system

Abstract

We provide the system. [Solution] A means of receiving voice input from customers, A speech recognition means that converts the aforementioned voice input into text data, A natural language processing means for analyzing customer intent from the aforementioned text data, A response generation means that generates appropriate response text based on the analyzed intent, A speech synthesis means that converts the aforementioned response text into speech data, A system including means for transmitting the aforementioned audio data to a customer.

Description

【Technical Field】 【0001】 The technology of the present disclosure relates to a system. 【Background Art】 【0002】 Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. 【Prior Art Documents】 【Patent Documents】 【0003】 【Patent Document 1】 Japanese Patent Application Laid-Open No. 2022-180282 【Summary of the Invention】 【Problems to be Solved by the Invention】 【0004】 In a conventional call center system, it is difficult to respond appropriately and promptly to inquiries from customers. In particular, when there is a shortage of operators or during peak inquiry hours, customers may be made to wait for a long time, which may lead to a decrease in customer satisfaction and cancellations. In addition, due to insufficient multilingual support, the support for customers who speak foreign languages is limited. There is a need to solve such problems, reduce customer stress, and improve customer satisfaction. 【Means for Solving the Problems】 【0005】 This invention provides a system that receives voice input from customers, converts it into text data using speech recognition, and analyzes the customer's intent using natural language processing. Based on the analyzed intent, it generates response text and sends it to the customer using speech synthesis. Furthermore, it improves the accuracy of natural language processing by accumulating and analyzing feedback data with learning capabilities. In addition, by making speech recognition and speech synthesis compatible with multiple languages, it enables customer support in a variety of languages, including foreign languages. This enables efficient and cost-effective customer support 24 hours a day, 365 days a year. 【0006】 "Voice recognition means" refers to a device or program that converts voice input from a customer into text data. 【0007】 "Natural language processing means" refers to a technology or program that analyzes customer intent from text data and extracts information necessary for generating a response. 【0008】 A "response generation means" is a process or system that generates an appropriate response in text format based on the analyzed intent. 【0009】 "Speech synthesis means" refers to a system or technology that converts generated text responses into natural-sounding speech expressions. 【0010】 A "learning tool" is a process or device for accumulating and analyzing customer feedback data and using the results to improve the accuracy and performance of the system. 【0011】 "Adjustment means" refers to methods or mechanisms for adjusting speech recognition and speech synthesis functions to support multiple languages. [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, a processor with a reference numeral (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, a RAM (Random Access Memory) with a reference numeral is a memory in which information is temporarily stored and is used as a work memory by the processor. 【0017】 In the following embodiments, a storage with a reference numeral is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like. 【0018】 In the following embodiments, a communication I / F (Interface) with a reference numeral is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like. 【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】 The system of this invention automatically processes voice data using AI technology to handle customer inquiries via telephone. First, when a user makes a call, the server receives the voice input. The server uses speech recognition means to convert the user's voice into text data. This speech recognition includes advanced noise reduction technology and can handle various voice environments. 【0034】 Next, the server applies natural language processing to analyze the user's intent from the converted text. The natural language processing model is trained to understand the context of the conversation and extract relevant information. Through this process, the server identifies the user's specific requests and questions. 【0035】 Based on the identified intent, the server uses response generation means to generate appropriate response text. This response generation flow is supported by an algorithm that considers the customer interaction history and selects the best response from a past response database. 【0036】 The generated response text is converted into speech data by a speech synthesis system. The speech synthesis technology uses multiple speech patterns to enable natural-sounding speech that closely resembles human speech. Finally, the device plays this speech back to the user, and the interaction with the user continues. 【0037】 For example, if a user says, "I want to check my credit card statement," the server converts that speech into text, "I want to check my credit card statement." Once natural language processing identifies the request as "checking my statement," the server checks the relevant statement and generates a response such as, "Your most recent statement shows a charge of XX yen on September 5th," which it then communicates to the user using speech synthesis. 【0038】 This system incorporates a learning mechanism that aggregates customer feedback data and uses it to improve processing accuracy. Furthermore, it can handle inquiries in multiple languages, enabling international customer support. As described above, the system of the present invention dramatically improves service quality and customer satisfaction through an automated customer support process. 【0039】 The following describes the processing flow. 【0040】 Step 1: 【0041】 The user makes a phone call. The server receives the call and obtains the voice input. The server then prepares to process this voice data in real time. 【0042】 Step 2: 【0043】 The server uses speech recognition to convert the user's voice input into text data. This conversion process removes noise from the voice data and analyzes it according to the characteristics of the language. 【0044】 Step 3: 【0045】 The server uses natural language processing to analyze the user's intent from the converted text. Based on keywords and context within the text, it identifies the specific information and actions the user is seeking. 【0046】 Step 4: 【0047】 Based on the analyzed intent, the server generates appropriate response text using a response generation mechanism. The generated response is customized by referring to a fixed dialogue flow and past databases. 【0048】 Step 5: 【0049】 The server uses speech synthesis to convert the generated text responses into natural-sounding speech data. This synthesis process takes into account the intonation and accent specific to each language. 【0050】 Step 6: 【0051】 The terminal plays audio data sent from the server and lets the user hear the response. The user can then ask further questions or confirm necessary information based on this audio response. 【0052】 Step 7: 【0053】 After a call ends, the server collects and analyzes user feedback. This feedback data is used to train the system to improve the accuracy of natural language processing and response generation. 【0054】 (Example 1) 【0055】 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." 【0056】 Traditional customer service systems suffered from low accuracy in voice input and insufficient multilingual support. This resulted in inaccurate processing of customer feedback and decreased customer satisfaction. Furthermore, there is a need to improve the accuracy of intent analysis and response generation from voice input. 【0057】 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. 【0058】 In this invention, the server includes means for receiving voice data from a customer, voice processing means for converting the voice data into a string, and language analysis means for analyzing the customer's request from the string. This enables accurate understanding of the customer's intent and appropriate responses accordingly. 【0059】 "Audio data" refers to information that represents sound waveforms in digital format and is used for communication and data processing. 【0060】 "Speech processing means" refers to a technology or device that analyzes speech data and converts it into text. 【0061】 A "string" is a collection of data represented as text, and is used for language processing. 【0062】 "Linguistic analysis means" refers to technologies or devices for analyzing text and understanding its meaning and context. 【0063】 "Response formation means" refers to a technology or apparatus for generating an appropriate response based on analyzed information. 【0064】 "Speech formation means" refers to a technology or device that converts text data into speech data. 【0065】 A "medium" refers to a method or device for transmitting information, enabling the sending and receiving of data. 【0066】 "Evaluation data" refers to feedback information provided by customers, which is used to evaluate and improve the quality of services. 【0067】 "Learning function" refers to a function that improves the performance of technology based on accumulated data. 【0068】 "Multilingual support" means adjusting or designing technology or equipment to support multiple languages. 【0069】 This invention is a system for automating customer service, utilizing voice processing and natural language processing technologies. Specifically, a server receives and processes voice data to enable interaction with customers. The detailed procedure for carrying out the invention is described below. 【0070】 When a customer makes a phone call, the server receives the audio data. The customer's voice is captured by the server as digital audio data. The server then uses speech recognition software as an audio processing tool to convert the received audio data into text. This process may involve using, for example, a common speech recognition API. 【0071】 Next, the server uses language analysis tools to analyze the customer's intent from the converted string. Natural language processing models are used at this stage. For example, a generative AI model is used to understand the context of the conversation and identify the customer's request. 【0072】 Based on the analysis results, the server uses response formation means to generate an appropriate response. The server prepares the response by implementing an algorithm that considers past response history and selects the optimal response from the database. Once the response text is complete, the server uses speech formation means to convert it back into speech data. A general-purpose synthesis engine may be used as the speech synthesis technology. 【0073】 Finally, the device sends this audio data to the customer, and the conversation is transmitted to the user. The customer can hear the generated audio through the device's audio output function. 【0074】 For example, if a user says, "I want to check my credit card statement," the server converts that into a string and analyzes it to identify the user's intention: "to inquire about their statement." It then generates a specific response, such as, "Your most recent statement shows a transaction of XX yen on September 5th," and converts it into speech to provide to the customer. 【0075】 Examples of prompt messages include the following: 【0076】 "Please provide me with my credit card statement." 【0077】 "I'd like to check my latest usage history." 【0078】 Thus, the present invention aims to improve service quality by utilizing customer feedback data and enabling multilingual support, thereby achieving international customer service. 【0079】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0080】 Step 1: 【0081】 When a user makes a phone call, the audio is transmitted to the server via the terminal. The server takes the received audio data in digital format and prepares the speech recognition system. At this stage, a noise reduction filter is applied to ensure a clear audio signal. 【0082】 Step 2: 【0083】 The server uses speech processing to generate text strings from the received audio data. Specifically, speech recognition software analyzes the audio data and converts each audio component into corresponding text information. The input is audio data, and the output is the corresponding text data. 【0084】 Step 3: 【0085】 The server uses language analysis tools to take the converted text data as input and analyze the customer's intent. It utilizes a generative AI model to identify the user's request based on the context and keywords in the text. In this process, the input is text data, and the output is information indicating the user's intent. 【0086】 Step 4: 【0087】 The server generates an appropriate response using response formation mechanisms based on the identified user intent. It executes an algorithm to select the optimal answer by referring to past queries and existing knowledge bases. The input is user intent information, and the output is the response text. 【0088】 Step 5: 【0089】 The server converts the response text into speech data using speech synthesis technology. At this stage, human-like speech is achieved using speech synthesis technology. The input is the response text, and the output is synthesized speech data. 【0090】 Step 6: 【0091】 The device plays synthesized voice data to the user. The user receives voice responses through the speaker and makes additional inquiries as needed. The output is the voice the user hears, which allows the conversation to continue. 【0092】 (Application Example 1) 【0093】 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." 【0094】 Conventional customer support systems do not efficiently process voice-based inquiries about transaction information, making it difficult to improve user satisfaction. Furthermore, generating multilingual responses is not easy, posing a barrier to international use. To address these issues, there is a need for a system that efficiently acquires transaction information from voice input and generates natural-sounding multilingual voice responses. 【0095】 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. 【0096】 In this invention, the server includes a component for receiving voice input, a voice recognition component for converting the voice input into text data, and a natural language processing component for analyzing the user's intent from the text data. This enables efficient retrieval of the user's transaction information and natural-sounding voice responses. 【0097】 "Voice input" refers to information transmitted by the user via voice, and the voice signal received by the system. 【0098】 "Character data" refers to a string of characters generated based on voice input, and is the format used by the system for analysis. 【0099】 "Speech recognition components" refer to technical means for converting speech input into text data. 【0100】 "Natural language processing components" are information processing technologies used to analyze user intent from text data. 【0101】 "Response generation components" refer to technologies within a system that generate appropriate response character data based on the analyzed intent. 【0102】 "Speech synthesis components" refer to technologies for converting response text data into speech data. 【0103】 "Transaction information components" refer to the internal technical means of a system for querying and providing users' transaction information. 【0104】 "Learning components" are components used to improve the accuracy of natural language processing using feedback data. 【0105】 "Adjustment components" are components that enable speech recognition and speech synthesis to support multiple languages. 【0106】 A description of the embodiment for carrying out the invention will be provided. 【0107】 This system receives voice input from the user via the microphone of their smartphone or computer. The server uses the Google® Cloud Speech-to-Text API to convert the voice input into text data. The converted text data is then processed using natural language processing with the Hugging Face Transformers library to analyze the user's intent. This analysis identifies the transaction and payment information the user is requesting. 【0108】 Next, the server retrieves relevant transaction information from the database based on the analyzed information. The response generation component generates appropriate response text data based on this information. The generated text data is converted into audio data using Microsoft® Azure® Cognitive Services. Finally, this audio data is played through the speaker of the user's smartphone or device, providing the information to the user. 【0109】 For example, if a user asks, "What is my credit card payment amount for this month?", the server can convert the speech into text data, retrieve payment information from the database, generate a response such as, "Your credit card payment amount for this month is 15,000 yen," and then respond to the user in voice. 【0110】 An example of a prompt for a generative AI model might be, "Please describe the design of a system that can naturally respond with payment information based on the user's voice input." 【0111】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0112】 Step 1: 【0113】 The user provides voice input through their smartphone's microphone. The input voice data is then transmitted to a server via the network. 【0114】 Step 2: 【0115】 The server uses the Google Cloud Speech-to-Text API to convert the received audio data into text data. In this step, speech recognition is performed to convert the audio signal into text, and the output is as text data. 【0116】 Step 3: 【0117】 The server processes the text data it receives using the Hugging Face Transformers library for natural language processing. This process analyzes the user's intent from the text data. The input is text data, and after analysis, information is output to identify the user's questions and requests. 【0118】 Step 4: 【0119】 The server verifies relevant transaction information based on the analyzed user intent. In this step, it accesses the database and searches for the corresponding transaction and payment data. The input is the identified request information, and the output is the transaction data to be provided to the user. 【0120】 Step 5: 【0121】 The server generates appropriate response text data based on the acquired transaction information. Response generation components work, utilizing past response generation algorithms to produce natural-sounding text. The input is transaction data, and the output is the response text to be returned to the user. 【0122】 Step 6: 【0123】 The server converts the response text into speech data via Microsoft Azure Cognitive Services. This speech synthesis process converts text data into speech, generating natural-sounding human-like voices. The input is the response text, and the output is speech-readable audio data. 【0124】 Step 7: 【0125】 The terminal plays audio data received from the server to the user through its speaker. This allows the user to receive responses to their questions via audio. The input is audio data, and the output is audio playback from the terminal. 【0126】 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. 【0127】 The system of this invention incorporates an emotion engine to further enhance automated responses through customer calls. This allows the server to recognize the user's emotional state and adjust the response process based on that information. 【0128】 When a user makes a call, the server receives the voice input. This voice input is converted into text data by a speech recognition system. At this point, the server activates an emotion engine to analyze the user's emotions from the converted voice data. The emotion engine analyzes the tone, speed, and pauses of the voice to identify emotions such as anger, confusion, or satisfaction. 【0129】 Next, the server uses natural language processing to analyze the user's intent from the text data and considers the response content in combination with the results of emotion recognition. For example, if a user is frustrated and complains that "the bill is wrong," the server takes that emotional state into account and generates a response that is kind and empathetic. 【0130】 The generated response text is converted into speech data using speech synthesis technology, and the terminal plays the response to the customer in a natural voice. This response is appropriately adjusted according to the user's emotions, with the aim of making communication with the customer smoother. 【0131】 For example, if a user expresses frustration by saying, "I'm getting really annoyed because I can't connect at all," the server's emotion engine recognizes that the user is annoyed. Based on this information and the result of intent analysis ("cannot connect"), the server generates a response such as, "We apologize for the delay. We will do our best to resolve this issue as quickly as possible," and delivers it via speech synthesis. 【0132】 Furthermore, the server has a learning function that accumulates user feedback data and improves the accuracy of emotion recognition and response generation. In this way, the system improves with repeated use, enabling it to provide higher customer satisfaction. 【0133】 This invention enables a more personalized and effective customer service experience by responding not only to the user's words but also to the emotions hidden beneath them. 【0134】 The following describes the processing flow. 【0135】 Step 1: 【0136】 The user makes a phone call, and the server receives the voice input. At this point, the server begins collecting voice data as soon as the call starts. 【0137】 Step 2: 【0138】 The server utilizes speech recognition technology to convert received speech input into text data. The process involves removing noise using speech recognition technology and accurately converting utterances into text. 【0139】 Step 3: 【0140】 The server passes the converted text data to the emotion engine. The emotion engine analyzes the characteristics of this text and voice (tone, speed, etc.) to recognize the user's emotional state (e.g., anger, sadness, joy). 【0141】 Step 4: 【0142】 The server uses natural language processing to analyze the user's intent from the text data. This analysis clarifies the intent behind the user's requests and questions, and combines this with the sentiment analysis results from earlier to prepare for the next step. 【0143】 Step 5: 【0144】 The server generates appropriate response text based on the analyzed intent and recognized emotions using a response generation mechanism. This generation process incorporates empathetic language that takes the user's emotions into consideration, as well as specific suggestions for problem solving, into the response. 【0145】 Step 6: 【0146】 The server converts the generated response text into speech data using a speech synthesis system. Speech synthesis requires natural and easy-to-understand pronunciation, and, if necessary, sets a tone that reflects emotion. 【0147】 Step 7: 【0148】 The terminal plays audio data from the server and communicates the response to the user. The user can listen to this audio response and respond, and the conversation continues from there. 【0149】 Step 8: 【0150】 The server collects user feedback after a call, analyzes the data to improve the accuracy of speech recognition, emotion recognition, and natural language processing, and works to continuously improve the system. 【0151】 (Example 2) 【0152】 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 will be referred to as the "terminal." 【0153】 Conventional automated response systems often provide uniform and mechanical responses to user voice input, potentially resulting in inappropriate responses that disregard the customer's emotional state. This can lead to decreased customer satisfaction and negatively impact service quality. Furthermore, if the system does not support multiple languages, language barriers can hinder appropriate customer service, posing another challenge. 【0154】 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. 【0155】 In this invention, the server includes a mechanism for receiving voice input from a customer, a voice recognition mechanism for converting the voice input into text data, an emotion recognition mechanism for analyzing the customer's emotional state from the text data, a natural language processing mechanism for analyzing the customer's intentions based on the emotional state and text data, a response generation mechanism for generating appropriate response text based on the analyzed intentions and emotions, a voice synthesis mechanism for converting the response text into voice data, and a device for transmitting the voice data to the customer. This enables personalized responses tailored to the user's emotional state, thereby improving customer satisfaction. Furthermore, a system that includes multilingual support enables appropriate customer service that transcends language barriers. 【0156】 "Voice input" refers to voice information spoken by customers, and the system processes this information based on that input. 【0157】 A "speech recognition system" is a technology that converts speech input into text data, and its role is to analyze the user's speech and convert it into a digital format. 【0158】 An "emotion recognition mechanism" is a technology that analyzes a customer's emotional state from voice data, identifying emotions based on voice tone, speaking speed, and pauses between sounds. 【0159】 A "natural language processing mechanism" is a technology that analyzes user intent from text data, and is designed to understand natural language and determine appropriate responses. 【0160】 A "response generation mechanism" is a technology that generates appropriate response text based on analyzed intentions and emotions. 【0161】 A "speech synthesis mechanism" is a technology that converts response text into speech data, and its role is to convey the generated response content to the customer as speech. 【0162】 "Device" refers to a part of a system that includes hardware and software for transmitting voice data to customers. 【0163】 A "learning mechanism" is a technology in which a system continuously learns by accumulating feedback data from customers in order to improve the accuracy of its analysis. 【0164】 The "adjustment mechanism" is a technology that configures the system to support multiple languages ​​for speech recognition and speech synthesis mechanisms, thereby achieving multilingual support. 【0165】 The system of this invention is built to further enhance automated responses through customer calls. By integrating speech recognition, emotion recognition, natural language processing, response generation, and speech synthesis technologies, this system provides customers with flexible and personalized responses. 【0166】 The server has the capability to receive voice input when a user makes a phone call. The received voice is converted into text data using speech recognition software (for example, an API known as a general speech recognition engine). At this point, the content of the voice becomes available for processing in digital format. 【0167】 Next, the server inputs the text data into an emotion recognition engine to identify the customer's emotional state. This emotion recognition is based on factors such as tone of voice, speed, and word spacing. For example, if a user's voice is high-pitched and they are speaking quickly, the server can determine that the person is angry. 【0168】 Furthermore, the server uses a natural language processing engine to analyze the user's intent from their text. This process utilizes generative AI models to accurately understand what the user is asking for. 【0169】 During the response generation phase, the server generates an appropriate response based on the results of emotion recognition and intent analysis. This response is designed to be empathetic and considerate of the user's emotions. 【0170】 The generated response is converted back into speech data using speech synthesis software. The terminal then plays the response back to the user in a natural voice through this speech data. In this way, communication becomes smoother, and interactions can be conducted without causing excessive stress. 【0171】 For example, if a user expresses dissatisfaction such as "I can't connect at all," the server's emotion recognition engine will detect the user's dissatisfaction. Based on the analysis, the server will generate a response such as "We apologize for the delay. We are working to resolve the issue, so please wait a little longer," and deliver it via speech synthesis. 【0172】 An example of a prompt might be, "Analyze the user's utterance, recognize their emotions, and then generate an appropriate response." Based on this prompt, the AI ​​model can devise responses that enable sophisticated customer service. 【0173】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0174】 Step 1: 【0175】 When a user makes a phone call, the server receives the voice input. The voice data arrives at the server as input. This voice data is sent to speech recognition software, which converts it into digital text. This conversion outputs the voice content as text data for natural language processing. 【0176】 Step 2: 【0177】 The server passes the speech-recognized text data to the emotion recognition engine. From this input text data, the server analyzes the tone and tempo of the voice, as well as emphasized words in the text. Based on this data, the emotion recognition engine identifies the user's emotional state and outputs it as a basic emotion such as "anger," "satisfaction," or "confusion." 【0178】 Step 3: 【0179】 The server combines the emotion recognition results with text data and inputs it into a natural language processing engine. In this step, the server uses a generative AI model to analyze the text data in detail and understand the user's intent. As a result of this analysis, semantic data identifying the user's requests and inquiries is output. 【0180】 Step 4: 【0181】 The server combines the intent analysis results and emotion recognition results and passes them to the response generation engine. The response generation engine uses a generation AI model to create appropriate response text that takes the user's emotions into account. As a result, response text that includes empathy and problem-solving is output. 【0182】 Step 5: 【0183】 The server inputs the generated response text into speech synthesis software. The speech synthesis software converts this text into speech data and outputs more natural-sounding speech data. 【0184】 Step 6: 【0185】 The terminal receives audio data output from the server and speaks it to the user. At this stage, the volume and tone of voice are adjusted according to the user's emotions, and an appropriate response is provided to the user. 【0186】 (Application Example 2) 【0187】 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". 【0188】 In modern society, understanding user emotions and providing appropriate information and services accordingly is crucial for enhancing the personalized experience. However, conventional automated response systems have struggled to generate responses that take emotions into account and to provide security information in real time. Further improving user satisfaction remains a challenge. 【0189】 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. 【0190】 In this invention, the server includes means for receiving voice input, means for converting the voice input into text data, and means for analyzing the user's intent from the text data. This makes it possible to understand the user's emotions and provide security information based on them. 【0191】 "Means for receiving voice input" refers to a device or technology that collects voice data provided by a user and prepares it for processing. 【0192】 "Conversion means" refers to a technology or device that converts audio data into text data, and then converts the response text back into audio data. 【0193】 "Analysis means" refers to a technology or device that determines the user's intentions and emotions from text data and extracts information for generating appropriate responses. 【0194】 "Generation means" refers to a technology or device that generates response text to be provided to the user based on analyzed intentions and emotions. 【0195】 "Outputting means" refers to a device or technology for directly transmitting the generated audio data to the user. 【0196】 "Proposal means" refers to technology or devices for providing necessary information and advice based on the user's emotions and intentions. 【0197】 A description of the embodiment for carrying out the invention will be given. 【0198】 This system aims to recognize emotions through interaction with the user and provide appropriate communication accordingly. The system primarily operates by combining speech recognition, emotion analysis, natural language processing, and speech synthesis functions. Details are described below. 【0199】 The server first obtains the voice input provided by the user through a means of receiving voice input. Next, it converts that voice data into text data using a conversion means. This conversion process includes the Google Voice API, which is widely used as speech recognition software. 【0200】 Next, an analysis tool works to analyze the user's emotions and intentions from the converted text data. Here, an emotion analysis engine like EmoVoice and natural language processing libraries such as spaCy and NLTK are used to analyze the tone and speed of the voice and infer the user's emotional state. 【0201】 Based on the analysis results, the generation mechanism generates response text appropriate to the user. In this part, an AI model generates responses that correspond to specific emotions and intentions. Furthermore, Amazon Polly is used as a speech synthesis tool to convert the generated text into natural-sounding speech data. 【0202】 Subsequently, the audio data is transmitted to the user via an output method. The interaction is completed when the data is sent to the user through the speaker. 【0203】 For example, if a child says via smartphone, "I'm worried because my family hasn't come home," the system will provide an emotionally sensitive response such as, "It's okay. We'll let you know when your family arrives." 【0204】 Examples of prompts include, "Recognize that the user is feeling anxious and consider a reassuring response," and "Read the emotion from this audio data and generate a script that instantly suggests a course of action." In this way, the present invention enables personalized and effective support for users. 【0205】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0206】 Step 1: 【0207】 The user provides voice input. This voice input is captured by the device's microphone. The input is audio data, and the output is the same. 【0208】 Step 2: 【0209】 The server converts voice input into text data using speech recognition software, which acts as the conversion mechanism. The input is voice data, and the Google Voice API is used to convert the voice waveform into text data. The output is the converted text data. 【0210】 Step 3: 【0211】 The server analyzes the converted text data using an emotion analysis engine. The input is text data, and EmoVoice is used to analyze voice tone, speed, etc., to infer the user's emotional state. The output is emotion evaluation data. 【0212】 Step 4: 【0213】 The server uses natural language processing libraries to analyze user intent. The input is text data, and the server understands intent by performing syntactic analysis using tools like spaCy and NLTK. The output is data indicating the intent. 【0214】 Step 5: 【0215】 The server uses a generative AI model to generate appropriate response text based on sentiment and intent data. The input is sentiment and intent data, and the response generation process constructs an appropriate sentence. The output is the generated response text. 【0216】 Step 6: 【0217】 The server converts the response text into speech data using a speech synthesis tool. The input is the response text, and Amazon Polly is used to generate natural-sounding speech. The output is the synthesized speech data. 【0218】 Step 7: 【0219】 The device transmits synthesized audio data to the user through its speaker. The input is audio data, and the task is completed when this data finally reaches the user's ears. 【0220】 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. 【0221】 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. 【0222】 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. 【0223】 [Second Embodiment] 【0224】 Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment. 【0225】 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. 【0226】 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). 【0227】 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. 【0228】 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. 【0229】 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). 【0230】 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. 【0231】 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. 【0232】 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. 【0233】 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. 【0234】 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. 【0235】 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". 【0236】 The system of this invention automatically processes voice data using AI technology to handle customer inquiries via telephone. First, when a user makes a call, the server receives the voice input. The server uses speech recognition means to convert the user's voice into text data. This speech recognition includes advanced noise reduction technology and can handle various voice environments. 【0237】 Next, the server applies natural language processing to analyze the user's intent from the converted text. The natural language processing model is trained to understand the context of the conversation and extract relevant information. Through this process, the server identifies the user's specific requests and questions. 【0238】 Based on the identified intent, the server uses response generation means to generate appropriate response text. This response generation flow is supported by an algorithm that considers the customer interaction history and selects the best response from a past response database. 【0239】 The generated response text is converted into speech data by a speech synthesis system. The speech synthesis technology uses multiple speech patterns to enable natural-sounding speech that closely resembles human speech. Finally, the device plays this speech back to the user, and the interaction with the user continues. 【0240】 For example, if a user says, "I want to check my credit card statement," the server converts that speech into text, "I want to check my credit card statement." Once natural language processing identifies the request as "checking my statement," the server checks the relevant statement and generates a response such as, "Your most recent statement shows a charge of XX yen on September 5th," which it then communicates to the user using speech synthesis. 【0241】 This system incorporates a learning mechanism that aggregates customer feedback data and uses it to improve processing accuracy. Furthermore, it can handle inquiries in multiple languages, enabling international customer support. As described above, the system of the present invention dramatically improves service quality and customer satisfaction through an automated customer support process. 【0242】 The following describes the processing flow. 【0243】 Step 1: 【0244】 The user makes a phone call. The server receives the call and obtains the voice input. The server then prepares to process this voice data in real time. 【0245】 Step 2: 【0246】 The server uses speech recognition to convert the user's voice input into text data. This conversion process removes noise from the voice data and analyzes it according to the characteristics of the language. 【0247】 Step 3: 【0248】 The server uses natural language processing to analyze the user's intent from the converted text. Based on keywords and context within the text, it identifies the specific information and actions the user is seeking. 【0249】 Step 4: 【0250】 Based on the analyzed intent, the server generates appropriate response text using a response generation mechanism. The generated response is customized by referring to a fixed dialogue flow and past databases. 【0251】 Step 5: 【0252】 The server uses speech synthesis to convert the generated text responses into natural-sounding speech data. This synthesis process takes into account the intonation and accent specific to each language. 【0253】 Step 6: 【0254】 The terminal plays audio data sent from the server and lets the user hear the response. The user can then ask further questions or confirm necessary information based on this audio response. 【0255】 Step 7: 【0256】 After a call ends, the server collects and analyzes user feedback. This feedback data is used to train the system to improve the accuracy of natural language processing and response generation. 【0257】 (Example 1) 【0258】 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." 【0259】 Traditional customer service systems suffered from low accuracy in voice input and insufficient multilingual support. This resulted in inaccurate processing of customer feedback and decreased customer satisfaction. Furthermore, there is a need to improve the accuracy of intent analysis and response generation from voice input. 【0260】 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. 【0261】 In this invention, the server includes means for receiving voice data from a customer, voice processing means for converting the voice data into a string, and language analysis means for analyzing the customer's request from the string. This enables accurate understanding of the customer's intent and appropriate responses accordingly. 【0262】 "Audio data" refers to information that represents sound waveforms in digital format and is used for communication and data processing. 【0263】 "Speech processing means" refers to a technology or device that analyzes speech data and converts it into text. 【0264】 A "string" is a collection of data represented as text, and is used for language processing. 【0265】 "Linguistic analysis means" refers to technologies or devices for analyzing text and understanding its meaning and context. 【0266】 "Response formation means" refers to a technology or apparatus for generating an appropriate response based on analyzed information. 【0267】 "Speech formation means" refers to a technology or device that converts text data into speech data. 【0268】 A "medium" refers to a method or device for transmitting information, enabling the sending and receiving of data. 【0269】 "Evaluation data" refers to feedback information provided by customers, which is used to evaluate and improve the quality of services. 【0270】 "Learning function" refers to a function that improves the performance of technology based on accumulated data. 【0271】 "Multilingual support" means adjusting or designing technology or equipment to support multiple languages. 【0272】 This invention is a system for automating customer service, utilizing voice processing and natural language processing technologies. Specifically, a server receives and processes voice data to enable interaction with customers. The detailed procedure for carrying out the invention is described below. 【0273】 When a customer makes a phone call, the server receives the audio data. The customer's voice is captured by the server as digital audio data. The server then uses speech recognition software as an audio processing tool to convert the received audio data into text. This process may involve using, for example, a common speech recognition API. 【0274】 Next, the server uses language analysis tools to analyze the customer's intent from the converted string. Natural language processing models are used at this stage. For example, a generative AI model is used to understand the context of the conversation and identify the customer's request. 【0275】 Based on the analysis results, the server uses response formation means to generate an appropriate response. The server prepares the response by implementing an algorithm that considers past response history and selects the optimal response from the database. Once the response text is complete, the server uses speech formation means to convert it back into speech data. A general-purpose synthesis engine may be used as the speech synthesis technology. 【0276】 Finally, the device sends this audio data to the customer, and the conversation is transmitted to the user. The customer can hear the generated audio through the device's audio output function. 【0277】 For example, if a user says, "I want to check my credit card statement," the server converts that into a string and analyzes it to identify the user's intention: "to inquire about their statement." It then generates a specific response, such as, "Your most recent statement shows a transaction of XX yen on September 5th," and converts it into speech to provide to the customer. 【0278】 Examples of prompt messages include the following: 【0279】 "Please provide me with my credit card statement." 【0280】 "I'd like to check my latest usage history." 【0281】 Thus, the present invention aims to improve service quality by utilizing customer feedback data and enabling multilingual support, thereby achieving international customer service. 【0282】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0283】 Step 1: 【0284】 When the user makes a call, the voice is input into the server through the terminal. The server captures the received voice data in digital format and prepares the voice recognition means. At this stage, a noise removal filter is applied to ensure a clear voice signal. 【0285】 Step 2: 【0286】 The server uses voice processing means to generate a character string from the received voice data. Specifically, voice recognition software analyzes the voice data and converts each voice component into corresponding character information. The input is voice data and the output is the corresponding text data. 【0287】 Step 3: 【0288】 The server uses language analysis means to analyze the converted text data as input to analyze the customer's intention. Utilizing the generated AI model, the server identifies the user's request based on the context and keywords in the text. In this process, the input is text data and the output is information indicating the user's intention. 【0289】 Step 4: 【0290】 Based on the identified user intention, the server uses response formation means to generate an appropriate response. It executes an algorithm that refers to past inquiries and the existing knowledge base to select the optimal answer. The input is the user's intention information and the output is the response text. 【0291】 Step 5: 【0292】 The server converts the response text into voice data by voice formation means. At this stage, voice synthesis technology is used to achieve a human-like voice. The input is the response text and the output is the synthesized voice data. 【0293】 Step 6: 【0294】 The device plays synthesized voice data to the user. The user receives voice responses through the speaker and makes additional inquiries as needed. The output is the voice the user hears, which allows the conversation to continue. 【0295】 (Application Example 1) 【0296】 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." 【0297】 Conventional customer support systems do not efficiently process voice-based inquiries about transaction information, making it difficult to improve user satisfaction. Furthermore, generating multilingual responses is not easy, posing a barrier to international use. To address these issues, there is a need for a system that efficiently acquires transaction information from voice input and generates natural-sounding multilingual voice responses. 【0298】 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. 【0299】 In this invention, the server includes a component for receiving voice input, a voice recognition component for converting the voice input into text data, and a natural language processing component for analyzing the user's intent from the text data. This enables efficient retrieval of the user's transaction information and natural-sounding voice responses. 【0300】 "Voice input" refers to information transmitted by the user via voice, and the voice signal received by the system. 【0301】 "Character data" refers to a string of characters generated based on voice input, in a format used by the system for analysis. 【0302】 "Speech recognition components" refer to technical means for converting speech input into text data. 【0303】 The "Natural Language Processing Component" is an information processing technology for analyzing the user's intention from character data. 【0304】 The "Response Generation Component" is a technology within the system that generates appropriate response character data based on the analyzed intention. 【0305】 The "Text-to-Speech Component" is a technology for converting response character data into voice data. 【0306】 The "Transaction Information Component" is a technical means within the system for querying and providing the user's transaction information. 【0307】 The "Learning Component" is a component for improving the accuracy of natural language processing using feedback data. 【0308】 The "Adjustment Component" is a component for making speech recognition and text-to-speech support multiple languages. 【0309】 The mode for implementing the invention will be described. 【0310】 In this system, the voice input uttered by the user is received through the microphone of a smartphone or computer. The server uses the Google Cloud Speech-to-Text API to convert the voice input into character data. The converted character data performs natural language processing using the Transformers library of Hugging Face to analyze the user's intention. Through this analysis, the transaction information and payment information required by the user are identified. 【0311】 Next, the server retrieves relevant transaction information from the database based on the analyzed information. The response generation component generates appropriate response text data based on this information. The generated text data is converted into audio data using Microsoft Azure Cognitive Services. Finally, this audio data is played through the speaker of the user's smartphone or device, providing the information to the user. 【0312】 For example, if a user asks, "What is my credit card payment amount for this month?", the server can convert the speech into text data, retrieve payment information from the database, generate a response such as, "Your credit card payment amount for this month is 15,000 yen," and then respond to the user in voice. 【0313】 An example of a prompt for a generative AI model might be, "Please describe the design of a system that can naturally respond with payment information based on the user's voice input." 【0314】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0315】 Step 1: 【0316】 The user provides voice input through their smartphone's microphone. The input voice data is then transmitted to a server via the network. 【0317】 Step 2: 【0318】 The server uses the Google Cloud Speech-to-Text API to convert the received audio data into text data. In this step, speech recognition is performed to convert the audio signal into text, and the output is as text data. 【0319】 Step 3: 【0320】 The server processes the text data it receives using the Hugging Face Transformers library for natural language processing. This process analyzes the user's intent from the text data. The input is text data, and after analysis, information is output to identify the user's questions and requests. 【0321】 Step 4: 【0322】 The server verifies relevant transaction information based on the analyzed user intent. In this step, it accesses the database and searches for the corresponding transaction and payment data. The input is the identified request information, and the output is the transaction data to be provided to the user. 【0323】 Step 5: 【0324】 The server generates appropriate response text data based on the acquired transaction information. Response generation components work, utilizing past response generation algorithms to produce natural-sounding text. The input is transaction data, and the output is the response text to be returned to the user. 【0325】 Step 6: 【0326】 The server converts the response text into speech data via Microsoft Azure Cognitive Services. This speech synthesis process converts text data into speech, generating natural-sounding human-like voices. The input is the response text, and the output is speech-readable audio data. 【0327】 Step 7: 【0328】 The terminal plays audio data received from the server to the user through its speaker. This allows the user to receive responses to their questions via audio. The input is audio data, and the output is audio playback from the terminal. 【0329】 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. 【0330】 The system of this invention incorporates an emotion engine to further enhance automated responses through customer calls. This allows the server to recognize the user's emotional state and adjust the response process based on that information. 【0331】 When a user makes a call, the server receives the voice input. This voice input is converted into text data by a speech recognition system. At this point, the server activates an emotion engine to analyze the user's emotions from the converted voice data. The emotion engine analyzes the tone, speed, and pauses of the voice to identify emotions such as anger, confusion, or satisfaction. 【0332】 Next, the server uses natural language processing to analyze the user's intent from the text data and considers the response content in combination with the results of emotion recognition. For example, if a user is frustrated and complains that "the bill is wrong," the server takes that emotional state into account and generates a response that is kind and empathetic. 【0333】 The generated response text is converted into speech data using speech synthesis technology, and the terminal plays the response to the customer in a natural voice. This response is appropriately adjusted according to the user's emotions, with the aim of making communication with the customer smoother. 【0334】 For example, if a user expresses frustration by saying, "I'm getting really annoyed because I can't connect at all," the server's emotion engine recognizes that the user is annoyed. Based on this information and the result of intent analysis ("cannot connect"), the server generates a response such as, "We apologize for the delay. We will do our best to resolve this issue as quickly as possible," and delivers it via speech synthesis. 【0335】 Furthermore, the server has a learning function that accumulates user feedback data and improves the accuracy of emotion recognition and response generation. In this way, the system improves with repeated use, enabling it to provide higher customer satisfaction. 【0336】 This invention enables a more personalized and effective customer service experience by responding not only to the user's words but also to the emotions hidden beneath them. 【0337】 The following describes the processing flow. 【0338】 Step 1: 【0339】 The user makes a phone call, and the server receives the voice input. At this point, the server begins collecting voice data as soon as the call starts. 【0340】 Step 2: 【0341】 The server utilizes speech recognition technology to convert received speech input into text data. The process involves removing noise using speech recognition technology and accurately converting utterances into text. 【0342】 Step 3: 【0343】 The server passes the converted text data to the emotion engine. The emotion engine analyzes the characteristics of this text and voice (tone, speed, etc.) to recognize the user's emotional state (e.g., anger, sadness, joy). 【0344】 Step 4: 【0345】 The server uses natural language processing to analyze the user's intent from the text data. This analysis clarifies the intent behind the user's requests and questions, and combines this with the sentiment analysis results from earlier to prepare for the next step. 【0346】 Step 5: 【0347】 The server generates appropriate response text based on the analyzed intent and recognized emotions using a response generation mechanism. This generation process incorporates empathetic language that takes the user's emotions into consideration, as well as specific suggestions for problem solving, into the response. 【0348】 Step 6: 【0349】 The server converts the generated response text into speech data using a speech synthesis system. Speech synthesis requires natural and easy-to-understand pronunciation, and, if necessary, sets a tone that reflects emotion. 【0350】 Step 7: 【0351】 The terminal plays audio data from the server and communicates the response to the user. The user can listen to this audio response and respond, and the conversation continues from there. 【0352】 Step 8: 【0353】 The server collects user feedback after a call, analyzes the data to improve the accuracy of speech recognition, emotion recognition, and natural language processing, and works to continuously improve the system. 【0354】 (Example 2) 【0355】 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". 【0356】 Conventional automated response systems often provide uniform and mechanical responses to user voice input, potentially resulting in inappropriate responses that disregard the customer's emotional state. This can lead to decreased customer satisfaction and negatively impact service quality. Furthermore, if the system does not support multiple languages, language barriers can hinder appropriate customer service, posing another challenge. 【0357】 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. 【0358】 In this invention, the server includes a mechanism for receiving voice input from a customer, a voice recognition mechanism for converting the voice input into text data, an emotion recognition mechanism for analyzing the customer's emotional state from the text data, a natural language processing mechanism for analyzing the customer's intentions based on the emotional state and text data, a response generation mechanism for generating appropriate response text based on the analyzed intentions and emotions, a voice synthesis mechanism for converting the response text into voice data, and a device for transmitting the voice data to the customer. This enables personalized responses tailored to the user's emotional state, thereby improving customer satisfaction. Furthermore, a system that includes multilingual support enables appropriate customer service that transcends language barriers. 【0359】 "Voice input" refers to voice information spoken by customers, and the system processes this information based on that input. 【0360】 A "speech recognition system" is a technology that converts speech input into text data, and its role is to analyze the user's speech and convert it into a digital format. 【0361】 An "emotion recognition mechanism" is a technology that analyzes a customer's emotional state from voice data, identifying emotions based on voice tone, speaking speed, and pauses between sounds. 【0362】 A "natural language processing mechanism" is a technology that analyzes user intent from text data, and is designed to understand natural language and determine appropriate responses. 【0363】 A "response generation mechanism" is a technology that generates appropriate response text based on analyzed intentions and emotions. 【0364】 A "speech synthesis mechanism" is a technology that converts response text into speech data, and its role is to convey the generated response content to the customer as speech. 【0365】 "Device" refers to a part of a system that includes hardware and software for transmitting voice data to customers. 【0366】 A "learning mechanism" is a technology in which a system continuously learns by accumulating feedback data from customers in order to improve the accuracy of its analysis. 【0367】 The "adjustment mechanism" is a technology that configures the system to support multiple languages ​​for speech recognition and speech synthesis mechanisms, thereby achieving multilingual support. 【0368】 The system of this invention is built to further enhance automated responses through customer calls. By integrating speech recognition, emotion recognition, natural language processing, response generation, and speech synthesis technologies, this system provides customers with flexible and personalized responses. 【0369】 The server has the capability to receive voice input when a user makes a phone call. The received voice is converted into text data using speech recognition software (for example, an API known as a general speech recognition engine). At this point, the content of the voice becomes available for processing in digital format. 【0370】 Next, the server inputs the text data into an emotion recognition engine to identify the customer's emotional state. This emotion recognition is based on factors such as tone of voice, speed, and word spacing. For example, if a user's voice is high-pitched and they are speaking quickly, the server can determine that the person is angry. 【0371】 Furthermore, the server uses a natural language processing engine to analyze the user's intent from their text. This process utilizes generative AI models to accurately understand what the user is asking for. 【0372】 During the response generation phase, the server generates an appropriate response based on the results of emotion recognition and intent analysis. This response is designed to be empathetic and considerate of the user's emotions. 【0373】 The generated response is converted back into speech data using speech synthesis software. The terminal then plays the response back to the user in a natural voice through this speech data. In this way, communication becomes smoother, and interactions can be conducted without causing excessive stress. 【0374】 For example, if a user expresses dissatisfaction such as "I can't connect at all," the server's emotion recognition engine will detect the user's dissatisfaction. Based on the analysis, the server will generate a response such as "We apologize for the delay. We are working to resolve the issue, so please wait a little longer," and deliver it via speech synthesis. 【0375】 An example of a prompt might be, "Analyze the user's utterance, recognize their emotions, and then generate an appropriate response." Based on this prompt, the AI ​​model can devise responses that enable sophisticated customer service. 【0376】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0377】 Step 1: 【0378】 When a user makes a phone call, the server receives the voice input. The voice data arrives at the server as input. This voice data is sent to speech recognition software, which converts it into digital text. This conversion outputs the voice content as text data for natural language processing. 【0379】 Step 2: 【0380】 The server passes the speech-recognized text data to the emotion recognition engine. From this input text data, the server analyzes the tone and tempo of the voice, as well as emphasized words in the text. Based on this data, the emotion recognition engine identifies the user's emotional state and outputs it as a basic emotion such as "anger," "satisfaction," or "confusion." 【0381】 Step 3: 【0382】 The server combines the emotion recognition results with text data and inputs it into a natural language processing engine. In this step, the server uses a generative AI model to analyze the text data in detail and understand the user's intent. As a result of this analysis, semantic data identifying the user's requests and inquiries is output. 【0383】 Step 4: 【0384】 The server combines the intent analysis results and emotion recognition results and passes them to the response generation engine. The response generation engine uses a generation AI model to create appropriate response text that takes the user's emotions into account. As a result, response text that includes empathy and problem-solving is output. 【0385】 Step 5: 【0386】 The server inputs the generated response text into speech synthesis software. The speech synthesis software converts this text into speech data and outputs more natural-sounding speech data. 【0387】 Step 6: 【0388】 The terminal receives audio data output from the server and speaks it to the user. At this stage, the volume and tone of voice are adjusted according to the user's emotions, and an appropriate response is provided to the user. 【0389】 (Application Example 2) 【0390】 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." 【0391】 In modern society, understanding user emotions and providing appropriate information and services accordingly is crucial for enhancing the personalized experience. However, conventional automated response systems have struggled to generate responses that take emotions into account and to provide security information in real time. Further improving user satisfaction remains a challenge. 【0392】 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. 【0393】 In this invention, the server includes means for receiving voice input, means for converting the voice input into text data, and means for analyzing the user's intent from the text data. This makes it possible to understand the user's emotions and provide security information based on them. 【0394】 "Means for receiving voice input" refers to a device or technology that collects voice data provided by a user and prepares it for processing. 【0395】 "Conversion means" refers to a technology or device that converts audio data into text data, and then converts the response text back into audio data. 【0396】 "Analysis means" refers to a technology or device that determines the user's intentions and emotions from text data and extracts information for generating appropriate responses. 【0397】 "Generation means" refers to a technology or device that generates response text to be provided to the user based on analyzed intentions and emotions. 【0398】 "Outputting means" refers to a device or technology for directly transmitting the generated audio data to the user. 【0399】 "Proposal means" refers to technology or devices for providing necessary information and advice based on the user's emotions and intentions. 【0400】 A description of the embodiment for carrying out the invention will be given. 【0401】 This system aims to recognize emotions through interaction with the user and provide appropriate communication accordingly. The system primarily operates by combining speech recognition, emotion analysis, natural language processing, and speech synthesis functions. Details are described below. 【0402】 The server first obtains the voice input provided by the user through a means of receiving voice input. Next, it converts that voice data into text data using a conversion means. This conversion process includes the Google Voice API, which is widely used as speech recognition software. 【0403】 Next, an analysis tool works to analyze the user's emotions and intentions from the converted text data. Here, an emotion analysis engine like EmoVoice and natural language processing libraries such as spaCy and NLTK are used to analyze the tone and speed of the voice and infer the user's emotional state. 【0404】 Based on the analysis results, the generation mechanism generates response text appropriate to the user. In this part, an AI model generates responses that correspond to specific emotions and intentions. Furthermore, Amazon Polly is used as a speech synthesis tool to convert the generated text into natural-sounding speech data. 【0405】 Subsequently, the audio data is transmitted to the user via an output method. The interaction is completed when the data is sent to the user through the speaker. 【0406】 For example, if a child says via smartphone, "I'm worried because my family hasn't come home," the system will provide an emotionally sensitive response such as, "It's okay. We'll let you know when your family arrives." 【0407】 Examples of prompts include, "Recognize that the user is feeling anxious and consider a reassuring response," and "Read the emotion from this audio data and generate a script that instantly suggests a course of action." In this way, the present invention enables personalized and effective support for users. 【0408】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0409】 Step 1: 【0410】 The user provides voice input. This voice input is captured by the device's microphone. The input is audio data, and the output is the same. 【0411】 Step 2: 【0412】 The server converts voice input into text data using speech recognition software, which acts as the conversion mechanism. The input is voice data, and the Google Voice API is used to convert the voice waveform into text data. The output is the converted text data. 【0413】 Step 3: 【0414】 The server analyzes the converted text data using an emotion analysis engine. The input is text data, and EmoVoice is used to analyze voice tone, speed, etc., to infer the user's emotional state. The output is emotion evaluation data. 【0415】 Step 4: 【0416】 The server uses natural language processing libraries to analyze user intent. The input is text data, and the server understands intent by performing syntactic analysis using tools like spaCy and NLTK. The output is data indicating the intent. 【0417】 Step 5: 【0418】 The server uses a generative AI model to generate appropriate response text based on sentiment and intent data. The input is sentiment and intent data, and the response generation process constructs an appropriate sentence. The output is the generated response text. 【0419】 Step 6: 【0420】 The server converts the response text into speech data using a speech synthesis tool. The input is the response text, and Amazon Polly is used to generate natural-sounding speech. The output is the synthesized speech data. 【0421】 Step 7: 【0422】 The device transmits synthesized audio data to the user through its speaker. The input is audio data, and the task is completed when this data finally reaches the user's ears. 【0423】 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. 【0424】 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. 【0425】 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. 【0426】 [Third Embodiment] 【0427】 Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment. 【0428】 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. 【0429】 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). 【0430】 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. 【0431】 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. 【0432】 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). 【0433】 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. 【0434】 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. 【0435】 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. 【0436】 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. 【0437】 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. 【0438】 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". 【0439】 The system of this invention automatically processes voice data using AI technology to handle customer inquiries via telephone. First, when a user makes a call, the server receives the voice input. The server uses speech recognition means to convert the user's voice into text data. This speech recognition includes advanced noise reduction technology and can handle various voice environments. 【0440】 Next, the server applies natural language processing to analyze the user's intent from the converted text. The natural language processing model is trained to understand the context of the conversation and extract relevant information. Through this process, the server identifies the user's specific requests and questions. 【0441】 Based on the identified intent, the server uses response generation means to generate appropriate response text. This response generation flow is supported by an algorithm that considers the customer interaction history and selects the best response from a past response database. 【0442】 The generated response text is converted into speech data by a speech synthesis system. The speech synthesis technology uses multiple speech patterns to enable natural-sounding speech that closely resembles human speech. Finally, the device plays this speech back to the user, and the interaction with the user continues. 【0443】 For example, if a user says, "I want to check my credit card statement," the server converts that speech into text, "I want to check my credit card statement." Once natural language processing identifies the request as "checking my statement," the server checks the relevant statement and generates a response such as, "Your most recent statement shows a charge of XX yen on September 5th," which it then communicates to the user using speech synthesis. 【0444】 This system incorporates a learning mechanism that aggregates customer feedback data and uses it to improve processing accuracy. Furthermore, it can handle inquiries in multiple languages, enabling international customer support. As described above, the system of the present invention dramatically improves service quality and customer satisfaction through an automated customer support process. 【0445】 The following describes the processing flow. 【0446】 Step 1: 【0447】 The user makes a phone call. The server receives the call and obtains the voice input. The server then prepares to process this voice data in real time. 【0448】 Step 2: 【0449】 The server uses speech recognition to convert the user's voice input into text data. This conversion process removes noise from the voice data and analyzes it according to the characteristics of the language. 【0450】 Step 3: 【0451】 The server uses natural language processing to analyze the user's intent from the converted text. Based on keywords and context within the text, it identifies the specific information and actions the user is seeking. 【0452】 Step 4: 【0453】 Based on the analyzed intent, the server generates appropriate response text using a response generation mechanism. The generated response is customized by referring to a fixed dialogue flow and past databases. 【0454】 Step 5: 【0455】 The server uses speech synthesis to convert the generated text responses into natural-sounding speech data. This synthesis process takes into account the intonation and accent specific to each language. 【0456】 Step 6: 【0457】 The terminal plays audio data sent from the server and lets the user hear the response. The user can then ask further questions or confirm necessary information based on this audio response. 【0458】 Step 7: 【0459】 After a call ends, the server collects and analyzes user feedback. This feedback data is used to train the system to improve the accuracy of natural language processing and response generation. 【0460】 (Example 1) 【0461】 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." 【0462】 Traditional customer service systems suffered from low accuracy in voice input and insufficient multilingual support. This resulted in inaccurate processing of customer feedback and decreased customer satisfaction. Furthermore, there is a need to improve the accuracy of intent analysis and response generation from voice input. 【0463】 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. 【0464】 In this invention, the server includes means for receiving voice data from a customer, voice processing means for converting the voice data into a string, and language analysis means for analyzing the customer's request from the string. This enables accurate understanding of the customer's intent and appropriate responses accordingly. 【0465】 "Audio data" refers to information that represents sound waveforms in digital format and is used for communication and data processing. 【0466】 "Speech processing means" refers to a technology or device that analyzes speech data and converts it into text. 【0467】 A "string" is a collection of data represented as text, and is used for language processing. 【0468】 "Linguistic analysis means" refers to technologies or devices for analyzing text and understanding its meaning and context. 【0469】 "Response formation means" refers to a technology or apparatus for generating an appropriate response based on analyzed information. 【0470】 "Speech formation means" refers to a technology or device that converts text data into speech data. 【0471】 A "medium" refers to a method or device for transmitting information, enabling the sending and receiving of data. 【0472】 "Evaluation data" refers to feedback information provided by customers, which is used to evaluate and improve the quality of services. 【0473】 "Learning function" refers to a function that improves the performance of technology based on accumulated data. 【0474】 "Multilingual support" means adjusting or designing technology or equipment to support multiple languages. 【0475】 This invention is a system for automating customer service, utilizing voice processing and natural language processing technologies. Specifically, a server receives and processes voice data to enable interaction with customers. The detailed procedure for carrying out the invention is described below. 【0476】 When a customer makes a phone call, the server receives the audio data. The customer's voice is captured by the server as digital audio data. The server then uses speech recognition software as an audio processing tool to convert the received audio data into text. This process may involve using, for example, a common speech recognition API. 【0477】 Next, the server uses language analysis tools to analyze the customer's intent from the converted string. Natural language processing models are used at this stage. For example, a generative AI model is used to understand the context of the conversation and identify the customer's request. 【0478】 Based on the analysis results, the server uses response formation means to generate an appropriate response. The server prepares the response by implementing an algorithm that considers past response history and selects the optimal response from the database. Once the response text is complete, the server uses speech formation means to convert it back into speech data. A general-purpose synthesis engine may be used as the speech synthesis technology. 【0479】 Finally, the device sends this audio data to the customer, and the conversation is transmitted to the user. The customer can hear the generated audio through the device's audio output function. 【0480】 For example, if a user says, "I want to check my credit card statement," the server converts that into a string and analyzes it to identify the user's intention: "to inquire about their statement." It then generates a specific response, such as, "Your most recent statement shows a transaction of XX yen on September 5th," and converts it into speech to provide to the customer. 【0481】 Examples of prompt messages include the following: 【0482】 "Please provide me with my credit card statement." 【0483】 "I'd like to check my latest usage history." 【0484】 Thus, the present invention aims to improve service quality by utilizing customer feedback data and enabling multilingual support, thereby achieving international customer service. 【0485】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0486】 Step 1: 【0487】 When a user makes a phone call, the audio is transmitted to the server via the terminal. The server takes the received audio data in digital format and prepares the speech recognition system. At this stage, a noise reduction filter is applied to ensure a clear audio signal. 【0488】 Step 2: 【0489】 The server uses speech processing to generate text strings from the received audio data. Specifically, speech recognition software analyzes the audio data and converts each audio component into corresponding text information. The input is audio data, and the output is the corresponding text data. 【0490】 Step 3: 【0491】 The server uses language analysis tools to take the converted text data as input and analyze the customer's intent. It utilizes a generative AI model to identify the user's request based on the context and keywords in the text. In this process, the input is text data, and the output is information indicating the user's intent. 【0492】 Step 4: 【0493】 The server generates an appropriate response using response formation mechanisms based on the identified user intent. It executes an algorithm to select the optimal answer by referring to past queries and existing knowledge bases. The input is user intent information, and the output is the response text. 【0494】 Step 5: 【0495】 The server converts the response text into speech data using speech synthesis technology. At this stage, human-like speech is achieved using speech synthesis technology. The input is the response text, and the output is synthesized speech data. 【0496】 Step 6: 【0497】 The device plays synthesized voice data to the user. The user receives voice responses through the speaker and makes additional inquiries as needed. The output is the voice the user hears, which allows the conversation to continue. 【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】 Conventional customer support systems do not efficiently process voice-based inquiries about transaction information, making it difficult to improve user satisfaction. Furthermore, generating multilingual responses is not easy, posing a barrier to international use. To address these issues, there is a need for a system that efficiently acquires transaction information from voice input and generates natural-sounding multilingual voice responses. 【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 a component for receiving voice input, a voice recognition component for converting the voice input into text data, and a natural language processing component for analyzing the user's intent from the text data. This enables efficient retrieval of the user's transaction information and natural-sounding voice responses. 【0503】 "Voice input" refers to information transmitted by the user via voice, and the voice signal received by the system. 【0504】 "Character data" refers to a string of characters generated based on voice input, in a format used by the system for analysis. 【0505】 "Speech recognition components" refer to technical means for converting speech input into text data. 【0506】 "Natural language processing components" are information processing technologies used to analyze user intent from text data. 【0507】 "Response generation components" refer to technologies within a system that generate appropriate response character data based on the analyzed intent. 【0508】 "Speech synthesis components" refer to technologies for converting response text data into speech data. 【0509】 "Transaction information components" refer to the internal technical means of a system for querying and providing users' transaction information. 【0510】 "Learning components" are components used to improve the accuracy of natural language processing using feedback data. 【0511】 "Adjustment components" are components that enable speech recognition and speech synthesis to support multiple languages. 【0512】 A description of the embodiment for carrying out the invention will be provided. 【0513】 This system receives voice input from the user via the microphone of their smartphone or computer. The server uses the Google Cloud Speech-to-Text API to convert the voice input into text data. The converted text data is then processed using natural language processing with the Hugging Face Transformers library to analyze the user's intent. This analysis identifies the transaction and payment information the user is requesting. 【0514】 Next, the server retrieves relevant transaction information from the database based on the analyzed information. The response generation component generates appropriate response text data based on this information. The generated text data is converted into audio data using Microsoft Azure Cognitive Services. Finally, this audio data is played through the speaker of the user's smartphone or device, providing the information to the user. 【0515】 For example, if a user asks, "What is my credit card payment amount for this month?", the server can convert the speech into text data, retrieve payment information from the database, generate a response such as, "Your credit card payment amount for this month is 15,000 yen," and then respond to the user in voice. 【0516】 An example of a prompt for a generative AI model might be, "Please describe the design of a system that can naturally respond with payment information based on the user's voice input." 【0517】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0518】 Step 1: 【0519】 The user provides voice input through their smartphone's microphone. The input voice data is then transmitted to a server via the network. 【0520】 Step 2: 【0521】 The server uses the Google Cloud Speech-to-Text API to convert the received audio data into text data. In this step, speech recognition is performed to convert the audio signal into text, and the output is as text data. 【0522】 Step 3: 【0523】 The server processes the text data it receives using the Hugging Face Transformers library for natural language processing. This process analyzes the user's intent from the text data. The input is text data, and after analysis, information is output to identify the user's questions and requests. 【0524】 Step 4: 【0525】 The server verifies relevant transaction information based on the analyzed user intent. In this step, it accesses the database and searches for the corresponding transaction and payment data. The input is the identified request information, and the output is the transaction data to be provided to the user. 【0526】 Step 5: 【0527】 The server generates appropriate response text data based on the acquired transaction information. Response generation components work, utilizing past response generation algorithms to produce natural-sounding text. The input is transaction data, and the output is the response text to be returned to the user. 【0528】 Step 6: 【0529】 The server converts the response text into speech data via Microsoft Azure Cognitive Services. This speech synthesis process converts text data into speech, generating natural-sounding human-like voices. The input is the response text, and the output is speech-readable audio data. 【0530】 Step 7: 【0531】 The terminal plays audio data received from the server to the user through its speaker. This allows the user to receive responses to their questions via audio. The input is audio data, and the output is audio playback from the terminal. 【0532】 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. 【0533】 The system of this invention incorporates an emotion engine to further enhance automated responses through customer calls. This allows the server to recognize the user's emotional state and adjust the response process based on that information. 【0534】 When a user makes a call, the server receives the voice input. This voice input is converted into text data by a speech recognition system. At this point, the server activates an emotion engine to analyze the user's emotions from the converted voice data. The emotion engine analyzes the tone, speed, and pauses of the voice to identify emotions such as anger, confusion, or satisfaction. 【0535】 Next, the server uses natural language processing to analyze the user's intent from the text data and considers the response content in combination with the results of emotion recognition. For example, if a user is frustrated and complains that "the bill is wrong," the server takes that emotional state into account and generates a response that is kind and empathetic. 【0536】 The generated response text is converted into speech data using speech synthesis technology, and the terminal plays the response to the customer in a natural voice. This response is appropriately adjusted according to the user's emotions, with the aim of making communication with the customer smoother. 【0537】 For example, if a user expresses frustration by saying, "I'm getting really annoyed because I can't connect at all," the server's emotion engine recognizes that the user is annoyed. Based on this information and the result of intent analysis ("cannot connect"), the server generates a response such as, "We apologize for the delay. We will do our best to resolve this issue as quickly as possible," and delivers it via speech synthesis. 【0538】 Furthermore, the server has a learning function that accumulates user feedback data and improves the accuracy of emotion recognition and response generation. In this way, the system improves with repeated use, enabling it to provide higher customer satisfaction. 【0539】 This invention enables a more personalized and effective customer service experience by responding not only to the user's words but also to the emotions hidden beneath them. 【0540】 The following describes the processing flow. 【0541】 Step 1: 【0542】 The user makes a phone call, and the server receives the voice input. At this point, the server begins collecting voice data as soon as the call starts. 【0543】 Step 2: 【0544】 The server utilizes speech recognition technology to convert received speech input into text data. The process involves removing noise using speech recognition technology and accurately converting utterances into text. 【0545】 Step 3: 【0546】 The server passes the converted text data to the emotion engine. The emotion engine analyzes the characteristics of this text and voice (tone, speed, etc.) to recognize the user's emotional state (e.g., anger, sadness, joy). 【0547】 Step 4: 【0548】 The server uses natural language processing to analyze the user's intent from the text data. This analysis clarifies the intent behind the user's requests and questions, and combines this with the sentiment analysis results from earlier to prepare for the next step. 【0549】 Step 5: 【0550】 The server generates appropriate response text based on the analyzed intent and recognized emotions using a response generation mechanism. This generation process incorporates empathetic language that takes the user's emotions into consideration, as well as specific suggestions for problem solving, into the response. 【0551】 Step 6: 【0552】 The server converts the generated response text into speech data using a speech synthesis system. Speech synthesis requires natural and easy-to-understand pronunciation, and, if necessary, sets a tone that reflects emotion. 【0553】 Step 7: 【0554】 The terminal plays audio data from the server and communicates the response to the user. The user can listen to this audio response and respond, and the conversation continues from there. 【0555】 Step 8: 【0556】 The server collects user feedback after a call, analyzes the data to improve the accuracy of speech recognition, emotion recognition, and natural language processing, and works to continuously improve the system. 【0557】 (Example 2) 【0558】 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." 【0559】 Conventional automated response systems often provide uniform and mechanical responses to user voice input, potentially resulting in inappropriate responses that disregard the customer's emotional state. This can lead to decreased customer satisfaction and negatively impact service quality. Furthermore, if the system does not support multiple languages, language barriers can hinder appropriate customer service, posing another challenge. 【0560】 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. 【0561】 In this invention, the server includes a mechanism for receiving voice input from a customer, a voice recognition mechanism for converting the voice input into text data, an emotion recognition mechanism for analyzing the customer's emotional state from the text data, a natural language processing mechanism for analyzing the customer's intentions based on the emotional state and text data, a response generation mechanism for generating appropriate response text based on the analyzed intentions and emotions, a voice synthesis mechanism for converting the response text into voice data, and a device for transmitting the voice data to the customer. This enables personalized responses tailored to the user's emotional state, thereby improving customer satisfaction. Furthermore, a system that includes multilingual support enables appropriate customer service that transcends language barriers. 【0562】 "Voice input" refers to voice information spoken by customers, and the system processes this information based on that input. 【0563】 A "speech recognition system" is a technology that converts speech input into text data, and its role is to analyze the user's speech and convert it into a digital format. 【0564】 An "emotion recognition mechanism" is a technology that analyzes a customer's emotional state from voice data, identifying emotions based on voice tone, speaking speed, and pauses between sounds. 【0565】 A "natural language processing mechanism" is a technology that analyzes user intent from text data, and is designed to understand natural language and determine appropriate responses. 【0566】 A "response generation mechanism" is a technology that generates appropriate response text based on analyzed intentions and emotions. 【0567】 A "speech synthesis mechanism" is a technology that converts response text into speech data, and its role is to convey the generated response content to the customer as speech. 【0568】 "Device" refers to a part of a system that includes hardware and software for transmitting voice data to customers. 【0569】 A "learning mechanism" is a technology in which a system continuously learns by accumulating feedback data from customers in order to improve the accuracy of its analysis. 【0570】 The "adjustment mechanism" is a technology that configures the system to support multiple languages ​​for speech recognition and speech synthesis mechanisms, thereby achieving multilingual support. 【0571】 The system of this invention is built to further enhance automated responses through customer calls. By integrating speech recognition, emotion recognition, natural language processing, response generation, and speech synthesis technologies, this system provides customers with flexible and personalized responses. 【0572】 The server has the capability to receive voice input when a user makes a phone call. The received voice is converted into text data using speech recognition software (for example, an API known as a general speech recognition engine). At this point, the content of the voice becomes available for processing in digital format. 【0573】 Next, the server inputs the text data into an emotion recognition engine to identify the customer's emotional state. This emotion recognition is based on factors such as tone of voice, speed, and word spacing. For example, if a user's voice is high-pitched and they are speaking quickly, the server can determine that the person is angry. 【0574】 Furthermore, the server uses a natural language processing engine to analyze the user's intent from their text. This process utilizes generative AI models to accurately understand what the user is asking for. 【0575】 During the response generation phase, the server generates an appropriate response based on the results of emotion recognition and intent analysis. This response is designed to be empathetic and considerate of the user's emotions. 【0576】 The generated response is converted back into speech data using speech synthesis software. The terminal then plays the response back to the user in a natural voice through this speech data. In this way, communication becomes smoother, and interactions can be conducted without causing excessive stress. 【0577】 For example, if a user expresses dissatisfaction such as "I can't connect at all," the server's emotion recognition engine will detect the user's dissatisfaction. Based on the analysis, the server will generate a response such as "We apologize for the delay. We are working to resolve the issue, so please wait a little longer," and deliver it via speech synthesis. 【0578】 An example of a prompt might be, "Analyze the user's utterance, recognize their emotions, and then generate an appropriate response." Based on this prompt, the AI ​​model can devise responses that enable sophisticated customer service. 【0579】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0580】 Step 1: 【0581】 When a user makes a phone call, the server receives the voice input. The voice data arrives at the server as input. This voice data is sent to speech recognition software, which converts it into digital text. This conversion outputs the voice content as text data for natural language processing. 【0582】 Step 2: 【0583】 The server passes the speech-recognized text data to the emotion recognition engine. From this input text data, the server analyzes the tone and tempo of the voice, as well as emphasized words in the text. Based on this data, the emotion recognition engine identifies the user's emotional state and outputs it as a basic emotion such as "anger," "satisfaction," or "confusion." 【0584】 Step 3: 【0585】 The server combines the emotion recognition results with text data and inputs it into a natural language processing engine. In this step, the server uses a generative AI model to analyze the text data in detail and understand the user's intent. As a result of this analysis, semantic data identifying the user's requests and inquiries is output. 【0586】 Step 4: 【0587】 The server combines the intent analysis results and emotion recognition results and passes them to the response generation engine. The response generation engine uses a generation AI model to create appropriate response text that takes the user's emotions into account. As a result, response text that includes empathy and problem-solving is output. 【0588】 Step 5: 【0589】 The server inputs the generated response text into speech synthesis software. The speech synthesis software converts this text into speech data and outputs more natural-sounding speech data. 【0590】 Step 6: 【0591】 The terminal receives audio data output from the server and speaks it to the user. At this stage, the volume and tone of voice are adjusted according to the user's emotions, and an appropriate response is provided to the user. 【0592】 (Application Example 2) 【0593】 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." 【0594】 In modern society, understanding user emotions and providing appropriate information and services accordingly is crucial for enhancing the personalized experience. However, conventional automated response systems have struggled to generate responses that take emotions into account and to provide security information in real time. Further improving user satisfaction remains a challenge. 【0595】 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. 【0596】 In this invention, the server includes means for receiving voice input, means for converting the voice input into text data, and means for analyzing the user's intent from the text data. This makes it possible to understand the user's emotions and provide security information based on them. 【0597】 "Means for receiving voice input" refers to a device or technology that collects voice data provided by a user and prepares it for processing. 【0598】 "Conversion means" refers to a technology or device that converts audio data into text data, and then converts the response text back into audio data. 【0599】 "Analysis means" refers to a technology or device that determines the user's intentions and emotions from text data and extracts information for generating appropriate responses. 【0600】 "Generation means" refers to a technology or device that generates response text to be provided to the user based on analyzed intentions and emotions. 【0601】 "Outputting means" refers to a device or technology for directly transmitting the generated audio data to the user. 【0602】 "Proposal means" refers to technology or devices for providing necessary information and advice based on the user's emotions and intentions. 【0603】 A description of the embodiment for carrying out the invention will be given. 【0604】 This system aims to recognize emotions through interaction with the user and provide appropriate communication accordingly. The system primarily operates by combining speech recognition, emotion analysis, natural language processing, and speech synthesis functions. Details are described below. 【0605】 The server first obtains the voice input provided by the user through a means of receiving voice input. Next, it converts that voice data into text data using a conversion means. This conversion process includes the Google Voice API, which is widely used as speech recognition software. 【0606】 Next, an analysis tool works to analyze the user's emotions and intentions from the converted text data. Here, an emotion analysis engine like EmoVoice and natural language processing libraries such as spaCy and NLTK are used to analyze the tone and speed of the voice and infer the user's emotional state. 【0607】 Based on the analysis results, the generation mechanism generates response text appropriate to the user. In this part, an AI model generates responses that correspond to specific emotions and intentions. Furthermore, Amazon Polly is used as a speech synthesis tool to convert the generated text into natural-sounding speech data. 【0608】 Subsequently, the audio data is transmitted to the user via an output method. The interaction is completed when the data is sent to the user through the speaker. 【0609】 For example, if a child says via smartphone, "I'm worried because my family hasn't come home," the system will provide an emotionally sensitive response such as, "It's okay. We'll let you know when your family arrives." 【0610】 Examples of prompts include, "Recognize that the user is feeling anxious and consider a reassuring response," and "Read the emotion from this audio data and generate a script that instantly suggests a course of action." In this way, the present invention enables personalized and effective support for users. 【0611】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0612】 Step 1: 【0613】 The user provides voice input. This voice input is captured by the device's microphone. The input is audio data, and the output is the same. 【0614】 Step 2: 【0615】 The server converts voice input into text data using speech recognition software, which acts as the conversion mechanism. The input is voice data, and the Google Voice API is used to convert the voice waveform into text data. The output is the converted text data. 【0616】 Step 3: 【0617】 The server analyzes the converted text data using an emotion analysis engine. The input is text data, and EmoVoice is used to analyze voice tone, speed, etc., to infer the user's emotional state. The output is emotion evaluation data. 【0618】 Step 4: 【0619】 The server uses natural language processing libraries to analyze user intent. The input is text data, and the server understands intent by performing syntactic analysis using tools like spaCy and NLTK. The output is data indicating the intent. 【0620】 Step 5: 【0621】 The server uses a generative AI model to generate appropriate response text based on sentiment and intent data. The input is sentiment and intent data, and the response generation process constructs an appropriate sentence. The output is the generated response text. 【0622】 Step 6: 【0623】 The server converts the response text into speech data using a speech synthesis tool. The input is the response text, and Amazon Polly is used to generate natural-sounding speech. The output is the synthesized speech data. 【0624】 Step 7: 【0625】 The device transmits synthesized audio data to the user through its speaker. The input is audio data, and the task is completed when this data finally reaches the user's ears. 【0626】 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. 【0627】 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. 【0628】 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. 【0629】 [Fourth Embodiment] 【0630】 Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment. 【0631】 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. 【0632】 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). 【0633】 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. 【0634】 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. 【0635】 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). 【0636】 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. 【0637】 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. 【0638】 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. 【0639】 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. 【0640】 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. 【0641】 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. 【0642】 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". 【0643】 The system of this invention automatically processes voice data using AI technology to handle customer inquiries via telephone. First, when a user makes a call, the server receives the voice input. The server uses speech recognition means to convert the user's voice into text data. This speech recognition includes advanced noise reduction technology and can handle various voice environments. 【0644】 Next, the server applies natural language processing to analyze the user's intent from the converted text. The natural language processing model is trained to understand the context of the conversation and extract relevant information. Through this process, the server identifies the user's specific requests and questions. 【0645】 Based on the identified intent, the server uses response generation means to generate appropriate response text. This response generation flow is supported by an algorithm that considers the customer interaction history and selects the best response from a past response database. 【0646】 The generated response text is converted into speech data by a speech synthesis system. The speech synthesis technology uses multiple speech patterns to enable natural-sounding speech that closely resembles human speech. Finally, the device plays this speech back to the user, and the interaction with the user continues. 【0647】 For example, if a user says, "I want to check my credit card statement," the server converts that speech into text, "I want to check my credit card statement." Once natural language processing identifies the request as "checking my statement," the server checks the relevant statement and generates a response such as, "Your most recent statement shows a charge of XX yen on September 5th," which it then communicates to the user using speech synthesis. 【0648】 This system incorporates a learning mechanism that aggregates customer feedback data and uses it to improve processing accuracy. Furthermore, it can handle inquiries in multiple languages, enabling international customer support. As described above, the system of the present invention dramatically improves service quality and customer satisfaction through an automated customer support process. 【0649】 The following describes the processing flow. 【0650】 Step 1: 【0651】 The user makes a phone call. The server receives the call and obtains the voice input. The server then prepares to process this voice data in real time. 【0652】 Step 2: 【0653】 The server uses speech recognition to convert the user's voice input into text data. This conversion process removes noise from the voice data and analyzes it according to the characteristics of the language. 【0654】 Step 3: 【0655】 The server uses natural language processing to analyze the user's intent from the converted text. Based on keywords and context within the text, it identifies the specific information and actions the user is seeking. 【0656】 Step 4: 【0657】 Based on the analyzed intent, the server generates appropriate response text using a response generation mechanism. The generated response is customized by referring to a fixed dialogue flow and past databases. 【0658】 Step 5: 【0659】 The server uses speech synthesis to convert the generated text responses into natural-sounding speech data. This synthesis process takes into account the intonation and accent specific to each language. 【0660】 Step 6: 【0661】 The terminal plays audio data sent from the server and lets the user hear the response. The user can then ask further questions or confirm necessary information based on this audio response. 【0662】 Step 7: 【0663】 After a call ends, the server collects and analyzes user feedback. This feedback data is used to train the system to improve the accuracy of natural language processing and response generation. 【0664】 (Example 1) 【0665】 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". 【0666】 Traditional customer service systems suffered from low accuracy in voice input and insufficient multilingual support. This resulted in inaccurate processing of customer feedback and decreased customer satisfaction. Furthermore, there is a need to improve the accuracy of intent analysis and response generation from voice input. 【0667】 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. 【0668】 In this invention, the server includes means for receiving voice data from a customer, voice processing means for converting the voice data into a string, and language analysis means for analyzing the customer's request from the string. This enables accurate understanding of the customer's intent and appropriate responses accordingly. 【0669】 "Audio data" refers to information that represents sound waveforms in digital format and is used for communication and data processing. 【0670】 "Speech processing means" refers to a technology or device that analyzes speech data and converts it into text. 【0671】 A "string" is a collection of data represented as text, and is used for language processing. 【0672】 "Linguistic analysis means" refers to technologies or devices for analyzing text and understanding its meaning and context. 【0673】 "Response formation means" refers to a technology or apparatus for generating an appropriate response based on analyzed information. 【0674】 "Speech formation means" refers to a technology or device that converts text data into speech data. 【0675】 A "medium" refers to a method or device for transmitting information, enabling the sending and receiving of data. 【0676】 "Evaluation data" refers to feedback information provided by customers, which is used to evaluate and improve the quality of services. 【0677】 "Learning function" refers to a function that improves the performance of technology based on accumulated data. 【0678】 "Multilingual support" means adjusting or designing technology or equipment to support multiple languages. 【0679】 This invention is a system for automating customer service, utilizing voice processing and natural language processing technologies. Specifically, a server receives and processes voice data to enable interaction with customers. The detailed procedure for carrying out the invention is described below. 【0680】 When a customer makes a phone call, the server receives the audio data. The customer's voice is captured by the server as digital audio data. The server then uses speech recognition software as an audio processing tool to convert the received audio data into text. This process may involve using, for example, a common speech recognition API. 【0681】 Next, the server uses language analysis tools to analyze the customer's intent from the converted string. Natural language processing models are used at this stage. For example, a generative AI model is used to understand the context of the conversation and identify the customer's request. 【0682】 Based on the analysis results, the server uses response formation means to generate an appropriate response. The server prepares the response by implementing an algorithm that considers past response history and selects the optimal response from the database. Once the response text is complete, the server uses speech formation means to convert it back into speech data. A general-purpose synthesis engine may be used as the speech synthesis technology. 【0683】 Finally, the device sends this audio data to the customer, and the conversation is transmitted to the user. The customer can hear the generated audio through the device's audio output function. 【0684】 For example, if a user says, "I want to check my credit card statement," the server converts that into a string and analyzes it to identify the user's intention: "to inquire about their statement." It then generates a specific response, such as, "Your most recent statement shows a transaction of XX yen on September 5th," and converts it into speech to provide to the customer. 【0685】 Examples of prompt messages include the following: 【0686】 "Please provide me with my credit card statement." 【0687】 "I'd like to check my latest usage history." 【0688】 Thus, the present invention aims to improve service quality by utilizing customer feedback data and enabling multilingual support, thereby achieving international customer service. 【0689】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0690】 Step 1: 【0691】 When a user makes a phone call, the audio is transmitted to the server via the terminal. The server takes the received audio data in digital format and prepares the speech recognition system. At this stage, a noise reduction filter is applied to ensure a clear audio signal. 【0692】 Step 2: 【0693】 The server uses speech processing to generate text strings from the received audio data. Specifically, speech recognition software analyzes the audio data and converts each audio component into corresponding text information. The input is audio data, and the output is the corresponding text data. 【0694】 Step 3: 【0695】 The server uses language analysis tools to take the converted text data as input and analyze the customer's intent. It utilizes a generative AI model to identify the user's request based on the context and keywords in the text. In this process, the input is text data, and the output is information indicating the user's intent. 【0696】 Step 4: 【0697】 The server generates an appropriate response using response formation mechanisms based on the identified user intent. It executes an algorithm to select the optimal answer by referring to past queries and existing knowledge bases. The input is user intent information, and the output is the response text. 【0698】 Step 5: 【0699】 The server converts the response text into speech data using speech synthesis technology. At this stage, human-like speech is achieved using speech synthesis technology. The input is the response text, and the output is synthesized speech data. 【0700】 Step 6: 【0701】 The device plays synthesized voice data to the user. The user receives voice responses through the speaker and makes additional inquiries as needed. The output is the voice the user hears, which allows the conversation to continue. 【0702】 (Application Example 1) 【0703】 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". 【0704】 Conventional customer support systems do not efficiently process voice-based inquiries about transaction information, making it difficult to improve user satisfaction. Furthermore, generating multilingual responses is not easy, posing a barrier to international use. To address these issues, there is a need for a system that efficiently acquires transaction information from voice input and generates natural-sounding multilingual voice responses. 【0705】 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. 【0706】 In this invention, the server includes a component for receiving voice input, a voice recognition component for converting the voice input into text data, and a natural language processing component for analyzing the user's intent from the text data. This enables efficient retrieval of the user's transaction information and natural-sounding voice responses. 【0707】 "Voice input" refers to information transmitted by the user via voice, and the voice signal received by the system. 【0708】 "Character data" refers to a string of characters generated based on voice input, in a format used by the system for analysis. 【0709】 "Speech recognition components" refer to technical means for converting speech input into text data. 【0710】 "Natural language processing components" are information processing technologies used to analyze user intent from text data. 【0711】 "Response generation components" refer to technologies within a system that generate appropriate response character data based on the analyzed intent. 【0712】 "Speech synthesis components" refer to technologies for converting response text data into speech data. 【0713】 "Transaction information components" refer to the internal technical means of a system for querying and providing users' transaction information. 【0714】 "Learning components" are components used to improve the accuracy of natural language processing using feedback data. 【0715】 "Adjustment components" are components that enable speech recognition and speech synthesis to support multiple languages. 【0716】 A description of the embodiment for carrying out the invention will be provided. 【0717】 This system receives voice input from the user via the microphone of their smartphone or computer. The server uses the Google Cloud Speech-to-Text API to convert the voice input into text data. The converted text data is then processed using natural language processing with the Hugging Face Transformers library to analyze the user's intent. This analysis identifies the transaction and payment information the user is requesting. 【0718】 Next, the server retrieves relevant transaction information from the database based on the analyzed information. The response generation component generates appropriate response text data based on this information. The generated text data is converted into audio data using Microsoft Azure Cognitive Services. Finally, this audio data is played through the speaker of the user's smartphone or device, providing the information to the user. 【0719】 For example, if a user asks, "What is my credit card payment amount for this month?", the server can convert the speech into text data, retrieve payment information from the database, generate a response such as, "Your credit card payment amount for this month is 15,000 yen," and then respond to the user in voice. 【0720】 An example of a prompt for a generative AI model might be, "Please describe the design of a system that can naturally respond with payment information based on the user's voice input." 【0721】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0722】 Step 1: 【0723】 The user provides voice input through their smartphone's microphone. The input voice data is then transmitted to a server via the network. 【0724】 Step 2: 【0725】 The server uses the Google Cloud Speech-to-Text API to convert the received audio data into text data. In this step, speech recognition is performed to convert the audio signal into text, and the output is as text data. 【0726】 Step 3: 【0727】 The server processes the text data it receives using the Hugging Face Transformers library for natural language processing. This process analyzes the user's intent from the text data. The input is text data, and after analysis, information is output to identify the user's questions and requests. 【0728】 Step 4: 【0729】 The server verifies relevant transaction information based on the analyzed user intent. In this step, it accesses the database and searches for the corresponding transaction and payment data. The input is the identified request information, and the output is the transaction data to be provided to the user. 【0730】 Step 5: 【0731】 The server generates appropriate response text data based on the acquired transaction information. Response generation components work, utilizing past response generation algorithms to produce natural-sounding text. The input is transaction data, and the output is the response text to be returned to the user. 【0732】 Step 6: 【0733】 The server converts the response text into speech data via Microsoft Azure Cognitive Services. This speech synthesis process converts text data into speech, generating natural-sounding human-like voices. The input is the response text, and the output is speech-readable audio data. 【0734】 Step 7: 【0735】 The terminal plays audio data received from the server to the user through its speaker. This allows the user to receive responses to their questions via audio. The input is audio data, and the output is audio playback from the terminal. 【0736】 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. 【0737】 The system of this invention incorporates an emotion engine to further enhance automated responses through customer calls. This allows the server to recognize the user's emotional state and adjust the response process based on that information. 【0738】 When a user makes a call, the server receives the voice input. This voice input is converted into text data by a speech recognition system. At this point, the server activates an emotion engine to analyze the user's emotions from the converted voice data. The emotion engine analyzes the tone, speed, and pauses of the voice to identify emotions such as anger, confusion, or satisfaction. 【0739】 Next, the server uses natural language processing to analyze the user's intent from the text data and considers the response content in combination with the results of emotion recognition. For example, if a user is frustrated and complains that "the bill is wrong," the server takes that emotional state into account and generates a response that is kind and empathetic. 【0740】 The generated response text is converted into speech data using speech synthesis technology, and the terminal plays the response to the customer in a natural voice. This response is appropriately adjusted according to the user's emotions, with the aim of making communication with the customer smoother. 【0741】 For example, if a user expresses frustration by saying, "I'm getting really annoyed because I can't connect at all," the server's emotion engine recognizes that the user is annoyed. Based on this information and the result of intent analysis ("cannot connect"), the server generates a response such as, "We apologize for the delay. We will do our best to resolve this issue as quickly as possible," and delivers it via speech synthesis. 【0742】 Furthermore, the server has a learning function that accumulates user feedback data and improves the accuracy of emotion recognition and response generation. In this way, the system improves with repeated use, enabling it to provide higher customer satisfaction. 【0743】 This invention enables a more personalized and effective customer service experience by responding not only to the user's words but also to the emotions hidden beneath them. 【0744】 The following describes the processing flow. 【0745】 Step 1: 【0746】 The user makes a phone call, and the server receives the voice input. At this point, the server begins collecting voice data as soon as the call starts. 【0747】 Step 2: 【0748】 The server utilizes speech recognition technology to convert received speech input into text data. The process involves removing noise using speech recognition technology and accurately converting utterances into text. 【0749】 Step 3: 【0750】 The server passes the converted text data to the emotion engine. The emotion engine analyzes the characteristics of this text and voice (tone, speed, etc.) to recognize the user's emotional state (e.g., anger, sadness, joy). 【0751】 Step 4: 【0752】 The server uses natural language processing to analyze the user's intent from the text data. This analysis clarifies the intent behind the user's requests and questions, and combines this with the sentiment analysis results from earlier to prepare for the next step. 【0753】 Step 5: 【0754】 The server generates appropriate response text based on the analyzed intent and recognized emotions using a response generation mechanism. This generation process incorporates empathetic language that takes the user's emotions into consideration, as well as specific suggestions for problem solving, into the response. 【0755】 Step 6: 【0756】 The server converts the generated response text into speech data using a speech synthesis system. Speech synthesis requires natural and easy-to-understand pronunciation, and, if necessary, sets a tone that reflects emotion. 【0757】 Step 7: 【0758】 The terminal plays audio data from the server and communicates the response to the user. The user can listen to this audio response and respond, and the conversation continues from there. 【0759】 Step 8: 【0760】 The server collects user feedback after a call, analyzes the data to improve the accuracy of speech recognition, emotion recognition, and natural language processing, and works to continuously improve the system. 【0761】 (Example 2) 【0762】 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". 【0763】 Conventional automated response systems often provide uniform and mechanical responses to user voice input, potentially resulting in inappropriate responses that disregard the customer's emotional state. This can lead to decreased customer satisfaction and negatively impact service quality. Furthermore, if the system does not support multiple languages, language barriers can hinder appropriate customer service, posing another challenge. 【0764】 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. 【0765】 In this invention, the server includes a mechanism for receiving voice input from a customer, a voice recognition mechanism for converting the voice input into text data, an emotion recognition mechanism for analyzing the customer's emotional state from the text data, a natural language processing mechanism for analyzing the customer's intentions based on the emotional state and text data, a response generation mechanism for generating appropriate response text based on the analyzed intentions and emotions, a voice synthesis mechanism for converting the response text into voice data, and a device for transmitting the voice data to the customer. This enables personalized responses tailored to the user's emotional state, thereby improving customer satisfaction. Furthermore, a system that includes multilingual support enables appropriate customer service that transcends language barriers. 【0766】 "Voice input" refers to voice information spoken by customers, and the system processes this information based on that input. 【0767】 A "speech recognition system" is a technology that converts speech input into text data, and its role is to analyze the user's speech and convert it into a digital format. 【0768】 An "emotion recognition mechanism" is a technology that analyzes a customer's emotional state from voice data, identifying emotions based on voice tone, speaking speed, and pauses between sounds. 【0769】 A "natural language processing mechanism" is a technology that analyzes user intent from text data, and is designed to understand natural language and determine appropriate responses. 【0770】 A "response generation mechanism" is a technology that generates appropriate response text based on analyzed intentions and emotions. 【0771】 A "speech synthesis mechanism" is a technology that converts response text into speech data, and its role is to convey the generated response content to the customer as speech. 【0772】 "Device" refers to a part of a system that includes hardware and software for transmitting voice data to customers. 【0773】 A "learning mechanism" is a technology in which a system continuously learns by accumulating feedback data from customers in order to improve the accuracy of its analysis. 【0774】 The "adjustment mechanism" is a technology that configures the system to support multiple languages ​​for speech recognition and speech synthesis mechanisms, thereby achieving multilingual support. 【0775】 The system of this invention is built to further enhance automated responses through customer calls. By integrating speech recognition, emotion recognition, natural language processing, response generation, and speech synthesis technologies, this system provides customers with flexible and personalized responses. 【0776】 The server has the capability to receive voice input when a user makes a phone call. The received voice is converted into text data using speech recognition software (for example, an API known as a general speech recognition engine). At this point, the content of the voice becomes available for processing in digital format. 【0777】 Next, the server inputs the text data into an emotion recognition engine to identify the customer's emotional state. This emotion recognition is based on factors such as tone of voice, speed, and word spacing. For example, if a user's voice is high-pitched and they are speaking quickly, the server can determine that the person is angry. 【0778】 Furthermore, the server uses a natural language processing engine to analyze the user's intent from their text. This process utilizes generative AI models to accurately understand what the user is asking for. 【0779】 During the response generation phase, the server generates an appropriate response based on the results of emotion recognition and intent analysis. This response is designed to be empathetic and considerate of the user's emotions. 【0780】 The generated response is converted back into speech data using speech synthesis software. The terminal then plays the response back to the user in a natural voice through this speech data. In this way, communication becomes smoother, and interactions can be conducted without causing excessive stress. 【0781】 For example, if a user expresses dissatisfaction such as "I can't connect at all," the server's emotion recognition engine will detect the user's dissatisfaction. Based on the analysis, the server will generate a response such as "We apologize for the delay. We are working to resolve the issue, so please wait a little longer," and deliver it via speech synthesis. 【0782】 An example of a prompt might be, "Analyze the user's utterance, recognize their emotions, and then generate an appropriate response." Based on this prompt, the AI ​​model can devise responses that enable sophisticated customer service. 【0783】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0784】 Step 1: 【0785】 When a user makes a phone call, the server receives the voice input. The voice data arrives at the server as input. This voice data is sent to speech recognition software, which converts it into digital text. This conversion outputs the voice content as text data for natural language processing. 【0786】 Step 2: 【0787】 The server passes the speech-recognized text data to the emotion recognition engine. From this input text data, the server analyzes the tone and tempo of the voice, as well as emphasized words in the text. Based on this data, the emotion recognition engine identifies the user's emotional state and outputs it as a basic emotion such as "anger," "satisfaction," or "confusion." 【0788】 Step 3: 【0789】 The server combines the emotion recognition results with text data and inputs it into a natural language processing engine. In this step, the server uses a generative AI model to analyze the text data in detail and understand the user's intent. As a result of this analysis, semantic data identifying the user's requests and inquiries is output. 【0790】 Step 4: 【0791】 The server combines the intent analysis results and emotion recognition results and passes them to the response generation engine. The response generation engine uses a generation AI model to create appropriate response text that takes the user's emotions into account. As a result, response text that includes empathy and problem-solving is output. 【0792】 Step 5: 【0793】 The server inputs the generated response text into speech synthesis software. The speech synthesis software converts this text into speech data and outputs more natural-sounding speech data. 【0794】 Step 6: 【0795】 The terminal receives audio data output from the server and speaks it to the user. At this stage, the volume and tone of voice are adjusted according to the user's emotions, and an appropriate response is provided to the user. 【0796】 (Application Example 2) 【0797】 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". 【0798】 In modern society, understanding user emotions and providing appropriate information and services accordingly is crucial for enhancing the personalized experience. However, conventional automated response systems have struggled to generate responses that take emotions into account and to provide security information in real time. Further improving user satisfaction remains a challenge. 【0799】 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. 【0800】 In this invention, the server includes means for receiving voice input, means for converting the voice input into text data, and means for analyzing the user's intent from the text data. This makes it possible to understand the user's emotions and provide security information based on them. 【0801】 "Means for receiving voice input" refers to a device or technology that collects voice data provided by a user and prepares it for processing. 【0802】 "Conversion means" refers to a technology or device that converts audio data into text data, and then converts the response text back into audio data. 【0803】 "Analysis means" refers to a technology or device that determines the user's intentions and emotions from text data and extracts information for generating appropriate responses. 【0804】 "Generation means" refers to a technology or device that generates response text to be provided to the user based on analyzed intentions and emotions. 【0805】 "Outputting means" refers to a device or technology for directly transmitting the generated audio data to the user. 【0806】 "Proposal means" refers to technology or devices for providing necessary information and advice based on the user's emotions and intentions. 【0807】 A description of the embodiment for carrying out the invention will be given. 【0808】 This system aims to recognize emotions through interaction with the user and provide appropriate communication accordingly. The system primarily operates by combining speech recognition, emotion analysis, natural language processing, and speech synthesis functions. Details are described below. 【0809】 The server first obtains the voice input provided by the user through a means of receiving voice input. Next, it converts that voice data into text data using a conversion means. This conversion process includes the Google Voice API, which is widely used as speech recognition software. 【0810】 Next, an analysis tool works to analyze the user's emotions and intentions from the converted text data. Here, an emotion analysis engine like EmoVoice and natural language processing libraries such as spaCy and NLTK are used to analyze the tone and speed of the voice and infer the user's emotional state. 【0811】 Based on the analysis results, the generation mechanism generates response text appropriate to the user. In this part, an AI model generates responses that correspond to specific emotions and intentions. Furthermore, Amazon Polly is used as a speech synthesis tool to convert the generated text into natural-sounding speech data. 【0812】 Subsequently, the audio data is transmitted to the user via an output method. The interaction is completed when the data is sent to the user through the speaker. 【0813】 For example, if a child says via smartphone, "I'm worried because my family hasn't come home," the system will provide an emotionally sensitive response such as, "It's okay. We'll let you know when your family arrives." 【0814】 Examples of prompts include, "Recognize that the user is feeling anxious and consider a reassuring response," and "Read the emotion from this audio data and generate a script that instantly suggests a course of action." In this way, the present invention enables personalized and effective support for users. 【0815】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0816】 Step 1: 【0817】 The user provides voice input. This voice input is captured by the device's microphone. The input is audio data, and the output is the same. 【0818】 Step 2: 【0819】 The server converts voice input into text data using speech recognition software, which acts as the conversion mechanism. The input is voice data, and the Google Voice API is used to convert the voice waveform into text data. The output is the converted text data. 【0820】 Step 3: 【0821】 The server analyzes the converted text data using an emotion analysis engine. The input is text data, and EmoVoice is used to analyze voice tone, speed, etc., to infer the user's emotional state. The output is emotion evaluation data. 【0822】 Step 4: 【0823】 The server uses natural language processing libraries to analyze user intent. The input is text data, and the server understands intent by performing syntactic analysis using tools like spaCy and NLTK. The output is data indicating the intent. 【0824】 Step 5: 【0825】 The server uses a generative AI model to generate appropriate response text based on sentiment and intent data. The input is sentiment and intent data, and the response generation process constructs an appropriate sentence. The output is the generated response text. 【0826】 Step 6: 【0827】 The server converts the response text into speech data using a speech synthesis tool. The input is the response text, and Amazon Polly is used to generate natural-sounding speech. The output is the synthesized speech data. 【0828】 Step 7: 【0829】 The device transmits synthesized audio data to the user through its speaker. The input is audio data, and the task is completed when this data finally reaches the user's ears. 【0830】 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. 【0831】 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. 【0832】 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. 【0833】 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. 【0834】 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. 【0835】 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. 【0836】 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. 【0837】 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. 【0838】 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." 【0839】 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. 【0840】 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. 【0841】 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. 【0842】 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. 【0843】 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. 【0844】 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. 【0845】 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. 【0846】 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. 【0847】 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. 【0848】 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. 【0849】 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. 【0850】 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. 【0851】 The following is further disclosed regarding the embodiments described above. 【0852】 (Claim 1) 【0853】 A means of receiving voice input from customers, 【0854】 A speech recognition means that converts the aforementioned voice input into text data, 【0855】 A natural language processing means for analyzing customer intent from the aforementioned text data, 【0856】 A response generation means that generates appropriate response text based on the analyzed intent, 【0857】 A speech synthesis means that converts the aforementioned response text into speech data, 【0858】 A system including means for transmitting the aforementioned audio data to a customer. 【0859】 (Claim 2) 【0860】 The system according to claim 1, comprising a learning means for accumulating and analyzing customer feedback data and for improving the accuracy of the natural language processing means. 【0861】 (Claim 3) 【0862】 The system according to claim 1, further comprising adjustment means for enabling multilingual customer support by making the speech recognition means and speech synthesis means compatible with multiple languages. 【0863】 【0864】 "Example 1" 【0865】 (Claim 1) 【0866】 A means of receiving voice data from customers, 【0867】 A speech processing means that converts the aforementioned speech data into a string, 【0868】 A language analysis means for analyzing customer requests from the aforementioned string, 【0869】 A response forming means that generates a suitable response based on the analyzed requirements, 【0870】 A speech forming means for converting the aforementioned response back into speech data, 【0871】 A system including a medium for transmitting the aforementioned audio data to a customer. 【0872】 (Claim 2) 【0873】 The system according to claim 1, further comprising a learning function that accumulates and analyzes customer evaluation data to improve the accuracy of the language analysis means. 【0874】 (Claim 3) 【0875】 The system according to claim 1, further comprising a function for adjusting the voice processing means and voice forming means to support multiple languages ​​in order to enable customer service in multiple languages. 【0876】 "Application Example 1" 【0877】 (Claim 1) 【0878】 Components for receiving voice input, 【0879】 A speech recognition component that converts the aforementioned voice input into text data, 【0880】 A natural language processing component that analyzes the user's intent from the aforementioned text data, 【0881】 A response generation component that generates appropriate response character data based on the analyzed intent, 【0882】 A speech synthesis component that converts the aforementioned response character data into speech data, 【0883】 A component that transmits the aforementioned audio data to the user, 【0884】 A system including a transaction information component that queries and provides user transaction information. 【0885】 (Claim 2) 【0886】 The system according to claim 1, which includes a learning component that accumulates and analyzes user feedback data to improve the accuracy of the natural language processing component. 【0887】 (Claim 3) 【0888】 The system according to claim 1, further comprising an adjustment component that enables the speech recognition component and the speech synthesis component to support multiple languages ​​in order to support users in multiple languages. 【0889】 "Example 2 of combining an emotion engine" 【0890】 (Claim 1) 【0891】 A mechanism for receiving voice input from customers, 【0892】 A speech recognition mechanism that converts the aforementioned voice input into text data, 【0893】 An emotion recognition mechanism that analyzes the customer's emotional state from the aforementioned text data, 【0894】 A natural language processing mechanism that analyzes customer intent based on the aforementioned emotional state and text data, 【0895】 A response generation mechanism that generates appropriate response text based on the analyzed intentions and emotions, 【0896】 A speech synthesis mechanism that converts the aforementioned response text into speech data, 【0897】 A system including a device for transmitting the aforementioned voice data to a customer. 【0898】 (Claim 2) 【0899】 The system according to claim 1, comprising a learning mechanism that accumulates and analyzes customer feedback data to improve the accuracy of the natural language processing mechanism and the emotion recognition mechanism. 【0900】 (Claim 3) 【0901】 The system according to claim 1, further comprising an adjustment mechanism for enabling multilingual customer support by making the speech recognition mechanism and speech synthesis mechanism compatible with multiple languages, and an adjustment mechanism for enabling multilingual emotion recognition. 【0902】 "Application example 2 when combining with an emotional engine" 【0903】 (Claim 1) 【0904】 A means for receiving voice input, 【0905】 A conversion means for converting the aforementioned voice input into text data, 【0906】 An analysis means for analyzing the user's intent from the aforementioned text data, 【0907】 A generation means that generates appropriate response text based on the intentions and emotions analyzed by the aforementioned analysis means, 【0908】 A conversion means for converting the aforementioned response text into audio data, 【0909】 means for outputting the aforementioned audio data, 【0910】 A system that includes a means for providing security information. 【0911】 (Claim 2) 【0912】 The system according to claim 1, comprising a learning means for accumulating and analyzing feedback data to improve the accuracy of the analysis means. 【0913】 (Claim 3) 【0914】 The system according to claim 1, further comprising an adjustment means for making the conversion means compatible with multiple languages ​​in order to enable multilingual support. [Explanation of symbols] 【0915】 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

[Claim 1] A means of receiving voice input from customers, A speech recognition means that converts the aforementioned voice input into text data, A natural language processing means for analyzing customer intent from the aforementioned text data, A response generation means that generates appropriate response text based on the analyzed intent, A speech synthesis means that converts the aforementioned response text into speech data, A system including means for transmitting the aforementioned audio data to a customer. [Claim 2] The system according to claim 1, comprising a learning means for accumulating and analyzing customer feedback data and for improving the accuracy of the natural language processing means. [Claim 3] The system according to claim 1, further comprising adjustment means for enabling multilingual customer support by making the speech recognition means and speech synthesis means compatible with multiple languages.

Images