the invention begins by providing a terminal with an interface for the user to input the details of a customer's request. The request details entered into the terminal are transmitted to a server.

[0362] The server analyzes the received request using natural language processing techniques. This analysis step involves tokenizing and grammatically analyzing the request to extract important keywords and phrases. For example, a request like "My product delivery is delayed. Please tell me the status" is broken down into keywords such as "delivery," "delay," and "status."

[0363] Next, the server generates appropriate answer candidates based on the analyzed keywords and request details. This involves referencing internal databases and FAQ documents, and utilizing a machine learning model. This machine learning model learns from past responses to similar inquiries, enabling it to generate the most appropriate answer. For example, it might generate answers such as "There is a temporary problem with the delivery service" and "The reason for the delay in product delivery is insufficient stock."

[0364] The generated response options are displayed on the user's device. The user selects the most appropriate response from these options. After selection, the user can edit the response. For example, the response "There is a temporary problem with the delivery service" can be edited to "We apologize for the delay in delivery. There is currently a temporary problem with the delivery service."

[0365] Subsequently, the server generates suggestions and information for additional services tailored to the company's size and business type. In this step, it refers to the customer profile and makes optimal suggestions based on past purchase history and company characteristics. For example, it might generate a suggestion such as, "We'll provide you with a 20% discount coupon that you can use on your next order."

[0366] The generated additional service suggestions and information are also presented on the user's device, allowing the user to review and edit them as needed. For example, it is possible to change a "20% discount coupon" to a "30% discount coupon."

[0367] Finally, the user sends the edited response and additional suggestions to the customer. This sending process uses communication methods such as email or chat, which the server uses. For example, it might say, "We apologize for the delay in delivery. We are currently experiencing a temporary issue with our delivery service. As an apology, we are offering a 30% discount coupon that can be used on your next order."

[0368] In this way, the system of the present invention enables prompt and appropriate customer service, thereby improving customer satisfaction and sales.

[0369] The following describes the processing flow.

[0370] Step 1:

[0371] The user enters their request into the terminal. For example, they might enter a request such as, "My product delivery is delayed. Please tell me the status." This input is done through the interface on the terminal.

[0372] Step 2:

[0373] The terminal sends the request details entered by the user to the server. This transmission is done via an API and uses a secure communication protocol.

[0374] Step 3:

[0375] The server analyzes the received request using natural language processing techniques. Specifically, it breaks down the request into tokens, performs grammatical analysis, and extracts keywords and important phrases. For example, it identifies keywords such as "delivery," "delay," and "situation."

[0376] Step 4:

[0377] Based on the keywords analyzed by the server, it generates appropriate answer candidates. In this process, the server refers to an internal database and FAQ documents and uses a machine learning model to generate answer candidates. Examples of generated answers include "The reason for the delay in product delivery is insufficient stock" and "There is a temporary problem with the delivery service."

[0378] Step 5:

[0379] The server sends the generated answer candidates to the terminal. The terminal receives them and displays them in the user interface. The user reviews the multiple answer candidates presented.

[0380] Step 6:

[0381] The user selects the answer they deem most appropriate on their device. After selecting, the user can edit the selected answer as needed. For example, they might edit the answer "There is a temporary problem with our delivery service" to "We apologize for the delay in delivery. There is currently a temporary problem with our delivery service."

[0382] Step 7:

[0383] The server receives the edited response and, referencing the customer profile, generates additional service suggestions and information tailored to the company size and type. For example, if the customer is a small business, it might generate a suggestion such as, "We'll give you a 20% discount coupon for your next order."

[0384] Step 8:

[0385] The server sends additional suggestions and information it generates to the user's terminal, where the user can review and edit them. For example, a "20% discount coupon" can be changed to a "30% discount coupon."

[0386] Step 9:

[0387] The user sends their final edited response and additional suggestions to the server via their device. The server receives this and sends the final response to the customer via email, chat, or other means. For example, it might say, "We apologize for the delay in delivery. We are currently experiencing a temporary issue with our delivery service. As an apology, we are offering a 30% discount coupon for your next order."

[0388] In this way, the system enables quick and appropriate customer service, contributing to increased customer satisfaction and improved company sales.

[0389] (Example 1)

[0390] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0391] In today's business environment, responding quickly and appropriately to a wide range of customer inquiries is crucial for improving customer satisfaction and maintaining a company's competitiveness. However, efficiently handling a large volume of inquiries requires an automated response system utilizing advanced natural language processing technology and machine learning models. Furthermore, providing proposals and services tailored to individual customer needs necessitates a flexible system based on the company's size, industry, and customer profile. Developing a system that meets these diverse requirements remains challenging, and many companies have yet to implement one effectively.

[0392] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0393] In this invention, the server includes means for inputting the request details, means for analyzing the request details and generating appropriate response candidates, means for selecting a response from the generated response candidates, means for editing the selected response, means for generating suggestions and information on additional services according to the size and type of business, means for editing the suggestions and information on additional services, and means for transmitting the response and the suggestions and information on additional services. This enables prompt and appropriate customer service.

[0394] "Request details" refers to information about inquiries and requests received by the user from customers.

[0395] "Means of input" refers to the interface or device used by the user to input the details of their request into the system, as well as the method of operating it.

[0396] "Means of analysis" refers to the process and techniques used to analyze the received request using language processing technology and extract the necessary information.

[0397] "Response candidates" refer to several appropriate response options generated based on the analyzed request.

[0398] "Means of selection" refers to the interface or method that allows the user to choose the most suitable response from among the generated candidate responses.

[0399] "Means of editing" refer to tools and functions that allow users to modify or supplement selected responses as appropriate.

[0400] "Proposal for additional services" refers to additional services or offers provided based on customer needs, company size, and business type.

[0401] "Means of generating information" refers to processes and technologies for automatically creating suggestions for additional services and other related information.

[0402] "Means of transmission" refers to the means or methods of communication used to deliver the final edited response or additional service suggestions to the customer.

[0403] "Natural language processing technology" refers to the technology used by computers to understand and analyze natural language and extract relevant information.

[0404] A "machine learning model" is an algorithm that learns patterns based on past data and uses that knowledge to perform inferences and predictions on new data.

[0405] A "customer profile" refers to detailed information about individual customers, such as their past purchase history and behavioral data.

[0406] The system according to this invention provides a comprehensive solution for responding quickly and appropriately to customer inquiries. Specific embodiments of this system are described below.

[0407] First, a terminal is provided that offers an interface for users to input the details of requests received from customers. This interface is built as a web application using HTML and JavaScript. Through this interface, users input the request details in text format. For example, "The delivery of the product is delayed. Please let me know the status."

[0408] The request details entered on the terminal are sent to the server via the internet. The HTTPS protocol is used for this communication, ensuring secure data transfer. Specifically, an Ajax request is generated, and data is sent in JSON format, as shown below.

[0409] json

[0410] {

[0411] "request": "My order is delayed. Please tell me the status."

[0412] }

[0413] The request content that reaches the server is analyzed using natural language processing (NLP) technology. This analysis uses spaCy, a Python NLP library, to tokenize the request content, perform grammatical analysis, and extract important keywords. For example, when tokenizing "My product delivery is delayed. Please tell me the status," the tokens would be "product," "delivery," "delay," "status," and "tell me."

[0414] Next, the server generates appropriate response candidates based on the analyzed keywords and request details. At this stage, it refers to internal databases and FAQ documents, and uses machine learning models. Specifically, it uses machine learning libraries such as TensorFlow and scikit-learn, and models trained on historical data generate the best response. Examples of generated responses include "There is a temporary problem with the delivery service" and "The reason for the delay in product delivery is insufficient stock."

[0415] Once answer suggestions are generated, the server sends them to the user's device. The user reviews the suggested answers on their device and selects the most appropriate one. Furthermore, the user can edit their selected answer. For example, they can change the answer "There is a temporary problem with the delivery service" to "We apologize for the delay in delivery. There is currently a temporary problem with the delivery service."

[0416] In addition, the server generates suggestions for additional services tailored to the company's size and business type. This suggestion generation is performed by retrieving data from CRM systems such as Salesforce, based on customer profiles and past purchase history. Specific examples of suggestions include, "We'll provide you with a 20% discount coupon for your next order." Users can also edit the generated additional suggestions.

[0417] Finally, the user sends the edited response and additional suggestions to the customer. This sending process utilizes email and chat tool APIs. For example, the SendGrid API might be used to send a final message like the following:

[0418] "We sincerely apologize for the delay in delivery. We are currently experiencing a temporary issue with our delivery service. As an apology, we are offering a 30% discount coupon that can be used on your next order."

[0419] This system allows users to respond quickly and accurately, leading to increased customer satisfaction and sales.

[0420] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0421] Step 1:

[0422] The user enters customer requests using their device. The interface is built as a web application, and the user enters the request details into a text box. For example, they might enter, "The product delivery is delayed. Please let me know the status."

[0423] Step 2:

[0424] The terminal sends the entered request details to the server. HTTPS protocol is used for communication, and an Ajax request is generated. The input is in text format and is converted to JSON format upon transmission. Specific request example:

[0425] json

[0426] {

[0427] "request": "My order is delayed. Please tell me the status."

[0428] }

[0429] The output is the data packet sent to the server.

[0430] Step 3:

[0431] The server analyzes the received request using natural language processing techniques. The library used is spaCy in Python, which performs tokenization and grammatical analysis. The input is the request content in JSON format, and the output is extracted keywords. For example, if the input sentence "The delivery of my product is delayed. Please tell me the status" is analyzed, the output will be tokenized as "product", "delivery", "delay", "status", and "tell me".

[0432] Step 4:

[0433] The server generates appropriate answer candidates based on the analyzed keywords and request details. It references an internal database and FAQ documentation and runs a machine learning model using TensorFlow. The input is tokenized keywords, and the output is multiple answer candidates. For example, it might generate answers such as "There is a temporary problem with the delivery service" or "The reason for the delay in product delivery is insufficient stock."

[0434] Step 5:

[0435] The server sends the generated answer suggestions to the user's device. The user's device displays the answer suggestions and provides a confirmation UI. The input is the answer suggestion data, and the output is the confirmation screen the user can view. Specific UI example:

[0436] Option 1: "There is a temporary issue with our delivery service."

[0437] Option 2: "The reason for the delay in product delivery is a shortage of stock."

[0438] Step 6:

[0439] The user selects the most suitable answer from a list of options and edits it. Selection is done on the UI, and editing is done using a text box. The input is the answer options, and the output is the final edited response. For example, "There is a temporary problem with our delivery service" can be edited to "We apologize for the delay in delivery. There is currently a temporary problem with our delivery service."

[0440] Step 7:

[0441] The server generates additional service suggestions tailored to the company's size and business type. This step involves retrieving customer profiles and past purchase history from CRM systems such as Salesforce. The input is customer profile data, and the output is additional service suggestions. A specific example suggestion: "We offer a 20% discount coupon for your next order."

[0442] Step 8:

[0443] The user reviews the generated additional service suggestions and edits them as needed. The input is the suggestion data, and the output is the edited suggestion. For example, it is possible to change "20% discount coupon" to "30% discount coupon".

[0444] Step 9:

[0445] The user edits the response and additional suggestions, which are then sent to the customer as the final message. This sending process uses email service APIs such as SendGrid. The input is the edited response and additional suggestions, and the output is the final message sent to the customer. For example, a message such as, "We apologize for the delay in delivery. We are currently experiencing a temporary issue with our delivery service. As an apology, we are offering a 30% discount coupon for your next order," might be sent.

[0446] By following these steps, users can respond quickly and accurately, leading to increased customer satisfaction and sales.

[0447] (Application Example 1)

[0448] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0449] Modern content delivery services require prompt and appropriate responses to user problems and requests. However, previous systems had drawbacks, such as low efficiency, as they required a lot of manual work to analyze user requests, generate appropriate responses, and propose services tailored to the size and type of company. Furthermore, the lack of a good user interface and the difficulty in effectively utilizing natural language processing technology limited the improvement of user satisfaction.

[0450] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0451] In this invention, the server includes means for inputting the request content, means for analyzing the request content and generating appropriate answer candidates, means for selecting an answer from the generated answer candidates, means for editing the selected answer, means for generating suggestions and information on additional services according to the size and type of business, means for editing the suggestions and information on additional services, means for transmitting the answer and the suggestions and information on additional services, means for providing a user interface for inputting the request content and displaying and editing the answer, means for analyzing the request content using natural language processing technology and generating an appropriate answer by referring to specific documents or databases based on the analysis results, means for using a generation AI model to generate the answer, and means for displaying prompt sentences on the user interface to prompt user input. This enables efficient and automated user support.

[0452] "Request details" refers to the description of the problem or request entered by the user.

[0453] "Analysis" refers to the process of tokenizing and grammatically analyzing the request content entered by the user.

[0454] "Possible responses" are a selection of appropriate responses to the user's request.

[0455] A "user interface" is an interface through which users input their requests and view and edit analysis results and responses.

[0456] "Natural language processing technology" is a technology that analyzes user input and enables computers to understand language that humans speak naturally.

[0457] A "generative AI model" is an artificial intelligence algorithm that learns from past data and generates appropriate responses to user requests.

[0458] A "prompt message" is a sample sentence or input guidance displayed to encourage user input.

[0459] "Additional service proposals" refer to special services or promotions that are suggested based on the company's size, business type, and customer profile.

[0460] A "database" is a system that manages a collection of information, and it is used by the system to understand the content of a request.

[0461] "Editing" is the process of modifying or changing the generated answers or suggested additional services.

[0462] "Sending" refers to the act of sending a final response or proposal to the user or customer.

[0463] The embodiments for carrying out this invention will be described in detail. This system is for automating and streamlining user support in content distribution services. It is composed of the following roles: server, terminal, and user.

[0464] The server first provides a means for inputting the request details. This is an interface where the user inputs problems and requests, and it is embedded in devices such as smartphones, smart glasses, and robots using HTML, CSS, and JavaScript. The input data from this interface is sent to the server via an API.

[0465] Next, the server analyzes the received request using natural language processing technology (such as spaCy or NLTK). This involves tokenizing the request, performing grammatical analysis, and then extracting important keywords and phrases. For example, if the request is "the streaming stops midway," keywords such as "streaming," "midway," and "stop" will be extracted.

[0466] Subsequently, the server uses a generative AI model (e.g., TensorFlow) to generate candidate answers based on the analysis results. These models learn from past data and generate the best possible answers to the user's questions. For example, they might generate answers such as "Please check your network connection" or "Please update to the latest app version."

[0467] The generated response suggestions are sent from the server to the user interface. The user interface provides a means for the user to select a response suggestion and edit it as needed. For example, a text area can be used to allow the user to change the response "Please check your network connection" to "Could you please check your network connection?".

[0468] The server also generates suggestions and information for additional services tailored to the size and type of business. This is done by referencing customer profiles (such as viewing and purchase history). For example, suggestions such as "a 10% discount coupon for your next visit" may be generated. These suggestions are also displayed in the user interface and can be edited by the user.

[0469] Finally, the user's edited response and suggestions for additional services are sent from the server to the customer. This transmission is done using communication methods such as email or chat. For example, a message might be sent in the form of, "Thank you for letting us know about the issue with streaming stopping midway. We are currently asking you to check your network connection. You can also use a 10% discount coupon for your next order."

[0470] Examples of prompt messages used include the following:

[0471] "The streaming stops midway."

[0472] "I can't find the content I'm looking for."

[0473] "Please tell me how to use the app."

[0474] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0475] Step 1:

[0476] The terminal provides an interface for the user to input their request. The user enters the problem or request in the input field. The input data is sent to the server via the API in JSON format. For example, the user might enter "The streaming stops midway."

[0477] Step 2:

[0478] The server analyzes the received request using natural language processing techniques (e.g., spaCy or NLTK). Specifically, it tokenizes the input text, performs grammatical analysis, and extracts important keywords and phrases. In this case, the input data "streaming stops midway" is tokenized into "streaming," "midway," and "stop."

[0479] Step 3:

[0480] The server references databases and FAQ documents based on the analysis results and generates answer candidates using a generative AI model (e.g., TensorFlow). For example, it might generate answers such as "Please check your network connection" or "Please update to the latest app version."

[0481] Step 4:

[0482] The server sends the generated answer suggestions to the user interface. The user interface displays the answer suggestions to the user. At this time, the user interface displays a prompt message to encourage user feedback and editing. For example, the answer suggestion "Please check your network connection" might be displayed in the text area.

[0483] Step 5:

[0484] The user selects the most appropriate answer from the displayed options and edits it as needed. The edited answer is then sent back to the server. For example, "Please check your network connection" can be edited to "Could you please check your network connection?".

[0485] Step 6:

[0486] The server generates additional service suggestions based on the company's size and business type. To do this, it refers to customer profiles (such as viewing and purchase history) to determine appropriate suggestions. For example, it might generate a suggestion such as "a 10% discount coupon for your next visit."

[0487] Step 7:

[0488] The server sends the generated additional service suggestions to the user interface. The user interface displays them and allows the user to edit them. For example, the displayed "10% discount coupon" can be changed to a "15% discount coupon".

[0489] Step 8:

[0490] The user then reviews the edited response and any suggested additional services and sends them to the customer. The server then sends the reviewed information to the customer via email, chat, or other means of communication. For example, it might say, "Thank you for letting us know about the issue with the streaming stopping midway. We are currently asking you to check your network connection. You can also use a 10% discount coupon for your next order."

[0491] This series of processes allows users to respond to customers quickly and effectively.

[0492] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0493] The embodiments for carrying out the present invention will be described in detail. This invention combines a system that takes a request as input, analyzes it, generates appropriate response candidates, and also provides suggestions and information on additional services tailored to the size and type of company with an emotion engine that recognizes the user's emotions.

[0494] First, the user enters their request into the device. For example, they might enter, "My delivery is delayed. Please tell me the status." During this input process, the device uses its built-in emotion engine to recognize the user's emotions. This emotion information is extracted through voice and text analysis.

[0495] Next, the terminal sends emotional information along with the request to the server. The server analyzes the received request using natural language processing technology to understand its meaning and extract important keywords and phrases. For example, it identifies keywords such as "delivery," "delay," and "situation."

[0496] Based on the analysis results, the server uses a machine learning model to generate appropriate response candidates. This generation process also takes into account the user's sentiment information. For example, if sentiment data indicates the user is dissatisfied, responses that include an apology will be prioritized. For instance, a response such as "We are experiencing a temporary problem with our delivery service. We sincerely apologize" might be generated.

[0497] The server generates suggested responses, which are sent to the terminal and presented to the user. The user selects the most suitable response from the presented options and edits it as needed. For example, they might edit it to include specific wording such as, "We apologize for the delay in delivery. We are currently experiencing a temporary issue with our delivery service."

[0498] Next, the server generates additional service suggestions and information based on the customer profile, tailored to the company size and type of business. Sentimental information is also considered in this suggestion generation process, ensuring that the most appropriate suggestions are made in response to the user's emotions. For example, if the user appears very dissatisfied, a suggestion such as "We offer a 30% discount coupon for your next order" will be generated.

[0499] The generated additional suggestions and information are also sent to the user's device, where the user can review and edit them as needed. For example, it is possible to change a "30% discount coupon" to a "40% discount coupon."

[0500] Finally, the user sends their edited response and additional suggestions to the server via their device. The server receives this and sends the final response to the customer via email, chat, or other means. For example, it might say, "We apologize for the delay in delivery. We are currently experiencing a temporary issue with our delivery service. As an apology, we are offering a 40% discount coupon that can be used on your next order."

[0501] Thus, by combining the system of the present invention with an emotion engine, it is possible to achieve prompt and appropriate customer service that takes customer emotions into consideration, thereby improving customer satisfaction and corporate sales.

[0502] The following describes the processing flow.

[0503] Step 1:

[0504] The user enters their request into the terminal. The input interface of the terminal will contain a request such as, "My product delivery is delayed. Please tell me the status." The terminal is also equipped with an emotion engine that recognizes the user's emotions during input through voice and facial expression analysis. It also analyzes emotions from text input.

[0505] Step 2:

[0506] The terminal sends the entered request details and emotional information to the server. This data is transmitted using a secure communication protocol, ensuring data security.

[0507] Step 3:

[0508] The server analyzes the received request using natural language processing technology. Specifically, it breaks down the input request into tokens and analyzes its grammatical structure. It extracts important keywords and phrases and identifies elements such as "delivery," "delay," and "situation."

[0509] Step 4:

[0510] The server generates appropriate response options based on the analyzed request content and sentiment information. This process references internal databases and FAQ documents. For example, if dissatisfaction is detected, a response option including an apology, such as "We are experiencing a temporary problem with our delivery service. We sincerely apologize," will be generated.

[0511] Step 5:

[0512] The server sends the generated answer candidates to the terminal. The terminal displays the received answer candidates in the user interface, presenting the user with multiple answer options.

[0513] Step 6:

[0514] The user selects the most suitable answer from the suggested answers displayed on their device. After selection, they can edit the selected answer as needed. For example, they can change the answer "There is a temporary problem with our delivery service" to a more specific wording such as "We apologize for the delay in delivery. There is currently a temporary problem with our delivery service."

[0515] Step 7:

[0516] The server receives the user's edited responses and, referencing the customer profile, generates additional service suggestions and information tailored to the company's size and business type. Sentimental information is also considered, ensuring that the most appropriate suggestions are made based on the user's emotions. For example, if the user appears very dissatisfied, additional suggestions including a perk such as "We'll provide you with a 30% discount coupon for your next order" are generated.

[0517] Step 8:

[0518] The server sends additional suggestions and information it generates to the user's terminal, where the user can review and edit them. For example, the user can edit an additional suggestion, such as changing a "30% discount coupon" to a "40% discount coupon."

[0519] Step 9:

[0520] The user sends their final edited response and additional suggestions to the server via their device. The server receives this and sends the final response to the customer via a communication method such as email or chat. For example, the customer might receive a message such as, "We apologize for the delay in delivery. We are currently experiencing a temporary issue with our delivery service. As an apology, we are offering a 40% discount coupon that can be used on your next order."

[0521] In this way, by combining an emotion engine, the system provides quick and appropriate responses that take customer emotions into account, resulting in increased customer satisfaction and improved company sales.

[0522] (Example 2)

[0523] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0524] Traditional customer service systems simply process customer requests without considering customer emotions. This makes it difficult to achieve sufficient customer satisfaction, hindering the company's ability to build trust and increase sales.

[0525] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for analyzing the request content and generating appropriate response candidates, means for recognizing the user's emotions, and means for generating response candidates while considering the emotional information. This enables a quick and appropriate response that takes into account the customer's emotions, thereby improving customer satisfaction and enhancing the company's credibility.

[0526] "Request details" refer to the information and requirements that the user enters into the system.

[0527] "Emotional information" refers to data obtained by analyzing a user's emotions and feelings.

[0528] "Natural language processing technology" is a technology that analyzes text data and helps it understand meaning and context.

[0529] A "machine learning model" is an algorithm or framework that learns from data and performs predictions and classifications.

[0530] "Possible responses" refer to appropriate replies or suggested actions in response to a request.

[0531] "Company size and type" refers to the size of a company (for example, a small or medium-sized enterprise, or a large corporation) and its business operations.

[0532] A "customer profile" is data that records a customer's personal information, purchase history, preferences, and other details.

[0533] A "proposal for additional services" refers to a proposal for additional services or benefits that a company can offer.

[0534] A "system" is a set of devices or programs designed to achieve a specific purpose.

[0535] A "user" is an individual or organization that uses the system to input request details.

[0536] A "server" is the central device of a system, responsible for processing and managing data.

[0537] Modes for carrying out the invention

[0538] The system of the present invention analyzes the user's request, generates appropriate response candidates that take emotional information into consideration, and proposes additional services tailored to the size and type of business. The embodiments for carrying out the present invention are described in detail below.

[0539] System Configuration

[0540] This system broadly includes the following main components:

[0541] A means (terminal) for entering request details.

[0542] A means of recognizing user emotions (emotion engine)

[0543] A method (server) for analyzing request content using natural language processing technology.

[0544] A method (server) for generating answer candidates using a machine learning model.

[0545] A server for generating proposals for additional services tailored to the size and type of business.

[0546] Means for transmitting and receiving various types of data (terminals, servers)

[0547] Hardware and software configuration

[0548] The following hardware and software will be used to implement this system.

[0549] Terminal: A device used by users to input request details. This includes personal computers and smartphones.

[0550] Emotion engine: Software used to recognize user emotions. Examples include IBM Watson Tone Analyzer and Microsoft Text Analytics.

[0551] Server: A device that analyzes the request content and generates answer candidates and additional service suggestions. It can use the Google Cloud Natural Language API to implement natural language processing technology and OpenAI's GPT series for answer candidate generation.

[0552] Communication method: Internet connection for data transmission between terminal and server.

[0553] Data processing and data calculation

[0554] The operation of this system follows the steps below.

[0555] 1. Enter the request details and emotional information:

[0556] The user enters their request details into their device. During this process, an emotion engine is used to analyze and recognize the user's emotional information.

[0557] 2. Sending data:

[0558] The device sends the request details and sentiment information to the server. This data is transmitted securely using a standard communication protocol (e.g., HTTPS).

[0559] 3. Analysis using natural language processing:

[0560] The server analyzes the received request using natural language processing technology and extracts important keywords and phrases.

[0561] 4. Generating answer candidates:

[0562] Based on the analyzed keywords and sentiment information, the server uses a machine learning model (e.g., OpenAI's GPT series) to generate appropriate response candidates. The generated response candidates take the user's sentiment into account; for example, if the user expresses dissatisfaction, a response including an apology will be provided.

[0563] 5. Generating proposals for additional services:

[0564] Based on the company profile, the server generates suggestions and information for additional services tailored to the company's size and business type. Sentimental information is also taken into consideration; for example, if a user is highly dissatisfied, a suggestion such as "We will provide you with a 30% discount coupon that you can use on your next order" will be generated.

[0565] Specific examples and prompt statements

[0566] To illustrate the specific operation, the following are examples of concrete actions and prompt statements.

[0567] Specific example:

[0568] User input: "My order is delayed. Please tell me the status."

[0569] Emotion engine's recognition result: "Dissatisfaction"

[0570] Keyword extraction using natural language processing: "delivery," "delay," "situation"

[0571] Suggested response: "We are experiencing a temporary issue with our delivery service. We sincerely apologize."

[0572] Example of a prompt:

[0573] "Your delivery is delayed. Please let me know the status."

[0574] "There is an error in the invoice. Please check it."

[0575] "My ordered item hasn't arrived yet. What's going on?"

[0576] "The service wasn't what I expected. Why?"

[0577] Based on the above explanation, this system can provide prompt and appropriate customer service that takes user emotions into consideration, thereby improving customer satisfaction, corporate credibility, and sales.

[0578] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0579] Step 1:

[0580] The user enters their request into the terminal. For example, they might enter, "My product delivery is delayed. Please tell me the status." This input data becomes the starting point for the system's processing.

[0581] Step 2:

[0582] The terminal uses an emotion engine to recognize the user's emotions based on the input request. Examples of emotion engines used include IBM Watson Tone Analyzer and Microsoft Text Analytics. At this stage, the request content is passed to the emotion engine as input data, and emotion information such as "dissatisfied" is obtained as output.

[0583] Step 3:

[0584] The terminal sends the entered request details and recognized emotion information to the server. The data is sent, for example, via the HTTPS protocol. The input data consists of the request details and emotion information, and the output is the transmission of data to the server.

[0585] Step 4:

[0586] The server analyzes the received request using natural language processing technology. One example of this technology is the Google Cloud Natural Language API. The input data is the request content, and the output is important keywords and phrases (e.g., "delivery," "delay," "status").

[0587] Step 5:

[0588] The server uses the analyzed keywords and sentiment information to generate appropriate response candidates using a machine learning model (e.g., OpenAI's GPT series). The input data consists of keywords and sentiment information, and the output is the generated response candidates (e.g., "We are experiencing a temporary problem with our delivery service. We sincerely apologize.").

[0589] Step 6:

[0590] The server sends the generated answer candidates to the terminal. The input data is the answer candidates, and the output is the transmission of data to the terminal.

[0591] Step 7:

[0592] The user reviews the suggested answers presented on their device and edits them as needed. The input data is the presented answer candidates, and the output is the user's final edited answer (e.g., "We apologize for the delay in delivery. We are currently experiencing a temporary issue with our delivery service.").

[0593] Step 8:

[0594] After the server receives the edited response, it generates additional service suggestions tailored to the company size and type based on the customer profile. The input data is the edited response and customer profile, and the output is the generated additional suggestion (e.g., "We'll give you a 30% discount coupon for your next order").

[0595] Step 9:

[0596] The server sends the generated additional suggestions to the terminal and presents them to the user. The input data is the additional suggestions, and the output is the data transmission to the terminal.

[0597] Step 10:

[0598] Users can review the presented additional suggestions and edit them as needed. The input data is the presented additional suggestions, and the output is the final suggestion edited by the user (e.g., "40% discount coupon").

[0599] Step 11:

[0600] The user submits their final edited response and suggestions to the server. The input data is the final response and suggestions, and the output is the data submission to the server.

[0601] Step 12:

[0602] The server sends the final response to the customer. The final response is delivered to the customer via communication methods such as email or chat. The input data is the final response and proposal, and the output is what is sent to the customer. For example, it might say, "We apologize for the delay in delivery. We are currently experiencing a temporary problem with our delivery service. As an apology, we are offering a 40% discount coupon that can be used on your next order."

[0603] (Application Example 2)

[0604] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0605] Traditional customer service systems had limitations in generating appropriate responses to requests, and particularly struggled to respond to users' emotions. Furthermore, providing appropriate additional suggestions and information was difficult, resulting in a lack of means to improve customer satisfaction. As a result, customer dissatisfaction accumulated, potentially negatively impacting the company's sales and brand image.

[0606] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0607] In this invention, the server includes means for inputting the request content, means for recognizing the user's emotions based on the request content, means for analyzing the request content and generating appropriate response candidates, means for selecting a response from the generated response candidates, means for editing the selected response, means for generating additional suggestions and information according to the company size and type of business, means for editing the additional suggestions and information, and means for transmitting the response and the additional suggestions and information. This enables prompt and appropriate customer service that responds to the user's emotions, thereby improving customer satisfaction and corporate sales.

[0608] "Request details" refers to the information or problem-solving needs that users seek regarding a service or product.

[0609] "Means of recognizing emotions" refers to technology that analyzes the user's emotional state from their input and has the function of determining a specific emotion (such as joy, anger, or sadness).

[0610] "Methods for generating response candidates" refer to analytical engines or algorithms used to generate multiple appropriate responses to a request.

[0611] "Means of selecting an answer" refers to the interface or function used to choose the most appropriate answer from the generated list of candidates.

[0612] "Means for editing answers" refers to a function that allows users to modify or change selected answers as appropriate.

[0613] "Means for generating additional suggestions and information" refers to analytical engines and algorithms for generating and providing services and information tailored to the size and type of business of the company.

[0614] "Means for editing additional suggestions and information" refers to functions that allow users to modify or change generated additional suggestions and information as needed.

[0615] "Means of transmission" refers to communication functions used to convey generated responses and additional suggestions to users and customers.

[0616] "Natural language processing technology" refers to technologies that understand and analyze human language and perform appropriate information processing based on that understanding.

[0617] A "machine learning model" refers to artificial intelligence technology that learns from large amounts of data to solve problems and make predictions.

[0618] A "customer profile" refers to a database that includes customer behavior history and attribute information.

[0619] "Food delivery" refers to a service that delivers food and beverages to a specific location.

[0620] This invention is a system that provides prompt and appropriate customer service in the food delivery field, taking into account the user's emotions. As mentioned above, this system handles the input of the request, recognition of emotions, generation of appropriate response candidates, and generation of additional suggestions and information.

[0621] Specifically, the process begins with the user entering their request using a smartphone or other device, and the system receiving this information. For example, the user might enter, "My pizza order is late and I'm getting frustrated. Please tell me what's happening." Based on this request, the system's emotion recognition engine analyzes the user's emotions and extracts emotional information.

[0622] The analyzed sentiment information and request details are sent to the server. The server uses natural language processing techniques to analyze the request details and extract key keywords. This process utilizes the Python TextBlob library. For example, keywords such as "order," "pizza," "delay," and "situation" are identified.

[0623] Next, the server uses Hugging Face's sentiment analysis model to analyze the user's emotional information. After identifying the emotion, the server uses a machine learning model to generate appropriate response candidates. In this process, the user's emotional information is given special consideration, resulting in responses such as, "We apologize for the delay in delivery. We are currently investigating the situation."

[0624] The suggested answers are sent to the user's device, where they can review and edit them as needed. This editing function allows users to modify the suggested answers as appropriate and optimize them for submission.

[0625] Subsequently, the server generates additional suggestions tailored to the company size and industry based on the customer profile and user sentiment information. This may include information such as, "We offer a 30% discount coupon that can be used on your next order."

[0626] The generated additional suggestions and information are sent back to the user's device, where the user reviews and edits them as needed. The final response and additional suggestions are then sent to the customer via the server.

[0627] In summary, this system effectively combines an emotion recognition engine, natural language processing, and machine learning models to quickly provide responses tailored to customer needs and improve customer satisfaction. Key hardware and software used include Python, TextBlob, Hugging Face Transformers, and smartphones.

[0628] Examples of prompt statements include:

[0629] "My pizza order is delayed, could you please tell me what's happening?"

[0630] "It's been two hours since I placed my order, why hasn't it arrived yet?"

[0631] "I would like to be notified if there is a delay in delivery."

[0632] As described above, the system of the present invention aims to improve the quality of customer service in the food delivery sector by enabling responses that take customer emotions into consideration.

[0633] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0634] Step 1:

[0635] Users enter their requests using a smartphone or other device. The input includes problems and requests in text or audio format. For example, one user might enter, "My pizza order is late and I'm getting frustrated. Please tell me what's happening."

[0636] Input: User's request (text or voice)

[0637] Output: Input request details

[0638] Step 2:

[0639] The terminal receives the input request and analyzes the user's emotions using an emotion recognition engine. This analysis employs algorithms that extract emotions from voice and text. For example, the emotion "irritated" might be identified.

[0640] Input: User's request (text or voice)

[0641] Output: Analyzed sentiment information

[0642] Step 3:

[0643] The terminal sends the analyzed sentiment information and request details to the server. The server analyzes the request details using natural language processing techniques and extracts important keywords and phrases. For example, keywords such as "order," "pizza," and "delay" may be identified.

[0644] Input: Request details and emotional information

[0645] Output: Analyzed keywords and phrases

[0646] Step 4:

[0647] The server generates appropriate response candidates based on keywords and sentiment information analyzed using a machine learning model. Sentiment information is given particular consideration, and responses including apologies are prioritized if dissatisfaction is strong. For example, a response such as "We apologize for the delay in delivery. We are currently investigating the situation" might be generated.

[0648] Input: Analyzed keywords and sentiment information

[0649] Output: Generated answer candidates

[0650] Step 5:

[0651] The server sends the generated response options to the terminal. The user reviews the suggested responses and modifies / edits them as needed. For example, they might edit them to include more specific wording, such as "We are currently checking the delivery status."

[0652] Input: Generated answer suggestions

[0653] Output: User-edited response

[0654] Step 6:

[0655] Next, the server generates additional suggestions and information tailored to the company size and type, based on customer profiles and user sentiment information. For example, it might generate a suggestion such as, "We'll give you a 30% discount coupon for your next order."

[0656] Input: Customer profile and sentiment information

[0657] Output: Generated additional suggestions and information

[0658] Step 7:

[0659] The server sends the generated additional suggestions and information to the terminal, where the user reviews and edits them as needed. For example, they might change "30% discount coupon" to "40% discount coupon."

[0660] Input: Generated additional suggestions and information

[0661] Output: Additional suggestions and information edited by the user.

[0662] Step 8:

[0663] Finally, the user's edited response and additional suggestions are sent to the server, which receives them and forwards them to the customer via email, chat, or other methods. For example, a message might be sent saying, "We apologize for the delay in delivery. We are currently experiencing a temporary issue with our delivery service. As an apology, we will provide you with a 40% discount coupon for your next order."

[0664] Input: User-edited answers and additional suggestions

[0665] Output: Final response and additional suggestions (to be sent to the customer)

[0666] Through the steps outlined above, prompt and appropriate customer service that takes user emotions into consideration is achieved.

[0667] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0668] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0669] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0670] [Third Embodiment]

[0671] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0672] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0673] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0674] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0675] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0676] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0677] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0678] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0679] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0680] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0681] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0682] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0683] The embodiments for carrying out this invention will now be described. The system of the invention begins by providing a terminal with an interface for the user to input the details of a customer's request. The request details entered into the terminal are transmitted to a server.

[0684] The server analyzes the received request using natural language processing techniques. This analysis step involves tokenizing and grammatically analyzing the request to extract important keywords and phrases. For example, a request like "My product delivery is delayed. Please tell me the status" is broken down into keywords such as "delivery," "delay," and "status."

[0685] Next, the server generates appropriate answer candidates based on the analyzed keywords and request details. This involves referencing internal databases and FAQ documents, and utilizing a machine learning model. This machine learning model learns from past responses to similar inquiries, enabling it to generate the most appropriate answer. For example, it might generate answers such as "There is a temporary problem with the delivery service" and "The reason for the delay in product delivery is insufficient stock."

[0686] The generated response options are displayed on the user's device. The user selects the most appropriate response from these options. After selection, the user can edit the response. For example, the response "There is a temporary problem with the delivery service" can be edited to "We apologize for the delay in delivery. There is currently a temporary problem with the delivery service."

[0687] Subsequently, the server generates suggestions and information for additional services tailored to the company's size and business type. In this step, it refers to the customer profile and makes optimal suggestions based on past purchase history and company characteristics. For example, it might generate a suggestion such as, "We'll provide you with a 20% discount coupon that you can use on your next order."

[0688] The generated additional service suggestions and information are also presented on the user's device, allowing the user to review and edit them as needed. For example, it is possible to change a "20% discount coupon" to a "30% discount coupon."

[0689] Finally, the user sends the edited response and additional suggestions to the customer. This sending process uses communication methods such as email or chat, which the server uses. For example, it might say, "We apologize for the delay in delivery. We are currently experiencing a temporary issue with our delivery service. As an apology, we are offering a 30% discount coupon that can be used on your next order."

[0690] In this way, the system of the present invention enables prompt and appropriate customer service, thereby improving customer satisfaction and sales.

[0691] The following describes the processing flow.

[0692] Step 1:

[0693] The user enters their request into the terminal. For example, they might enter a request such as, "My product delivery is delayed. Please tell me the status." This input is done through the interface on the terminal.

[0694] Step 2:

[0695] The terminal sends the request details entered by the user to the server. This transmission is done via an API and uses a secure communication protocol.

[0696] Step 3:

[0697] The server analyzes the received request using natural language processing techniques. Specifically, it breaks down the request into tokens, performs grammatical analysis, and extracts keywords and important phrases. For example, it identifies keywords such as "delivery," "delay," and "situation."

[0698] Step 4:

[0699] Based on the keywords analyzed by the server, it generates appropriate answer candidates. In this process, the server refers to an internal database and FAQ documents and uses a machine learning model to generate answer candidates. Examples of generated answers include "The reason for the delay in product delivery is insufficient stock" and "There is a temporary problem with the delivery service."

[0700] Step 5:

[0701] The server sends the generated answer candidates to the terminal. The terminal receives them and displays them in the user interface. The user reviews the multiple answer candidates presented.

[0702] Step 6:

[0703] The user selects the answer they deem most appropriate on their device. After selecting, the user can edit the selected answer as needed. For example, they might edit the answer "There is a temporary problem with our delivery service" to "We apologize for the delay in delivery. There is currently a temporary problem with our delivery service."

[0704] Step 7:

[0705] The server receives the edited response and, referencing the customer profile, generates additional service suggestions and information tailored to the company size and type. For example, if the customer is a small business, it might generate a suggestion such as, "We'll give you a 20% discount coupon for your next order."

[0706] Step 8:

[0707] The server sends additional suggestions and information it generates to the user's terminal, where the user can review and edit them. For example, a "20% discount coupon" can be changed to a "30% discount coupon."

[0708] Step 9:

[0709] The user sends their final edited response and additional suggestions to the server via their device. The server receives this and sends the final response to the customer via email, chat, or other means. For example, it might say, "We apologize for the delay in delivery. We are currently experiencing a temporary issue with our delivery service. As an apology, we are offering a 30% discount coupon for your next order."

[0710] In this way, the system enables quick and appropriate customer service, contributing to increased customer satisfaction and improved company sales.

[0711] (Example 1)

[0712] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0713] In today's business environment, responding quickly and appropriately to a wide range of customer inquiries is crucial for improving customer satisfaction and maintaining a company's competitiveness. However, efficiently handling a large volume of inquiries requires an automated response system utilizing advanced natural language processing technology and machine learning models. Furthermore, providing proposals and services tailored to individual customer needs necessitates a flexible system based on the company's size, industry, and customer profile. Developing a system that meets these diverse requirements remains challenging, and many companies have yet to implement one effectively.

[0714] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0715] In this invention, the server includes means for inputting the request details, means for analyzing the request details and generating appropriate response candidates, means for selecting a response from the generated response candidates, means for editing the selected response, means for generating suggestions and information on additional services according to the size and type of business, means for editing the suggestions and information on additional services, and means for transmitting the response and the suggestions and information on additional services. This enables prompt and appropriate customer service.

[0716] "Request details" refers to information about inquiries and requests received by the user from customers.

[0717] "Means of input" refers to the interface or device used by the user to input the details of their request into the system, as well as the method of operating it.

[0718] "Means of analysis" refers to the process and techniques used to analyze the received request using language processing technology and extract the necessary information.

[0719] "Response candidates" refer to several appropriate response options generated based on the analyzed request.

[0720] "Means of selection" refers to the interface or method that allows the user to choose the most suitable response from among the generated candidate responses.

[0721] "Means of editing" refer to tools and functions that allow users to modify or supplement selected responses as appropriate.

[0722] "Proposal for additional services" refers to additional services or offers provided based on customer needs, company size, and business type.

[0723] "Means of generating information" refers to processes and technologies for automatically creating suggestions for additional services and other related information.

[0724] "Means of transmission" refers to the means or methods of communication used to deliver the final edited response or additional service suggestions to the customer.

[0725] "Natural language processing technology" refers to the technology used by computers to understand and analyze natural language and extract relevant information.

[0726] A "machine learning model" is an algorithm that learns patterns based on past data and uses that knowledge to perform inferences and predictions on new data.

[0727] A "customer profile" refers to detailed information about individual customers, such as their past purchase history and behavioral data.

[0728] The system according to this invention provides a comprehensive solution for responding quickly and appropriately to customer inquiries. Specific embodiments of this system are described below.

[0729] First, a terminal is provided that offers an interface for users to input the details of requests received from customers. This interface is built as a web application using HTML and JavaScript. Through this interface, users input the request details in text format. For example, "The delivery of the product is delayed. Please let me know the status."

[0730] The request details entered on the terminal are sent to the server via the internet. The HTTPS protocol is used for this communication, ensuring secure data transfer. Specifically, an Ajax request is generated, and data is sent in JSON format, as shown below.

[0731] json

[0732] {

[0733] "request": "My order is delayed. Please tell me the status."

[0734] }

[0735] The request content that reaches the server is analyzed using natural language processing (NLP) technology. This analysis uses spaCy, a Python NLP library, to tokenize the request content, perform grammatical analysis, and extract important keywords. For example, when tokenizing "My product delivery is delayed. Please tell me the status," the tokens would be "product," "delivery," "delay," "status," and "tell me."

[0736] Next, the server generates appropriate response candidates based on the analyzed keywords and request details. At this stage, it refers to internal databases and FAQ documents, and uses machine learning models. Specifically, it uses machine learning libraries such as TensorFlow and scikit-learn, and models trained on historical data generate the best response. Examples of generated responses include "There is a temporary problem with the delivery service" and "The reason for the delay in product delivery is insufficient stock."

[0737] Once answer suggestions are generated, the server sends them to the user's device. The user reviews the suggested answers on their device and selects the most appropriate one. Furthermore, the user can edit their selected answer. For example, they can change the answer "There is a temporary problem with the delivery service" to "We apologize for the delay in delivery. There is currently a temporary problem with the delivery service."

[0738] In addition, the server generates suggestions for additional services tailored to the company's size and business type. This suggestion generation is performed by retrieving data from CRM systems such as Salesforce, based on customer profiles and past purchase history. Specific examples of suggestions include, "We'll provide you with a 20% discount coupon for your next order." Users can also edit the generated additional suggestions.

[0739] Finally, the user sends the edited response and additional suggestions to the customer. This sending process utilizes email and chat tool APIs. For example, the SendGrid API might be used to send a final message like the following:

[0740] "We sincerely apologize for the delay in delivery. We are currently experiencing a temporary issue with our delivery service. As an apology, we are offering a 30% discount coupon that can be used on your next order."

[0741] This system allows users to respond quickly and accurately, leading to increased customer satisfaction and sales.

[0742] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0743] Step 1:

[0744] The user enters customer requests using their device. The interface is built as a web application, and the user enters the request details into a text box. For example, they might enter, "The product delivery is delayed. Please let me know the status."

[0745] Step 2:

[0746] The terminal sends the entered request details to the server. HTTPS protocol is used for communication, and an Ajax request is generated. The input is in text format and is converted to JSON format upon transmission. Specific request example:

[0747] json

[0748] {

[0749] "request": "My order is delayed. Please tell me the status."

[0750] }

[0751] The output is the data packet sent to the server.

[0752] Step 3:

[0753] The server analyzes the received request using natural language processing techniques. The library used is spaCy in Python, which performs tokenization and grammatical analysis. The input is the request content in JSON format, and the output is extracted keywords. For example, if the input sentence "The delivery of my product is delayed. Please tell me the status" is analyzed, the output will be tokenized as "product", "delivery", "delay", "status", and "tell me".

[0754] Step 4:

[0755] The server generates appropriate answer candidates based on the analyzed keywords and request details. It references an internal database and FAQ documentation and runs a machine learning model using TensorFlow. The input is tokenized keywords, and the output is multiple answer candidates. For example, it might generate answers such as "There is a temporary problem with the delivery service" or "The reason for the delay in product delivery is insufficient stock."

[0756] Step 5:

[0757] The server sends the generated answer suggestions to the user's device. The user's device displays the answer suggestions and provides a confirmation UI. The input is the answer suggestion data, and the output is the confirmation screen the user can view. Specific UI example:

[0758] Option 1: "There is a temporary issue with our delivery service."

[0759] Option 2: "The reason for the delay in product delivery is a shortage of stock."

[0760] Step 6:

[0761] The user selects the most suitable answer from a list of options and edits it. Selection is done on the UI, and editing is done using a text box. The input is the answer options, and the output is the final edited response. For example, "There is a temporary problem with our delivery service" can be edited to "We apologize for the delay in delivery. There is currently a temporary problem with our delivery service."

[0762] Step 7:

[0763] The server generates additional service suggestions tailored to the company's size and business type. This step involves retrieving customer profiles and past purchase history from CRM systems such as Salesforce. The input is customer profile data, and the output is additional service suggestions. A specific example suggestion: "We offer a 20% discount coupon for your next order."

[0764] Step 8:

[0765] The user reviews the generated additional service suggestions and edits them as needed. The input is the suggestion data, and the output is the edited suggestion. For example, it is possible to change "20% discount coupon" to "30% discount coupon".

[0766] Step 9:

[0767] The user edits the response and additional suggestions, which are then sent to the customer as the final message. This sending process uses email service APIs such as SendGrid. The input is the edited response and additional suggestions, and the output is the final message sent to the customer. For example, a message such as, "We apologize for the delay in delivery. We are currently experiencing a temporary issue with our delivery service. As an apology, we are offering a 30% discount coupon for your next order," might be sent.

[0768] By following these steps, users can respond quickly and accurately, leading to increased customer satisfaction and sales.

[0769] (Application Example 1)

[0770] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0771] Modern content delivery services require prompt and appropriate responses to user problems and requests. However, previous systems had drawbacks, such as low efficiency, as they required a lot of manual work to analyze user requests, generate appropriate responses, and propose services tailored to the size and type of company. Furthermore, the lack of a good user interface and the difficulty in effectively utilizing natural language processing technology limited the improvement of user satisfaction.

[0772] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0773] In this invention, the server includes means for inputting the request content, means for analyzing the request content and generating appropriate answer candidates, means for selecting an answer from the generated answer candidates, means for editing the selected answer, means for generating suggestions and information on additional services according to the size and type of business, means for editing the suggestions and information on additional services, means for transmitting the answer and the suggestions and information on additional services, means for providing a user interface for inputting the request content and displaying and editing the answer, means for analyzing the request content using natural language processing technology and generating an appropriate answer by referring to specific documents or databases based on the analysis results, means for using a generation AI model to generate the answer, and means for displaying prompt sentences on the user interface to prompt user input. This enables efficient and automated user support.

[0774] "Request details" refers to the description of the problem or request entered by the user.

[0775] "Analysis" refers to the process of tokenizing and grammatically analyzing the request content entered by the user.

[0776] "Possible responses" are a selection of appropriate responses to the user's request.

[0777] A "user interface" is an interface through which users input their requests and view and edit analysis results and responses.

[0778] "Natural language processing technology" is a technology that analyzes user input and enables computers to understand language that humans speak naturally.

[0779] A "generative AI model" is an artificial intelligence algorithm that learns from past data and generates appropriate responses to user requests.

[0780] A "prompt message" is a sample sentence or input guidance displayed to encourage user input.

[0781] "Additional service proposals" refer to special services or promotions that are suggested based on the company's size, business type, and customer profile.

[0782] A "database" is a system that manages a collection of information, and it is used by the system to understand the content of a request.

[0783] "Editing" is the process of modifying or changing the generated answers or suggested additional services.

[0784] "Sending" refers to the act of sending a final response or proposal to the user or customer.

[0785] The embodiments for carrying out this invention will be described in detail. This system is for automating and streamlining user support in content distribution services. It is composed of the following roles: server, terminal, and user.

[0786] The server first provides a means for inputting the request details. This is an interface where the user inputs problems and requests, and it is embedded in devices such as smartphones, smart glasses, and robots using HTML, CSS, and JavaScript. The input data from this interface is sent to the server via an API.

[0787] Next, the server analyzes the received request using natural language processing technology (such as spaCy or NLTK). This involves tokenizing the request, performing grammatical analysis, and then extracting important keywords and phrases. For example, if the request is "the streaming stops midway," keywords such as "streaming," "midway," and "stop" will be extracted.

[0788] Subsequently, the server uses a generative AI model (e.g., TensorFlow) to generate candidate answers based on the analysis results. These models learn from past data and generate the best possible answers to the user's questions. For example, they might generate answers such as "Please check your network connection" or "Please update to the latest app version."

[0789] The generated response suggestions are sent from the server to the user interface. The user interface provides a means for the user to select a response suggestion and edit it as needed. For example, a text area can be used to allow the user to change the response "Please check your network connection" to "Could you please check your network connection?".

[0790] The server also generates suggestions and information for additional services tailored to the size and type of business. This is done by referencing customer profiles (such as viewing and purchase history). For example, suggestions such as "a 10% discount coupon for your next visit" may be generated. These suggestions are also displayed in the user interface and can be edited by the user.

[0791] Finally, the user's edited response and suggestions for additional services are sent from the server to the customer. This transmission is done using communication methods such as email or chat. For example, a message might be sent in the form of, "Thank you for letting us know about the issue with streaming stopping midway. We are currently asking you to check your network connection. You can also use a 10% discount coupon for your next order."

[0792] Examples of prompt messages used include the following:

[0793] "The streaming stops midway."

[0794] "I can't find the content I'm looking for."

[0795] "Please tell me how to use the app."

[0796] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0797] Step 1:

[0798] The terminal provides an interface for the user to input their request. The user enters the problem or request in the input field. The input data is sent to the server via the API in JSON format. For example, the user might enter "The streaming stops midway."

[0799] Step 2:

[0800] The server analyzes the received request using natural language processing techniques (e.g., spaCy or NLTK). Specifically, it tokenizes the input text, performs grammatical analysis, and extracts important keywords and phrases. In this case, the input data "streaming stops midway" is tokenized into "streaming," "midway," and "stop."

[0801] Step 3:

[0802] The server references databases and FAQ documents based on the analysis results and generates answer candidates using a generative AI model (e.g., TensorFlow). For example, it might generate answers such as "Please check your network connection" or "Please update to the latest app version."

[0803] Step 4:

[0804] The server sends the generated answer suggestions to the user interface. The user interface displays the answer suggestions to the user. At this time, the user interface displays a prompt message to encourage user feedback and editing. For example, the answer suggestion "Please check your network connection" might be displayed in the text area.

[0805] Step 5:

[0806] The user selects the most appropriate answer from the displayed options and edits it as needed. The edited answer is then sent back to the server. For example, "Please check your network connection" can be edited to "Could you please check your network connection?".

[0807] Step 6:

[0808] The server generates additional service suggestions based on the company's size and business type. To do this, it refers to customer profiles (such as viewing and purchase history) to determine appropriate suggestions. For example, it might generate a suggestion such as "a 10% discount coupon for your next visit."

[0809] Step 7:

[0810] The server sends the generated additional service suggestions to the user interface. The user interface displays them and allows the user to edit them. For example, the displayed "10% discount coupon" can be changed to a "15% discount coupon".

[0811] Step 8:

[0812] The user then reviews the edited response and any suggested additional services and sends them to the customer. The server then sends the reviewed information to the customer via email, chat, or other means of communication. For example, it might say, "Thank you for letting us know about the issue with the streaming stopping midway. We are currently asking you to check your network connection. You can also use a 10% discount coupon for your next order."

[0813] This series of processes allows users to respond to customers quickly and effectively.

[0814] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0815] The embodiments for carrying out the present invention will be described in detail. This invention combines a system that takes a request as input, analyzes it, generates appropriate response candidates, and also provides suggestions and information on additional services tailored to the size and type of company with an emotion engine that recognizes the user's emotions.

[0816] First, the user enters their request into the device. For example, they might enter, "My delivery is delayed. Please tell me the status." During this input process, the device uses its built-in emotion engine to recognize the user's emotions. This emotion information is extracted through voice and text analysis.

[0817] Next, the terminal sends emotional information along with the request to the server. The server analyzes the received request using natural language processing technology to understand its meaning and extract important keywords and phrases. For example, it identifies keywords such as "delivery," "delay," and "situation."

[0818] Based on the analysis results, the server uses a machine learning model to generate appropriate response candidates. This generation process also takes into account the user's sentiment information. For example, if sentiment data indicates the user is dissatisfied, responses that include an apology will be prioritized. For instance, a response such as "We are experiencing a temporary problem with our delivery service. We sincerely apologize" might be generated.

[0819] The server generates suggested responses, which are sent to the terminal and presented to the user. The user selects the most suitable response from the presented options and edits it as needed. For example, they might edit it to include specific wording such as, "We apologize for the delay in delivery. We are currently experiencing a temporary issue with our delivery service."

[0820] Next, the server generates additional service suggestions and information based on the customer profile, tailored to the company size and type of business. Sentimental information is also considered in this suggestion generation process, ensuring that the most appropriate suggestions are made in response to the user's emotions. For example, if the user appears very dissatisfied, a suggestion such as "We offer a 30% discount coupon for your next order" will be generated.

[0821] The generated additional suggestions and information are also sent to the user's device, where the user can review and edit them as needed. For example, it is possible to change a "30% discount coupon" to a "40% discount coupon."

[0822] Finally, the user sends their edited response and additional suggestions to the server via their device. The server receives this and sends the final response to the customer via email, chat, or other means. For example, it might say, "We apologize for the delay in delivery. We are currently experiencing a temporary issue with our delivery service. As an apology, we are offering a 40% discount coupon that can be used on your next order."

[0823] Thus, by combining the system of the present invention with an emotion engine, it is possible to achieve prompt and appropriate customer service that takes customer emotions into consideration, thereby improving customer satisfaction and corporate sales.

[0824] The following describes the processing flow.

[0825] Step 1:

[0826] The user enters their request into the terminal. The input interface of the terminal will contain a request such as, "My product delivery is delayed. Please tell me the status." The terminal is also equipped with an emotion engine that recognizes the user's emotions during input through voice and facial expression analysis. It also analyzes emotions from text input.

[0827] Step 2:

[0828] The terminal sends the entered request details and emotional information to the server. This data is transmitted using a secure communication protocol, ensuring data security.

[0829] Step 3:

[0830] The server analyzes the received request using natural language processing technology. Specifically, it breaks down the input request into tokens and analyzes its grammatical structure. It extracts important keywords and phrases and identifies elements such as "delivery," "delay," and "situation."

[0831] Step 4:

[0832] The server generates appropriate response options based on the analyzed request content and sentiment information. This process references internal databases and FAQ documents. For example, if dissatisfaction is detected, a response option including an apology, such as "We are experiencing a temporary problem with our delivery service. We sincerely apologize," will be generated.

[0833] Step 5:

[0834] The server sends the generated answer candidates to the terminal. The terminal displays the received answer candidates in the user interface, presenting the user with multiple answer options.

[0835] Step 6:

[0836] The user selects the most suitable answer from the suggested answers displayed on their device. After selection, they can edit the selected answer as needed. For example, they can change the answer "There is a temporary problem with our delivery service" to a more specific wording such as "We apologize for the delay in delivery. There is currently a temporary problem with our delivery service."

[0837] Step 7:

[0838] The server receives the user's edited responses and, referencing the customer profile, generates additional service suggestions and information tailored to the company's size and business type. Sentimental information is also considered, ensuring that the most appropriate suggestions are made based on the user's emotions. For example, if the user appears very dissatisfied, additional suggestions including a perk such as "We'll provide you with a 30% discount coupon for your next order" are generated.

[0839] Step 8:

[0840] The server sends additional suggestions and information it generates to the user's terminal, where the user can review and edit them. For example, the user can edit an additional suggestion, such as changing a "30% discount coupon" to a "40% discount coupon."

[0841] Step 9:

[0842] The user sends their final edited response and additional suggestions to the server via their device. The server receives this and sends the final response to the customer via a communication method such as email or chat. For example, the customer might receive a message such as, "We apologize for the delay in delivery. We are currently experiencing a temporary issue with our delivery service. As an apology, we are offering a 40% discount coupon that can be used on your next order."

[0843] In this way, by combining an emotion engine, the system provides quick and appropriate responses that take customer emotions into account, resulting in increased customer satisfaction and improved company sales.

[0844] (Example 2)

[0845] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0846] Traditional customer service systems simply process customer requests without considering customer emotions. This makes it difficult to achieve sufficient customer satisfaction, hindering the company's ability to build trust and increase sales.

[0847] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for analyzing the request content and generating appropriate response candidates, means for recognizing the user's emotions, and means for generating response candidates while considering the emotional information. This enables a quick and appropriate response that takes into account the customer's emotions, thereby improving customer satisfaction and enhancing the company's credibility.

[0848] "Request details" refer to the information and requirements that the user enters into the system.

[0849] "Emotional information" refers to data obtained by analyzing a user's emotions and feelings.

[0850] "Natural language processing technology" is a technology that analyzes text data and helps it understand meaning and context.

[0851] A "machine learning model" is an algorithm or framework that learns from data and performs predictions and classifications.

[0852] "Possible responses" refer to appropriate replies or suggested actions in response to a request.

[0853] "Company size and type" refers to the size of a company (for example, a small or medium-sized enterprise, or a large corporation) and its business operations.

[0854] A "customer profile" is data that records a customer's personal information, purchase history, preferences, and other details.

[0855] A "proposal for additional services" refers to a proposal for additional services or benefits that a company can offer.

[0856] A "system" is a set of devices or programs designed to achieve a specific purpose.

[0857] A "user" is an individual or organization that uses the system to input request details.

[0858] A "server" is the central device of a system, responsible for processing and managing data.

[0859] Modes for carrying out the invention

[0860] The system of the present invention analyzes the user's request, generates appropriate response candidates that take emotional information into consideration, and proposes additional services tailored to the size and type of business. The embodiments for carrying out the present invention are described in detail below.

[0861] System Configuration

[0862] This system broadly includes the following main components:

[0863] A means (terminal) for entering request details.

[0864] A means of recognizing user emotions (emotion engine)

[0865] A method (server) for analyzing request content using natural language processing technology.

[0866] A method (server) for generating answer candidates using a machine learning model.

[0867] A server for generating proposals for additional services tailored to the size and type of business.

[0868] Means for transmitting and receiving various types of data (terminals, servers)

[0869] Hardware and software configuration

[0870] The following hardware and software will be used to implement this system.

[0871] Terminal: A device used by users to input request details. This includes personal computers and smartphones.

[0872] Emotion engine: Software used to recognize user emotions. Examples include IBM Watson Tone Analyzer and Microsoft Text Analytics.

[0873] Server: A device that analyzes the request content and generates answer candidates and additional service suggestions. It can use the Google Cloud Natural Language API to implement natural language processing technology and OpenAI's GPT series for answer candidate generation.

[0874] Communication method: Internet connection for data transmission between terminal and server.

[0875] Data processing and data calculation

[0876] The operation of this system follows the steps below.

[0877] 1. Enter the request details and emotional information:

[0878] The user enters their request details into their device. During this process, an emotion engine is used to analyze and recognize the user's emotional information.

[0879] 2. Sending data:

[0880] The device sends the request details and sentiment information to the server. This data is transmitted securely using a standard communication protocol (e.g., HTTPS).

[0881] 3. Analysis using natural language processing:

[0882] The server analyzes the received request using natural language processing technology and extracts important keywords and phrases.

[0883] 4. Generating answer candidates:

[0884] Based on the analyzed keywords and sentiment information, the server uses a machine learning model (e.g., OpenAI's GPT series) to generate appropriate response candidates. The generated response candidates take the user's sentiment into account; for example, if the user expresses dissatisfaction, a response including an apology will be provided.

[0885] 5. Generating proposals for additional services:

[0886] Based on the company profile, the server generates suggestions and information for additional services tailored to the company's size and business type. Sentimental information is also taken into consideration; for example, if a user is highly dissatisfied, a suggestion such as "We will provide you with a 30% discount coupon that you can use on your next order" will be generated.

[0887] Specific examples and prompt statements

[0888] To illustrate the specific operation, the following are examples of concrete actions and prompt statements.

[0889] Specific example:

[0890] User input: "My order is delayed. Please tell me the status."

[0891] Emotion engine's recognition result: "Dissatisfaction"

[0892] Keyword extraction using natural language processing: "delivery," "delay," "situation"

[0893] Suggested response: "We are experiencing a temporary issue with our delivery service. We sincerely apologize."

[0894] Example of a prompt:

[0895] "Your delivery is delayed. Please let me know the status."

[0896] "There is an error in the invoice. Please check it."

[0897] "My ordered item hasn't arrived yet. What's going on?"

[0898] "The service wasn't what I expected. Why?"

[0899] Based on the above explanation, this system can provide prompt and appropriate customer service that takes user emotions into consideration, thereby improving customer satisfaction, corporate credibility, and sales.

[0900] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0901] Step 1:

[0902] The user enters their request into the terminal. For example, they might enter, "My product delivery is delayed. Please tell me the status." This input data becomes the starting point for the system's processing.

[0903] Step 2:

[0904] The terminal uses an emotion engine to recognize the user's emotions based on the input request. Examples of emotion engines used include IBM Watson Tone Analyzer and Microsoft Text Analytics. At this stage, the request content is passed to the emotion engine as input data, and emotion information such as "dissatisfied" is obtained as output.

[0905] Step 3:

[0906] The terminal sends the entered request details and recognized emotion information to the server. The data is sent, for example, via the HTTPS protocol. The input data consists of the request details and emotion information, and the output is the transmission of data to the server.

[0907] Step 4:

[0908] The server analyzes the received request using natural language processing technology. One example of this technology is the Google Cloud Natural Language API. The input data is the request content, and the output is important keywords and phrases (e.g., "delivery," "delay," "status").

[0909] Step 5:

[0910] The server uses the analyzed keywords and sentiment information to generate appropriate response candidates using a machine learning model (e.g., OpenAI's GPT series). The input data consists of keywords and sentiment information, and the output is the generated response candidates (e.g., "We are experiencing a temporary problem with our delivery service. We sincerely apologize.").

[0911] Step 6:

[0912] The server sends the generated answer candidates to the terminal. The input data is the answer candidates, and the output is the transmission of data to the terminal.

[0913] Step 7:

[0914] The user reviews the suggested answers presented on their device and edits them as needed. The input data is the presented answer candidates, and the output is the user's final edited answer (e.g., "We apologize for the delay in delivery. We are currently experiencing a temporary issue with our delivery service.").

[0915] Step 8:

[0916] After the server receives the edited response, it generates additional service suggestions tailored to the company size and type based on the customer profile. The input data is the edited response and customer profile, and the output is the generated additional suggestion (e.g., "We'll give you a 30% discount coupon for your next order").

[0917] Step 9:

[0918] The server sends the generated additional suggestions to the terminal and presents them to the user. The input data is the additional suggestions, and the output is the data transmission to the terminal.

[0919] Step 10:

[0920] Users can review the presented additional suggestions and edit them as needed. The input data is the presented additional suggestions, and the output is the final suggestion edited by the user (e.g., "40% discount coupon").

[0921] Step 11:

[0922] The user submits their final edited response and suggestions to the server. The input data is the final response and suggestions, and the output is the data submission to the server.

[0923] Step 12:

[0924] The server sends the final response to the customer. The final response is delivered to the customer via communication methods such as email or chat. The input data is the final response and proposal, and the output is what is sent to the customer. For example, it might say, "We apologize for the delay in delivery. We are currently experiencing a temporary problem with our delivery service. As an apology, we are offering a 40% discount coupon that can be used on your next order."

[0925] (Application Example 2)

[0926] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0927] Traditional customer service systems had limitations in generating appropriate responses to requests, and particularly struggled to respond to users' emotions. Furthermore, providing appropriate additional suggestions and information was difficult, resulting in a lack of means to improve customer satisfaction. As a result, customer dissatisfaction accumulated, potentially negatively impacting the company's sales and brand image.

[0928] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0929] In this invention, the server includes means for inputting the request content, means for recognizing the user's emotions based on the request content, means for analyzing the request content and generating appropriate response candidates, means for selecting a response from the generated response candidates, means for editing the selected response, means for generating additional suggestions and information according to the company size and type of business, means for editing the additional suggestions and information, and means for transmitting the response and the additional suggestions and information. This enables prompt and appropriate customer service that responds to the user's emotions, thereby improving customer satisfaction and corporate sales.

[0930] "Request details" refers to the information or problem-solving needs that users seek regarding a service or product.

[0931] "Means of recognizing emotions" refers to technology that analyzes the user's emotional state from their input and has the function of determining a specific emotion (such as joy, anger, or sadness).

[0932] "Methods for generating response candidates" refer to analytical engines or algorithms used to generate multiple appropriate responses to a request.

[0933] "Means of selecting an answer" refers to the interface or function used to choose the most appropriate answer from the generated list of candidates.

[0934] "Means for editing answers" refers to a function that allows users to modify or change selected answers as appropriate.

[0935] "Means for generating additional suggestions and information" refers to analytical engines and algorithms for generating and providing services and information tailored to the size and type of business of the company.

[0936] "Means for editing additional suggestions and information" refers to functions that allow users to modify or change generated additional suggestions and information as needed.

[0937] "Means of transmission" refers to communication functions used to convey generated responses and additional suggestions to users and customers.

[0938] "Natural language processing technology" refers to technologies that understand and analyze human language and perform appropriate information processing based on that understanding.

[0939] A "machine learning model" refers to artificial intelligence technology that learns from large amounts of data to solve problems and make predictions.

[0940] A "customer profile" refers to a database that includes customer behavior history and attribute information.

[0941] "Food delivery" refers to a service that delivers food and beverages to a specific location.

[0942] This invention is a system that provides prompt and appropriate customer service in the food delivery field, taking into account the user's emotions. As mentioned above, this system handles the input of the request, recognition of emotions, generation of appropriate response candidates, and generation of additional suggestions and information.

[0943] Specifically, the process begins with the user entering their request using a smartphone or other device, and the system receiving this information. For example, the user might enter, "My pizza order is late and I'm getting frustrated. Please tell me what's happening." Based on this request, the system's emotion recognition engine analyzes the user's emotions and extracts emotional information.

[0944] The analyzed sentiment information and request details are sent to the server. The server uses natural language processing techniques to analyze the request details and extract key keywords. This process utilizes the Python TextBlob library. For example, keywords such as "order," "pizza," "delay," and "situation" are identified.

[0945] Next, the server uses Hugging Face's sentiment analysis model to analyze the user's emotional information. After identifying the emotion, the server uses a machine learning model to generate appropriate response candidates. In this process, the user's emotional information is given special consideration, resulting in responses such as, "We apologize for the delay in delivery. We are currently investigating the situation."

[0946] The suggested answers are sent to the user's device, where they can review and edit them as needed. This editing function allows users to modify the suggested answers as appropriate and optimize them for submission.

[0947] Subsequently, the server generates additional suggestions tailored to the company size and industry based on the customer profile and user sentiment information. This may include information such as, "We offer a 30% discount coupon that can be used on your next order."

[0948] The generated additional suggestions and information are sent back to the user's device, where the user reviews and edits them as needed. The final response and additional suggestions are then sent to the customer via the server.

[0949] In summary, this system effectively combines an emotion recognition engine, natural language processing, and machine learning models to quickly provide responses tailored to customer needs and improve customer satisfaction. Key hardware and software used include Python, TextBlob, Hugging Face Transformers, and smartphones.

[0950] Examples of prompt statements include:

[0951] "My pizza order is delayed, could you please tell me what's happening?"

[0952] "It's been two hours since I placed my order, why hasn't it arrived yet?"

[0953] "I would like to be notified if there is a delay in delivery."

[0954] As described above, the system of the present invention aims to improve the quality of customer service in the food delivery sector by enabling responses that take customer emotions into consideration.

[0955] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0956] Step 1:

[0957] Users enter their requests using a smartphone or other device. The input includes problems and requests in text or audio format. For example, one user might enter, "My pizza order is late and I'm getting frustrated. Please tell me what's happening."

[0958] Input: User's request (text or voice)

[0959] Output: Input request details

[0960] Step 2:

[0961] The terminal receives the input request and analyzes the user's emotions using an emotion recognition engine. This analysis employs algorithms that extract emotions from voice and text. For example, the emotion "irritated" might be identified.

[0962] Input: User's request (text or voice)

[0963] Output: Analyzed sentiment information

[0964] Step 3:

[0965] The terminal sends the analyzed sentiment information and request details to the server. The server analyzes the request details using natural language processing techniques and extracts important keywords and phrases. For example, keywords such as "order," "pizza," and "delay" may be identified.

[0966] Input: Request details and emotional information

[0967] Output: Analyzed keywords and phrases

[0968] Step 4:

[0969] The server generates appropriate response candidates based on keywords and sentiment information analyzed using a machine learning model. Sentiment information is given particular consideration, and responses including apologies are prioritized if dissatisfaction is strong. For example, a response such as "We apologize for the delay in delivery. We are currently investigating the situation" might be generated.

[0970] Input: Analyzed keywords and sentiment information

[0971] Output: Generated answer candidates

[0972] Step 5:

[0973] The server sends the generated response options to the terminal. The user reviews the suggested responses and modifies / edits them as needed. For example, they might edit them to include more specific wording, such as "We are currently checking the delivery status."

[0974] Input: Generated answer suggestions

[0975] Output: User-edited response

[0976] Step 6:

[0977] Next, the server generates additional suggestions and information tailored to the company size and type, based on customer profiles and user sentiment information. For example, it might generate a suggestion such as, "We'll give you a 30% discount coupon for your next order."

[0978] Input: Customer profile and sentiment information

[0979] Output: Generated additional suggestions and information

[0980] Step 7:

[0981] The server sends the generated additional suggestions and information to the terminal, where the user reviews and edits them as needed. For example, they might change "30% discount coupon" to "40% discount coupon."

[0982] Input: Generated additional suggestions and information

[0983] Output: Additional suggestions and information edited by the user.

[0984] Step 8:

[0985] Finally, the user's edited response and additional suggestions are sent to the server, which receives them and forwards them to the customer via email, chat, or other methods. For example, a message might be sent saying, "We apologize for the delay in delivery. We are currently experiencing a temporary issue with our delivery service. As an apology, we will provide you with a 40% discount coupon for your next order."

[0986] Input: User-edited answers and additional suggestions

[0987] Output: Final response and additional suggestions (to be sent to the customer)

[0988] Through the steps outlined above, prompt and appropriate customer service that takes user emotions into consideration is achieved.

[0989] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0990] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0991] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0992] [Fourth Embodiment]

[0993] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0994] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0995] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0996] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0997] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0998] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0999] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1000] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1001] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1002] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1003] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1004] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1005] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1006] The embodiments for carrying out this invention will now be described. The system of the invention begins by providing a terminal with an interface for the user to input the details of a customer's request. The request details entered into the terminal are transmitted to a server.

[1007] The server analyzes the received request using natural language processing techniques. This analysis step involves tokenizing and grammatically analyzing the request to extract important keywords and phrases. For example, a request like "My product delivery is delayed. Please tell me the status" is broken down into keywords such as "delivery," "delay," and "status."

[1008] Next, the server generates appropriate answer candidates based on the analyzed keywords and request details. This involves referencing internal databases and FAQ documents, and utilizing a machine learning model. This machine learning model learns from past responses to similar inquiries, enabling it to generate the most appropriate answer. For example, it might generate answers such as "There is a temporary problem with the delivery service" and "The reason for the delay in product delivery is insufficient stock."

[1009] The generated response options are displayed on the user's device. The user selects the most appropriate response from these options. After selection, the user can edit the response. For example, the response "There is a temporary problem with the delivery service" can be edited to "We apologize for the delay in delivery. There is currently a temporary problem with the delivery service."

[1010] Subsequently, the server generates suggestions and information for additional services tailored to the company's size and business type. In this step, it refers to the customer profile and makes optimal suggestions based on past purchase history and company characteristics. For example, it might generate a suggestion such as, "We'll provide you with a 20% discount coupon that you can use on your next order."

[1011] The generated additional service suggestions and information are also presented on the user's device, allowing the user to review and edit them as needed. For example, it is possible to change a "20% discount coupon" to a "30% discount coupon."

[1012] Finally, the user sends the edited response and additional suggestions to the customer. This sending process uses communication methods such as email or chat, which the server uses. For example, it might say, "We apologize for the delay in delivery. We are currently experiencing a temporary issue with our delivery service. As an apology, we are offering a 30% discount coupon that can be used on your next order."

[1013] In this way, the system of the present invention enables prompt and appropriate customer service, thereby improving customer satisfaction and sales.

[1014] The following describes the processing flow.

[1015] Step 1:

[1016] The user enters their request into the terminal. For example, they might enter a request such as, "My product delivery is delayed. Please tell me the status." This input is done through the interface on the terminal.

[1017] Step 2:

[1018] The terminal sends the request details entered by the user to the server. This transmission is done via an API and uses a secure communication protocol.

[1019] Step 3:

[1020] The server analyzes the received request using natural language processing techniques. Specifically, it breaks down the request into tokens, performs grammatical analysis, and extracts keywords and important phrases. For example, it identifies keywords such as "delivery," "delay," and "situation."

[1021] Step 4:

[1022] Based on the keywords analyzed by the server, it generates appropriate answer candidates. In this process, the server refers to an internal database and FAQ documents and uses a machine learning model to generate answer candidates. Examples of generated answers include "The reason for the delay in product delivery is insufficient stock" and "There is a temporary problem with the delivery service."

[1023] Step 5:

[1024] The server sends the generated answer candidates to the terminal. The terminal receives them and displays them in the user interface. The user reviews the multiple answer candidates presented.

[1025] Step 6:

[1026] The user selects the answer they deem most appropriate on their device. After selecting, the user can edit the selected answer as needed. For example, they might edit the answer "There is a temporary problem with our delivery service" to "We apologize for the delay in delivery. There is currently a temporary problem with our delivery service."

[1027] Step 7:

[1028] The server receives the edited response and, referencing the customer profile, generates additional service suggestions and information tailored to the company size and type. For example, if the customer is a small business, it might generate a suggestion such as, "We'll give you a 20% discount coupon for your next order."

[1029] Step 8:

[1030] The server sends additional suggestions and information it generates to the user's terminal, where the user can review and edit them. For example, a "20% discount coupon" can be changed to a "30% discount coupon."

[1031] Step 9:

[1032] The user sends their final edited response and additional suggestions to the server via their device. The server receives this and sends the final response to the customer via email, chat, or other means. For example, it might say, "We apologize for the delay in delivery. We are currently experiencing a temporary issue with our delivery service. As an apology, we are offering a 30% discount coupon for your next order."

[1033] In this way, the system enables quick and appropriate customer service, contributing to increased customer satisfaction and improved company sales.

[1034] (Example 1)

[1035] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1036] In today's business environment, responding quickly and appropriately to a wide range of customer inquiries is crucial for improving customer satisfaction and maintaining a company's competitiveness. However, efficiently handling a large volume of inquiries requires an automated response system utilizing advanced natural language processing technology and machine learning models. Furthermore, providing proposals and services tailored to individual customer needs necessitates a flexible system based on the company's size, industry, and customer profile. Developing a system that meets these diverse requirements remains challenging, and many companies have yet to implement one effectively.

[1037] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1038] In this invention, the server includes means for inputting the request details, means for analyzing the request details and generating appropriate response candidates, means for selecting a response from the generated response candidates, means for editing the selected response, means for generating suggestions and information on additional services according to the size and type of business, means for editing the suggestions and information on additional services, and means for transmitting the response and the suggestions and information on additional services. This enables prompt and appropriate customer service.

[1039] "Request details" refers to information about inquiries and requests received by the user from customers.

[1040] "Means of input" refers to the interface or device used by the user to input the details of their request into the system, as well as the method of operating it.

[1041] "Means of analysis" refers to the process and techniques used to analyze the received request using language processing technology and extract the necessary information.

[1042] "Response candidates" refer to several appropriate response options generated based on the analyzed request.

[1043] "Means of selection" refers to the interface or method that allows the user to choose the most suitable response from among the generated candidate responses.

[1044] "Means of editing" refer to tools and functions that allow users to modify or supplement selected responses as appropriate.

[1045] "Proposal for additional services" refers to additional services or offers provided based on customer needs, company size, and business type.

[1046] "Means of generating information" refers to processes and technologies for automatically creating suggestions for additional services and other related information.

[1047] "Means of transmission" refers to the means or methods of communication used to deliver the final edited response or additional service suggestions to the customer.

[1048] "Natural language processing technology" refers to the technology used by computers to understand and analyze natural language and extract relevant information.

[1049] A "machine learning model" is an algorithm that learns patterns based on past data and uses that knowledge to perform inferences and predictions on new data.

[1050] A "customer profile" refers to detailed information about individual customers, such as their past purchase history and behavioral data.

[1051] The system according to this invention provides a comprehensive solution for responding quickly and appropriately to customer inquiries. Specific embodiments of this system are described below.

[1052] First, a terminal is provided that offers an interface for users to input the details of requests received from customers. This interface is built as a web application using HTML and JavaScript. Through this interface, users input the request details in text format. For example, "The delivery of the product is delayed. Please let me know the status."

[1053] The request details entered on the terminal are sent to the server via the internet. The HTTPS protocol is used for this communication, ensuring secure data transfer. Specifically, an Ajax request is generated, and data is sent in JSON format, as shown below.

[1054] json

[1055] {

[1056] "request": "My order is delayed. Please tell me the status."

[1057] }

[1058] The request content that reaches the server is analyzed using natural language processing (NLP) technology. This analysis uses spaCy, a Python NLP library, to tokenize the request content, perform grammatical analysis, and extract important keywords. For example, when tokenizing "My product delivery is delayed. Please tell me the status," the tokens would be "product," "delivery," "delay," "status," and "tell me."

[1059] Next, the server generates appropriate response candidates based on the analyzed keywords and request details. At this stage, it refers to internal databases and FAQ documents, and uses machine learning models. Specifically, it uses machine learning libraries such as TensorFlow and scikit-learn, and models trained on historical data generate the best response. Examples of generated responses include "There is a temporary problem with the delivery service" and "The reason for the delay in product delivery is insufficient stock."

[1060] Once answer suggestions are generated, the server sends them to the user's device. The user reviews the suggested answers on their device and selects the most appropriate one. Furthermore, the user can edit their selected answer. For example, they can change the answer "There is a temporary problem with the delivery service" to "We apologize for the delay in delivery. There is currently a temporary problem with the delivery service."

[1061] In addition, the server generates suggestions for additional services tailored to the company's size and business type. This suggestion generation is performed by retrieving data from CRM systems such as Salesforce, based on customer profiles and past purchase history. Specific examples of suggestions include, "We'll provide you with a 20% discount coupon for your next order." Users can also edit the generated additional suggestions.

[1062] Finally, the user sends the edited response and additional suggestions to the customer. This sending process utilizes email and chat tool APIs. For example, the SendGrid API might be used to send a final message like the following:

[1063] "We sincerely apologize for the delay in delivery. We are currently experiencing a temporary issue with our delivery service. As an apology, we are offering a 30% discount coupon that can be used on your next order."

[1064] This system allows users to respond quickly and accurately, leading to increased customer satisfaction and sales.

[1065] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1066] Step 1:

[1067] The user enters customer requests using their device. The interface is built as a web application, and the user enters the request details into a text box. For example, they might enter, "The product delivery is delayed. Please let me know the status."

[1068] Step 2:

[1069] The terminal sends the entered request details to the server. HTTPS protocol is used for communication, and an Ajax request is generated. The input is in text format and is converted to JSON format upon transmission. Specific request example:

[1070] json

[1071] {

[1072] "request": "My order is delayed. Please tell me the status."

[1073] }

[1074] The output is the data packet sent to the server.

[1075] Step 3:

[1076] The server analyzes the received request using natural language processing techniques. The library used is spaCy in Python, which performs tokenization and grammatical analysis. The input is the request content in JSON format, and the output is extracted keywords. For example, if the input sentence "The delivery of my product is delayed. Please tell me the status" is analyzed, the output will be tokenized as "product", "delivery", "delay", "status", and "tell me".

[1077] Step 4:

[1078] The server generates appropriate answer candidates based on the analyzed keywords and request details. It references an internal database and FAQ documentation and runs a machine learning model using TensorFlow. The input is tokenized keywords, and the output is multiple answer candidates. For example, it might generate answers such as "There is a temporary problem with the delivery service" or "The reason for the delay in product delivery is insufficient stock."

[1079] Step 5:

[1080] The server sends the generated answer suggestions to the user's device. The user's device displays the answer suggestions and provides a confirmation UI. The input is the answer suggestion data, and the output is the confirmation screen the user can view. Specific UI example:

[1081] Option 1: "There is a temporary issue with our delivery service."

[1082] Option 2: "The reason for the delay in product delivery is a shortage of stock."

[1083] Step 6:

[1084] The user selects the most suitable answer from a list of options and edits it. Selection is done on the UI, and editing is done using a text box. The input is the answer options, and the output is the final edited response. For example, "There is a temporary problem with our delivery service" can be edited to "We apologize for the delay in delivery. There is currently a temporary problem with our delivery service."

[1085] Step 7:

[1086] The server generates additional service suggestions tailored to the company's size and business type. This step involves retrieving customer profiles and past purchase history from CRM systems such as Salesforce. The input is customer profile data, and the output is additional service suggestions. A specific example suggestion: "We offer a 20% discount coupon for your next order."

[1087] Step 8:

[1088] The user reviews the generated additional service suggestions and edits them as needed. The input is the suggestion data, and the output is the edited suggestion. For example, it is possible to change "20% discount coupon" to "30% discount coupon".

[1089] Step 9:

[1090] The user edits the response and additional suggestions, which are then sent to the customer as the final message. This sending process uses email service APIs such as SendGrid. The input is the edited response and additional suggestions, and the output is the final message sent to the customer. For example, a message such as, "We apologize for the delay in delivery. We are currently experiencing a temporary issue with our delivery service. As an apology, we are offering a 30% discount coupon for your next order," might be sent.

[1091] By following these steps, users can respond quickly and accurately, leading to increased customer satisfaction and sales.

[1092] (Application Example 1)

[1093] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1094] Modern content delivery services require prompt and appropriate responses to user problems and requests. However, previous systems had drawbacks, such as low efficiency, as they required a lot of manual work to analyze user requests, generate appropriate responses, and propose services tailored to the size and type of company. Furthermore, the lack of a good user interface and the difficulty in effectively utilizing natural language processing technology limited the improvement of user satisfaction.

[1095] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1096] In this invention, the server includes means for inputting the request content, means for analyzing the request content and generating appropriate answer candidates, means for selecting an answer from the generated answer candidates, means for editing the selected answer, means for generating suggestions and information on additional services according to the size and type of business, means for editing the suggestions and information on additional services, means for transmitting the answer and the suggestions and information on additional services, means for providing a user interface for inputting the request content and displaying and editing the answer, means for analyzing the request content using natural language processing technology and generating an appropriate answer by referring to specific documents or databases based on the analysis results, means for using a generation AI model to generate the answer, and means for displaying prompt sentences on the user interface to prompt user input. This enables efficient and automated user support.

[1097] "Request details" refers to the description of the problem or request entered by the user.

[1098] "Analysis" refers to the process of tokenizing and grammatically analyzing the request content entered by the user.

[1099] "Possible responses" are a selection of appropriate responses to the user's request.

[1100] A "user interface" is an interface through which users input their requests and view and edit analysis results and responses.

[1101] "Natural language processing technology" is a technology that analyzes user input and enables computers to understand language that humans speak naturally.

[1102] A "generative AI model" is an artificial intelligence algorithm that learns from past data and generates appropriate responses to user requests.

[1103] A "prompt message" is a sample sentence or input guidance displayed to encourage user input.

[1104] "Additional service proposals" refer to special services or promotions that are suggested based on the company's size, business type, and customer profile.

[1105] A "database" is a system that manages a collection of information, and it is used by the system to understand the content of a request.

[1106] "Editing" is the process of modifying or changing the generated answers or suggested additional services.

[1107] "Sending" refers to the act of sending a final response or proposal to the user or customer.

[1108] The embodiments for carrying out this invention will be described in detail. This system is for automating and streamlining user support in content distribution services. It is composed of the following roles: server, terminal, and user.

[1109] The server first provides a means for inputting the request details. This is an interface where the user inputs problems and requests, and it is embedded in devices such as smartphones, smart glasses, and robots using HTML, CSS, and JavaScript. The input data from this interface is sent to the server via an API.

[1110] Next, the server analyzes the received request using natural language processing technology (such as spaCy or NLTK). This involves tokenizing the request, performing grammatical analysis, and then extracting important keywords and phrases. For example, if the request is "the streaming stops midway," keywords such as "streaming," "midway," and "stop" will be extracted.

[1111] Subsequently, the server uses a generative AI model (e.g., TensorFlow) to generate candidate answers based on the analysis results. These models learn from past data and generate the best possible answers to the user's questions. For example, they might generate answers such as "Please check your network connection" or "Please update to the latest app version."

[1112] The generated response suggestions are sent from the server to the user interface. The user interface provides a means for the user to select a response suggestion and edit it as needed. For example, a text area can be used to allow the user to change the response "Please check your network connection" to "Could you please check your network connection?".

[1113] The server also generates suggestions and information for additional services tailored to the size and type of business. This is done by referencing customer profiles (such as viewing and purchase history). For example, suggestions such as "a 10% discount coupon for your next visit" may be generated. These suggestions are also displayed in the user interface and can be edited by the user.

[1114] Finally, the user's edited response and suggestions for additional services are sent from the server to the customer. This transmission is done using communication methods such as email or chat. For example, a message might be sent in the form of, "Thank you for letting us know about the issue with streaming stopping midway. We are currently asking you to check your network connection. You can also use a 10% discount coupon for your next order."

[1115] Examples of prompt messages used include the following:

[1116] "The streaming stops midway."

[1117] "I can't find the content I'm looking for."

[1118] "Please tell me how to use the app."

[1119] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1120] Step 1:

[1121] The terminal provides an interface for the user to input their request. The user enters the problem or request in the input field. The input data is sent to the server via the API in JSON format. For example, the user might enter "The streaming stops midway."

[1122] Step 2:

[1123] The server analyzes the received request using natural language processing techniques (e.g., spaCy or NLTK). Specifically, it tokenizes the input text, performs grammatical analysis, and extracts important keywords and phrases. In this case, the input data "streaming stops midway" is tokenized into "streaming," "midway," and "stop."

[1124] Step 3:

[1125] The server references databases and FAQ documents based on the analysis results and generates answer candidates using a generative AI model (e.g., TensorFlow). For example, it might generate answers such as "Please check your network connection" or "Please update to the latest app version."

[1126] Step 4:

[1127] The server sends the generated answer suggestions to the user interface. The user interface displays the answer suggestions to the user. At this time, the user interface displays a prompt message to encourage user feedback and editing. For example, the answer suggestion "Please check your network connection" might be displayed in the text area.

[1128] Step 5:

[1129] The user selects the most appropriate answer from the displayed options and edits it as needed. The edited answer is then sent back to the server. For example, "Please check your network connection" can be edited to "Could you please check your network connection?".

[1130] Step 6:

[1131] The server generates additional service suggestions based on the company's size and business type. To do this, it refers to customer profiles (such as viewing and purchase history) to determine appropriate suggestions. For example, it might generate a suggestion such as "a 10% discount coupon for your next visit."

[1132] Step 7:

[1133] The server sends the generated additional service suggestions to the user interface. The user interface displays them and allows the user to edit them. For example, the displayed "10% discount coupon" can be changed to a "15% discount coupon".

[1134] Step 8:

[1135] The user then reviews the edited response and any suggested additional services and sends them to the customer. The server then sends the reviewed information to the customer via email, chat, or other means of communication. For example, it might say, "Thank you for letting us know about the issue with the streaming stopping midway. We are currently asking you to check your network connection. You can also use a 10% discount coupon for your next order."

[1136] This series of processes allows users to respond to customers quickly and effectively.

[1137] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1138] The embodiments for carrying out the present invention will be described in detail. This invention combines a system that takes a request as input, analyzes it, generates appropriate response candidates, and also provides suggestions and information on additional services tailored to the size and type of company with an emotion engine that recognizes the user's emotions.

[1139] First, the user enters their request into the device. For example, they might enter, "My delivery is delayed. Please tell me the status." During this input process, the device uses its built-in emotion engine to recognize the user's emotions. This emotion information is extracted through voice and text analysis.

[1140] Next, the terminal sends emotional information along with the request to the server. The server analyzes the received request using natural language processing technology to understand its meaning and extract important keywords and phrases. For example, it identifies keywords such as "delivery," "delay," and "situation."

[1141] Based on the analysis results, the server uses a machine learning model to generate appropriate response candidates. This generation process also takes into account the user's sentiment information. For example, if sentiment data indicates the user is dissatisfied, responses that include an apology will be prioritized. For instance, a response such as "We are experiencing a temporary problem with our delivery service. We sincerely apologize" might be generated.

[1142] The server generates suggested responses, which are sent to the terminal and presented to the user. The user selects the most suitable response from the presented options and edits it as needed. For example, they might edit it to include specific wording such as, "We apologize for the delay in delivery. We are currently experiencing a temporary issue with our delivery service."

[1143] Next, the server generates additional service suggestions and information based on the customer profile, tailored to the company size and type of business. Sentimental information is also considered in this suggestion generation process, ensuring that the most appropriate suggestions are made in response to the user's emotions. For example, if the user appears very dissatisfied, a suggestion such as "We offer a 30% discount coupon for your next order" will be generated.

[1144] The generated additional suggestions and information are also sent to the user's device, where the user can review and edit them as needed. For example, it is possible to change a "30% discount coupon" to a "40% discount coupon."

[1145] Finally, the user sends their edited response and additional suggestions to the server via their device. The server receives this and sends the final response to the customer via email, chat, or other means. For example, it might say, "We apologize for the delay in delivery. We are currently experiencing a temporary issue with our delivery service. As an apology, we are offering a 40% discount coupon that can be used on your next order."

[1146] Thus, by combining the system of the present invention with an emotion engine, it is possible to achieve prompt and appropriate customer service that takes customer emotions into consideration, thereby improving customer satisfaction and corporate sales.

[1147] The following describes the processing flow.

[1148] Step 1:

[1149] The user enters their request into the terminal. The input interface of the terminal will contain a request such as, "My product delivery is delayed. Please tell me the status." The terminal is also equipped with an emotion engine that recognizes the user's emotions during input through voice and facial expression analysis. It also analyzes emotions from text input.

[1150] Step 2:

[1151] The terminal sends the entered request details and emotional information to the server. This data is transmitted using a secure communication protocol, ensuring data security.

[1152] Step 3:

[1153] The server analyzes the received request using natural language processing technology. Specifically, it breaks down the input request into tokens and analyzes its grammatical structure. It extracts important keywords and phrases and identifies elements such as "delivery," "delay," and "situation."

[1154] Step 4:

[1155] The server generates appropriate response options based on the analyzed request content and sentiment information. This process references internal databases and FAQ documents. For example, if dissatisfaction is detected, a response option including an apology, such as "We are experiencing a temporary problem with our delivery service. We sincerely apologize," will be generated.

[1156] Step 5:

[1157] The server sends the generated answer candidates to the terminal. The terminal displays the received answer candidates in the user interface, presenting the user with multiple answer options.

[1158] Step 6:

[1159] The user selects the most suitable answer from the suggested answers displayed on their device. After selection, they can edit the selected answer as needed. For example, they can change the answer "There is a temporary problem with our delivery service" to a more specific wording such as "We apologize for the delay in delivery. There is currently a temporary problem with our delivery service."

[1160] Step 7:

[1161] The server receives the user's edited responses and, referencing the customer profile, generates additional service suggestions and information tailored to the company's size and business type. Sentimental information is also considered, ensuring that the most appropriate suggestions are made based on the user's emotions. For example, if the user appears very dissatisfied, additional suggestions including a perk such as "We'll provide you with a 30% discount coupon for your next order" are generated.

[1162] Step 8:

[1163] The server sends additional suggestions and information it generates to the user's terminal, where the user can review and edit them. For example, the user can edit an additional suggestion, such as changing a "30% discount coupon" to a "40% discount coupon."

[1164] Step 9:

[1165] The user sends their final edited response and additional suggestions to the server via their device. The server receives this and sends the final response to the customer via a communication method such as email or chat. For example, the customer might receive a message such as, "We apologize for the delay in delivery. We are currently experiencing a temporary issue with our delivery service. As an apology, we are offering a 40% discount coupon that can be used on your next order."

[1166] In this way, by combining an emotion engine, the system provides quick and appropriate responses that take customer emotions into account, resulting in increased customer satisfaction and improved company sales.

[1167] (Example 2)

[1168] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1169] Traditional customer service systems simply process customer requests without considering customer emotions. This makes it difficult to achieve sufficient customer satisfaction, hindering the company's ability to build trust and increase sales.

[1170] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for analyzing the request content and generating appropriate response candidates, means for recognizing the user's emotions, and means for generating response candidates while considering the emotional information. This enables a quick and appropriate response that takes into account the customer's emotions, thereby improving customer satisfaction and enhancing the company's credibility.

[1171] "Request details" refer to the information and requirements that the user enters into the system.

[1172] "Emotional information" refers to data obtained by analyzing a user's emotions and feelings.

[1173] "Natural language processing technology" is a technology that analyzes text data and helps it understand meaning and context.

[1174] A "machine learning model" is an algorithm or framework that learns from data and performs predictions and classifications.

[1175] "Possible responses" refer to appropriate replies or suggested actions in response to a request.

[1176] "Company size and type" refers to the size of a company (for example, a small or medium-sized enterprise, or a large corporation) and its business operations.

[1177] A "customer profile" is data that records a customer's personal information, purchase history, preferences, and other details.

[1178] A "proposal for additional services" refers to a proposal for additional services or benefits that a company can offer.

[1179] A "system" is a set of devices or programs designed to achieve a specific purpose.

[1180] A "user" is an individual or organization that uses the system to input request details.

[1181] A "server" is the central device of a system, responsible for processing and managing data.

[1182] Modes for carrying out the invention

[1183] The system of the present invention analyzes the user's request, generates appropriate response candidates that take emotional information into consideration, and proposes additional services tailored to the size and type of business. The embodiments for carrying out the present invention are described in detail below.

[1184] System Configuration

[1185] This system broadly includes the following main components:

[1186] A means (terminal) for entering request details.

[1187] A means of recognizing user emotions (emotion engine)

[1188] A method (server) for analyzing request content using natural language processing technology.

[1189] A method (server) for generating answer candidates using a machine learning model.

[1190] A server for generating proposals for additional services tailored to the size and type of business.

[1191] Means for transmitting and receiving various types of data (terminals, servers)

[1192] Hardware and software configuration

[1193] The following hardware and software will be used to implement this system.

[1194] Terminal: A device used by users to input request details. This includes personal computers and smartphones.

[1195] Emotion engine: Software used to recognize user emotions. Examples include IBM Watson Tone Analyzer and Microsoft Text Analytics.

[1196] Server: A device that analyzes the request content and generates answer candidates and additional service suggestions. It can use the Google Cloud Natural Language API to implement natural language processing technology and OpenAI's GPT series for answer candidate generation.

[1197] Communication method: Internet connection for data transmission between terminal and server.

[1198] Data processing and data calculation

[1199] The operation of this system follows the steps below.

[1200] 1. Enter the request details and emotional information:

[1201] The user enters their request details into their device. During this process, an emotion engine is used to analyze and recognize the user's emotional information.

[1202] 2. Sending data:

[1203] The device sends the request details and sentiment information to the server. This data is transmitted securely using a standard communication protocol (e.g., HTTPS).

[1204] 3. Analysis using natural language processing:

[1205] The server analyzes the received request using natural language processing technology and extracts important keywords and phrases.

[1206] 4. Generating answer candidates:

[1207] Based on the analyzed keywords and sentiment information, the server uses a machine learning model (e.g., OpenAI's GPT series) to generate appropriate response candidates. The generated response candidates take the user's sentiment into account; for example, if the user expresses dissatisfaction, a response including an apology will be provided.

[1208] 5. Generating proposals for additional services:

[1209] Based on the company profile, the server generates suggestions and information for additional services tailored to the company's size and business type. Sentimental information is also taken into consideration; for example, if a user is highly dissatisfied, a suggestion such as "We will provide you with a 30% discount coupon that you can use on your next order" will be generated.

[1210] Specific examples and prompt statements

[1211] To illustrate the specific operation, the following are examples of concrete actions and prompt statements.

[1212] Specific example:

[1213] User input: "My order is delayed. Please tell me the status."

[1214] Emotion engine's recognition result: "Dissatisfaction"

[1215] Keyword extraction using natural language processing: "delivery," "delay," "situation"

[1216] Suggested response: "We are experiencing a temporary issue with our delivery service. We sincerely apologize."

[1217] Example of a prompt:

[1218] "Your delivery is delayed. Please let me know the status."

[1219] "There is an error in the invoice. Please check it."

[1220] "My ordered item hasn't arrived yet. What's going on?"

[1221] "The service wasn't what I expected. Why?"

[1222] Based on the above explanation, this system can provide prompt and appropriate customer service that takes user emotions into consideration, thereby improving customer satisfaction, corporate credibility, and sales.

[1223] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1224] Step 1:

[1225] The user enters their request into the terminal. For example, they might enter, "My product delivery is delayed. Please tell me the status." This input data becomes the starting point for the system's processing.

[1226] Step 2:

[1227] The terminal uses an emotion engine to recognize the user's emotions based on the input request. Examples of emotion engines used include IBM Watson Tone Analyzer and Microsoft Text Analytics. At this stage, the request content is passed to the emotion engine as input data, and emotion information such as "dissatisfied" is obtained as output.

[1228] Step 3:

[1229] The terminal sends the entered request details and recognized emotion information to the server. The data is sent, for example, via the HTTPS protocol. The input data consists of the request details and emotion information, and the output is the transmission of data to the server.

[1230] Step 4:

[1231] The server analyzes the received request using natural language processing technology. One example of this technology is the Google Cloud Natural Language API. The input data is the request content, and the output is important keywords and phrases (e.g., "delivery," "delay," "status").

[1232] Step 5:

[1233] The server uses the analyzed keywords and sentiment information to generate appropriate response candidates using a machine learning model (e.g., OpenAI's GPT series). The input data consists of keywords and sentiment information, and the output is the generated response candidates (e.g., "We are experiencing a temporary problem with our delivery service. We sincerely apologize.").

[1234] Step 6:

[1235] The server sends the generated answer candidates to the terminal. The input data is the answer candidates, and the output is the transmission of data to the terminal.

[1236] Step 7:

[1237] The user reviews the suggested answers presented on their device and edits them as needed. The input data is the presented answer candidates, and the output is the user's final edited answer (e.g., "We apologize for the delay in delivery. We are currently experiencing a temporary issue with our delivery service.").

[1238] Step 8:

[1239] After the server receives the edited response, it generates additional service suggestions tailored to the company size and type based on the customer profile. The input data is the edited response and customer profile, and the output is the generated additional suggestion (e.g., "We'll give you a 30% discount coupon for your next order").

[1240] Step 9:

[1241] The server sends the generated additional suggestions to the terminal and presents them to the user. The input data is the additional suggestions, and the output is the data transmission to the terminal.

[1242] Step 10:

[1243] Users can review the presented additional suggestions and edit them as needed. The input data is the presented additional suggestions, and the output is the final suggestion edited by the user (e.g., "40% discount coupon").

[1244] Step 11:

[1245] The user submits their final edited response and suggestions to the server. The input data is the final response and suggestions, and the output is the data submission to the server.

[1246] Step 12:

[1247] The server sends the final response to the customer. The final response is delivered to the customer via communication methods such as email or chat. The input data is the final response and proposal, and the output is what is sent to the customer. For example, it might say, "We apologize for the delay in delivery. We are currently experiencing a temporary problem with our delivery service. As an apology, we are offering a 40% discount coupon that can be used on your next order."

[1248] (Application Example 2)

[1249] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1250] Traditional customer service systems had limitations in generating appropriate responses to requests, and particularly struggled to respond to users' emotions. Furthermore, providing appropriate additional suggestions and information was difficult, resulting in a lack of means to improve customer satisfaction. As a result, customer dissatisfaction accumulated, potentially negatively impacting the company's sales and brand image.

[1251] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1252] In this invention, the server includes means for inputting the request content, means for recognizing the user's emotions based on the request content, means for analyzing the request content and generating appropriate response candidates, means for selecting a response from the generated response candidates, means for editing the selected response, means for generating additional suggestions and information according to the company size and type of business, means for editing the additional suggestions and information, and means for transmitting the response and the additional suggestions and information. This enables prompt and appropriate customer service that responds to the user's emotions, thereby improving customer satisfaction and corporate sales.

[1253] "Request details" refers to the information or problem-solving needs that users seek regarding a service or product.

[1254] "Means of recognizing emotions" refers to technology that analyzes the user's emotional state from their input and has the function of determining a specific emotion (such as joy, anger, or sadness).

[1255] "Methods for generating response candidates" refer to analytical engines or algorithms used to generate multiple appropriate responses to a request.

[1256] "Means of selecting an answer" refers to the interface or function used to choose the most appropriate answer from the generated list of candidates.

[1257] "Means for editing answers" refers to a function that allows users to modify or change selected answers as appropriate.

[1258] "Means for generating additional suggestions and information" refers to analytical engines and algorithms for generating and providing services and information tailored to the size and type of business of the company.

[1259] "Means for editing additional suggestions and information" refers to functions that allow users to modify or change generated additional suggestions and information as needed.

[1260] "Means of transmission" refers to communication functions used to convey generated responses and additional suggestions to users and customers.

[1261] "Natural language processing technology" refers to technologies that understand and analyze human language and perform appropriate information processing based on that understanding.

[1262] A "machine learning model" refers to artificial intelligence technology that learns from large amounts of data to solve problems and make predictions.

[1263] A "customer profile" refers to a database that includes customer behavior history and attribute information.

[1264] "Food delivery" refers to a service that delivers food and beverages to a specific location.

[1265] This invention is a system that provides prompt and appropriate customer service in the food delivery field, taking into account the user's emotions. As mentioned above, this system handles the input of the request, recognition of emotions, generation of appropriate response candidates, and generation of additional suggestions and information.

[1266] Specifically, the process begins with the user entering their request using a smartphone or other device, and the system receiving this information. For example, the user might enter, "My pizza order is late and I'm getting frustrated. Please tell me what's happening." Based on this request, the system's emotion recognition engine analyzes the user's emotions and extracts emotional information.

[1267] The analyzed sentiment information and request details are sent to the server. The server uses natural language processing techniques to analyze the request details and extract key keywords. This process utilizes the Python TextBlob library. For example, keywords such as "order," "pizza," "delay," and "situation" are identified.

[1268] Next, the server uses Hugging Face's sentiment analysis model to analyze the user's emotional information. After identifying the emotion, the server uses a machine learning model to generate appropriate response candidates. In this process, the user's emotional information is given special consideration, resulting in responses such as, "We apologize for the delay in delivery. We are currently investigating the situation."

[1269] The suggested answers are sent to the user's device, where they can review and edit them as needed. This editing function allows users to modify the suggested answers as appropriate and optimize them for submission.

[1270] Subsequently, the server generates additional suggestions tailored to the company size and industry based on the customer profile and user sentiment information. This may include information such as, "We offer a 30% discount coupon that can be used on your next order."

[1271] The generated additional suggestions and information are sent back to the user's device, where the user reviews and edits them as needed. The final response and additional suggestions are then sent to the customer via the server.

[1272] In summary, this system effectively combines an emotion recognition engine, natural language processing, and machine learning models to quickly provide responses tailored to customer needs and improve customer satisfaction. Key hardware and software used include Python, TextBlob, Hugging Face Transformers, and smartphones.

[1273] Examples of prompt statements include:

[1274] "My pizza order is delayed, could you please tell me what's happening?"

[1275] "It's been two hours since I placed my order, why hasn't it arrived yet?"

[1276] "I would like to be notified if there is a delay in delivery."

[1277] As described above, the system of the present invention aims to improve the quality of customer service in the food delivery sector by enabling responses that take customer emotions into consideration.

[1278] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1279] Step 1:

[1280] Users enter their requests using a smartphone or other device. The input includes problems and requests in text or audio format. For example, one user might enter, "My pizza order is late and I'm getting frustrated. Please tell me what's happening."

[1281] Input: User's request (text or voice)

[1282] Output: Input request details

[1283] Step 2:

[1284] The terminal receives the input request and analyzes the user's emotions using an emotion recognition engine. This analysis employs algorithms that extract emotions from voice and text. For example, the emotion "irritated" might be identified.

[1285] Input: User's request (text or voice)

[1286] Output: Analyzed sentiment information

[1287] Step 3:

[1288] The terminal sends the analyzed sentiment information and request details to the server. The server analyzes the request details using natural language processing techniques and extracts important keywords and phrases. For example, keywords such as "order," "pizza," and "delay" may be identified.

[1289] Input: Request details and emotional information

[1290] Output: Analyzed keywords and phrases

[1291] Step 4:

[1292] The server generates appropriate response candidates based on keywords and sentiment information analyzed using a machine learning model. Sentiment information is given particular consideration, and responses including apologies are prioritized if dissatisfaction is strong. For example, a response such as "We apologize for the delay in delivery. We are currently investigating the situation" might be generated.

[1293] Input: Analyzed keywords and sentiment information

[1294] Output: Generated answer candidates

[1295] Step 5:

[1296] The server sends the generated response options to the terminal. The user reviews the suggested responses and modifies / edits them as needed. For example, they might edit them to include more specific wording, such as "We are currently checking the delivery status."

[1297] Input: Generated answer suggestions

[1298] Output: User-edited response

[1299] Step 6:

[1300] Next, the server generates additional suggestions and information tailored to the company size and type, based on customer profiles and user sentiment information. For example, it might generate a suggestion such as, "We'll give you a 30% discount coupon for your next order."

[1301] Input: Customer profile and sentiment information

[1302] Output: Generated additional suggestions and information

[1303] Step 7:

[1304] The server sends the generated additional suggestions and information to the terminal, where the user reviews and edits them as needed. For example, they might change "30% discount coupon" to "40% discount coupon."

[1305] Input: Generated additional suggestions and information

[1306] Output: Additional suggestions and information edited by the user.

[1307] Step 8:

[1308] Finally, the user's edited response and additional suggestions are sent to the server, which receives them and forwards them to the customer via email, chat, or other methods. For example, a message might be sent saying, "We apologize for the delay in delivery. We are currently experiencing a temporary issue with our delivery service. As an apology, we will provide you with a 40% discount coupon for your next order."

[1309] Input: User-edited answers and additional suggestions

[1310] Output: Final response and additional suggestions (to be sent to the customer)

[1311] Through the steps outlined above, prompt and appropriate customer service that takes user emotions into consideration is achieved.

[1312] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1313] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1314] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1315] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1316] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1317] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1318] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1319] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1320] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1321] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1322] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1323] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1324] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1325] 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.

[1326] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1327] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1328] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1329] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1330] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1331] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1332] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[1333] The following is further disclosed regarding the embodiments described above.

[1334] (Claim 1)

[1335] A means of entering the request details,

[1336] A means for analyzing the aforementioned request and generating appropriate response candidates,

[1337] A means for selecting an answer from the generated candidate answers,

[1338] Means for editing the selected response,

[1339] A means of generating proposals and information for additional services tailored to the size and type of business,

[1340] A means of compiling proposals and information for the aforementioned additional services,

[1341] Means for sending the above response and the above-mentioned proposals and information for additional services

[1342] Includes system.

[1343] (Claim 2)

[1344] The request details were analyzed using natural language processing technology.

[1345] Generate answer candidates using a machine learning model.

[1346] The system according to claim 1.

[1347] (Claim 3)

[1348] In generating proposals tailored to company size and business type,

[1349] Refer to customer profiles

[1350] The system according to claim 1.

[1351] "Example 1"

[1352] (Claim 1)

[1353] A means of entering the request details,

[1354] A means for analyzing the aforementioned request and generating appropriate response candidates,

[1355] Means for selecting a response from the generated candidate responses,

[1356] Means for editing the selected response,

[1357] A means of generating proposals and information for additional services tailored to the size and type of business,

[1358] A means of compiling proposals and information for the aforementioned additional services,

[1359] Means for transmitting the above response and the above-mentioned proposals and information for additional services

[1360] Includes system.

[1361] (Claim 2)

[1362] The request details were analyzed using natural language processing technology.

[1363] Generate response candidates using machine learning models

[1364] The system according to claim 1.

[1365] (Claim 3)

[1366] In generating proposals tailored to company size and business type,

[1367] Refer to customer profiles

[1368] The system according to claim 1.

[1369] "Application Example 1"

[1370] (Claim 1)

[1371] A means of entering the request details,

[1372] A means for analyzing the aforementioned request and generating appropriate response candidates,

[1373] A means for selecting an answer from the generated candidate answers,

[1374] Means for editing the selected response,

[1375] A means of generating proposals and information for additional services tailored to the size and type of business,

[1376] A means of compiling proposals and information for the aforementioned additional services,

[1377] A means for transmitting the aforementioned response and the aforementioned proposals and information on additional services,

[1378] Means for providing a user interface for inputting the details of the request and displaying and editing the response,

[1379] A means for analyzing the aforementioned request using natural language processing technology, and generating an appropriate response by referring to specific documents or databases based on the analysis results,

[1380] Means for using a generative AI model to generate the aforementioned answer,

[1381] A means for displaying a prompt message on the user interface to prompt user input,

[1382] A system that includes this.

[1383] (Claim 2)

[1384] The request details were analyzed using natural language processing technology.

[1385] Generate answer candidates using a machine learning model.

[1386] The system according to claim 1.

[1387] (Claim 3)

[1388] In generating proposals tailored to company size and business type,

[1389] Refer to customer profiles

[1390] The system according to claim 1.

[1391] "Example 2 of combining an emotion engine"

[1392] (Claim 1)

[1393] A means of entering the request details,

[1394] A means for analyzing the aforementioned request and generating appropriate response candidates,

[1395] A means for selecting an answer from the generated candidate answers,

[1396] Means for editing the selected response,

[1397] A means of generating proposals and information for additional services tailored to the size and type of business,

[1398] A means of compiling proposals and information for the aforementioned additional services,

[1399] Means for sending the above response and the above-mentioned proposals and information for additional services

[1400] A system that includes,

[1401] Means of recognizing user emotions,

[1402] A means for generating response candidates while taking the aforementioned emotional information into consideration,

[1403] A means for generating suggestions for additional services, taking into account the aforementioned emotional information.

[1404] include

[1405] system.

[1406] (Claim 2)

[1407] The request details were analyzed using natural language processing technology.

[1408] Generate answer candidates using a machine learning model.

[1409] The system according to claim 1.

[1410] (Claim 3)

[1411] In generating proposals tailored to company size and business type,

[1412] Refer to customer profiles

[1413] The system according to claim 1.

[1414] "Application example 2 when combining with an emotional engine"

[1415] (Claim 1)

[1416] A means of entering the request details,

[1417] A means for recognizing the user's emotions based on the aforementioned request,

[1418] A means for analyzing the aforementioned request and generating appropriate response candidates,

[1419] A means for selecting an answer from the generated answer candidates,

[1420] Means for editing the selected response,

[1421] A means of generating additional proposals and information tailored to the size and type of business,

[1422] The means of editing the aforementioned additional suggestions and information,

[1423] The means of transmitting the above response and the above additional suggestions and information

[1424] Includes system.

[1425] (Claim 2)

[1426] The request details were analyzed using natural language processing technology.

[1427] Generate answer candidates using a machine learning model.

[1428] The system according to claim 1.

[1429] (Claim 3)

[1430] In generating proposals tailored to company size and business type,

[1431] Referencing customer profiles and user sentiment information.

[1432] The system according to claim 1. [Explanation of symbols]

[1433] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of entering the request details, A means for analyzing the aforementioned request and generating appropriate response candidates, A means for selecting an answer from the generated candidate answers, Means for editing the selected response, A means of generating proposals and information for additional services tailored to the size and type of business, A means of compiling proposals and information for the aforementioned additional services, Means for sending the above response and the above-mentioned proposals and information for additional services Includes system.

2. The request details were analyzed using natural language processing technology. Generate answer candidates using a machine learning model. The system according to claim 1.

3. In generating proposals tailored to company size and business type, Refer to customer profiles The system according to claim 1.

Images