system

Abstract

We provide the system. [Solution] A natural language processing method that automatically analyzes customer inquiries, A response generation means that generates an appropriate automatic response based on the content analyzed by the analysis means, A sentiment analysis tool for identifying emotions from the aforementioned customer inquiry, A tone adjustment means that adjusts the tone of the response generated by the response generation means in accordance with the emotion identified by the emotion analysis means, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In many modern enterprises, a quick and accurate response to inquiries from customers is required. However, the conventional manual response takes time for the response, and there is a problem that the quality of the response varies depending on the person in charge. In addition, it is difficult to accurately judge the emotions of customers and respond appropriately, which has led to a decrease in customer satisfaction. To solve these problems, a quick and consistent response by an automated system is required.

Means for Solving the Problems

[0005] This invention provides a response generation means that automatically analyzes customer inquiries using natural language processing technology and generates appropriate responses based on the analysis results. Furthermore, it incorporates an emotion analysis means that identifies customer emotions from inquiries and utilizes a tone adjustment means that adjusts the tone of the response according to the identified emotions, thereby achieving consistent and personalized support for customers. This makes it possible to achieve both rapid response and improved customer satisfaction simultaneously.

[0006] "Natural language processing means" refers to methods for automatically processing queries using techniques that analyze text data and understand the structure and meaning of language.

[0007] A "response generation means" is a means of automatically creating an appropriate response to an inquiry and performing the necessary processing to present it to the customer.

[0008] "Sentiment analysis tools" refer to methods that provide technologies and processes for extracting and identifying emotions from customer inquiry texts.

[0009] "Tone adjustment means" refers to methods for adjusting the tone and style of responses that are automatically generated based on emotion analysis, in order to maintain appropriate dialogue quality.

[0010] "Transmission means" refers to means of using communication protocols and technologies to transmit the generated response to the customer's terminal.

[0011] "Data recording means" refers to means that provide storage and processes for saving inquiry content and related sentiment data, and preparing them for later analysis and reference. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2]This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, the labeled 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.

[0016] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0018] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0019] 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."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] 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.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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".

[0033] This invention is a generative AI-based solution that fully automates a company's customer support system, aiming to respond to customer inquiries quickly and accurately. The system uses natural language processing technology to analyze inquiry content, generate responses, perform sentiment analysis, and adjust tone, thereby achieving sophisticated customer service.

[0034] First, the user accesses the support system and enters their inquiry into the chat window. For example, "How do I get a refund for my product?" Once the inquiry is sent, the device transfers the entered text data to the server.

[0035] Subsequently, the server analyzes the received text using natural language processing to understand the customer's intent. Based on this analysis, the server uses response generation tools to generate an appropriate response. The generated response provides relevant information based on the customer's inquiry.

[0036] Next, the server uses sentiment analysis tools to identify the customer's emotions from their language and context. This analysis allows the server to determine whether the customer's emotions are in a state such as "dissatisfaction," "doubt," or "gratitude." The results of this sentiment analysis are used to deliver a response to the customer in an appropriate tone. The server uses tone adjustment tools to adjust the tone of the response and provide appropriate communication to the customer.

[0037] Finally, the server uses a transmission method to send the generated response and text with an adjusted tone to the terminal. The terminal receives this and displays it to the user. For example, the displayed message might say, "If you would like a refund for your order, please follow these steps," with the wording becoming gentler or more polite depending on the user's emotions.

[0038] Furthermore, this system is equipped with data recording capabilities, allowing the server to record all inquiry details and sentiment data, which can then be used for later analysis and service improvement.

[0039] This system allows companies to significantly improve the efficiency of customer support and achieve higher customer satisfaction.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The user opens the customer support chat window and enters their inquiry. For example, they might enter a specific question such as, "How do I exchange a product?"

[0043] Step 2:

[0044] The terminal retrieves text data entered by the user and sends it to the server. The terminal uses a REST API to serialize the query content in JSON format and send it to the server.

[0045] Step 3:

[0046] The server receives data sent from the terminal and passes it to a natural language processing system to analyze the query. Here, the server checks the data format and filters out unnecessary information.

[0047] Step 4:

[0048] The natural language processing system installed on the server analyzes the query content and understands the user's intentions. It understands what the query is requesting and prepares to select relevant information from the database.

[0049] Step 5:

[0050] The server uses a response generation mechanism to construct an appropriate response based on the analysis results. For example, it combines necessary information, such as policies and procedures related to product exchange, to create a response.

[0051] Step 6:

[0052] The server uses sentiment analysis tools to extract emotions from user inquiries. Based on the linguistic expression of the inquiry, it determines whether the user is experiencing emotions such as "anxiety" or "doubt."

[0053] Step 7:

[0054] The server uses tone adjustment mechanisms to appropriately adjust the tone of responses based on the results of sentiment analysis. For example, if the user is showing anxiety, the response will be made more reassuring.

[0055] Step 8:

[0056] The server prepares to send the completed response to the terminal and sends it to the terminal using the transmission method. The response is then converted back to JSON format and sent to the terminal.

[0057] Step 9:

[0058] The terminal receives the response sent from the server and displays it in the user's chat window. Based on the displayed information, the user can receive appropriate instructions and complete the support process.

[0059] (Example 1)

[0060] 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."

[0061] In today's world, there is a demand for prompt and accurate responses to customer inquiries. However, conventional systems struggle to efficiently handle a large volume of inquiries, potentially leading to decreased customer satisfaction. Furthermore, the lack of flexible responses tailored to the user's emotions results in inconsistent service quality.

[0062] 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.

[0063] In this invention, the server includes language processing means for automatically analyzing information from users, information generation means for generating appropriate responses, and information analysis means for identifying emotions. This enables rapid and accurate analysis of user inquiries and the provision of appropriate responses tailored to the user's emotions.

[0064] "Users" refer to individuals or organizations that access the system and use its services.

[0065] "Information" refers to data and inquiries provided by users, and is the subject of language processing and analysis.

[0066] "Processing means" refers to technical methods and devices for analyzing information and performing appropriate data processing.

[0067] "Language processing means" refers to methods and technological devices for analyzing natural language and understanding information.

[0068] "Information generation means" refers to methods and technical devices for generating appropriate responses based on analyzed information.

[0069] "Information analysis means" refers to methods and technological devices used to analyze user information and specifically identify emotions.

[0070] "Adjustment means" refers to methods or technical devices for changing the nature or tone of the generated response according to the situation.

[0071] "Reference means" refers to methods and technical devices for querying related materials and databases based on the analyzed information.

[0072] "Generation means" refers to methods and technical devices for optimizing answers generated using a pre-trained artificial intelligence model.

[0073] "Transmission means" refers to methods or technical devices for transmitting the generated response to the user's display device.

[0074] "Data processing means" refers to methods, technologies, and devices for handling recorded and analyzed information and utilizing it for operation and improvement.

[0075] The system in this invention automates customer support for businesses, enabling them to respond to user inquiries quickly and accurately. This system primarily communicates between a server, a terminal, and a user, and operates through multiple stages of processing.

[0076] The server first receives data sent from the user. It uses natural language processing (NLP) software, such as spaCy or Transformers, which are well-known NLP libraries for Python. To quickly analyze the received text, the server uses these libraries to perform syntactic and semantic analysis.

[0077] Once the analysis is complete, the server generates a response based on the generated data. This process utilizes a generative AI model. For example, it leverages advanced models such as OpenAI's GPT-3 to generate a natural response based on the analyzed content. The generated response is further optimized by information generation means.

[0078] Next, the server uses sentiment analysis tools to determine the emotion behind the user's statements. Software such as VADER and TextBlob is used for sentiment analysis. Based on the analyzed sentiment information, the generated response is tone-adjusted to make it more personalized.

[0079] The generated response is sent to the terminal and displayed to the user. This process takes place via WebSocket or HTTP requests, and the terminal presents the provided information to the user. The wording and tone of the presentation are adjusted according to the customer's mood.

[0080] Furthermore, the server records all inquiry and sentiment data, which can then be used for later analysis and logistics improvements. This allows companies to significantly improve the efficiency of customer service and increase customer satisfaction.

[0081] As a concrete example, here is an example of a prompt sentence to be input into the generation AI model: "When a user inquires about how to get a refund for a product, analyze the customer's emotions and generate a response in an appropriate tone."

[0082] Thus, this invention utilizes natural language processing technology and AI generation technology to realize an automated response system for user inquiries.

[0083] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0084] Step 1:

[0085] The user accesses the customer support system and enters their inquiry into the chat window. At this point, the entered information is sent to the server as text data. For example, suppose the user enters the inquiry, "How do I get a refund for this product?" At this stage, the user has entered information, and its output is processed as text data.

[0086] Step 2:

[0087] The terminal transfers the text data entered by the user to the server. This data is transmitted via WebSocket or HTTP requests. The input is the user's inquiry text, and the output is sending this text data to the server. Through this process, the terminal acts as a bridge, conveying the user's intent to the server.

[0088] Step 3:

[0089] The server performs natural language processing on the received text data. Specifically, it uses Python libraries such as spaCy and Transformers to perform syntactic and semantic analysis. The input is the user's query text, and the output is the parsed text data. Through this analysis, the server accurately understands the user's intent.

[0090] Step 4:

[0091] The server generates a response based on the analyzed data. This process utilizes a generative AI model, such as OpenAI's GPT-3. The input is the analysis result, and the output is a response message based on the user's intent. At this stage, a prompt is input to the generative AI model to generate an appropriate message.

[0092] Step 5:

[0093] The server then performs sentiment analysis to adjust the tone of its responses. Tools such as VADER and TextBlob are used for sentiment analysis. The input is the user's text data, and the output is sentiment information associated with that text. This sentiment information is used to adjust the tone of the responses to better reflect the user's emotions.

[0094] Step 6:

[0095] The server sends the final response message to the terminal and displays it to the user. The response is transmitted quickly via WebSocket or HTTP response. The input is the tone-adjusted response, and the output is what is displayed to the user. The terminal displays this message in the chat window so that the user can see it.

[0096] Step 7:

[0097] The server records all inquiries and sentiment data in a database. This data is later analyzed and used to improve services and enhance the quality of customer support. The input consists of inquiry content and sentiment data, which are stored in the database. This process allows the server to accumulate resources for future analysis.

[0098] (Application Example 1)

[0099] 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."

[0100] Responding to customer inquiries is crucial for businesses, but it also requires significant effort and cost. E-commerce sites, in particular, experience frequent customer inquiries and demand prompt and accurate responses. However, relying solely on human resources has its limitations, and it's difficult to provide responses that truly address customer needs and emotions. Therefore, there is a need to develop systems that efficiently handle customer inquiries without compromising the customer experience.

[0101] 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.

[0102] In this invention, the server includes information processing means for automatically analyzing customer inquiries, response generation means for generating appropriate automatic responses based on the analyzed content, analysis means for identifying emotions from inquiries, adjustment means for adjusting the method of transmitting the response according to the emotions identified by the analysis means, and display control means for displaying the response on the customer terminal in real time on the e-commerce site. This makes it possible to automatically provide appropriate and rapid responses that correspond to the customer's emotions.

[0103] "Information processing means" refers to technical methods for automatically analyzing customer inquiries.

[0104] The "response generation means" is a function that generates an appropriate automated response based on the analyzed inquiry content.

[0105] "Analysis tools" refer to functions used to identify emotions from customer inquiries.

[0106] A "regulatory mechanism" is a system that adjusts the method of communication of a response according to a specific emotion.

[0107] "Display control means" refers to a function used on e-commerce sites to display responses on customer terminals in real time.

[0108] A "communication terminal" is a device used by customers to access online shopping sites.

[0109] "Information recording means" refers to a function for recording and analyzing customer inquiries and emotional data.

[0110] This invention is an advanced application system for streamlining customer support on e-commerce websites. The system consists of a server on the cloud and customer communication terminals.

[0111] The server analyzes customer inquiries using information processing tools equipped with natural language processing technology. For this purpose, natural language processing libraries such as NLTK and TENSORFLOW®, using Python, are employed. Once a customer inquiry is sent to the server, it quickly analyzes it to identify the customer's intent.

[0112] After analysis, a response generation system generates an appropriate response based on the identified intent, and this response is operated using cloud services such as Amazon Web Services (AWS®) Lambda. This response is not only a direct answer but is also adjusted based on sentiment analysis. The server uses the analysis system to determine the customer's emotions at the time of the inquiry. For example, if it is identified that the customer is feeling "dissatisfied," the response tone is softened and adjusted to provide reassurance.

[0113] The retuned response is sent in real time to the customer's communication terminal via a display control device. For example, if a customer asks, "How do I get a refund for my product?", a response such as, "Thank you for your question. If you wish to receive a refund for your product, please first select the relevant product from your order history and submit a refund request. We will be happy to assist you further if you have any difficulties with this procedure," is generated. The generated response and its process involve prompts generated using a generation AI model.

[0114] An example of a generated AI prompt might be: "Generate an appropriate response to a customer inquiry. The inquiry is 'How do I get a refund for this product?' The customer's sentiment is somewhat dissatisfied." This aims to improve the quality of responses and further increase customer satisfaction with inquiries.

[0115] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0116] Step 1:

[0117] The user uses a communication terminal to enter their inquiry and send it to the support system. The entered text is first forwarded by the terminal to the server. This allows the support system to receive the inquiry data.

[0118] Step 2:

[0119] The server analyzes the received text data using natural language processing (NLTK) tools. The text received as input undergoes grammatical and semantic analysis using natural language processing libraries such as NLTK and TensorFlow. The analysis results identify the intent of the query and related information.

[0120] Step 3:

[0121] The response generation mechanism within the server generates an appropriate response based on the analysis results. The AI ​​model then uses prompts to output the optimal response based on the input analysis results. These prompts include specific examples such as "Generate an appropriate response to the customer's inquiry."

[0122] Step 4:

[0123] The server uses sentiment analysis tools to identify the emotions contained in the inquiry. Using the analyzed text as input data, it employs a psychological model to output emotions such as "dissatisfaction" or "gratitude." This provides foundational data for adjusting the response.

[0124] Step 5:

[0125] The server performs tone adjustments on the responses generated by the response generation means, according to the emotion. The adjustment means receives the identified emotion as input and outputs an appropriate response tone. This adjustment makes it possible to generate responses that are empathetic to the emotions.

[0126] Step 6:

[0127] The server sends a coordinated response to the terminal and displays it to the user. This process is controlled by a display control mechanism, allowing the user to receive the response in real time on their communication terminal. This ensures that inquiries are answered quickly and appropriately.

[0128] Step 7:

[0129] The server records all inquiry content and sentiment data using information recording devices and stores it in a database for later analysis. The recorded data is used to improve the service and analyze inquiry trends.

[0130] 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.

[0131] The present invention relates to an advanced customer support system for automatically processing customer inquiries and generating responses. This system includes natural language processing means, response generation means, sentiment analysis means, tone adjustment means, and an emotion engine that recognizes the user's emotions in real time.

[0132] First, the user opens a chat window and enters their inquiry to support. For example, they might state a specific problem such as, "There is a problem with the product that was delivered. What should I do?" This inquiry is entered into the terminal and sent to the server.

[0133] The server analyzes the received text information using natural language processing to clarify the intent of the query. Based on the analyzed information, the server uses response generation tools to prepare a response that presents an appropriate solution to the user's problem. This response includes specific actions that the user should take.

[0134] To provide further added value, an emotion engine is utilized. The server uses the emotion engine to analyze the user's emotions in real time. By referring to past emotion history, it precisely analyzes the emotions derived from the current inquiry. This analysis allows the server to grasp subtle emotional nuances, such as whether the user is irritated or confused.

[0135] The results of sentiment analysis can be used to adjust the tone of responses. For example, if a user expresses dissatisfaction, the response will be more empathetic and polite. This tone adjustment allows the server to maximize customer satisfaction. Furthermore, if the sentiment engine recognizes a specific urgent emotional state, it promptly notifies support staff to facilitate direct human intervention.

[0136] Ultimately, the server sends the generated response to the terminal, which then displays it to the user. During this process, the response data is serialized and securely delivered to the user.

[0137] This invention enables companies to provide fast, accurate, and emotionally sensitive customer support, significantly improving the quality of the customer experience.

[0138] The following describes the processing flow.

[0139] Step 1:

[0140] The user opens the support chat window on the website or mobile app and enters their inquiry as text. For example, they might type, "My product is broken and I would like to return it. Could you please tell me how to do that?"

[0141] Step 2:

[0142] The terminal retrieves user input data and sends it to the server using a secure protocol. During this process, the query content is serialized in JSON format.

[0143] Step 3:

[0144] The server receives query data from the terminal and automatically analyzes the text using natural language processing. This analysis identifies the subject and intent, and then begins preparing an appropriate response.

[0145] Step 4:

[0146] The server activates an emotion engine to perform sentiment analysis on the inquiry. It recognizes the emotional state in real time and creates a more detailed emotion profile by comparing it with past emotion data.

[0147] Step 5:

[0148] Based on the sentiment analysis results and other analysis findings obtained, the server uses a response generation mechanism to construct a response appropriate to the user's situation. For example, it may generate a response that includes detailed steps for the return process and an apology to the user.

[0149] Step 6:

[0150] The server uses the results of its emotion engine analysis to adjust the tone of the response it generates. If the emotion is found to be dissatisfaction, the tone will be set to emphasize empathetic language and apologies.

[0151] Step 7:

[0152] After the response is completed, the server sends the response back to the terminal using a transmission method. At this time, the response is serialized in the appropriate format and delivered to the terminal securely and quickly.

[0153] Step 8:

[0154] The system deserializes the response received by the terminal and displays it visually to the user. Visual elements are used to display instructions in an easy-to-understand manner, helping the user to take quick action.

[0155] This entire process allows users to receive prompt and accurate support, and enables companies to increase customer satisfaction.

[0156] (Example 2)

[0157] 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".

[0158] Responding quickly and accurately to a wide range of customer inquiries is a crucial challenge in modern business. In particular, simply offering solutions without properly understanding the customer's emotions will not lead to improved customer satisfaction. Traditional systems often lacked sufficient emotional analysis and response tone adjustment capabilities, making it difficult to provide adequately satisfactory support.

[0159] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0160] In this invention, the server includes a natural language analysis means for automatically analyzing information from customers, a response generation means for generating an appropriate automatic response based on the analyzed information, an emotion analysis means for identifying emotions from the information, an expression adjustment means for adjusting the tone of the response according to the identified emotions, and a communication means for sending the adjusted response to the customer. This enables quick and appropriate responses that take into account the customer's emotions, thereby improving customer satisfaction.

[0161] A "natural language processing tool" is a program or device that analyzes text data provided by a customer and understands its intent and content.

[0162] A "response generation means" is a program or device for automatically creating an appropriate response to a customer based on information obtained by a natural language processing means.

[0163] "Emotional analysis tools" are programs or devices used to identify emotions contained in customer information and inquiries, and to analyze their nature and intensity.

[0164] "Expression adjustment means" refers to a program or device that adjusts the tone and expression of the generated response based on the results of emotion analysis means, and provides a response to the customer in an appropriate tone.

[0165] "Communication means" refers to technology or equipment that enables two-way information exchange by transmitting responses generated by a server to a customer's device.

[0166] "Information processing device" refers to a program or system for providing automated responses to customers, including the above-mentioned natural language processing means, response generation means, sentiment analysis means, expression adjustment means, and communication means.

[0167] A description of the embodiment for carrying out the invention will be provided.

[0168] This system consists of a server, terminals, and users. The server is the central component, primarily responsible for processing customer inquiries and generating automated responses.

[0169] The server first uses natural language processing (NLP) to analyze text information sent from the customer via their device. Examples of NLP tools used for this purpose include libraries such as "spaCy" and "BERT." This allows for accurate identification of the intent and content of the inquiry.

[0170] Next, the server uses a response generation mechanism to automatically create an appropriate response based on the analysis results. Here, a generative AI model is utilized to generate quick and accurate answers even to complex customer inquiries. The generative AI model uses prompt sentences such as, "Please tell me what to do if my product does not arrive."

[0171] Furthermore, the server uses sentiment analysis tools to extract customer emotions from text information. Sentiment analysis employs techniques that refer to past data to identify and analyze the intensity of emotions. Based on the obtained sentiment data, expression adjustment tools are used to adjust the tone and expression of the response. For example, if the customer expresses dissatisfaction or frustration, the response will be adjusted to be more empathetic and polite.

[0172] Finally, the server sends a refined response to the terminal via a communication method. The terminal displays the received response to the user and prompts the user for confirmation. This allows the user to quickly obtain appropriate countermeasures, which is expected to improve customer satisfaction.

[0173] For example, if a user asks, "What should I do if the clothes I ordered from the online store arrive in the wrong size?", the server will quickly generate a solution and provide an appropriate response. Thus, the ability to automatically provide accurate and emotionally sensitive responses to customer inquiries is a key feature of this invention.

[0174] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0175] Step 1:

[0176] The user opens a support chat window on their device and enters their specific inquiry. For example, "My ordered item hasn't arrived. What should I do?" This input is sent to the server as text data by the device.

[0177] Step 2:

[0178] The server analyzes text data received from the terminal using natural language processing (NLP) tools. The input is the user's inquiry text, and the analysis process extracts key topics and intents using a natural language processing library. The output of this process is data that clearly identifies the user's request.

[0179] Step 3:

[0180] The server generates an appropriate response using a response generation mechanism based on the analyzed data. The input for this step is the analysis results, and the output includes an automatically generated solution to the user's problem. The response is generated by a generation AI model. For example, it could provide instructions on how to check the delivery status or how to cancel an order.

[0181] Step 4:

[0182] The server evaluates the user's emotions using sentiment analysis tools based on the generated response. The input consists of the user's inquiry and response, and the sentiment analysis engine identifies the user's emotional state. The output of this process is data related to the user's emotions.

[0183] Step 5:

[0184] The server uses sentiment analysis results to apply expression adjustment mechanisms that modify the tone of the response. The input consists of the response and sentiment data, and the output is the adjusted response. This process makes the response empathetic and appropriate for the situation. For example, a response to a dissatisfied user can be changed to a tone that conveys apology and a promise of prompt action.

[0185] Step 6:

[0186] The server sends a pre-arranged response to the user's terminal via a communication method. The input is the pre-arranged response, and the output is a text message received by the terminal. The terminal displays the received response on its screen and notifies the user. This allows the user to quickly obtain appropriate countermeasures.

[0187] (Application Example 2)

[0188] 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".

[0189] In customer support, it is crucial to respond to customer inquiries quickly and appropriately. However, traditional systems have difficulty automatically generating responses that take customer emotions into account, which can lead to decreased customer satisfaction. Therefore, it is necessary to accurately analyze customer emotions and provide responses in an appropriate tone.

[0190] 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.

[0191] In this invention, the server includes a string analysis means for automatically analyzing customer inquiries, a response generation means for generating an appropriate automated response based on the content analyzed by the analysis means, and an emotion estimation means for identifying the customer's emotions from the customer's inquiry. This enables a quick and accurate response that takes the customer's emotions into consideration.

[0192] A "string analysis method" is a means of automatically analyzing customer inquiries to clarify their intent.

[0193] A "response generation means" is a means of automatically creating an appropriate response based on the analyzed content.

[0194] "Emotion estimation methods" are means of identifying customer emotions in real time from customer inquiries.

[0195] "Tone adjustment means" are means of adjusting the tone of the response produced in accordance with a specific emotion.

[0196] An "emotional evaluation method" is a means of evaluating a customer's emotions in real time and analyzing them precisely by referring to their past emotional history.

[0197] A "transmission device" is a device that securely serializes and transmits the generated response to the customer's information processing device.

[0198] An "information recording device" is a device used to record and analyze inquiry content and sentiment data.

[0199] In the system for carrying out this invention, the server is equipped with string analysis means, response generation means, emotion estimation means, tone adjustment means, and emotion evaluation means. This enables advanced customer support. Specifically, the server analyzes the inquiry entered by the user into the terminal and understands its intent.

[0200] This analysis uses Python, leveraging the spaCy library for natural language processing. Furthermore, Hugging Face's Transformers are used for sentiment estimation and evaluation, with real-time sentiment assessment performed via PyTorch. This allows for immediate understanding of the sentiment state of strings obtained from queries.

[0201] The response generation mechanism automatically generates an appropriate response based on the generated data, and this response is then adjusted by the tone adjustment mechanism to match the identified emotion. This tone adjustment allows customers to receive a more friendly and empathetic response, which is expected to improve customer satisfaction.

[0202] The serialized data is securely transmitted to the terminal via the transmission device and displayed to the user. The user can then use their smartphone to review the generated response and take action based on it.

[0203] As a concrete example, if a user inquires that "there is a problem with the product that was sold," the server will appropriately analyze the inquiry and provide an empathetic response such as, "We will address this immediately. We will send you a new product." An example of a prompt message might be, "Generate a response message for when a user reports a product error and requires a quick and empathetic response."

[0204] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0205] Step 1:

[0206] The user enters their inquiry using a terminal and submits it. This input is sent to the server as text data.

[0207] Step 2:

[0208] The server analyzes the received text data using string parsing. This process uses Python and the spaCy library to perform data processing to identify the intent of the query. The output is the analysis result.

[0209] Step 3:

[0210] The server uses emotion estimation tools based on the analysis results to estimate the user's emotional state. This process utilizes Hugging Face's Transformers to evaluate the emotion of the inquiry in real time. The output is the estimated emotion data.

[0211] Step 4:

[0212] The server uses a response generation mechanism to generate an appropriate response based on the analysis results and sentiment data. This procedure utilizes a generative AI model to perform data calculations and output an ideal response sentence.

[0213] Step 5:

[0214] The server adjusts the generated response using tone-adjustment mechanisms. Depending on the identified emotion, it adjusts the tone of the generated response, transforming it into an empathetic or polite tone. This adjusted response becomes the final output.

[0215] Step 6:

[0216] The server serializes the adjusted response and sends it to the user's terminal using a transmission device. During this process, the secure transport of data is ensured, and the terminal displays the final response to the user.

[0217] 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.

[0218] 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.

[0219] 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.

[0220] [Second Embodiment]

[0221] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0222] 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.

[0223] 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).

[0224] 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.

[0225] 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.

[0226] 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).

[0227] 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.

[0228] 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.

[0229] 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.

[0230] 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.

[0231] 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.

[0232] 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".

[0233] This invention is a generative AI-based solution that fully automates a company's customer support system, aiming to respond to customer inquiries quickly and accurately. The system uses natural language processing technology to analyze inquiry content, generate responses, perform sentiment analysis, and adjust tone, thereby achieving sophisticated customer service.

[0234] First, the user accesses the support system and enters their inquiry into the chat window. For example, "How do I get a refund for my product?" Once the inquiry is sent, the device transfers the entered text data to the server.

[0235] Subsequently, the server analyzes the received text using natural language processing to understand the customer's intent. Based on this analysis, the server uses response generation tools to generate an appropriate response. The generated response provides relevant information based on the customer's inquiry.

[0236] Next, the server uses sentiment analysis tools to identify the customer's emotions from their language and context. This analysis allows the server to determine whether the customer's emotions are in a state such as "dissatisfaction," "doubt," or "gratitude." The results of this sentiment analysis are used to deliver a response to the customer in an appropriate tone. The server uses tone adjustment tools to adjust the tone of the response and provide appropriate communication to the customer.

[0237] Finally, the server uses a transmission method to send the generated response and text with an adjusted tone to the terminal. The terminal receives this and displays it to the user. For example, the displayed message might say, "If you would like a refund for your order, please follow these steps," with the wording becoming gentler or more polite depending on the user's emotions.

[0238] Furthermore, this system is equipped with data recording capabilities, allowing the server to record all inquiry details and sentiment data, which can then be used for later analysis and service improvement.

[0239] This system allows companies to significantly improve the efficiency of customer support and achieve higher customer satisfaction.

[0240] The following describes the processing flow.

[0241] Step 1:

[0242] The user opens the customer support chat window and enters their inquiry. For example, they might enter a specific question such as, "How do I exchange a product?"

[0243] Step 2:

[0244] The terminal retrieves text data entered by the user and sends it to the server. The terminal uses a REST API to serialize the query content in JSON format and send it to the server.

[0245] Step 3:

[0246] The server receives data sent from the terminal and passes it to a natural language processing system to analyze the query. Here, the server checks the data format and filters out unnecessary information.

[0247] Step 4:

[0248] The natural language processing system installed on the server analyzes the query content and understands the user's intentions. It understands what the query is requesting and prepares to select relevant information from the database.

[0249] Step 5:

[0250] The server uses a response generation mechanism to construct an appropriate response based on the analysis results. For example, it combines necessary information, such as policies and procedures related to product exchange, to create a response.

[0251] Step 6:

[0252] The server uses sentiment analysis tools to extract emotions from user inquiries. Based on the linguistic expression of the inquiry, it determines whether the user is experiencing emotions such as "anxiety" or "doubt."

[0253] Step 7:

[0254] The server uses tone adjustment mechanisms to appropriately adjust the tone of responses based on the results of sentiment analysis. For example, if the user is showing anxiety, the response will be made more reassuring.

[0255] Step 8:

[0256] The server prepares to send the completed response to the terminal and sends it to the terminal using the transmission method. The response is then converted back to JSON format and sent to the terminal.

[0257] Step 9:

[0258] The terminal receives the response sent from the server and displays it in the user's chat window. Based on the displayed information, the user can receive appropriate instructions and complete the support process.

[0259] (Example 1)

[0260] 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."

[0261] In today's world, there is a demand for prompt and accurate responses to customer inquiries. However, conventional systems struggle to efficiently handle a large volume of inquiries, potentially leading to decreased customer satisfaction. Furthermore, the lack of flexible responses tailored to the user's emotions results in inconsistent service quality.

[0262] 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.

[0263] In this invention, the server includes language processing means for automatically analyzing information from users, information generation means for generating appropriate responses, and information analysis means for identifying emotions. This enables rapid and accurate analysis of user inquiries and the provision of appropriate responses tailored to the user's emotions.

[0264] "Users" refer to individuals or organizations that access the system and use its services.

[0265] "Information" refers to data and inquiries provided by users, and is the subject of language processing and analysis.

[0266] "Processing means" refers to technical methods and devices for analyzing information and performing appropriate data processing.

[0267] "Language processing means" refers to methods and technological devices for analyzing natural language and understanding information.

[0268] "Information generation means" refers to methods and technical devices for generating appropriate responses based on analyzed information.

[0269] "Information analysis means" refers to methods and technological devices used to analyze user information and specifically identify emotions.

[0270] "Adjustment means" refers to methods or technical devices for changing the nature or tone of the generated response according to the situation.

[0271] "Reference means" refers to methods and technical devices for querying related materials and databases based on the analyzed information.

[0272] "Generation means" refers to methods and technical devices for optimizing answers generated using a pre-trained artificial intelligence model.

[0273] "Transmission means" refers to methods or technical devices for transmitting the generated response to the user's display device.

[0274] "Data processing means" refers to methods, technologies, and devices for handling recorded and analyzed information and utilizing it for operation and improvement.

[0275] The system in this invention automates customer support for businesses, enabling them to respond to user inquiries quickly and accurately. This system primarily communicates between a server, a terminal, and a user, and operates through multiple stages of processing.

[0276] The server first receives data sent from the user. It uses natural language processing (NLP) software, such as spaCy or Transformers, which are well-known NLP libraries for Python. To quickly analyze the received text, the server uses these libraries to perform syntactic and semantic analysis.

[0277] Once the analysis is complete, the server generates a response based on the generated data. This process utilizes a generative AI model. For example, it leverages advanced models such as OpenAI's GPT-3 to generate a natural-sounding response based on the analyzed content. The generated response is then further optimized by information generation tools.

[0278] Next, the server uses sentiment analysis tools to determine the emotion behind the user's statements. Software such as VADER and TextBlob is used for sentiment analysis. Based on the analyzed sentiment information, the generated response is tone-adjusted to make it more personalized.

[0279] The generated response is sent to the terminal and displayed to the user. This process takes place via WebSocket or HTTP requests, and the terminal presents the provided information to the user. The wording and tone of the presentation are adjusted according to the customer's mood.

[0280] Furthermore, the server records all inquiry and sentiment data, which can then be used for later analysis and logistics improvements. This allows companies to significantly improve the efficiency of customer service and increase customer satisfaction.

[0281] As a specific example, an example of a prompt sentence input to the generative AI model is as follows. "When a user inquires about the method of returning a product, analyze the customer's sentiment and generate a response in an appropriate tone."

[0282] In this way, this invention realizes an automatic response system for inquiries from users by making full use of natural language processing technology and AI generation technology.

[0283] The flow of the specific process in Example 1 will be described with reference to FIG. 11.

[0284] Step 1:

[0285] The user accesses the customer support system and enters an inquiry into the chat window. At this time, the input content is transmitted to the server as text data. For example, assume that an inquiry such as "Please tell me the method of returning a product" is entered. At this stage, there is an input by the user, and the output is processed as text data.

[0286] Step 2:

[0287] The terminal transfers the text data input by the user to the server. Here, the data is transmitted via WebSocket or an HTTP request. The input is the inquiry text from the user, and the output is to send this text data to the server. Through this process, the terminal plays a role in bridging the user's intention to the server.

[0288] Step 3:

[0289] The server performs natural language processing on the received text data. Specifically, syntactic analysis and semantic analysis are executed using libraries in Python such as spaCy and Transformers. The input is the user's inquiry text, and the output is the analyzed text data. Through this analysis, the server accurately understands the user's intention.

[0290] Step 4:

[0291] The server generates a response based on the analyzed data. This process utilizes a generative AI model, such as OpenAI's GPT-3. The input is the analysis result, and the output is a response message based on the user's intent. At this stage, a prompt is input to the generative AI model to generate an appropriate message.

[0292] Step 5:

[0293] The server then performs sentiment analysis to adjust the tone of its responses. Tools such as VADER and TextBlob are used for sentiment analysis. The input is the user's text data, and the output is sentiment information associated with that text. This sentiment information is used to adjust the tone of the responses to better reflect the user's emotions.

[0294] Step 6:

[0295] The server sends the final response message to the terminal and displays it to the user. The response is transmitted quickly via WebSocket or HTTP response. The input is the tone-adjusted response, and the output is what is displayed to the user. The terminal displays this message in the chat window so that the user can see it.

[0296] Step 7:

[0297] The server records all inquiries and sentiment data in a database. This data is later analyzed and used to improve services and enhance the quality of customer support. The input consists of inquiry content and sentiment data, which are stored in the database. This process allows the server to accumulate resources for future analysis.

[0298] (Application Example 1)

[0299] 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."

[0300] Responding to customer inquiries is crucial for businesses, but it also requires significant effort and cost. E-commerce sites, in particular, experience frequent customer inquiries and demand prompt and accurate responses. However, relying solely on human resources has its limitations, and it's difficult to provide responses that truly address customer needs and emotions. Therefore, there is a need to develop systems that efficiently handle customer inquiries without compromising the customer experience.

[0301] 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.

[0302] In this invention, the server includes information processing means for automatically analyzing customer inquiries, response generation means for generating appropriate automatic responses based on the analyzed content, analysis means for identifying emotions from inquiries, adjustment means for adjusting the method of transmitting the response according to the emotions identified by the analysis means, and display control means for displaying the response on the customer terminal in real time on the e-commerce site. This makes it possible to automatically provide appropriate and rapid responses that correspond to the customer's emotions.

[0303] "Information processing means" refers to technical methods for automatically analyzing customer inquiries.

[0304] The "response generation means" is a function that generates an appropriate automated response based on the analyzed inquiry content.

[0305] "Analysis tools" refer to functions used to identify emotions from customer inquiries.

[0306] A "regulatory mechanism" is a system that adjusts the method of communication of a response according to a specific emotion.

[0307] The "display control means" is a function for displaying responses to the customer terminal in real time on the e-commerce site.

[0308] The "communication terminal" is a device used by customers to access the e-commerce site.

[0309] The "information recording means" is a function for recording and analyzing the customer's inquiry content and emotional data.

[0310] This invention is an advanced application system for improving the efficiency of customer support on an e-commerce site. The system is composed of a server on the cloud and the customer's communication terminal.

[0311] The server analyzes the inquiry sent by the customer using information processing means equipped with natural language processing technology. For this purpose, natural language processing libraries such as NLTK and TensorFlow using Python are used. When the inquiry content from the customer is sent to the server, the server quickly performs analysis to identify the customer's intention.

[0312] After analysis, the response generation means generates an appropriate response based on the identified intention and is operated using cloud services such as Amazon Web Services (AWS) Lambda. This response is not only a direct answer but also adjusted based on sentiment analysis. The server uses analysis means to judge the customer's emotion at the time of inquiry. Thus, for example, if the customer is identified as having an "angry" emotion, the tone of the response is softened and an adjustment is made to give reassurance.

[0313] The retuned response is sent in real time to the customer's communication terminal via a display control device. For example, if a customer asks, "How do I get a refund for my product?", a response such as, "Thank you for your question. If you wish to receive a refund for your product, please first select the relevant product from your order history and submit a refund request. We will be happy to assist you further if you have any difficulties with this procedure," is generated. The generated response and its process involve prompts generated using a generation AI model.

[0314] An example of a generated AI prompt might be: "Generate an appropriate response to a customer inquiry. The inquiry is 'How do I get a refund for this product?' The customer's sentiment is somewhat dissatisfied." This aims to improve the quality of responses and further increase customer satisfaction with inquiries.

[0315] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0316] Step 1:

[0317] The user uses a communication terminal to enter their inquiry and send it to the support system. The entered text is first forwarded by the terminal to the server. This allows the support system to receive the inquiry data.

[0318] Step 2:

[0319] The server analyzes the received text data using natural language processing (NLTK) tools. The text received as input undergoes grammatical and semantic analysis using natural language processing libraries such as NLTK and TensorFlow. The analysis results identify the intent of the query and related information.

[0320] Step 3:

[0321] The response generation mechanism within the server generates an appropriate response based on the analysis results. The AI ​​model then uses prompts to output the optimal response based on the input analysis results. These prompts include specific examples such as "Generate an appropriate response to the customer's inquiry."

[0322] Step 4:

[0323] The server uses sentiment analysis tools to identify the emotions contained in the inquiry. Using the analyzed text as input data, it employs a psychological model to output emotions such as "dissatisfaction" or "gratitude." This provides foundational data for adjusting the response.

[0324] Step 5:

[0325] The server performs tone adjustments on the responses generated by the response generation means, according to the emotion. The adjustment means receives the identified emotion as input and outputs an appropriate response tone. This adjustment makes it possible to generate responses that are empathetic to the emotions.

[0326] Step 6:

[0327] The server sends a coordinated response to the terminal and displays it to the user. This process is controlled by a display control mechanism, allowing the user to receive the response in real time on their communication terminal. This ensures that inquiries are answered quickly and appropriately.

[0328] Step 7:

[0329] The server records all inquiry content and sentiment data using information recording devices and stores it in a database for later analysis. The recorded data is used to improve the service and analyze inquiry trends.

[0330] 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.

[0331] The present invention relates to an advanced customer support system for automatically processing customer inquiries and generating responses. This system includes natural language processing means, response generation means, sentiment analysis means, tone adjustment means, and an emotion engine that recognizes the user's emotions in real time.

[0332] First, the user opens a chat window and enters their inquiry to support. For example, they might state a specific problem such as, "There is a problem with the product that was delivered. What should I do?" This inquiry is entered into the terminal and sent to the server.

[0333] The server analyzes the received text information using natural language processing to clarify the intent of the query. Based on the analyzed information, the server uses response generation tools to prepare a response that presents an appropriate solution to the user's problem. This response includes specific actions that the user should take.

[0334] To provide further added value, an emotion engine is utilized. The server uses the emotion engine to analyze the user's emotions in real time. By referring to past emotion history, it precisely analyzes the emotions derived from the current inquiry. This analysis allows the server to grasp subtle emotional nuances, such as whether the user is irritated or confused.

[0335] The results of sentiment analysis can be used to adjust the tone of responses. For example, if a user expresses dissatisfaction, the response will be more empathetic and polite. This tone adjustment allows the server to maximize customer satisfaction. Furthermore, if the sentiment engine recognizes a specific urgent emotional state, it promptly notifies support staff to facilitate direct human intervention.

[0336] Ultimately, the server sends the generated response to the terminal, which then displays it to the user. During this process, the response data is serialized and securely delivered to the user.

[0337] This invention enables companies to provide fast, accurate, and emotionally sensitive customer support, significantly improving the quality of the customer experience.

[0338] The following describes the processing flow.

[0339] Step 1:

[0340] The user opens the support chat window on the website or mobile app and enters their inquiry as text. For example, they might type, "My product is broken and I would like to return it. Could you please tell me how to do that?"

[0341] Step 2:

[0342] The terminal retrieves user input data and sends it to the server using a secure protocol. During this process, the query content is serialized in JSON format.

[0343] Step 3:

[0344] The server receives query data from the terminal and automatically analyzes the text using natural language processing. This analysis identifies the subject and intent, and then begins preparing an appropriate response.

[0345] Step 4:

[0346] The server activates an emotion engine to perform sentiment analysis on the inquiry. It recognizes the emotional state in real time and creates a more detailed emotion profile by comparing it with past emotion data.

[0347] Step 5:

[0348] Based on the sentiment analysis results and other analysis findings obtained, the server uses a response generation mechanism to construct a response appropriate to the user's situation. For example, it may generate a response that includes detailed steps for the return process and an apology to the user.

[0349] Step 6:

[0350] The server uses the results of its emotion engine analysis to adjust the tone of the response it generates. If the emotion is found to be dissatisfaction, the tone will be set to emphasize empathetic language and apologies.

[0351] Step 7:

[0352] After the response is completed, the server sends the response back to the terminal using a transmission method. At this time, the response is serialized in the appropriate format and delivered to the terminal securely and quickly.

[0353] Step 8:

[0354] The system deserializes the response received by the terminal and displays it visually to the user. Visual elements are used to display instructions in an easy-to-understand manner, helping the user to take quick action.

[0355] This entire process allows users to receive prompt and accurate support, and enables companies to increase customer satisfaction.

[0356] (Example 2)

[0357] 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".

[0358] Responding quickly and accurately to a wide range of customer inquiries is a crucial challenge in modern business. In particular, simply offering solutions without properly understanding the customer's emotions will not lead to improved customer satisfaction. Traditional systems often lacked sufficient emotional analysis and response tone adjustment capabilities, making it difficult to provide adequately satisfactory support.

[0359] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0360] In this invention, the server includes a natural language analysis means for automatically analyzing information from customers, a response generation means for generating an appropriate automatic response based on the analyzed information, an emotion analysis means for identifying emotions from the information, an expression adjustment means for adjusting the tone of the response according to the identified emotions, and a communication means for sending the adjusted response to the customer. This enables quick and appropriate responses that take into account the customer's emotions, thereby improving customer satisfaction.

[0361] A "natural language processing tool" is a program or device that analyzes text data provided by a customer and understands its intent and content.

[0362] A "response generation means" is a program or device for automatically creating an appropriate response to a customer based on information obtained by a natural language processing means.

[0363] "Emotional analysis tools" are programs or devices used to identify emotions contained in customer information and inquiries, and to analyze their nature and intensity.

[0364] "Expression adjustment means" refers to a program or device that adjusts the tone and expression of the generated response based on the results of emotion analysis means, and provides a response to the customer in an appropriate tone.

[0365] "Communication means" refers to technology or equipment that enables two-way information exchange by transmitting responses generated by a server to a customer's device.

[0366] "Information processing device" refers to a program or system for providing automated responses to customers, including the above-mentioned natural language processing means, response generation means, sentiment analysis means, expression adjustment means, and communication means.

[0367] A description of the embodiment for carrying out the invention will be provided.

[0368] This system consists of a server, terminals, and users. The server is the central component, primarily responsible for processing customer inquiries and generating automated responses.

[0369] The server first uses natural language processing (NLP) to analyze text information sent from the customer via their device. Examples of NLP tools used for this purpose include libraries such as "spaCy" and "BERT." This allows for accurate identification of the intent and content of the inquiry.

[0370] Next, the server uses a response generation mechanism to automatically create an appropriate response based on the analysis results. Here, a generative AI model is utilized to generate quick and accurate answers even to complex customer inquiries. The generative AI model uses prompt sentences such as, "Please tell me what to do if my product does not arrive."

[0371] Furthermore, the server uses sentiment analysis tools to extract customer emotions from text information. Sentiment analysis employs techniques that refer to past data to identify and analyze the intensity of emotions. Based on the obtained sentiment data, expression adjustment tools are used to adjust the tone and expression of the response. For example, if the customer expresses dissatisfaction or frustration, the response will be adjusted to be more empathetic and polite.

[0372] Finally, the server sends a refined response to the terminal via a communication method. The terminal displays the received response to the user and prompts the user for confirmation. This allows the user to quickly obtain appropriate countermeasures, which is expected to improve customer satisfaction.

[0373] For example, if a user asks, "What should I do if the clothes I ordered from the online store arrive in the wrong size?", the server will quickly generate a solution and provide an appropriate response. Thus, the ability to automatically provide accurate and emotionally sensitive responses to customer inquiries is a key feature of this invention.

[0374] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0375] Step 1:

[0376] The user opens a support chat window on their device and enters their specific inquiry. For example, "My ordered item hasn't arrived. What should I do?" This input is sent to the server as text data by the device.

[0377] Step 2:

[0378] The server analyzes text data received from the terminal using natural language processing (NLP) tools. The input is the user's inquiry text, and the analysis process extracts key topics and intents using a natural language processing library. The output of this process is data that clearly identifies the user's request.

[0379] Step 3:

[0380] The server generates an appropriate response using a response generation mechanism based on the analyzed data. The input for this step is the analysis results, and the output includes an automatically generated solution to the user's problem. The response is generated by a generation AI model. For example, it could provide instructions on how to check the delivery status or how to cancel an order.

[0381] Step 4:

[0382] The server evaluates the user's emotions using sentiment analysis tools based on the generated response. The input consists of the user's inquiry and response, and the sentiment analysis engine identifies the user's emotional state. The output of this process is data related to the user's emotions.

[0383] Step 5:

[0384] The server uses sentiment analysis results to apply expression adjustment mechanisms that modify the tone of the response. The input consists of the response and sentiment data, and the output is the adjusted response. This process makes the response empathetic and appropriate for the situation. For example, a response to a dissatisfied user can be changed to a tone that conveys apology and a promise of prompt action.

[0385] Step 6:

[0386] The server sends a pre-arranged response to the user's terminal via a communication method. The input is the pre-arranged response, and the output is a text message received by the terminal. The terminal displays the received response on its screen and notifies the user. This allows the user to quickly obtain appropriate countermeasures.

[0387] (Application Example 2)

[0388] 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."

[0389] In customer support, it is crucial to respond to customer inquiries quickly and appropriately. However, traditional systems have difficulty automatically generating responses that take customer emotions into account, which can lead to decreased customer satisfaction. Therefore, it is necessary to accurately analyze customer emotions and provide responses in an appropriate tone.

[0390] 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.

[0391] In this invention, the server includes a string analysis means for automatically analyzing customer inquiries, a response generation means for generating an appropriate automated response based on the content analyzed by the analysis means, and an emotion estimation means for identifying the customer's emotions from the customer's inquiry. This enables a quick and accurate response that takes the customer's emotions into consideration.

[0392] A "string analysis method" is a means of automatically analyzing customer inquiries to clarify their intent.

[0393] A "response generation means" is a means of automatically creating an appropriate response based on the analyzed content.

[0394] "Emotion estimation methods" are means of identifying customer emotions in real time from customer inquiries.

[0395] "Tone adjustment means" are means of adjusting the tone of the response produced in accordance with a specific emotion.

[0396] An "emotional evaluation method" is a means of evaluating a customer's emotions in real time and analyzing them precisely by referring to their past emotional history.

[0397] A "transmission device" is a device that securely serializes and transmits the generated response to the customer's information processing device.

[0398] An "information recording device" is a device used to record and analyze inquiry content and sentiment data.

[0399] In the system for carrying out this invention, the server is equipped with string analysis means, response generation means, emotion estimation means, tone adjustment means, and emotion evaluation means. This enables advanced customer support. Specifically, the server analyzes the inquiry entered by the user into the terminal and understands its intent.

[0400] This analysis uses Python, leveraging the spaCy library for natural language processing. Furthermore, Hugging Face's Transformers are used for sentiment estimation and evaluation, with real-time sentiment assessment performed via PyTorch. This allows for immediate understanding of the sentiment state of strings obtained from queries.

[0401] The response generation mechanism automatically generates an appropriate response based on the generated data, and this response is then adjusted by the tone adjustment mechanism to match the identified emotion. This tone adjustment allows customers to receive a more friendly and empathetic response, which is expected to improve customer satisfaction.

[0402] The serialized data is securely transmitted to the terminal via the transmission device and displayed to the user. The user can then use their smartphone to review the generated response and take action based on it.

[0403] As a concrete example, if a user inquires that "there is a problem with the product that was sold," the server will appropriately analyze the inquiry and provide an empathetic response such as, "We will address this immediately. We will send you a new product." An example of a prompt message might be, "Generate a response message for when a user reports a product error and requires a quick and empathetic response."

[0404] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0405] Step 1:

[0406] The user enters their inquiry using a terminal and submits it. This input is sent to the server as text data.

[0407] Step 2:

[0408] The server analyzes the received text data using string parsing. This process uses Python and the spaCy library to perform data processing to identify the intent of the query. The output is the analysis result.

[0409] Step 3:

[0410] The server uses emotion estimation tools based on the analysis results to estimate the user's emotional state. This process utilizes Hugging Face's Transformers to evaluate the emotion of the inquiry in real time. The output is the estimated emotion data.

[0411] Step 4:

[0412] The server uses a response generation mechanism to generate an appropriate response based on the analysis results and sentiment data. This procedure utilizes a generative AI model to perform data calculations and output an ideal response sentence.

[0413] Step 5:

[0414] The server adjusts the generated response using tone-adjustment mechanisms. Depending on the identified emotion, it adjusts the tone of the generated response, transforming it into an empathetic or polite tone. This adjusted response becomes the final output.

[0415] Step 6:

[0416] The server serializes the adjusted response and sends it to the user's terminal using a transmission device. During this process, the secure transport of data is ensured, and the terminal displays the final response to the user.

[0417] 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.

[0418] 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.

[0419] 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.

[0420] [Third Embodiment]

[0421] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0422] 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.

[0423] 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).

[0424] 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.

[0425] 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.

[0426] 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).

[0427] 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.

[0428] 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.

[0429] 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.

[0430] 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.

[0431] 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.

[0432] 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".

[0433] This invention is a generative AI-based solution that fully automates a company's customer support system, aiming to respond to customer inquiries quickly and accurately. The system uses natural language processing technology to analyze inquiry content, generate responses, perform sentiment analysis, and adjust tone, thereby achieving sophisticated customer service.

[0434] First, the user accesses the support system and enters their inquiry into the chat window. For example, "How do I get a refund for my product?" Once the inquiry is sent, the device transfers the entered text data to the server.

[0435] Subsequently, the server analyzes the received text using natural language processing to understand the customer's intent. Based on this analysis, the server uses response generation tools to generate an appropriate response. The generated response provides relevant information based on the customer's inquiry.

[0436] Next, the server uses sentiment analysis tools to identify the customer's emotions from their language and context. This analysis allows the server to determine whether the customer's emotions are in a state such as "dissatisfaction," "doubt," or "gratitude." The results of this sentiment analysis are used to deliver a response to the customer in an appropriate tone. The server uses tone adjustment tools to adjust the tone of the response and provide appropriate communication to the customer.

[0437] Finally, the server uses a transmission method to send the generated response and text with an adjusted tone to the terminal. The terminal receives this and displays it to the user. For example, the displayed message might say, "If you would like a refund for your order, please follow these steps," with the wording becoming gentler or more polite depending on the user's emotions.

[0438] Furthermore, this system is equipped with data recording capabilities, allowing the server to record all inquiry details and sentiment data, which can then be used for later analysis and service improvement.

[0439] This system allows companies to significantly improve the efficiency of customer support and achieve higher customer satisfaction.

[0440] The following describes the processing flow.

[0441] Step 1:

[0442] The user opens the customer support chat window and enters their inquiry. For example, they might enter a specific question such as, "How do I exchange a product?"

[0443] Step 2:

[0444] The terminal retrieves text data entered by the user and sends it to the server. The terminal uses a REST API to serialize the query content in JSON format and send it to the server.

[0445] Step 3:

[0446] The server receives data sent from the terminal and passes it to a natural language processing system to analyze the query. Here, the server checks the data format and filters out unnecessary information.

[0447] Step 4:

[0448] The natural language processing system installed on the server analyzes the query content and understands the user's intentions. It understands what the query is requesting and prepares to select relevant information from the database.

[0449] Step 5:

[0450] The server uses a response generation mechanism to construct an appropriate response based on the analysis results. For example, it combines necessary information, such as policies and procedures related to product exchange, to create a response.

[0451] Step 6:

[0452] The server uses sentiment analysis tools to extract emotions from user inquiries. Based on the linguistic expression of the inquiry, it determines whether the user is experiencing emotions such as "anxiety" or "doubt."

[0453] Step 7:

[0454] The server uses tone adjustment mechanisms to appropriately adjust the tone of responses based on the results of sentiment analysis. For example, if the user is showing anxiety, the response will be made more reassuring.

[0455] Step 8:

[0456] The server prepares to send the completed response to the terminal and sends it to the terminal using the transmission method. The response is then converted back to JSON format and sent to the terminal.

[0457] Step 9:

[0458] The terminal receives the response sent from the server and displays it in the user's chat window. Based on the displayed information, the user can receive appropriate instructions and complete the support process.

[0459] (Example 1)

[0460] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0461] In today's world, there is a demand for prompt and accurate responses to customer inquiries. However, conventional systems struggle to efficiently handle a large volume of inquiries, potentially leading to decreased customer satisfaction. Furthermore, the lack of flexible responses tailored to the user's emotions results in inconsistent service quality.

[0462] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0463] In this invention, the server includes language processing means for automatically analyzing information from users, information generation means for generating appropriate responses, and information analysis means for identifying emotions. This enables rapid and accurate analysis of user inquiries and the provision of appropriate responses tailored to the user's emotions.

[0464] "Users" refer to individuals or organizations that access the system and use its services.

[0465] "Information" refers to data and inquiries provided by users, and is the subject of language processing and analysis.

[0466] "Processing means" refers to technical methods and devices for analyzing information and performing appropriate data processing.

[0467] "Language processing means" refers to methods and technological devices for analyzing natural language and understanding information.

[0468] "Information generation means" refers to methods and technical devices for generating appropriate responses based on analyzed information.

[0469] "Information analysis means" refers to methods and technological devices used to analyze user information and specifically identify emotions.

[0470] "Adjustment means" refers to methods or technical devices for changing the nature or tone of the generated response according to the situation.

[0471] "Reference means" refers to methods and technical devices for querying related materials and databases based on the analyzed information.

[0472] "Generation means" refers to methods and technical devices for optimizing answers generated using a pre-trained artificial intelligence model.

[0473] "Transmission means" refers to methods or technical devices for transmitting the generated response to the user's display device.

[0474] "Data processing means" refers to methods, technologies, and devices for handling recorded and analyzed information and utilizing it for operation and improvement.

[0475] The system in this invention automates customer support for businesses, enabling them to respond to user inquiries quickly and accurately. This system primarily communicates between a server, a terminal, and a user, and operates through multiple stages of processing.

[0476] The server first receives data sent from the user. It uses natural language processing (NLP) software, such as spaCy or Transformers, which are well-known NLP libraries for Python. To quickly analyze the received text, the server uses these libraries to perform syntactic and semantic analysis.

[0477] Once the analysis is complete, the server generates a response based on the generated data. This process utilizes a generative AI model. For example, it leverages advanced models such as OpenAI's GPT-3 to generate a natural-sounding response based on the analyzed content. The generated response is then further optimized by information generation tools.

[0478] Next, the server uses sentiment analysis tools to determine the emotion behind the user's statements. Software such as VADER and TextBlob is used for sentiment analysis. Based on the analyzed sentiment information, the generated response is tone-adjusted to make it more personalized.

[0479] The generated response is sent to the terminal and displayed to the user. This process takes place via WebSocket or HTTP requests, and the terminal presents the provided information to the user. The wording and tone of the presentation are adjusted according to the customer's mood.

[0480] Furthermore, the server records all inquiry and sentiment data, which can then be used for later analysis and logistics improvements. This allows companies to significantly improve the efficiency of customer service and increase customer satisfaction.

[0481] As a concrete example, here is an example of a prompt sentence to be input into the generation AI model: "When a user inquires about how to get a refund for a product, analyze the customer's emotions and generate a response in an appropriate tone."

[0482] Thus, this invention utilizes natural language processing technology and AI generation technology to realize an automated response system for user inquiries.

[0483] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0484] Step 1:

[0485] The user accesses the customer support system and enters their inquiry into the chat window. At this point, the entered information is sent to the server as text data. For example, suppose the user enters the inquiry, "How do I get a refund for this product?" At this stage, the user has entered information, and its output is processed as text data.

[0486] Step 2:

[0487] The terminal transfers the text data entered by the user to the server. This data is transmitted via WebSocket or HTTP requests. The input is the user's inquiry text, and the output is sending this text data to the server. Through this process, the terminal acts as a bridge, conveying the user's intent to the server.

[0488] Step 3:

[0489] The server performs natural language processing on the received text data. Specifically, it uses Python libraries such as spaCy and Transformers to perform syntactic and semantic analysis. The input is the user's query text, and the output is the parsed text data. Through this analysis, the server accurately understands the user's intent.

[0490] Step 4:

[0491] The server generates a response based on the analyzed data. This process utilizes a generative AI model, such as OpenAI's GPT-3. The input is the analysis result, and the output is a response message based on the user's intent. At this stage, a prompt is input to the generative AI model to generate an appropriate message.

[0492] Step 5:

[0493] The server then performs sentiment analysis to adjust the tone of its responses. Tools such as VADER and TextBlob are used for sentiment analysis. The input is the user's text data, and the output is sentiment information associated with that text. This sentiment information is used to adjust the tone of the responses to better reflect the user's emotions.

[0494] Step 6:

[0495] The server sends the final response message to the terminal and displays it to the user. The response is transmitted quickly via WebSocket or HTTP response. The input is the tone-adjusted response, and the output is what is displayed to the user. The terminal displays this message in the chat window so that the user can see it.

[0496] Step 7:

[0497] The server records all inquiries and sentiment data in a database. This data is later analyzed and used to improve services and enhance the quality of customer support. The input consists of inquiry content and sentiment data, which are stored in the database. This process allows the server to accumulate resources for future analysis.

[0498] (Application Example 1)

[0499] 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."

[0500] Responding to customer inquiries is crucial for businesses, but it also requires significant effort and cost. E-commerce sites, in particular, experience frequent customer inquiries and demand prompt and accurate responses. However, relying solely on human resources has its limitations, and it's difficult to provide responses that truly address customer needs and emotions. Therefore, there is a need to develop systems that efficiently handle customer inquiries without compromising the customer experience.

[0501] 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.

[0502] In this invention, the server includes information processing means for automatically analyzing customer inquiries, response generation means for generating appropriate automatic responses based on the analyzed content, analysis means for identifying emotions from inquiries, adjustment means for adjusting the method of transmitting the response according to the emotions identified by the analysis means, and display control means for displaying the response on the customer terminal in real time on the e-commerce site. This makes it possible to automatically provide appropriate and rapid responses that correspond to the customer's emotions.

[0503] "Information processing means" refers to technical methods for automatically analyzing customer inquiries.

[0504] The "response generation means" is a function that generates an appropriate automated response based on the analyzed inquiry content.

[0505] "Analysis tools" refer to functions used to identify emotions from customer inquiries.

[0506] A "regulatory mechanism" is a system that adjusts the method of communication of a response according to a specific emotion.

[0507] "Display control means" refers to a function used on e-commerce sites to display responses on customer terminals in real time.

[0508] A "communication terminal" is a device used by customers to access online shopping sites.

[0509] "Information recording means" refers to a function for recording and analyzing customer inquiries and emotional data.

[0510] This invention is an advanced application system for streamlining customer support on e-commerce websites. The system consists of a server on the cloud and customer communication terminals.

[0511] The server uses information processing tools equipped with natural language processing technology to analyze inquiries sent by customers. For this purpose, natural language processing libraries such as NLTK and TensorFlow using Python are used. When customer inquiries are sent to the server, the server quickly analyzes them and identifies the customer's intent.

[0512] After analysis, a response generation system generates an appropriate response based on the identified intent, and this response is operated using cloud services such as Amazon Web Services (AWS) Lambda. This response is not only a direct answer but is also adjusted based on sentiment analysis. The server uses the analysis system to determine the customer's emotions at the time of the inquiry. For example, if it is determined that the customer is feeling "dissatisfied," the response tone is softened and adjusted to provide reassurance.

[0513] The retuned response is sent in real time to the customer's communication terminal via a display control device. For example, if a customer asks, "How do I get a refund for my product?", a response such as, "Thank you for your question. If you wish to receive a refund for your product, please first select the relevant product from your order history and submit a refund request. We will be happy to assist you further if you have any difficulties with this procedure," is generated. The generated response and its process involve prompts generated using a generation AI model.

[0514] An example of a generated AI prompt might be: "Generate an appropriate response to a customer inquiry. The inquiry is 'How do I get a refund for this product?' The customer's sentiment is somewhat dissatisfied." This aims to improve the quality of responses and further increase customer satisfaction with inquiries.

[0515] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0516] Step 1:

[0517] The user uses a communication terminal to enter their inquiry and send it to the support system. The entered text is first forwarded by the terminal to the server. This allows the support system to receive the inquiry data.

[0518] Step 2:

[0519] The server analyzes the received text data using natural language processing (NLTK) tools. The text received as input undergoes grammatical and semantic analysis using natural language processing libraries such as NLTK and TensorFlow. The analysis results identify the intent of the query and related information.

[0520] Step 3:

[0521] The response generation mechanism within the server generates an appropriate response based on the analysis results. The AI ​​model then uses prompts to output the optimal response based on the input analysis results. These prompts include specific examples such as "Generate an appropriate response to the customer's inquiry."

[0522] Step 4:

[0523] The server uses sentiment analysis tools to identify the emotions contained in the inquiry. Using the analyzed text as input data, it employs a psychological model to output emotions such as "dissatisfaction" or "gratitude." This provides foundational data for adjusting the response.

[0524] Step 5:

[0525] The server performs tone adjustments on the responses generated by the response generation means, according to the emotion. The adjustment means receives the identified emotion as input and outputs an appropriate response tone. This adjustment makes it possible to generate responses that are empathetic to the emotions.

[0526] Step 6:

[0527] The server sends a coordinated response to the terminal and displays it to the user. This process is controlled by a display control mechanism, allowing the user to receive the response in real time on their communication terminal. This ensures that inquiries are answered quickly and appropriately.

[0528] Step 7:

[0529] The server records all inquiry content and sentiment data using information recording devices and stores it in a database for later analysis. The recorded data is used to improve the service and analyze inquiry trends.

[0530] 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.

[0531] The present invention relates to an advanced customer support system for automatically processing customer inquiries and generating responses. This system includes natural language processing means, response generation means, sentiment analysis means, tone adjustment means, and an emotion engine that recognizes the user's emotions in real time.

[0532] First, the user opens a chat window and enters their inquiry to support. For example, they might state a specific problem such as, "There is a problem with the product that was delivered. What should I do?" This inquiry is entered into the terminal and sent to the server.

[0533] The server analyzes the received text information using natural language processing to clarify the intent of the query. Based on the analyzed information, the server uses response generation tools to prepare a response that presents an appropriate solution to the user's problem. This response includes specific actions that the user should take.

[0534] To provide further added value, an emotion engine is utilized. The server uses the emotion engine to analyze the user's emotions in real time. By referring to past emotion history, it precisely analyzes the emotions derived from the current inquiry. This analysis allows the server to grasp subtle emotional nuances, such as whether the user is irritated or confused.

[0535] The results of sentiment analysis can be used to adjust the tone of responses. For example, if a user expresses dissatisfaction, the response will be more empathetic and polite. This tone adjustment allows the server to maximize customer satisfaction. Furthermore, if the sentiment engine recognizes a specific urgent emotional state, it promptly notifies support staff to facilitate direct human intervention.

[0536] Ultimately, the server sends the generated response to the terminal, which then displays it to the user. During this process, the response data is serialized and securely delivered to the user.

[0537] This invention enables companies to provide fast, accurate, and emotionally sensitive customer support, significantly improving the quality of the customer experience.

[0538] The following describes the processing flow.

[0539] Step 1:

[0540] The user opens the support chat window on the website or mobile app and enters their inquiry as text. For example, they might type, "My product is broken and I would like to return it. Could you please tell me how to do that?"

[0541] Step 2:

[0542] The terminal retrieves user input data and sends it to the server using a secure protocol. During this process, the query content is serialized in JSON format.

[0543] Step 3:

[0544] The server receives query data from the terminal and automatically analyzes the text using natural language processing. This analysis identifies the subject and intent, and then begins preparing an appropriate response.

[0545] Step 4:

[0546] The server activates an emotion engine to perform sentiment analysis on the inquiry. It recognizes the emotional state in real time and creates a more detailed emotion profile by comparing it with past emotion data.

[0547] Step 5:

[0548] Based on the sentiment analysis results and other analysis findings obtained, the server uses a response generation mechanism to construct a response appropriate to the user's situation. For example, it may generate a response that includes detailed steps for the return process and an apology to the user.

[0549] Step 6:

[0550] The server uses the results of its emotion engine analysis to adjust the tone of the response it generates. If the emotion is found to be dissatisfaction, the tone will be set to emphasize empathetic language and apologies.

[0551] Step 7:

[0552] After the response is completed, the server sends the response back to the terminal using a transmission method. At this time, the response is serialized in the appropriate format and delivered to the terminal securely and quickly.

[0553] Step 8:

[0554] The system deserializes the response received by the terminal and displays it visually to the user. Visual elements are used to display instructions in an easy-to-understand manner, helping the user to take quick action.

[0555] This entire process allows users to receive prompt and accurate support, and enables companies to increase customer satisfaction.

[0556] (Example 2)

[0557] 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."

[0558] Responding quickly and accurately to a wide range of customer inquiries is a crucial challenge in modern business. In particular, simply offering solutions without properly understanding the customer's emotions will not lead to improved customer satisfaction. Traditional systems often lacked sufficient emotional analysis and response tone adjustment capabilities, making it difficult to provide adequately satisfactory support.

[0559] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0560] In this invention, the server includes a natural language analysis means for automatically analyzing information from customers, a response generation means for generating an appropriate automatic response based on the analyzed information, an emotion analysis means for identifying emotions from the information, an expression adjustment means for adjusting the tone of the response according to the identified emotions, and a communication means for sending the adjusted response to the customer. This enables quick and appropriate responses that take into account the customer's emotions, thereby improving customer satisfaction.

[0561] A "natural language processing tool" is a program or device that analyzes text data provided by a customer and understands its intent and content.

[0562] A "response generation means" is a program or device for automatically creating an appropriate response to a customer based on information obtained by a natural language processing means.

[0563] "Emotional analysis tools" are programs or devices used to identify emotions contained in customer information and inquiries, and to analyze their nature and intensity.

[0564] "Expression adjustment means" refers to a program or device that adjusts the tone and expression of the generated response based on the results of emotion analysis means, and provides a response to the customer in an appropriate tone.

[0565] "Communication means" refers to technology or equipment that enables two-way information exchange by transmitting responses generated by a server to a customer's device.

[0566] "Information processing device" refers to a program or system for providing automated responses to customers, including the above-mentioned natural language processing means, response generation means, sentiment analysis means, expression adjustment means, and communication means.

[0567] A description of the embodiment for carrying out the invention will be provided.

[0568] This system consists of a server, terminals, and users. The server is the central component, primarily responsible for processing customer inquiries and generating automated responses.

[0569] The server first uses natural language processing (NLP) to analyze text information sent from the customer via their device. Examples of NLP tools used for this purpose include libraries such as "spaCy" and "BERT." This allows for accurate identification of the intent and content of the inquiry.

[0570] Next, the server uses a response generation mechanism to automatically create an appropriate response based on the analysis results. Here, a generative AI model is utilized to generate quick and accurate answers even to complex customer inquiries. The generative AI model uses prompt sentences such as, "Please tell me what to do if my product does not arrive."

[0571] Furthermore, the server uses sentiment analysis tools to extract customer emotions from text information. Sentiment analysis employs techniques that refer to past data to identify and analyze the intensity of emotions. Based on the obtained sentiment data, expression adjustment tools are used to adjust the tone and expression of the response. For example, if the customer expresses dissatisfaction or frustration, the response will be adjusted to be more empathetic and polite.

[0572] Finally, the server sends a refined response to the terminal via a communication method. The terminal displays the received response to the user and prompts the user for confirmation. This allows the user to quickly obtain appropriate countermeasures, which is expected to improve customer satisfaction.

[0573] For example, if a user asks, "What should I do if the clothes I ordered from the online store arrive in the wrong size?", the server will quickly generate a solution and provide an appropriate response. Thus, the ability to automatically provide accurate and emotionally sensitive responses to customer inquiries is a key feature of this invention.

[0574] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0575] Step 1:

[0576] The user opens a support chat window on their device and enters their specific inquiry. For example, "My ordered item hasn't arrived. What should I do?" This input is sent to the server as text data by the device.

[0577] Step 2:

[0578] The server analyzes text data received from the terminal using natural language processing (NLP) tools. The input is the user's inquiry text, and the analysis process extracts key topics and intents using a natural language processing library. The output of this process is data that clearly identifies the user's request.

[0579] Step 3:

[0580] The server generates an appropriate response using a response generation mechanism based on the analyzed data. The input for this step is the analysis results, and the output includes an automatically generated solution to the user's problem. The response is generated by a generation AI model. For example, it could provide instructions on how to check the delivery status or how to cancel an order.

[0581] Step 4:

[0582] The server evaluates the user's emotions using sentiment analysis tools based on the generated response. The input consists of the user's inquiry and response, and the sentiment analysis engine identifies the user's emotional state. The output of this process is data related to the user's emotions.

[0583] Step 5:

[0584] The server uses sentiment analysis results to apply expression adjustment mechanisms that modify the tone of the response. The input consists of the response and sentiment data, and the output is the adjusted response. This process makes the response empathetic and appropriate for the situation. For example, a response to a dissatisfied user can be changed to a tone that conveys apology and a promise of prompt action.

[0585] Step 6:

[0586] The server sends a pre-arranged response to the user's terminal via a communication method. The input is the pre-arranged response, and the output is a text message received by the terminal. The terminal displays the received response on its screen and notifies the user. This allows the user to quickly obtain appropriate countermeasures.

[0587] (Application Example 2)

[0588] 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."

[0589] In customer support, it is crucial to respond to customer inquiries quickly and appropriately. However, traditional systems have difficulty automatically generating responses that take customer emotions into account, which can lead to decreased customer satisfaction. Therefore, it is necessary to accurately analyze customer emotions and provide responses in an appropriate tone.

[0590] 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.

[0591] In this invention, the server includes a string analysis means for automatically analyzing customer inquiries, a response generation means for generating an appropriate automated response based on the content analyzed by the analysis means, and an emotion estimation means for identifying the customer's emotions from the customer's inquiry. This enables a quick and accurate response that takes the customer's emotions into consideration.

[0592] A "string analysis method" is a means of automatically analyzing customer inquiries to clarify their intent.

[0593] A "response generation means" is a means of automatically creating an appropriate response based on the analyzed content.

[0594] "Emotion estimation methods" are means of identifying customer emotions in real time from customer inquiries.

[0595] "Tone adjustment means" are means of adjusting the tone of the response produced in accordance with a specific emotion.

[0596] An "emotional evaluation method" is a means of evaluating a customer's emotions in real time and analyzing them precisely by referring to their past emotional history.

[0597] A "transmission device" is a device that securely serializes and transmits the generated response to the customer's information processing device.

[0598] An "information recording device" is a device used to record and analyze inquiry content and sentiment data.

[0599] In the system for carrying out this invention, the server is equipped with string analysis means, response generation means, emotion estimation means, tone adjustment means, and emotion evaluation means. This enables advanced customer support. Specifically, the server analyzes the inquiry entered by the user into the terminal and understands its intent.

[0600] This analysis uses Python, leveraging the spaCy library for natural language processing. Furthermore, Hugging Face's Transformers are used for sentiment estimation and evaluation, with real-time sentiment assessment performed via PyTorch. This allows for immediate understanding of the sentiment state of strings obtained from queries.

[0601] The response generation mechanism automatically generates an appropriate response based on the generated data, and this response is then adjusted by the tone adjustment mechanism to match the identified emotion. This tone adjustment allows customers to receive a more friendly and empathetic response, which is expected to improve customer satisfaction.

[0602] The serialized data is securely transmitted to the terminal via the transmission device and displayed to the user. The user can then use their smartphone to review the generated response and take action based on it.

[0603] As a concrete example, if a user inquires that "there is a problem with the product that was sold," the server will appropriately analyze the inquiry and provide an empathetic response such as, "We will address this immediately. We will send you a new product." An example of a prompt message might be, "Generate a response message for when a user reports a product error and requires a quick and empathetic response."

[0604] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0605] Step 1:

[0606] The user enters their inquiry using a terminal and submits it. This input is sent to the server as text data.

[0607] Step 2:

[0608] The server analyzes the received text data using string parsing. This process uses Python and the spaCy library to perform data processing to identify the intent of the query. The output is the analysis result.

[0609] Step 3:

[0610] The server uses emotion estimation tools based on the analysis results to estimate the user's emotional state. This process utilizes Hugging Face's Transformers to evaluate the emotion of the inquiry in real time. The output is the estimated emotion data.

[0611] Step 4:

[0612] The server uses a response generation mechanism to generate an appropriate response based on the analysis results and sentiment data. This procedure utilizes a generative AI model to perform data calculations and output an ideal response sentence.

[0613] Step 5:

[0614] The server adjusts the generated response using tone-adjustment mechanisms. Depending on the identified emotion, it adjusts the tone of the generated response, transforming it into an empathetic or polite tone. This adjusted response becomes the final output.

[0615] Step 6:

[0616] The server serializes the adjusted response and sends it to the user's terminal using a transmission device. During this process, the secure transport of data is ensured, and the terminal displays the final response to the user.

[0617] 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.

[0618] 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.

[0619] 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.

[0620] [Fourth Embodiment]

[0621] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0622] 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.

[0623] 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).

[0624] 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.

[0625] 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.

[0626] 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).

[0627] 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.

[0628] 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.

[0629] 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.

[0630] 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.

[0631] 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.

[0632] 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.

[0633] 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".

[0634] This invention is a generative AI-based solution that fully automates a company's customer support system, aiming to respond to customer inquiries quickly and accurately. The system uses natural language processing technology to analyze inquiry content, generate responses, perform sentiment analysis, and adjust tone, thereby achieving sophisticated customer service.

[0635] First, the user accesses the support system and enters their inquiry into the chat window. For example, "How do I get a refund for my product?" Once the inquiry is sent, the device transfers the entered text data to the server.

[0636] Subsequently, the server analyzes the received text using natural language processing to understand the customer's intent. Based on this analysis, the server uses response generation tools to generate an appropriate response. The generated response provides relevant information based on the customer's inquiry.

[0637] Next, the server uses sentiment analysis tools to identify the customer's emotions from their language and context. This analysis allows the server to determine whether the customer's emotions are in a state such as "dissatisfaction," "doubt," or "gratitude." The results of this sentiment analysis are used to deliver a response to the customer in an appropriate tone. The server uses tone adjustment tools to adjust the tone of the response and provide appropriate communication to the customer.

[0638] Finally, the server uses a transmission method to send the generated response and text with an adjusted tone to the terminal. The terminal receives this and displays it to the user. For example, the displayed message might say, "If you would like a refund for your order, please follow these steps," with the wording becoming gentler or more polite depending on the user's emotions.

[0639] Furthermore, this system is equipped with data recording capabilities, allowing the server to record all inquiry details and sentiment data, which can then be used for later analysis and service improvement.

[0640] This system allows companies to significantly improve the efficiency of customer support and achieve higher customer satisfaction.

[0641] The following describes the processing flow.

[0642] Step 1:

[0643] The user opens the customer support chat window and enters their inquiry. For example, they might enter a specific question such as, "How do I exchange a product?"

[0644] Step 2:

[0645] The terminal retrieves text data entered by the user and sends it to the server. The terminal uses a REST API to serialize the query content in JSON format and send it to the server.

[0646] Step 3:

[0647] The server receives data sent from the terminal and passes it to a natural language processing system to analyze the query. Here, the server checks the data format and filters out unnecessary information.

[0648] Step 4:

[0649] The natural language processing system installed on the server analyzes the query content and understands the user's intentions. It understands what the query is requesting and prepares to select relevant information from the database.

[0650] Step 5:

[0651] The server uses a response generation mechanism to construct an appropriate response based on the analysis results. For example, it combines necessary information, such as policies and procedures related to product exchange, to create a response.

[0652] Step 6:

[0653] The server uses sentiment analysis tools to extract emotions from user inquiries. Based on the linguistic expression of the inquiry, it determines whether the user is experiencing emotions such as "anxiety" or "doubt."

[0654] Step 7:

[0655] The server uses tone adjustment mechanisms to appropriately adjust the tone of responses based on the results of sentiment analysis. For example, if the user is showing anxiety, the response will be made more reassuring.

[0656] Step 8:

[0657] The server prepares to send the completed response to the terminal and sends it to the terminal using the transmission method. The response is then converted back to JSON format and sent to the terminal.

[0658] Step 9:

[0659] The terminal receives the response sent from the server and displays it in the user's chat window. Based on the displayed information, the user can receive appropriate instructions and complete the support process.

[0660] (Example 1)

[0661] 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".

[0662] In today's world, there is a demand for prompt and accurate responses to customer inquiries. However, conventional systems struggle to efficiently handle a large volume of inquiries, potentially leading to decreased customer satisfaction. Furthermore, the lack of flexible responses tailored to the user's emotions results in inconsistent service quality.

[0663] 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.

[0664] In this invention, the server includes language processing means for automatically analyzing information from users, information generation means for generating appropriate responses, and information analysis means for identifying emotions. This enables rapid and accurate analysis of user inquiries and the provision of appropriate responses tailored to the user's emotions.

[0665] "Users" refer to individuals or organizations that access the system and use its services.

[0666] "Information" refers to data and inquiries provided by users, and is the subject of language processing and analysis.

[0667] "Processing means" refers to technical methods and devices for analyzing information and performing appropriate data processing.

[0668] "Language processing means" refers to methods and technological devices for analyzing natural language and understanding information.

[0669] "Information generation means" refers to methods and technical devices for generating appropriate responses based on analyzed information.

[0670] "Information analysis means" refers to methods and technological devices used to analyze user information and specifically identify emotions.

[0671] "Adjustment means" refers to methods or technical devices for changing the nature or tone of the generated response according to the situation.

[0672] "Reference means" refers to methods and technical devices for querying related materials and databases based on the analyzed information.

[0673] "Generation means" refers to methods and technical devices for optimizing answers generated using a pre-trained artificial intelligence model.

[0674] "Transmission means" refers to methods or technical devices for transmitting the generated response to the user's display device.

[0675] "Data processing means" refers to methods, technologies, and devices for handling recorded and analyzed information and utilizing it for operation and improvement.

[0676] The system in this invention automates customer support for businesses, enabling them to respond to user inquiries quickly and accurately. This system primarily communicates between a server, a terminal, and a user, and operates through multiple stages of processing.

[0677] The server first receives data sent from the user. It uses natural language processing (NLP) software, such as spaCy or Transformers, which are well-known NLP libraries for Python. To quickly analyze the received text, the server uses these libraries to perform syntactic and semantic analysis.

[0678] Once the analysis is complete, the server generates a response based on the generated data. This process utilizes a generative AI model. For example, it leverages advanced models such as OpenAI's GPT-3 to generate a natural-sounding response based on the analyzed content. The generated response is then further optimized by information generation tools.

[0679] Next, the server uses sentiment analysis tools to determine the emotion behind the user's statements. Software such as VADER and TextBlob is used for sentiment analysis. Based on the analyzed sentiment information, the generated response is tone-adjusted to make it more personalized.

[0680] The generated response is sent to the terminal and displayed to the user. This process takes place via WebSocket or HTTP requests, and the terminal presents the provided information to the user. The wording and tone of the presentation are adjusted according to the customer's mood.

[0681] Furthermore, the server records all inquiry and sentiment data, which can then be used for later analysis and logistics improvements. This allows companies to significantly improve the efficiency of customer service and increase customer satisfaction.

[0682] As a concrete example, here is an example of a prompt sentence to be input into the generation AI model: "When a user inquires about how to get a refund for a product, analyze the customer's emotions and generate a response in an appropriate tone."

[0683] Thus, this invention utilizes natural language processing technology and AI generation technology to realize an automated response system for user inquiries.

[0684] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0685] Step 1:

[0686] The user accesses the customer support system and enters their inquiry into the chat window. At this point, the entered information is sent to the server as text data. For example, suppose the user enters the inquiry, "How do I get a refund for this product?" At this stage, the user has entered information, and its output is processed as text data.

[0687] Step 2:

[0688] The terminal transfers the text data entered by the user to the server. This data is transmitted via WebSocket or HTTP requests. The input is the user's inquiry text, and the output is sending this text data to the server. Through this process, the terminal acts as a bridge, conveying the user's intent to the server.

[0689] Step 3:

[0690] The server performs natural language processing on the received text data. Specifically, it uses Python libraries such as spaCy and Transformers to perform syntactic and semantic analysis. The input is the user's query text, and the output is the parsed text data. Through this analysis, the server accurately understands the user's intent.

[0691] Step 4:

[0692] The server generates a response based on the analyzed data. This process utilizes a generative AI model, such as OpenAI's GPT-3. The input is the analysis result, and the output is a response message based on the user's intent. At this stage, a prompt is input to the generative AI model to generate an appropriate message.

[0693] Step 5:

[0694] The server then performs sentiment analysis to adjust the tone of its responses. Tools such as VADER and TextBlob are used for sentiment analysis. The input is the user's text data, and the output is sentiment information associated with that text. This sentiment information is used to adjust the tone of the responses to better reflect the user's emotions.

[0695] Step 6:

[0696] The server sends the final response message to the terminal and displays it to the user. The response is transmitted quickly via WebSocket or HTTP response. The input is the tone-adjusted response, and the output is what is displayed to the user. The terminal displays this message in the chat window so that the user can see it.

[0697] Step 7:

[0698] The server records all inquiries and sentiment data in a database. This data is later analyzed and used to improve services and enhance the quality of customer support. The input consists of inquiry content and sentiment data, which are stored in the database. This process allows the server to accumulate resources for future analysis.

[0699] (Application Example 1)

[0700] 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".

[0701] Responding to customer inquiries is crucial for businesses, but it also requires significant effort and cost. E-commerce sites, in particular, experience frequent customer inquiries and demand prompt and accurate responses. However, relying solely on human resources has its limitations, and it's difficult to provide responses that truly address customer needs and emotions. Therefore, there is a need to develop systems that efficiently handle customer inquiries without compromising the customer experience.

[0702] 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.

[0703] In this invention, the server includes information processing means for automatically analyzing customer inquiries, response generation means for generating appropriate automatic responses based on the analyzed content, analysis means for identifying emotions from inquiries, adjustment means for adjusting the method of transmitting the response according to the emotions identified by the analysis means, and display control means for displaying the response on the customer terminal in real time on the e-commerce site. This makes it possible to automatically provide appropriate and rapid responses that correspond to the customer's emotions.

[0704] "Information processing means" refers to technical methods for automatically analyzing customer inquiries.

[0705] The "response generation means" is a function that generates an appropriate automated response based on the analyzed inquiry content.

[0706] "Analysis tools" refer to functions used to identify emotions from customer inquiries.

[0707] A "regulatory mechanism" is a system that adjusts the method of communication of a response according to a specific emotion.

[0708] "Display control means" refers to a function used on e-commerce sites to display responses on customer terminals in real time.

[0709] A "communication terminal" is a device used by customers to access online shopping sites.

[0710] "Information recording means" refers to a function for recording and analyzing customer inquiries and emotional data.

[0711] This invention is an advanced application system for streamlining customer support on e-commerce websites. The system consists of a server on the cloud and customer communication terminals.

[0712] The server uses information processing tools equipped with natural language processing technology to analyze inquiries sent by customers. For this purpose, natural language processing libraries such as NLTK and TensorFlow using Python are used. When customer inquiries are sent to the server, the server quickly analyzes them and identifies the customer's intent.

[0713] After analysis, a response generation system generates an appropriate response based on the identified intent, and this response is operated using cloud services such as Amazon Web Services (AWS) Lambda. This response is not only a direct answer but is also adjusted based on sentiment analysis. The server uses the analysis system to determine the customer's emotions at the time of the inquiry. For example, if it is determined that the customer is feeling "dissatisfied," the response tone is softened and adjusted to provide reassurance.

[0714] The retuned response is sent in real time to the customer's communication terminal via a display control device. For example, if a customer asks, "How do I get a refund for my product?", a response such as, "Thank you for your question. If you wish to receive a refund for your product, please first select the relevant product from your order history and submit a refund request. We will be happy to assist you further if you have any difficulties with this procedure," is generated. The generated response and its process involve prompts generated using a generation AI model.

[0715] An example of a generated AI prompt might be: "Generate an appropriate response to a customer inquiry. The inquiry is 'How do I get a refund for this product?' The customer's sentiment is somewhat dissatisfied." This aims to improve the quality of responses and further increase customer satisfaction with inquiries.

[0716] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0717] Step 1:

[0718] The user uses a communication terminal to enter their inquiry and send it to the support system. The entered text is first forwarded by the terminal to the server. This allows the support system to receive the inquiry data.

[0719] Step 2:

[0720] The server analyzes the received text data using natural language processing (NLTK) tools. The text received as input undergoes grammatical and semantic analysis using natural language processing libraries such as NLTK and TensorFlow. The analysis results identify the intent of the query and related information.

[0721] Step 3:

[0722] The response generation mechanism within the server generates an appropriate response based on the analysis results. The AI ​​model then uses prompts to output the optimal response based on the input analysis results. These prompts include specific examples such as "Generate an appropriate response to the customer's inquiry."

[0723] Step 4:

[0724] The server uses sentiment analysis tools to identify the emotions contained in the inquiry. Using the analyzed text as input data, it employs a psychological model to output emotions such as "dissatisfaction" or "gratitude." This provides foundational data for adjusting the response.

[0725] Step 5:

[0726] The server performs tone adjustments on the responses generated by the response generation means, according to the emotion. The adjustment means receives the identified emotion as input and outputs an appropriate response tone. This adjustment makes it possible to generate responses that are empathetic to the emotions.

[0727] Step 6:

[0728] The server sends a coordinated response to the terminal and displays it to the user. This process is controlled by a display control mechanism, allowing the user to receive the response in real time on their communication terminal. This ensures that inquiries are answered quickly and appropriately.

[0729] Step 7:

[0730] The server records all inquiry content and sentiment data using information recording devices and stores it in a database for later analysis. The recorded data is used to improve the service and analyze inquiry trends.

[0731] 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.

[0732] The present invention relates to an advanced customer support system for automatically processing customer inquiries and generating responses. This system includes natural language processing means, response generation means, sentiment analysis means, tone adjustment means, and an emotion engine that recognizes the user's emotions in real time.

[0733] First, the user opens a chat window and enters their inquiry to support. For example, they might state a specific problem such as, "There is a problem with the product that was delivered. What should I do?" This inquiry is entered into the terminal and sent to the server.

[0734] The server analyzes the received text information using natural language processing to clarify the intent of the query. Based on the analyzed information, the server uses response generation tools to prepare a response that presents an appropriate solution to the user's problem. This response includes specific actions that the user should take.

[0735] To provide further added value, an emotion engine is utilized. The server uses the emotion engine to analyze the user's emotions in real time. By referring to past emotion history, it precisely analyzes the emotions derived from the current inquiry. This analysis allows the server to grasp subtle emotional nuances, such as whether the user is irritated or confused.

[0736] The results of sentiment analysis can be used to adjust the tone of responses. For example, if a user expresses dissatisfaction, the response will be more empathetic and polite. This tone adjustment allows the server to maximize customer satisfaction. Furthermore, if the sentiment engine recognizes a specific urgent emotional state, it promptly notifies support staff to facilitate direct human intervention.

[0737] Ultimately, the server sends the generated response to the terminal, which then displays it to the user. During this process, the response data is serialized and securely delivered to the user.

[0738] This invention enables companies to provide fast, accurate, and emotionally sensitive customer support, significantly improving the quality of the customer experience.

[0739] The following describes the processing flow.

[0740] Step 1:

[0741] The user opens the support chat window on the website or mobile app and enters their inquiry as text. For example, they might type, "My product is broken and I would like to return it. Could you please tell me how to do that?"

[0742] Step 2:

[0743] The terminal retrieves user input data and sends it to the server using a secure protocol. During this process, the query content is serialized in JSON format.

[0744] Step 3:

[0745] The server receives query data from the terminal and automatically analyzes the text using natural language processing. This analysis identifies the subject and intent, and then begins preparing an appropriate response.

[0746] Step 4:

[0747] The server activates an emotion engine to perform sentiment analysis on the inquiry. It recognizes the emotional state in real time and creates a more detailed emotion profile by comparing it with past emotion data.

[0748] Step 5:

[0749] Based on the sentiment analysis results and other analysis findings obtained, the server uses a response generation mechanism to construct a response appropriate to the user's situation. For example, it may generate a response that includes detailed steps for the return process and an apology to the user.

[0750] Step 6:

[0751] The server uses the results of its emotion engine analysis to adjust the tone of the response it generates. If the emotion is found to be dissatisfaction, the tone will be set to emphasize empathetic language and apologies.

[0752] Step 7:

[0753] After the response is completed, the server sends the response back to the terminal using a transmission method. At this time, the response is serialized in the appropriate format and delivered to the terminal securely and quickly.

[0754] Step 8:

[0755] The system deserializes the response received by the terminal and displays it visually to the user. Visual elements are used to display instructions in an easy-to-understand manner, helping the user to take quick action.

[0756] This entire process allows users to receive prompt and accurate support, and enables companies to increase customer satisfaction.

[0757] (Example 2)

[0758] 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".

[0759] Responding quickly and accurately to a wide range of customer inquiries is a crucial challenge in modern business. In particular, simply offering solutions without properly understanding the customer's emotions will not lead to improved customer satisfaction. Traditional systems often lacked sufficient emotional analysis and response tone adjustment capabilities, making it difficult to provide adequately satisfactory support.

[0760] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0761] In this invention, the server includes a natural language analysis means for automatically analyzing information from customers, a response generation means for generating an appropriate automatic response based on the analyzed information, an emotion analysis means for identifying emotions from the information, an expression adjustment means for adjusting the tone of the response according to the identified emotions, and a communication means for sending the adjusted response to the customer. This enables quick and appropriate responses that take into account the customer's emotions, thereby improving customer satisfaction.

[0762] A "natural language processing tool" is a program or device that analyzes text data provided by a customer and understands its intent and content.

[0763] A "response generation means" is a program or device for automatically creating an appropriate response to a customer based on information obtained by a natural language processing means.

[0764] "Emotional analysis tools" are programs or devices used to identify emotions contained in customer information and inquiries, and to analyze their nature and intensity.

[0765] "Expression adjustment means" refers to a program or device that adjusts the tone and expression of the generated response based on the results of emotion analysis means, and provides a response to the customer in an appropriate tone.

[0766] "Communication means" refers to technology or equipment that enables two-way information exchange by transmitting responses generated by a server to a customer's device.

[0767] "Information processing device" refers to a program or system for providing automated responses to customers, including the above-mentioned natural language processing means, response generation means, sentiment analysis means, expression adjustment means, and communication means.

[0768] A description of the embodiment for carrying out the invention will be provided.

[0769] This system consists of a server, terminals, and users. The server is the central component, primarily responsible for processing customer inquiries and generating automated responses.

[0770] The server first uses natural language processing (NLP) to analyze text information sent from the customer via their device. Examples of NLP tools used for this purpose include libraries such as "spaCy" and "BERT." This allows for accurate identification of the intent and content of the inquiry.

[0771] Next, the server uses a response generation mechanism to automatically create an appropriate response based on the analysis results. Here, a generative AI model is utilized to generate quick and accurate answers even to complex customer inquiries. The generative AI model uses prompt sentences such as, "Please tell me what to do if my product does not arrive."

[0772] Furthermore, the server uses sentiment analysis tools to extract customer emotions from text information. Sentiment analysis employs techniques that refer to past data to identify and analyze the intensity of emotions. Based on the obtained sentiment data, expression adjustment tools are used to adjust the tone and expression of the response. For example, if the customer expresses dissatisfaction or frustration, the response will be adjusted to be more empathetic and polite.

[0773] Finally, the server sends a refined response to the terminal via a communication method. The terminal displays the received response to the user and prompts the user for confirmation. This allows the user to quickly obtain appropriate countermeasures, which is expected to improve customer satisfaction.

[0774] For example, if a user asks, "What should I do if the clothes I ordered from the online store arrive in the wrong size?", the server will quickly generate a solution and provide an appropriate response. Thus, the ability to automatically provide accurate and emotionally sensitive responses to customer inquiries is a key feature of this invention.

[0775] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0776] Step 1:

[0777] The user opens a support chat window on their device and enters their specific inquiry. For example, "My ordered item hasn't arrived. What should I do?" This input is sent to the server as text data by the device.

[0778] Step 2:

[0779] The server analyzes text data received from the terminal using natural language processing (NLP) tools. The input is the user's inquiry text, and the analysis process extracts key topics and intents using a natural language processing library. The output of this process is data that clearly identifies the user's request.

[0780] Step 3:

[0781] The server generates an appropriate response using a response generation mechanism based on the analyzed data. The input for this step is the analysis results, and the output includes an automatically generated solution to the user's problem. The response is generated by a generation AI model. For example, it could provide instructions on how to check the delivery status or how to cancel an order.

[0782] Step 4:

[0783] The server evaluates the user's emotions using sentiment analysis tools based on the generated response. The input consists of the user's inquiry and response, and the sentiment analysis engine identifies the user's emotional state. The output of this process is data related to the user's emotions.

[0784] Step 5:

[0785] The server uses sentiment analysis results to apply expression adjustment mechanisms that modify the tone of the response. The input consists of the response and sentiment data, and the output is the adjusted response. This process makes the response empathetic and appropriate for the situation. For example, a response to a dissatisfied user can be changed to a tone that conveys apology and a promise of prompt action.

[0786] Step 6:

[0787] The server sends a pre-arranged response to the user's terminal via a communication method. The input is the pre-arranged response, and the output is a text message received by the terminal. The terminal displays the received response on its screen and notifies the user. This allows the user to quickly obtain appropriate countermeasures.

[0788] (Application Example 2)

[0789] 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".

[0790] In customer support, it is crucial to respond to customer inquiries quickly and appropriately. However, traditional systems have difficulty automatically generating responses that take customer emotions into account, which can lead to decreased customer satisfaction. Therefore, it is necessary to accurately analyze customer emotions and provide responses in an appropriate tone.

[0791] 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.

[0792] In this invention, the server includes a string analysis means for automatically analyzing customer inquiries, a response generation means for generating an appropriate automated response based on the content analyzed by the analysis means, and an emotion estimation means for identifying the customer's emotions from the customer's inquiry. This enables a quick and accurate response that takes the customer's emotions into consideration.

[0793] A "string analysis method" is a means of automatically analyzing customer inquiries to clarify their intent.

[0794] A "response generation means" is a means of automatically creating an appropriate response based on the analyzed content.

[0795] "Emotion estimation methods" are means of identifying customer emotions in real time from customer inquiries.

[0796] "Tone adjustment means" are means of adjusting the tone of the response produced in accordance with a specific emotion.

[0797] An "emotional evaluation method" is a means of evaluating a customer's emotions in real time and analyzing them precisely by referring to their past emotional history.

[0798] A "transmission device" is a device that securely serializes and transmits the generated response to the customer's information processing device.

[0799] An "information recording device" is a device used to record and analyze inquiry content and sentiment data.

[0800] In the system for carrying out this invention, the server is equipped with string analysis means, response generation means, emotion estimation means, tone adjustment means, and emotion evaluation means. This enables advanced customer support. Specifically, the server analyzes the inquiry entered by the user into the terminal and understands its intent.

[0801] This analysis uses Python, leveraging the spaCy library for natural language processing. Furthermore, Hugging Face's Transformers are used for sentiment estimation and evaluation, with real-time sentiment assessment performed via PyTorch. This allows for immediate understanding of the sentiment state of strings obtained from queries.

[0802] The response generation mechanism automatically generates an appropriate response based on the generated data, and this response is then adjusted by the tone adjustment mechanism to match the identified emotion. This tone adjustment allows customers to receive a more friendly and empathetic response, which is expected to improve customer satisfaction.

[0803] The serialized data is securely transmitted to the terminal via the transmission device and displayed to the user. The user can then use their smartphone to review the generated response and take action based on it.

[0804] As a concrete example, if a user inquires that "there is a problem with the product that was sold," the server will appropriately analyze the inquiry and provide an empathetic response such as, "We will address this immediately. We will send you a new product." An example of a prompt message might be, "Generate a response message for when a user reports a product error and requires a quick and empathetic response."

[0805] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0806] Step 1:

[0807] The user enters their inquiry using a terminal and submits it. This input is sent to the server as text data.

[0808] Step 2:

[0809] The server analyzes the received text data using string parsing. This process uses Python and the spaCy library to perform data processing to identify the intent of the query. The output is the analysis result.

[0810] Step 3:

[0811] The server uses emotion estimation tools based on the analysis results to estimate the user's emotional state. This process utilizes Hugging Face's Transformers to evaluate the emotion of the inquiry in real time. The output is the estimated emotion data.

[0812] Step 4:

[0813] The server uses a response generation mechanism to generate an appropriate response based on the analysis results and sentiment data. This procedure utilizes a generative AI model to perform data calculations and output an ideal response sentence.

[0814] Step 5:

[0815] The server adjusts the generated response using tone-adjustment mechanisms. Depending on the identified emotion, it adjusts the tone of the generated response, transforming it into an empathetic or polite tone. This adjusted response becomes the final output.

[0816] Step 6:

[0817] The server serializes the adjusted response and sends it to the user's terminal using a transmission device. During this process, the secure transport of data is ensured, and the terminal displays the final response to the user.

[0818] 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.

[0819] 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.

[0820] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0821] 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.

[0822] 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.

[0823] 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.

[0824] 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.

[0825] 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.

[0826] 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."

[0827] 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.

[0828] 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.

[0829] 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.

[0830] 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.

[0831] 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.

[0832] 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.

[0833] 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.

[0834] 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.

[0835] 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.

[0836] 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.

[0837] 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.

[0838] 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.

[0839] The following is further disclosed regarding the embodiments described above.

[0840] (Claim 1)

[0841] A natural language processing method that automatically analyzes customer inquiries,

[0842] A response generation means that generates an appropriate automatic response based on the content analyzed by the analysis means,

[0843] A sentiment analysis tool for identifying emotions from the aforementioned customer inquiry,

[0844] A tone adjustment means that adjusts the tone of the response generated by the response generation means in accordance with the emotion identified by the emotion analysis means,

[0845] A system that includes this.

[0846] (Claim 2)

[0847] The system according to claim 1, further comprising a transmission means for serializing and transmitting the response generated by the response generation means to a customer's terminal.

[0848] (Claim 3)

[0849] The system according to claim 1, further comprising data recording means for recording and analyzing the customer's inquiry content and emotional data obtained by the emotional analysis means.

[0850] "Example 1"

[0851] (Claim 1)

[0852] A language processing method that automatically analyzes information from users,

[0853] Information generation means that generates an appropriate response based on the content analyzed by the analysis means,

[0854] Information analysis means for identifying emotions from the aforementioned user information,

[0855] An adjustment means for adjusting the response generated by the information generation means in accordance with the emotion identified by the information analysis means,

[0856] A reference means for querying related materials based on the results obtained from the aforementioned information analysis,

[0857] A generation means that optimizes the answer generated using a trained artificial intelligence model,

[0858] A system that includes this.

[0859] (Claim 2)

[0860] The system according to claim 1, further comprising a transmission means for transmitting the response generated by the information generation means in data format to a user's display device.

[0861] (Claim 3)

[0862] The system according to claim 1, further comprising a data processing means for recording and analyzing the user's information content and emotional data obtained by the information analysis means.

[0863] "Application Example 1"

[0864] (Claim 1)

[0865] Information processing means for automatically analyzing customer inquiries,

[0866] A response generation means that generates an appropriate automatic response based on the content analyzed by the information processing means,

[0867] An analytical means for identifying emotions from the aforementioned customer inquiry,

[0868] An adjustment means for adjusting the method of transmitting the response generated by the response generation means in accordance with the emotion identified by the analysis means,

[0869] A display control means for displaying the aforementioned response on a customer terminal in real time on an e-commerce site,

[0870] A system that includes this.

[0871] (Claim 2)

[0872] The system according to claim 1, further comprising a transmission means for serializing and transmitting the response generated by the response generation means to a customer's communication terminal.

[0873] (Claim 3)

[0874] The system according to claim 1, further comprising information recording means for recording and analyzing the customer's inquiry content and emotional data obtained by the analysis means.

[0875] "Example 2 of combining an emotion engine"

[0876] (Claim 1)

[0877] A natural language processing method that automatically analyzes customer information,

[0878] A response generation means that generates an appropriate automatic response based on the information analyzed by the analysis means,

[0879] A means for analyzing emotions to identify emotions from the aforementioned customer information,

[0880] Expression adjustment means that adjusts the tone of the response generated by the response generation means in accordance with the emotion identified by the emotion analysis means,

[0881] A communication means for transmitting the adjusted response to the customer,

[0882] Information processing device including

[0883] (Claim 2)

[0884] The information processing apparatus according to claim 1, further comprising a transmission function for converting and transmitting the response generated by the communication means to a customer's device.

[0885] (Claim 3)

[0886] The information processing apparatus according to claim 1, further comprising an information recording means for recording and analyzing the customer information content and the emotional information obtained by the emotional analysis means.

[0887] "Application example 2 when combining with an emotional engine"

[0888] (Claim 1)

[0889] A string analysis method that automatically analyzes customer inquiries,

[0890] A response generation means that generates an appropriate automatic response based on the content analyzed by the analysis means,

[0891] A means for estimating emotions to identify emotions from the aforementioned customer inquiry,

[0892] A tone-of-speech adjustment means adjusts the tone of the response generated by the response generation means in accordance with the emotion identified by the emotion estimation means,

[0893] An emotion evaluation means for evaluating the customer's emotions in real time,

[0894] A system that includes this.

[0895] (Claim 2)

[0896] The system according to claim 1, further comprising a transmitting device for serializing and transmitting the response generated by the response generation means to a customer information processing device.

[0897] (Claim 3)

[0898] The system according to claim 1, further comprising an information recording device for recording and analyzing the customer's inquiry content and emotion data obtained by the emotion estimation means. [Explanation of Symbols]

[0899] 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 natural language processing method that automatically analyzes customer inquiries, A response generation means that generates an appropriate automatic response based on the content analyzed by the analysis means, A sentiment analysis tool for identifying emotions from the aforementioned customer inquiry, A tone adjustment means that adjusts the tone of the response generated by the response generation means in accordance with the emotion identified by the emotion analysis means, A system that includes this.

2. The system according to claim 1, further comprising a transmission means for serializing and transmitting the response generated by the response generation means to a customer's terminal.

3. The system according to claim 1, further comprising data recording means for recording and analyzing the customer's inquiry content and emotional data obtained by the emotional analysis means.

Images