system

Abstract

We provide the system. [Solution] An acoustic conversion means that receives an acoustic signal and converts the acoustic signal into character data, A natural language processing means for extracting specific information from the character data, A data input means for automatically inputting the extracted specific information into a recording device, To reduce the burden on on-site workers, a means of presenting information using face-worn information devices, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In telephone response operations, manual recording of voices takes a great deal of time and effort, and there is also a risk of recording errors and information leakage. As a result, the efficiency of incident response may decrease, and customer satisfaction may be impaired. In order to solve such problems, it is aimed to provide a technology for automatically and accurately processing voice information and using it for incident management.

Means for Solving the Problems

[0005] By using acoustic conversion means for receiving an acoustic signal and converting it into text in real time, and further implementing natural language processing means for extracting specific information from the text and providing data input means for automatically inputting it into an electronic recording device, the recording and management of telephone conversations are automated, and the problems of conventional manual work are solved.

[0006] An "acoustic signal" is a signal that electrically represents sound, and is usually collected by a device such as a microphone.

[0007] "Acoustic conversion means" refers to a process or device that digitizes an acoustic signal and converts that digital audio data into text.

[0008] "Natural language processing methods" are technologies for extracting useful information from text data and understanding the language-specific meaning and context.

[0009] A "data entry means" is a device or process that electronically records extracted information and automatically registers it in an incident management tool or database.

[0010] An "electronic recording device" is a device for recording and storing digital information, and generally refers to a storage device in a computer or server.

[0011] "Real-time" refers to a method where data processing is performed instantly, resulting in virtually no delay.

[0012] "Specific information" refers to important and relevant data extracted from audio or text, and typically includes information necessary for incident response. [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]It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

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

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

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

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

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

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

[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 the present invention is implemented with multiple components, including a terminal and a server, to efficiently utilize the content of telephone conversations for incident management. First, when a user answers a telephone call, the terminal acquires the conversation as an acoustic signal. The terminal is equipped with a communication module for transmitting this acoustic signal and sends the data to the server in real time.

[0035] The server converts the received acoustic signal into text data using an acoustic conversion device. This text conversion process efficiently converts the voice input into text information, allowing it to proceed to the next processing stage.

[0036] The converted text data is analyzed by natural language processing tools on the server. Here, important specific information is extracted. This process identifies information highly necessary for incident management, such as user IDs and the nature of the problem, improving the accuracy of the records.

[0037] The extracted information is automatically registered in an electronic recording device using a data entry mechanism. Registration is performed according to a pre-configured format and stored in a format easily usable by the incident management system. This eliminates the need for manual data entry, significantly reducing processing time and preventing errors.

[0038] As a concrete example, consider a scenario where a user receives a customer call and handles a system login issue as an incident. The terminal collects the entire conversation, and the server immediately transcribes it into text, extracts important information, and registers it. This entire process allows the user to complete incident response quickly and efficiently.

[0039] The system of the present invention records specific information in real time, is effective in improving incident management operations, reduces the workload on users, and enhances the overall reliability of operations.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The device acquires the user's phone conversation and records it in real time as an acoustic signal. The recorded acoustic signal is immediately prepared to be sent to the server.

[0043] Step 2:

[0044] The server receives an acoustic signal from the terminal. Using an acoustic conversion device, this acoustic signal is converted into text data. This allows the audio to be treated as text information.

[0045] Step 3:

[0046] The server passes the text data to a natural language processing system, which then extracts important specific information. Specifically, user IDs, problem descriptions, dates, and times are analyzed.

[0047] Step 4:

[0048] The server extracts specific information, organizes it, and registers it in an electronic recording device using data entry tools. The information is formatted in a way suitable for the incident management system and recorded without errors.

[0049] Step 5:

[0050] The user reviews the recorded information using the incident management tool. They enter additional information as needed and complete the incident processing. This review ensures the accuracy and reliability of the information.

[0051] (Example 1)

[0052] 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."

[0053] In modern communications, there is a need to efficiently convert telephone conversations into incident management data. Traditional methods require manual recording and analysis of conversations, which is time-consuming and carries the risk of human error. The challenge lies in accurately extracting and quickly recording critical specific information in real time.

[0054] 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.

[0055] In this invention, the server includes communication means for acquiring an acoustic signal and transmitting the acoustic signal to a data processing device, speech recognition means for converting the acoustic signal into text, and information analysis means for analyzing specific identification information from the text. This makes it possible to utilize the content of telephone conversations in real time, efficiently and accurately for incident management.

[0056] An "acoustic signal" is a data format that converts sound into an electrical signal and is used in communications and data processing.

[0057] A "data processing device" is a device used to analyze, transform, store, or transfer received data.

[0058] "Communication means" refers to technologies and modules for sending and receiving information, and plays a role in transmitting data to other devices.

[0059] "Speech recognition means" refers to the process or technology of converting speech into text, and is a mechanism that analyzes acoustic signals and converts them into textual information.

[0060] "Information analysis means" refers to techniques and methods for extracting, organizing, or understanding specific information from data.

[0061] An "information recording device" refers to a device or format for storing data for a long period of time, and it holds data in a way that allows it to be referenced as needed.

[0062] "Data registration means" refers to methods or devices for formally storing or recording acquired information within a system.

[0063] This invention comprises a system for efficiently utilizing telephone conversations for incident management. Specifically, it employs terminals, servers, and related software technologies.

[0064] Terminal role:

[0065] When a user answers a phone call, the terminal captures the conversation as an acoustic signal. The terminal is equipped with a microphone device and a communication module. This allows it to acquire the acoustic signal in real time and transmit it to a server. The communication module supports Wi-Fi and 4G / 5G networks.

[0066] Server role:

[0067] The server receives acoustic signals transmitted from the terminal and converts them into text using speech recognition technology. Specifically, it uses a commonly used speech recognition service as speech recognition software. The transcribed data is analyzed using natural language processing techniques to extract specific information from the conversation (e.g., the type of problem or user identification information). Based on this information, the server registers the data in an information recording device.

[0068] Specific example:

[0069] For example, if a user says "a login error occurred" during a phone call from a customer, the device collects the audio and sends it to the server. The server converts this audio to text and extracts the keyword "login error." This allows for quick registration of the incident.

[0070] Example of a prompt:

[0071] "Please begin registering login issues as incidents in customer support."

[0072] By combining the functions of the server and terminal in this way, users can efficiently incorporate telephone conversations into incident management, improving the efficiency and accuracy of their work.

[0073] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0074] Step 1:

[0075] The terminal captures the sound of a phone conversation as an acoustic signal. The input is audio data, which is converted into an electrical signal by the microphone. The output is a real-time acoustic signal. A communication module is used to prepare this acoustic signal for transmission to the server.

[0076] Step 2:

[0077] The server receives an acoustic signal from the terminal as input. It then performs a process of converting the acoustic signal into text data using speech recognition software. The output is text data in string format. This conversion visualizes the speech as concrete characters, which are then used for subsequent analysis.

[0078] Step 3:

[0079] The server takes text data as input and extracts specific identifying information using natural language processing techniques. Data analysis identifies keywords and phrases contained in the conversation and uses that information to uncover important details. The output is the analyzed identifying information. This clarifies the data necessary for incident management.

[0080] Step 4:

[0081] The server takes the extracted identification information as input and automatically registers it in the information recording device. The information is organized according to a predetermined format and stored in the database. The output becomes stored data that can be immediately accessed by the incident management system. This registration improves the speed and accuracy of management operations.

[0082] (Application Example 1)

[0083] 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."

[0084] When field workers respond to security incidents, it is crucial to quickly and accurately understand and respond to information received over the phone. However, manually transcribing audio information into text and extracting key points is time-consuming and labor-intensive, creating a significant burden on workers.

[0085] 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.

[0086] In this invention, the server includes acoustic conversion means for converting acoustic signals into text data, natural language processing means for extracting specific information from the text data, data input means for automatically inputting the extracted specific information into a recording device, and means for presenting information using a face-worn information device to reduce the burden on field workers. As a result, workers can check important information in real time and take appropriate action.

[0087] An "acoustic signal" is an electrical signal used to transmit real-time sound information, such as speech.

[0088] "Text data" refers to a format of information obtained by converting speech into text.

[0089] "Acoustic conversion means" refers to a device or software for processing acoustic signals as character data.

[0090] "Natural language processing means" refers to techniques or processes for extracting and analyzing specific information from text data.

[0091] A "recording device" is a device or system used to store data.

[0092] "Data input means" refers to a process or device for automatically inputting digital information into a recording device.

[0093] "Field workers" primarily refer to individuals engaged in responding to security incidents.

[0094] A "face-worn information device" is a device that a user wears on their head to display or present information.

[0095] "Information presentation means" refers to a process or device for displaying necessary information to a user.

[0096] "Specific information" refers to important data points extracted from audio data, which are elements necessary for incident response.

[0097] The embodiments for carrying out the invention are described below.

[0098] This system is designed to efficiently process audio information and extract specific details for incident management. Upon receiving an audio signal, the server converts it into text data in real time using an audio conversion mechanism. At this stage, the use of speech recognition software such as Google® Cloud Speech-to-Text or Amazon Transcribe is recommended.

[0099] Next, the server extracts specific information from the text data using natural language processing. This process utilizes natural language processing libraries such as spaCy and nltk to analyze important keywords and phrases. The analyzed results are automatically input into the recording device and organized as specific information. This process is automated by data entry mechanisms, which helps reduce recording errors.

[0100] Furthermore, necessary information is presented to field workers through face-worn information devices without placing an additional burden on them. For example, by displaying information on smart glasses, users can grasp the situation in real time and make quick decisions. This process is highly effective in improving on-site responsiveness.

[0101] As a concrete example, if a security guard at a shopping mall receives an emergency call from an unknown source, this system instantly transcribes the call into text, extracts key information, and displays it on the guard's smart glasses. This allows the guard to quickly understand the situation and take the most appropriate action.

[0102] An example of a prompt message that utilizes a generative AI model might be: "We want to develop a system that converts audio recording data into text and extracts and visualizes important incident information. Please tell us a specific scenario of how this system could be useful for security operations in a shopping mall."

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

[0104] Step 1:

[0105] The terminal acquires the telephone conversation as an acoustic signal. The input is voice data, and the output is an acoustic signal. The microphone built into the terminal captures the telephone conversation and records it as acoustic data through the communication module.

[0106] Step 2:

[0107] The server uses an acoustic conversion mechanism to convert the acoustic signal into text data. The input is an acoustic signal, and the output is text data. Speech recognition software (e.g., Google Cloud Speech-to-Text) is used to transcribe the audio content into text in real time.

[0108] Step 3:

[0109] The server extracts specific information from text data using natural language processing techniques. The input is text data, and the output is specific information. Natural language processing libraries (e.g., spaCy and nltk) are utilized to analyze and extract important keywords and phrases within the text.

[0110] Step 4:

[0111] The server automatically inputs specific information into a recording device through a data input mechanism. The input is specific information, and the output is organized data. By executing the automated input process, data is stored in an orderly manner in the recording device (such as a database).

[0112] Step 5:

[0113] The server displays specific information to the field worker's face-worn information device. The input is organized data, and the output is information display. Important specific information is displayed on smart glasses, allowing the worker to instantly access the information.

[0114] This allows users to transcribe and analyze conversational audio in near real-time, enabling them to quickly utilize necessary information on-site.

[0115] 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.

[0116] This invention relates to an automated voice information processing system equipped with a function to analyze the emotions of a user during a telephone conversation. The system's components consist of a terminal, a server, an emotion engine, and an incident management tool.

[0117] First, the terminal records the phone conversation with the user and acquires it as an acoustic signal. The acquired acoustic signal is sent to the server in real time, and the acoustic conversion mechanism within the server is activated.

[0118] The server converts speech to text using an acoustic conversion mechanism. Simultaneously, an emotion engine analyzes the speech data, recognizing and extracting emotional information from the user's tone of voice and the content of their words. This emotional information includes, for example, types of emotions such as "excitement," "disappointment," and "anger."

[0119] The server processes the converted text data using natural language processing techniques to extract specific information necessary for the incident from the conversation. This specific information, along with emotional information, is organized and registered in an electronic recording device via data input.

[0120] Furthermore, emotional information is also used to prioritize incidents. For example, if the emotion is "anger," it is judged to be highly urgent, and the order of responses in incident management is adjusted in real time.

[0121] As a concrete example, consider a scenario where a user files a complaint about a product defect while experiencing high levels of stress. The device records the conversation, and the server analyzes the content and emotions to automatically adjust the system so that this incident is handled quickly and with high priority.

[0122] Thus, the system of the present invention accurately recognizes user emotions by adding an emotion engine, improving the quality and efficiency of incident response. This system is expected to reduce the burden on operators while significantly improving customer satisfaction.

[0123] The following describes the processing flow.

[0124] Step 1:

[0125] The terminal records the user's phone conversation. The recorded audio signal is immediately prepared for transmission to the server by the communication module.

[0126] Step 2:

[0127] The server receives an acoustic signal from the terminal. Using an acoustic conversion device, this acoustic signal is converted into text data. At this point, the audio information is processed as text information.

[0128] Step 3:

[0129] The server activates the emotion engine and analyzes the user's emotions from the voice data. The emotion engine recognizes and extracts emotional information from the tone of voice and linguistic features.

[0130] Step 4:

[0131] The server passes the text data to a natural language processing system, which extracts specific information related to the incident. This information includes the user ID and the reported problem details.

[0132] Step 5:

[0133] The server organizes the specific information and emotional information it extracts and records it on an electronic recording device via a data input mechanism. Here, the information is formatted to be suitable for the incident management system.

[0134] Step 6:

[0135] The server prioritizes incidents based on emotional information. For example, if the emotion is "anger" or "anxiety," the server will set the incident to have a higher priority.

[0136] Step 7:

[0137] The user reviews the records in the incident management tool. They add details as needed and complete the incident processing. This review ensures the accuracy of the information.

[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 customer service, accurately understanding user emotions and handling incidents quickly and appropriately is essential. However, conventional systems do not automate emotion analysis from voice data or incident prioritization based on that information, resulting in a heavy burden on operators and insufficient improvement in customer satisfaction.

[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 signal conversion means for converting acoustic signals into strings, information processing means for extracting specific information, and emotion analysis means for analyzing the user's emotions. This makes it possible to analyze emotions from voice data in real time, extract specific information, and automatically set incident priorities based on that information.

[0143] An "acoustic signal" is an analog or digital signal that enables the transmission of a series of data, including sound.

[0144] "Signal conversion means" refers to a process or device that converts an acoustic signal into a string of characters.

[0145] "Information processing means" refers to a function or mechanism for extracting specific information required from text data.

[0146] "Emotion analysis means" refers to a function or process for identifying emotions contained in audio data.

[0147] "Data input means" refers to a function or device for registering extracted specific information and emotional information into an electronic record.

[0148] A "prioritization mechanism" is a function or mechanism for determining the priority of incident response based on emotional information.

[0149] An "electronic recording medium" is a physical or virtual platform for recording digital data.

[0150] This automated voice information processing system consists of a terminal for telephone conversations with users, a server for processing data, an emotion engine for analyzing emotions, and an incident management tool for organizing information. The invention is implemented in this system as follows:

[0151] First, the user engages in conversation through the device. The device records the conversation in real time and acquires it as an acoustic signal. This signal is immediately sent to the server. The server uses a signal conversion mechanism to convert the acoustic signal into text data. Speech recognition software can be utilized in this process.

[0152] Simultaneously, the server activates an emotion analysis system, analyzing the user's voice tone and word content from the audio data to extract emotional information. Specifically, it identifies types of emotions such as "excitement," "disappointment," and "anger." Emotion analysis software is used for this analysis.

[0153] Furthermore, the server uses information processing tools to extract specific information from text data and performs incident management based on that information. At this stage, the specific information and emotional information are registered on an electronic recording medium by data input tools. The emotional information is used to prioritize incidents; for example, if the emotion is determined to be "anger," the urgency of the incident is set to high.

[0154] As a concrete example, consider a situation where a user experiences high stress when reporting a product defect. The terminal records the conversation, and the server analyzes the audio, automatically adjusting the system to prioritize the incident. This system can reduce the burden on operators and improve customer satisfaction.

[0155] Example prompt to input into the generating AI model: "Please provide a description of how the system works, which analyzes customer emotions in real time during phone conversations and adjusts response priorities accordingly."

[0156] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0157] Step 1:

[0158] The device initiates a phone conversation with the user and records the audio in real time. The input is the user's voice, which is acquired as a digital audio signal. The output is the audio signal temporarily stored within the device.

[0159] Step 2:

[0160] The terminal transmits the acquired acoustic signal to the server. The input is an acoustic signal, which is transmitted using a high-speed data communication method. The output is the acoustic signal as it reaches the server.

[0161] Step 3:

[0162] The server receives an acoustic signal and converts it into text data using a signal conversion device. The input is an acoustic signal, which is converted into a string using speech recognition software. The output is the text data converted into a string.

[0163] Step 4:

[0164] The server uses emotion analysis tools to extract user emotion information from audio data. Input is either an acoustic signal or text data, which is analyzed using emotion analysis software. Output is emotion information, including feelings such as "excitement" and "anger."

[0165] Step 5:

[0166] The server uses information processing tools to extract specific information from text data. The input is text data, and natural language processing techniques are used to extract necessary information from the conversation. The output is specific information necessary for incident management.

[0167] Step 6:

[0168] The server registers emotional information and specific information on an electronic recording medium through a data input means. The input consists of emotional information and specific information, which are organized and stored in the recording device. The output is the organized electronic recording data.

[0169] Step 7:

[0170] The server determines incident priorities based on registered sentiment information. The input is sentiment information, and the urgency is set using a ranking mechanism. The output is incident management information with the assigned priorities.

[0171] Step 8:

[0172] The server notifies operators of incidents requiring attention, ensuring appropriate action is taken. Input is prioritized incident information, which generates response instructions. Output is notification information prompting action.

[0173] (Application Example 2)

[0174] 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".

[0175] In traditional customer support, operators had to directly assess customers' emotions and prioritize them based on urgency. This increased the burden on operators and potentially reduced the efficiency of customer service. Furthermore, if emotions could not be accurately assessed, there was a risk of delays in customer service and decreased customer satisfaction.

[0176] 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.

[0177] In this invention, the server includes a conversion device that receives an acoustic signal and converts the acoustic signal into text, a language processing device that extracts specific information from the text, a data transmission device that automatically inputs the extracted specific information into a recording medium, an emotion analysis device that analyzes the type of emotion of the user, and a management device that sets priorities based on the type of emotion. This enables rapid and accurate incident management based on emotion information.

[0178] An "acoustic signal" is a representation of sound as an electrical signal, and it can handle a variety of sounds, including human speech.

[0179] A "conversion device" is a device that converts acoustic signals into text information, using speech recognition technology to turn speech into text.

[0180] A "language processing device" is a device that uses natural language processing technology to extract specific information from textual data.

[0181] A "recording medium" is a medium for storing information that can retain electronic data for a long period of time.

[0182] A "data transmission device" is a device that has the function of automatically inputting extracted information into a recording medium.

[0183] An "emotion analysis device" is a device that identifies a user's emotions from voice and text information and analyzes their type.

[0184] A "management device" is a device that has the function of setting priorities and adjusting the order of responses based on the results of emotional analysis.

[0185] An "information processing system" is a collection of devices and programs that receive, convert, analyze, and ultimately record and manage input data.

[0186] To implement this invention, a terminal, a server, and various related software are mainly used. The terminal records telephone conversations with the user and transmits the resulting audio signal to the server. The server is equipped with various devices for processing the received audio signal.

[0187] 1. Acoustic Converter: The server uses an acoustic converter to convert acoustic signals into text information. This process utilizes a speech recognition engine (e.g., Google Cloud Speech-to-Text API).

[0188] 2. Language Processing Unit: The server uses a language processing unit to extract specific instructions and requests from text information. Natural language processing libraries (e.g., spaCy, NLTK) are used for this process.

[0189] 3. Sentiment Analysis Device: The server also includes a sentiment analysis device that analyzes the user's emotions based on voice tone and text. This process utilizes a sentiment analysis engine (e.g., IBM Watson® Tone Analyzer).

[0190] 4. Recording medium and management device: The analyzed specific information is stored on the recording medium. Furthermore, the server's management device sets priorities and performs incident management based on the obtained sentiment information.

[0191] As a concrete example, consider a case where a user calls customer support expressing strong dissatisfaction with a delayed delivery of a product. In this case, the terminal records the conversation, and the server analyzes the content and determines that the user is "angry," thus setting the importance level high. This allows for prompt instructions to be given to the appropriate department, leading to improved user satisfaction.

[0192] An example of a prompt message would be, "Analyze the emotions from this conversation, extract emotional information such as anger, excitement, and disappointment, and set priorities for response." This allows the server to automatically perform the appropriate actions, enabling efficient customer management.

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

[0194] Step 1:

[0195] The terminal records phone conversations with the user. It receives the user's voice signal as input and sends it to the server as digital data, specifically as an acoustic signal, as output.

[0196] Step 2:

[0197] The server inputs the received acoustic signal into an acoustic converter. The acoustic converter converts the acoustic signal into text. This process uses a speech recognition engine to process the audio data into text information. The output is the conversation content in text format.

[0198] Step 3:

[0199] The server inputs text information into the language processing unit. The language processing unit extracts specific information from the text. At this stage, natural language processing techniques are used to identify and extract specific information such as product names and problems to be solved. The output is specific, identified information.

[0200] Step 4:

[0201] The server inputs text information into the sentiment analysis device. The sentiment analysis device analyzes the user's emotional state based on the tone of voice and the content of the text. In this process, it uses an emotion analysis engine to classify and output emotions such as "anger" and "joy."

[0202] Step 5:

[0203] The server stores the obtained specific information and emotional information on a recording medium. During this process, a data input device is used to automatically organize and record the data. The output is the stored data for use in subsequent processing.

[0204] Step 6:

[0205] The server management system prioritizes incidents based on emotional information. If the emotion is "anger," it assigns a higher priority and determines the order of response. The management system uses this information to immediately issue instructions to the relevant departments. The output is the response order according to priority.

[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 type of 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 the present invention is implemented with multiple components, including a terminal and a server, to efficiently utilize the content of telephone conversations for incident management. First, when a user answers a telephone call, the terminal acquires the conversation as an acoustic signal. The terminal is equipped with a communication module for transmitting this acoustic signal and sends the data to the server in real time.

[0223] The server converts the received acoustic signal into text data using an acoustic conversion device. This text conversion process efficiently converts the voice input into text information, allowing it to proceed to the next processing stage.

[0224] The converted text data is analyzed by natural language processing tools on the server. Here, important specific information is extracted. This process identifies information highly necessary for incident management, such as user IDs and the nature of the problem, improving the accuracy of the records.

[0225] The extracted information is automatically registered in an electronic recording device using a data entry mechanism. Registration is performed according to a pre-configured format and stored in a format easily usable by the incident management system. This eliminates the need for manual data entry, significantly reducing processing time and preventing errors.

[0226] As a concrete example, consider a scenario where a user receives a customer call and handles a system login issue as an incident. The terminal collects the entire conversation, and the server immediately transcribes it into text, extracts important information, and registers it. This entire process allows the user to complete incident response quickly and efficiently.

[0227] The system of the present invention records specific information in real time, is effective in improving incident management operations, reduces the workload on users, and enhances the overall reliability of operations.

[0228] The following describes the processing flow.

[0229] Step 1:

[0230] The device acquires the user's phone conversation and records it in real time as an acoustic signal. The recorded acoustic signal is immediately prepared to be sent to the server.

[0231] Step 2:

[0232] The server receives an acoustic signal from the terminal. Using an acoustic conversion device, this acoustic signal is converted into text data. This allows the audio to be treated as text information.

[0233] Step 3:

[0234] The server passes the text data to a natural language processing system, which then extracts important specific information. Specifically, user IDs, problem descriptions, dates, and times are analyzed.

[0235] Step 4:

[0236] The server extracts specific information, organizes it, and registers it in an electronic recording device using data entry tools. The information is formatted in a way suitable for the incident management system and recorded without errors.

[0237] Step 5:

[0238] The user reviews the recorded information using the incident management tool. They enter additional information as needed and complete the incident processing. This review ensures the accuracy and reliability of the information.

[0239] (Example 1)

[0240] 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."

[0241] In modern communications, there is a need to efficiently convert telephone conversations into incident management data. Traditional methods require manual recording and analysis of conversations, which is time-consuming and carries the risk of human error. The challenge lies in accurately extracting and quickly recording critical specific information in real time.

[0242] 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.

[0243] In this invention, the server includes communication means for acquiring an acoustic signal and transmitting the acoustic signal to a data processing device, speech recognition means for converting the acoustic signal into text, and information analysis means for analyzing specific identification information from the text. This makes it possible to utilize the content of telephone conversations in real time, efficiently and accurately for incident management.

[0244] An "acoustic signal" is a data format that converts sound into an electrical signal and is used in communications and data processing.

[0245] A "data processing device" is a device used to analyze, transform, store, or transfer received data.

[0246] "Communication means" refers to technologies and modules for sending and receiving information, and plays a role in transmitting data to other devices.

[0247] "Speech recognition means" refers to the process or technology of converting speech into text, and is a mechanism that analyzes acoustic signals and converts them into textual information.

[0248] "Information analysis means" refers to techniques and methods for extracting, organizing, or understanding specific information from data.

[0249] An "information recording device" refers to a device or format for storing data for a long period of time, and it holds data in a way that allows it to be referenced as needed.

[0250] "Data registration means" refers to methods or devices for formally storing or recording acquired information within a system.

[0251] This invention comprises a system for efficiently utilizing telephone conversations for incident management. Specifically, it employs terminals, servers, and related software technologies.

[0252] Terminal role:

[0253] When a user answers a phone call, the terminal captures the conversation as an acoustic signal. The terminal is equipped with a microphone device and a communication module. This allows it to acquire the acoustic signal in real time and transmit it to a server. The communication module supports Wi-Fi and 4G / 5G networks.

[0254] Server role:

[0255] The server receives acoustic signals transmitted from the terminal and converts them into text using speech recognition technology. Specifically, it uses a commonly used speech recognition service as speech recognition software. The transcribed data is analyzed using natural language processing techniques to extract specific information from the conversation (e.g., the type of problem or user identification information). Based on this information, the server registers the data in an information recording device.

[0256] Specific example:

[0257] For example, if a user says "a login error occurred" during a phone call from a customer, the device collects the audio and sends it to the server. The server converts this audio to text and extracts the keyword "login error." This allows for quick registration of the incident.

[0258] Example of a prompt:

[0259] "Please begin registering login issues as incidents in customer support."

[0260] By combining the functions of the server and terminal in this way, users can efficiently incorporate telephone conversations into incident management, improving the efficiency and accuracy of their work.

[0261] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0262] Step 1:

[0263] The terminal captures the sound of a phone conversation as an acoustic signal. The input is audio data, which is converted into an electrical signal by the microphone. The output is a real-time acoustic signal. A communication module is used to prepare this acoustic signal for transmission to the server.

[0264] Step 2:

[0265] The server receives an acoustic signal from the terminal as input. It then performs a process of converting the acoustic signal into text data using speech recognition software. The output is text data in string format. This conversion visualizes the speech as concrete characters, which are then used for subsequent analysis.

[0266] Step 3:

[0267] The server takes text data as input and extracts specific identifying information using natural language processing techniques. Data analysis identifies keywords and phrases contained in the conversation and uses that information to uncover important details. The output is the analyzed identifying information. This clarifies the data necessary for incident management.

[0268] Step 4:

[0269] The server takes the extracted identification information as input and automatically registers it in the information recording device. The information is organized according to a predetermined format and stored in the database. The output becomes stored data that can be immediately accessed by the incident management system. This registration improves the speed and accuracy of management operations.

[0270] (Application Example 1)

[0271] 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."

[0272] When field workers respond to security incidents, it is crucial to quickly and accurately understand and respond to information received over the phone. However, manually transcribing audio information into text and extracting key points is time-consuming and labor-intensive, creating a significant burden on workers.

[0273] 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.

[0274] In this invention, the server includes acoustic conversion means for converting acoustic signals into text data, natural language processing means for extracting specific information from the text data, data input means for automatically inputting the extracted specific information into a recording device, and means for presenting information using a face-worn information device to reduce the burden on field workers. As a result, workers can check important information in real time and take appropriate action.

[0275] An "acoustic signal" is an electrical signal used to transmit real-time sound information, such as speech.

[0276] "Text data" refers to a format of information obtained by converting speech into text.

[0277] "Acoustic conversion means" refers to a device or software for processing acoustic signals as character data.

[0278] "Natural language processing means" refers to techniques or processes for extracting and analyzing specific information from text data.

[0279] A "recording device" is a device or system used to store data.

[0280] "Data input means" refers to a process or device for automatically inputting digital information into a recording device.

[0281] "Field workers" primarily refer to individuals engaged in responding to security incidents.

[0282] The "head-mounted information device" is a device that a user wears on the head to display or present information.

[0283] The "information presentation means" is a process or device for displaying necessary information to the user.

[0284] The "specific information" is an important data point extracted from voice data and refers to the elements necessary for incident response.

[0285] The embodiments for implementing the invention will be described below.

[0286] This system is designed to efficiently process voice information, extract specific information, and utilize it for incident management. When the server receives an acoustic signal, it converts it into character data in real time using acoustic conversion means. At this stage, it is recommended to use speech recognition software such as Google Cloud Speech-to-Text or Amazon Transcribe.

[0287] Next, the server extracts specific information from the character data using natural language processing. In this process, natural language processing libraries such as spaCy or nltk are utilized to analyze important keywords and phrases. The analyzed results are automatically input into the recording device and organized as specific information. This work is automated by the data input means and has the effect of reducing recording errors.

[0288] Furthermore, the necessary information is presented through the head-mounted information device without burdening the on-site workers. For example, by being displayed on smart glasses, the user can grasp the situation in real time and make quick decisions. This process is very effective for improving the response ability on site.

[0289] As a concrete example, if a security guard at a shopping mall receives an emergency call from an unknown source, this system instantly transcribes the call into text, extracts key information, and displays it on the guard's smart glasses. This allows the guard to quickly understand the situation and take the most appropriate action.

[0290] An example of a prompt message that utilizes a generative AI model might be: "We want to develop a system that converts audio recording data into text and extracts and visualizes important incident information. Please tell us a specific scenario of how this system could be useful for security operations in a shopping mall."

[0291] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0292] Step 1:

[0293] The terminal acquires the telephone conversation as an acoustic signal. The input is voice data, and the output is an acoustic signal. The microphone built into the terminal captures the telephone conversation and records it as acoustic data through the communication module.

[0294] Step 2:

[0295] The server uses an acoustic conversion mechanism to convert the acoustic signal into text data. The input is an acoustic signal, and the output is text data. Speech recognition software (e.g., Google Cloud Speech-to-Text) is used to transcribe the audio content into text in real time.

[0296] Step 3:

[0297] The server extracts specific information from text data using natural language processing techniques. The input is text data, and the output is specific information. Natural language processing libraries (e.g., spaCy and nltk) are used to analyze and extract important keywords and phrases within the text.

[0298] Step 4:

[0299] The server automatically inputs specific information into a recording device through a data input mechanism. The input is specific information, and the output is organized data. By executing the automated input process, data is stored in an orderly manner in the recording device (such as a database).

[0300] Step 5:

[0301] The server displays specific information to the field worker's face-worn information device. The input is organized data, and the output is information display. Important specific information is displayed on smart glasses, allowing the worker to instantly access the information.

[0302] This allows users to transcribe and analyze conversational audio in near real-time, enabling them to quickly utilize necessary information on-site.

[0303] 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.

[0304] This invention relates to an automated voice information processing system equipped with a function to analyze the emotions of a user during a telephone conversation. The system's components consist of a terminal, a server, an emotion engine, and an incident management tool.

[0305] First, the terminal records the phone conversation with the user and acquires it as an acoustic signal. The acquired acoustic signal is sent to the server in real time, and the acoustic conversion mechanism within the server is activated.

[0306] The server converts speech to text using an acoustic conversion mechanism. Simultaneously, an emotion engine analyzes the speech data, recognizing and extracting emotional information from the user's tone of voice and the content of their words. This emotional information includes, for example, types of emotions such as "excitement," "disappointment," and "anger."

[0307] The server processes the converted text data using natural language processing means and extracts specific information required for an incident from the conversation content. Along with this specific information, sentiment information is also organized and registered in an electronic recording device by the data input means.

[0308] Furthermore, the sentiment information is also used for prioritizing incidents. For example, when the sentiment is "anger", it is determined that the urgency is high, and the response order in incident management is adjusted in real time.

[0309] As a specific example, consider the case where a user files a claim while feeling high stress about a product defect. The terminal records the conversation, and the server analyzes the content and sentiment, so that this incident is automatically adjusted to be promptly and highly prioritized.

[0310] In this way, the system of the present invention accurately recognizes the user's sentiment by adding a sentiment engine, and improves the quality and efficiency of incident response. With this system, it is expected that the burden on the operator will be reduced and at the same time the customer satisfaction will be greatly improved.

[0311] The following describes the processing flow.

[0312] Step 1:

[0313] The terminal records the user's phone call. The recorded acoustic signal is prepared to be immediately transmitted to the server by the communication module.

[0314] Step 2:

[0315] The server receives the acoustic signal from the terminal. Using acoustic conversion means, this acoustic signal is converted into text data. Here, the voice information comes to be processed as character information.

[0316] Step 3:

[0317] The server activates the emotion engine and analyzes the user's emotions from the voice data. The emotion engine recognizes and extracts emotional information from the tone of voice and linguistic features.

[0318] Step 4:

[0319] The server passes the text data to a natural language processing system, which extracts specific information related to the incident. This information includes the user ID and the reported problem details.

[0320] Step 5:

[0321] The server organizes the specific information and emotional information it extracts and records it on an electronic recording device via a data input mechanism. Here, the information is formatted to be suitable for the incident management system.

[0322] Step 6:

[0323] The server prioritizes incidents based on emotional information. For example, if the emotion is "anger" or "anxiety," the server will set the incident to have a higher priority.

[0324] Step 7:

[0325] The user reviews the records in the incident management tool. They add details as needed and complete the incident processing. This review ensures the accuracy of the information.

[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 customer service, accurately understanding user emotions and handling incidents quickly and appropriately is essential. However, conventional systems do not automate emotion analysis from voice data or incident prioritization based on that information, resulting in a heavy burden on operators and insufficient improvement in customer satisfaction.

[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 signal conversion means for converting acoustic signals into strings, information processing means for extracting specific information, and emotion analysis means for analyzing the user's emotions. This makes it possible to analyze emotions from voice data in real time, extract specific information, and automatically set incident priorities based on that information.

[0331] An "acoustic signal" is an analog or digital signal that enables the transmission of a series of data, including sound.

[0332] "Signal conversion means" refers to a process or device that converts an acoustic signal into a string of characters.

[0333] "Information processing means" refers to a function or mechanism for extracting specific information required from text data.

[0334] "Emotion analysis means" refers to a function or process for identifying emotions contained in audio data.

[0335] "Data input means" refers to a function or device for registering extracted specific information and emotional information into an electronic record.

[0336] A "prioritization mechanism" is a function or mechanism for determining the priority of incident response based on emotional information.

[0337] An "electronic recording medium" is a physical or virtual platform for recording digital data.

[0338] This automated voice information processing system consists of a terminal for telephone conversations with users, a server for processing data, an emotion engine for analyzing emotions, and an incident management tool for organizing information. The invention is implemented in this system as follows:

[0339] First, the user engages in conversation through the device. The device records the conversation in real time and acquires it as an acoustic signal. This signal is immediately sent to the server. The server uses a signal conversion mechanism to convert the acoustic signal into text data. Speech recognition software can be utilized in this process.

[0340] Simultaneously, the server activates an emotion analysis system, analyzing the user's voice tone and word content from the audio data to extract emotional information. Specifically, it identifies types of emotions such as "excitement," "disappointment," and "anger." Emotion analysis software is used for this analysis.

[0341] Furthermore, the server uses information processing tools to extract specific information from text data and performs incident management based on that information. At this stage, the specific information and emotional information are registered on an electronic recording medium by data input tools. The emotional information is used to prioritize incidents; for example, if the emotion is determined to be "anger," the urgency of the incident is set to high.

[0342] As a concrete example, consider a situation where a user experiences high stress when reporting a product defect. The terminal records the conversation, and the server analyzes the audio, automatically adjusting the system to prioritize the incident. This system can reduce the burden on operators and improve customer satisfaction.

[0343] Example prompt to input into the generating AI model: "Please provide a description of how the system works, which analyzes customer emotions in real time during phone conversations and adjusts response priorities accordingly."

[0344] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0345] Step 1:

[0346] The device initiates a phone conversation with the user and records the audio in real time. The input is the user's voice, which is acquired as a digital audio signal. The output is the audio signal temporarily stored within the device.

[0347] Step 2:

[0348] The terminal transmits the acquired acoustic signal to the server. The input is an acoustic signal, which is transmitted using a high-speed data communication method. The output is the acoustic signal as it reaches the server.

[0349] Step 3:

[0350] The server receives an acoustic signal and converts it into text data using a signal conversion device. The input is an acoustic signal, which is converted into a string using speech recognition software. The output is the text data converted into a string.

[0351] Step 4:

[0352] The server uses emotion analysis tools to extract user emotion information from audio data. Input is either an acoustic signal or text data, which is analyzed using emotion analysis software. Output is emotion information, including feelings such as "excitement" and "anger."

[0353] Step 5:

[0354] The server uses information processing tools to extract specific information from text data. The input is text data, and natural language processing techniques are used to extract necessary information from the conversation. The output is specific information necessary for incident management.

[0355] Step 6:

[0356] The server registers emotional information and specific information on an electronic recording medium through a data input means. The input consists of emotional information and specific information, which are organized and stored in the recording device. The output is the organized electronic recording data.

[0357] Step 7:

[0358] The server determines incident priorities based on registered sentiment information. The input is sentiment information, and the urgency is set using a ranking mechanism. The output is incident management information with the assigned priorities.

[0359] Step 8:

[0360] The server notifies operators of incidents requiring attention, ensuring appropriate action is taken. Input is prioritized incident information, which generates response instructions. Output is notification information prompting action.

[0361] (Application Example 2)

[0362] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0363] In traditional customer support, operators had to directly assess customers' emotions and prioritize them based on urgency. This increased the burden on operators and potentially reduced the efficiency of customer service. Furthermore, if emotions could not be accurately assessed, there was a risk of delays in customer service and decreased customer satisfaction.

[0364] 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.

[0365] In this invention, the server includes a conversion device that receives an acoustic signal and converts the acoustic signal into text, a language processing device that extracts specific information from the text, a data transmission device that automatically inputs the extracted specific information into a recording medium, an emotion analysis device that analyzes the type of emotion of the user, and a management device that sets priorities based on the type of emotion. This enables rapid and accurate incident management based on emotion information.

[0366] An "acoustic signal" is a representation of sound as an electrical signal, and it can handle a variety of sounds, including human speech.

[0367] A "conversion device" is a device that converts acoustic signals into text information, using speech recognition technology to turn speech into text.

[0368] A "language processing device" is a device that uses natural language processing technology to extract specific information from textual data.

[0369] A "recording medium" is a medium for storing information that can retain electronic data for a long period of time.

[0370] A "data transmission device" is a device that has the function of automatically inputting extracted information into a recording medium.

[0371] An "emotion analysis device" is a device that identifies a user's emotions from voice and text information and analyzes their type.

[0372] A "management device" is a device that has the function of setting priorities and adjusting the order of responses based on the results of emotional analysis.

[0373] An "information processing system" is a collection of devices and programs that receive, convert, analyze, and ultimately record and manage input data.

[0374] To implement this invention, a terminal, a server, and various related software are mainly used. The terminal records telephone conversations with the user and transmits the resulting audio signal to the server. The server is equipped with various devices for processing the received audio signal.

[0375] 1. Acoustic Converter: The server uses an acoustic converter to convert acoustic signals into text information. This process utilizes a speech recognition engine (e.g., Google Cloud Speech-to-Text API).

[0376] 2. Language Processing Unit: The server uses a language processing unit to extract specific instructions and requests from text information. Natural language processing libraries (e.g., spaCy, NLTK) are used for this process.

[0377] 3. Sentiment Analysis Device: The server also includes a sentiment analysis device that analyzes the user's emotions based on voice tone and text. This process utilizes a sentiment analysis engine (e.g., IBM Watson Tone Analyzer).

[0378] 4. Recording medium and management device: The analyzed specific information is stored on the recording medium. Furthermore, the server's management device sets priorities and performs incident management based on the obtained sentiment information.

[0379] As a concrete example, consider a case where a user calls customer support expressing strong dissatisfaction with a delayed delivery of a product. In this case, the terminal records the conversation, and the server analyzes the content and determines that the user is "angry," thus setting the importance level high. This allows for prompt instructions to be given to the appropriate department, leading to improved user satisfaction.

[0380] An example of a prompt message would be, "Analyze the emotions from this conversation, extract emotional information such as anger, excitement, and disappointment, and prioritize the appropriate response." This allows the server to automatically perform the appropriate actions, enabling efficient customer management.

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

[0382] Step 1:

[0383] The terminal records phone conversations with the user. It receives the user's voice signal as input and sends it to the server as digital data, specifically as an acoustic signal, as output.

[0384] Step 2:

[0385] The server inputs the received acoustic signal into an acoustic converter. The acoustic converter converts the acoustic signal into text. This process uses a speech recognition engine to process the audio data into text information. The output is the conversation content in text format.

[0386] Step 3:

[0387] The server inputs text information into the language processing unit. The language processing unit extracts specific information from the text. At this stage, natural language processing techniques are used to identify and extract specific information such as product names and problems to be solved. The output is specific, identified information.

[0388] Step 4:

[0389] The server inputs text information into the sentiment analysis device. The sentiment analysis device analyzes the user's emotional state based on the tone of voice and the content of the text. In this process, it uses an emotion analysis engine to classify and output emotions such as "anger" and "joy."

[0390] Step 5:

[0391] The server stores the obtained specific information and emotional information on a recording medium. During this process, a data input device is used to automatically organize and record the data. The output is the stored data for use in subsequent processing.

[0392] Step 6:

[0393] The server management system prioritizes incidents based on emotional information. If the emotion is "anger," it assigns a higher priority and determines the order of response. The management system uses this information to immediately issue instructions to the relevant departments. The output is the response order according to priority.

[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 the present invention is implemented with multiple components, including a terminal and a server, to efficiently utilize the content of telephone conversations for incident management. First, when a user answers a telephone call, the terminal acquires the conversation as an acoustic signal. The terminal is equipped with a communication module for transmitting this acoustic signal and sends the data to the server in real time.

[0411] The server converts the received acoustic signal into text data using an acoustic conversion device. This text conversion process efficiently converts the voice input into text information, allowing it to proceed to the next processing stage.

[0412] The converted text data is analyzed by natural language processing tools on the server. Here, important specific information is extracted. This process identifies information highly necessary for incident management, such as user IDs and the nature of the problem, improving the accuracy of the records.

[0413] The extracted information is automatically registered in an electronic recording device using a data entry mechanism. Registration is performed according to a pre-configured format and stored in a format easily usable by the incident management system. This eliminates the need for manual data entry, significantly reducing processing time and preventing errors.

[0414] As a concrete example, consider a scenario where a user receives a customer call and handles a system login issue as an incident. The terminal collects the entire conversation, and the server immediately transcribes it into text, extracts important information, and registers it. This entire process allows the user to complete incident response quickly and efficiently.

[0415] The system of the present invention records specific information in real time, is effective in improving incident management operations, reduces the workload on users, and enhances the overall reliability of operations.

[0416] The following describes the processing flow.

[0417] Step 1:

[0418] The device acquires the user's phone conversation and records it in real time as an acoustic signal. The recorded acoustic signal is immediately prepared to be sent to the server.

[0419] Step 2:

[0420] The server receives an acoustic signal from the terminal. Using an acoustic conversion device, this acoustic signal is converted into text data. This allows the audio to be treated as text information.

[0421] Step 3:

[0422] The server passes the text data to a natural language processing system, which then extracts important specific information. Specifically, user IDs, problem descriptions, dates, and times are analyzed.

[0423] Step 4:

[0424] The server extracts specific information, organizes it, and registers it in an electronic recording device using data entry tools. The information is formatted in a way suitable for the incident management system and recorded without errors.

[0425] Step 5:

[0426] The user reviews the recorded information using the incident management tool. They enter additional information as needed and complete the incident processing. This review ensures the accuracy and reliability of the information.

[0427] (Example 1)

[0428] 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."

[0429] In modern communications, there is a need to efficiently convert telephone conversations into incident management data. Traditional methods require manual recording and analysis of conversations, which is time-consuming and carries the risk of human error. The challenge lies in accurately extracting and quickly recording critical specific information in real time.

[0430] 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.

[0431] In this invention, the server includes communication means for acquiring an acoustic signal and transmitting the acoustic signal to a data processing device, speech recognition means for converting the acoustic signal into text, and information analysis means for analyzing specific identification information from the text. This makes it possible to utilize the content of telephone conversations in real time, efficiently and accurately for incident management.

[0432] An "acoustic signal" is a data format that converts sound into an electrical signal and is used in communications and data processing.

[0433] A "data processing device" is a device used to analyze, transform, store, or transfer received data.

[0434] "Communication means" refers to technologies and modules for sending and receiving information, and plays a role in transmitting data to other devices.

[0435] "Speech recognition means" refers to the process or technology of converting speech into text, and is a mechanism that analyzes acoustic signals and converts them into textual information.

[0436] "Information analysis means" refers to techniques and methods for extracting, organizing, or understanding specific information from data.

[0437] An "information recording device" refers to a device or format for storing data for a long period of time, and it holds data in a way that allows it to be referenced as needed.

[0438] "Data registration means" refers to methods or devices for formally storing or recording acquired information within a system.

[0439] This invention comprises a system for efficiently utilizing telephone conversations for incident management. Specifically, it employs terminals, servers, and related software technologies.

[0440] Terminal role:

[0441] When a user answers a phone call, the terminal captures the conversation as an acoustic signal. The terminal is equipped with a microphone device and a communication module. This allows it to acquire the acoustic signal in real time and transmit it to a server. The communication module supports Wi-Fi and 4G / 5G networks.

[0442] Server role:

[0443] The server receives acoustic signals transmitted from the terminal and converts them into text using speech recognition technology. Specifically, it uses a commonly used speech recognition service as speech recognition software. The transcribed data is analyzed using natural language processing techniques to extract specific information from the conversation (e.g., the type of problem or user identification information). Based on this information, the server registers the data in an information recording device.

[0444] Specific example:

[0445] For example, if a user says "a login error occurred" during a phone call from a customer, the device collects the audio and sends it to the server. The server converts this audio to text and extracts the keyword "login error." This allows for quick registration of the incident.

[0446] Example of a prompt:

[0447] "Please begin registering login issues as incidents in customer support."

[0448] By combining the functions of the server and terminal in this way, users can efficiently incorporate telephone conversations into incident management, improving the efficiency and accuracy of their work.

[0449] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0450] Step 1:

[0451] The terminal captures the sound of a phone conversation as an acoustic signal. The input is audio data, which is converted into an electrical signal by the microphone. The output is a real-time acoustic signal. A communication module is used to prepare this acoustic signal for transmission to the server.

[0452] Step 2:

[0453] The server receives an acoustic signal from the terminal as input. It then performs a process of converting the acoustic signal into text data using speech recognition software. The output is text data in string format. This conversion visualizes the speech as concrete characters, which are then used for subsequent analysis.

[0454] Step 3:

[0455] The server takes text data as input and extracts specific identifying information using natural language processing techniques. Data analysis identifies keywords and phrases contained in the conversation and uses that information to uncover important details. The output is the analyzed identifying information. This clarifies the data necessary for incident management.

[0456] Step 4:

[0457] The server takes the extracted identification information as input and automatically registers it in the information recording device. The information is organized according to a predetermined format and stored in the database. The output becomes stored data that can be immediately accessed by the incident management system. This registration improves the speed and accuracy of management operations.

[0458] (Application Example 1)

[0459] 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."

[0460] When field workers respond to security incidents, it is crucial to quickly and accurately understand and respond to information received over the phone. However, manually transcribing audio information into text and extracting key points is time-consuming and labor-intensive, creating a significant burden on workers.

[0461] 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.

[0462] In this invention, the server includes acoustic conversion means for converting acoustic signals into text data, natural language processing means for extracting specific information from the text data, data input means for automatically inputting the extracted specific information into a recording device, and means for presenting information using a face-worn information device to reduce the burden on field workers. As a result, workers can check important information in real time and take appropriate action.

[0463] An "acoustic signal" is an electrical signal used to transmit real-time sound information, such as speech.

[0464] "Text data" refers to a format of information obtained by converting speech into text.

[0465] "Acoustic conversion means" refers to a device or software for processing acoustic signals as character data.

[0466] "Natural language processing means" refers to techniques or processes for extracting and analyzing specific information from text data.

[0467] A "recording device" is a device or system used to store data.

[0468] "Data input means" refers to a process or device for automatically inputting digital information into a recording device.

[0469] "Field workers" primarily refer to individuals engaged in responding to security incidents.

[0470] A "face-worn information device" is a device that a user wears on their head to display or present information.

[0471] "Information presentation means" refers to a process or device for displaying necessary information to a user.

[0472] "Specific information" refers to important data points extracted from audio data, which are elements necessary for incident response.

[0473] The embodiments for carrying out the invention are described below.

[0474] This system is designed to efficiently process audio information, extract specific details, and use them for incident management. Upon receiving an audio signal, the server converts it into text data in real time using an audio conversion mechanism. At this stage, the use of speech recognition software such as Google Cloud Speech-to-Text or Amazon Transcribe is recommended.

[0475] Next, the server extracts specific information from the text data using natural language processing. This process utilizes natural language processing libraries such as spaCy and nltk to analyze important keywords and phrases. The analyzed results are automatically input into the recording device and organized as specific information. This process is automated by data entry mechanisms, which helps reduce recording errors.

[0476] Furthermore, necessary information is presented to field workers through face-worn information devices without placing an additional burden on them. For example, by displaying information on smart glasses, users can grasp the situation in real time and make quick decisions. This process is highly effective in improving on-site responsiveness.

[0477] As a concrete example, if a security guard at a shopping mall receives an emergency call from an unknown source, this system instantly transcribes the call into text, extracts key information, and displays it on the guard's smart glasses. This allows the guard to quickly understand the situation and take the most appropriate action.

[0478] An example of a prompt message that utilizes a generative AI model might be: "We want to develop a system that converts audio recording data into text and extracts and visualizes important incident information. Please tell us a specific scenario of how this system could be useful for security operations in a shopping mall."

[0479] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0480] Step 1:

[0481] The terminal acquires the telephone conversation as an acoustic signal. The input is voice data, and the output is an acoustic signal. The microphone built into the terminal captures the telephone conversation and records it as acoustic data through the communication module.

[0482] Step 2:

[0483] The server uses an acoustic conversion mechanism to convert the acoustic signal into text data. The input is an acoustic signal, and the output is text data. Speech recognition software (e.g., Google Cloud Speech-to-Text) is used to transcribe the audio content into text in real time.

[0484] Step 3:

[0485] The server extracts specific information from text data using natural language processing techniques. The input is text data, and the output is specific information. Natural language processing libraries (e.g., spaCy and nltk) are used to analyze and extract important keywords and phrases within the text.

[0486] Step 4:

[0487] The server automatically inputs specific information into a recording device through a data input mechanism. The input is specific information, and the output is organized data. By executing the automated input process, data is stored in an orderly manner in the recording device (such as a database).

[0488] Step 5:

[0489] The server displays specific information to the field worker's face-worn information device. The input is organized data, and the output is information display. Important specific information is displayed on smart glasses, allowing the worker to instantly access the information.

[0490] This allows users to transcribe and analyze conversational audio in near real-time, enabling them to quickly utilize necessary information on-site.

[0491] 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.

[0492] This invention relates to an automated voice information processing system equipped with a function to analyze the emotions of a user during a telephone conversation. The system's components consist of a terminal, a server, an emotion engine, and an incident management tool.

[0493] First, the terminal records the phone conversation with the user and acquires it as an acoustic signal. The acquired acoustic signal is sent to the server in real time, and the acoustic conversion mechanism within the server is activated.

[0494] The server converts speech to text using an acoustic conversion mechanism. Simultaneously, an emotion engine analyzes the speech data, recognizing and extracting emotional information from the user's tone of voice and the content of their words. This emotional information includes, for example, types of emotions such as "excitement," "disappointment," and "anger."

[0495] The server processes the converted text data using natural language processing techniques to extract specific information necessary for the incident from the conversation. This specific information, along with emotional information, is organized and registered in an electronic recording device via data input.

[0496] Furthermore, emotional information is also used to prioritize incidents. For example, if the emotion is "anger," it is judged to be highly urgent, and the order of responses in incident management is adjusted in real time.

[0497] As a concrete example, consider a scenario where a user files a complaint about a product defect while experiencing high levels of stress. The device records the conversation, and the server analyzes the content and emotions to automatically adjust the system so that this incident is handled quickly and with high priority.

[0498] Thus, the system of the present invention accurately recognizes user emotions by adding an emotion engine, improving the quality and efficiency of incident response. This system is expected to reduce the burden on operators while significantly improving customer satisfaction.

[0499] The following describes the processing flow.

[0500] Step 1:

[0501] The terminal records the user's phone conversation. The recorded audio signal is immediately prepared for transmission to the server by the communication module.

[0502] Step 2:

[0503] The server receives an acoustic signal from the terminal. Using an acoustic conversion device, this acoustic signal is converted into text data. At this point, the audio information is processed as text information.

[0504] Step 3:

[0505] The server activates the emotion engine and analyzes the user's emotions from the voice data. The emotion engine recognizes and extracts emotional information from the tone of voice and linguistic features.

[0506] Step 4:

[0507] The server passes the text data to a natural language processing system, which extracts specific information related to the incident. This information includes the user ID and the reported problem details.

[0508] Step 5:

[0509] The server organizes the specific information and emotional information it extracts and records it on an electronic recording device via a data input mechanism. Here, the information is formatted to be suitable for the incident management system.

[0510] Step 6:

[0511] The server prioritizes incidents based on emotional information. For example, if the emotion is "anger" or "anxiety," the server will set the incident to have a higher priority.

[0512] Step 7:

[0513] The user reviews the records in the incident management tool. They add details as needed and complete the incident processing. This review ensures the accuracy of the information.

[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 customer service, accurately understanding user emotions and handling incidents quickly and appropriately is essential. However, conventional systems do not automate emotion analysis from voice data or incident prioritization based on that information, resulting in a heavy burden on operators and insufficient improvement in customer satisfaction.

[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 signal conversion means for converting acoustic signals into strings, information processing means for extracting specific information, and emotion analysis means for analyzing the user's emotions. This makes it possible to analyze emotions from voice data in real time, extract specific information, and automatically set incident priorities based on that information.

[0519] An "acoustic signal" is an analog or digital signal that enables the transmission of a series of data, including sound.

[0520] "Signal conversion means" refers to a process or device that converts an acoustic signal into a string of characters.

[0521] "Information processing means" refers to a function or mechanism for extracting specific information required from text data.

[0522] "Emotion analysis means" refers to a function or process for identifying emotions contained in audio data.

[0523] "Data input means" refers to a function or device for registering extracted specific information and emotional information into an electronic record.

[0524] A "prioritization mechanism" is a function or mechanism for determining the priority of incident response based on emotional information.

[0525] An "electronic recording medium" is a physical or virtual platform for recording digital data.

[0526] This automated voice information processing system consists of a terminal for telephone conversations with users, a server for processing data, an emotion engine for analyzing emotions, and an incident management tool for organizing information. The invention is implemented in this system as follows:

[0527] First, the user engages in conversation through the device. The device records the conversation in real time and acquires it as an acoustic signal. This signal is immediately sent to the server. The server uses a signal conversion mechanism to convert the acoustic signal into text data. Speech recognition software can be utilized in this process.

[0528] Simultaneously, the server activates an emotion analysis system, analyzing the user's voice tone and word content from the audio data to extract emotional information. Specifically, it identifies types of emotions such as "excitement," "disappointment," and "anger." Emotion analysis software is used for this analysis.

[0529] Furthermore, the server uses information processing tools to extract specific information from text data and performs incident management based on that information. At this stage, the specific information and emotional information are registered on an electronic recording medium by data input tools. The emotional information is used to prioritize incidents; for example, if the emotion is determined to be "anger," the urgency of the incident is set to high.

[0530] As a concrete example, consider a situation where a user experiences high stress when reporting a product defect. The terminal records the conversation, and the server analyzes the audio, automatically adjusting the system to prioritize the incident. This system can reduce the burden on operators and improve customer satisfaction.

[0531] Example prompt to input into the generating AI model: "Please provide a description of how the system works, which analyzes customer emotions in real time during phone conversations and adjusts response priorities accordingly."

[0532] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0533] Step 1:

[0534] The device initiates a phone conversation with the user and records the audio in real time. The input is the user's voice, which is acquired as a digital audio signal. The output is the audio signal temporarily stored within the device.

[0535] Step 2:

[0536] The terminal transmits the acquired acoustic signal to the server. The input is an acoustic signal, which is transmitted using a high-speed data communication method. The output is the acoustic signal as it reaches the server.

[0537] Step 3:

[0538] The server receives an acoustic signal and converts it into text data using a signal conversion device. The input is an acoustic signal, which is converted into a string using speech recognition software. The output is the text data converted into a string.

[0539] Step 4:

[0540] The server uses emotion analysis tools to extract user emotion information from audio data. Input is either an acoustic signal or text data, which is analyzed using emotion analysis software. Output is emotion information, including feelings such as "excitement" and "anger."

[0541] Step 5:

[0542] The server uses information processing tools to extract specific information from text data. The input is text data, and natural language processing techniques are used to extract necessary information from the conversation. The output is specific information necessary for incident management.

[0543] Step 6:

[0544] The server registers emotional information and specific information on an electronic recording medium through a data input means. The input consists of emotional information and specific information, which are organized and stored in the recording device. The output is the organized electronic recording data.

[0545] Step 7:

[0546] The server determines incident priorities based on registered sentiment information. The input is sentiment information, and the urgency is set using a ranking mechanism. The output is incident management information with the assigned priorities.

[0547] Step 8:

[0548] The server notifies operators of incidents requiring attention, ensuring appropriate action is taken. Input is prioritized incident information, which generates response instructions. Output is notification information prompting action.

[0549] (Application Example 2)

[0550] 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."

[0551] In traditional customer support, operators had to directly assess customers' emotions and prioritize them based on urgency. This increased the burden on operators and potentially reduced the efficiency of customer service. Furthermore, if emotions could not be accurately assessed, there was a risk of delays in customer service and decreased customer satisfaction.

[0552] 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.

[0553] In this invention, the server includes a conversion device that receives an acoustic signal and converts the acoustic signal into text, a language processing device that extracts specific information from the text, a data transmission device that automatically inputs the extracted specific information into a recording medium, an emotion analysis device that analyzes the type of emotion of the user, and a management device that sets priorities based on the type of emotion. This enables rapid and accurate incident management based on emotion information.

[0554] An "acoustic signal" is a representation of sound as an electrical signal, and it can handle a variety of sounds, including human speech.

[0555] A "conversion device" is a device that converts acoustic signals into text information, using speech recognition technology to turn speech into text.

[0556] A "language processing device" is a device that uses natural language processing technology to extract specific information from textual data.

[0557] A "recording medium" is a medium for storing information that can retain electronic data for a long period of time.

[0558] A "data transmission device" is a device that has the function of automatically inputting extracted information into a recording medium.

[0559] An "emotion analysis device" is a device that identifies a user's emotions from voice and text information and analyzes their type.

[0560] A "management device" is a device that has the function of setting priorities and adjusting the order of responses based on the results of emotional analysis.

[0561] An "information processing system" is a collection of devices and programs that receive, convert, analyze, and ultimately record and manage input data.

[0562] To implement this invention, a terminal, a server, and various related software are mainly used. The terminal records telephone conversations with the user and transmits the resulting audio signal to the server. The server is equipped with various devices for processing the received audio signal.

[0563] 1. Acoustic Converter: The server uses an acoustic converter to convert acoustic signals into text information. This process utilizes a speech recognition engine (e.g., Google Cloud Speech-to-Text API).

[0564] 2. Language Processing Unit: The server uses a language processing unit to extract specific instructions and requests from text information. Natural language processing libraries (e.g., spaCy, NLTK) are used for this process.

[0565] 3. Sentiment Analysis Device: The server also includes a sentiment analysis device that analyzes the user's emotions based on voice tone and text. This process utilizes a sentiment analysis engine (e.g., IBM Watson Tone Analyzer).

[0566] 4. Recording medium and management device: The analyzed specific information is stored on the recording medium. Furthermore, the server's management device sets priorities and performs incident management based on the obtained sentiment information.

[0567] As a concrete example, consider a case where a user calls customer support expressing strong dissatisfaction with a delayed delivery of a product. In this case, the terminal records the conversation, and the server analyzes the content and determines that the user is "angry," thus setting the importance level high. This allows for prompt instructions to be given to the appropriate department, leading to improved user satisfaction.

[0568] An example of a prompt message would be, "Analyze the emotions from this conversation, extract emotional information such as anger, excitement, and disappointment, and prioritize the appropriate response." This allows the server to automatically perform the appropriate actions, enabling efficient customer management.

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

[0570] Step 1:

[0571] The terminal records phone conversations with the user. It receives the user's voice signal as input and sends it to the server as digital data, specifically as an acoustic signal, as output.

[0572] Step 2:

[0573] The server inputs the received acoustic signal into an acoustic converter. The acoustic converter converts the acoustic signal into text. This process uses a speech recognition engine to process the audio data into text information. The output is the conversation content in text format.

[0574] Step 3:

[0575] The server inputs text information into the language processing unit. The language processing unit extracts specific information from the text. At this stage, natural language processing techniques are used to identify and extract specific information such as product names and problems to be solved. The output is specific, identified information.

[0576] Step 4:

[0577] The server inputs text information into the sentiment analysis device. The sentiment analysis device analyzes the user's emotional state based on the tone of voice and the content of the text. In this process, it uses an emotion analysis engine to classify and output emotions such as "anger" and "joy."

[0578] Step 5:

[0579] The server stores the obtained specific information and emotional information on a recording medium. During this process, a data input device is used to automatically organize and record the data. The output is the stored data for use in subsequent processing.

[0580] Step 6:

[0581] The server management system prioritizes incidents based on emotional information. If the emotion is "anger," it assigns a higher priority and determines the order of response. The management system uses this information to immediately issue instructions to the relevant departments. The output is the response order according to priority.

[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 the present invention is implemented with multiple components, including a terminal and a server, to efficiently utilize the content of telephone conversations for incident management. First, when a user answers a telephone call, the terminal acquires the conversation as an acoustic signal. The terminal is equipped with a communication module for transmitting this acoustic signal and sends the data to the server in real time.

[0600] The server converts the received acoustic signal into text data using an acoustic conversion device. This text conversion process efficiently converts the voice input into text information, allowing it to proceed to the next processing stage.

[0601] The converted text data is analyzed by natural language processing tools on the server. Here, important specific information is extracted. This process identifies information highly necessary for incident management, such as user IDs and the nature of the problem, improving the accuracy of the records.

[0602] The extracted information is automatically registered in an electronic recording device using a data entry mechanism. Registration is performed according to a pre-configured format and stored in a format easily usable by the incident management system. This eliminates the need for manual data entry, significantly reducing processing time and preventing errors.

[0603] As a concrete example, consider a scenario where a user receives a customer call and handles a system login issue as an incident. The terminal collects the entire conversation, and the server immediately transcribes it into text, extracts important information, and registers it. This entire process allows the user to complete incident response quickly and efficiently.

[0604] The system of the present invention records specific information in real time, is effective in improving incident management operations, reduces the workload on users, and enhances the overall reliability of operations.

[0605] The following describes the processing flow.

[0606] Step 1:

[0607] The device acquires the user's phone conversation and records it in real time as an acoustic signal. The recorded acoustic signal is immediately prepared to be sent to the server.

[0608] Step 2:

[0609] The server receives an acoustic signal from the terminal. Using an acoustic conversion device, this acoustic signal is converted into text data. This allows the audio to be treated as text information.

[0610] Step 3:

[0611] The server passes the text data to a natural language processing system, which then extracts important specific information. Specifically, user IDs, problem descriptions, dates, and times are analyzed.

[0612] Step 4:

[0613] The server extracts specific information, organizes it, and registers it in an electronic recording device using data entry tools. The information is formatted in a way suitable for the incident management system and recorded without errors.

[0614] Step 5:

[0615] The user reviews the recorded information using the incident management tool. They enter additional information as needed and complete the incident processing. This review ensures the accuracy and reliability of the information.

[0616] (Example 1)

[0617] 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".

[0618] In modern communications, there is a need to efficiently convert telephone conversations into incident management data. Traditional methods require manual recording and analysis of conversations, which is time-consuming and carries the risk of human error. The challenge lies in accurately extracting and quickly recording critical specific information in real time.

[0619] 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.

[0620] In this invention, the server includes communication means for acquiring an acoustic signal and transmitting the acoustic signal to a data processing device, speech recognition means for converting the acoustic signal into text, and information analysis means for analyzing specific identification information from the text. This makes it possible to utilize the content of telephone conversations in real time, efficiently and accurately for incident management.

[0621] An "acoustic signal" is a data format that converts sound into an electrical signal and is used in communications and data processing.

[0622] A "data processing device" is a device used to analyze, transform, store, or transfer received data.

[0623] "Communication means" refers to technologies and modules for sending and receiving information, and plays a role in transmitting data to other devices.

[0624] "Speech recognition means" refers to the process or technology of converting speech into text, and is a mechanism that analyzes acoustic signals and converts them into textual information.

[0625] "Information analysis means" refers to techniques and methods for extracting, organizing, or understanding specific information from data.

[0626] An "information recording device" refers to a device or format for storing data for a long period of time, and it holds data in a way that allows it to be referenced as needed.

[0627] "Data registration means" refers to methods or devices for formally storing or recording acquired information within a system.

[0628] This invention comprises a system for efficiently utilizing telephone conversations for incident management. Specifically, it employs terminals, servers, and related software technologies.

[0629] Terminal role:

[0630] When a user answers a phone call, the terminal captures the conversation as an acoustic signal. The terminal is equipped with a microphone device and a communication module. This allows it to acquire the acoustic signal in real time and transmit it to a server. The communication module supports Wi-Fi and 4G / 5G networks.

[0631] Server role:

[0632] The server receives acoustic signals transmitted from the terminal and converts them into text using speech recognition technology. Specifically, it uses a commonly used speech recognition service as speech recognition software. The transcribed data is analyzed using natural language processing techniques to extract specific information from the conversation (e.g., the type of problem or user identification information). Based on this information, the server registers the data in an information recording device.

[0633] Specific example:

[0634] For example, if a user says "a login error occurred" during a phone call from a customer, the device collects the audio and sends it to the server. The server converts this audio to text and extracts the keyword "login error." This allows for quick registration of the incident.

[0635] Example of a prompt:

[0636] "Please begin registering login issues as incidents in customer support."

[0637] By combining the functions of the server and terminal in this way, users can efficiently incorporate telephone conversations into incident management, improving the efficiency and accuracy of their work.

[0638] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0639] Step 1:

[0640] The terminal captures the sound of a phone conversation as an acoustic signal. The input is audio data, which is converted into an electrical signal by the microphone. The output is a real-time acoustic signal. A communication module is used to prepare this acoustic signal for transmission to the server.

[0641] Step 2:

[0642] The server receives an acoustic signal from the terminal as input. It then performs a process of converting the acoustic signal into text data using speech recognition software. The output is text data in string format. This conversion visualizes the speech as concrete characters, which are then used for subsequent analysis.

[0643] Step 3:

[0644] The server takes text data as input and extracts specific identifying information using natural language processing techniques. Data analysis identifies keywords and phrases contained in the conversation and uses that information to uncover important details. The output is the analyzed identifying information. This clarifies the data necessary for incident management.

[0645] Step 4:

[0646] The server takes the extracted identification information as input and automatically registers it in the information recording device. The information is organized according to a predetermined format and stored in the database. The output becomes stored data that can be immediately accessed by the incident management system. This registration improves the speed and accuracy of management operations.

[0647] (Application Example 1)

[0648] 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".

[0649] When field workers respond to security incidents, it is crucial to quickly and accurately understand and respond to information received over the phone. However, manually transcribing audio information into text and extracting key points is time-consuming and labor-intensive, creating a significant burden on workers.

[0650] 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.

[0651] In this invention, the server includes acoustic conversion means for converting acoustic signals into text data, natural language processing means for extracting specific information from the text data, data input means for automatically inputting the extracted specific information into a recording device, and means for presenting information using a face-worn information device to reduce the burden on field workers. As a result, workers can check important information in real time and take appropriate action.

[0652] An "acoustic signal" is an electrical signal used to transmit real-time sound information, such as speech.

[0653] "Text data" refers to a format of information obtained by converting speech into text.

[0654] "Acoustic conversion means" refers to a device or software for processing acoustic signals as character data.

[0655] "Natural language processing means" refers to techniques or processes for extracting and analyzing specific information from text data.

[0656] A "recording device" is a device or system used to store data.

[0657] "Data input means" refers to a process or device for automatically inputting digital information into a recording device.

[0658] "Field workers" primarily refer to individuals engaged in responding to security incidents.

[0659] A "face-worn information device" is a device that a user wears on their head to display or present information.

[0660] "Information presentation means" refers to a process or device for displaying necessary information to a user.

[0661] "Specific information" refers to important data points extracted from audio data, which are elements necessary for incident response.

[0662] The embodiments for carrying out the invention are described below.

[0663] This system is designed to efficiently process audio information, extract specific details, and use them for incident management. Upon receiving an audio signal, the server converts it into text data in real time using an audio conversion mechanism. At this stage, the use of speech recognition software such as Google Cloud Speech-to-Text or Amazon Transcribe is recommended.

[0664] Next, the server extracts specific information from the text data using natural language processing. This process utilizes natural language processing libraries such as spaCy and nltk to analyze important keywords and phrases. The analyzed results are automatically input into the recording device and organized as specific information. This process is automated by data entry mechanisms, which helps reduce recording errors.

[0665] Furthermore, necessary information is presented to field workers through face-worn information devices without placing an additional burden on them. For example, by displaying information on smart glasses, users can grasp the situation in real time and make quick decisions. This process is highly effective in improving on-site responsiveness.

[0666] As a concrete example, if a security guard at a shopping mall receives an emergency call from an unknown source, this system instantly transcribes the call into text, extracts key information, and displays it on the guard's smart glasses. This allows the guard to quickly understand the situation and take the most appropriate action.

[0667] An example of a prompt message that utilizes a generative AI model might be: "We want to develop a system that converts audio recording data into text and extracts and visualizes important incident information. Please tell us a specific scenario of how this system could be useful for security operations in a shopping mall."

[0668] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0669] Step 1:

[0670] The terminal acquires the telephone conversation as an acoustic signal. The input is voice data, and the output is an acoustic signal. The microphone built into the terminal captures the telephone conversation and records it as acoustic data through the communication module.

[0671] Step 2:

[0672] The server uses an acoustic conversion mechanism to convert the acoustic signal into text data. The input is an acoustic signal, and the output is text data. Speech recognition software (e.g., Google Cloud Speech-to-Text) is used to transcribe the audio content into text in real time.

[0673] Step 3:

[0674] The server extracts specific information from text data using natural language processing techniques. The input is text data, and the output is specific information. Natural language processing libraries (e.g., spaCy and nltk) are used to analyze and extract important keywords and phrases within the text.

[0675] Step 4:

[0676] The server automatically inputs specific information into a recording device through a data input mechanism. The input is specific information, and the output is organized data. By executing the automated input process, data is stored in an orderly manner in the recording device (such as a database).

[0677] Step 5:

[0678] The server displays specific information to the field worker's face-worn information device. The input is organized data, and the output is information display. Important specific information is displayed on smart glasses, allowing the worker to instantly access the information.

[0679] This allows users to transcribe and analyze conversational audio in near real-time, enabling them to quickly utilize necessary information on-site.

[0680] 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.

[0681] This invention relates to an automated voice information processing system equipped with a function to analyze the emotions of a user during a telephone conversation. The system's components consist of a terminal, a server, an emotion engine, and an incident management tool.

[0682] First, the terminal records the phone conversation with the user and acquires it as an acoustic signal. The acquired acoustic signal is sent to the server in real time, and the acoustic conversion mechanism within the server is activated.

[0683] The server converts speech to text using an acoustic conversion mechanism. Simultaneously, an emotion engine analyzes the speech data, recognizing and extracting emotional information from the user's tone of voice and the content of their words. This emotional information includes, for example, types of emotions such as "excitement," "disappointment," and "anger."

[0684] The server processes the converted text data using natural language processing techniques to extract specific information necessary for the incident from the conversation. This specific information, along with emotional information, is organized and registered in an electronic recording device via data input.

[0685] Furthermore, emotional information is also used to prioritize incidents. For example, if the emotion is "anger," it is judged to be highly urgent, and the order of responses in incident management is adjusted in real time.

[0686] As a concrete example, consider a scenario where a user files a complaint about a product defect while experiencing high levels of stress. The device records the conversation, and the server analyzes the content and emotions to automatically adjust the system so that this incident is handled quickly and with high priority.

[0687] Thus, the system of the present invention accurately recognizes user emotions by adding an emotion engine, improving the quality and efficiency of incident response. This system is expected to reduce the burden on operators while significantly improving customer satisfaction.

[0688] The following describes the processing flow.

[0689] Step 1:

[0690] The terminal records the user's phone conversation. The recorded audio signal is immediately prepared for transmission to the server by the communication module.

[0691] Step 2:

[0692] The server receives an acoustic signal from the terminal. Using an acoustic conversion device, this acoustic signal is converted into text data. At this point, the audio information is processed as text information.

[0693] Step 3:

[0694] The server activates the emotion engine and analyzes the user's emotions from the voice data. The emotion engine recognizes and extracts emotional information from the tone of voice and linguistic features.

[0695] Step 4:

[0696] The server passes the text data to a natural language processing system, which extracts specific information related to the incident. This information includes the user ID and the reported problem details.

[0697] Step 5:

[0698] The server organizes the specific information and emotional information it extracts and records it on an electronic recording device via a data input mechanism. Here, the information is formatted to be suitable for the incident management system.

[0699] Step 6:

[0700] The server prioritizes incidents based on emotional information. For example, if the emotion is "anger" or "anxiety," the server will set the incident to have a higher priority.

[0701] Step 7:

[0702] The user reviews the records in the incident management tool. They add details as needed and complete the incident processing. This review ensures the accuracy of the information.

[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 customer service, accurately understanding user emotions and handling incidents quickly and appropriately is essential. However, conventional systems do not automate emotion analysis from voice data or incident prioritization based on that information, resulting in a heavy burden on operators and insufficient improvement in customer satisfaction.

[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 signal conversion means for converting acoustic signals into strings, information processing means for extracting specific information, and emotion analysis means for analyzing the user's emotions. This makes it possible to analyze emotions from voice data in real time, extract specific information, and automatically set incident priorities based on that information.

[0708] An "acoustic signal" is an analog or digital signal that enables the transmission of a series of data, including sound.

[0709] "Signal conversion means" refers to a process or device that converts an acoustic signal into a string of characters.

[0710] "Information processing means" refers to a function or mechanism for extracting specific information required from text data.

[0711] "Emotion analysis means" refers to a function or process for identifying emotions contained in audio data.

[0712] "Data input means" refers to a function or device for registering extracted specific information and emotional information into an electronic record.

[0713] A "prioritization mechanism" is a function or mechanism for determining the priority of incident response based on emotional information.

[0714] An "electronic recording medium" is a physical or virtual platform for recording digital data.

[0715] This automated voice information processing system consists of a terminal for telephone conversations with users, a server for processing data, an emotion engine for analyzing emotions, and an incident management tool for organizing information. The invention is implemented in this system as follows:

[0716] First, the user engages in conversation through the device. The device records the conversation in real time and acquires it as an acoustic signal. This signal is immediately sent to the server. The server uses a signal conversion mechanism to convert the acoustic signal into text data. Speech recognition software can be utilized in this process.

[0717] Simultaneously, the server activates an emotion analysis system, analyzing the user's voice tone and word content from the audio data to extract emotional information. Specifically, it identifies types of emotions such as "excitement," "disappointment," and "anger." Emotion analysis software is used for this analysis.

[0718] Furthermore, the server uses information processing tools to extract specific information from text data and performs incident management based on that information. At this stage, the specific information and emotional information are registered on an electronic recording medium by data input tools. The emotional information is used to prioritize incidents; for example, if the emotion is determined to be "anger," the urgency of the incident is set to high.

[0719] As a concrete example, consider a situation where a user experiences high stress when reporting a product defect. The terminal records the conversation, and the server analyzes the audio, automatically adjusting the system to prioritize the incident. This system can reduce the burden on operators and improve customer satisfaction.

[0720] Example prompt to input into the generating AI model: "Please provide a description of how the system works, which analyzes customer emotions in real time during phone conversations and adjusts response priorities accordingly."

[0721] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0722] Step 1:

[0723] The device initiates a phone conversation with the user and records the audio in real time. The input is the user's voice, which is acquired as a digital audio signal. The output is the audio signal temporarily stored within the device.

[0724] Step 2:

[0725] The terminal transmits the acquired acoustic signal to the server. The input is an acoustic signal, which is transmitted using a high-speed data communication method. The output is the acoustic signal as it reaches the server.

[0726] Step 3:

[0727] The server receives an acoustic signal and converts it into text data using a signal conversion device. The input is an acoustic signal, which is converted into a string using speech recognition software. The output is the text data converted into a string.

[0728] Step 4:

[0729] The server uses emotion analysis tools to extract user emotion information from audio data. Input is either an acoustic signal or text data, which is analyzed using emotion analysis software. Output is emotion information, including feelings such as "excitement" and "anger."

[0730] Step 5:

[0731] The server uses information processing tools to extract specific information from text data. The input is text data, and natural language processing techniques are used to extract necessary information from the conversation. The output is specific information necessary for incident management.

[0732] Step 6:

[0733] The server registers emotional information and specific information on an electronic recording medium through a data input means. The input consists of emotional information and specific information, which are organized and stored in the recording device. The output is the organized electronic recording data.

[0734] Step 7:

[0735] The server determines incident priorities based on registered sentiment information. The input is sentiment information, and the urgency is set using a ranking mechanism. The output is incident management information with the assigned priorities.

[0736] Step 8:

[0737] The server notifies operators of incidents requiring attention, ensuring appropriate action is taken. Input is prioritized incident information, which generates response instructions. Output is notification information prompting action.

[0738] (Application Example 2)

[0739] 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".

[0740] In traditional customer support, operators had to directly assess customers' emotions and prioritize them based on urgency. This increased the burden on operators and potentially reduced the efficiency of customer service. Furthermore, if emotions could not be accurately assessed, there was a risk of delays in customer service and decreased customer satisfaction.

[0741] 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.

[0742] In this invention, the server includes a conversion device that receives an acoustic signal and converts the acoustic signal into text, a language processing device that extracts specific information from the text, a data transmission device that automatically inputs the extracted specific information into a recording medium, an emotion analysis device that analyzes the type of emotion of the user, and a management device that sets priorities based on the type of emotion. This enables rapid and accurate incident management based on emotion information.

[0743] An "acoustic signal" is a representation of sound as an electrical signal, and it can handle a variety of sounds, including human speech.

[0744] A "conversion device" is a device that converts acoustic signals into text information, using speech recognition technology to turn speech into text.

[0745] A "language processing device" is a device that uses natural language processing technology to extract specific information from textual data.

[0746] A "recording medium" is a medium for storing information that can retain electronic data for a long period of time.

[0747] A "data transmission device" is a device that has the function of automatically inputting extracted information into a recording medium.

[0748] An "emotion analysis device" is a device that identifies a user's emotions from voice and text information and analyzes their type.

[0749] A "management device" is a device that has the function of setting priorities and adjusting the order of responses based on the results of emotional analysis.

[0750] An "information processing system" is a collection of devices and programs that receive, convert, analyze, and ultimately record and manage input data.

[0751] To implement this invention, a terminal, a server, and various related software are mainly used. The terminal records telephone conversations with the user and transmits the resulting audio signal to the server. The server is equipped with various devices for processing the received audio signal.

[0752] 1. Acoustic Converter: The server uses an acoustic converter to convert acoustic signals into text information. This process utilizes a speech recognition engine (e.g., Google Cloud Speech-to-Text API).

[0753] 2. Language Processing Unit: The server uses a language processing unit to extract specific instructions and requests from text information. Natural language processing libraries (e.g., spaCy, NLTK) are used for this process.

[0754] 3. Sentiment Analysis Device: The server also includes a sentiment analysis device that analyzes the user's emotions based on voice tone and text. This process utilizes a sentiment analysis engine (e.g., IBM Watson Tone Analyzer).

[0755] 4. Recording medium and management device: The analyzed specific information is stored on the recording medium. Furthermore, the server's management device sets priorities and performs incident management based on the obtained sentiment information.

[0756] As a concrete example, consider a case where a user calls customer support expressing strong dissatisfaction with a delayed delivery of a product. In this case, the terminal records the conversation, and the server analyzes the content and determines that the user is "angry," thus setting the importance level high. This allows for prompt instructions to be given to the appropriate department, leading to improved user satisfaction.

[0757] An example of a prompt message would be, "Analyze the emotions from this conversation, extract emotional information such as anger, excitement, and disappointment, and prioritize the appropriate response." This allows the server to automatically perform the appropriate actions, enabling efficient customer management.

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

[0759] Step 1:

[0760] The terminal records phone conversations with the user. It receives the user's voice signal as input and sends it to the server as digital data, specifically as an acoustic signal, as output.

[0761] Step 2:

[0762] The server inputs the received acoustic signal into an acoustic converter. The acoustic converter converts the acoustic signal into text. This process uses a speech recognition engine to process the audio data into text information. The output is the conversation content in text format.

[0763] Step 3:

[0764] The server inputs text information into the language processing unit. The language processing unit extracts specific information from the text. At this stage, natural language processing techniques are used to identify and extract specific information such as product names and problems to be solved. The output is specific, identified information.

[0765] Step 4:

[0766] The server inputs text information into the sentiment analysis device. The sentiment analysis device analyzes the user's emotional state based on the tone of voice and the content of the text. In this process, it uses an emotion analysis engine to classify and output emotions such as "anger" and "joy."

[0767] Step 5:

[0768] The server stores the obtained specific information and emotional information on a recording medium. During this process, a data input device is used to automatically organize and record the data. The output is the stored data for use in subsequent processing.

[0769] Step 6:

[0770] The server management system prioritizes incidents based on emotional information. If the emotion is "anger," it assigns a higher priority and determines the order of response. The management system uses this information to immediately issue instructions to the relevant departments. The output is the response order according to priority.

[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] An acoustic conversion means that receives an acoustic signal and converts the acoustic signal into text,

[0795] A natural language processing means for extracting specific information from the text,

[0796] A data input means for automatically inputting the extracted specific information into an electronic recording device,

[0797] A system that includes this.

[0798] (Claim 2)

[0799] The system according to claim 1, which performs processing in real time upon reception of an acoustic signal.

[0800] (Claim 3)

[0801] The system according to claim 1, further comprising data organization means for organizing specific information according to a format.

[0802] "Example 1"

[0803] (Claim 1)

[0804] A communication means for acquiring an acoustic signal and transmitting the acoustic signal to a data processing device,

[0805] A speech recognition means that converts the acoustic signal into text,

[0806] Information analysis means for analyzing specific identification information from the text,

[0807] A data registration means for automatically saving the analyzed identification information to an information recording device,

[0808] A system that includes this.

[0809] (Claim 2)

[0810] The system according to claim 1, which performs the acquisition of acoustic signals and registration of data in real time.

[0811] (Claim 3)

[0812] The system according to claim 1, further comprising data management means for structuring identification information based on a pre-configured format.

[0813] "Application Example 1"

[0814] (Claim 1)

[0815] An acoustic conversion means that receives an acoustic signal and converts the acoustic signal into character data,

[0816] A natural language processing means for extracting specific information from the character data,

[0817] A data input means for automatically inputting the extracted specific information into a recording device,

[0818] To reduce the burden on on-site workers, a means of presenting information using face-worn information devices,

[0819] A system that includes this.

[0820] (Claim 2)

[0821] The system according to claim 1, which processes acoustic signals in real time upon reception and presents extracted specific information to on-site workers.

[0822] (Claim 3)

[0823] The system according to claim 1, further comprising data organization means for organizing specific information according to a standardized information format and presenting it appropriately on a display device.

[0824] "Example 2 of combining an emotion engine"

[0825] (Claim 1)

[0826] A signal conversion means that receives an acoustic signal and converts the acoustic signal into a string of characters,

[0827] Information processing means for extracting specific information from the string,

[0828] A means of analyzing user emotions,

[0829] A data input means for automatically inputting the extracted specific information and emotional information into an electronic recording medium,

[0830] A ranking method that determines priorities based on extracted emotional information,

[0831] A system that includes this.

[0832] (Claim 2)

[0833] The system according to claim 1, which performs processing in real time upon reception of an acoustic signal.

[0834] (Claim 3)

[0835] The system according to claim 1, further comprising data organization means for organizing specific information according to a format.

[0836] "Application example 2 when combining with an emotional engine"

[0837] (Claim 1)

[0838] A conversion device that receives an acoustic signal and converts the acoustic signal into text,

[0839] A language processing device that extracts specific information from the text,

[0840] A data transmission device that automatically inputs the extracted specific information into a recording medium,

[0841] An emotion analysis device that analyzes the types of emotions of users,

[0842] A management device that sets priorities based on the type of emotion,

[0843] An information processing system that includes this.

[0844] (Claim 2)

[0845] The information processing system according to claim 1, which processes acoustic signals in real time upon reception and adjusts the correspondence order.

[0846] (Claim 3)

[0847] The information processing system according to claim 1, further comprising a data sorting device for organizing specific information and emotional information according to a format. [Explanation of Symbols]

[0848] 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. An acoustic conversion means that receives an acoustic signal and converts the acoustic signal into character data, A natural language processing means for extracting specific information from the character data, A data input means for automatically inputting the extracted specific information into a recording device, To reduce the burden on on-site workers, a means of presenting information using face-worn information devices, A system that includes this.

2. The system according to claim 1, which processes acoustic signals in real time upon reception and presents the extracted specific information to the field worker.

3. The system according to claim 1, further comprising data organization means for organizing specific information according to a standardized information format and presenting it appropriately on a display device.

Images