system

Abstract

We provide the system. [Solution] A speech recognition means that receives audio data and converts that audio data into text data, A natural language processing means that analyzes the aforementioned character data and summarizes and classifies the query content based on comparison with a pre-learned database, A response generation means that generates relevant answers based on the summary and classification, Verification means for confirming the accuracy of the generated response, A display means for presenting the confirmed answer on a display device, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] An object of the present invention is to provide a system that efficiently and accurately responds to various inquiries at an inquiry window. In conventional systems, manual response is mainly used, which requires a lot of time and labor, and furthermore, since the determination of the inquiry content is complicated, misunderstandings and inefficiencies are likely to occur. There is an increasing need for a technology that can solve such problems and respond to users quickly and accurately.

Means for Solving the Problems

[0005] This invention provides a system that converts speech data into text data using speech recognition means and summarizes and classifies inquiry content using natural language processing means. Furthermore, it guarantees the quality of the response by generating relevant answers using response generation means and verifying their accuracy with verification means. In this way, it enables quick and accurate responses at inquiry desks and improves operational efficiency.

[0006] "Speech recognition means" refers to a process or device for receiving speech data and converting it into text data.

[0007] "Natural language processing means" refers to a process or technique for analyzing character data, comparing it with a pre-trained database, and summarizing and classifying the content of a query.

[0008] "Response generation means" refers to a process or device for generating relevant answers based on the results of summarization and classification.

[0009] A "verification method" is a process or system for checking the accuracy and consistency of the generated responses and inspecting them for errors.

[0010] "Display means" refers to a display device or interface for presenting the confirmed answer to the user.

[0011] "Transmission means" refers to a process or device for transmitting audio data to an external system such as a cloud server via a network.

[0012] A "double-checking mechanism" is a process in which responses are re-evaluated, and the consistency of the responses is further verified using a pre-configured, rule-based system. [Brief explanation of the drawing]

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

Mode for Carrying Out the Invention

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described according to the accompanying drawings.

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

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

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

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

[0019] In the following embodiments, the numbered communication I / F (Interface) 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), etc.

[0020] 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."

[0021] [First Embodiment]

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

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0028] 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.

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

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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".

[0034] This invention provides a system for streamlining customer service at inquiry desks, and is implemented by combining speech recognition, natural language processing, and automated response generation. The elements necessary to implement this system are a terminal for processing user voice data, a server that connects to and processes the terminal via a network, and a means for the user to ultimately receive the response.

[0035] The user inputs their inquiry into the terminal using voice input. This voice data is sent from the terminal to the server. The server converts the received voice data into text data using speech recognition, and then analyzes the text data using natural language processing. In this analysis, the inquiry is summarized based on a pre-trained database and FAQs, and classified into the appropriate category.

[0036] Based on the analysis results, the server automatically generates an appropriate response using a response generation mechanism. The generated response is double-checked by a verification mechanism to confirm its accuracy and consistency. The final verified response is sent to the terminal via the network and presented to the user.

[0037] As a concrete example, consider a case where a user asks, "What is the product exchange policy?" The user inputs this via voice input through their device, and the server converts it into text data. The server analyzes this text using natural language processing and recognizes the keyword "exchange policy." As a result, it summarizes relevant information from FAQs and standards regarding exchanges and generates a response stating, "Exchanges are possible within 30 days of purchase." The generated response is double-checked to confirm its accuracy before being displayed on the user's device.

[0038] This system enables the automation and streamlining of customer inquiries, significantly reducing the workload.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] The user initiates voice input using the device. The user speaks their inquiry into the microphone, and the voice data is recorded on the device.

[0042] Step 2:

[0043] The device converts the recorded audio data into a digital format and sends it to the server via the network.

[0044] Step 3:

[0045] The server analyzes the received audio data using speech recognition and converts it into text data. This text data is then processed as basic information for the inquiry.

[0046] Step 4:

[0047] The server analyzes the converted text data using natural language processing techniques. Specifically, it summarizes the data and classifies it into categories based on a pre-trained database and FAQs.

[0048] Step 5:

[0049] Based on the analysis results, the server uses a response generation mechanism to create an appropriate answer. At this stage, it scrutinizes the most relevant information and generates a short but accurate response.

[0050] Step 6:

[0051] The server uses verification methods to double-check the consistency and accuracy of the generated responses. Responses are modified as needed, and a final confirmation is performed.

[0052] Step 7:

[0053] The server sends the fully verified response to the terminal. The terminal displays the received response to the user, allowing the user to review the content.

[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] The problem that this invention aims to solve is to improve the efficiency of responses at inquiry desks, optimize human resources, and provide accurate, consistent answers quickly.

[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 speech recognition means for receiving voice data and converting the voice data into text data; natural language processing means for analyzing the text data and summarizing and classifying the inquiry content based on comparison with stored information sources; and response generation means for generating relevant answers based on the summarization and classification. This makes it possible to automatically process the inquiry content and quickly provide accurate and consistent answers.

[0059] "Speech recognition means" refers to a technology that receives speech data and converts that speech data into text data.

[0060] "Natural language processing means" refers to technologies that analyze character data and summarize and classify query content based on comparison with stored information sources.

[0061] "Response generation means" refers to a technology that generates relevant responses based on summarized and categorized information.

[0062] A "verification method" is a technique for confirming the accuracy of the generated response based on a set of criteria.

[0063] "Presentation means" refers to the technology for presenting the confirmed answer to an output device.

[0064] "Transfer means" refers to a technology for transmitting voice data received by a voice recognition means to an external processing device via a communication network.

[0065] A "verification method" is a technique that uses a set of rule-based structures to organize the consistency of responses.

[0066] This invention is implemented as a system to streamline customer service inquiries. The basic elements of this system include a terminal for user voice input, a server for processing the voice, and means for returning information to the user.

[0067] The user inputs their inquiry by voice using the microphone on their device. This voice data is temporarily stored on the device and sent via the communication network to an external processing unit, the server.

[0068] The server uses speech recognition software to convert audio data into text data. Speech recognition employs technology that accurately converts audio data into text.

[0069] Subsequently, the server uses a generative AI model to process the text data using natural language. Specifically, it analyzes, summarizes, and classifies the inquiry based on comparison with stored information sources. An example of a prompt at this stage would be: "Generate the best answer to the user's question: 'What is the product exchange policy?'"

[0070] Based on the analyzed data, the server uses response generation means to create relevant answers. The generated answers are verified for accuracy and consistency through verification means. Once verification is complete, the answers are sent by the server to the terminal and presented to the user.

[0071] This system allows users to receive quick and accurate answers, streamlining the inquiry process. For example, if a user asks, "What is the product exchange policy?", the generated answer will provide specific information such as, "Exchanges are possible within 30 days of purchase."

[0072] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0073] Step 1:

[0074] The user performs voice input on the device. When the user speaks their inquiry through the microphone, the device captures the audio data. The input is the user's voice data, and the output is a digital file containing that audio data.

[0075] Step 2:

[0076] The terminal transmits the captured audio data to the server via the communication network. The input is an audio digital file, and the server's reception is the output. Data transmission processing takes place here.

[0077] Step 3:

[0078] The server uses speech recognition software to convert received audio data into text data. Specifically, the server analyzes the audio data and converts it into a single text string. The input is an audio digital file, and the output is text data containing the audio content.

[0079] Step 4:

[0080] The server performs natural language processing using a generative AI model. In this step, the server processes text data as prompt sentences and performs analysis, summarization, and classification. The input is text data obtained through speech recognition, and the output is the analyzed summary information and its classification results.

[0081] Step 5:

[0082] The server uses a response generation mechanism based on the analysis results to generate an appropriate answer. In this step, the server utilizes a generation AI model to create an answer by matching it with information in the database. The input is the analyzed text data, and the output is the text of the generated answer.

[0083] Step 6:

[0084] The server verifies the generated responses using validation mechanisms. Specifically, it checks the accuracy and consistency of the generated responses and makes corrections as needed. The input is the generated response text, and the output is the validated response text.

[0085] Step 7:

[0086] The server transmits the verified response to the terminal via the communication network and presents it to the user. The input is the verified response text, and the output is the response information displayed on the terminal. In this step, the display process is performed so that the user can receive the response.

[0087] (Application Example 1)

[0088] 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."

[0089] Conventional inquiry handling systems have struggled to efficiently process voice input and provide users with quick and accurate answers. In particular, inquiries via portable devices require ensuring portability and real-time capabilities while guaranteeing accuracy and consistency in responses. This necessitates improvements in both user experience and operational efficiency.

[0090] 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.

[0091] In this invention, the server includes speech recognition means for receiving voice data and converting it into text data, natural language processing means for analyzing the text data and summarizing and classifying the query content, and information generation means for generating relevant responses. This makes it possible to provide accurate responses in real time to voice queries via portable devices.

[0092] "Speech recognition means" refers to technology that receives speech data and performs the process of converting it into text data.

[0093] "Natural language processing means" refers to techniques that analyze received character data and summarize and classify the content of inquiries based on a pre-learned knowledge base.

[0094] "Information generation means" refers to technology that automatically generates relevant responses based on data summarized and classified by natural language processing.

[0095] "Verification means" refers to techniques for performing processes to confirm the accuracy and consistency of the generated response.

[0096] "Display means" refers to a device or system for presenting a confirmed response to the user.

[0097] "Application program means for portable devices" refers to a technology for installing a program on a portable device that processes voice inquiries and immediately presents relevant information.

[0098] The system realizing this invention uses a speech recognition means that receives user voice data and converts it into text data. By utilizing the Google® Speech Recognition API, highly accurate conversion to text data is possible. Users make inquiries by voice using a portable device, such as a smartphone.

[0099] The terminal sends the text data converted by speech recognition to the server. The server analyzes the text data using natural language processing and compares it with a pre-trained knowledge base. Possible technologies used for this include machine learning libraries such as TENSORFLOW® and PyTorch. The analyzed data is processed by information generation tools that accurately summarize the query and generate relevant responses.

[0100] The generated response is verified for accuracy and consistency by a validation mechanism within the server. This validation mechanism employs a rule-based system to check whether the response content conforms to predefined criteria.

[0101] Finally, the confirmed response is presented to the user via a display on a portable device. The user can immediately obtain the necessary information, for example, in response to the inquiry "What is the return period for the product?", they can receive a specific answer such as "You can return the product within 30 days of purchase."

[0102] An example of a prompt message might be, "The user has asked a question about a product. Find the most relevant FAQ and generate an answer based on that information." This allows the system to generate an appropriate response and provide information to the user quickly.

[0103] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0104] Step 1:

[0105] The user makes a voice inquiry using a portable device. The input is the user's voice data. The device receives this voice data and converts it into text data using a speech recognition API. The output is the converted text data.

[0106] Step 2:

[0107] The terminal sends the text data obtained through speech recognition to the server. It receives text data as input and forwards it to the server. The output is the text data sent to the server.

[0108] Step 3:

[0109] The server receives text data and performs natural language processing. Here, it analyzes the text data using a generative AI model such as TensorFlow. As input, the server receives text data, summarizes the query, and performs classification. The output is the summarized and classified data.

[0110] Step 4:

[0111] The server generates relevant responses using information generation tools based on summarized and classified data. The input is classified data, and an AI model is used to automatically generate appropriate responses as output. Specifically, this involves matching data against an FAQ database.

[0112] Step 5:

[0113] The generated response is verified for accuracy and consistency within the server using validation mechanisms. The generated response is received as input, and its conformance to the criteria is checked using a rule-based system. The output is the verified, accurate response.

[0114] Step 6:

[0115] The server sends the confirmed response back to the terminal. The input is the verified response, which is then sent to the terminal. The output is the response presented to the terminal.

[0116] Step 7:

[0117] The terminal presents the final response to the user. It receives the response sent from the server as input and displays it visually to the user. The output is the response information received by the user.

[0118] 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.

[0119] This invention provides a system that enables more personalized responses by recognizing user emotions and reflecting that information in response generation. This system integrates speech recognition, natural language processing, and emotion recognition to generate appropriate and emotionally resonant answers to user inquiries.

[0120] The user inputs their inquiry into the terminal using voice. This voice data is transmitted from the terminal to the server via the network. The server first converts the voice data into text data using speech recognition. The converted text data is then analyzed by natural language processing to summarize the inquiry and classify it based on a pre-trained database.

[0121] Furthermore, the server analyzes text and audio data using an emotion engine to recognize the user's emotional state. Based on the results of the emotion recognition, the response generation system generates a response with a tone and content appropriate to the user's emotions. For example, if the user is showing signs of anxiety, the server will create a response in a reassuring tone.

[0122] The generated responses are verified by a validation system with a double-check function. Here, the accuracy of the response and whether it is expressed appropriately for the desired emotion are evaluated. The verified responses are sent from the server to the terminal and presented to the user. User feedback on the displayed responses is also evaluated by the emotion engine and used to improve subsequent response generation.

[0123] For example, if a user makes an inquiry in an anxious tone saying, "My recent order hasn't arrived," the emotion engine recognizes that anxiety. The server then generates a reassuring response, such as, "We apologize for the inconvenience. We have checked the shipping status and expect to deliver it tomorrow, so please rest assured," and presents it to the user.

[0124] This system allows for personalized responses that are empathetic to the user's emotions, rather than simply providing mechanical answers, thereby improving customer satisfaction with inquiries.

[0125] The following describes the processing flow.

[0126] Step 1:

[0127] The user initiates voice input using the device. As the user speaks their inquiry, the device records the voice and generates digital audio data.

[0128] Step 2:

[0129] The device transmits the recorded digital audio data to the server via the network.

[0130] Step 3:

[0131] The server analyzes the received audio data using speech recognition and converts it into text data. This text data forms the basis for subsequent processing.

[0132] Step 4:

[0133] The server analyzes the converted character data using natural language processing tools, summarizes the query content, and classifies it into categories by comparing it with a pre-trained database.

[0134] Step 5:

[0135] The server further analyzes the voice and text data using an emotion engine to recognize the emotions the user is expressing. In this step, emotions are detected, for example, from the user's tone of voice and word choice.

[0136] Step 6:

[0137] The server considers the results of the emotion engine and uses response generation means to generate a response that is sensitive to the user's emotions. For example, if an emotion seeking reassurance is recognized, a response in a gentle tone will be created.

[0138] Step 7:

[0139] The server double-checks the generated responses using verification tools to ensure their accuracy and appropriate expression of sentiment. If no problems are found, the verification is complete.

[0140] Step 8:

[0141] The server sends the verified response to the terminal. The terminal displays the result to the user, allowing the user to visually confirm the response.

[0142] Step 9:

[0143] The user reviews the displayed response and, if they wish to provide feedback, enters their opinion into the device. The device sends this feedback to the server, which helps optimize the sentiment engine and other processes.

[0144] (Example 2)

[0145] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0146] Conventional systems could convert voice data into text data and generate general responses, but they had the challenge of not being able to provide individualized responses that were sensitive to the user's emotions. Specifically, the responses were uniform, and responses were not provided in an appropriate tone or content that matched the user's emotional state, resulting in a failure to sufficiently improve user satisfaction.

[0147] 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.

[0148] In this invention, the server includes speech recognition means for converting speech data into text data, natural language processing means for analyzing, summarizing, and classifying the text data, and emotion recognition means for recognizing an individual's emotional state from the text data and speech data. This enables personalized responses adapted to the user's emotions, thereby improving user satisfaction with inquiries.

[0149] "Audio data" refers to digital data that contains information transmitted through sound.

[0150] "Text data" refers to information expressed in string format, which is a converted form of audio data.

[0151] "Speech recognition means" refers to the function of a device or software for converting speech data into text data.

[0152] "Natural language processing means" refers to a technology or function that analyzes character data to summarize and classify the content of a query.

[0153] "Emotion recognition means" refers to a technology or function that identifies a user's emotional state based on text data and audio data.

[0154] "Response generation means" refers to a technology or function that generates relevant responses based on an individual's emotional state.

[0155] "Verification means" refers to techniques or functions for verifying the accuracy and emotional appropriateness of the generated responses.

[0156] "Display means" refers to a device or function for presenting the confirmed answer to the user.

[0157] "Transmission means" refers to a technology or function for transferring audio data to another device via a network.

[0158] A "double-checking method" is a technique that re-evaluates the results of natural language processing to confirm its consistency and adaptability to emotions.

[0159] The system of this invention starts with the user making an inquiry by voice. First, the user inputs a question or inquiry as voice into a terminal. The terminal receives this voice data and transmits it to a server via a communication network. The voice data arrives at the server in digital format.

[0160] The server uses high-precision speech recognition technology to convert speech data into text data. Technologies such as a "speech recognition API" can be used here. This text data serves to record the content of the user's speech.

[0161] Next, the server analyzes the generated text data using natural language processing techniques. This natural language processing uses software such as a "language processing engine" to summarize the utterances and classify them based on comparisons with pre-learned information sources and materials.

[0162] Furthermore, voice and text data are analyzed using emotion recognition technology. The server uses an "emotion analysis engine" to determine the user's emotions. This makes it possible to recognize what emotions the user is experiencing, such as anxiety, joy, or anger.

[0163] Based on the results of emotion recognition, the server uses a generative AI model to generate a response. For example, it uses a "generative AI engine" to construct a response with a tone and content that takes the user's emotions into consideration. If the user is showing signs of anxiety, it can generate a response that provides reassurance.

[0164] The generated responses are verified through a validation process to check their accuracy and whether they retain appropriate emotional expression. This double-check function ensures the quality of the responses.

[0165] Finally, the server sends the verified response to the terminal and displays it to the user. The user can then review the provided response on their terminal. The user can also provide feedback on the received response, which will be used to improve the system in the future.

[0166] For example, a user might inquire in a worried tone that their recent order hasn't arrived. In this case, the system would generate a reassuring response such as, "We've checked the shipping status and it's expected to arrive tomorrow, so please don't worry."

[0167] Example prompt to input into the generation AI model: "If a user inquires in an anxious tone that 'my recent order hasn't arrived,' how should the system generate a reassuring response?"

[0168] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0169] Step 1:

[0170] The user inputs their inquiry into the terminal using voice. The terminal receives this voice data as a digital signal and sends it to a server in the cloud system. In this step, the user's voice is the starting point for processing.

[0171] Step 2:

[0172] When the server receives audio data, it uses speech recognition to convert the digital audio into text data. For example, a "speech recognition engine" is used to analyze the audio waveform and convert it into corresponding text. This converted text data then becomes the input for the next process.

[0173] Step 3:

[0174] The server inputs the converted character data into a natural language processing system for analysis. This process utilizes "language processing software" to summarize the content and perform classification based on a pre-trained database. As a result of the analysis, a summary and classification of the query are obtained.

[0175] Step 4:

[0176] The server processes the parsed text data and the original audio data through an emotion recognition system. Here, an emotion analysis engine is used to evaluate the user's emotional state. Through emotion analysis, specific emotion labels, such as anxiety or joy, are output.

[0177] Step 5:

[0178] The server generates a response using a generative AI model based on the result of the emotional state. In this step, the response generation algorithm is applied to construct a response with a tone and content that resonates with the individual's emotions. The output of this generation process is an emotionally appropriate response text.

[0179] Step 6:

[0180] The server passes the generated response to a verification system for a double-check of its accuracy and sentiment appropriateness. A virtual verification system is used to ensure the response is indeed appropriate. Through verification, a quality-assured response is confirmed.

[0181] Step 7:

[0182] Confirmed responses are sent from the server to the terminal. The terminal displays this response to the user. The user can then review the response displayed on the terminal and take action based on its content.

[0183] Step 8:

[0184] Users send feedback on the provided responses to the server via their device. The server receives this feedback, performs sentiment analysis again, and uses it to improve the response generation process. Through this process, the system continuously evolves, enabling more emotionally resonant responses.

[0185] (Application Example 2)

[0186] 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".

[0187] Conventional systems only received voice data and provided automated responses to inquiries, making it difficult to provide personalized support that took into account the user's emotional state. As a result, there was a problem of decreased user satisfaction with the resolution of their anxieties and questions.

[0188] 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.

[0189] In this invention, the server includes speech recognition means for converting speech data into text data, means for summarizing and classifying the text data using natural language processing, and emotion recognition means for recognizing the user's emotions and adjusting the tone and content of the response. This makes it possible to provide flexible and appropriate responses that are sensitive to the user's emotions.

[0190] "Speech recognition means" refers to a technology that converts speech data into text data, and is a means for analyzing a user's speech as text information.

[0191] "Natural language processing means" refers to technologies that analyze input character data and summarize or classify the content of inquiries by referring to a pre-trained database.

[0192] "Response generation means" refers to a technology for generating relevant responses based on summarized and categorized information.

[0193] "Emotion recognition means" refers to a technology that analyzes the user's text and voice data to identify their emotional state and reflect it in response generation.

[0194] "Verification means" are methods for confirming the accuracy and emotional relevance of generated responses, and are techniques for evaluating whether they are appropriate responses.

[0195] "Display means" refers to a device or function for presenting confirmed answers to the user.

[0196] "Transmission means" refers to the function of sending audio data received by the speech recognition means to a cloud server via the network.

[0197] A "double-checking method" is a system used to further re-evaluate the consistency of answers obtained through natural language processing.

[0198] This invention is a system that generates responses that are in line with the user's emotional state. The system consists of speech recognition means, natural language processing means, emotion recognition means, response generation means, verification means, display means, and transmission means.

[0199] First, the device receives voice input from the user. This voice data is converted into text data using speech recognition software. For example, Google's speech recognition API is used for this speech recognition.

[0200] The server analyzes text data using natural language processing (NLP) methods to summarize and classify the query content. It can utilize natural language processing technologies such as IBM Watson® and Google NLP API.

[0201] Furthermore, as a means of emotion recognition, the system analyzes text data and voice features to recognize the user's emotional state. This process utilizes emotion recognition APIs included in Microsoft® Azure® Cognitive Services, among others.

[0202] The response generation mechanism generates a response with appropriate tone and content based on the recognized emotion. This generation can utilize AI models such as OpenAI®.

[0203] The generated responses are verified for accuracy and emotional relevance through validation methods. A rule-based system is applied for this verification.

[0204] Finally, the verified answers are presented to the user's device through a display mechanism.

[0205] For example, if a user inquires in an anxious tone that "my recent order hasn't arrived," emotion recognition identifies "anxiety." The server then generates a response such as, "We apologize for the inconvenience. We have checked the shipping status and expect to deliver it tomorrow, so please rest assured," and presents it to the user.

[0206] Examples of prompts for a generative AI model are as follows:

[0207] "Voice input from user: 'My recent order hasn't arrived.' Emotion recognition: Anxiety Generated response: 'We apologize for the inconvenience. We have checked the shipping status and expect it to arrive tomorrow, so please rest assured.'"

[0208] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0209] Step 1:

[0210] The user inputs their inquiry into the terminal using voice. This voice data is received by the terminal as input. The user's voice is captured as a digital signal through the microphone.

[0211] Step 2:

[0212] The terminal sends the received audio data to the server. The transmitted audio data arrives at the server as input. The server prepares to start the speech recognition process by receiving the audio data over the network.

[0213] Step 3:

[0214] The server converts audio data into text data using speech recognition technology. The input audio data is analyzed and converted into text data. For example, the process of converting an audio waveform to text is performed using Google's speech recognition API.

[0215] Step 4:

[0216] The server analyzes the text data using natural language processing tools to summarize and classify the query content. In this process, the input text data undergoes the following processing and classification: The server uses natural language processing algorithms (e.g., IBM Watson) to extract important keywords and phrases and identify the content of the query.

[0217] Step 5:

[0218] The server analyzes text and audio data using emotion recognition tools to recognize the user's emotional state. In this process, the input data is analyzed using an emotion recognition API (e.g., Microsoft Azure Cognitive Services), and the emotional state (e.g., anxiety, joy) is output.

[0219] Step 6:

[0220] The server generates a response using a response generation mechanism based on the recognized emotion. In this step, the emotional state and summarized inquiry content are inputs, and the response content is generated using a generation AI model (e.g., OpenAI). The output is an appropriate response in a context that aligns with the emotion.

[0221] Step 7:

[0222] The server verifies the accuracy and sentiment relevance of the generated responses using verification mechanisms. This verification uses a rule-based system to determine whether the generated responses are appropriate. Based on the verification process, verified responses are output.

[0223] Step 8:

[0224] The server sends the verified response to the terminal, which is then presented to the user via a display device. The user can then receive the final response and verify the information on the terminal screen.

[0225] 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.

[0226] 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.

[0227] 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.

[0228] [Second Embodiment]

[0229] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0230] 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.

[0231] 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).

[0232] 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.

[0233] 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.

[0234] 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).

[0235] 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.

[0236] 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.

[0237] 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.

[0238] 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.

[0239] 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.

[0240] 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".

[0241] This invention provides a system for streamlining customer service at inquiry desks, and is implemented by combining speech recognition, natural language processing, and automated response generation. The elements necessary to implement this system are a terminal for processing user voice data, a server that connects to and processes the terminal via a network, and a means for the user to ultimately receive the response.

[0242] The user inputs their inquiry into the terminal using voice input. This voice data is sent from the terminal to the server. The server converts the received voice data into text data using speech recognition, and then analyzes the text data using natural language processing. In this analysis, the inquiry is summarized based on a pre-trained database and FAQs, and classified into the appropriate category.

[0243] Based on the analysis results, the server automatically generates an appropriate response using a response generation mechanism. The generated response is double-checked by a verification mechanism to confirm its accuracy and consistency. The final verified response is sent to the terminal via the network and presented to the user.

[0244] As a concrete example, consider a case where a user asks, "What is the product exchange policy?" The user inputs this via voice input through their device, and the server converts it into text data. The server analyzes this text using natural language processing and recognizes the keyword "exchange policy." As a result, it summarizes relevant information from FAQs and standards regarding exchanges and generates a response stating, "Exchanges are possible within 30 days of purchase." The generated response is double-checked to confirm its accuracy before being displayed on the user's device.

[0245] This system enables the automation and streamlining of customer inquiries, significantly reducing the workload.

[0246] The following describes the processing flow.

[0247] Step 1:

[0248] The user initiates voice input using the device. The user speaks their inquiry into the microphone, and the voice data is recorded on the device.

[0249] Step 2:

[0250] The device converts the recorded audio data into a digital format and sends it to the server via the network.

[0251] Step 3:

[0252] The server analyzes the received audio data using speech recognition and converts it into text data. This text data is then processed as basic information for the inquiry.

[0253] Step 4:

[0254] The server analyzes the converted text data using natural language processing techniques. Specifically, it summarizes the data and classifies it into categories based on a pre-trained database and FAQs.

[0255] Step 5:

[0256] Based on the analysis results, the server uses a response generation mechanism to create an appropriate answer. At this stage, it scrutinizes the most relevant information and generates a short but accurate response.

[0257] Step 6:

[0258] The server uses verification methods to double-check the consistency and accuracy of the generated responses. Responses are modified as needed, and a final confirmation is performed.

[0259] Step 7:

[0260] The server sends the fully verified response to the terminal. The terminal displays the received response to the user, allowing the user to review the content.

[0261] (Example 1)

[0262] 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."

[0263] The problem that this invention aims to solve is to improve the efficiency of responses at inquiry desks, optimize human resources, and provide accurate, consistent answers quickly.

[0264] 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.

[0265] In this invention, the server includes speech recognition means for receiving voice data and converting the voice data into text data; natural language processing means for analyzing the text data and summarizing and classifying the inquiry content based on comparison with stored information sources; and response generation means for generating relevant answers based on the summarization and classification. This makes it possible to automatically process the inquiry content and quickly provide accurate and consistent answers.

[0266] "Speech recognition means" refers to a technology that receives speech data and converts that speech data into text data.

[0267] "Natural language processing means" refers to technologies that analyze character data and summarize and classify query content based on comparison with stored information sources.

[0268] "Response generation means" refers to a technology that generates relevant responses based on summarized and categorized information.

[0269] A "verification method" is a technique for confirming the accuracy of the generated response based on a set of criteria.

[0270] "Presentation means" refers to the technology for presenting the confirmed answer to an output device.

[0271] "Transfer means" refers to a technology for transmitting voice data received by a voice recognition means to an external processing device via a communication network.

[0272] A "verification method" is a technique that uses a set of rule-based structures to organize the consistency of responses.

[0273] This invention is implemented as a system to streamline customer service inquiries. The basic elements of this system include a terminal for user voice input, a server for processing the voice, and means for returning information to the user.

[0274] The user inputs their inquiry by voice using the microphone on their device. This voice data is temporarily stored on the device and sent via the communication network to an external processing unit, the server.

[0275] The server uses speech recognition software to convert audio data into text data. Speech recognition employs technology that accurately converts audio data into text.

[0276] Subsequently, the server uses a generative AI model to process the text data using natural language. Specifically, it analyzes, summarizes, and classifies the inquiry based on comparison with stored information sources. An example of a prompt at this stage would be: "Generate the best answer to the user's question: 'What is the product exchange policy?'"

[0277] Based on the analyzed data, the server uses response generation means to create relevant answers. The generated answers are verified for accuracy and consistency through verification means. Once verification is complete, the answers are sent by the server to the terminal and presented to the user.

[0278] This system allows users to receive quick and accurate answers, streamlining the inquiry process. For example, if a user asks, "What is the product exchange policy?", the generated answer will provide specific information such as, "Exchanges are possible within 30 days of purchase."

[0279] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0280] Step 1:

[0281] The user performs voice input on the terminal. When the user speaks the inquiry content via the microphone, the voice data is captured by the terminal. The input is the user's voice data, and the output is a digital file containing the voice data.

[0282] Step 2:

[0283] The terminal transmits the captured voice data to the server via the communication network. The input is the voice digital file, and the reception by the server is the output. Here, the data transmission process is performed.

[0284] Step 3:

[0285] The server uses voice recognition software to convert the received voice data into character data. Specifically, the server analyzes the voice data and makes it into a single text string. The input is the voice digital file, and the output is the character data containing the voice content.

[0286] Step 4:

[0287] The server performs natural language processing using the generative AI model. In this step, the server processes the character data as a prompt sentence and performs analysis, summarization, and classification. The input is the character data obtained by voice recognition, and the output is the analyzed summary information and its classification result.

[0288] Step 5:

[0289] The server uses the response generation means based on the analysis result to generate an appropriate answer. In this step, the server utilizes the generative AI model to collate with the information in the database to create an answer. The input is the analyzed text data, and the output is the text of the generated answer.

[0290] Step 6:

[0291] The server verifies the generated responses using validation mechanisms. Specifically, it checks the accuracy and consistency of the generated responses and makes corrections as needed. The input is the generated response text, and the output is the validated response text.

[0292] Step 7:

[0293] The server transmits the verified response to the terminal via the communication network and presents it to the user. The input is the verified response text, and the output is the response information displayed on the terminal. In this step, the display process is performed so that the user can receive the response.

[0294] (Application Example 1)

[0295] 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."

[0296] Conventional inquiry handling systems have struggled to efficiently process voice input and provide users with quick and accurate answers. In particular, inquiries via portable devices require ensuring portability and real-time capabilities while guaranteeing accuracy and consistency in responses. This necessitates improvements in both user experience and operational efficiency.

[0297] 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.

[0298] In this invention, the server includes speech recognition means for receiving voice data and converting it into text data, natural language processing means for analyzing the text data and summarizing and classifying the query content, and information generation means for generating relevant responses. This makes it possible to provide accurate responses in real time to voice queries via portable devices.

[0299] "Speech recognition means" refers to technology that receives speech data and performs the process of converting it into text data.

[0300] "Natural language processing means" refers to techniques that analyze received character data and summarize and classify the content of inquiries based on a pre-learned knowledge base.

[0301] "Information generation means" refers to technology that automatically generates relevant responses based on data summarized and classified by natural language processing.

[0302] "Verification means" refers to techniques for performing processes to confirm the accuracy and consistency of the generated response.

[0303] "Display means" refers to a device or system for presenting a confirmed response to the user.

[0304] "Application program means for portable devices" refers to a technology for installing a program on a portable device that processes voice inquiries and immediately presents relevant information.

[0305] The system realizing this invention uses a speech recognition means that receives user voice data and converts it into text data. By utilizing the Google Speech Recognition API for speech recognition, highly accurate conversion to text data is possible. Users make inquiries by voice using a portable device, such as a smartphone.

[0306] The terminal sends the text data converted by speech recognition to the server. The server analyzes the text data using natural language processing tools and compares it with a pre-trained knowledge base. Possible technologies used for this include machine learning libraries such as TensorFlow and PyTorch. The analyzed data is then processed by information generation tools that accurately summarize the query and generate relevant responses.

[0307] The generated response is verified for accuracy and consistency by the verification means within the server. A rule-based system is introduced as the verification means to check whether the response content conforms to the pre-defined criteria.

[0308] Finally, the verified response is presented to the user via the display means of the portable device. The user can immediately obtain the necessary information. For example, for a query such as "What is the return deadline for the product?", a specific answer like "Returns are possible within 30 days from the date of purchase" can be obtained.

[0309] As an example of the prompt text, "The user has asked a question about the product. Search for the most relevant FAQ and generate an answer based on that information." can be considered. This enables the system to appropriately generate a response and quickly provide information to the user.

[0310] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0311] Step 1:

[0312] The user makes an inquiry by voice using the portable device. As input, the user's voice data is obtained. The terminal receives this voice data and converts it into character data using the speech recognition API. The output is the converted character data.

[0313] Step 2:

[0314] The terminal transmits the character data obtained by speech recognition to the server. An operation of receiving the character data as input and transferring it to the server is performed. The output is the character data transmitted to the server.

[0315] Step 3:

[0316] The server receives text data and performs natural language processing. Here, it analyzes the text data using a generative AI model such as TensorFlow. As input, the server receives text data, summarizes the query, and performs classification. The output is the summarized and classified data.

[0317] Step 4:

[0318] The server generates relevant responses using information generation tools based on summarized and classified data. The input is classified data, and an AI model is used to automatically generate appropriate responses as output. Specifically, this involves matching data against an FAQ database.

[0319] Step 5:

[0320] The generated response is verified for accuracy and consistency within the server using validation mechanisms. The generated response is received as input, and its conformance to the criteria is checked using a rule-based system. The output is the verified, accurate response.

[0321] Step 6:

[0322] The server sends the confirmed response back to the terminal. The input is the verified response, which is then sent to the terminal. The output is the response presented to the terminal.

[0323] Step 7:

[0324] The terminal presents the final response to the user. It receives the response sent from the server as input and displays it visually to the user. The output is the response information received by the user.

[0325] 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.

[0326] This invention provides a system that enables more personalized responses by recognizing user emotions and reflecting that information in response generation. This system integrates speech recognition, natural language processing, and emotion recognition to generate appropriate and emotionally resonant answers to user inquiries.

[0327] The user inputs their inquiry into the terminal using voice. This voice data is transmitted from the terminal to the server via the network. The server first converts the voice data into text data using speech recognition. The converted text data is then analyzed by natural language processing to summarize the inquiry and classify it based on a pre-trained database.

[0328] Furthermore, the server analyzes text and audio data using an emotion engine to recognize the user's emotional state. Based on the results of the emotion recognition, the response generation system generates a response with a tone and content appropriate to the user's emotions. For example, if the user is showing signs of anxiety, the server will create a response in a reassuring tone.

[0329] The generated responses are verified by a validation system with a double-check function. Here, the accuracy of the response and whether it is expressed appropriately for the desired emotion are evaluated. The verified responses are sent from the server to the terminal and presented to the user. User feedback on the displayed responses is also evaluated by the emotion engine and used to improve subsequent response generation.

[0330] For example, if a user makes an inquiry in an anxious tone saying, "My recent order hasn't arrived," the emotion engine recognizes that anxiety. The server then generates a reassuring response, such as, "We apologize for the inconvenience. We have checked the shipping status and expect to deliver it tomorrow, so please rest assured," and presents it to the user.

[0331] This system allows for personalized responses that are empathetic to the user's emotions, rather than simply providing mechanical answers, thereby improving customer satisfaction with inquiries.

[0332] The following describes the processing flow.

[0333] Step 1:

[0334] The user initiates voice input using the device. As the user speaks their inquiry, the device records the voice and generates digital audio data.

[0335] Step 2:

[0336] The device transmits the recorded digital audio data to the server via the network.

[0337] Step 3:

[0338] The server analyzes the received audio data using speech recognition and converts it into text data. This text data forms the basis for subsequent processing.

[0339] Step 4:

[0340] The server analyzes the converted character data using natural language processing tools, summarizes the query content, and classifies it into categories by comparing it with a pre-trained database.

[0341] Step 5:

[0342] The server further analyzes the voice and text data using an emotion engine to recognize the emotions the user is expressing. In this step, emotions are detected, for example, from the user's tone of voice and word choice.

[0343] Step 6:

[0344] The server considers the results of the emotion engine and uses response generation means to generate a response that is sensitive to the user's emotions. For example, if an emotion seeking reassurance is recognized, a response in a gentle tone will be created.

[0345] Step 7:

[0346] The server double-checks the generated responses using verification tools to ensure their accuracy and appropriate expression of sentiment. If no problems are found, the verification is complete.

[0347] Step 8:

[0348] The server sends the verified response to the terminal. The terminal displays the result to the user, allowing the user to visually confirm the response.

[0349] Step 9:

[0350] The user reviews the displayed response and, if they wish to provide feedback, enters their opinion into the device. The device sends this feedback to the server, which helps optimize the sentiment engine and other processes.

[0351] (Example 2)

[0352] 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".

[0353] Conventional systems could convert voice data into text data and generate general responses, but they had the challenge of not being able to provide individualized responses that were sensitive to the user's emotions. Specifically, the responses were uniform, and responses were not provided in an appropriate tone or content that matched the user's emotional state, resulting in a failure to sufficiently improve user satisfaction.

[0354] 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.

[0355] In this invention, the server includes speech recognition means for converting speech data into text data, natural language processing means for analyzing, summarizing, and classifying the text data, and emotion recognition means for recognizing an individual's emotional state from the text data and speech data. This enables personalized responses adapted to the user's emotions, thereby improving user satisfaction with inquiries.

[0356] "Audio data" refers to digital data that contains information transmitted through sound.

[0357] "Text data" refers to information expressed in string format, which is a converted form of audio data.

[0358] "Speech recognition means" refers to the function of a device or software for converting speech data into text data.

[0359] "Natural language processing means" refers to a technology or function that analyzes character data to summarize and classify the content of a query.

[0360] "Emotion recognition means" refers to a technology or function that identifies a user's emotional state based on text data and audio data.

[0361] "Response generation means" refers to a technology or function that generates relevant responses based on an individual's emotional state.

[0362] "Verification means" refers to techniques or functions for verifying the accuracy and emotional appropriateness of the generated responses.

[0363] "Display means" refers to a device or function for presenting the confirmed answer to the user.

[0364] "Transmission means" refers to a technology or function for transferring audio data to another device via a network.

[0365] A "double-checking method" is a technique that re-evaluates the results of natural language processing to confirm its consistency and adaptability to emotions.

[0366] The system of this invention starts with the user making an inquiry by voice. First, the user inputs a question or inquiry as voice into a terminal. The terminal receives this voice data and transmits it to a server via a communication network. The voice data arrives at the server in digital format.

[0367] The server uses high-precision speech recognition technology to convert speech data into text data. Technologies such as a "speech recognition API" can be used here. This text data serves to record the content of the user's speech.

[0368] Next, the server analyzes the generated text data using natural language processing techniques. This natural language processing uses software such as a "language processing engine" to summarize the utterances and classify them based on comparisons with pre-learned information sources and materials.

[0369] Furthermore, voice and text data are analyzed using emotion recognition technology. The server uses an "emotion analysis engine" to determine the user's emotions. This makes it possible to recognize what emotions the user is experiencing, such as anxiety, joy, or anger.

[0370] Based on the results of emotion recognition, the server uses a generative AI model to generate a response. For example, it uses a "generative AI engine" to construct a response with a tone and content that takes the user's emotions into consideration. If the user is showing signs of anxiety, it can generate a response that provides reassurance.

[0371] The generated responses are verified through a validation process to check their accuracy and whether they retain appropriate emotional expression. This double-check function ensures the quality of the responses.

[0372] Finally, the server sends the verified response to the terminal and displays it to the user. The user can then review the provided response on their terminal. The user can also provide feedback on the received response, which will be used to improve the system in the future.

[0373] For example, a user might inquire in a worried tone that their recent order hasn't arrived. In this case, the system would generate a reassuring response such as, "We've checked the shipping status and it's expected to arrive tomorrow, so please don't worry."

[0374] Example prompt text to input into the generation AI model: "If a user inquires in an anxious tone that 'my recent order hasn't arrived,' how should the system generate a reassuring response?"

[0375] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0376] Step 1:

[0377] The user inputs their inquiry into the terminal using voice. The terminal receives this voice data as a digital signal and sends it to a server in the cloud system. In this step, the user's voice is the starting point for processing.

[0378] Step 2:

[0379] When the server receives audio data, it uses speech recognition to convert the digital audio into text data. For example, a "speech recognition engine" is used to analyze the audio waveform and convert it into corresponding text. This converted text data then becomes the input for the next process.

[0380] Step 3:

[0381] The server inputs the converted character data into a natural language processing system for analysis. This process utilizes "language processing software" to summarize the content and perform classification based on a pre-trained database. As a result of the analysis, a summary and classification of the query are obtained.

[0382] Step 4:

[0383] The server processes the parsed text data and the original audio data through an emotion recognition system. Here, an emotion analysis engine is used to evaluate the user's emotional state. Through emotion analysis, specific emotion labels, such as anxiety or joy, are output.

[0384] Step 5:

[0385] The server generates a response using a generative AI model based on the result of the emotional state. In this step, the response generation algorithm is applied to construct a response with a tone and content that resonates with the individual's emotions. The output of this generation process is an emotionally appropriate response text.

[0386] Step 6:

[0387] The server passes the generated response to a verification system for a double-check of its accuracy and sentiment appropriateness. A virtual verification system is used to ensure the response is indeed appropriate. Through verification, a quality-assured response is confirmed.

[0388] Step 7:

[0389] Confirmed responses are sent from the server to the terminal. The terminal displays this response to the user. The user can then review the response displayed on the terminal and take action based on its content.

[0390] Step 8:

[0391] Users send feedback on the provided responses to the server via their device. The server receives this feedback, performs sentiment analysis again, and uses it to improve the response generation process. Through this process, the system continuously evolves, enabling more emotionally resonant responses.

[0392] (Application Example 2)

[0393] 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."

[0394] Conventional systems only received voice data and provided automated responses to inquiries, making it difficult to provide personalized support that took into account the user's emotional state. As a result, there was a problem of decreased user satisfaction with the resolution of their anxieties and questions.

[0395] 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.

[0396] In this invention, the server includes speech recognition means for converting speech data into text data, means for summarizing and classifying the text data using natural language processing, and emotion recognition means for recognizing the user's emotions and adjusting the tone and content of the response. This makes it possible to provide flexible and appropriate responses that are sensitive to the user's emotions.

[0397] "Speech recognition means" refers to a technology that converts speech data into text data, and is a means for analyzing a user's speech as text information.

[0398] "Natural language processing means" refers to technologies that analyze input character data and summarize or classify the content of inquiries by referring to a pre-trained database.

[0399] "Response generation means" refers to a technology for generating relevant responses based on summarized and categorized information.

[0400] "Emotion recognition means" refers to a technology that analyzes the user's text and voice data to identify their emotional state and reflect it in response generation.

[0401] "Verification means" are methods for confirming the accuracy and emotional relevance of generated responses, and are techniques for evaluating whether they are appropriate responses.

[0402] "Display means" refers to a device or function for presenting confirmed answers to the user.

[0403] "Transmission means" refers to the function of sending audio data received by the speech recognition means to a cloud server via the network.

[0404] A "double-checking method" is a system used to further re-evaluate the consistency of answers obtained through natural language processing.

[0405] This invention is a system that generates responses that are in line with the user's emotional state. The system consists of speech recognition means, natural language processing means, emotion recognition means, response generation means, verification means, display means, and transmission means.

[0406] First, the device receives voice input from the user. This voice data is converted into text data using speech recognition software. For example, Google's speech recognition API is used for this speech recognition.

[0407] The server analyzes text data using natural language processing (NLP) tools to summarize and classify the query content. Natural language processing technologies such as IBM Watson and Google NLP API can be used.

[0408] Furthermore, as a means of emotion recognition, the system analyzes text data and voice features to recognize the user's emotional state. This process utilizes emotion recognition APIs included in Microsoft Azure Cognitive Services, among others.

[0409] The response generation mechanism generates a response with appropriate tone and content based on the recognized emotion. This generation can utilize generative AI models such as those from OpenAI.

[0410] The generated responses are verified for accuracy and emotional relevance through validation methods. A rule-based system is applied for this verification.

[0411] Finally, the verified answers are presented to the user's device through a display mechanism.

[0412] For example, if a user inquires in an anxious tone that "my recent order hasn't arrived," emotion recognition identifies "anxiety." The server then generates a response such as, "We apologize for the inconvenience. We have checked the shipping status and expect to deliver it tomorrow, so please rest assured," and presents it to the user.

[0413] Examples of prompts for a generative AI model are as follows:

[0414] "Voice input from user: 'My recent order hasn't arrived.' Emotion recognition: Anxiety Generated response: 'We apologize for the inconvenience. We have checked the shipping status and expect it to arrive tomorrow, so please rest assured.'"

[0415] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0416] Step 1:

[0417] The user inputs their inquiry into the terminal using voice. This voice data is received by the terminal as input. The user's voice is captured as a digital signal through the microphone.

[0418] Step 2:

[0419] The terminal sends the received audio data to the server. The transmitted audio data arrives at the server as input. The server prepares to start the speech recognition process by receiving the audio data over the network.

[0420] Step 3:

[0421] The server converts audio data into text data using speech recognition technology. The input audio data is analyzed and converted into text data. For example, the process of converting an audio waveform to text is performed using Google's speech recognition API.

[0422] Step 4:

[0423] The server analyzes the text data using natural language processing tools to summarize and classify the query content. In this process, the input text data undergoes the following processing and classification: The server uses natural language processing algorithms (e.g., IBM Watson) to extract important keywords and phrases and identify the content of the query.

[0424] Step 5:

[0425] The server analyzes text and audio data using emotion recognition tools to recognize the user's emotional state. In this process, the input data is analyzed using an emotion recognition API (e.g., Microsoft Azure Cognitive Services), and the emotional state (e.g., anxiety, joy) is output.

[0426] Step 6:

[0427] The server generates a response using a response generation mechanism based on the recognized emotion. In this step, the emotional state and summarized inquiry content are inputs, and the response content is generated using a generation AI model (e.g., OpenAI). The output is an appropriate response in a context that aligns with the emotion.

[0428] Step 7:

[0429] The server verifies the accuracy and sentiment relevance of the generated responses using verification mechanisms. This verification uses a rule-based system to determine whether the generated responses are appropriate. Based on the verification process, verified responses are output.

[0430] Step 8:

[0431] The server sends the verified response to the terminal, which is then presented to the user via a display device. The user can then receive the final response and verify the information on the terminal screen.

[0432] 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.

[0433] 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.

[0434] 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.

[0435] [Third Embodiment]

[0436] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0437] 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.

[0438] 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).

[0439] 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.

[0440] 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.

[0441] 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).

[0442] 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.

[0443] 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.

[0444] 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.

[0445] 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.

[0446] 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.

[0447] 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".

[0448] This invention provides a system for streamlining customer service at inquiry desks, and is implemented by combining speech recognition, natural language processing, and automated response generation. The elements necessary to implement this system are a terminal for processing user voice data, a server that connects to and processes the terminal via a network, and a means for the user to ultimately receive the response.

[0449] The user inputs their inquiry into the terminal using voice input. This voice data is sent from the terminal to the server. The server converts the received voice data into text data using speech recognition, and then analyzes the text data using natural language processing. In this analysis, the inquiry is summarized based on a pre-trained database and FAQs, and classified into the appropriate category.

[0450] Based on the analysis results, the server automatically generates an appropriate response using a response generation mechanism. The generated response is double-checked by a verification mechanism to confirm its accuracy and consistency. The final verified response is sent to the terminal via the network and presented to the user.

[0451] As a concrete example, consider a case where a user asks, "What is the product exchange policy?" The user inputs this via voice input through their device, and the server converts it into text data. The server analyzes this text using natural language processing and recognizes the keyword "exchange policy." As a result, it summarizes relevant information from FAQs and standards regarding exchanges and generates a response stating, "Exchanges are possible within 30 days of purchase." The generated response is double-checked to confirm its accuracy before being displayed on the user's device.

[0452] This system enables the automation and streamlining of customer inquiries, significantly reducing the workload.

[0453] The following describes the processing flow.

[0454] Step 1:

[0455] The user initiates voice input using the device. The user speaks their inquiry into the microphone, and the voice data is recorded on the device.

[0456] Step 2:

[0457] The device converts the recorded audio data into a digital format and sends it to the server via the network.

[0458] Step 3:

[0459] The server analyzes the received audio data using speech recognition and converts it into text data. This text data is then processed as basic information for the inquiry.

[0460] Step 4:

[0461] The server analyzes the converted text data using natural language processing techniques. Specifically, it summarizes the data and classifies it into categories based on a pre-trained database and FAQs.

[0462] Step 5:

[0463] Based on the analysis results, the server uses a response generation mechanism to create an appropriate answer. At this stage, it scrutinizes the most relevant information and generates a short but accurate response.

[0464] Step 6:

[0465] The server uses verification methods to double-check the consistency and accuracy of the generated responses. Responses are modified as needed, and a final confirmation is performed.

[0466] Step 7:

[0467] The server sends the fully verified response to the terminal. The terminal displays the received response to the user, allowing the user to review the content.

[0468] (Example 1)

[0469] 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."

[0470] The problem that this invention aims to solve is to improve the efficiency of responses at inquiry desks, optimize human resources, and provide accurate, consistent answers quickly.

[0471] 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.

[0472] In this invention, the server includes speech recognition means for receiving voice data and converting the voice data into text data; natural language processing means for analyzing the text data and summarizing and classifying the inquiry content based on comparison with stored information sources; and response generation means for generating relevant answers based on the summarization and classification. This makes it possible to automatically process the inquiry content and quickly provide accurate and consistent answers.

[0473] "Speech recognition means" refers to a technology that receives speech data and converts that speech data into text data.

[0474] "Natural language processing means" refers to technologies that analyze character data and summarize and classify query content based on comparison with stored information sources.

[0475] "Response generation means" refers to a technology that generates relevant responses based on summarized and categorized information.

[0476] A "verification method" is a technique for confirming the accuracy of the generated response based on a set of criteria.

[0477] "Presentation means" refers to the technology for presenting the confirmed answer to an output device.

[0478] "Transfer means" refers to a technology for transmitting voice data received by a voice recognition means to an external processing device via a communication network.

[0479] A "verification method" is a technique that uses a set of rule-based structures to organize the consistency of responses.

[0480] This invention is implemented as a system to streamline customer service inquiries. The basic elements of this system include a terminal for user voice input, a server for processing the voice, and means for returning information to the user.

[0481] The user inputs their inquiry by voice using the microphone on their device. This voice data is temporarily stored on the device and sent via the communication network to an external processing unit, the server.

[0482] The server uses speech recognition software to convert audio data into text data. Speech recognition employs technology that accurately converts audio data into text.

[0483] Subsequently, the server uses a generative AI model to process the text data using natural language. Specifically, it analyzes, summarizes, and classifies the inquiry based on comparison with stored information sources. An example of a prompt at this stage would be: "Generate the best answer to the user's question: 'What is the product exchange policy?'"

[0484] Based on the analyzed data, the server uses response generation means to create relevant answers. The generated answers are verified for accuracy and consistency through verification means. Once verification is complete, the answers are sent by the server to the terminal and presented to the user.

[0485] This system allows users to receive quick and accurate answers, streamlining the inquiry process. For example, if a user asks, "What is the product exchange policy?", the generated answer will provide specific information such as, "Exchanges are possible within 30 days of purchase."

[0486] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0487] Step 1:

[0488] The user performs voice input on the device. When the user speaks their inquiry through the microphone, the device captures the audio data. The input is the user's voice data, and the output is a digital file containing that audio data.

[0489] Step 2:

[0490] The terminal transmits the captured audio data to the server via the communication network. The input is an audio digital file, and the server's reception is the output. Data transmission processing takes place here.

[0491] Step 3:

[0492] The server uses speech recognition software to convert received audio data into text data. Specifically, the server analyzes the audio data and converts it into a single text string. The input is an audio digital file, and the output is text data containing the audio content.

[0493] Step 4:

[0494] The server performs natural language processing using a generative AI model. In this step, the server processes text data as prompt sentences and performs analysis, summarization, and classification. The input is text data obtained through speech recognition, and the output is the analyzed summary information and its classification results.

[0495] Step 5:

[0496] The server uses a response generation mechanism based on the analysis results to generate an appropriate answer. In this step, the server utilizes a generation AI model to create an answer by matching it with information in the database. The input is the analyzed text data, and the output is the text of the generated answer.

[0497] Step 6:

[0498] The server verifies the generated responses using validation mechanisms. Specifically, it checks the accuracy and consistency of the generated responses and makes corrections as needed. The input is the generated response text, and the output is the validated response text.

[0499] Step 7:

[0500] The server transmits the verified response to the terminal via the communication network and presents it to the user. The input is the verified response text, and the output is the response information displayed on the terminal. In this step, the display process is performed so that the user can receive the response.

[0501] (Application Example 1)

[0502] 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."

[0503] Conventional inquiry handling systems have struggled to efficiently process voice input and provide users with quick and accurate answers. In particular, inquiries via portable devices require ensuring portability and real-time capabilities while guaranteeing accuracy and consistency in responses. This necessitates improvements in both user experience and operational efficiency.

[0504] 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.

[0505] In this invention, the server includes speech recognition means for receiving voice data and converting it into text data, natural language processing means for analyzing the text data and summarizing and classifying the query content, and information generation means for generating relevant responses. This makes it possible to provide accurate responses in real time to voice queries via portable devices.

[0506] "Speech recognition means" refers to technology that receives speech data and performs the process of converting it into text data.

[0507] "Natural language processing means" refers to techniques that analyze received character data and summarize and classify the content of inquiries based on a pre-learned knowledge base.

[0508] "Information generation means" refers to technology that automatically generates relevant responses based on data summarized and classified by natural language processing.

[0509] "Verification means" refers to techniques for performing processes to confirm the accuracy and consistency of the generated response.

[0510] "Display means" refers to a device or system for presenting a confirmed response to the user.

[0511] "Application program means for portable devices" refers to a technology for installing a program on a portable device that processes voice inquiries and immediately presents relevant information.

[0512] The system realizing this invention uses a speech recognition means that receives user voice data and converts it into text data. By utilizing the Google Speech Recognition API for speech recognition, highly accurate conversion to text data is possible. Users make inquiries by voice using a portable device, such as a smartphone.

[0513] The terminal sends the text data converted by speech recognition to the server. The server analyzes the text data using natural language processing tools and compares it with a pre-trained knowledge base. Possible technologies used for this include machine learning libraries such as TensorFlow and PyTorch. The analyzed data is then processed by information generation tools that accurately summarize the query and generate relevant responses.

[0514] The generated response is verified for accuracy and consistency by a validation mechanism within the server. This validation mechanism employs a rule-based system to check whether the response content conforms to predefined criteria.

[0515] Finally, the confirmed response is presented to the user via a display on a portable device. The user can immediately obtain the necessary information, for example, in response to the inquiry "What is the return period for the product?", they can receive a specific answer such as "You can return the product within 30 days of purchase."

[0516] An example of a prompt message might be, "The user has asked a question about a product. Find the most relevant FAQ and generate an answer based on that information." This allows the system to generate an appropriate response and provide information to the user quickly.

[0517] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0518] Step 1:

[0519] The user makes a voice inquiry using a portable device. The input is the user's voice data. The device receives this voice data and converts it into text data using a speech recognition API. The output is the converted text data.

[0520] Step 2:

[0521] The terminal sends the text data obtained through speech recognition to the server. It receives text data as input and forwards it to the server. The output is the text data sent to the server.

[0522] Step 3:

[0523] The server receives text data and performs natural language processing. Here, it analyzes the text data using a generative AI model such as TensorFlow. As input, the server receives text data, summarizes the query, and performs classification. The output is the summarized and classified data.

[0524] Step 4:

[0525] The server generates relevant responses using information generation tools based on summarized and classified data. The input is classified data, and an AI model is used to automatically generate appropriate responses as output. Specifically, this involves matching data against an FAQ database.

[0526] Step 5:

[0527] The generated response is verified for accuracy and consistency within the server using validation mechanisms. The generated response is received as input, and its conformance to the criteria is checked using a rule-based system. The output is the verified, accurate response.

[0528] Step 6:

[0529] The server sends the confirmed response back to the terminal. The input is the verified response, which is then sent to the terminal. The output is the response presented to the terminal.

[0530] Step 7:

[0531] The terminal presents the final response to the user. It receives the response sent from the server as input and displays it visually to the user. The output is the response information received by the user.

[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] This invention provides a system that enables more personalized responses by recognizing user emotions and reflecting that information in response generation. This system integrates speech recognition, natural language processing, and emotion recognition to generate appropriate and emotionally resonant answers to user inquiries.

[0534] The user inputs their inquiry into the terminal using voice. This voice data is transmitted from the terminal to the server via the network. The server first converts the voice data into text data using speech recognition. The converted text data is then analyzed by natural language processing to summarize the inquiry and classify it based on a pre-trained database.

[0535] Furthermore, the server analyzes text and audio data using an emotion engine to recognize the user's emotional state. Based on the results of the emotion recognition, the response generation system generates a response with a tone and content appropriate to the user's emotions. For example, if the user is showing signs of anxiety, the server will create a response in a reassuring tone.

[0536] The generated responses are verified by a validation system with a double-check function. Here, the accuracy of the response and whether it is expressed appropriately for the desired emotion are evaluated. The verified responses are sent from the server to the terminal and presented to the user. User feedback on the displayed responses is also evaluated by the emotion engine and used to improve subsequent response generation.

[0537] For example, if a user makes an inquiry in an anxious tone saying, "My recent order hasn't arrived," the emotion engine recognizes that anxiety. The server then generates a reassuring response, such as, "We apologize for the inconvenience. We have checked the shipping status and expect to deliver it tomorrow, so please rest assured," and presents it to the user.

[0538] This system allows for personalized responses that are empathetic to the user's emotions, rather than simply providing mechanical answers, thereby improving customer satisfaction with inquiries.

[0539] The following describes the processing flow.

[0540] Step 1:

[0541] The user initiates voice input using the device. As the user speaks their inquiry, the device records the voice and generates digital audio data.

[0542] Step 2:

[0543] The device transmits the recorded digital audio data to the server via the network.

[0544] Step 3:

[0545] The server analyzes the received audio data using speech recognition and converts it into text data. This text data forms the basis for subsequent processing.

[0546] Step 4:

[0547] The server analyzes the converted character data using natural language processing tools, summarizes the query content, and classifies it into categories by comparing it with a pre-trained database.

[0548] Step 5:

[0549] The server further analyzes the voice and text data using an emotion engine to recognize the emotions the user is expressing. In this step, emotions are detected, for example, from the user's tone of voice and word choice.

[0550] Step 6:

[0551] The server considers the results of the emotion engine and uses response generation means to generate a response that is sensitive to the user's emotions. For example, if an emotion seeking reassurance is recognized, a response in a gentle tone will be created.

[0552] Step 7:

[0553] The server double-checks the generated responses using verification tools to ensure their accuracy and appropriate expression of sentiment. If no problems are found, the verification is complete.

[0554] Step 8:

[0555] The server sends the verified response to the terminal. The terminal displays the result to the user, allowing the user to visually confirm the response.

[0556] Step 9:

[0557] The user reviews the displayed response and, if they wish to provide feedback, enters their opinion into the device. The device sends this feedback to the server, which helps optimize the sentiment engine and other processes.

[0558] (Example 2)

[0559] 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."

[0560] Conventional systems could convert voice data into text data and generate general responses, but they had the challenge of not being able to provide individualized responses that were sensitive to the user's emotions. Specifically, the responses were uniform, and responses were not provided in an appropriate tone or content that matched the user's emotional state, resulting in a failure to sufficiently improve user satisfaction.

[0561] 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.

[0562] In this invention, the server includes speech recognition means for converting speech data into text data, natural language processing means for analyzing, summarizing, and classifying the text data, and emotion recognition means for recognizing an individual's emotional state from the text data and speech data. This enables personalized responses adapted to the user's emotions, thereby improving user satisfaction with inquiries.

[0563] "Audio data" refers to digital data that contains information transmitted through sound.

[0564] "Text data" refers to information expressed in string format, which is a converted form of audio data.

[0565] "Speech recognition means" refers to the function of a device or software for converting speech data into text data.

[0566] "Natural language processing means" refers to a technology or function that analyzes character data to summarize and classify the content of a query.

[0567] "Emotion recognition means" refers to a technology or function that identifies a user's emotional state based on text data and audio data.

[0568] "Response generation means" refers to a technology or function that generates relevant responses based on an individual's emotional state.

[0569] "Verification means" refers to techniques or functions for verifying the accuracy and emotional appropriateness of the generated responses.

[0570] "Display means" refers to a device or function for presenting the confirmed answer to the user.

[0571] "Transmission means" refers to a technology or function for transferring audio data to another device via a network.

[0572] A "double-checking method" is a technique that re-evaluates the results of natural language processing to confirm its consistency and adaptability to emotions.

[0573] The system of this invention starts with the user making an inquiry by voice. First, the user inputs a question or inquiry as voice into a terminal. The terminal receives this voice data and transmits it to a server via a communication network. The voice data arrives at the server in digital format.

[0574] The server uses high-precision speech recognition technology to convert speech data into text data. Technologies such as a "speech recognition API" can be used here. This text data serves to record the content of the user's speech.

[0575] Next, the server analyzes the generated text data using natural language processing techniques. This natural language processing uses software such as a "language processing engine" to summarize the utterances and classify them based on comparisons with pre-learned information sources and materials.

[0576] Furthermore, voice and text data are analyzed using emotion recognition technology. The server uses an "emotion analysis engine" to determine the user's emotions. This makes it possible to recognize what emotions the user is experiencing, such as anxiety, joy, or anger.

[0577] Based on the results of emotion recognition, the server uses a generative AI model to generate a response. For example, it uses a "generative AI engine" to construct a response with a tone and content that takes the user's emotions into consideration. If the user is showing signs of anxiety, it can generate a response that provides reassurance.

[0578] The generated responses are verified through a validation process to check their accuracy and whether they retain appropriate emotional expression. This double-check function ensures the quality of the responses.

[0579] Finally, the server sends the verified response to the terminal and displays it to the user. The user can then review the provided response on their terminal. The user can also provide feedback on the received response, which will be used to improve the system in the future.

[0580] For example, a user might inquire in a worried tone that their recent order hasn't arrived. In this case, the system would generate a reassuring response such as, "We've checked the shipping status and it's expected to arrive tomorrow, so please don't worry."

[0581] Example prompt text to input into the generation AI model: "If a user inquires in an anxious tone that 'my recent order hasn't arrived,' how should the system generate a reassuring response?"

[0582] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0583] Step 1:

[0584] The user inputs their inquiry into the terminal using voice. The terminal receives this voice data as a digital signal and sends it to a server in the cloud system. In this step, the user's voice is the starting point for processing.

[0585] Step 2:

[0586] When the server receives audio data, it uses speech recognition to convert the digital audio into text data. For example, a "speech recognition engine" is used to analyze the audio waveform and convert it into corresponding text. This converted text data then becomes the input for the next process.

[0587] Step 3:

[0588] The server inputs the converted character data into a natural language processing system for analysis. This process utilizes "language processing software" to summarize the content and perform classification based on a pre-trained database. As a result of the analysis, a summary and classification of the query are obtained.

[0589] Step 4:

[0590] The server processes the parsed text data and the original audio data through an emotion recognition system. Here, an emotion analysis engine is used to evaluate the user's emotional state. Through emotion analysis, specific emotion labels, such as anxiety or joy, are output.

[0591] Step 5:

[0592] The server generates a response using a generative AI model based on the result of the emotional state. In this step, the response generation algorithm is applied to construct a response with a tone and content that resonates with the individual's emotions. The output of this generation process is an emotionally appropriate response text.

[0593] Step 6:

[0594] The server passes the generated response to a verification system for a double-check of its accuracy and sentiment appropriateness. A virtual verification system is used to ensure the response is indeed appropriate. Through verification, a quality-assured response is confirmed.

[0595] Step 7:

[0596] Confirmed responses are sent from the server to the terminal. The terminal displays this response to the user. The user can then review the response displayed on the terminal and take action based on its content.

[0597] Step 8:

[0598] Users send feedback on the provided responses to the server via their device. The server receives this feedback, performs sentiment analysis again, and uses it to improve the response generation process. Through this process, the system continuously evolves, enabling more emotionally resonant responses.

[0599] (Application Example 2)

[0600] 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."

[0601] Conventional systems only received voice data and provided automated responses to inquiries, making it difficult to provide personalized support that took into account the user's emotional state. As a result, there was a problem of decreased user satisfaction with the resolution of their anxieties and questions.

[0602] 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.

[0603] In this invention, the server includes speech recognition means for converting speech data into text data, means for summarizing and classifying the text data using natural language processing, and emotion recognition means for recognizing the user's emotions and adjusting the tone and content of the response. This makes it possible to provide flexible and appropriate responses that are sensitive to the user's emotions.

[0604] "Speech recognition means" refers to a technology that converts speech data into text data, and is a means for analyzing a user's speech as text information.

[0605] "Natural language processing means" refers to technologies that analyze input character data and summarize or classify the content of inquiries by referring to a pre-trained database.

[0606] "Response generation means" refers to a technology for generating relevant responses based on summarized and categorized information.

[0607] "Emotion recognition means" refers to a technology that analyzes the user's text and voice data to identify their emotional state and reflect it in response generation.

[0608] "Verification means" are methods for confirming the accuracy and emotional relevance of generated responses, and are techniques for evaluating whether they are appropriate responses.

[0609] "Display means" refers to a device or function for presenting confirmed answers to the user.

[0610] "Transmission means" refers to the function of sending audio data received by the speech recognition means to a cloud server via the network.

[0611] A "double-checking method" is a system used to further re-evaluate the consistency of answers obtained through natural language processing.

[0612] This invention is a system that generates responses that are in line with the user's emotional state. The system consists of speech recognition means, natural language processing means, emotion recognition means, response generation means, verification means, display means, and transmission means.

[0613] First, the device receives voice input from the user. This voice data is converted into text data using speech recognition software. For example, Google's speech recognition API is used for this speech recognition.

[0614] The server analyzes text data using natural language processing (NLP) tools to summarize and classify the query content. Natural language processing technologies such as IBM Watson and Google NLP API can be used.

[0615] Furthermore, as a means of emotion recognition, the system analyzes text data and voice features to recognize the user's emotional state. This process utilizes emotion recognition APIs included in Microsoft Azure Cognitive Services, among others.

[0616] The response generation mechanism generates a response with appropriate tone and content based on the recognized emotion. This generation can utilize generative AI models such as those from OpenAI.

[0617] The generated responses are verified for accuracy and emotional relevance through validation methods. A rule-based system is applied for this verification.

[0618] Finally, the verified answers are presented to the user's device through a display mechanism.

[0619] For example, if a user inquires in an anxious tone that "my recent order hasn't arrived," emotion recognition identifies "anxiety." The server then generates a response such as, "We apologize for the inconvenience. We have checked the shipping status and expect to deliver it tomorrow, so please rest assured," and presents it to the user.

[0620] Examples of prompts for a generative AI model are as follows:

[0621] "Voice input from user: 'My recent order hasn't arrived.' Emotion recognition: Anxiety Generated response: 'We apologize for the inconvenience. We have checked the shipping status and expect it to arrive tomorrow, so please rest assured.'"

[0622] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0623] Step 1:

[0624] The user inputs their inquiry into the terminal using voice. This voice data is received by the terminal as input. The user's voice is captured as a digital signal through the microphone.

[0625] Step 2:

[0626] The terminal sends the received audio data to the server. The transmitted audio data arrives at the server as input. The server prepares to start the speech recognition process by receiving the audio data over the network.

[0627] Step 3:

[0628] The server converts audio data into text data using speech recognition technology. The input audio data is analyzed and converted into text data. For example, the process of converting an audio waveform to text is performed using Google's speech recognition API.

[0629] Step 4:

[0630] The server analyzes the text data using natural language processing tools to summarize and classify the query content. In this process, the input text data undergoes the following processing and classification: The server uses natural language processing algorithms (e.g., IBM Watson) to extract important keywords and phrases and identify the content of the query.

[0631] Step 5:

[0632] The server analyzes text and audio data using emotion recognition tools to recognize the user's emotional state. In this process, the input data is analyzed using an emotion recognition API (e.g., Microsoft Azure Cognitive Services), and the emotional state (e.g., anxiety, joy) is output.

[0633] Step 6:

[0634] The server generates a response using a response generation mechanism based on the recognized emotion. In this step, the emotional state and summarized inquiry content are inputs, and the response content is generated using a generation AI model (e.g., OpenAI). The output is an appropriate response in a context that aligns with the emotion.

[0635] Step 7:

[0636] The server verifies the accuracy and sentiment relevance of the generated responses using verification mechanisms. This verification uses a rule-based system to determine whether the generated responses are appropriate. Based on the verification process, verified responses are output.

[0637] Step 8:

[0638] The server sends the verified response to the terminal, which is then presented to the user via a display device. The user can then receive the final response and verify the information on the terminal screen.

[0639] 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.

[0640] 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.

[0641] 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.

[0642] [Fourth Embodiment]

[0643] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0644] 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.

[0645] 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).

[0646] 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.

[0647] 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.

[0648] 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).

[0649] 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.

[0650] 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.

[0651] 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.

[0652] 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.

[0653] 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.

[0654] 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.

[0655] 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".

[0656] This invention provides a system for streamlining customer service at inquiry desks, and is implemented by combining speech recognition, natural language processing, and automated response generation. The elements necessary to implement this system are a terminal for processing user voice data, a server that connects to and processes the terminal via a network, and a means for the user to ultimately receive the response.

[0657] The user inputs their inquiry into the terminal using voice input. This voice data is sent from the terminal to the server. The server converts the received voice data into text data using speech recognition, and then analyzes the text data using natural language processing. In this analysis, the inquiry is summarized based on a pre-trained database and FAQs, and classified into the appropriate category.

[0658] Based on the analysis results, the server automatically generates an appropriate response using a response generation mechanism. The generated response is double-checked by a verification mechanism to confirm its accuracy and consistency. The final verified response is sent to the terminal via the network and presented to the user.

[0659] As a concrete example, consider a case where a user asks, "What is the product exchange policy?" The user inputs this via voice input through their device, and the server converts it into text data. The server analyzes this text using natural language processing and recognizes the keyword "exchange policy." As a result, it summarizes relevant information from FAQs and standards regarding exchanges and generates a response stating, "Exchanges are possible within 30 days of purchase." The generated response is double-checked to confirm its accuracy before being displayed on the user's device.

[0660] This system enables the automation and streamlining of customer inquiries, significantly reducing the workload.

[0661] The following describes the processing flow.

[0662] Step 1:

[0663] The user initiates voice input using the device. The user speaks their inquiry into the microphone, and the voice data is recorded on the device.

[0664] Step 2:

[0665] The device converts the recorded audio data into a digital format and sends it to the server via the network.

[0666] Step 3:

[0667] The server analyzes the received audio data using speech recognition and converts it into text data. This text data is then processed as basic information for the inquiry.

[0668] Step 4:

[0669] The server analyzes the converted text data using natural language processing techniques. Specifically, it summarizes the data and classifies it into categories based on a pre-trained database and FAQs.

[0670] Step 5:

[0671] Based on the analysis results, the server uses a response generation mechanism to create an appropriate answer. At this stage, it scrutinizes the most relevant information and generates a short but accurate response.

[0672] Step 6:

[0673] The server uses verification methods to double-check the consistency and accuracy of the generated responses. It then modifies the responses as needed and performs a final check.

[0674] Step 7:

[0675] The server sends the fully verified response to the terminal. The terminal displays the received response to the user, allowing the user to review the content.

[0676] (Example 1)

[0677] 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".

[0678] The problem that this invention aims to solve is to improve the efficiency of responses at inquiry desks, optimize human resources, and provide accurate, consistent answers quickly.

[0679] 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.

[0680] In this invention, the server includes speech recognition means for receiving voice data and converting the voice data into text data; natural language processing means for analyzing the text data and summarizing and classifying the inquiry content based on comparison with stored information sources; and response generation means for generating relevant answers based on the summarization and classification. This makes it possible to automatically process the inquiry content and quickly provide accurate and consistent answers.

[0681] "Speech recognition means" refers to a technology that receives speech data and converts that speech data into text data.

[0682] "Natural language processing means" refers to technologies that analyze character data and summarize and classify query content based on comparison with stored information sources.

[0683] "Response generation means" refers to a technology that generates relevant responses based on summarized and categorized information.

[0684] A "verification method" is a technique for confirming the accuracy of the generated response based on a set of criteria.

[0685] "Presentation means" refers to the technology for presenting the confirmed answer to an output device.

[0686] "Transfer means" refers to a technology for transmitting voice data received by a voice recognition means to an external processing device via a communication network.

[0687] A "verification method" is a technique that uses a set of rule-based structures to organize the consistency of responses.

[0688] This invention is implemented as a system to streamline customer service inquiries. The basic elements of this system include a terminal for user voice input, a server for processing the voice, and means for returning information to the user.

[0689] The user inputs their inquiry by voice using the microphone on their device. This voice data is temporarily stored on the device and sent via the communication network to an external processing unit, the server.

[0690] The server uses speech recognition software to convert audio data into text data. Speech recognition employs technology that accurately converts audio data into text.

[0691] Subsequently, the server uses a generative AI model to process the text data using natural language. Specifically, it analyzes, summarizes, and classifies the inquiry based on comparison with stored information sources. An example of a prompt at this stage would be: "Generate the best answer to the user's question: 'What is the product exchange policy?'"

[0692] Based on the analyzed data, the server uses response generation means to create relevant answers. The generated answers are verified for accuracy and consistency through verification means. Once verification is complete, the answers are sent by the server to the terminal and presented to the user.

[0693] This system allows users to receive quick and accurate answers, streamlining the inquiry process. For example, if a user asks, "What is the product exchange policy?", the generated answer will provide specific information such as, "Exchanges are possible within 30 days of purchase."

[0694] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0695] Step 1:

[0696] The user performs voice input on the device. When the user speaks their inquiry through the microphone, the device captures the audio data. The input is the user's voice data, and the output is a digital file containing that audio data.

[0697] Step 2:

[0698] The terminal transmits the captured audio data to the server via the communication network. The input is an audio digital file, and the server's reception is the output. Data transmission processing takes place here.

[0699] Step 3:

[0700] The server uses speech recognition software to convert received audio data into text data. Specifically, the server analyzes the audio data and converts it into a single text string. The input is an audio digital file, and the output is text data containing the audio content.

[0701] Step 4:

[0702] The server performs natural language processing using a generative AI model. In this step, the server processes text data as prompt sentences and performs analysis, summarization, and classification. The input is text data obtained through speech recognition, and the output is the analyzed summary information and its classification results.

[0703] Step 5:

[0704] The server uses a response generation mechanism based on the analysis results to generate an appropriate answer. In this step, the server utilizes a generation AI model to create an answer by matching it with information in the database. The input is the analyzed text data, and the output is the text of the generated answer.

[0705] Step 6:

[0706] The server verifies the generated responses using validation mechanisms. Specifically, it checks the accuracy and consistency of the generated responses and makes corrections as needed. The input is the generated response text, and the output is the validated response text.

[0707] Step 7:

[0708] The server transmits the verified response to the terminal via the communication network and presents it to the user. The input is the verified response text, and the output is the response information displayed on the terminal. In this step, the display process is performed so that the user can receive the response.

[0709] (Application Example 1)

[0710] 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".

[0711] Conventional inquiry handling systems have struggled to efficiently process voice input and provide users with quick and accurate answers. In particular, inquiries via portable devices require ensuring portability and real-time capabilities while guaranteeing accuracy and consistency in responses. This necessitates improvements in both user experience and operational efficiency.

[0712] 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.

[0713] In this invention, the server includes speech recognition means for receiving voice data and converting it into text data, natural language processing means for analyzing the text data and summarizing and classifying the query content, and information generation means for generating relevant responses. This makes it possible to provide accurate responses in real time to voice queries via portable devices.

[0714] "Speech recognition means" refers to technology that receives speech data and performs the process of converting it into text data.

[0715] "Natural language processing means" refers to techniques that analyze received character data and summarize and classify the content of inquiries based on a pre-learned knowledge base.

[0716] "Information generation means" refers to technology that automatically generates relevant responses based on data summarized and classified by natural language processing.

[0717] "Verification means" refers to techniques for performing processes to confirm the accuracy and consistency of the generated response.

[0718] "Display means" refers to a device or system for presenting a confirmed response to the user.

[0719] "Application program means for portable devices" refers to a technology for installing a program on a portable device that processes voice inquiries and immediately presents relevant information.

[0720] The system realizing this invention uses a speech recognition means that receives user voice data and converts it into text data. By utilizing the Google Speech Recognition API for speech recognition, highly accurate conversion to text data is possible. Users make inquiries by voice using a portable device, such as a smartphone.

[0721] The terminal sends the text data converted by speech recognition to the server. The server analyzes the text data using natural language processing tools and compares it with a pre-trained knowledge base. Possible technologies used for this include machine learning libraries such as TensorFlow and PyTorch. The analyzed data is then processed by information generation tools that accurately summarize the query and generate relevant responses.

[0722] The generated response is verified for accuracy and consistency by a validation mechanism within the server. This validation mechanism employs a rule-based system to check whether the response content conforms to predefined criteria.

[0723] Finally, the confirmed response is presented to the user via a display on a portable device. The user can immediately obtain the necessary information, for example, in response to the inquiry "What is the return period for the product?", they can receive a specific answer such as "You can return the product within 30 days of purchase."

[0724] An example of a prompt message might be, "The user has asked a question about a product. Find the most relevant FAQ and generate an answer based on that information." This allows the system to generate an appropriate response and provide information to the user quickly.

[0725] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0726] Step 1:

[0727] The user makes a voice inquiry using a portable device. The input is the user's voice data. The device receives this voice data and converts it into text data using a speech recognition API. The output is the converted text data.

[0728] Step 2:

[0729] The terminal sends the text data obtained through speech recognition to the server. It receives text data as input and forwards it to the server. The output is the text data sent to the server.

[0730] Step 3:

[0731] The server receives text data and performs natural language processing. Here, it analyzes the text data using a generative AI model such as TensorFlow. As input, the server receives text data, summarizes the query, and performs classification. The output is the summarized and classified data.

[0732] Step 4:

[0733] The server generates relevant responses using information generation tools based on summarized and classified data. The input is classified data, and an AI model is used to automatically generate appropriate responses as output. Specifically, this involves matching data against an FAQ database.

[0734] Step 5:

[0735] The generated response is verified for accuracy and consistency within the server using validation mechanisms. The generated response is received as input, and its conformance to the criteria is checked using a rule-based system. The output is the verified, accurate response.

[0736] Step 6:

[0737] The server sends the confirmed response back to the terminal. The input is the verified response, which is then sent to the terminal. The output is the response presented to the terminal.

[0738] Step 7:

[0739] The terminal presents the final response to the user. It receives the response sent from the server as input and displays it visually to the user. The output is the response information received by the user.

[0740] 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.

[0741] This invention provides a system that enables more personalized responses by recognizing user emotions and reflecting that information in response generation. This system integrates speech recognition, natural language processing, and emotion recognition to generate appropriate and emotionally resonant answers to user inquiries.

[0742] The user inputs their inquiry into the terminal using voice. This voice data is transmitted from the terminal to the server via the network. The server first converts the voice data into text data using speech recognition. The converted text data is then analyzed by natural language processing to summarize the inquiry and classify it based on a pre-trained database.

[0743] Furthermore, the server analyzes text and audio data using an emotion engine to recognize the user's emotional state. Based on the results of the emotion recognition, the response generation system generates a response with a tone and content appropriate to the user's emotions. For example, if the user is showing signs of anxiety, the server will create a response in a reassuring tone.

[0744] The generated responses are verified by a validation system with a double-check function. Here, the accuracy of the response and whether it is expressed appropriately for the desired emotion are evaluated. The verified responses are sent from the server to the terminal and presented to the user. User feedback on the displayed responses is also evaluated by the emotion engine and used to improve subsequent response generation.

[0745] For example, if a user makes an inquiry in an anxious tone saying, "My recent order hasn't arrived," the emotion engine recognizes that anxiety. The server then generates a reassuring response, such as, "We apologize for the inconvenience. We have checked the shipping status and expect to deliver it tomorrow, so please rest assured," and presents it to the user.

[0746] This system allows for personalized responses that are empathetic to the user's emotions, rather than simply providing mechanical answers, thereby improving customer satisfaction with inquiries.

[0747] The following describes the processing flow.

[0748] Step 1:

[0749] The user initiates voice input using the device. As the user speaks their inquiry, the device records the voice and generates digital audio data.

[0750] Step 2:

[0751] The device transmits the recorded digital audio data to the server via the network.

[0752] Step 3:

[0753] The server analyzes the received audio data using speech recognition and converts it into text data. This text data forms the basis for subsequent processing.

[0754] Step 4:

[0755] The server analyzes the converted character data using natural language processing tools, summarizes the query content, and classifies it into categories by comparing it with a pre-trained database.

[0756] Step 5:

[0757] The server further analyzes the voice and text data using an emotion engine to recognize the emotions the user is expressing. In this step, emotions are detected, for example, from the user's tone of voice and word choice.

[0758] Step 6:

[0759] The server considers the results of the emotion engine and uses response generation means to generate a response that is sensitive to the user's emotions. For example, if an emotion seeking reassurance is recognized, a response in a gentle tone will be created.

[0760] Step 7:

[0761] The server double-checks the generated responses using verification tools to ensure their accuracy and appropriate expression of sentiment. If no problems are found, the verification is complete.

[0762] Step 8:

[0763] The server sends the verified response to the terminal. The terminal displays the result to the user, allowing the user to visually confirm the response.

[0764] Step 9:

[0765] The user reviews the displayed response and, if they wish to provide feedback, enters their opinion into the device. The device sends this feedback to the server, which helps optimize the sentiment engine and other processes.

[0766] (Example 2)

[0767] 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".

[0768] Conventional systems could convert voice data into text data and generate general responses, but they had the challenge of not being able to provide individualized responses that were sensitive to the user's emotions. Specifically, the responses were uniform, and responses were not provided in an appropriate tone or content that matched the user's emotional state, resulting in a failure to sufficiently improve user satisfaction.

[0769] 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.

[0770] In this invention, the server includes speech recognition means for converting speech data into text data, natural language processing means for analyzing, summarizing, and classifying the text data, and emotion recognition means for recognizing an individual's emotional state from the text data and speech data. This enables personalized responses adapted to the user's emotions, thereby improving user satisfaction with inquiries.

[0771] "Audio data" refers to digital data that contains information transmitted through sound.

[0772] "Text data" refers to information expressed in string format, which is a converted form of audio data.

[0773] "Speech recognition means" refers to the function of a device or software for converting speech data into text data.

[0774] "Natural language processing means" refers to a technology or function that analyzes character data to summarize and classify the content of a query.

[0775] "Emotion recognition means" refers to a technology or function that identifies a user's emotional state based on text data and audio data.

[0776] "Response generation means" refers to a technology or function that generates relevant responses based on an individual's emotional state.

[0777] "Verification means" refers to techniques or functions for verifying the accuracy and emotional appropriateness of the generated responses.

[0778] "Display means" refers to a device or function for presenting the confirmed answer to the user.

[0779] "Transmission means" refers to a technology or function for transferring audio data to another device via a network.

[0780] A "double-checking method" is a technique that re-evaluates the results of natural language processing to confirm its consistency and adaptability to emotions.

[0781] The system of this invention starts with the user making an inquiry by voice. First, the user inputs a question or inquiry as voice into a terminal. The terminal receives this voice data and transmits it to a server via a communication network. The voice data arrives at the server in digital format.

[0782] The server uses high-precision speech recognition technology to convert speech data into text data. Technologies such as a "speech recognition API" can be used here. This text data serves to record the content of the user's speech.

[0783] Next, the server analyzes the generated text data using natural language processing techniques. This natural language processing uses software such as a "language processing engine" to summarize the utterances and classify them based on comparisons with pre-learned information sources and materials.

[0784] Furthermore, voice and text data are analyzed using emotion recognition technology. The server uses an "emotion analysis engine" to determine the user's emotions. This makes it possible to recognize what emotions the user is experiencing, such as anxiety, joy, or anger.

[0785] Based on the results of emotion recognition, the server uses a generative AI model to generate a response. For example, it uses a "generative AI engine" to construct a response with a tone and content that takes the user's emotions into consideration. If the user is showing signs of anxiety, it can generate a response that provides reassurance.

[0786] The generated responses are verified through a validation process to check their accuracy and whether they retain appropriate emotional expression. This double-check function ensures the quality of the responses.

[0787] Finally, the server sends the verified response to the terminal and displays it to the user. The user can then review the provided response on their terminal. The user can also provide feedback on the received response, which will be used to improve the system in the future.

[0788] For example, a user might inquire in a worried tone that their recent order hasn't arrived. In this case, the system would generate a reassuring response such as, "We've checked the shipping status and it's expected to arrive tomorrow, so please don't worry."

[0789] Example prompt text to input into the generation AI model: "If a user inquires in an anxious tone that 'my recent order hasn't arrived,' how should the system generate a reassuring response?"

[0790] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0791] Step 1:

[0792] The user inputs their inquiry into the terminal using voice. The terminal receives this voice data as a digital signal and sends it to a server in the cloud system. In this step, the user's voice is the starting point for processing.

[0793] Step 2:

[0794] When the server receives audio data, it uses speech recognition to convert the digital audio into text data. For example, a "speech recognition engine" is used to analyze the audio waveform and convert it into corresponding text. This converted text data then becomes the input for the next process.

[0795] Step 3:

[0796] The server inputs the converted character data into a natural language processing system for analysis. This process utilizes "language processing software" to summarize the content and perform classification based on a pre-trained database. As a result of the analysis, a summary and classification of the query are obtained.

[0797] Step 4:

[0798] The server processes the parsed text data and the original audio data through an emotion recognition system. Here, an emotion analysis engine is used to evaluate the user's emotional state. Through emotion analysis, specific emotion labels, such as anxiety or joy, are output.

[0799] Step 5:

[0800] The server generates a response using a generative AI model based on the result of the emotional state. In this step, the response generation algorithm is applied to construct a response with a tone and content that resonates with the individual's emotions. The output of this generation process is an emotionally appropriate response text.

[0801] Step 6:

[0802] The server passes the generated response to a verification system for a double-check of its accuracy and sentiment appropriateness. A virtual verification system is used to ensure the response is indeed appropriate. Through verification, a quality-assured response is confirmed.

[0803] Step 7:

[0804] Confirmed responses are sent from the server to the terminal. The terminal displays this response to the user. The user can then review the response displayed on the terminal and take action based on its content.

[0805] Step 8:

[0806] Users send feedback on the provided responses to the server via their device. The server receives this feedback, performs sentiment analysis again, and uses it to improve the response generation process. Through this process, the system continuously evolves, enabling more emotionally resonant responses.

[0807] (Application Example 2)

[0808] 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".

[0809] Conventional systems only received voice data and provided automated responses to inquiries, making it difficult to provide personalized support that took into account the user's emotional state. As a result, there was a problem of decreased user satisfaction with the resolution of their anxieties and questions.

[0810] 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.

[0811] In this invention, the server includes speech recognition means for converting speech data into text data, means for summarizing and classifying the text data using natural language processing, and emotion recognition means for recognizing the user's emotions and adjusting the tone and content of the response. This makes it possible to provide flexible and appropriate responses that are sensitive to the user's emotions.

[0812] "Speech recognition means" refers to a technology that converts speech data into text data, and is a means for analyzing a user's speech as text information.

[0813] "Natural language processing means" refers to technologies that analyze input character data and summarize or classify the content of inquiries by referring to a pre-trained database.

[0814] "Response generation means" refers to a technology for generating relevant responses based on summarized and categorized information.

[0815] "Emotion recognition means" refers to a technology that analyzes the user's text and voice data to identify their emotional state and reflect it in response generation.

[0816] "Verification means" are methods for confirming the accuracy and emotional relevance of generated responses, and are techniques for evaluating whether they are appropriate responses.

[0817] "Display means" refers to a device or function for presenting confirmed answers to the user.

[0818] "Transmission means" refers to the function of sending audio data received by the speech recognition means to a cloud server via the network.

[0819] A "double-checking method" is a system used to further re-evaluate the consistency of answers obtained through natural language processing.

[0820] This invention is a system that generates responses that are in line with the user's emotional state. The system consists of speech recognition means, natural language processing means, emotion recognition means, response generation means, verification means, display means, and transmission means.

[0821] First, the device receives voice input from the user. This voice data is converted into text data using speech recognition software. For example, Google's speech recognition API is used for this speech recognition.

[0822] The server analyzes text data using natural language processing (NLP) tools to summarize and classify the query content. Natural language processing technologies such as IBM Watson and Google NLP API can be used.

[0823] Furthermore, as a means of emotion recognition, the system analyzes text data and voice features to recognize the user's emotional state. This process utilizes emotion recognition APIs included in Microsoft Azure Cognitive Services, among others.

[0824] The response generation mechanism generates a response with appropriate tone and content based on the recognized emotion. This generation can utilize generative AI models such as those from OpenAI.

[0825] The generated responses are verified for accuracy and emotional relevance through validation methods. A rule-based system is applied for this verification.

[0826] Finally, the verified answers are presented to the user's device through a display mechanism.

[0827] For example, if a user inquires in an anxious tone that "my recent order hasn't arrived," emotion recognition identifies "anxiety." The server then generates a response such as, "We apologize for the inconvenience. We have checked the shipping status and expect to deliver it tomorrow, so please rest assured," and presents it to the user.

[0828] Examples of prompts for a generative AI model are as follows:

[0829] "Voice input from user: 'My recent order hasn't arrived.' Emotion recognition: Anxiety Generated response: 'We apologize for the inconvenience. We have checked the shipping status and expect it to arrive tomorrow, so please rest assured.'"

[0830] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0831] Step 1:

[0832] The user inputs their inquiry into the terminal using voice. This voice data is received by the terminal as input. The user's voice is captured as a digital signal through the microphone.

[0833] Step 2:

[0834] The terminal sends the received audio data to the server. The transmitted audio data arrives at the server as input. The server prepares to start the speech recognition process by receiving the audio data over the network.

[0835] Step 3:

[0836] The server converts audio data into text data using speech recognition technology. The input audio data is analyzed and converted into text data. For example, the process of converting an audio waveform to text is performed using Google's speech recognition API.

[0837] Step 4:

[0838] The server analyzes the text data using natural language processing tools to summarize and classify the query content. In this process, the input text data undergoes the following processing and classification: The server uses natural language processing algorithms (e.g., IBM Watson) to extract important keywords and phrases and identify the content of the query.

[0839] Step 5:

[0840] The server analyzes text and audio data using emotion recognition tools to recognize the user's emotional state. In this process, the input data is analyzed using an emotion recognition API (e.g., Microsoft Azure Cognitive Services), and the emotional state (e.g., anxiety, joy) is output.

[0841] Step 6:

[0842] The server generates a response using a response generation mechanism based on the recognized emotion. In this step, the emotional state and summarized inquiry content are inputs, and the response content is generated using a generation AI model (e.g., OpenAI). The output is an appropriate response in a context that aligns with the emotion.

[0843] Step 7:

[0844] The server verifies the accuracy and sentiment relevance of the generated responses using verification mechanisms. This verification uses a rule-based system to determine whether the generated responses are appropriate. Based on the verification process, verified responses are output.

[0845] Step 8:

[0846] The server sends the verified response to the terminal, which is then presented to the user via a display device. The user can then receive the final response and verify the information on the terminal screen.

[0847] 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.

[0848] 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.

[0849] 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.

[0850] 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.

[0851] 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.

[0852] 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.

[0853] 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.

[0854] 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.

[0855] 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."

[0856] 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.

[0857] 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.

[0858] 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.

[0859] 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.

[0860] 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.

[0861] 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.

[0862] 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.

[0863] 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.

[0864] 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.

[0865] 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.

[0866] 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.

[0867] 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.

[0868] The following is further disclosed regarding the embodiments described above.

[0869] (Claim 1)

[0870] A speech recognition means that receives audio data and converts that audio data into text data,

[0871] A natural language processing means that analyzes the aforementioned character data and summarizes and classifies the query content based on comparison with a pre-learned database,

[0872] A response generation means that generates relevant answers based on the summary and classification,

[0873] Verification means for confirming the accuracy of the generated response,

[0874] A display means for presenting the confirmed answer on a display device,

[0875] A system that includes this.

[0876] (Claim 2)

[0877] The system according to claim 1, further comprising a transmission means for transmitting voice data received by the voice recognition means to a cloud server via a network.

[0878] (Claim 3)

[0879] The system according to claim 1, further comprising a double-checking means for re-evaluating the consistency of the response using a pre-configured rule-based system, wherein the natural language processing means is further a double-checking means.

[0880] "Example 1"

[0881] (Claim 1)

[0882] A speech recognition means that receives audio data and converts that audio data into text data,

[0883] A natural language processing means that analyzes the aforementioned character data and summarizes and classifies the query content based on comparison with the stored information sources,

[0884] A response generation means that generates relevant answers based on the summary and classification,

[0885] Verification means for confirming the accuracy of the generated response based on a standard,

[0886] A presentation means for displaying the confirmed answer to an output device,

[0887] A system that includes this.

[0888] (Claim 2)

[0889] The system according to claim 1, further comprising a transfer means for transmitting voice data received by the voice recognition means to an external processing device via a communication network.

[0890] (Claim 3)

[0891] The system according to claim 1, further comprising a verification means for organizing the consistency of responses using a set rule-based structure, wherein the natural language processing means is further a verification means.

[0892] "Application Example 1"

[0893] (Claim 1)

[0894] A speech recognition means that receives audio data and converts that audio data into text data,

[0895] A natural language processing means that analyzes the aforementioned character data and summarizes and classifies the query content based on comparison with a pre-learned knowledge base,

[0896] Information generation means for generating relevant responses based on the summary and classification,

[0897] Verification means for confirming the accuracy of the generated response,

[0898] A display means for presenting the confirmed response to the user terminal,

[0899] A portable device application program means for processing voice inquiries and immediately presenting relevant information,

[0900] A system that includes this.

[0901] (Claim 2)

[0902] The system according to claim 1, further comprising a transmission means for transmitting voice data received by the voice recognition means to a server via a network.

[0903] (Claim 3)

[0904] The system according to claim 1, further comprising a re-verification means for re-evaluating the consistency of the response using a pre-configured rule-based method, wherein the natural language processing means further comprises a re-verification means.

[0905] "Example 2 of combining an emotion engine"

[0906] (Claim 1)

[0907] A speech recognition means that receives audio data and converts that audio data into text data,

[0908] A natural language processing means that analyzes the aforementioned character data and summarizes and classifies the query content based on matching it with pre-learned information sources,

[0909] An emotion recognition means for recognizing an individual's emotional state from the aforementioned text data and audio data,

[0910] A response generation means that generates a personalized and relevant response based on the aforementioned emotional state,

[0911] Verification means including a double-check to confirm the accuracy and emotional appropriateness of the generated response,

[0912] A display means for displaying the confirmed answer on a display device,

[0913] A system that includes this.

[0914] (Claim 2)

[0915] The system according to claim 1, further comprising a transmission means for transmitting voice data received by the voice recognition means to a data center via a communication network.

[0916] (Claim 3)

[0917] The system according to claim 1, further comprising a double-checking means for re-evaluating the consistency and emotional adaptability of responses using a pre-configured rule-based mechanism, wherein the natural language processing means is further a double-checking means.

[0918] "Application example 2 when combining with an emotional engine"

[0919] (Claim 1)

[0920] A speech recognition means that receives audio data and converts that audio data into text data,

[0921] A natural language processing means that analyzes the aforementioned character data and summarizes and classifies the query content based on comparison with a pre-learned database,

[0922] A response generation means that generates relevant answers based on the summary and classification,

[0923] An emotion recognition means that analyzes the user's emotional state and adjusts the tone and content of the response based on that analysis,

[0924] A verification means for confirming the accuracy and emotional relevance of the generated response,

[0925] A display means for presenting the confirmed answer on a display device,

[0926] A system that includes this.

[0927] (Claim 2)

[0928] The system according to claim 1, further comprising a transmission means for transmitting voice data received by the voice recognition means to a cloud server via a network.

[0929] (Claim 3)

[0930] The system according to claim 1, further comprising a double-checking means for re-evaluating the consistency of the response using a pre-configured rule-based system, wherein the natural language processing means is further a double-checking means. [Explanation of symbols]

[0931] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A speech recognition means that receives audio data and converts that audio data into text data, A natural language processing means that analyzes the aforementioned character data and summarizes and classifies the query content based on comparison with a pre-learned database, A response generation means that generates relevant answers based on the summary and classification, Verification means for confirming the accuracy of the generated response, A display means for presenting the confirmed answer on a display device, A system that includes this.

2. The system according to claim 1, further comprising a transmission means for transmitting voice data received by the voice recognition means to a cloud server via a network.

3. The system according to claim 1, further comprising a double-checking means for re-evaluating the consistency of the response using a pre-configured rule-based system, wherein the natural language processing means is further a double-checking means.

Images