system

Abstract

Provide a system. 【Solution means】 Means for obtaining the dialogue with the user as voice, Means for converting the obtained voice into digital text, Means for extracting necessary registration information from the digital text, Means for automatically generating registration data based on the extracted information, Means for detecting insufficient explanations and supplying supplementary information, Means for presenting the generated registration data to the user for confirmation, Means for completing the registration process based on the user's confirmation, Means for analyzing customer requirements and dynamically creating a contract document, A system including

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] It aims to solve the problems of time waste caused by separate customer service and procedures and information loss due to insufficient explanation in the registration process of mobile phones. This problem becomes a factor increasing stress for both users and operators and may reduce the quality of services.

Means for Solving the Problems

[0005] This invention provides a means for acquiring conversations between users and operators using speech recognition and converting them into text data. It then extracts the information necessary for registration from the acquired text data and automatically generates it as registration data. Furthermore, by incorporating means for detecting insufficient explanation and providing supplementary information, the system streamlines the registration process and prevents information omissions. This system treats the registration process as a continuous flow, enabling rapid and accurate registration.

[0006] "Audio data" refers to electronically recorded information acquired as sound waves, such as conversations between users and workers.

[0007] "Text data" refers to audio data converted into written information in a format that can be processed by a computer.

[0008] "Registration data" refers to a dataset containing information necessary for the user registration process, which is ultimately entered into the registration system.

[0009] "Means of extracting information" refers to technologies for identifying and extracting necessary registration elements from text data.

[0010] "Supplementary information" refers to additional explanations provided when the operator's explanation is insufficient during a conversation with a user, and is information that helps the user deepen their understanding.

[0011] A "confirmation screen" is a display screen that presents the generated registration data to the user and allows them to confirm its contents. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3]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.

Embodiments for Carrying Out the Invention

[0013] 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.

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

[0015] 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.

[0016] 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.

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

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

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

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

[0022] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0029] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] The present invention provides a system that performs real-time speech recognition of conversations between users and operators, and efficiently facilitates the registration process. The system is configured as follows for implementation.

[0034] 1. Speech recognition engine

[0035] The terminal continuously captures conversations between the user and the worker via a microphone for voice input. This voice data is immediately sent to a speech recognition engine and converted into text data. For example, if the user says, "I would like to sign a new contract," the terminal records this information as text.

[0036] 2. Data Analysis Module

[0037] The server analyzes the text data and extracts information necessary for registration, such as contract type and pricing plan. The information obtained through this analysis forms the basis for generating registration data.

[0038] 3. Data Generation System

[0039] The server uses the analysis results to organize the information necessary for registration and constructs it as registration data. For example, if the user's desired pricing plan is identified, a corresponding contract is automatically prepared.

[0040] 4. Supplementary information presentation function

[0041] If the terminal determines that the operator's explanation is insufficient, it will automatically provide supplementary information to the user via voice or on screen. This feature allows the user to gain a thorough understanding of the contract details and options.

[0042] 5. Verification Interface

[0043] The terminal presents the final registration data to the user for confirmation. The server completes the registration process only after the user has confirmed and agreed to the information.

[0044] This system will solve the time-consuming and insufficient explanation problems of the conventional registration process, enabling fast and accurate registration. For example, smoother communication with users will allow registration to be completed on the spot, significantly reducing waiting times.

[0045] The following describes the processing flow.

[0046] Step 1:

[0047] The terminal captures the conversation between the user and the worker via a microphone for voice input. This voice data is sent in real time to a speech recognition engine and converted into text data.

[0048] Step 2:

[0049] The server analyzes the text data and extracts the information necessary for registration. At this stage, it identifies elements such as contract preferences and pricing plans.

[0050] Step 3:

[0051] The server generates registration data based on the analysis results. This includes the contents of the contract documents and details of the selected plan.

[0052] Step 4:

[0053] The terminal checks the adequacy of the worker's explanation, and if the explanation is insufficient, it provides supplementary information to the user via audio or on-screen display.

[0054] Step 5:

[0055] The terminal displays a confirmation screen of the generated registration data to the user. Here, the user can finally review the contract details and indicate their consent.

[0056] Step 6:

[0057] After the user confirms and agrees, the server completes the final registration process based on the confirmed information and saves it to the database as an official registration.

[0058] (Example 1)

[0059] 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."

[0060] Registration processes using acoustic information are time-consuming in conventional systems and can lead to insufficient explanations and misinterpretations of information. Furthermore, there are challenges in ensuring the accuracy of the generated information and the user's understanding. An efficient method is needed to facilitate smooth communication between users and operators and achieve accurate and rapid information registration.

[0061] 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.

[0062] In this invention, the server includes means for acquiring acoustic information while interacting with the user, means for converting the acquired acoustic information into text information, and means for extracting information necessary for registration from the text information. This enables efficient and accurate conversion of acoustic information into registration information, and facilitates efficient and reliable communication between the user and the operator.

[0063] "Acoustic information" refers to information obtained by acquiring sound or audio, and the data that is processed based on this information.

[0064] "Textual information" refers to information in text format converted from acoustic information, and serves as the foundational data for further analysis and processing.

[0065] "Registration information" refers to the data ultimately used, generated from the interaction between the user and the worker, and the results of its analysis.

[0066] "Additional information" refers to further information provided to supplement explanations given to users or workers that are insufficient.

[0067] A "user interface" refers to the screens and display devices that allow a user to interact with a system and input and output information.

[0068] "Acoustic recognition functionality" is a technical function that analyzes speech in real time and converts it into text information.

[0069] A "database" is a place where generated registration information and related data are systematically stored.

[0070] This system provides technology for quickly and accurately registering information based on user-operator interaction. The following hardware and software will be used for implementation.

[0071] The terminal continuously acquires acoustic information from the user and worker using a microphone. This acoustic information is instantly converted into text information through an acoustic recognition engine. The acoustic recognition engine uses software that utilizes the latest speech recognition technology. This converted text information is sent to a server, which extracts the necessary information for registration using a data analysis module that employs natural language processing technology.

[0072] The server constructs registration information based on the analysis results. For example, if a user requests a new contract, the server automatically generates registration information containing the necessary contract details and presents it to the user through the user interface. The user interface is a screen display device that assists the user in their operations and confirmations.

[0073] If the device detects insufficient explanation, it will provide audio or visual information to supplement it. This ensures the user fully understands the contract and can proceed with confidence. Once the user has confirmed the information, the server saves the registration information to the database and completes the registration process.

[0074] To improve the efficiency of this system, the prompt statements using the generative AI model are set as follows:

[0075] "Use speech recognition to transcribe user conversations into text in real time, extract necessary information, and generate registration data. Also, provide supplementary information if the user asks questions, and complete the registration once confirmation is received."

[0076] By following these prompts, the generative AI model can perform the necessary processing at each step, ensuring the overall process runs smoothly.

[0077] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0078] Step 1:

[0079] The terminal acquires acoustic information via the microphone. The input is a conversation between the user and the worker, and it is captured by the terminal as raw audio data. This audio data is pre-processed for noise reduction and sound quality improvement before being sent to the acoustic recognition engine. The output is the pre-processed audio data.

[0080] Step 2:

[0081] The server uses an acoustic recognition engine to convert speech data into text information. The input is pre-processed speech data, and a generative AI model is used to perform the speech recognition task. Data processing includes phoneme extraction and matching. The output is the converted text information.

[0082] Step 3:

[0083] The server analyzes the text information and extracts the necessary details for registration. The input is text information sent to the server, and a natural language processing algorithm is applied. Through data analysis, necessary information such as contract type and pricing plan is identified. The output is a list of the extracted items.

[0084] Step 4:

[0085] The server generates registration information based on the extracted data. The input is a list of extracted items, and the server automatically creates a registration form based on a template. This process involves document construction and information embedding. The output is a digital document containing the constructed registration information.

[0086] Step 5:

[0087] The terminal detects when the operator's explanation is insufficient and provides additional information to the user if necessary. Input consists of user questions or points of confusion, which triggers the system to display additional information verbally or on the display. The system then searches for and presents relevant information. The output is the additional information presented to the user.

[0088] Step 6:

[0089] The terminal prompts the user to review and agree to the generated registration information. The input is a digital document of the constructed registration information, presented to the user on the user interface. In this review process, the user either clicks a confirmation button or gives voice approval. The output is the user's agreement or a request for correction.

[0090] Step 7:

[0091] The server confirms the user's information and completes the final registration process. The input is user consent information, and the registration information is stored in the database. The operation involves writing to the database and confirmation. The output is the completed registration procedure.

[0092] (Application Example 1)

[0093] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0094] Modern interactive services face the challenge of quickly and accurately acquiring information while interacting with users and providing immediate, optimal suggestions. In particular, real-time information generation and contract creation are required in in-store and field interactions, but conventional technologies lack the efficiency to do so effectively. Furthermore, misunderstandings and delays in agreement can occur due to insufficient explanation.

[0095] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0096] In this invention, the server includes means for acquiring user interaction as audio, means for converting the acquired audio into digital text, and means for extracting necessary registration information from the digital text. This enables real-time audio analysis and dynamic generation of contracts.

[0097] "Means for acquiring user interactions as audio" refers to a device or method that physically captures verbal communication between a user and a staff member and records it as audio data.

[0098] "Methods for converting acquired audio into digital text" refers to technologies that analyze collected audio data and convert it into corresponding textual information.

[0099] "Means for extracting necessary registration information from digital text" refers to an algorithm or process for selecting and classifying specific information from text data.

[0100] "Methods for automatically generating registration data based on extracted information" refers to a series of operations that automatically form the necessary documents and data based on selected information.

[0101] "Means for detecting insufficient explanation and providing supplementary information" refers to a mechanism that identifies missing information and provides additional information to the user.

[0102] "A means of presenting the generated registration data to the user for verification" refers to a method of displaying the created data to the user and having them verify that there are no errors in its contents.

[0103] "Means for completing the registration process based on user verification" refers to a system or process that performs final data processing once user approval is obtained.

[0104] "Methods for dynamically creating contract documents by analyzing customer requirements" refers to technologies that automatically evaluate customer requests and generate appropriate contract documents in real time based on those evaluations.

[0105] The system for implementing this invention primarily involves the cooperation of a server and a terminal. The terminal first collects audio data using its built-in microphone to capture the interaction with the user as voice. The collected audio data is processed in real time and transmitted to the server.

[0106] The server uses speech recognition software such as "speech_recognition" to convert this audio data into digital text. Next, natural language processing techniques are used to extract the necessary registration information from the digital text, and registration data is automatically generated based on that information. Data structuring algorithms are involved in the generation of registration data.

[0107] Furthermore, if the server detects insufficient explanation, it generates supplementary information and presents it to the user through the terminal. This feature allows the user to gain a thorough understanding of the contract details and options.

[0108] The generated registration data is presented to the user via the terminal, and they are asked to confirm it. Once the user confirms, the final registration process is completed by the server. This entire process enables the dynamic generation, confirmation, and provision of supplementary information of contracts in real time.

[0109] A concrete example would be a scenario where a mail-order agent at a physical store is interacting with a customer who wants a new communication plan. When the customer verbally states a request such as "I want to know about the new communication plan," the utterance is immediately analyzed, and an appropriate plan and contract are generated on the spot. An example of a prompt sentence for the generating AI model would be, "Analyze the voice input from the user and create information about the new smartphone plan."

[0110] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0111] Step 1:

[0112] The device captures the user's interaction as audio. Here, the built-in microphone is used to record the user's speech in real time. This audio data becomes the input for the next processing step.

[0113] Step 2:

[0114] The terminal sends the acquired audio data to the server. The server converts this audio data into digital text using speech recognition software such as "speech_recognition". This converted text data becomes the output for the next processing step.

[0115] Step 3:

[0116] The server analyzes the digital text using natural language processing technology and extracts the necessary registration information. Specifically, it extracts keywords related to contract items and pricing plans from the text. This analysis result forms the basis for generating registration data.

[0117] Step 4:

[0118] The server automatically generates a contract using a document generation algorithm based on the extracted registration information. This generated contract data is then output to the next processing step.

[0119] Step 5:

[0120] If the server detects insufficient explanation, it generates supplementary information. Additional documents or comments regarding sections lacking detail are generated and presented to the user via the terminal. This supplementary information complements communication with the user.

[0121] Step 6:

[0122] The terminal presents the generated contract data to the user and asks for confirmation of its contents. As this data is displayed on the screen, a prompt for the user's feedback is generated.

[0123] Step 7:

[0124] The terminal notifies the server that it has received user confirmation. The server completes the final registration process based on the confirmed contract. This completion process is the final result of all calculations based on the input.

[0125] 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.

[0126] This invention provides a system that combines speech recognition of conversations between a user and an operator with an emotion engine that recognizes the user's emotions. The system is implemented in the following manner.

[0127] 1. Speech Recognition and Sentiment Analysis

[0128] The device passes the conversation to a speech recognition engine, which converts it into text data, while an emotion engine analyzes the user's emotions from the conversation. For example, if the user is nervous, the emotion is determined from changes in their tension and tone of voice.

[0129] 2. Data extraction and registration process

[0130] The server analyzes the text data obtained through speech recognition and extracts the information necessary for registration. This generates registration data that clearly specifies the user's desired pricing plan and contract details.

[0131] 3. Emotion-based response adjustments

[0132] Based on information from the emotion engine, the device responds in accordance with the user's emotions. For example, if the user shows frustration, it will provide more polite explanations or faster procedures to improve user satisfaction.

[0133] 4. Supplementary explanation function

[0134] If the emotion engine determines, based on conversation and sentiment analysis, that the worker's explanation is insufficient, the terminal will automatically provide additional explanations about that information. This allows the user to reduce anxiety and obtain more accurate information.

[0135] 5. Confirmation screen and final procedure

[0136] The terminal displays the generated registration data on a confirmation screen and completes the registration process by requesting final confirmation and consent from the user. Upon receiving this confirmation, the server saves the registration details to the database.

[0137] This system accurately grasps user emotions based on interactions, enabling flexible responses. As a result, the user experience is significantly improved, and the registration process becomes more efficient. For example, by using the emotion engine to provide reassurance in situations where users feel anxious, the registration process becomes smoother.

[0138] The following describes the processing flow.

[0139] Step 1:

[0140] The device collects conversations between the user and the worker via the microphone. This audio data is sent to a speech recognition engine and converted into text data. Simultaneously, an emotion engine analyzes the user's emotions from the audio.

[0141] Step 2:

[0142] The server analyzes the text data and extracts the information necessary for registration. This includes the type of contract and the desired plan. The results of the emotion engine's analysis are also sent to the server, supplementing the information with details about the user's emotional state.

[0143] Step 3:

[0144] The server generates registration data based on the extracted information. This is also where information obtained from the emotion engine is used to create a flexible data structure tailored to the user's stress level.

[0145] Step 4:

[0146] The device reflects the analysis results from the emotion engine and takes appropriate action for the user. For example, if anxiety is detected, it provides additional support information and detailed explanations via voice or text.

[0147] Step 5:

[0148] The terminal displays the generated registration data to the user on a confirmation screen. The user can review the content and indicate their consent. If the user's emotions become unstable during this process, it is possible to display an operation guide or other appropriate support.

[0149] Step 6:

[0150] After the user confirms and agrees, the server performs the final registration process and saves the registration details to the database based on the confirmed information. This completes the registration process.

[0151] (Example 2)

[0152] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0153] Conventional interactive systems fail to provide a satisfactory user experience because they only perform standardized procedures without considering user emotions. In particular, the inability to respond quickly and appropriately to users who have anxieties or questions was a major problem. Furthermore, the lack of features to compensate for insufficient explanations during the voice recognition-based information registration process sometimes led to user misunderstandings. Solving these problems is essential.

[0154] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0155] In this invention, the server includes means for analyzing the user's emotional state and responding flexibly based on that information, means for converting acquired acoustic information into text information, and means for presenting the generated registration data to the user and prompting confirmation. This enables effective interaction that takes the user's emotions into consideration.

[0156] "Acoustic information" refers to data about human voices and ambient sounds acquired through voice acquisition devices such as microphones.

[0157] "Textual information" refers to data obtained by converting acoustic information into text format using speech recognition technology.

[0158] "Registration data" refers to a collection of necessary information generated within the system based on user requests and contract terms.

[0159] "Emotional state" refers to the psychological state or feelings detected from the user's speech and tone of voice.

[0160] "Flexible response" refers to the adaptive reactions and procedures that the system employs, changing according to the user's emotional state and circumstances.

[0161] A "confirmation response" is an action or statement by a user indicating approval or disapproval of data or procedures presented by a system.

[0162] In this invention, the system consists of a terminal and a server. The terminal is equipped with a device that collects audio between the user and the worker via a high-performance microphone. This acoustic information is transmitted to a speech recognition engine (e.g., speech recognition application technology) and converted into text information. The converted text information is transmitted to the server and analyzed using natural language processing technology. As a result of the analysis, the information necessary for registration data is extracted, and the server generates the registration data.

[0163] In addition, the device uses an emotion engine (e.g., emotion analysis application technology) to analyze the user's emotional state. Based on this emotional state, the device takes flexible actions that are appropriate to the user's situation. These actions include providing supplementary information using speech synthesis technology.

[0164] The server sends the generated registration data back to the terminal, which then presents it to the user for confirmation. Once the user confirms, the server completes the final registration process and saves the information to the database.

[0165] For example, when a user signs up for a new internet service contract, if they express a question during the registration process, the emotion engine will detect this dissatisfaction, and the device will provide necessary supplementary explanations to reassure them, such as "Your data is secure and can be accessed at any time."

[0166] An example of a prompt is, "Design a system that provides a standard reassuring message if the user may show signs of anxiety."

[0167] In this way, the system can take emotions into consideration during user interaction, enabling it to provide an effective and comfortable experience.

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

[0169] Step 1:

[0170] The terminal uses a microphone to capture voice conversations between the user and the worker in real time. The input is voice data, and the terminal performs noise filtering to extract clear acoustic information. The output is the filtered acoustic information.

[0171] Step 2:

[0172] The device passes the filtered acoustic information to the speech recognition engine, which converts it into text. The input is filtered acoustic information, and the device uses speech recognition technology to parse this acoustic information into a string. The output is text.

[0173] Step 3:

[0174] The server analyzes the text information received from the terminal and extracts the information necessary for registration. The input is text information sent from the terminal, and the server uses natural language processing techniques to calculate and extract the necessary data points (e.g., contract details and plan settings). The output is the registration data.

[0175] Step 4:

[0176] The device analyzes the user's emotions using an emotion engine based on registered data. The input consists of registered data and textual information from conversations. The device evaluates the user's emotional state (e.g., dissatisfaction, confidence, excitement) using emotion analysis technology. The output is the user's emotional information.

[0177] Step 5:

[0178] The device considers emotional information and provides flexible responses to the user. The input is emotional information, and the device uses natural language generation technology to determine the appropriate communication method. For example, it provides reassuring messages and clear explanations of procedures through voice output and screen display. The output is the result of the user interaction.

[0179] Step 6:

[0180] The terminal presents the registration data to the user and requests a confirmation response from the user. The input is the registration data, and the terminal uses a screen display or audio output device to have the user confirm the data and receive an approval or rejection response. The output is the user's confirmation response.

[0181] Step 7:

[0182] The server receives the user's acknowledgment and performs the final registration process. The input is the user's acknowledgment, the server registers the requested information in the database, and verifies data consistency. The output is the registered data.

[0183] This process enables the system to provide emotionally sensitive interactions with users and allows for efficient and smooth registration procedures.

[0184] (Application Example 2)

[0185] 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".

[0186] Traditional user dialogue systems could recognize user speech and extract and register necessary information, but they lacked the ability to respond flexibly based on user emotions. Therefore, it was difficult to provide appropriate support when users felt anxious or frustrated, hindering the improvement of the user experience. This challenge needs to be addressed to further enhance the user experience.

[0187] 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.

[0188] In this invention, the server includes means for acquiring voice data while interacting with the user, means for converting the acquired voice data into text data, means for extracting information necessary for registration from the text data, means for generating registration data based on the extracted information, means for detecting insufficient explanation from the user or operator and providing supplementary information, means for having the user confirm the generated registration data, means for completing the final registration process after receiving confirmation from the user, and means for analyzing the user's emotions and adjusting responses based on those emotions. This makes it possible to accurately grasp the user's emotions and respond appropriately, thereby improving the user experience.

[0189] A "user" is a person who uses the system to interact with others, provide voice data, and receive services.

[0190] A "worker" is someone who provides support and information during interactions with users.

[0191] "Audio data" refers to audio recordings of conversations between users and workers.

[0192] "Text data" refers to data obtained by converting audio data into written text.

[0193] "Means of extracting information" refers to the function of extracting and aggregating necessary information from text data.

[0194] "Registered data" refers to data that includes user preferences and contract details, created based on extracted information.

[0195] "Emotions" refer to the psychological state a user exhibits during a conversation, and are judged based on factors such as tone of voice and facial expressions.

[0196] The "emotion engine" is a function that analyzes the user's voice data to determine their emotions and state.

[0197] A "confirmation screen" is a screen that presents the user with the contents of their registered data and asks them to confirm it.

[0198] "Final registration processing" refers to the series of processes that formally save and process registration data after user verification.

[0199] This invention provides a system that improves the user experience by recognizing the user's voice in real time and analyzing their emotions. The system mainly consists of three elements: a server, a terminal, and the user.

[0200] The server collects audio data and converts it into text data using the Google® Cloud Speech-to-Text API. This text data is then used to analyze emotions using IBM Watson® Tone Analyzer. Based on the results of the emotion analysis, appropriate responses can be provided in real time according to the user's state.

[0201] The device uses this data to display a confirmation screen to the user through the user interface. After the user confirms and agrees, this information is stored in the AWS (registered trademark) cloud database.

[0202] For example, when a user makes an electronic payment, this system allows them to ask about the payee and amount via a voice interface. If the user expresses concern, the terminal automatically provides additional support information to reassure them. This allows the user to proceed with the transaction more smoothly.

[0203] Examples of prompts for the generative AI model include, "When a user utters a specific word, how should the application determine their emotions?" and "Generate scenarios to alleviate user anxiety during the payment process."

[0204] This invention utilizes speech recognition and sentiment analysis to improve the quality of user interactions. As a result, it is possible to improve user satisfaction and streamline processes.

[0205] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0206] Step 1:

[0207] The device acquires the user's voice data through the microphone. This acquired voice data is sent in real time to the Google Cloud Speech-to-Text API, where it is converted into text data. Here, the voice waveform data is the input, and the converted text information is the output.

[0208] Step 2:

[0209] The server receives text data and performs sentiment analysis using IBM Watson Tone Analyzer. The input is the text data obtained in step 1, and the output is a detailed evaluation of the user's emotional state. Specifically, the intensity and type of emotional tone are analyzed.

[0210] Step 3:

[0211] The server sends a notification to the terminal based on the sentiment analysis results to determine the appropriate course of action for the user. The input is the result of the sentiment analysis, and the output is the optimal course of action for the user. For example, if it is determined that the user is feeling anxious, the terminal will be instructed to provide additional information.

[0212] Step 4:

[0213] The terminal displays the necessary information to the user through the user interface. The input is the countermeasure determined in step 3, and the output is the information and additional support measures presented to the user. Specifically, detailed information and detailed guidelines are shown.

[0214] Step 5:

[0215] The user reviews the presented information and instructs the terminal to perform the final procedure. Input is the user's confirmation action, and output is the completed procedure data. This includes specific actions such as the user pressing a consent button.

[0216] Step 6:

[0217] The final registration data is saved by the server to the AWS cloud database. The input is the completed procedural data from step 5, and the output is the data securely stored in the cloud. This step specifically involves data backup and security protection.

[0218] 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.

[0219] 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.

[0220] 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.

[0221] [Second Embodiment]

[0222] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0223] 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.

[0224] 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).

[0225] 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.

[0226] 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.

[0227] 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).

[0228] 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.

[0229] 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.

[0230] 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.

[0231] 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.

[0232] 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.

[0233] 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".

[0234] The present invention provides a system that performs real-time speech recognition of conversations between users and operators, and efficiently facilitates the registration process. The system is configured as follows for implementation.

[0235] 1. Speech recognition engine

[0236] The terminal continuously captures conversations between the user and the worker via a microphone for voice input. This voice data is immediately sent to a speech recognition engine and converted into text data. For example, if the user says, "I would like to sign a new contract," the terminal records this information as text.

[0237] 2. Data Analysis Module

[0238] The server analyzes the text data and extracts information necessary for registration, such as contract type and pricing plan. The information obtained through this analysis forms the basis for generating registration data.

[0239] 3. Data Generation System

[0240] The server uses the analysis results to organize the information necessary for registration and constructs it as registration data. For example, if the user's desired pricing plan is identified, a corresponding contract is automatically prepared.

[0241] 4. Supplementary information presentation function

[0242] If the terminal determines that the operator's explanation is insufficient, it will automatically provide supplementary information to the user via voice or on screen. This feature allows the user to gain a thorough understanding of the contract details and options.

[0243] 5. Verification Interface

[0244] The terminal presents the final registration data to the user for confirmation. The server completes the registration process only after the user has confirmed and agreed to the information.

[0245] This system will solve the time-consuming and insufficient explanation problems of the conventional registration process, enabling fast and accurate registration. For example, smoother communication with users will allow registration to be completed on the spot, significantly reducing waiting times.

[0246] The following describes the processing flow.

[0247] Step 1:

[0248] The terminal captures the conversation between the user and the worker via a microphone for voice input. This voice data is sent in real time to a speech recognition engine and converted into text data.

[0249] Step 2:

[0250] The server analyzes the text data and extracts the information necessary for registration. At this stage, it identifies elements such as contract preferences and pricing plans.

[0251] Step 3:

[0252] The server generates registration data based on the analysis results. This includes the contents of the contract documents and details of the selected plan.

[0253] Step 4:

[0254] The terminal checks the adequacy of the worker's explanation, and if the explanation is insufficient, it provides supplementary information to the user via audio or on-screen display.

[0255] Step 5:

[0256] The terminal displays a confirmation screen of the generated registration data to the user. Here, the user can finally review the contract details and indicate their consent.

[0257] Step 6:

[0258] After the user confirms and agrees, the server completes the final registration process based on the confirmed information and saves it to the database as an official registration.

[0259] (Example 1)

[0260] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0261] Registration processes using acoustic information are time-consuming in conventional systems and can lead to insufficient explanations and misinterpretations of information. Furthermore, there are challenges in ensuring the accuracy of the generated information and the user's understanding. An efficient method is needed to facilitate smooth communication between users and operators and achieve accurate and rapid information registration.

[0262] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0263] In this invention, the server includes means for acquiring acoustic information while interacting with the user, means for converting the acquired acoustic information into text information, and means for extracting information necessary for registration from the text information. This enables efficient and accurate conversion of acoustic information into registration information, and facilitates efficient and reliable communication between the user and the operator.

[0264] "Acoustic information" refers to information obtained by acquiring sound or audio, and the data that is processed based on this information.

[0265] "Textual information" refers to information in text format converted from acoustic information, and serves as the foundational data for further analysis and processing.

[0266] "Registration information" refers to the data ultimately used, generated from the interaction between the user and the worker, and the results of its analysis.

[0267] "Additional information" refers to further information provided to supplement explanations given to users or workers that are insufficient.

[0268] A "user interface" refers to the screens and display devices that allow a user to interact with a system and input and output information.

[0269] "Acoustic recognition functionality" is a technical function that analyzes speech in real time and converts it into text information.

[0270] A "database" is a place where generated registration information and related data are systematically stored.

[0271] This system provides technology for quickly and accurately registering information based on user-operator interaction. The following hardware and software will be used for implementation.

[0272] The terminal continuously acquires acoustic information from the user and worker using a microphone. This acoustic information is instantly converted into text information through an acoustic recognition engine. The acoustic recognition engine uses software that utilizes the latest speech recognition technology. This converted text information is sent to a server, which extracts the necessary information for registration using a data analysis module that employs natural language processing technology.

[0273] The server constructs registration information based on the analysis results. For example, if a user requests a new contract, the server automatically generates registration information containing the necessary contract details and presents it to the user through the user interface. The user interface is a screen display device that assists the user in their operations and confirmations.

[0274] If the device detects insufficient explanation, it will provide audio or visual information to supplement it. This ensures the user fully understands the contract and can proceed with confidence. Once the user has confirmed the information, the server saves the registration information to the database and completes the registration process.

[0275] To improve the efficiency of this system, the prompt statements using the generative AI model are set as follows:

[0276] "Use speech recognition to transcribe user conversations into text in real time, extract necessary information, and generate registration data. Also, provide supplementary information if the user asks questions, and complete the registration once confirmation is received."

[0277] According to this prompt sentence, the generative AI model can perform the necessary processing at each step, enabling the smooth progress of the overall process.

[0278] The flow of the specific process in Example 1 will be described using FIG. 11.

[0279] Step 1:

[0280] The terminal acquires acoustic information via the microphone. The input is the conversation between the user and the operator, which is taken into the terminal as raw voice data. This voice data is preprocessed for noise reduction and sound quality improvement and then sent to the acoustic recognition engine. The output is the preprocessed voice data.

[0281] Step 2:

[0282] The server uses the acoustic recognition engine to convert the voice data into character information. The input is the preprocessed voice data, and the generative AI model is used to perform the acoustic recognition task. As data processing, phoneme extraction and matching are performed. The output is the converted character information.

[0283] Step 3:

[0284] The server analyzes the character information to extract the matters necessary for registration. The input is the character information sent to the server, and natural language processing algorithms are applied. Through data analysis, information such as the required contract form and fee plan is identified. The output is a list of the extracted matters.

[0285] Step 4:

[0286] The server generates registration information based on the extracted information. The input is the list of the extracted matters, and a registration form is automatically created based on a template. In this process, document construction and information embedding are performed. The output is a digital document of the constructed registration information.

[0287] Step 5:

[0288] The terminal detects when the operator's explanation is insufficient and provides additional information to the user if necessary. Input consists of user questions or points of confusion, which triggers the system to display additional information verbally or on the display. The system then searches for and presents relevant information. The output is the additional information presented to the user.

[0289] Step 6:

[0290] The terminal prompts the user to review and agree to the generated registration information. The input is a digital document of the constructed registration information, presented to the user on the user interface. In this review process, the user either clicks a confirmation button or gives voice approval. The output is the user's agreement or a request for correction.

[0291] Step 7:

[0292] The server confirms the user's information and completes the final registration process. The input is user consent information, and the registration information is stored in the database. The operation involves writing to the database and confirmation. The output is the completed registration procedure.

[0293] (Application Example 1)

[0294] 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."

[0295] Modern interactive services face the challenge of quickly and accurately acquiring information while interacting with users and providing immediate, optimal suggestions. In particular, real-time information generation and contract creation are required in in-store and field interactions, but conventional technologies lack the efficiency to do so effectively. Furthermore, misunderstandings and delays in agreement can occur due to insufficient explanation.

[0296] 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.

[0297] In this invention, the server includes means for acquiring user interaction as audio, means for converting the acquired audio into digital text, and means for extracting necessary registration information from the digital text. This enables real-time audio analysis and dynamic generation of contracts.

[0298] "Means for acquiring user interactions as audio" refers to a device or method that physically captures verbal communication between a user and a staff member and records it as audio data.

[0299] "Methods for converting acquired audio into digital text" refers to technologies that analyze collected audio data and convert it into corresponding textual information.

[0300] "Means for extracting necessary registration information from digital text" refers to an algorithm or process for selecting and classifying specific information from text data.

[0301] "Methods for automatically generating registration data based on extracted information" refers to a series of operations that automatically form the necessary documents and data based on selected information.

[0302] "Means for detecting insufficient explanation and providing supplementary information" refers to a mechanism that identifies missing information and provides additional information to the user.

[0303] "A means of presenting the generated registration data to the user for verification" refers to a method of displaying the created data to the user and having them verify that there are no errors in its contents.

[0304] "Means for completing the registration process based on user verification" refers to a system or process that performs final data processing once user approval is obtained.

[0305] The means of "analyzing customer requirements and dynamically creating contract documents" is a technology that automatically evaluates the requests issued by customers and generates appropriate contract documents in real time based on them.

[0306] The system for implementing this invention mainly operates with the cooperation of a server and a terminal. First, the terminal uses the built-in microphone to collect voice data in order to obtain the interaction with the user as voice. The collected voice data is processed in real time and sent to the server.

[0307] The server uses speech recognition software such as "speech_recognition" to convert this voice data into digital text. Next, it extracts the necessary registration information from the digital text using natural language processing technology and automatically generates registration data based on that information. A data structuring algorithm is involved in the generation of the registration data.

[0308] Also, when detecting insufficient explanations, the server generates supplementary information and presents the information to the user through the terminal. With this function, the user can obtain a sufficient understanding of the contract content and options.

[0309] The generated registration data is presented to the user via the terminal and a confirmation is requested. If the user's confirmation is obtained, the final registration process is completed by the server. Through this series of processes, the dynamic generation, confirmation, and provision of supplementary information of the contract document in real time are realized.

[0310] As a specific example, there is a situation where a telesales agent in a physical store is interacting with a customer who desires a new communication plan. When the customer verbally states a desire such as "I want to know about a new communication plan", the utterance is immediately analyzed and an appropriate plan and contract document are generated on the spot. An example of a prompt sentence for the generation AI model is "Analyze the voice input from the user and create materials for a new plan for a smartphone."

[0311] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0312] Step 1:

[0313] The device captures the user's interaction as audio. Here, the built-in microphone is used to record the user's speech in real time. This audio data becomes the input for the next processing step.

[0314] Step 2:

[0315] The terminal sends the acquired audio data to the server. The server converts this audio data into digital text using speech recognition software such as "speech_recognition". This converted text data becomes the output for the next processing step.

[0316] Step 3:

[0317] The server analyzes the digital text using natural language processing technology and extracts the necessary registration information. Specifically, it extracts keywords related to contract items and pricing plans from the text. This analysis result forms the basis for generating registration data.

[0318] Step 4:

[0319] The server automatically generates a contract using a document generation algorithm based on the extracted registration information. This generated contract data is then output to the next processing step.

[0320] Step 5:

[0321] If the server detects insufficient explanation, it generates supplementary information. Additional documents or comments regarding sections lacking detail are generated and presented to the user via the terminal. This supplementary information complements communication with the user.

[0322] Step 6:

[0323] The terminal presents the generated contract data to the user and asks for confirmation of its contents. As this data is displayed on the screen, a prompt for the user's feedback is generated.

[0324] Step 7:

[0325] The terminal notifies the server that it has received user confirmation. The server completes the final registration process based on the confirmed contract. This completion process is the final result of all calculations based on the input.

[0326] 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.

[0327] This invention provides a system that combines speech recognition of conversations between a user and an operator with an emotion engine that recognizes the user's emotions. The system is implemented in the following manner.

[0328] 1. Speech Recognition and Sentiment Analysis

[0329] The device passes the conversation to a speech recognition engine, which converts it into text data, while an emotion engine analyzes the user's emotions from the conversation. For example, if the user is nervous, the emotion is determined from changes in their tension and tone of voice.

[0330] 2. Data extraction and registration process

[0331] The server analyzes the text data obtained through speech recognition and extracts the information necessary for registration. This generates registration data that clearly specifies the user's desired pricing plan and contract details.

[0332] 3. Emotion-based response adjustments

[0333] Based on information from the emotion engine, the device responds in accordance with the user's emotions. For example, if the user shows frustration, it will provide more polite explanations or faster procedures to improve user satisfaction.

[0334] 4. Supplementary explanation function

[0335] If the emotion engine determines, based on conversation and sentiment analysis, that the worker's explanation is insufficient, the terminal will automatically provide additional explanations about that information. This allows the user to reduce anxiety and obtain more accurate information.

[0336] 5. Confirmation screen and final procedure

[0337] The terminal displays the generated registration data on a confirmation screen and completes the registration process by requesting final confirmation and consent from the user. Upon receiving this confirmation, the server saves the registration details to the database.

[0338] This system accurately grasps user emotions based on interactions, enabling flexible responses. As a result, the user experience is significantly improved, and the registration process becomes more efficient. For example, by using the emotion engine to provide reassurance in situations where users feel anxious, the registration process becomes smoother.

[0339] The following describes the processing flow.

[0340] Step 1:

[0341] The device collects conversations between the user and the worker via the microphone. This audio data is sent to a speech recognition engine and converted into text data. Simultaneously, an emotion engine analyzes the user's emotions from the audio.

[0342] Step 2:

[0343] The server analyzes the text data and extracts the information necessary for registration. This includes the type of contract and the desired plan. The results of the emotion engine's analysis are also sent to the server, supplementing the information with details about the user's emotional state.

[0344] Step 3:

[0345] The server generates registration data based on the extracted information. This is also where information obtained from the emotion engine is used to create a flexible data structure tailored to the user's stress level.

[0346] Step 4:

[0347] The device reflects the analysis results from the emotion engine and takes appropriate action for the user. For example, if anxiety is detected, it provides additional support information and detailed explanations via voice or text.

[0348] Step 5:

[0349] The terminal displays the generated registration data to the user on a confirmation screen. The user can review the content and indicate their consent. If the user's emotions become unstable during this process, it is possible to display an operation guide or other appropriate support.

[0350] Step 6:

[0351] After the user confirms and agrees, the server performs the final registration process and saves the registration details to the database based on the confirmed information. This completes the registration process.

[0352] (Example 2)

[0353] 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".

[0354] Conventional interactive systems fail to provide a satisfactory user experience because they only perform standardized procedures without considering user emotions. In particular, the inability to respond quickly and appropriately to users who have anxieties or questions was a major problem. Furthermore, the lack of features to compensate for insufficient explanations during the voice recognition-based information registration process sometimes led to user misunderstandings. Solving these problems is essential.

[0355] 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.

[0356] In this invention, the server includes means for analyzing the user's emotional state and responding flexibly based on that information, means for converting acquired acoustic information into text information, and means for presenting the generated registration data to the user and prompting confirmation. This enables effective interaction that takes the user's emotions into consideration.

[0357] "Acoustic information" refers to data about human voices and ambient sounds acquired through voice acquisition devices such as microphones.

[0358] "Textual information" refers to data obtained by converting acoustic information into text format using speech recognition technology.

[0359] "Registration data" refers to a collection of necessary information generated within the system based on user requests and contract terms.

[0360] "Emotional state" refers to the psychological state or feelings detected from the user's speech and tone of voice.

[0361] "Flexible response" refers to the adaptive reactions and procedures that the system employs, changing according to the user's emotional state and circumstances.

[0362] A "confirmation response" is an action or statement by a user indicating approval or disapproval of data or procedures presented by a system.

[0363] In this invention, the system consists of a terminal and a server. The terminal is equipped with a device that collects audio between the user and the worker via a high-performance microphone. This acoustic information is transmitted to a speech recognition engine (e.g., speech recognition application technology) and converted into text information. The converted text information is transmitted to the server and analyzed using natural language processing technology. As a result of the analysis, the information necessary for registration data is extracted, and the server generates the registration data.

[0364] In addition, the device uses an emotion engine (e.g., emotion analysis application technology) to analyze the user's emotional state. Based on this emotional state, the device takes flexible actions that are appropriate to the user's situation. These actions include providing supplementary information using speech synthesis technology.

[0365] The server sends the generated registration data back to the terminal, which then presents it to the user for confirmation. Once the user confirms, the server completes the final registration process and saves the information to the database.

[0366] For example, when a user signs up for a new internet service contract, if they express a question during the registration process, the emotion engine will detect this dissatisfaction, and the device will provide necessary supplementary explanations to reassure them, such as "Your data is secure and can be accessed at any time."

[0367] An example of a prompt is, "Design a system that provides a standard reassuring message if the user may show signs of anxiety."

[0368] In this way, the system can take emotions into consideration during user interaction, enabling it to provide an effective and comfortable experience.

[0369] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0370] Step 1:

[0371] The terminal uses a microphone to capture voice conversations between the user and the worker in real time. The input is voice data, and the terminal performs noise filtering to extract clear acoustic information. The output is the filtered acoustic information.

[0372] Step 2:

[0373] The device passes the filtered acoustic information to the speech recognition engine, which converts it into text. The input is filtered acoustic information, and the device uses speech recognition technology to parse this acoustic information into a string. The output is text.

[0374] Step 3:

[0375] The server analyzes the text information received from the terminal and extracts the information necessary for registration. The input is text information sent from the terminal, and the server uses natural language processing techniques to calculate and extract the necessary data points (e.g., contract details and plan settings). The output is the registration data.

[0376] Step 4:

[0377] The device analyzes the user's emotions using an emotion engine based on registered data. The input consists of registered data and textual information from conversations. The device evaluates the user's emotional state (e.g., dissatisfaction, confidence, excitement) using emotion analysis technology. The output is the user's emotional information.

[0378] Step 5:

[0379] The device considers emotional information and provides flexible responses to the user. The input is emotional information, and the device uses natural language generation technology to determine the appropriate communication method. For example, it provides reassuring messages and clear explanations of procedures through voice output and screen display. The output is the result of the user interaction.

[0380] Step 6:

[0381] The terminal presents the registration data to the user and requests a confirmation response from the user. The input is the registration data, and the terminal uses a screen display or audio output device to have the user confirm the data and receive an approval or rejection response. The output is the user's confirmation response.

[0382] Step 7:

[0383] The server receives the user's acknowledgment and performs the final registration process. The input is the user's acknowledgment, the server registers the requested information in the database, and verifies data consistency. The output is the registered data.

[0384] This process enables the system to provide emotionally sensitive interactions with users and allows for efficient and smooth registration procedures.

[0385] (Application Example 2)

[0386] 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 as the "terminal".

[0387] Traditional user dialogue systems could recognize user speech and extract and register necessary information, but they lacked the ability to respond flexibly based on user emotions. Therefore, it was difficult to provide appropriate support when users felt anxious or frustrated, hindering the improvement of the user experience. This challenge needs to be addressed to further enhance the user experience.

[0388] 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.

[0389] In this invention, the server includes means for acquiring voice data while interacting with the user, means for converting the acquired voice data into text data, means for extracting information necessary for registration from the text data, means for generating registration data based on the extracted information, means for detecting insufficient explanation from the user or operator and providing supplementary information, means for having the user confirm the generated registration data, means for completing the final registration process after receiving confirmation from the user, and means for analyzing the user's emotions and adjusting responses based on those emotions. This makes it possible to accurately grasp the user's emotions and respond appropriately, thereby improving the user experience.

[0390] A "user" is a person who uses the system to interact with others, provide voice data, and receive services.

[0391] A "worker" is someone who provides support and information during interactions with users.

[0392] "Audio data" refers to audio recordings of conversations between users and workers.

[0393] "Text data" refers to data obtained by converting audio data into written text.

[0394] "Means of extracting information" refers to the function of extracting and aggregating necessary information from text data.

[0395] "Registered data" refers to data that includes user preferences and contract details, created based on extracted information.

[0396] "Emotions" refer to the psychological state a user exhibits during a conversation, and are judged based on factors such as tone of voice and facial expressions.

[0397] The "emotion engine" is a function that analyzes the user's voice data to determine their emotions and state.

[0398] A "confirmation screen" is a screen that presents the user with the contents of their registered data and asks them to confirm it.

[0399] "Final registration processing" refers to the series of processes that formally save and process registration data after user verification.

[0400] This invention provides a system that improves the user experience by recognizing the user's voice in real time and analyzing their emotions. The system mainly consists of three elements: a server, a terminal, and the user.

[0401] The server collects audio data and converts it into text data using the Google Cloud Speech-to-Text API. Then, IBM Watson Tone Analyzer is used to analyze the emotions expressed in this text data. Based on the results of this emotion analysis, the system can provide real-time support to respond appropriately to the user's state.

[0402] The device uses this data to display a confirmation screen to the user through the user interface. After the user confirms and agrees, this information is stored in an AWS cloud database.

[0403] For example, when a user makes an electronic payment, this system allows them to ask about the payee and amount via a voice interface. If the user expresses concern, the terminal automatically provides additional support information to reassure them. This allows the user to proceed with the transaction more smoothly.

[0404] Examples of prompts for the generative AI model include, "When a user utters a specific word, how should the application determine their emotions?" and "Generate scenarios to alleviate user anxiety during the payment process."

[0405] This invention utilizes speech recognition and sentiment analysis to improve the quality of user interactions. As a result, it is possible to improve user satisfaction and streamline processes.

[0406] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0407] Step 1:

[0408] The device acquires the user's voice data through the microphone. This acquired voice data is sent in real time to the Google Cloud Speech-to-Text API, where it is converted into text data. Here, the voice waveform data is the input, and the converted text information is the output.

[0409] Step 2:

[0410] The server receives text data and performs sentiment analysis using IBM Watson Tone Analyzer. The input is the text data obtained in step 1, and the output is a detailed evaluation of the user's emotional state. Specifically, the intensity and type of emotional tone are analyzed.

[0411] Step 3:

[0412] The server sends a notification to the terminal based on the sentiment analysis results to determine the appropriate course of action for the user. The input is the result of the sentiment analysis, and the output is the optimal course of action for the user. For example, if it is determined that the user is feeling anxious, the terminal will be instructed to provide additional information.

[0413] Step 4:

[0414] The terminal displays the necessary information to the user through the user interface. The input is the countermeasure determined in step 3, and the output is the information and additional support measures presented to the user. Specifically, detailed information and detailed guidelines are shown.

[0415] Step 5:

[0416] The user reviews the presented information and instructs the terminal to perform the final procedure. Input is the user's confirmation action, and output is the completed procedure data. This includes specific actions such as the user pressing a consent button.

[0417] Step 6:

[0418] The final registration data is saved by the server to the AWS cloud database. The input is the completed procedural data from step 5, and the output is the data securely stored in the cloud. This step specifically involves data backup and security protection.

[0419] 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.

[0420] 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.

[0421] 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.

[0422] [Third Embodiment]

[0423] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0424] 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.

[0425] 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).

[0426] 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.

[0427] 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.

[0428] 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).

[0429] 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.

[0430] 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.

[0431] 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.

[0432] 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.

[0433] 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.

[0434] 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".

[0435] The present invention provides a system that performs real-time speech recognition of conversations between users and operators, and efficiently facilitates the registration process. The system is configured as follows for implementation.

[0436] 1. Speech recognition engine

[0437] The terminal continuously captures conversations between the user and the worker via a microphone for voice input. This voice data is immediately sent to a speech recognition engine and converted into text data. For example, if the user says, "I would like to sign a new contract," the terminal records this information as text.

[0438] 2. Data Analysis Module

[0439] The server analyzes the text data and extracts information necessary for registration, such as contract type and pricing plan. The information obtained through this analysis forms the basis for generating registration data.

[0440] 3. Data Generation System

[0441] The server uses the analysis results to organize the information necessary for registration and constructs it as registration data. For example, if the user's desired pricing plan is identified, a corresponding contract is automatically prepared.

[0442] 4. Supplementary information presentation function

[0443] If the terminal determines that the operator's explanation is insufficient, it will automatically provide supplementary information to the user via voice or on screen. This feature allows the user to gain a thorough understanding of the contract details and options.

[0444] 5. Verification Interface

[0445] The terminal presents the final registration data to the user for confirmation. The server completes the registration process only after the user has confirmed and agreed to the information.

[0446] This system will solve the time-consuming and insufficient explanation problems of the conventional registration process, enabling fast and accurate registration. For example, smoother communication with users will allow registration to be completed on the spot, significantly reducing waiting times.

[0447] The following describes the processing flow.

[0448] Step 1:

[0449] The terminal captures the conversation between the user and the worker via a microphone for voice input. This voice data is sent in real time to a speech recognition engine and converted into text data.

[0450] Step 2:

[0451] The server analyzes the text data and extracts the information necessary for registration. At this stage, it identifies elements such as contract preferences and pricing plans.

[0452] Step 3:

[0453] The server generates registration data based on the analysis results. This includes the contents of the contract documents and details of the selected plan.

[0454] Step 4:

[0455] The terminal checks the adequacy of the worker's explanation, and if the explanation is insufficient, it provides supplementary information to the user via audio or on-screen display.

[0456] Step 5:

[0457] The terminal displays a confirmation screen of the generated registration data to the user. Here, the user can finally review the contract details and indicate their consent.

[0458] Step 6:

[0459] After the user confirms and agrees, the server completes the final registration process based on the confirmed information and saves it to the database as an official registration.

[0460] (Example 1)

[0461] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0462] Registration processes using acoustic information are time-consuming in conventional systems and can lead to insufficient explanations and misinterpretations of information. Furthermore, there are challenges in ensuring the accuracy of the generated information and the user's understanding. An efficient method is needed to facilitate smooth communication between users and operators and achieve accurate and rapid information registration.

[0463] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0464] In this invention, the server includes means for acquiring acoustic information while interacting with the user, means for converting the acquired acoustic information into text information, and means for extracting information necessary for registration from the text information. This enables efficient and accurate conversion of acoustic information into registration information, and facilitates efficient and reliable communication between the user and the operator.

[0465] "Acoustic information" refers to information obtained by acquiring sound or audio, and the data that is processed based on this information.

[0466] "Textual information" refers to information in text format converted from acoustic information, and serves as the foundational data for further analysis and processing.

[0467] "Registration information" refers to the data ultimately used, generated from the interaction between the user and the worker, and the results of its analysis.

[0468] "Additional information" refers to further information provided to supplement explanations given to users or workers that are insufficient.

[0469] A "user interface" refers to the screens and display devices that allow a user to interact with a system and input and output information.

[0470] "Acoustic recognition functionality" is a technical function that analyzes speech in real time and converts it into text information.

[0471] A "database" is a place where generated registration information and related data are systematically stored.

[0472] This system provides technology for quickly and accurately registering information based on user-operator interaction. The following hardware and software will be used for implementation.

[0473] The terminal continuously acquires acoustic information from the user and worker using a microphone. This acoustic information is instantly converted into text information through an acoustic recognition engine. The acoustic recognition engine uses software that utilizes the latest speech recognition technology. This converted text information is sent to a server, which extracts the necessary information for registration using a data analysis module that employs natural language processing technology.

[0474] The server constructs registration information based on the analysis results. For example, if a user requests a new contract, the server automatically generates registration information containing the necessary contract details and presents it to the user through the user interface. The user interface is a screen display device that assists the user in their operations and confirmations.

[0475] If the device detects insufficient explanation, it will provide audio or visual information to supplement it. This ensures the user fully understands the contract and can proceed with confidence. Once the user has confirmed the information, the server saves the registration information to the database and completes the registration process.

[0476] To improve the efficiency of this system, the prompt statements using the generative AI model are set as follows:

[0477] "Use speech recognition to transcribe user conversations into text in real time, extract necessary information, and generate registration data. Also, provide supplementary information if the user asks questions, and complete the registration once confirmation is received."

[0478] By following these prompts, the generative AI model can perform the necessary processing at each step, ensuring the overall process runs smoothly.

[0479] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0480] Step 1:

[0481] The terminal acquires acoustic information via the microphone. The input is a conversation between the user and the worker, and it is captured by the terminal as raw audio data. This audio data is pre-processed for noise reduction and sound quality improvement before being sent to the acoustic recognition engine. The output is the pre-processed audio data.

[0482] Step 2:

[0483] The server uses an acoustic recognition engine to convert speech data into text information. The input is pre-processed speech data, and a generative AI model is used to perform the speech recognition task. Data processing includes phoneme extraction and matching. The output is the converted text information.

[0484] Step 3:

[0485] The server analyzes the text information and extracts the necessary details for registration. The input is text information sent to the server, and a natural language processing algorithm is applied. Through data analysis, necessary information such as contract type and pricing plan is identified. The output is a list of the extracted items.

[0486] Step 4:

[0487] The server generates registration information based on the extracted data. The input is a list of extracted items, and the server automatically creates a registration form based on a template. This process involves document construction and information embedding. The output is a digital document containing the constructed registration information.

[0488] Step 5:

[0489] The terminal detects when the operator's explanation is insufficient and provides additional information to the user if necessary. Input consists of user questions or points of confusion, which triggers the system to display additional information verbally or on the display. The system then searches for and presents relevant information. The output is the additional information presented to the user.

[0490] Step 6:

[0491] The terminal prompts the user to review and agree to the generated registration information. The input is a digital document of the constructed registration information, presented to the user on the user interface. In this review process, the user either clicks a confirmation button or gives voice approval. The output is the user's agreement or a request for correction.

[0492] Step 7:

[0493] The server confirms the user's information and completes the final registration process. The input is user consent information, and the registration information is stored in the database. The operation involves writing to the database and confirmation. The output is the completed registration procedure.

[0494] (Application Example 1)

[0495] 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."

[0496] Modern interactive services face the challenge of quickly and accurately acquiring information while interacting with users and providing immediate, optimal suggestions. In particular, real-time information generation and contract creation are required in in-store and field interactions, but conventional technologies lack the efficiency to do so effectively. Furthermore, misunderstandings and delays in agreement can occur due to insufficient explanation.

[0497] 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.

[0498] In this invention, the server includes means for acquiring user interaction as audio, means for converting the acquired audio into digital text, and means for extracting necessary registration information from the digital text. This enables real-time audio analysis and dynamic generation of contracts.

[0499] "Means for acquiring user interactions as audio" refers to a device or method that physically captures verbal communication between a user and a staff member and records it as audio data.

[0500] "Methods for converting acquired audio into digital text" refers to technologies that analyze collected audio data and convert it into corresponding textual information.

[0501] "Means for extracting necessary registration information from digital text" refers to an algorithm or process for selecting and classifying specific information from text data.

[0502] "Methods for automatically generating registration data based on extracted information" refers to a series of operations that automatically form the necessary documents and data based on selected information.

[0503] "Means for detecting insufficient explanation and providing supplementary information" refers to a mechanism that identifies missing information and provides additional information to the user.

[0504] "A means of presenting the generated registration data to the user for verification" refers to a method of displaying the created data to the user and having them verify that there are no errors in its contents.

[0505] "Means for completing the registration process based on user verification" refers to a system or process that performs final data processing once user approval is obtained.

[0506] "Methods for dynamically creating contract documents by analyzing customer requirements" refers to technologies that automatically evaluate customer requests and generate appropriate contract documents in real time based on those evaluations.

[0507] The system for implementing this invention primarily involves the cooperation of a server and a terminal. The terminal first collects audio data using its built-in microphone to capture the interaction with the user as voice. The collected audio data is processed in real time and transmitted to the server.

[0508] The server uses speech recognition software such as "speech_recognition" to convert this audio data into digital text. Next, natural language processing techniques are used to extract the necessary registration information from the digital text, and registration data is automatically generated based on that information. Data structuring algorithms are involved in the generation of registration data.

[0509] Furthermore, if the server detects insufficient explanation, it generates supplementary information and presents it to the user through the terminal. This feature allows the user to gain a thorough understanding of the contract details and options.

[0510] The generated registration data is presented to the user via the terminal, and they are asked to confirm it. Once the user confirms, the final registration process is completed by the server. This entire process enables the dynamic generation, confirmation, and provision of supplementary information of contracts in real time.

[0511] A concrete example would be a scenario where a mail-order agent at a physical store is interacting with a customer who wants a new communication plan. When the customer verbally states a request such as "I want to know about the new communication plan," the utterance is immediately analyzed, and an appropriate plan and contract are generated on the spot. An example of a prompt sentence for the generating AI model would be, "Analyze the voice input from the user and create information about the new smartphone plan."

[0512] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0513] Step 1:

[0514] The device captures the user's interaction as audio. Here, the built-in microphone is used to record the user's speech in real time. This audio data becomes the input for the next processing step.

[0515] Step 2:

[0516] The terminal sends the acquired audio data to the server. The server converts this audio data into digital text using speech recognition software such as "speech_recognition". This converted text data becomes the output for the next processing step.

[0517] Step 3:

[0518] The server analyzes the digital text using natural language processing technology and extracts the necessary registration information. Specifically, it extracts keywords related to contract items and pricing plans from the text. This analysis result forms the basis for generating registration data.

[0519] Step 4:

[0520] The server automatically generates a contract using a document generation algorithm based on the extracted registration information. This generated contract data is then output to the next processing step.

[0521] Step 5:

[0522] If the server detects insufficient explanation, it generates supplementary information. Additional documents or comments regarding sections lacking detail are generated and presented to the user via the terminal. This supplementary information complements communication with the user.

[0523] Step 6:

[0524] The terminal presents the generated contract data to the user and asks for confirmation of its contents. As this data is displayed on the screen, a prompt for the user's feedback is generated.

[0525] Step 7:

[0526] The terminal notifies the server that it has received user confirmation. The server completes the final registration process based on the confirmed contract. This completion process is the final result of all calculations based on the input.

[0527] 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.

[0528] This invention provides a system that combines speech recognition of conversations between a user and an operator with an emotion engine that recognizes the user's emotions. The system is implemented in the following manner.

[0529] 1. Speech Recognition and Sentiment Analysis

[0530] The device passes the conversation to a speech recognition engine, which converts it into text data, while an emotion engine analyzes the user's emotions from the conversation. For example, if the user is nervous, the emotion is determined from changes in their tension and tone of voice.

[0531] 2. Data extraction and registration process

[0532] The server analyzes the text data obtained through speech recognition and extracts the information necessary for registration. This generates registration data that clearly specifies the user's desired pricing plan and contract details.

[0533] 3. Emotion-based response adjustments

[0534] Based on information from the emotion engine, the device responds in accordance with the user's emotions. For example, if the user shows frustration, it will provide more polite explanations or faster procedures to improve user satisfaction.

[0535] 4. Supplementary explanation function

[0536] If the emotion engine determines, based on conversation and sentiment analysis, that the worker's explanation is insufficient, the terminal will automatically provide additional explanations about that information. This allows the user to reduce anxiety and obtain more accurate information.

[0537] 5. Confirmation screen and final procedure

[0538] The terminal displays the generated registration data on a confirmation screen and completes the registration process by requesting final confirmation and consent from the user. Upon receiving this confirmation, the server saves the registration details to the database.

[0539] This system accurately grasps user emotions based on interactions, enabling flexible responses. As a result, the user experience is significantly improved, and the registration process becomes more efficient. For example, by using the emotion engine to provide reassurance in situations where users feel anxious, the registration process becomes smoother.

[0540] The following describes the processing flow.

[0541] Step 1:

[0542] The device collects conversations between the user and the worker via the microphone. This audio data is sent to a speech recognition engine and converted into text data. Simultaneously, an emotion engine analyzes the user's emotions from the audio.

[0543] Step 2:

[0544] The server analyzes the text data and extracts the information necessary for registration. This includes the type of contract and the desired plan. The results of the emotion engine's analysis are also sent to the server, supplementing the information with details about the user's emotional state.

[0545] Step 3:

[0546] The server generates registration data based on the extracted information. This is also where information obtained from the emotion engine is used to create a flexible data structure tailored to the user's stress level.

[0547] Step 4:

[0548] The device reflects the analysis results from the emotion engine and takes appropriate action for the user. For example, if anxiety is detected, it provides additional support information and detailed explanations via voice or text.

[0549] Step 5:

[0550] The terminal displays the generated registration data to the user on a confirmation screen. The user can review the content and indicate their consent. If the user's emotions become unstable during this process, it is possible to display an operation guide or other appropriate support.

[0551] Step 6:

[0552] After the user confirms and agrees, the server performs the final registration process and saves the registration details to the database based on the confirmed information. This completes the registration process.

[0553] (Example 2)

[0554] 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."

[0555] Conventional interactive systems fail to provide a satisfactory user experience because they only perform standardized procedures without considering user emotions. In particular, the inability to respond quickly and appropriately to users who have anxieties or questions was a major problem. Furthermore, the lack of features to compensate for insufficient explanations during the voice recognition-based information registration process sometimes led to user misunderstandings. Solving these problems is essential.

[0556] 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.

[0557] In this invention, the server includes means for analyzing the user's emotional state and responding flexibly based on that information, means for converting acquired acoustic information into text information, and means for presenting the generated registration data to the user and prompting confirmation. This enables effective interaction that takes the user's emotions into consideration.

[0558] "Acoustic information" refers to data about human voices and ambient sounds acquired through voice acquisition devices such as microphones.

[0559] "Textual information" refers to data obtained by converting acoustic information into text format using speech recognition technology.

[0560] "Registration data" refers to a collection of necessary information generated within the system based on user requests and contract terms.

[0561] "Emotional state" refers to the psychological state or feelings detected from the user's speech and tone of voice.

[0562] "Flexible response" refers to the adaptive reactions and procedures that the system employs, changing according to the user's emotional state and circumstances.

[0563] A "confirmation response" is an action or statement by a user indicating approval or disapproval of data or procedures presented by a system.

[0564] In this invention, the system consists of a terminal and a server. The terminal is equipped with a device that collects audio between the user and the worker via a high-performance microphone. This acoustic information is transmitted to a speech recognition engine (e.g., speech recognition application technology) and converted into text information. The converted text information is transmitted to the server and analyzed using natural language processing technology. As a result of the analysis, the information necessary for registration data is extracted, and the server generates the registration data.

[0565] In addition, the device uses an emotion engine (e.g., emotion analysis application technology) to analyze the user's emotional state. Based on this emotional state, the device takes flexible actions that are appropriate to the user's situation. These actions include providing supplementary information using speech synthesis technology.

[0566] The server sends the generated registration data back to the terminal, which then presents it to the user for confirmation. Once the user confirms, the server completes the final registration process and saves the information to the database.

[0567] For example, when a user signs up for a new internet service contract, if they express a question during the registration process, the emotion engine will detect this dissatisfaction, and the device will provide necessary supplementary explanations to reassure them, such as "Your data is secure and can be accessed at any time."

[0568] An example of a prompt is, "Design a system that provides a standard reassuring message if the user may show signs of anxiety."

[0569] In this way, the system can take emotions into consideration during user interaction, enabling it to provide an effective and comfortable experience.

[0570] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0571] Step 1:

[0572] The terminal uses a microphone to capture voice conversations between the user and the worker in real time. The input is voice data, and the terminal performs noise filtering to extract clear acoustic information. The output is the filtered acoustic information.

[0573] Step 2:

[0574] The device passes the filtered acoustic information to the speech recognition engine, which converts it into text. The input is filtered acoustic information, and the device uses speech recognition technology to parse this acoustic information into a string. The output is text.

[0575] Step 3:

[0576] The server analyzes the text information received from the terminal and extracts the information necessary for registration. The input is text information sent from the terminal, and the server uses natural language processing techniques to calculate and extract the necessary data points (e.g., contract details and plan settings). The output is the registration data.

[0577] Step 4:

[0578] The device analyzes the user's emotions using an emotion engine based on registered data. The input consists of registered data and textual information from conversations. The device evaluates the user's emotional state (e.g., dissatisfaction, confidence, excitement) using emotion analysis technology. The output is the user's emotional information.

[0579] Step 5:

[0580] The device considers emotional information and provides flexible responses to the user. The input is emotional information, and the device uses natural language generation technology to determine the appropriate communication method. For example, it provides reassuring messages and clear explanations of procedures through voice output and screen display. The output is the result of the user interaction.

[0581] Step 6:

[0582] The terminal presents the registration data to the user and requests a confirmation response from the user. The input is the registration data, and the terminal uses a screen display or audio output device to have the user confirm the data and receive an approval or rejection response. The output is the user's confirmation response.

[0583] Step 7:

[0584] The server receives the user's acknowledgment and performs the final registration process. The input is the user's acknowledgment, the server registers the requested information in the database, and verifies data consistency. The output is the registered data.

[0585] This process enables the system to provide emotionally sensitive interactions with users and allows for efficient and smooth registration procedures.

[0586] (Application Example 2)

[0587] 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."

[0588] Traditional user dialogue systems could recognize user speech and extract and register necessary information, but they lacked the ability to respond flexibly based on user emotions. Therefore, it was difficult to provide appropriate support when users felt anxious or frustrated, hindering the improvement of the user experience. This challenge needs to be addressed to further enhance the user experience.

[0589] 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.

[0590] In this invention, the server includes means for acquiring voice data while interacting with the user, means for converting the acquired voice data into text data, means for extracting information necessary for registration from the text data, means for generating registration data based on the extracted information, means for detecting insufficient explanation from the user or operator and providing supplementary information, means for having the user confirm the generated registration data, means for completing the final registration process after receiving confirmation from the user, and means for analyzing the user's emotions and adjusting responses based on those emotions. This makes it possible to accurately grasp the user's emotions and respond appropriately, thereby improving the user experience.

[0591] A "user" is a person who uses the system to interact with others, provide voice data, and receive services.

[0592] A "worker" is someone who provides support and information during interactions with users.

[0593] "Audio data" refers to audio recordings of conversations between users and workers.

[0594] "Text data" refers to data obtained by converting audio data into written text.

[0595] "Means of extracting information" refers to the function of extracting and aggregating necessary information from text data.

[0596] "Registered data" refers to data that includes user preferences and contract details, created based on extracted information.

[0597] "Emotions" refer to the psychological state a user exhibits during a conversation, and are judged based on factors such as tone of voice and facial expressions.

[0598] The "emotion engine" is a function that analyzes the user's voice data to determine their emotions and state.

[0599] A "confirmation screen" is a screen that presents the user with the contents of their registered data and asks them to confirm it.

[0600] "Final registration processing" refers to the series of processes that formally save and process registration data after user verification.

[0601] This invention provides a system that improves the user experience by recognizing the user's voice in real time and analyzing their emotions. The system mainly consists of three elements: a server, a terminal, and the user.

[0602] The server collects audio data and converts it into text data using the Google Cloud Speech-to-Text API. Then, IBM Watson Tone Analyzer is used to analyze the emotions expressed in this text data. Based on the results of this emotion analysis, the system can provide real-time support to respond appropriately to the user's state.

[0603] The device uses this data to display a confirmation screen to the user through the user interface. After the user confirms and agrees, this information is stored in an AWS cloud database.

[0604] For example, when a user makes an electronic payment, this system allows them to ask about the payee and amount via a voice interface. If the user expresses concern, the terminal automatically provides additional support information to reassure them. This allows the user to proceed with the transaction more smoothly.

[0605] Examples of prompts for the generative AI model include, "When a user utters a specific word, how should the application determine their emotions?" and "Generate scenarios to alleviate user anxiety during the payment process."

[0606] This invention utilizes speech recognition and sentiment analysis to improve the quality of user interactions. As a result, it is possible to improve user satisfaction and streamline processes.

[0607] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0608] Step 1:

[0609] The device acquires the user's voice data through the microphone. This acquired voice data is sent in real time to the Google Cloud Speech-to-Text API, where it is converted into text data. Here, the voice waveform data is the input, and the converted text information is the output.

[0610] Step 2:

[0611] The server receives text data and performs sentiment analysis using IBM Watson Tone Analyzer. The input is the text data obtained in step 1, and the output is a detailed evaluation of the user's emotional state. Specifically, the intensity and type of emotional tone are analyzed.

[0612] Step 3:

[0613] The server sends a notification to the terminal based on the sentiment analysis results to determine the appropriate course of action for the user. The input is the result of the sentiment analysis, and the output is the optimal course of action for the user. For example, if it is determined that the user is feeling anxious, the terminal will be instructed to provide additional information.

[0614] Step 4:

[0615] The terminal displays the necessary information to the user through the user interface. The input is the countermeasure determined in step 3, and the output is the information and additional support measures presented to the user. Specifically, detailed information and detailed guidelines are shown.

[0616] Step 5:

[0617] The user reviews the presented information and instructs the terminal to perform the final procedure. Input is the user's confirmation action, and output is the completed procedure data. This includes specific actions such as the user pressing a consent button.

[0618] Step 6:

[0619] The final registration data is saved by the server to the AWS cloud database. The input is the completed procedural data from step 5, and the output is the data securely stored in the cloud. This step specifically involves data backup and security protection.

[0620] 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.

[0621] 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.

[0622] 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.

[0623] [Fourth Embodiment]

[0624] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0625] 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.

[0626] 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).

[0627] 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.

[0628] 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.

[0629] 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).

[0630] 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.

[0631] 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.

[0632] 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.

[0633] 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.

[0634] 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.

[0635] 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.

[0636] 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".

[0637] The present invention provides a system that performs real-time speech recognition of conversations between users and operators, and efficiently facilitates the registration process. The system is configured as follows for implementation.

[0638] 1. Speech recognition engine

[0639] The terminal continuously captures conversations between the user and the worker via a microphone for voice input. This voice data is immediately sent to a speech recognition engine and converted into text data. For example, if the user says, "I would like to sign a new contract," the terminal records this information as text.

[0640] 2. Data Analysis Module

[0641] The server analyzes the text data and extracts information necessary for registration, such as contract type and pricing plan. The information obtained through this analysis forms the basis for generating registration data.

[0642] 3. Data Generation System

[0643] The server uses the analysis results to organize the information necessary for registration and constructs it as registration data. For example, if the user's desired pricing plan is identified, a corresponding contract is automatically prepared.

[0644] 4. Supplementary information presentation function

[0645] If the terminal determines that the operator's explanation is insufficient, it will automatically provide supplementary information to the user via voice or on screen. This feature allows the user to gain a thorough understanding of the contract details and options.

[0646] 5. Verification Interface

[0647] The terminal presents the final registration data to the user for confirmation. The server completes the registration process only after the user has confirmed and agreed to the information.

[0648] This system will solve the time-consuming and insufficient explanation problems of the conventional registration process, enabling fast and accurate registration. For example, smoother communication with users will allow registration to be completed on the spot, significantly reducing waiting times.

[0649] The following describes the processing flow.

[0650] Step 1:

[0651] The terminal captures the conversation between the user and the worker via a microphone for voice input. This voice data is sent in real time to a speech recognition engine and converted into text data.

[0652] Step 2:

[0653] The server analyzes the text data and extracts the information necessary for registration. At this stage, it identifies elements such as contract preferences and pricing plans.

[0654] Step 3:

[0655] The server generates registration data based on the analysis results. This includes the contents of the contract documents and details of the selected plan.

[0656] Step 4:

[0657] The terminal checks the adequacy of the worker's explanation, and if the explanation is insufficient, it provides supplementary information to the user via audio or on-screen display.

[0658] Step 5:

[0659] The terminal displays a confirmation screen of the generated registration data to the user. Here, the user can finally review the contract details and indicate their consent.

[0660] Step 6:

[0661] After the user confirms and agrees, the server completes the final registration process based on the confirmed information and saves it to the database as an official registration.

[0662] (Example 1)

[0663] 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".

[0664] Registration processes using acoustic information are time-consuming in conventional systems and can lead to insufficient explanations and misinterpretations of information. Furthermore, there are challenges in ensuring the accuracy of the generated information and the user's understanding. An efficient method is needed to facilitate smooth communication between users and operators and achieve accurate and rapid information registration.

[0665] 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.

[0666] In this invention, the server includes means for acquiring acoustic information while interacting with the user, means for converting the acquired acoustic information into text information, and means for extracting information necessary for registration from the text information. This enables efficient and accurate conversion of acoustic information into registration information, and facilitates efficient and reliable communication between the user and the operator.

[0667] "Acoustic information" refers to information obtained by acquiring sound or audio, and the data that is processed based on this information.

[0668] "Textual information" refers to information in text format converted from acoustic information, and serves as the foundational data for further analysis and processing.

[0669] "Registration information" refers to the data ultimately used, generated from the interaction between the user and the worker, and the results of its analysis.

[0670] "Additional information" refers to further information provided to supplement explanations given to users or workers that are insufficient.

[0671] A "user interface" refers to the screens and display devices that allow a user to interact with a system and input and output information.

[0672] "Acoustic recognition functionality" is a technical function that analyzes speech in real time and converts it into text information.

[0673] A "database" is a place where generated registration information and related data are systematically stored.

[0674] This system provides technology for quickly and accurately registering information based on user-operator interaction. The following hardware and software will be used for implementation.

[0675] The terminal continuously acquires acoustic information from the user and worker using a microphone. This acoustic information is instantly converted into text information through an acoustic recognition engine. The acoustic recognition engine uses software that utilizes the latest speech recognition technology. This converted text information is sent to a server, which extracts the necessary information for registration using a data analysis module that employs natural language processing technology.

[0676] The server constructs registration information based on the analysis results. For example, if a user requests a new contract, the server automatically generates registration information containing the necessary contract details and presents it to the user through the user interface. The user interface is a screen display device that assists the user in their operations and confirmations.

[0677] If the device detects insufficient explanation, it will provide audio or visual information to supplement it. This ensures the user fully understands the contract and can proceed with confidence. Once the user has confirmed the information, the server saves the registration information to the database and completes the registration process.

[0678] To improve the efficiency of this system, the prompt statements using the generative AI model are set as follows:

[0679] "Use speech recognition to transcribe user conversations into text in real time, extract necessary information, and generate registration data. Also, provide supplementary information if the user asks questions, and complete the registration once confirmation is received."

[0680] By following these prompts, the generative AI model can perform the necessary processing at each step, ensuring the overall process runs smoothly.

[0681] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0682] Step 1:

[0683] The terminal acquires acoustic information via the microphone. The input is a conversation between the user and the worker, and it is captured by the terminal as raw audio data. This audio data is pre-processed for noise reduction and sound quality improvement before being sent to the acoustic recognition engine. The output is the pre-processed audio data.

[0684] Step 2:

[0685] The server uses an acoustic recognition engine to convert speech data into text information. The input is pre-processed speech data, and a generative AI model is used to perform the speech recognition task. Data processing includes phoneme extraction and matching. The output is the converted text information.

[0686] Step 3:

[0687] The server analyzes the text information and extracts the necessary details for registration. The input is text information sent to the server, and a natural language processing algorithm is applied. Through data analysis, necessary information such as contract type and pricing plan is identified. The output is a list of the extracted items.

[0688] Step 4:

[0689] The server generates registration information based on the extracted data. The input is a list of extracted items, and the server automatically creates a registration form based on a template. This process involves document construction and information embedding. The output is a digital document containing the constructed registration information.

[0690] Step 5:

[0691] The terminal detects when the operator's explanation is insufficient and provides additional information to the user if necessary. Input consists of user questions or points of confusion, which triggers the system to display additional information verbally or on the display. The system then searches for and presents relevant information. The output is the additional information presented to the user.

[0692] Step 6:

[0693] The terminal prompts the user to review and agree to the generated registration information. The input is a digital document of the constructed registration information, presented to the user on the user interface. In this review process, the user either clicks a confirmation button or gives voice approval. The output is the user's agreement or a request for correction.

[0694] Step 7:

[0695] The server confirms the user's information and completes the final registration process. The input is user consent information, and the registration information is stored in the database. The operation involves writing to the database and confirmation. The output is the completed registration procedure.

[0696] (Application Example 1)

[0697] 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".

[0698] Modern interactive services face the challenge of quickly and accurately acquiring information while interacting with users and providing immediate, optimal suggestions. In particular, real-time information generation and contract creation are required in in-store and field interactions, but conventional technologies lack the efficiency to do so effectively. Furthermore, misunderstandings and delays in agreement can occur due to insufficient explanation.

[0699] 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.

[0700] In this invention, the server includes means for acquiring user interaction as audio, means for converting the acquired audio into digital text, and means for extracting necessary registration information from the digital text. This enables real-time audio analysis and dynamic generation of contracts.

[0701] "Means for acquiring user interactions as audio" refers to a device or method that physically captures verbal communication between a user and a staff member and records it as audio data.

[0702] "Methods for converting acquired audio into digital text" refers to technologies that analyze collected audio data and convert it into corresponding textual information.

[0703] "Means for extracting necessary registration information from digital text" refers to an algorithm or process for selecting and classifying specific information from text data.

[0704] "Methods for automatically generating registration data based on extracted information" refers to a series of operations that automatically form the necessary documents and data based on selected information.

[0705] "Means for detecting insufficient explanation and providing supplementary information" refers to a mechanism that identifies missing information and provides additional information to the user.

[0706] "A means of presenting the generated registration data to the user for verification" refers to a method of displaying the created data to the user and having them verify that there are no errors in its contents.

[0707] "Means for completing the registration process based on user verification" refers to a system or process that performs final data processing once user approval is obtained.

[0708] "Methods for dynamically creating contract documents by analyzing customer requirements" refers to technologies that automatically evaluate customer requests and generate appropriate contract documents in real time based on those evaluations.

[0709] The system for implementing this invention primarily involves the cooperation of a server and a terminal. The terminal first collects audio data using its built-in microphone to capture the interaction with the user as voice. The collected audio data is processed in real time and transmitted to the server.

[0710] The server uses speech recognition software such as "speech_recognition" to convert this audio data into digital text. Next, natural language processing techniques are used to extract the necessary registration information from the digital text, and registration data is automatically generated based on that information. Data structuring algorithms are involved in the generation of registration data.

[0711] Furthermore, if the server detects insufficient explanation, it generates supplementary information and presents it to the user through the terminal. This feature allows the user to gain a thorough understanding of the contract details and options.

[0712] The generated registration data is presented to the user via the terminal, and they are asked to confirm it. Once the user confirms, the final registration process is completed by the server. This entire process enables the dynamic generation, confirmation, and provision of supplementary information of contracts in real time.

[0713] A concrete example would be a scenario where a mail-order agent at a physical store is interacting with a customer who wants a new communication plan. When the customer verbally states a request such as "I want to know about the new communication plan," the utterance is immediately analyzed, and an appropriate plan and contract are generated on the spot. An example of a prompt sentence for the generating AI model would be, "Analyze the voice input from the user and create information about the new smartphone plan."

[0714] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0715] Step 1:

[0716] The device captures the user's interaction as audio. Here, the built-in microphone is used to record the user's speech in real time. This audio data becomes the input for the next processing step.

[0717] Step 2:

[0718] The terminal sends the acquired audio data to the server. The server converts this audio data into digital text using speech recognition software such as "speech_recognition". This converted text data becomes the output for the next processing step.

[0719] Step 3:

[0720] The server analyzes the digital text using natural language processing technology and extracts the necessary registration information. Specifically, it extracts keywords related to contract items and pricing plans from the text. This analysis result forms the basis for generating registration data.

[0721] Step 4:

[0722] The server automatically generates a contract using a document generation algorithm based on the extracted registration information. This generated contract data is then output to the next processing step.

[0723] Step 5:

[0724] If the server detects insufficient explanation, it generates supplementary information. Additional documents or comments regarding sections lacking detail are generated and presented to the user via the terminal. This supplementary information complements communication with the user.

[0725] Step 6:

[0726] The terminal presents the generated contract data to the user and asks for confirmation of its contents. As this data is displayed on the screen, a prompt for the user's feedback is generated.

[0727] Step 7:

[0728] The terminal notifies the server that it has received user confirmation. The server completes the final registration process based on the confirmed contract. This completion process is the final result of all calculations based on the input.

[0729] 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.

[0730] This invention provides a system that combines speech recognition of conversations between a user and an operator with an emotion engine that recognizes the user's emotions. The system is implemented in the following manner.

[0731] 1. Speech Recognition and Sentiment Analysis

[0732] The device passes the conversation to a speech recognition engine, which converts it into text data, while an emotion engine analyzes the user's emotions from the conversation. For example, if the user is nervous, the emotion is determined from changes in their tension and tone of voice.

[0733] 2. Data extraction and registration process

[0734] The server analyzes the text data obtained through speech recognition and extracts the information necessary for registration. This generates registration data that clearly specifies the user's desired pricing plan and contract details.

[0735] 3. Emotion-based response adjustments

[0736] Based on information from the emotion engine, the device responds in accordance with the user's emotions. For example, if the user shows frustration, it will provide more polite explanations or faster procedures to improve user satisfaction.

[0737] 4. Supplementary explanation function

[0738] If the emotion engine determines, based on conversation and sentiment analysis, that the worker's explanation is insufficient, the terminal will automatically provide additional explanations about that information. This allows the user to reduce anxiety and obtain more accurate information.

[0739] 5. Confirmation screen and final procedure

[0740] The terminal displays the generated registration data on a confirmation screen and completes the registration process by requesting final confirmation and consent from the user. Upon receiving this confirmation, the server saves the registration details to the database.

[0741] This system accurately grasps user emotions based on interactions, enabling flexible responses. As a result, the user experience is significantly improved, and the registration process becomes more efficient. For example, by using the emotion engine to provide reassurance in situations where users feel anxious, the registration process becomes smoother.

[0742] The following describes the processing flow.

[0743] Step 1:

[0744] The device collects conversations between the user and the worker via the microphone. This audio data is sent to a speech recognition engine and converted into text data. Simultaneously, an emotion engine analyzes the user's emotions from the audio.

[0745] Step 2:

[0746] The server analyzes the text data and extracts the information necessary for registration. This includes the type of contract and the desired plan. The results of the emotion engine's analysis are also sent to the server, supplementing the information with details about the user's emotional state.

[0747] Step 3:

[0748] The server generates registration data based on the extracted information. This is also where information obtained from the emotion engine is used to create a flexible data structure tailored to the user's stress level.

[0749] Step 4:

[0750] The device reflects the analysis results from the emotion engine and takes appropriate action for the user. For example, if anxiety is detected, it provides additional support information and detailed explanations via voice or text.

[0751] Step 5:

[0752] The terminal displays the generated registration data to the user on a confirmation screen. The user can review the content and indicate their consent. If the user's emotions become unstable during this process, it is possible to display an operation guide or other appropriate support.

[0753] Step 6:

[0754] After the user confirms and agrees, the server performs the final registration process and saves the registration details to the database based on the confirmed information. This completes the registration process.

[0755] (Example 2)

[0756] 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".

[0757] Conventional interactive systems fail to provide a satisfactory user experience because they only perform standardized procedures without considering user emotions. In particular, the inability to respond quickly and appropriately to users who have anxieties or questions was a major problem. Furthermore, the lack of features to compensate for insufficient explanations during the voice recognition-based information registration process sometimes led to user misunderstandings. Solving these problems is essential.

[0758] 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.

[0759] In this invention, the server includes means for analyzing the user's emotional state and responding flexibly based on that information, means for converting acquired acoustic information into text information, and means for presenting the generated registration data to the user and prompting confirmation. This enables effective interaction that takes the user's emotions into consideration.

[0760] "Acoustic information" refers to data about human voices and ambient sounds acquired through voice acquisition devices such as microphones.

[0761] "Textual information" refers to data obtained by converting acoustic information into text format using speech recognition technology.

[0762] "Registration data" refers to a collection of necessary information generated within the system based on user requests and contract terms.

[0763] "Emotional state" refers to the psychological state or feelings detected from the user's speech and tone of voice.

[0764] "Flexible response" refers to the adaptive reactions and procedures that the system employs, changing according to the user's emotional state and circumstances.

[0765] A "confirmation response" is an action or statement by a user indicating approval or disapproval of data or procedures presented by a system.

[0766] In this invention, the system consists of a terminal and a server. The terminal is equipped with a device that collects audio between the user and the worker via a high-performance microphone. This acoustic information is transmitted to a speech recognition engine (e.g., speech recognition application technology) and converted into text information. The converted text information is transmitted to the server and analyzed using natural language processing technology. As a result of the analysis, the information necessary for registration data is extracted, and the server generates the registration data.

[0767] In addition, the device uses an emotion engine (e.g., emotion analysis application technology) to analyze the user's emotional state. Based on this emotional state, the device takes flexible actions that are appropriate to the user's situation. These actions include providing supplementary information using speech synthesis technology.

[0768] The server sends the generated registration data back to the terminal, which then presents it to the user for confirmation. Once the user confirms, the server completes the final registration process and saves the information to the database.

[0769] For example, when a user signs up for a new internet service contract, if they express a question during the registration process, the emotion engine will detect this dissatisfaction, and the device will provide necessary supplementary explanations to reassure them, such as "Your data is secure and can be accessed at any time."

[0770] An example of a prompt is, "Design a system that provides a standard reassuring message if the user may show signs of anxiety."

[0771] In this way, the system can take emotions into consideration during user interaction, enabling it to provide an effective and comfortable experience.

[0772] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0773] Step 1:

[0774] The terminal uses a microphone to capture voice conversations between the user and the worker in real time. The input is voice data, and the terminal performs noise filtering to extract clear acoustic information. The output is the filtered acoustic information.

[0775] Step 2:

[0776] The device passes the filtered acoustic information to the speech recognition engine, which converts it into text. The input is filtered acoustic information, and the device uses speech recognition technology to parse this acoustic information into a string. The output is text.

[0777] Step 3:

[0778] The server analyzes the text information received from the terminal and extracts the information necessary for registration. The input is text information sent from the terminal, and the server uses natural language processing techniques to calculate and extract the necessary data points (e.g., contract details and plan settings). The output is the registration data.

[0779] Step 4:

[0780] The device analyzes the user's emotions using an emotion engine based on registered data. The input consists of registered data and textual information from conversations. The device evaluates the user's emotional state (e.g., dissatisfaction, confidence, excitement) using emotion analysis technology. The output is the user's emotional information.

[0781] Step 5:

[0782] The device considers emotional information and provides flexible responses to the user. The input is emotional information, and the device uses natural language generation technology to determine the appropriate communication method. For example, it provides reassuring messages and clear explanations of procedures through voice output and screen display. The output is the result of the user interaction.

[0783] Step 6:

[0784] The terminal presents the registration data to the user and requests a confirmation response from the user. The input is the registration data, and the terminal uses a screen display or audio output device to have the user confirm the data and receive an approval or rejection response. The output is the user's confirmation response.

[0785] Step 7:

[0786] The server receives the user's acknowledgment and performs the final registration process. The input is the user's acknowledgment, the server registers the requested information in the database, and verifies data consistency. The output is the registered data.

[0787] This process enables the system to provide emotionally sensitive interactions with users and allows for efficient and smooth registration procedures.

[0788] (Application Example 2)

[0789] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0790] Traditional user dialogue systems could recognize user speech and extract and register necessary information, but they lacked the ability to respond flexibly based on user emotions. Therefore, it was difficult to provide appropriate support when users felt anxious or frustrated, hindering the improvement of the user experience. This challenge needs to be addressed to further enhance the user experience.

[0791] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0792] In this invention, the server includes means for acquiring voice data while interacting with the user, means for converting the acquired voice data into text data, means for extracting information necessary for registration from the text data, means for generating registration data based on the extracted information, means for detecting insufficient explanation from the user or operator and providing supplementary information, means for having the user confirm the generated registration data, means for completing the final registration process after receiving confirmation from the user, and means for analyzing the user's emotions and adjusting responses based on those emotions. This makes it possible to accurately grasp the user's emotions and respond appropriately, thereby improving the user experience.

[0793] A "user" is a person who uses the system to interact with others, provide voice data, and receive services.

[0794] A "worker" is someone who provides support and information during interactions with users.

[0795] "Audio data" refers to audio recordings of conversations between users and workers.

[0796] "Text data" refers to data obtained by converting audio data into written text.

[0797] "Means of extracting information" refers to the function of extracting and aggregating necessary information from text data.

[0798] "Registered data" refers to data that includes user preferences and contract details, created based on extracted information.

[0799] "Emotions" refer to the psychological state a user exhibits during a conversation, and are judged based on factors such as tone of voice and facial expressions.

[0800] The "emotion engine" is a function that analyzes the user's voice data to determine their emotions and state.

[0801] A "confirmation screen" is a screen that presents the user with the contents of their registered data and asks them to confirm it.

[0802] "Final registration processing" refers to the series of processes that formally save and process registration data after user verification.

[0803] This invention provides a system that improves the user experience by recognizing the user's voice in real time and analyzing their emotions. The system mainly consists of three elements: a server, a terminal, and the user.

[0804] The server collects audio data and converts it into text data using the Google Cloud Speech-to-Text API. Then, IBM Watson Tone Analyzer is used to analyze the emotions expressed in this text data. Based on the results of this emotion analysis, the system can provide real-time support to respond appropriately to the user's state.

[0805] The device uses this data to display a confirmation screen to the user through the user interface. After the user confirms and agrees, this information is stored in an AWS cloud database.

[0806] For example, when a user makes an electronic payment, this system allows them to ask about the payee and amount via a voice interface. If the user expresses concern, the terminal automatically provides additional support information to reassure them. This allows the user to proceed with the transaction more smoothly.

[0807] Examples of prompts for the generative AI model include, "When a user utters a specific word, how should the application determine their emotions?" and "Generate scenarios to alleviate user anxiety during the payment process."

[0808] This invention utilizes speech recognition and sentiment analysis to improve the quality of user interactions. As a result, it is possible to improve user satisfaction and streamline processes.

[0809] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0810] Step 1:

[0811] The device acquires the user's voice data through the microphone. This acquired voice data is sent in real time to the Google Cloud Speech-to-Text API, where it is converted into text data. Here, the voice waveform data is the input, and the converted text information is the output.

[0812] Step 2:

[0813] The server receives text data and performs sentiment analysis using IBM Watson Tone Analyzer. The input is the text data obtained in step 1, and the output is a detailed evaluation of the user's emotional state. Specifically, the intensity and type of emotional tone are analyzed.

[0814] Step 3:

[0815] The server sends a notification to the terminal based on the sentiment analysis results to determine the appropriate course of action for the user. The input is the result of the sentiment analysis, and the output is the optimal course of action for the user. For example, if it is determined that the user is feeling anxious, the terminal will be instructed to provide additional information.

[0816] Step 4:

[0817] The terminal displays the necessary information to the user through the user interface. The input is the countermeasure determined in step 3, and the output is the information and additional support measures presented to the user. Specifically, detailed information and detailed guidelines are shown.

[0818] Step 5:

[0819] The user reviews the presented information and instructs the terminal to perform the final procedure. Input is the user's confirmation action, and output is the completed procedure data. This includes specific actions such as the user pressing a consent button.

[0820] Step 6:

[0821] The final registration data is saved by the server to the AWS cloud database. The input is the completed procedural data from step 5, and the output is the data securely stored in the cloud. This step specifically involves data backup and security protection.

[0822] 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.

[0823] 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.

[0824] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0825] 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.

[0826] 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. In the upper and lower directions of the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. Also, the upper side of the concentric circles is where "pleasant" emotions are located, and the lower side is where "unpleasant" emotions are located. In this way, 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.

[0827] 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.

[0828] 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.

[0829] 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.

[0830] 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."

[0831] 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.

[0832] 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.

[0833] 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.

[0834] 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.

[0835] 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.

[0836] 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.

[0837] 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.

[0838] 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.

[0839] 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.

[0840] 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.

[0841] 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.

[0842] 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.

[0843] The following is further disclosed regarding the embodiments described above.

[0844] (Claim 1)

[0845] A means of acquiring voice data while interacting with the user,

[0846] A means of converting acquired audio data into text data,

[0847] A method for extracting information necessary for registration from text data,

[0848] A means for generating registration data based on extracted information,

[0849] A means for detecting insufficient explanation from the user or worker and providing supplementary information,

[0850] A means of allowing the user to confirm the generated registration data,

[0851] A means of completing the final registration process after receiving user confirmation,

[0852] A system that includes this.

[0853] (Claim 2)

[0854] The system according to claim 1, which operates a voice recognition function in real time and immediately provides registered data.

[0855] (Claim 3)

[0856] The system according to claim 1, comprising a user interface for displaying a user confirmation screen.

[0857] "Example 1"

[0858] (Claim 1)

[0859] A means of acquiring acoustic information while interacting with the user,

[0860] A means of converting acquired acoustic information into text information,

[0861] A means of extracting the necessary information for registration from textual information,

[0862] A means for generating registration information based on extracted items,

[0863] A means for detecting insufficient explanation from the user or worker and providing additional information,

[0864] A means of having the user confirm the generated registration information,

[0865] A means of completing the final registration process after receiving user confirmation,

[0866] A means of operating the acoustic recognition function in real time and immediately providing registration information,

[0867] A means for generating and presenting responses to user questions,

[0868] A system that includes this.

[0869] (Claim 2)

[0870] The system according to claim 1, comprising a user interface, means for displaying a confirmation screen to the user, and means for providing additional explanations using audio or visual information.

[0871] (Claim 3)

[0872] The system according to claim 1, which includes a process for storing registration information in a database after obtaining the user's consent.

[0873] "Application Example 1"

[0874] (Claim 1)

[0875] A means of capturing user interactions as audio,

[0876] A means of converting acquired audio into digital text,

[0877] A means of extracting necessary registration information from digital text,

[0878] A means of automatically generating registration data based on extracted information,

[0879] A means for detecting insufficient explanation and supplying supplementary information,

[0880] A means of presenting the generated registration data to the user for confirmation,

[0881] A means of completing the registration process based on user verification,

[0882] A means of dynamically creating contract documents by analyzing customer requirements,

[0883] A system that includes this.

[0884] (Claim 2)

[0885] The system according to claim 1, which immediately activates a voice analysis function and provides an agreement document.

[0886] (Claim 3)

[0887] The system according to claim 1, comprising an operating interface for displaying a user confirmation screen.

[0888] "Example 2 of combining an emotion engine"

[0889] (Claim 1)

[0890] A means of acquiring acoustic information while interacting with the user,

[0891] A means of converting acquired acoustic information into text information,

[0892] A means for extracting information from textual information and generating registration data,

[0893] A means of analyzing the user's emotional state and responding flexibly based on that information,

[0894] A means for detecting a lack of information about a user or worker and providing supplementary information,

[0895] A means of presenting the generated registration data to the user and prompting them to confirm it,

[0896] A means of completing the registration process upon receiving a confirmation response from the user,

[0897] A system that includes this.

[0898] (Claim 2)

[0899] The system according to claim 1, which operates acoustic recognition technology in real time and immediately provides registered data.

[0900] (Claim 3)

[0901] The system according to claim 1, comprising a display device for displaying a user confirmation screen.

[0902] "Application example 2 when combining with an emotional engine"

[0903] (Claim 1)

[0904] A means of acquiring voice data while interacting with the user,

[0905] A means of converting acquired audio data into text data,

[0906] A method for extracting information necessary for registration from text data,

[0907] A means for generating registration data based on extracted information,

[0908] A means for detecting insufficient explanation from the user or worker and providing supplementary information,

[0909] A means of allowing the user to confirm the generated registration data,

[0910] A means of completing the final registration process after receiving user confirmation,

[0911] A means of analyzing user emotions and adjusting responses based on those emotions,

[0912] A system that includes this.

[0913] (Claim 2)

[0914] The system according to claim 1, which operates a voice recognition function in real time and immediately provides registered data.

[0915] (Claim 3)

[0916] The system according to claim 1, comprising a user interface for displaying a user confirmation screen. [Explanation of symbols]

[0917] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of capturing user interactions as audio, A means of converting acquired audio into digital text, A means of extracting necessary registration information from digital text, A means of automatically generating registration data based on extracted information, A means for detecting insufficient explanation and supplying supplementary information, A means of presenting the generated registration data to the user for confirmation, A means of completing the registration process based on user verification, A means of dynamically creating contract documents by analyzing customer requirements, A system that includes this.

2. The system according to claim 1, which immediately activates a voice analysis function and provides an agreement document.

3. The system according to claim 1, further comprising an operating interface for displaying a user confirmation screen.

Images