system

Abstract

We provide the system. [Solution] A means of acquiring voice data obtained from telephone communications in real time, A speech recognition means for converting acquired audio data into text data, A natural language processing method that analyzes the converted text data and extracts important information, A means of registering the extracted information in the incident management tool, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In customer service operations via a telephone with voice, conventionally, the operator has to manually record the conversation content and input it into an incident management tool, which results in a large workload and problems such as human errors and information leakage. As a result, the quality of customer service deteriorates, and there is a problem that prompt incident resolution is hindered.

Means for Solving the Problems

[0005] This invention provides a system that includes means for acquiring voice data obtained from telephone communications in real time, and speech recognition means for converting that voice data into text data. It also includes natural language processing means for analyzing the converted text data and extracting important information. Furthermore, by registering the extracted information in an incident management tool, the system eliminates the need for manual input by personnel, thereby improving operational efficiency and the accuracy of records.

[0006] A "system" refers to a group of devices or software that perform a series of processes, including acquiring voice data from telephone communications in real time, extracting important information using speech recognition and natural language processing, and registering that information in an incident management tool.

[0007] "Voice data" refers to digital data containing waveform information of sound waves, obtained through telephone communication.

[0008] "Methods for acquiring data in real time" refers to a function that instantly captures audio data during a phone call and quickly passes it on to the next processing step.

[0009] "Speech recognition means" refers to technology that converts speech data into text data and expresses it in a language that humans can understand.

[0010] "Text data" refers to a string of characters in a computer-processable format, which is obtained after audio data has been converted.

[0011] "Natural language processing methods" are technologies for analyzing text data, understanding important information and context, and organizing that information.

[0012] An "incident management tool" is software or a platform used to record, track, and manage problems and events that occur within a company or organization. [Brief explanation of the drawing]

[0013] [Figure 1]This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0014] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

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

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

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

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

[0019] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), etc.

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

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

[0023] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0030] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] The system of this invention is used in customer service and incident management via telephone. The system consists of the following steps and efficiently processes everything from acquiring voice data to registering it in a management tool.

[0035] First, the device detects a call and captures the phone's audio data in digital format. This audio data continues to be transmitted to the server in real time until the call ends.

[0036] Next, the server passes the received audio data to the speech recognition module. The speech recognition module uses a machine learning model to convert the audio data into text data. Here, the language model is designed to accurately understand the content of the speech and minimize misrecognition.

[0037] The converted text data is then sent to a natural language processing module. The server uses natural language processing techniques to analyze the text data and extract important information and keywords. This clarifies the essence of the problem and the data that needs to be solved, transforming it from a mere string of conversational text into a coherent and meaningful analysis.

[0038] Finally, the extracted information is automatically registered in the incident management tool via the server. This registration includes the incident's severity, category, and customer information. This allows users to easily review the registered incident information, facilitating faster response times.

[0039] For example, suppose a user calls technical support and reports a problem where their computer suddenly shuts down. The terminal captures this conversation, and the server converts it into text data that includes the context of "the user's computer unexpectedly shutting down." The server then registers this information as a "new hardware failure incident" in the incident management tool. Based on the record created by the system, the user can quickly take appropriate repair action.

[0040] Thus, the embodiment of the present invention combines speech recognition and natural language processing to enable accurate recording of call content and rapid registration in an incident management tool. This significantly improves the efficiency of customer service and the accuracy of operations.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The device detects the start of a call and captures the audio data. The audio data is digitized and transmitted in real time to a server via the communication network.

[0044] Step 2:

[0045] The server passes the received audio data to the speech recognition module. The speech recognition module uses a machine learning model powered by generative AI to convert the audio into text data.

[0046] Step 3:

[0047] The server sends the transcribed text data to a natural language processing module. The natural language processing module analyzes the text and extracts important keywords and semantic information.

[0048] Step 4:

[0049] The server prepares the extracted information for registration with the incident management tool. The data is organized into the appropriate format and sent to the management tool via API.

[0050] Step 5:

[0051] Users can view newly registered incidents through the incident management tool. The notification function immediately displays new incidents requiring attention.

[0052] Step 6:

[0053] Users can review the details and circumstances of registered incidents and take appropriate action as needed. This enables a swift and accurate response.

[0054] (Example 1)

[0055] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0056] Traditional telephone communication systems have struggled to process voice data in real time and quickly organize and register it as information necessary for incident management. In particular, there is a need to accurately convert voice to text and effectively analyze that information to extract important details. Furthermore, a lack of an interface that allows users to easily manipulate information and take appropriate action is also a problem.

[0057] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0058] In this invention, the server includes means for acquiring voice data obtained from telephone communications in real time, voice recognition means for converting the acquired voice data into text data, natural language processing means for analyzing the converted text data and automatically organizing the information contained therein, means for classifying the analyzed information and recording it directly in a management tool, and means for providing an interface for users to easily check information and respond. This enables accurate processing of telephone communication content in real time and rapid incident registration, allowing users to efficiently utilize information and respond in a timely manner.

[0059] "Telephone communication" is a form of communication that converts voice information into electrical signals and transmits them to a remote location; it is a means of communication and information exchange.

[0060] "Audio data" refers to data that digitizes a person's voice and is in a format that can be processed and analyzed by computer systems.

[0061] "Real-time" refers to the concept of processing or communication occurring instantly, without any delay.

[0062] "Speech recognition means" refers to technologies or devices that convert speech data into text data, often using artificial intelligence or machine learning models.

[0063] "Text data" refers to string data that can be processed by a computer, and is a transcript obtained through speech recognition.

[0064] "Natural language processing" refers to technologies that enable computers to understand and process the language that humans normally use.

[0065] An "incident management tool" is software used to manage and track anomalies and failures in systems and services.

[0066] A "user" refers to an individual or group that operates a system or device and utilizes its functions.

[0067] An "interface" refers to the points of contact or means that enable communication and operation between a user and a system.

[0068] The system for carrying out this invention efficiently processes voice data obtained through telephone communication. Specifically, it consists of a terminal for digital voice recording and a server for performing advanced analysis.

[0069] First, the device detects voice communication and captures the voice data in digital format. VoIP technology can be used for this capture, and a common software option is Asterisk, an open-source communication platform. This process extracts the call content as digital data in real time.

[0070] Next, the server receives the acquired audio data and performs speech recognition. This process utilizes speech recognition services such as Google® Speech-to-Text and Amazon Transcribe to convert the audio data into text data. As a result, the content of the audio is accurately represented in text with minimal errors.

[0071] The server then uses natural language processing technology to analyze the converted text data. Tools such as Python's NLTK library and spaCy are used to automatically extract important keywords and information from the text. This reveals the essence of the call content and makes it possible to define the next course of action.

[0072] The extracted information is automatically registered by the server in the incident management tool. This process utilizes commercially available software such as ServiceNow or JIRA, designed to comprehensively record incident type, severity, and customer details. This allows users to quickly access information through the system's interface and perform appropriate management and responses.

[0073] For example, if a technical support representative receives a call about a printer that has stopped printing, the terminal immediately records the conversation. The server identifies the "printer stopped printing" issue and registers this information as a "new printer malfunction" in the management tool. In this way, users can easily obtain information and take action quickly.

[0074] An example of a prompt message might be: "A user has reported a network latency issue. Please convert the audio data to text and register the necessary information in the management tool."

[0075] The introduction of this system will allow customer feedback to be instantly reflected within the system, enabling more effective customer service.

[0076] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0077] Step 1:

[0078] The terminal detects incoming calls and captures audio data in digital format as soon as the call begins. The input is an analog audio signal from a telephone call, which is converted into digital data using specific digitization software. This results in audio data packets that can be streamed in real time.

[0079] Step 2:

[0080] The server receives packets of audio data and sends the data to the speech recognition engine. The input is digital audio data sent from the terminal, which is converted into text data using the Google Speech-to-Text API or Amazon Transcribe. The speech recognition engine performs noise reduction and sound quality improvement filtering to generate accurate text data as output.

[0081] Step 3:

[0082] The server passes the acquired text data to a natural language processing engine for content analysis. It receives text data from a speech recognition engine as input and performs contextual analysis and keyword extraction using NLTK and spaCy libraries. Here, it identifies important information contained within the text, such as the type of problem and related information, and generates structured information data as output.

[0083] Step 4:

[0084] The server registers structured information with incident management tools. The input is information data extracted from a natural language processing engine, which is used to determine the category and priority of the problem. The output generates database entries that are registered with management tools such as ServiceNow and JIRA, organizing and storing the details of each incident.

[0085] Step 5:

[0086] Users review registered information and take action through the incident management tool interface. Input consists of data displayed on the management tool screen, and users can search for necessary information using specific search and filtering functions. Output provides users with the information needed for their next steps, enabling efficient response and problem resolution.

[0087] (Application Example 1)

[0088] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0089] Current voice assistant systems and home smart devices can provide basic query responses to voice commands, but they lack the ability to report complex problems or seamlessly integrate with external resources. Therefore, there is a need for improved user experience and faster, more efficient problem resolution when using smart devices in the home.

[0090] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0091] In this invention, the server includes means for acquiring voice input and performing voice recognition in real time, voice recognition means for converting the acquired voice data into text data, and natural language processing means for analyzing the converted text data and extracting important information. This enables the smart device to analyze the user's voice instructions and, if necessary, automate querying external information resources and reporting problems.

[0092] "Voice input" is the process of receiving a user's speech as a digital signal.

[0093] "Real-time" refers to a state where data processing is performed instantly, and results are obtained without delay.

[0094] "Speech recognition" is a technology that converts speech data into text data.

[0095] "Text data" refers to the transcribed text extracted from audio, and is data expressed in text format.

[0096] "Natural language processing" is a general term for technologies that use computers to understand, interpret, and generate human language.

[0097] "Information resources" refers to sources from which data is obtained, including external databases and information provision services.

[0098] "Problem reporting" refers to the act of a user informing the system of a bug or question.

[0099] A "management device" refers to a tool or system for registering, organizing, and transmitting data and information.

[0100] This invention is a system that analyzes user instructions and problem reports received via voice input in real time, and acquires information from external information resources as needed, thereby enabling automated responses and problem solving through smart devices and assistant devices within the home. Details are described below.

[0101] The server first uses smart speakers or home assistant devices (e.g., GOOGLE NEST®, Amazon Echo) as hardware. The speech recognition software installed on the server acquires voice input in real time and converts the voice data into text data. In this process, speech recognition technologies such as Google Cloud Speech-to-Text API and Amazon Transcribe are used.

[0102] Next, the server analyzes the obtained text data using natural language processing techniques. At this stage, software such as spaCy or Google Cloud Natural Language API is used to extract important information and generate queries to external information resources based on that information.

[0103] For example, if a user reports a problem such as "the living room lights won't turn on," the server analyzes the audio data, understands the problem, reports it to the management device and relevant support services, and either automatically suggests a solution or notifies the appropriate department.

[0104] An example of a prompt message would be, "We have received a report from a user that their robot vacuum cleaner is malfunctioning. Please explain how to analyze the report and forward it to customer support." This allows for efficient processing of user problem reports.

[0105] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0106] Step 1:

[0107] The device receives voice input from the user. Once voice input begins, the microphone captures the user's speech and prepares to send it to the server in real time as digital audio data. The input is raw audio data, and the output is audio data in digital format.

[0108] Step 2:

[0109] The server passes the received digital audio data to the speech recognition module. This module uses the Google Cloud Speech-to-Text API to convert the audio data into text data. The input is digital audio data, and the output is the converted text data. During this process, a machine learning model performs precise speech recognition based on the content of the audio utterance.

[0110] Step 3:

[0111] The server passes the text data obtained from speech recognition to a natural language processing module. This module uses spaCy or the Google Cloud Natural Language API to analyze the text data and extract important keywords and information. The input is text data, and the output is a set of extracted important information. This allows for a clear understanding of the context of the conversation and the essence of the issue.

[0112] Step 4:

[0113] The server uses the extracted information to query external information resources and management devices. In doing so, it generates API requests based on the information to respond to problem reports and information requests. The input is a set of important information, and the output is the API requests and the resulting query responses.

[0114] Step 5:

[0115] The server returns acquired external information or processing results to the user or sends them to the necessary support. In some cases, the management device provides notifications of improved lighting conditions via software. Inputs are external information and query responses, and outputs are problem solutions provided to the user or the appropriate department. This operation allows for the rapid and automated resolution of user problems.

[0116] 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.

[0117] The present invention provides a multifaceted incident management system that processes voice data obtained via telephone calls in real time and incorporates an emotion engine that identifies the user's emotions. This system includes the following elements:

[0118] The terminal first acquires the call audio data in real time and sends it to the server in digital format. Upon receiving the audio data, the server uses a speech recognition module to convert the audio into text data. Here, a machine learning model is used to apply speech recognition technology that supports multiple languages.

[0119] Next, the server passes the text data to a natural language processing module for contextual analysis. The natural language processing module extracts important information and uses an emotion engine to analyze the user's emotions expressed in the text. The emotion engine identifies the emotions the user may be feeling based on the expressions and phrasing in the text.

[0120] The analyzed text data and sentiment information are registered by the server in the incident management tool. The user sentiment information obtained here is used to prioritize responses and improve future customer service. The system can also analyze past sentiment data to help create response guidelines based on sentiment trends.

[0121] As a concrete example, suppose a customer says to support, "I've been waiting forever, and I'm really frustrated." The device acquires the audio data, and the server generates text data stating, "The customer is frustrated with the wait and really needs help." The emotion engine analyzes this text to identify strong frustration and urgency, and registers it as a high-priority incident. Based on this, the user can take swift action to alleviate the customer's anxiety.

[0122] Thus, the present invention provides a system that comprehensively responds to incidents, including not only the content of the incident but also the user's emotions, by combining speech recognition, natural language processing, and an emotion engine. This system can improve the quality of customer service and increase the overall efficiency of the organization.

[0123] The following describes the processing flow.

[0124] Step 1:

[0125] The device detects the start of a call and captures the audio data in real time. The audio data is digitized and ready to be sent to the server.

[0126] Step 2:

[0127] The server receives the audio data sent from the terminal. Upon receiving the data, it passes it to the speech recognition module, which then begins the process of converting the audio data into text data using a machine learning algorithm.

[0128] Step 3:

[0129] The server retrieves text data generated by the speech recognition module and sends it to the natural language processing module. Here, the context of the text data is analyzed, and important information is extracted.

[0130] Step 4:

[0131] The server sends the text data, which has been parsed by the natural language processing module, to the sentiment engine. The sentiment engine analyzes the customer's emotions revealed in the text and adds the results as metadata.

[0132] Step 5:

[0133] The server registers text data with sentiment information into the incident management tool. The system then records and stores the incident details, including sentiment information, in a formatted manner.

[0134] Step 6:

[0135] Users can review incident information registered using the incident management tool. By considering customer sentiment information, they can quickly take action on high-priority issues.

[0136] Step 7:

[0137] Users or organizations analyze long-term trends based on emotional data to improve their customer service strategies. This enables the implementation of measures that lead to increased customer satisfaction.

[0138] (Example 2)

[0139] 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".

[0140] In today's telephone communication environment, it is difficult to analyze the emotions and urgency conveyed by customers during calls in real time and to respond appropriately immediately. Traditional incident management systems simply transcribe voice information into text and report it, failing to grasp the user's emotions or underlying needs, which poses challenges to improving customer satisfaction and efficiently delivering services.

[0141] 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.

[0142] In this invention, the server includes means for acquiring voice information obtained from telephone communications in real time, voice conversion means for converting the acquired voice information into text information, natural language processing means for analyzing the converted text information and extracting important content, emotion analysis means for identifying emotions using the text information, and means for registering the analyzed text information and emotion information in a case management device. This makes it possible to quickly analyze the emotions and urgency of customers in telephone communications and respond appropriately.

[0143] "Telephone communication" is a means of communication that primarily transmits and receives voice information as voice signals.

[0144] "Audio information" refers to information that represents audio data in a digital format.

[0145] "Real-time" refers to a state where processing can be performed almost instantly, minimizing information delays.

[0146] "Voice conversion means" refers to technologies and devices for converting voice information into text information, and may utilize generation AI technology.

[0147] "Text information" refers to information expressed in the form of characters and symbols, and is a way of representing audio information as a string of characters.

[0148] "Natural language processing means" refers to technologies or devices for analyzing the grammar and context of text information and extracting important keywords and content.

[0149] "Emotion analysis means" refers to a technology or device for identifying a user's emotions based on expressions contained within text information.

[0150] An "incident management device" is a device or system that uses analyzed information to record and manage incidents, and to prioritize incidents and provide support for response.

[0151] This invention relates to a system that enables rapid customer service by analyzing voice information obtained from telephone communications in real time and making accurate emotional judgments. This system consists of three elements: a terminal, a server, and a user.

[0152] First, the terminal acquires voice information in real time. The terminal has a built-in microphone and communication device, which converts the voice into a digital format and sends it to the server as data. Encryption protocols are used to ensure the security of the communication.

[0153] Next, the server processes the received audio information using a speech conversion device, converting the audio data into text information. By using a generative AI model and applying advanced speech recognition technology, it is possible to generate highly accurate text information.

[0154] Subsequently, the server analyzes the text information using natural language processing tools and extracts important content. Simultaneously, sentiment analysis tools identify the user's emotions from the text information. This process allows the server to understand the customer's emotional state.

[0155] The analyzed information is registered in the incident management system. This system enables the prioritization of incidents and the proposal of countermeasures tailored to the nature of each incident.

[0156] Users use this analysis to handle customer interactions. For example, if a customer calls the support center and says, "I'm very frustrated because I've been kept waiting for a long time," the terminal captures this audio, the server transcribes the information into text, and analyzes it as "the customer is dissatisfied with the waiting time." Through sentiment analysis, this situation is registered as a high-priority case requiring urgent attention, allowing users to take swift action.

[0157] Examples of prompts generated using an AI model include: "If a customer says on the phone, 'I'm very frustrated because I've been kept waiting for a long time,' please analyze the sentiment of this statement and provide instructions on how to respond appropriately."

[0158] This system allows us to accurately understand customers' emotional states and respond quickly and effectively, which is expected to improve the quality of service.

[0159] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0160] Step 1:

[0161] The terminal acquires voice information in real time from received telephone communications. Specifically, it captures voice signals using the microphone and communication devices built into the terminal and converts them into a digital format. In this process, the input is an analog voice signal, and the output is digital voice data.

[0162] Step 2:

[0163] The terminal securely transmits the acquired digital voice data to the server using an encryption protocol. The input is digital voice data, and the output is encrypted data packets transmitted over the network. This ensures the privacy and integrity of the data.

[0164] Step 3:

[0165] The server processes the received audio data using a speech conversion device, converting the audio information into text information. At this stage, where a generative AI model is applied, digital audio data is provided as input, and converted text information is obtained as output. Speech recognition accurately transcribes the speaker's utterances into text.

[0166] Step 4:

[0167] The server analyzes text information using natural language processing techniques. The input is text, and the output is extracted important information. This process involves contextual and keyword analysis, clarifying the customer's intent.

[0168] Step 5:

[0169] The server processes text information using sentiment analysis tools to identify the user's emotions from the text. This process uses the already analyzed text information as input and outputs the type and intensity of the emotion. Sentiment analysis identifies the emotions the customer is experiencing.

[0170] Step 6:

[0171] The server registers the analyzed text and sentiment information into the case management system. In this section, sentiment-analyzed data is provided as input, and prioritized case information is generated as output. The registered information is then used to assist with subsequent customer interactions.

[0172] Step 7:

[0173] The user implements customer support based on analysis results provided by the incident management system. The input is information from the incident management system, and the output is specific customer support measures. In this way, the user can take appropriate action quickly, contributing to improved customer satisfaction.

[0174] (Application Example 2)

[0175] 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".

[0176] Traditional telephone incident management systems, while capable of converting voice data into text, have the drawback of failing to analyze user emotions in real time and present them immediately to operators, thus hindering the improvement of customer service quality. There is a need for a system that can accurately grasp user emotions and provide swift and appropriate responses.

[0177] 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.

[0178] In this invention, the server includes means for acquiring voice information obtained from communications in real time, voice recognition means for converting the acquired voice information into text information, natural language processing means for analyzing the converted text information and extracting important information, and means for analyzing the user's emotional state and providing the emotional state to a visual display device. This makes it possible to improve the quality of customer service by analyzing the user's emotions in real time and presenting them to the operator quickly.

[0179] "Communication" is a general term for the mediation and technologies used to send and receive information.

[0180] "Audio information" refers to information that includes human speech, based on sound waveform data.

[0181] "Real-time" refers to processing or responding instantly without delay.

[0182] "Speech recognition means" refers to a technology or device that analyzes speech data and converts it into text information.

[0183] "Textual information" refers to linguistic information expressed in text format.

[0184] "Natural language processing means" refers to computational technologies and devices used to analyze and understand human language.

[0185] "Important information" refers to valuable data that should be extracted or used for a specific purpose.

[0186] An "incident management system" is a system or mechanism for organizing and monitoring events such as incidents and accidents.

[0187] "User's emotional state" refers to the emotional fluctuations and circumstances of the user, such as joy, anger, sadness, and other feelings.

[0188] A "visual display device" is a device that converts data into a form that can be seen and presents it.

[0189] To realize this invention, a system is built in which a server is responsible for processing voice information. Voice information is sent from the user's terminal to the server in real time. The server uses a computational model as a speech recognition means to convert the voice information into text information. Here, speech recognition technologies such as the Google Cloud Speech-to-Text API are used. The text information is analyzed by a natural language processing means, and important information is extracted. In this process, the Google Cloud Natural Language API is used to identify the user's emotional state from the text.

[0190] Once the user's emotional state is analyzed, the server provides this information to a visual display device, allowing operators to visually confirm the information via a head-mounted display or similar device if a quick response is needed. This enables operators to immediately understand the customer's emotions and take appropriate action.

[0191] For example, if a user expresses in a call that they are "frustrated by being kept waiting for a long time," the server converts the audio into text and uses an emotion engine to analyze the level of dissatisfaction. The result of this analysis is then visually displayed on the operator's display device as "The customer is dissatisfied."

[0192] An example of a prompt message is, "Please advise on how to visualize the emotion engine's output in a way that is easy for operators to understand." This will enable the system to provide more effective customer service.

[0193] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0194] Step 1:

[0195] The terminal acquires audio information. Audio information exchanged during communication is captured by the microphone and converted into a digital format. The input is an audio signal, and the output is digital audio data. This data is prepared for the next processing step.

[0196] Step 2:

[0197] The terminal sends digital audio data to the server. Here, the audio data is transferred to the server in real time via the network. The input is digital audio data, and the output is the audio data sent to the server via the network. This allows the server to begin processing the speech recognition.

[0198] Step 3:

[0199] The server converts digital audio data into text information using speech recognition technology. Specifically, it uses a computational model to generate text data from audio data. The input is digital audio data, and the output is text information. APIs such as Google Cloud Speech-to-Text are used.

[0200] Step 4:

[0201] The server analyzes textual information using natural language processing techniques and extracts important information. Specifically, it analyzes the context of the text and extracts key words spoken by the user. The input is textual information, and the output is the extracted important information.

[0202] Step 5:

[0203] The server analyzes the user's emotional state from information extracted using an emotion engine. Here, data obtained from natural language processing is used to identify the user's emotions. The input is the extracted key information, and the output is the user's emotional state.

[0204] Step 6:

[0205] The server provides the user's emotional state to a visual display device. This allows the operator to visually understand the customer's emotions through a head-mounted display or similar device. The input is the user's emotional state, and the output is the visually displayed emotional state.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] [Second Embodiment]

[0210] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0211] 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.

[0212] 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).

[0213] 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.

[0214] 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.

[0215] 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).

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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.

[0220] 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.

[0221] 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".

[0222] The system of this invention is used in customer service and incident management via telephone. The system consists of the following steps and efficiently processes everything from acquiring voice data to registering it in a management tool.

[0223] First, the device detects a call and captures the phone's audio data in digital format. This audio data continues to be transmitted to the server in real time until the call ends.

[0224] Next, the server passes the received audio data to the speech recognition module. The speech recognition module uses a machine learning model to convert the audio data into text data. Here, the language model is designed to accurately understand the content of the speech and minimize misrecognition.

[0225] The converted text data is then sent to a natural language processing module. The server uses natural language processing techniques to analyze the text data and extract important information and keywords. This clarifies the essence of the problem and the data that needs to be solved, transforming it from a mere string of conversational text into a coherent and meaningful analysis.

[0226] Finally, the extracted information is automatically registered in the incident management tool via the server. This registration includes the incident's severity, category, and customer information. This allows users to easily review the registered incident information, facilitating faster response times.

[0227] For example, suppose a user calls technical support and reports a problem where their computer suddenly shuts down. The terminal captures this conversation, and the server converts it into text data that includes the context of "the user's computer unexpectedly shutting down." The server then registers this information as a "new hardware failure incident" in the incident management tool. Based on the record created by the system, the user can quickly take appropriate repair action.

[0228] Thus, the embodiment of the present invention combines speech recognition and natural language processing to enable accurate recording of call content and rapid registration in an incident management tool. This significantly improves the efficiency of customer service and the accuracy of operations.

[0229] The following describes the processing flow.

[0230] Step 1:

[0231] The device detects the start of a call and captures the audio data. The audio data is digitized and transmitted in real time to a server via the communication network.

[0232] Step 2:

[0233] The server passes the received audio data to the speech recognition module. The speech recognition module uses a machine learning model powered by generative AI to convert the audio into text data.

[0234] Step 3:

[0235] The server sends the transcribed text data to a natural language processing module. The natural language processing module analyzes the text and extracts important keywords and semantic information.

[0236] Step 4:

[0237] The server prepares the extracted information for registration with the incident management tool. The data is organized into the appropriate format and sent to the management tool via API.

[0238] Step 5:

[0239] Users can view newly registered incidents through the incident management tool. The notification function immediately displays new incidents requiring attention.

[0240] Step 6:

[0241] Users can review the details and circumstances of registered incidents and take appropriate action as needed. This enables a swift and accurate response.

[0242] (Example 1)

[0243] 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."

[0244] Traditional telephone communication systems have struggled to process voice data in real time and quickly organize and register it as information necessary for incident management. In particular, there is a need to accurately convert voice to text and effectively analyze that information to extract important details. Furthermore, a lack of an interface that allows users to easily manipulate information and take appropriate action is also a problem.

[0245] 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.

[0246] In this invention, the server includes means for acquiring voice data obtained from telephone communications in real time, voice recognition means for converting the acquired voice data into text data, natural language processing means for analyzing the converted text data and automatically organizing the information contained therein, means for classifying the analyzed information and recording it directly in a management tool, and means for providing an interface for users to easily check information and respond. This enables accurate processing of telephone communication content in real time and rapid incident registration, allowing users to efficiently utilize information and respond in a timely manner.

[0247] "Telephone communication" is a form of communication that converts voice information into electrical signals and transmits them to a remote location; it is a means of communication and information exchange.

[0248] "Audio data" refers to data that digitizes a person's voice and is in a format that can be processed and analyzed by computer systems.

[0249] "Real-time" refers to the concept of processing or communication occurring instantly, without any delay.

[0250] "Speech recognition means" refers to technologies or devices that convert speech data into text data, often using artificial intelligence or machine learning models.

[0251] "Text data" refers to string data that can be processed by a computer, and is a transcript obtained through speech recognition.

[0252] "Natural language processing" refers to technologies that enable computers to understand and process the language that humans normally use.

[0253] An "incident management tool" is software used to manage and track anomalies and failures in systems and services.

[0254] A "user" refers to an individual or group that operates a system or device and utilizes its functions.

[0255] An "interface" refers to the points of contact or means that enable communication and operation between a user and a system.

[0256] The system for carrying out this invention efficiently processes voice data obtained through telephone communication. Specifically, it consists of a terminal for digital voice recording and a server for performing advanced analysis.

[0257] First, the device detects voice communication and captures the voice data in digital format. VoIP technology can be used for this capture, and a common software option is Asterisk, an open-source communication platform. This process extracts the call content as digital data in real time.

[0258] Next, the server receives the acquired audio data and performs speech recognition. This process utilizes speech recognition services such as Google Speech-to-Text and Amazon Transcribe to convert the audio data into text data. As a result, the content of the audio is accurately represented in text with minimal errors.

[0259] The server then uses natural language processing technology to analyze the converted text data. Tools such as Python's NLTK library and spaCy are used to automatically extract important keywords and information from the text. This reveals the essence of the call content and makes it possible to define the next course of action.

[0260] The extracted information is automatically registered by the server in the incident management tool. This process utilizes commercially available software such as ServiceNow or JIRA, designed to comprehensively record incident type, severity, and customer details. This allows users to quickly access information through the system's interface and perform appropriate management and responses.

[0261] For example, if a technical support representative receives a call about a printer that has stopped printing, the terminal immediately records the conversation. The server identifies the "printer stopped printing" issue and registers this information as a "new printer malfunction" in the management tool. In this way, users can easily obtain information and take action quickly.

[0262] An example of a prompt message might be: "A user has reported a network latency issue. Please convert the audio data to text and register the necessary information in the management tool."

[0263] The introduction of this system will allow customer feedback to be instantly reflected within the system, enabling more effective customer service.

[0264] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0265] Step 1:

[0266] The terminal detects incoming calls and captures audio data in digital format as soon as the call begins. The input is an analog audio signal from a telephone call, which is converted into digital data using specific digitization software. This results in audio data packets that can be streamed in real time.

[0267] Step 2:

[0268] The server receives packets of audio data and sends the data to the speech recognition engine. The input is digital audio data sent from the terminal, which is converted into text data using the Google Speech-to-Text API or Amazon Transcribe. The speech recognition engine performs noise reduction and sound quality improvement filtering to generate accurate text data as output.

[0269] Step 3:

[0270] The server passes the acquired text data to a natural language processing engine for content analysis. It receives text data from a speech recognition engine as input and performs contextual analysis and keyword extraction using NLTK and spaCy libraries. Here, it identifies important information contained within the text, such as the type of problem and related information, and generates structured information data as output.

[0271] Step 4:

[0272] The server registers structured information with incident management tools. The input is information data extracted from a natural language processing engine, which is used to determine the category and priority of the problem. The output generates database entries that are registered with management tools such as ServiceNow and JIRA, organizing and storing the details of each incident.

[0273] Step 5:

[0274] Users review registered information and take action through the incident management tool interface. Input consists of data displayed on the management tool screen, and users can search for necessary information using specific search and filtering functions. Output provides users with the information needed for their next steps, enabling efficient response and problem resolution.

[0275] (Application Example 1)

[0276] 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."

[0277] Current voice assistant systems and home smart devices can provide basic query responses to voice commands, but they lack the ability to report complex problems or seamlessly integrate with external resources. Therefore, there is a need for improved user experience and faster, more efficient problem resolution when using smart devices in the home.

[0278] 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.

[0279] In this invention, the server includes means for acquiring voice input and performing voice recognition in real time, voice recognition means for converting the acquired voice data into text data, and natural language processing means for analyzing the converted text data and extracting important information. This enables the smart device to analyze the user's voice instructions and, if necessary, automate querying external information resources and reporting problems.

[0280] "Voice input" is the process of receiving a user's speech as a digital signal.

[0281] "Real-time" refers to a state where data processing is performed instantly, and results are obtained without delay.

[0282] "Voice recognition" is a technology that converts voice data into text data.

[0283] "Text data" refers to the transcribed text extracted from voice and represents data expressed in text format.

[0284] "Natural language processing" is a general term for technologies that enable a computer to understand, interpret, and generate human language.

[0285] "Information resource" refers to the source of data, including external databases and information-providing services.

[0286] "Problem reporting" refers to the act of a user communicating a defect or question to the system.

[0287] "Management device" refers to tools or systems for registering, organizing, and transmitting data and information.

[0288] The present invention is a system that analyzes voice-input user instructions and problem reports in real time and obtains information from external information resources as needed to perform automatic responses and problem-solving through smart devices and assistant devices within a home. Details will be described below.

[0289] The server first uses, as hardware, smart speakers and home assistant devices (e.g., Google Nest, Amazon Echo). The voice recognition software installed on the server acquires voice input in real time and converts the voice data into text data. In this process, voice recognition technologies such as Google Cloud Speech-to-Text API and Amazon Transcribe are used.

[0290] Next, the server analyzes the obtained text data using natural language processing techniques. At this stage, software such as spaCy or Google Cloud Natural Language API is used to extract important information and generate queries to external information resources based on that information.

[0291] For example, if a user reports a problem such as "the living room lights won't turn on," the server analyzes the audio data, understands the problem, reports it to the management device and relevant support services, and either automatically suggests a solution or notifies the appropriate department.

[0292] An example of a prompt message would be, "We have received a report from a user that their robot vacuum cleaner is malfunctioning. Please explain how to analyze the report and forward it to customer support." This allows for efficient processing of user problem reports.

[0293] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0294] Step 1:

[0295] The device receives voice input from the user. Once voice input begins, the microphone captures the user's speech and prepares to send it to the server in real time as digital audio data. The input is raw audio data, and the output is audio data in digital format.

[0296] Step 2:

[0297] The server passes the received digital audio data to the speech recognition module. This module uses the Google Cloud Speech-to-Text API to convert the audio data into text data. The input is digital audio data, and the output is the converted text data. During this process, a machine learning model performs precise speech recognition based on the content of the audio utterance.

[0298] Step 3:

[0299] The server passes the text data obtained from speech recognition to a natural language processing module. This module uses spaCy or the Google Cloud Natural Language API to analyze the text data and extract important keywords and information. The input is text data, and the output is a set of extracted important information. This allows for a clear understanding of the context of the conversation and the essence of the issue.

[0300] Step 4:

[0301] The server uses the extracted information to query external information resources and management devices. In doing so, it generates API requests based on the information to respond to problem reports and information requests. The input is a set of important information, and the output is the API requests and the resulting query responses.

[0302] Step 5:

[0303] The server returns acquired external information or processing results to the user or sends them to the necessary support. In some cases, the management device provides notifications of improved lighting conditions via software. Inputs are external information and query responses, and outputs are problem solutions provided to the user or the appropriate department. This operation allows for the rapid and automated resolution of user problems.

[0304] 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.

[0305] The present invention provides a multifaceted incident management system that processes voice data obtained via telephone calls in real time and incorporates an emotion engine that identifies the user's emotions. This system includes the following elements:

[0306] First, the terminal first obtains the voice data of the call in real time and transmits it to the server in digital format. When the server receives the voice data, it uses the voice recognition module to convert the voice into text data. Here, a machine learning model is utilized, and a voice recognition technology capable of supporting multiple languages is applied.

[0307] Next, the server passes the text data to the natural language processing module for context analysis. The natural language processing module extracts important information and analyzes the user's emotions indicated in the text using the emotion engine. The emotion engine identifies the emotions that the user may be feeling based on the expressions and turns of phrase in the text.

[0308] The analyzed text data and emotion information are registered by the server in the incident management tool. The user's emotion information obtained here is useful for prioritizing responses and improving future customer service. Also, the system can analyze the previous emotion data and assist in creating response guidelines based on the emotion trends.

[0309] As a specific example, suppose a customer makes a statement to support like "I've been waiting for a long time and I'm really in trouble". The terminal obtains the voice data, and the server generates text data like "The customer is dissatisfied with the waiting time and really needs help". The emotion engine analyzes strong frustration and a sense of urgency from this text and registers it as a high-priority incident. Based on this, the user can take prompt countermeasures and implement actions to relieve the customer's anxiety.

[0310] In this way, the present invention provides a mechanism that comprehensively responds not only to the content of the incident but also to the user's emotions by combining voice recognition, natural language processing, and an emotion engine. This system can improve the quality of customer response and enhance the efficiency of the entire organization.

[0311] The following describes the processing flow.

[0312] Step 1:

[0313] The device detects the start of a call and captures the audio data in real time. The audio data is digitized and ready to be sent to the server.

[0314] Step 2:

[0315] The server receives the audio data sent from the terminal. Upon receiving the data, it passes it to the speech recognition module, which then begins the process of converting the audio data into text data using a machine learning algorithm.

[0316] Step 3:

[0317] The server retrieves text data generated by the speech recognition module and sends it to the natural language processing module. Here, the context of the text data is analyzed, and important information is extracted.

[0318] Step 4:

[0319] The server sends the text data, which has been parsed by the natural language processing module, to the sentiment engine. The sentiment engine analyzes the customer's emotions revealed in the text and adds the results as metadata.

[0320] Step 5:

[0321] The server registers text data with sentiment information into the incident management tool. The system then records and stores the incident details, including sentiment information, in a formatted manner.

[0322] Step 6:

[0323] Users can review incident information registered using the incident management tool. By considering customer sentiment information, they can quickly take action on high-priority issues.

[0324] Step 7:

[0325] Users or organizations analyze long-term trends based on emotional data to improve their customer service strategies. This enables the implementation of measures that lead to increased customer satisfaction.

[0326] (Example 2)

[0327] 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".

[0328] In today's telephone communication environment, it is difficult to analyze the emotions and urgency conveyed by customers during calls in real time and to respond appropriately immediately. Traditional incident management systems simply transcribe voice information into text and report it, failing to grasp the user's emotions or underlying needs, which poses challenges to improving customer satisfaction and efficiently delivering services.

[0329] 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.

[0330] In this invention, the server includes means for acquiring voice information obtained from telephone communications in real time, voice conversion means for converting the acquired voice information into text information, natural language processing means for analyzing the converted text information and extracting important content, emotion analysis means for identifying emotions using the text information, and means for registering the analyzed text information and emotion information in a case management device. This makes it possible to quickly analyze the emotions and urgency of customers in telephone communications and respond appropriately.

[0331] "Telephone communication" is a means of communication that primarily transmits and receives voice information as voice signals.

[0332] "Audio information" refers to information that represents audio data in a digital format.

[0333] "Real-time" refers to a state where processing can be performed almost instantly, minimizing information delays.

[0334] "Voice conversion means" refers to technologies and devices for converting voice information into text information, and may utilize generation AI technology.

[0335] "Text information" refers to information expressed in the form of characters and symbols, and is a way of representing audio information as a string of characters.

[0336] "Natural language processing means" refers to technologies or devices for analyzing the grammar and context of text information and extracting important keywords and content.

[0337] "Emotion analysis means" refers to a technology or device for identifying a user's emotions based on expressions contained within text information.

[0338] An "incident management device" is a device or system that uses analyzed information to record and manage incidents, and to prioritize incidents and provide support for response.

[0339] This invention relates to a system that enables rapid customer service by analyzing voice information obtained from telephone communications in real time and making accurate emotional judgments. This system consists of three elements: a terminal, a server, and a user.

[0340] First, the terminal acquires voice information in real time. The terminal has a built-in microphone and communication device, which converts the voice into a digital format and sends it to the server as data. Encryption protocols are used to ensure the security of the communication.

[0341] Next, the server processes the received audio information using a speech conversion device, converting the audio data into text information. By using a generative AI model and applying advanced speech recognition technology, it is possible to generate highly accurate text information.

[0342] Subsequently, the server analyzes the text information using natural language processing tools and extracts important content. Simultaneously, sentiment analysis tools identify the user's emotions from the text information. This process allows the server to understand the customer's emotional state.

[0343] The analyzed information is registered in the incident management system. This system enables the prioritization of incidents and the proposal of countermeasures tailored to the nature of each incident.

[0344] Users use this analysis to handle customer interactions. For example, if a customer calls the support center and says, "I'm very frustrated because I've been kept waiting for a long time," the terminal captures this audio, the server transcribes the information into text, and analyzes it as "the customer is dissatisfied with the waiting time." Through sentiment analysis, this situation is registered as a high-priority case requiring urgent attention, allowing users to take swift action.

[0345] Examples of prompts generated using an AI model include: "If a customer says on the phone, 'I'm very frustrated because I've been kept waiting for a long time,' please analyze the sentiment of this statement and provide instructions on how to respond appropriately."

[0346] This system allows us to accurately understand customers' emotional states and respond quickly and effectively, which is expected to improve the quality of service.

[0347] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0348] Step 1:

[0349] The terminal acquires voice information in real time from received telephone communications. Specifically, it captures voice signals using the microphone and communication devices built into the terminal and converts them into a digital format. In this process, the input is an analog voice signal, and the output is digital voice data.

[0350] Step 2:

[0351] The terminal securely transmits the acquired digital voice data to the server using an encryption protocol. The input is digital voice data, and the output is encrypted data packets transmitted over the network. This ensures the privacy and integrity of the data.

[0352] Step 3:

[0353] The server processes the received audio data using a speech conversion device, converting the audio information into text information. At this stage, where a generative AI model is applied, digital audio data is provided as input, and converted text information is obtained as output. Speech recognition accurately transcribes the speaker's utterances into text.

[0354] Step 4:

[0355] The server analyzes text information using natural language processing techniques. The input is text, and the output is extracted important information. This process involves contextual and keyword analysis, clarifying the customer's intent.

[0356] Step 5:

[0357] The server processes text information using sentiment analysis tools to identify the user's emotions from the text. This process uses the already analyzed text information as input and outputs the type and intensity of the emotion. Sentiment analysis identifies the emotions the customer is experiencing.

[0358] Step 6:

[0359] The server registers the analyzed text and sentiment information into the case management system. In this section, sentiment-analyzed data is provided as input, and prioritized case information is generated as output. The registered information is then used to assist with subsequent customer interactions.

[0360] Step 7:

[0361] The user implements customer support based on analysis results provided by the incident management system. The input is information from the incident management system, and the output is specific customer support measures. In this way, the user can take appropriate action quickly, contributing to improved customer satisfaction.

[0362] (Application Example 2)

[0363] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0364] Traditional telephone incident management systems, while capable of converting voice data into text, have the drawback of failing to analyze user emotions in real time and present them immediately to operators, thus hindering the improvement of customer service quality. There is a need for a system that can accurately grasp user emotions and provide swift and appropriate responses.

[0365] 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.

[0366] In this invention, the server includes means for acquiring voice information obtained from communications in real time, voice recognition means for converting the acquired voice information into text information, natural language processing means for analyzing the converted text information and extracting important information, and means for analyzing the user's emotional state and providing the emotional state to a visual display device. This makes it possible to improve the quality of customer service by analyzing the user's emotions in real time and presenting them to the operator quickly.

[0367] "Communication" is a general term for the mediation and technologies used to send and receive information.

[0368] "Audio information" refers to information that includes human speech, based on sound waveform data.

[0369] "Real-time" refers to processing or responding instantly without delay.

[0370] "Speech recognition means" refers to a technology or device that analyzes speech data and converts it into text information.

[0371] "Textual information" refers to linguistic information expressed in text format.

[0372] "Natural language processing means" refers to computational technologies and devices used to analyze and understand human language.

[0373] "Important information" refers to valuable data that should be extracted or used for a specific purpose.

[0374] An "incident management system" is a system or mechanism for organizing and monitoring events such as incidents and accidents.

[0375] "User's emotional state" refers to the emotional fluctuations and circumstances of the user, such as joy, anger, sadness, and other feelings.

[0376] A "visual display device" is a device that converts data into a form that can be seen and presents it.

[0377] To realize this invention, a system is built in which a server is responsible for processing voice information. Voice information is sent from the user's terminal to the server in real time. The server uses a computational model as a speech recognition means to convert the voice information into text information. Here, speech recognition technologies such as the Google Cloud Speech-to-Text API are used. The text information is analyzed by a natural language processing means, and important information is extracted. In this process, the Google Cloud Natural Language API is used to identify the user's emotional state from the text.

[0378] Once the user's emotional state is analyzed, the server provides this information to a visual display device, allowing operators to visually confirm the information via a head-mounted display or similar device if a quick response is needed. This enables operators to immediately understand the customer's emotions and take appropriate action.

[0379] For example, if a user expresses in a call that they are "frustrated by being kept waiting for a long time," the server converts the audio into text and uses an emotion engine to analyze the level of dissatisfaction. The result of this analysis is then visually displayed on the operator's display device as "The customer is dissatisfied."

[0380] An example of a prompt message is, "Please advise on how to visualize the emotion engine's output in a way that is easy for operators to understand." This will enable the system to provide more effective customer service.

[0381] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0382] Step 1:

[0383] The terminal acquires audio information. Audio information exchanged during communication is captured by the microphone and converted into a digital format. The input is an audio signal, and the output is digital audio data. This data is prepared for the next processing step.

[0384] Step 2:

[0385] The terminal sends digital audio data to the server. Here, the audio data is transferred to the server in real time via the network. The input is digital audio data, and the output is the audio data sent to the server via the network. This allows the server to begin processing the speech recognition.

[0386] Step 3:

[0387] The server converts digital audio data into text information using speech recognition technology. Specifically, it uses a computational model to generate text data from audio data. The input is digital audio data, and the output is text information. APIs such as Google Cloud Speech-to-Text are used.

[0388] Step 4:

[0389] The server analyzes textual information using natural language processing techniques and extracts important information. Specifically, it analyzes the context of the text and extracts key words spoken by the user. The input is textual information, and the output is the extracted important information.

[0390] Step 5:

[0391] The server analyzes the user's emotional state from information extracted using an emotion engine. Here, data obtained from natural language processing is used to identify the user's emotions. The input is the extracted key information, and the output is the user's emotional state.

[0392] Step 6:

[0393] The server provides the user's emotional state to a visual display device. This allows the operator to visually understand the customer's emotions through a head-mounted display or similar device. The input is the user's emotional state, and the output is the visually displayed emotional state.

[0394] 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.

[0395] 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.

[0396] 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.

[0397] [Third Embodiment]

[0398] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0399] 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.

[0400] 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).

[0401] 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.

[0402] 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.

[0403] 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).

[0404] 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.

[0405] 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.

[0406] 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.

[0407] 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.

[0408] 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.

[0409] 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".

[0410] The system of this invention is used in customer service and incident management via telephone. The system consists of the following steps and efficiently processes everything from acquiring voice data to registering it in a management tool.

[0411] First, the device detects a call and captures the phone's audio data in digital format. This audio data continues to be transmitted to the server in real time until the call ends.

[0412] Next, the server passes the received audio data to the speech recognition module. The speech recognition module uses a machine learning model to convert the audio data into text data. Here, the language model is designed to accurately understand the content of the speech and minimize misrecognition.

[0413] The converted text data is then sent to a natural language processing module. The server uses natural language processing techniques to analyze the text data and extract important information and keywords. This clarifies the essence of the problem and the data that needs to be solved, transforming it from a mere string of conversational text into a coherent and meaningful analysis.

[0414] Finally, the extracted information is automatically registered in the incident management tool via the server. This registration includes the incident's severity, category, and customer information. This allows users to easily review the registered incident information, facilitating faster response times.

[0415] For example, suppose a user calls technical support and reports a problem where their computer suddenly shuts down. The terminal captures this conversation, and the server converts it into text data that includes the context of "the user's computer unexpectedly shutting down." The server then registers this information as a "new hardware failure incident" in the incident management tool. Based on the record created by the system, the user can quickly take appropriate repair action.

[0416] Thus, the embodiment of the present invention combines speech recognition and natural language processing to enable accurate recording of call content and rapid registration in an incident management tool. This significantly improves the efficiency of customer service and the accuracy of operations.

[0417] The following describes the processing flow.

[0418] Step 1:

[0419] The device detects the start of a call and captures the audio data. The audio data is digitized and transmitted in real time to a server via the communication network.

[0420] Step 2:

[0421] The server passes the received audio data to the speech recognition module. The speech recognition module uses a machine learning model powered by generative AI to convert the audio into text data.

[0422] Step 3:

[0423] The server sends the transcribed text data to a natural language processing module. The natural language processing module analyzes the text and extracts important keywords and semantic information.

[0424] Step 4:

[0425] The server prepares the extracted information for registration with the incident management tool. The data is organized into the appropriate format and sent to the management tool via API.

[0426] Step 5:

[0427] Users can view newly registered incidents through the incident management tool. The notification function immediately displays new incidents requiring attention.

[0428] Step 6:

[0429] Users can review the details and circumstances of registered incidents and take appropriate action as needed. This enables a swift and accurate response.

[0430] (Example 1)

[0431] 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."

[0432] Traditional telephone communication systems have struggled to process voice data in real time and quickly organize and register it as information necessary for incident management. In particular, there is a need to accurately convert voice to text and effectively analyze that information to extract important details. Furthermore, a lack of an interface that allows users to easily manipulate information and take appropriate action is also a problem.

[0433] 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.

[0434] In this invention, the server includes means for acquiring voice data obtained from telephone communications in real time, voice recognition means for converting the acquired voice data into text data, natural language processing means for analyzing the converted text data and automatically organizing the information contained therein, means for classifying the analyzed information and recording it directly in a management tool, and means for providing an interface for users to easily check information and respond. This enables accurate processing of telephone communication content in real time and rapid incident registration, allowing users to efficiently utilize information and respond in a timely manner.

[0435] "Telephone communication" is a form of communication that converts voice information into electrical signals and transmits them to a remote location; it is a means of communication and information exchange.

[0436] "Audio data" refers to data that digitizes a person's voice and is in a format that can be processed and analyzed by computer systems.

[0437] "Real-time" refers to the concept of processing or communication occurring instantly, without any delay.

[0438] "Speech recognition means" refers to technologies or devices that convert speech data into text data, often using artificial intelligence or machine learning models.

[0439] "Text data" refers to string data that can be processed by a computer, and is a transcript obtained through speech recognition.

[0440] "Natural language processing" refers to technologies that enable computers to understand and process the language that humans normally use.

[0441] An "incident management tool" is software used to manage and track anomalies and failures in systems and services.

[0442] A "user" refers to an individual or group that operates a system or device and utilizes its functions.

[0443] An "interface" refers to the points of contact or means that enable communication and operation between a user and a system.

[0444] The system for carrying out this invention efficiently processes voice data obtained through telephone communication. Specifically, it consists of a terminal for digital voice recording and a server for performing advanced analysis.

[0445] First, the device detects voice communication and captures the voice data in digital format. VoIP technology can be used for this capture, and a common software option is Asterisk, an open-source communication platform. This process extracts the call content as digital data in real time.

[0446] Next, the server receives the acquired audio data and performs speech recognition. This process utilizes speech recognition services such as Google Speech-to-Text and Amazon Transcribe to convert the audio data into text data. As a result, the content of the audio is accurately represented in text with minimal errors.

[0447] The server then uses natural language processing technology to analyze the converted text data. Tools such as Python's NLTK library and spaCy are used to automatically extract important keywords and information from the text. This reveals the essence of the call content and makes it possible to define the next course of action.

[0448] The extracted information is automatically registered by the server in the incident management tool. This process utilizes commercially available software such as ServiceNow or JIRA, designed to comprehensively record incident type, severity, and customer details. This allows users to quickly access information through the system's interface and perform appropriate management and responses.

[0449] For example, if a technical support representative receives a call about a printer that has stopped printing, the terminal immediately records the conversation. The server identifies the "printer stopped printing" issue and registers this information as a "new printer malfunction" in the management tool. In this way, users can easily obtain information and take action quickly.

[0450] An example of a prompt message might be: "A user has reported a network latency issue. Please convert the audio data to text and register the necessary information in the management tool."

[0451] The introduction of this system will allow customer feedback to be instantly reflected within the system, enabling more effective customer service.

[0452] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0453] Step 1:

[0454] The terminal detects incoming calls and captures audio data in digital format as soon as the call begins. The input is an analog audio signal from a telephone call, which is converted into digital data using specific digitization software. This results in audio data packets that can be streamed in real time.

[0455] Step 2:

[0456] The server receives packets of audio data and sends the data to the speech recognition engine. The input is digital audio data sent from the terminal, which is converted into text data using the Google Speech-to-Text API or Amazon Transcribe. The speech recognition engine performs noise reduction and sound quality improvement filtering to generate accurate text data as output.

[0457] Step 3:

[0458] The server passes the acquired text data to a natural language processing engine for content analysis. It receives text data from a speech recognition engine as input and performs contextual analysis and keyword extraction using NLTK and spaCy libraries. Here, it identifies important information contained within the text, such as the type of problem and related information, and generates structured information data as output.

[0459] Step 4:

[0460] The server registers structured information with incident management tools. The input is information data extracted from a natural language processing engine, which is used to determine the category and priority of the problem. The output generates database entries that are registered with management tools such as ServiceNow and JIRA, organizing and storing the details of each incident.

[0461] Step 5:

[0462] Users review registered information and take action through the incident management tool interface. Input consists of data displayed on the management tool screen, and users can search for necessary information using specific search and filtering functions. Output provides users with the information needed for their next steps, enabling efficient response and problem resolution.

[0463] (Application Example 1)

[0464] 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."

[0465] Current voice assistant systems and home smart devices can provide basic query responses to voice commands, but they lack the ability to report complex problems or seamlessly integrate with external resources. Therefore, there is a need for improved user experience and faster, more efficient problem resolution when using smart devices in the home.

[0466] 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.

[0467] In this invention, the server includes means for acquiring voice input and performing voice recognition in real time, voice recognition means for converting the acquired voice data into text data, and natural language processing means for analyzing the converted text data and extracting important information. This enables the smart device to analyze the user's voice instructions and, if necessary, automate querying external information resources and reporting problems.

[0468] "Voice input" is the process of receiving a user's speech as a digital signal.

[0469] "Real-time" refers to a state where data processing is performed instantly, and results are obtained without delay.

[0470] "Speech recognition" is a technology that converts speech data into text data.

[0471] "Text data" refers to the transcribed text extracted from audio, and is data expressed in text format.

[0472] "Natural language processing" is a general term for technologies that use computers to understand, interpret, and generate human language.

[0473] "Information resources" refers to sources from which data is obtained, including external databases and information provision services.

[0474] "Problem reporting" refers to the act of a user informing the system of a bug or question.

[0475] A "management device" refers to a tool or system for registering, organizing, and transmitting data and information.

[0476] This invention is a system that analyzes user instructions and problem reports received via voice input in real time, and acquires information from external information resources as needed, thereby enabling automated responses and problem solving through smart devices and assistant devices within the home. Details are described below.

[0477] The server first utilizes smart speakers or home assistant devices (e.g., Google Nest, Amazon Echo) as hardware. The speech recognition software installed on the server acquires voice input in real time and converts the voice data into text data. For this, speech recognition technologies such as Google Cloud Speech-to-Text API and Amazon Transcribe are used.

[0478] Next, the server analyzes the obtained text data using natural language processing techniques. At this stage, software such as spaCy or Google Cloud Natural Language API is used to extract important information and generate queries to external information resources based on that information.

[0479] For example, if a user reports a problem such as "the living room lights won't turn on," the server analyzes the audio data, understands the problem, reports it to the management device and relevant support services, and either automatically suggests a solution or notifies the appropriate department.

[0480] An example of a prompt message would be, "We have received a report from a user that their robot vacuum cleaner is malfunctioning. Please explain how to analyze the report and forward it to customer support." This allows for efficient processing of user problem reports.

[0481] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0482] Step 1:

[0483] The device receives voice input from the user. Once voice input begins, the microphone captures the user's speech and prepares to send it to the server in real time as digital audio data. The input is raw audio data, and the output is audio data in digital format.

[0484] Step 2:

[0485] The server passes the received digital audio data to the speech recognition module. This module uses the Google Cloud Speech-to-Text API to convert the audio data into text data. The input is digital audio data, and the output is the converted text data. During this process, a machine learning model performs precise speech recognition based on the content of the audio utterance.

[0486] Step 3:

[0487] The server passes the text data obtained from speech recognition to a natural language processing module. This module uses spaCy or the Google Cloud Natural Language API to analyze the text data and extract important keywords and information. The input is text data, and the output is a set of extracted important information. This allows for a clear understanding of the context of the conversation and the essence of the issue.

[0488] Step 4:

[0489] The server uses the extracted information to query external information resources and management devices. In doing so, it generates API requests based on the information to respond to problem reports and information requests. The input is a set of important information, and the output is the API requests and the resulting query responses.

[0490] Step 5:

[0491] The server returns acquired external information or processing results to the user or sends them to the necessary support. In some cases, the management device provides notifications of improved lighting conditions via software. Inputs are external information and query responses, and outputs are problem solutions provided to the user or the appropriate department. This operation allows for the rapid and automated resolution of user problems.

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

[0493] The present invention provides a multifaceted incident management system that processes voice data obtained via telephone calls in real time and incorporates an emotion engine that identifies the user's emotions. This system includes the following elements:

[0494] The terminal first acquires the call audio data in real time and sends it to the server in digital format. Upon receiving the audio data, the server uses a speech recognition module to convert the audio into text data. Here, a machine learning model is used to apply speech recognition technology that supports multiple languages.

[0495] Next, the server passes the text data to a natural language processing module for contextual analysis. The natural language processing module extracts important information and uses an emotion engine to analyze the user's emotions expressed in the text. The emotion engine identifies the emotions the user may be feeling based on the expressions and phrasing in the text.

[0496] The analyzed text data and sentiment information are registered by the server in the incident management tool. The user sentiment information obtained here is used to prioritize responses and improve future customer service. The system can also analyze past sentiment data to help create response guidelines based on sentiment trends.

[0497] As a concrete example, suppose a customer says to support, "I've been waiting forever, and I'm really frustrated." The device acquires the audio data, and the server generates text data stating, "The customer is frustrated with the wait and really needs help." The emotion engine analyzes this text to identify strong frustration and urgency, and registers it as a high-priority incident. Based on this, the user can take swift action to alleviate the customer's anxiety.

[0498] Thus, the present invention provides a system that comprehensively responds to incidents, including not only the content of the incident but also the user's emotions, by combining speech recognition, natural language processing, and an emotion engine. This system can improve the quality of customer service and increase the overall efficiency of the organization.

[0499] The following describes the processing flow.

[0500] Step 1:

[0501] The device detects the start of a call and captures the audio data in real time. The audio data is digitized and ready to be sent to the server.

[0502] Step 2:

[0503] The server receives the audio data sent from the terminal. Upon receiving the data, it passes it to the speech recognition module, which then begins the process of converting the audio data into text data using a machine learning algorithm.

[0504] Step 3:

[0505] The server retrieves text data generated by the speech recognition module and sends it to the natural language processing module. Here, the context of the text data is analyzed, and important information is extracted.

[0506] Step 4:

[0507] The server sends the text data, which has been parsed by the natural language processing module, to the sentiment engine. The sentiment engine analyzes the customer's emotions revealed in the text and adds the results as metadata.

[0508] Step 5:

[0509] The server registers text data with sentiment information into the incident management tool. The system then records and stores the incident details, including sentiment information, in a formatted manner.

[0510] Step 6:

[0511] Users can review incident information registered using the incident management tool. By considering customer sentiment information, they can quickly take action on high-priority issues.

[0512] Step 7:

[0513] Users or organizations analyze long-term trends based on emotional data to improve their customer service strategies. This enables the implementation of measures that lead to increased customer satisfaction.

[0514] (Example 2)

[0515] 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."

[0516] In today's telephone communication environment, it is difficult to analyze the emotions and urgency conveyed by customers during calls in real time and to respond appropriately immediately. Traditional incident management systems simply transcribe voice information into text and report it, failing to grasp the user's emotions or underlying needs, which poses challenges to improving customer satisfaction and efficiently delivering services.

[0517] 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.

[0518] In this invention, the server includes means for acquiring voice information obtained from telephone communications in real time, voice conversion means for converting the acquired voice information into text information, natural language processing means for analyzing the converted text information and extracting important content, emotion analysis means for identifying emotions using the text information, and means for registering the analyzed text information and emotion information in a case management device. This makes it possible to quickly analyze the emotions and urgency of customers in telephone communications and respond appropriately.

[0519] "Telephone communication" is a means of communication that primarily transmits and receives voice information as voice signals.

[0520] "Audio information" refers to information that represents audio data in a digital format.

[0521] "Real-time" refers to a state where processing can be performed almost instantly, minimizing information delays.

[0522] "Voice conversion means" refers to technologies and devices for converting voice information into text information, and may utilize generation AI technology.

[0523] "Text information" refers to information expressed in the form of characters and symbols, and is a way of representing audio information as a string of characters.

[0524] "Natural language processing means" refers to technologies or devices for analyzing the grammar and context of text information and extracting important keywords and content.

[0525] "Emotion analysis means" refers to a technology or device for identifying a user's emotions based on expressions contained within text information.

[0526] An "incident management device" is a device or system that uses analyzed information to record and manage incidents, and to prioritize incidents and provide support for response.

[0527] This invention relates to a system that enables rapid customer service by analyzing voice information obtained from telephone communications in real time and making accurate emotional judgments. This system consists of three elements: a terminal, a server, and a user.

[0528] First, the terminal acquires voice information in real time. The terminal has a built-in microphone and communication device, which converts the voice into a digital format and sends it to the server as data. Encryption protocols are used to ensure the security of the communication.

[0529] Next, the server processes the received audio information using a speech conversion device, converting the audio data into text information. By using a generative AI model and applying advanced speech recognition technology, it is possible to generate highly accurate text information.

[0530] Subsequently, the server analyzes the text information using natural language processing tools and extracts important content. Simultaneously, sentiment analysis tools identify the user's emotions from the text information. This process allows the server to understand the customer's emotional state.

[0531] The analyzed information is registered in the incident management system. This system enables the prioritization of incidents and the proposal of countermeasures tailored to the nature of each incident.

[0532] Users use this analysis to handle customer interactions. For example, if a customer calls the support center and says, "I'm very frustrated because I've been kept waiting for a long time," the terminal captures this audio, the server transcribes the information into text, and analyzes it as "the customer is dissatisfied with the waiting time." Through sentiment analysis, this situation is registered as a high-priority case requiring urgent attention, allowing users to take swift action.

[0533] Examples of prompts generated using an AI model include: "If a customer says on the phone, 'I'm very frustrated because I've been kept waiting for a long time,' please analyze the sentiment of this statement and provide instructions on how to respond appropriately."

[0534] This system allows us to accurately understand customers' emotional states and respond quickly and effectively, which is expected to improve the quality of service.

[0535] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0536] Step 1:

[0537] The terminal acquires voice information in real time from received telephone communications. Specifically, it captures voice signals using the microphone and communication devices built into the terminal and converts them into a digital format. In this process, the input is an analog voice signal, and the output is digital voice data.

[0538] Step 2:

[0539] The terminal securely transmits the acquired digital voice data to the server using an encryption protocol. The input is digital voice data, and the output is encrypted data packets transmitted over the network. This ensures the privacy and integrity of the data.

[0540] Step 3:

[0541] The server processes the received audio data using a speech conversion device, converting the audio information into text information. At this stage, where a generative AI model is applied, digital audio data is provided as input, and converted text information is obtained as output. Speech recognition accurately transcribes the speaker's utterances into text.

[0542] Step 4:

[0543] The server analyzes text information using natural language processing techniques. The input is text, and the output is extracted important information. This process involves contextual and keyword analysis, clarifying the customer's intent.

[0544] Step 5:

[0545] The server processes text information using sentiment analysis tools to identify the user's emotions from the text. This process uses the already analyzed text information as input and outputs the type and intensity of the emotion. Sentiment analysis identifies the emotions the customer is experiencing.

[0546] Step 6:

[0547] The server registers the analyzed text and sentiment information into the case management system. In this section, sentiment-analyzed data is provided as input, and prioritized case information is generated as output. The registered information is then used to assist with subsequent customer interactions.

[0548] Step 7:

[0549] The user implements customer support based on analysis results provided by the incident management system. The input is information from the incident management system, and the output is specific customer support measures. In this way, the user can take appropriate action quickly, contributing to improved customer satisfaction.

[0550] (Application Example 2)

[0551] 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."

[0552] Traditional telephone incident management systems, while capable of converting voice data into text, have the drawback of failing to analyze user emotions in real time and present them immediately to operators, thus hindering the improvement of customer service quality. There is a need for a system that can accurately grasp user emotions and provide swift and appropriate responses.

[0553] 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.

[0554] In this invention, the server includes means for acquiring voice information obtained from communications in real time, voice recognition means for converting the acquired voice information into text information, natural language processing means for analyzing the converted text information and extracting important information, and means for analyzing the user's emotional state and providing the emotional state to a visual display device. This makes it possible to improve the quality of customer service by analyzing the user's emotions in real time and presenting them to the operator quickly.

[0555] "Communication" is a general term for the mediation and technologies used to send and receive information.

[0556] "Audio information" refers to information that includes human speech, based on sound waveform data.

[0557] "Real-time" refers to processing or responding instantly without delay.

[0558] "Speech recognition means" refers to a technology or device that analyzes speech data and converts it into text information.

[0559] "Textual information" refers to linguistic information expressed in text format.

[0560] "Natural language processing means" refers to computational technologies and devices used to analyze and understand human language.

[0561] "Important information" refers to valuable data that should be extracted or used for a specific purpose.

[0562] An "incident management system" is a system or mechanism for organizing and monitoring events such as incidents and accidents.

[0563] "User's emotional state" refers to the emotional fluctuations and circumstances of the user, such as joy, anger, sadness, and other feelings.

[0564] A "visual display device" is a device that converts data into a form that can be seen and presents it.

[0565] To realize this invention, a system is built in which a server is responsible for processing voice information. Voice information is sent from the user's terminal to the server in real time. The server uses a computational model as a speech recognition means to convert the voice information into text information. Here, speech recognition technologies such as the Google Cloud Speech-to-Text API are used. The text information is analyzed by a natural language processing means, and important information is extracted. In this process, the Google Cloud Natural Language API is used to identify the user's emotional state from the text.

[0566] Once the user's emotional state is analyzed, the server provides this information to a visual display device, allowing operators to visually confirm the information via a head-mounted display or similar device if a quick response is needed. This enables operators to immediately understand the customer's emotions and take appropriate action.

[0567] For example, if a user expresses in a call that they are "frustrated by being kept waiting for a long time," the server converts the audio into text and uses an emotion engine to analyze the level of dissatisfaction. The result of this analysis is then visually displayed on the operator's display device as "The customer is dissatisfied."

[0568] An example of a prompt message is, "Please advise on how to visualize the emotion engine's output in a way that is easy for operators to understand." This will enable the system to provide more effective customer service.

[0569] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0570] Step 1:

[0571] The terminal acquires audio information. Audio information exchanged during communication is captured by the microphone and converted into a digital format. The input is an audio signal, and the output is digital audio data. This data is prepared for the next processing step.

[0572] Step 2:

[0573] The terminal sends digital audio data to the server. Here, the audio data is transferred to the server in real time via the network. The input is digital audio data, and the output is the audio data sent to the server via the network. This allows the server to begin processing the speech recognition.

[0574] Step 3:

[0575] The server converts digital audio data into text information using speech recognition technology. Specifically, it uses a computational model to generate text data from audio data. The input is digital audio data, and the output is text information. APIs such as Google Cloud Speech-to-Text are used.

[0576] Step 4:

[0577] The server analyzes textual information using natural language processing techniques and extracts important information. Specifically, it analyzes the context of the text and extracts key words spoken by the user. The input is textual information, and the output is the extracted important information.

[0578] Step 5:

[0579] The server analyzes the user's emotional state from information extracted using an emotion engine. Here, data obtained from natural language processing is used to identify the user's emotions. The input is the extracted key information, and the output is the user's emotional state.

[0580] Step 6:

[0581] The server provides the user's emotional state to a visual display device. This allows the operator to visually understand the customer's emotions through a head-mounted display or similar device. The input is the user's emotional state, and the output is the visually displayed emotional state.

[0582] 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.

[0583] 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.

[0584] 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.

[0585] [Fourth Embodiment]

[0586] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0587] 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.

[0588] 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).

[0589] 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.

[0590] 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.

[0591] 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).

[0592] 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.

[0593] 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.

[0594] 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.

[0595] 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.

[0596] 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.

[0597] 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.

[0598] 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".

[0599] The system of this invention is used in customer service and incident management via telephone. The system consists of the following steps and efficiently processes everything from acquiring voice data to registering it in a management tool.

[0600] First, the device detects a call and captures the phone's audio data in digital format. This audio data continues to be transmitted to the server in real time until the call ends.

[0601] Next, the server passes the received audio data to the speech recognition module. The speech recognition module uses a machine learning model to convert the audio data into text data. Here, the language model is designed to accurately understand the content of the speech and minimize misrecognition.

[0602] The converted text data is then sent to a natural language processing module. The server uses natural language processing techniques to analyze the text data and extract important information and keywords. This clarifies the essence of the problem and the data that needs to be solved, transforming it from a mere string of conversational text into a coherent and meaningful analysis.

[0603] Finally, the extracted information is automatically registered in the incident management tool via the server. This registration includes the incident's severity, category, and customer information. This allows users to easily review the registered incident information, facilitating faster response times.

[0604] For example, suppose a user calls technical support and reports a problem where their computer suddenly shuts down. The terminal captures this conversation, and the server converts it into text data that includes the context of "the user's computer unexpectedly shutting down." The server then registers this information as a "new hardware failure incident" in the incident management tool. Based on the record created by the system, the user can quickly take appropriate repair action.

[0605] Thus, the embodiment of the present invention combines speech recognition and natural language processing to enable accurate recording of call content and rapid registration in an incident management tool. This significantly improves the efficiency of customer service and the accuracy of operations.

[0606] The following describes the processing flow.

[0607] Step 1:

[0608] The device detects the start of a call and captures the audio data. The audio data is digitized and transmitted in real time to a server via the communication network.

[0609] Step 2:

[0610] The server passes the received audio data to the speech recognition module. The speech recognition module uses a machine learning model powered by generative AI to convert the audio into text data.

[0611] Step 3:

[0612] The server sends the transcribed text data to a natural language processing module. The natural language processing module analyzes the text and extracts important keywords and semantic information.

[0613] Step 4:

[0614] The server prepares the extracted information for registration with the incident management tool. The data is organized into the appropriate format and sent to the management tool via API.

[0615] Step 5:

[0616] Users can view newly registered incidents through the incident management tool. The notification function immediately displays new incidents requiring attention.

[0617] Step 6:

[0618] Users can review the details and circumstances of registered incidents and take appropriate action as needed. This enables a swift and accurate response.

[0619] (Example 1)

[0620] 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".

[0621] Traditional telephone communication systems have struggled to process voice data in real time and quickly organize and register it as information necessary for incident management. In particular, there is a need to accurately convert voice to text and effectively analyze that information to extract important details. Furthermore, a lack of an interface that allows users to easily manipulate information and take appropriate action is also a problem.

[0622] 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.

[0623] In this invention, the server includes means for acquiring voice data obtained from telephone communications in real time, voice recognition means for converting the acquired voice data into text data, natural language processing means for analyzing the converted text data and automatically organizing the information contained therein, means for classifying the analyzed information and recording it directly in a management tool, and means for providing an interface for users to easily check information and respond. This enables accurate processing of telephone communication content in real time and rapid incident registration, allowing users to efficiently utilize information and respond in a timely manner.

[0624] "Telephone communication" is a form of communication that converts voice information into electrical signals and transmits them to a remote location; it is a means of communication and information exchange.

[0625] "Audio data" refers to data that digitizes a person's voice and is in a format that can be processed and analyzed by computer systems.

[0626] "Real-time" refers to the concept of processing or communication occurring instantly, without any delay.

[0627] "Speech recognition means" refers to technologies or devices that convert speech data into text data, often using artificial intelligence or machine learning models.

[0628] "Text data" refers to string data that can be processed by a computer, and is a transcript obtained through speech recognition.

[0629] "Natural language processing" refers to technologies that enable computers to understand and process the language that humans normally use.

[0630] An "incident management tool" is software used to manage and track anomalies and failures in systems and services.

[0631] A "user" refers to an individual or group that operates a system or device and utilizes its functions.

[0632] An "interface" refers to the points of contact or means that enable communication and operation between a user and a system.

[0633] The system for carrying out this invention efficiently processes voice data obtained through telephone communication. Specifically, it consists of a terminal for digital voice recording and a server for performing advanced analysis.

[0634] First, the device detects voice communication and captures the voice data in digital format. VoIP technology can be used for this capture, and a common software option is Asterisk, an open-source communication platform. This process extracts the call content as digital data in real time.

[0635] Next, the server receives the acquired audio data and performs speech recognition. This process utilizes speech recognition services such as Google Speech-to-Text and Amazon Transcribe to convert the audio data into text data. As a result, the content of the audio is accurately represented in text with minimal errors.

[0636] The server then uses natural language processing technology to analyze the converted text data. Tools such as Python's NLTK library and spaCy are used to automatically extract important keywords and information from the text. This reveals the essence of the call content and makes it possible to define the next course of action.

[0637] The extracted information is automatically registered by the server in the incident management tool. This process utilizes commercially available software such as ServiceNow or JIRA, designed to comprehensively record incident type, severity, and customer details. This allows users to quickly access information through the system's interface and perform appropriate management and responses.

[0638] For example, if a technical support representative receives a call about a printer that has stopped printing, the terminal immediately records the conversation. The server identifies the "printer stopped printing" issue and registers this information as a "new printer malfunction" in the management tool. In this way, users can easily obtain information and take action quickly.

[0639] An example of a prompt message might be: "A user has reported a network latency issue. Please convert the audio data to text and register the necessary information in the management tool."

[0640] The introduction of this system will allow customer feedback to be instantly reflected within the system, enabling more effective customer service.

[0641] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0642] Step 1:

[0643] The terminal detects incoming calls and captures audio data in digital format as soon as the call begins. The input is an analog audio signal from a telephone call, which is converted into digital data using specific digitization software. This results in audio data packets that can be streamed in real time.

[0644] Step 2:

[0645] The server receives packets of audio data and sends the data to the speech recognition engine. The input is digital audio data sent from the terminal, which is converted into text data using the Google Speech-to-Text API or Amazon Transcribe. The speech recognition engine performs noise reduction and sound quality improvement filtering to generate accurate text data as output.

[0646] Step 3:

[0647] The server passes the acquired text data to a natural language processing engine for content analysis. It receives text data from a speech recognition engine as input and performs contextual analysis and keyword extraction using NLTK and spaCy libraries. Here, it identifies important information contained within the text, such as the type of problem and related information, and generates structured information data as output.

[0648] Step 4:

[0649] The server registers structured information with incident management tools. The input is information data extracted from a natural language processing engine, which is used to determine the category and priority of the problem. The output generates database entries that are registered with management tools such as ServiceNow and JIRA, organizing and storing the details of each incident.

[0650] Step 5:

[0651] Users review registered information and take action through the incident management tool interface. Input consists of data displayed on the management tool screen, and users can search for necessary information using specific search and filtering functions. Output provides users with the information needed for their next steps, enabling efficient response and problem resolution.

[0652] (Application Example 1)

[0653] 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".

[0654] Current voice assistant systems and home smart devices can provide basic query responses to voice commands, but they lack the ability to report complex problems or seamlessly integrate with external resources. Therefore, there is a need for improved user experience and faster, more efficient problem resolution when using smart devices in the home.

[0655] 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.

[0656] In this invention, the server includes means for acquiring voice input and performing voice recognition in real time, voice recognition means for converting the acquired voice data into text data, and natural language processing means for analyzing the converted text data and extracting important information. This enables the smart device to analyze the user's voice instructions and, if necessary, automate querying external information resources and reporting problems.

[0657] "Voice input" is the process of receiving a user's speech as a digital signal.

[0658] "Real-time" refers to a state where data processing is performed instantly, and results are obtained without delay.

[0659] "Speech recognition" is a technology that converts speech data into text data.

[0660] "Text data" refers to the transcribed text extracted from audio, and is data expressed in text format.

[0661] "Natural language processing" is a general term for technologies that use computers to understand, interpret, and generate human language.

[0662] "Information resources" refers to sources from which data is obtained, including external databases and information provision services.

[0663] "Problem reporting" refers to the act of a user informing the system of a bug or question.

[0664] A "management device" refers to a tool or system for registering, organizing, and transmitting data and information.

[0665] This invention is a system that analyzes user instructions and problem reports received via voice input in real time, and acquires information from external information resources as needed, thereby enabling automated responses and problem solving through smart devices and assistant devices within the home. Details are described below.

[0666] The server first utilizes smart speakers or home assistant devices (e.g., Google Nest, Amazon Echo) as hardware. The speech recognition software installed on the server acquires voice input in real time and converts the voice data into text data. For this, speech recognition technologies such as Google Cloud Speech-to-Text API and Amazon Transcribe are used.

[0667] Next, the server analyzes the obtained text data using natural language processing techniques. At this stage, software such as spaCy or Google Cloud Natural Language API is used to extract important information and generate queries to external information resources based on that information.

[0668] For example, if a user reports a problem such as "the living room lights won't turn on," the server analyzes the audio data, understands the problem, reports it to the management device and relevant support services, and either automatically suggests a solution or notifies the appropriate department.

[0669] An example of a prompt message would be, "We have received a report from a user that their robot vacuum cleaner is malfunctioning. Please explain how to analyze the report and forward it to customer support." This allows for efficient processing of user problem reports.

[0670] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0671] Step 1:

[0672] The device receives voice input from the user. Once voice input begins, the microphone captures the user's speech and prepares to send it to the server in real time as digital audio data. The input is raw audio data, and the output is audio data in digital format.

[0673] Step 2:

[0674] The server passes the received digital audio data to the speech recognition module. This module uses the Google Cloud Speech-to-Text API to convert the audio data into text data. The input is digital audio data, and the output is the converted text data. During this process, a machine learning model performs precise speech recognition based on the content of the audio utterance.

[0675] Step 3:

[0676] The server passes the text data obtained from speech recognition to a natural language processing module. This module uses spaCy or the Google Cloud Natural Language API to analyze the text data and extract important keywords and information. The input is text data, and the output is a set of extracted important information. This allows for a clear understanding of the context of the conversation and the essence of the issue.

[0677] Step 4:

[0678] The server uses the extracted information to query external information resources and management devices. In doing so, it generates API requests based on the information to respond to problem reports and information requests. The input is a set of important information, and the output is the API requests and the resulting query responses.

[0679] Step 5:

[0680] The server returns acquired external information or processing results to the user or sends them to the necessary support. In some cases, the management device provides notifications of improved lighting conditions via software. Inputs are external information and query responses, and outputs are problem solutions provided to the user or the appropriate department. This operation allows for the rapid and automated resolution of user problems.

[0681] 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.

[0682] The present invention provides a multifaceted incident management system that processes voice data obtained via telephone calls in real time and incorporates an emotion engine that identifies the user's emotions. This system includes the following elements:

[0683] The terminal first acquires the call audio data in real time and sends it to the server in digital format. Upon receiving the audio data, the server uses a speech recognition module to convert the audio into text data. Here, a machine learning model is used to apply speech recognition technology that supports multiple languages.

[0684] Next, the server passes the text data to a natural language processing module for contextual analysis. The natural language processing module extracts important information and uses an emotion engine to analyze the user's emotions expressed in the text. The emotion engine identifies the emotions the user may be feeling based on the expressions and phrasing in the text.

[0685] The analyzed text data and sentiment information are registered by the server in the incident management tool. The user sentiment information obtained here is used to prioritize responses and improve future customer service. The system can also analyze past sentiment data to help create response guidelines based on sentiment trends.

[0686] As a concrete example, suppose a customer says to support, "I've been waiting forever, and I'm really frustrated." The device acquires the audio data, and the server generates text data stating, "The customer is frustrated with the wait and really needs help." The emotion engine analyzes this text to identify strong frustration and urgency, and registers it as a high-priority incident. Based on this, the user can take swift action to alleviate the customer's anxiety.

[0687] Thus, the present invention provides a system that comprehensively responds to incidents, including not only the content of the incident but also the user's emotions, by combining speech recognition, natural language processing, and an emotion engine. This system can improve the quality of customer service and increase the overall efficiency of the organization.

[0688] The following describes the processing flow.

[0689] Step 1:

[0690] The device detects the start of a call and captures the audio data in real time. The audio data is digitized and ready to be sent to the server.

[0691] Step 2:

[0692] The server receives the audio data sent from the terminal. Upon receiving the data, it passes it to the speech recognition module, which then begins the process of converting the audio data into text data using a machine learning algorithm.

[0693] Step 3:

[0694] The server retrieves text data generated by the speech recognition module and sends it to the natural language processing module. Here, the context of the text data is analyzed, and important information is extracted.

[0695] Step 4:

[0696] The server sends the text data, which has been parsed by the natural language processing module, to the sentiment engine. The sentiment engine analyzes the customer's emotions revealed in the text and adds the results as metadata.

[0697] Step 5:

[0698] The server registers text data with sentiment information into the incident management tool. The system then records and stores the incident details, including sentiment information, in a formatted manner.

[0699] Step 6:

[0700] Users can review incident information registered using the incident management tool. By considering customer sentiment information, they can quickly take action on high-priority issues.

[0701] Step 7:

[0702] Users or organizations analyze long-term trends based on emotional data to improve their customer service strategies. This enables the implementation of measures that lead to increased customer satisfaction.

[0703] (Example 2)

[0704] 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".

[0705] In today's telephone communication environment, it is difficult to analyze the emotions and urgency conveyed by customers during calls in real time and to respond appropriately immediately. Traditional incident management systems simply transcribe voice information into text and report it, failing to grasp the user's emotions or underlying needs, which poses challenges to improving customer satisfaction and efficiently delivering services.

[0706] 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.

[0707] In this invention, the server includes means for acquiring voice information obtained from telephone communications in real time, voice conversion means for converting the acquired voice information into text information, natural language processing means for analyzing the converted text information and extracting important content, emotion analysis means for identifying emotions using the text information, and means for registering the analyzed text information and emotion information in a case management device. This makes it possible to quickly analyze the emotions and urgency of customers in telephone communications and respond appropriately.

[0708] "Telephone communication" is a means of communication that primarily transmits and receives voice information as voice signals.

[0709] "Audio information" refers to information that represents audio data in a digital format.

[0710] "Real-time" refers to a state where processing can be performed almost instantly, minimizing information delays.

[0711] "Voice conversion means" refers to technologies and devices for converting voice information into text information, and may utilize generation AI technology.

[0712] "Text information" refers to information expressed in the form of characters and symbols, and is a way of representing audio information as a string of characters.

[0713] "Natural language processing means" refers to technologies or devices for analyzing the grammar and context of text information and extracting important keywords and content.

[0714] "Emotion analysis means" refers to a technology or device for identifying a user's emotions based on expressions contained within text information.

[0715] An "incident management device" is a device or system that uses analyzed information to record and manage incidents, and to prioritize incidents and provide support for response.

[0716] This invention relates to a system that enables rapid customer service by analyzing voice information obtained from telephone communications in real time and making accurate emotional judgments. This system consists of three elements: a terminal, a server, and a user.

[0717] First, the terminal acquires voice information in real time. The terminal has a built-in microphone and communication device, which converts the voice into a digital format and sends it to the server as data. Encryption protocols are used to ensure the security of the communication.

[0718] Next, the server processes the received audio information using a speech conversion device, converting the audio data into text information. By using a generative AI model and applying advanced speech recognition technology, it is possible to generate highly accurate text information.

[0719] Subsequently, the server analyzes the text information using natural language processing tools and extracts important content. Simultaneously, sentiment analysis tools identify the user's emotions from the text information. This process allows the server to understand the customer's emotional state.

[0720] The analyzed information is registered in the incident management system. This system enables the prioritization of incidents and the proposal of countermeasures tailored to the nature of each incident.

[0721] Users use this analysis to handle customer interactions. For example, if a customer calls the support center and says, "I'm very frustrated because I've been kept waiting for a long time," the terminal captures this audio, the server transcribes the information into text, and analyzes it as "the customer is dissatisfied with the waiting time." Through sentiment analysis, this situation is registered as a high-priority case requiring urgent attention, allowing users to take swift action.

[0722] Examples of prompts generated using an AI model include: "If a customer says on the phone, 'I'm very frustrated because I've been kept waiting for a long time,' please analyze the sentiment of this statement and provide instructions on how to respond appropriately."

[0723] This system allows us to accurately understand customers' emotional states and respond quickly and effectively, which is expected to improve the quality of service.

[0724] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0725] Step 1:

[0726] The terminal acquires voice information in real time from received telephone communications. Specifically, it captures voice signals using the microphone and communication devices built into the terminal and converts them into a digital format. In this process, the input is an analog voice signal, and the output is digital voice data.

[0727] Step 2:

[0728] The terminal securely transmits the acquired digital voice data to the server using an encryption protocol. The input is digital voice data, and the output is encrypted data packets transmitted over the network. This ensures the privacy and integrity of the data.

[0729] Step 3:

[0730] The server processes the received audio data using a speech conversion device, converting the audio information into text information. At this stage, where a generative AI model is applied, digital audio data is provided as input, and converted text information is obtained as output. Speech recognition accurately transcribes the speaker's utterances into text.

[0731] Step 4:

[0732] The server analyzes text information using natural language processing techniques. The input is text, and the output is extracted important information. This process involves contextual and keyword analysis, clarifying the customer's intent.

[0733] Step 5:

[0734] The server processes text information using sentiment analysis tools to identify the user's emotions from the text. This process uses the already analyzed text information as input and outputs the type and intensity of the emotion. Sentiment analysis identifies the emotions the customer is experiencing.

[0735] Step 6:

[0736] The server registers the analyzed text and sentiment information into the case management system. In this section, sentiment-analyzed data is provided as input, and prioritized case information is generated as output. The registered information is then used to assist with subsequent customer interactions.

[0737] Step 7:

[0738] The user implements customer support based on analysis results provided by the incident management system. The input is information from the incident management system, and the output is specific customer support measures. In this way, the user can take appropriate action quickly, contributing to improved customer satisfaction.

[0739] (Application Example 2)

[0740] 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".

[0741] Traditional telephone incident management systems, while capable of converting voice data into text, have the drawback of failing to analyze user emotions in real time and present them immediately to operators, thus hindering the improvement of customer service quality. There is a need for a system that can accurately grasp user emotions and provide swift and appropriate responses.

[0742] 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.

[0743] In this invention, the server includes means for acquiring voice information obtained from communications in real time, voice recognition means for converting the acquired voice information into text information, natural language processing means for analyzing the converted text information and extracting important information, and means for analyzing the user's emotional state and providing the emotional state to a visual display device. This makes it possible to improve the quality of customer service by analyzing the user's emotions in real time and presenting them to the operator quickly.

[0744] "Communication" is a general term for the mediation and technologies used to send and receive information.

[0745] "Audio information" refers to information that includes human speech, based on sound waveform data.

[0746] "Real-time" refers to processing or responding instantly without delay.

[0747] "Speech recognition means" refers to a technology or device that analyzes speech data and converts it into text information.

[0748] "Textual information" refers to linguistic information expressed in text format.

[0749] "Natural language processing means" refers to computational technologies and devices used to analyze and understand human language.

[0750] "Important information" refers to valuable data that should be extracted or used for a specific purpose.

[0751] An "incident management system" is a system or mechanism for organizing and monitoring events such as incidents and accidents.

[0752] "User's emotional state" refers to the emotional fluctuations and circumstances of the user, such as joy, anger, sadness, and other feelings.

[0753] A "visual display device" is a device that converts data into a form that can be seen and presents it.

[0754] To realize this invention, a system is built in which a server is responsible for processing voice information. Voice information is sent from the user's terminal to the server in real time. The server uses a computational model as a speech recognition means to convert the voice information into text information. Here, speech recognition technologies such as the Google Cloud Speech-to-Text API are used. The text information is analyzed by a natural language processing means, and important information is extracted. In this process, the Google Cloud Natural Language API is used to identify the user's emotional state from the text.

[0755] Once the user's emotional state is analyzed, the server provides this information to a visual display device, allowing operators to visually confirm the information via a head-mounted display or similar device if a quick response is needed. This enables operators to immediately understand the customer's emotions and take appropriate action.

[0756] For example, if a user expresses in a call that they are "frustrated by being kept waiting for a long time," the server converts the audio into text and uses an emotion engine to analyze the level of dissatisfaction. The result of this analysis is then visually displayed on the operator's display device as "The customer is dissatisfied."

[0757] An example of a prompt message is, "Please advise on how to visualize the emotion engine's output in a way that is easy for operators to understand." This will enable the system to provide more effective customer service.

[0758] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0759] Step 1:

[0760] The terminal acquires audio information. Audio information exchanged during communication is captured by the microphone and converted into a digital format. The input is an audio signal, and the output is digital audio data. This data is prepared for the next processing step.

[0761] Step 2:

[0762] The terminal sends digital audio data to the server. Here, the audio data is transferred to the server in real time via the network. The input is digital audio data, and the output is the audio data sent to the server via the network. This allows the server to begin processing the speech recognition.

[0763] Step 3:

[0764] The server converts digital audio data into text information using speech recognition technology. Specifically, it uses a computational model to generate text data from audio data. The input is digital audio data, and the output is text information. APIs such as Google Cloud Speech-to-Text are used.

[0765] Step 4:

[0766] The server analyzes textual information using natural language processing techniques and extracts important information. Specifically, it analyzes the context of the text and extracts key words spoken by the user. The input is textual information, and the output is the extracted important information.

[0767] Step 5:

[0768] The server analyzes the user's emotional state from information extracted using an emotion engine. Here, data obtained from natural language processing is used to identify the user's emotions. The input is the extracted key information, and the output is the user's emotional state.

[0769] Step 6:

[0770] The server provides the user's emotional state to a visual display device. This allows the operator to visually understand the customer's emotions through a head-mounted display or similar device. The input is the user's emotional state, and the output is the visually displayed emotional state.

[0771] 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.

[0772] 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.

[0773] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0774] 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.

[0775] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0776] 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.

[0777] 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.

[0778] 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.

[0779] 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."

[0780] 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.

[0781] 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.

[0782] 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.

[0783] 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.

[0784] 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.

[0785] 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.

[0786] 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.

[0787] 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.

[0788] 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.

[0789] 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.

[0790] 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.

[0791] 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.

[0792] The following is further disclosed regarding the embodiments described above.

[0793] (Claim 1)

[0794] A means of acquiring voice data obtained from telephone communications in real time,

[0795] A speech recognition means for converting acquired audio data into text data,

[0796] A natural language processing method that analyzes the converted text data and extracts important information,

[0797] A means of registering the extracted information in the incident management tool,

[0798] A system that includes this.

[0799] (Claim 2)

[0800] The system according to claim 1, wherein the speech recognition means converts speech data into text data using a machine learning model.

[0801] (Claim 3)

[0802] The system according to claim 1, wherein the natural language processing means converts the extracted information into a format for registration and organization in an incident management tool.

[0803] "Example 1"

[0804] (Claim 1)

[0805] A means of acquiring voice data obtained from telephone communications in real time,

[0806] A speech recognition means for converting acquired audio data into text data,

[0807] A natural language processing means that analyzes converted text data and automatically organizes the information contained therein,

[0808] A means of classifying the analyzed information and recording it directly in a management tool,

[0809] A means of providing an interface for users to easily check information and respond,

[0810] A system that includes this.

[0811] (Claim 2)

[0812] The system according to claim 1, wherein the speech recognition means is a means of converting speech data into text data using a machine learning model and improving accuracy while removing speech noise from the external environment.

[0813] (Claim 3)

[0814] The system according to claim 1, wherein the natural language processing means is a means of converting information into a format for registration and organization in a management tool through an automated information extraction process using a generative model.

[0815] "Application Example 1"

[0816] (Claim 1)

[0817] A means of acquiring voice input and performing real-time speech recognition,

[0818] A speech recognition means for converting acquired audio data into text data,

[0819] A natural language processing method for analyzing converted text data and extracting important information,

[0820] A means for querying external information resources based on the analysis results and generating a response,

[0821] Means for registering and transmitting extracted information to a management device,

[0822] A system that includes this.

[0823] (Claim 2)

[0824] The system according to claim 1, wherein the speech recognition means converts speech data into text data using a machine learning model.

[0825] (Claim 3)

[0826] The system according to claim 1, wherein the natural language processing means converts the extracted information into a format for transmission to a relevant support center.

[0827] "Example 2 of combining an emotion engine"

[0828] (Claim 1)

[0829] A means of acquiring voice information obtained from telephone communications in real time,

[0830] A speech conversion means for converting acquired speech information into text information,

[0831] A natural language processing means that analyzes the converted text information and extracts important content,

[0832] A means of emotion analysis that identifies emotions using text information,

[0833] A means for registering analyzed text information and sentiment information in a case management device,

[0834] A system that includes this.

[0835] (Claim 2)

[0836] The system according to claim 1, wherein the voice conversion means converts voice information into text information using generation AI technology.

[0837] (Claim 3)

[0838] The system according to claim 1, wherein the natural language processing means identifies emotions from text information and organizes and registers the emotion information in a case management device.

[0839] "Application example 2 when combining with an emotional engine"

[0840] (Claim 1)

[0841] A means of acquiring voice information obtained from communications in real time,

[0842] A speech recognition means for converting acquired speech information into text information,

[0843] A natural language processing means that analyzes the converted text information and extracts important information,

[0844] A means for registering the extracted information with the incident management device,

[0845] A means for analyzing the user's emotional state and providing that emotional state to a visual display device,

[0846] A system that includes this.

[0847] (Claim 2)

[0848] The system according to claim 1, wherein the speech recognition means converts speech information into text information using a computational model.

[0849] (Claim 3)

[0850] The system according to claim 1, wherein the natural language processing means converts the extracted information into a format for registration and organization in an incident management device. [Explanation of symbols]

[0851] 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 acquiring voice data obtained from telephone communications in real time, A speech recognition means for converting acquired audio data into text data, A natural language processing method that analyzes the converted text data and extracts important information, A means of registering the extracted information in the incident management tool, A system that includes this.

2. The system according to claim 1, wherein the speech recognition means converts speech data into text data using a machine learning model.

3. The system according to claim 1, wherein the natural language processing means converts the extracted information into a format for registration and organization in an incident management tool.

Images