system

Abstract

We provide the system. [Solution] A means of acquiring audio data and converting it into text data, A means of analyzing the converted text data and extracting the intent of the inquiry, A means of identifying the person with the most suitable skills based on the extracted intent, A means of automatically transferring calls to a designated person, A system that includes means for recording call content and response history and updating it as system learning data.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance that responds 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 a modern business environment, a quick and appropriate response to inquiries from customers is essential for improving customer satisfaction. However, in conventional systems, when the content of an inquiry becomes complex, it is difficult to accurately analyze the content and connect it to a person in charge with the optimal skills, resulting in a problem of time-consuming response. In addition, there is a problem that means for effectively visualizing the skills and past response histories of employees are insufficient, making it difficult to allocate the optimal human resources. These problems lead to a decrease in business efficiency and, ultimately, a factor that undermines the competitiveness of enterprises.

Means for Solving the Problems

[0005] This invention provides a means for extracting the intent of an inquiry by acquiring voice data, converting it into text data in real time, and analyzing the converted text data using natural language processing technology. Furthermore, it includes a means for identifying a person with the most suitable skills based on the extracted intent, utilizing past interaction history, and automatically transferring the call to the identified person. In addition, by recording the call content and interaction history, updating it as learning data for the entire system, and improving accuracy, it becomes possible to solve problems efficiently.

[0006] "Voice data" refers to data obtained from phone calls or recorded audio, in either digital or analog format.

[0007] "Text data" refers to data expressed as written information, obtained after analyzing audio data.

[0008] "Natural language processing technology" is a general term for technologies that enable computers to understand, analyze, and generate human language.

[0009] "Intent of inquiry" refers to the information or solutions that a customer seeks when making an inquiry.

[0010] A "skilled employee" refers to an employee who possesses the necessary knowledge and abilities to address a specific problem and can effectively solve that problem.

[0011] "Automatically forwarding calls" refers to the process of switching communications to another person or device without human intervention, based on specific conditions.

[0012] "Response history" refers to information that summarizes records and results of past responses to customer inquiries.

[0013] "System training data" refers to a collection of information, including historical data and analysis results, used to improve the system's performance. [Brief explanation of the drawing]

[0014] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

MODE FOR CARRYING OUT THE INVENTION

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] 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."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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".

[0035] This invention is a system for efficiently and quickly processing customer calls, specifically a system that performs a series of operations from acquiring and analyzing voice data to automatically transferring the call to the most suitable person and recording the call history. The following describes the embodiments for carrying out the invention.

[0036] When a user makes a call, the server receives the call and retrieves the audio data. The server then starts streaming this audio data to process it in real time.

[0037] The audio data is sent from the device to Google Cloud's Speech-to-Text API. The device uses this API to quickly convert the audio data into text data.

[0038] The server, upon receiving the text data, analyzes it using natural language processing techniques. The server extracts keywords and phrases from the text to clarify the user's intent.

[0039] Based on the extracted intent, the server refers to a database of past interaction history. The server uses AI and machine learning models to identify the person with the skills best suited to the intent. Skill mapping technology is used to evaluate the capabilities of the person in question.

[0040] Once a suitable representative is identified, the server automatically transfers the call to that representative. This process is designed to be completed in the shortest possible time from the time the user initiates the inquiry.

[0041] Once the interaction is complete, the server records the details of the call and the solution. This data is then stored as training data for future use, helping to improve the system's accuracy.

[0042] For example, if a user requests support regarding an internet connection problem, the server extracts keywords such as "internet" and "connection" from the voice. A technical support representative who has handled similar cases in the past is identified, and the call is transferred. The representative quickly resolves the user's problem, and the result is recorded. In this way, the system is configured to provide efficient customer support.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The user makes a phone call. The server receives the call and begins streaming the audio data.

[0046] Step 2:

[0047] The server sends the audio data to the Google Cloud Speech-to-Text API and instructs the device to convert it into text data in real time.

[0048] Step 3:

[0049] The device receives the audio data and converts it into text data using the Speech-to-Text API. The converted text data is then sent to the server.

[0050] Step 4:

[0051] The server analyzes the received text data using natural language processing techniques. Through this analysis, it extracts keywords and important phrases from the text to identify the user's intent behind their inquiry.

[0052] Step 5:

[0053] Based on the identified intent, the server searches a database of past interactions and uses AI to identify the most suitable person with the appropriate skills. Past history and skill mapping assist in the decision-making process.

[0054] Step 6:

[0055] The server automatically transfers the call to the designated contact person. The server takes into account the contact person's availability and other factors to ensure the most optimal transfer.

[0056] Step 7:

[0057] The user speaks with a representative, and the problem is resolved. The server records the content of this call and the problem-solving process.

[0058] Step 8:

[0059] The server saves recorded call history and resolution information to a learning database, updating the system's overall learning data. This improves the accuracy of future responses.

[0060] (Example 1)

[0061] 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."

[0062] In voice-based customer support, efficiently handling customer calls and quickly connecting them to the appropriate representative is often considered difficult. Therefore, there is a need to improve customer satisfaction and streamline operations. Traditional methods often involve manual call transfers and history recording, which can be time-consuming and increase the risk of human error. Furthermore, the criteria for identifying the correct representative are often ambiguous, resulting in customers' requests not being properly understood.

[0063] 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.

[0064] In this invention, the server includes technical means for acquiring voice information and converting it into text information, technical means for analyzing the converted text information and extracting the purpose of the request, and technical means for identifying a business person with the most suitable capabilities. This enables voice inquiries to be processed quickly and accurately, and to be automatically transferred to the appropriate business person.

[0065] "Voice information" refers to information or data transmitted through voice, such as during phone calls.

[0066] "Textual information" refers to information obtained by converting audio information into text format, and is data that is stored in a format that can be analyzed.

[0067] "Technical means" refers to a technical approach, such as devices or methods, used to achieve a specific purpose or function.

[0068] A "business representative" refers to a person who possesses specific skills and knowledge and is engaged in duties such as providing services to customers or solving problems.

[0069] A "machine learning model" refers to an algorithm or method used to make predictions or classifications by analyzing data and learning patterns.

[0070] "Natural language processing technology" refers to the technology that enables computers to understand human language and analyze its meaning and structure.

[0071] "Real-time processing" refers to a process that processes input information immediately without delay after it is generated and outputs the results instantly.

[0072] This invention is a system aimed at efficiently and quickly responding to customer inquiries made by voice. When a user makes an inquiry by phone, the server receives the call and acquires voice information. The server immediately sends the voice information to the terminal in order to start streaming processing in real time. This terminal converts the voice information into text information using an API that uses general speech recognition technology (for example, an API for a voice recognition cloud service).

[0073] The converted text information is sent to the server, where it is analyzed using natural language processing technology. The server then extracts the purpose of the request from the data obtained through the analysis, understanding the content of the inquiry based on specific keywords and phrases. Accuracy is improved by utilizing generative AI models in this process.

[0074] The server uses past interaction history and newly extracted data, along with machine learning models, to identify the most suitable person to handle the call. Once the person is identified, the server automatically transfers the call to that person. This allows the user to receive a quick and appropriate response.

[0075] Once the interaction is complete, the server meticulously records the call content and solution, storing it as learning data for future use. This process helps improve the system's accuracy.

[0076] For example, if a user inquires about an issue such as "unstable network connection," the server will quickly identify the appropriate person in charge based on keywords such as "network" and "connection," and transfer the call. Furthermore, the system's operation can be verified by inputting prompts such as, "Please extract specific keywords from the voice data and show how to transfer the call to a person with the relevant skills," into the generative AI model.

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

[0078] Step 1:

[0079] When a user makes a call, the server receives the call. The server takes the audio information as input and begins streaming it in real time. This initial processing prepares the audio information for uninterrupted transmission to the next stage.

[0080] Step 2:

[0081] The server sends audio information to the terminal. The terminal forwards the received audio information to a speech recognition API. Specifically, the terminal uses this API to perform calculations that convert the audio information into text information. As a result, text data is generated as output.

[0082] Step 3:

[0083] The terminal sends the generated text information to the server. The server begins analyzing the received text information using natural language processing technology. During the analysis process, the server extracts keywords and phrases and obtains the data requested by the user as output.

[0084] Step 4:

[0085] The server uses the information obtained through analysis to confirm the purpose of the request as input. The server uses past response history data and a generated AI model to process the data in order to identify the most suitable person in charge of the task. This process results in output indicating the appropriate person in charge.

[0086] Step 5:

[0087] The server automatically transfers the call to the identified person in charge. This step uses the call between the identified person in charge and the user as input. By transferring the call, the server enables rapid customer response.

[0088] Step 6:

[0089] Once the interaction is complete, the server meticulously records the call content and resolution. The original call content and processing results are used as input, and this information is stored as system training data as output. This data will be used to improve future services.

[0090] (Application Example 1)

[0091] 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."

[0092] Responding quickly to suspicious activity and emergencies in residential areas and commercial facilities is crucial. However, traditional manual reporting systems have the drawback of being slow to respond to reports, making it difficult to resolve urgent issues immediately.

[0093] 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.

[0094] In this invention, the server includes means for acquiring voice information and converting it into text information, means for analyzing the converted text information and extracting the intent of the inquiry, means for identifying an expert with the most suitable capabilities based on the extracted intent, and means for analyzing suspicious activity and immediately notifying security personnel. This enables a rapid response to suspicious activity and emergencies.

[0095] "Voice information" refers to the acquisition of voice data generated by the user.

[0096] "Text information" refers to audio information converted into a string of characters.

[0097] "Analysis" is the process of processing acquired text information and extracting useful information and intent from it.

[0098] "Ability" refers to the level of specific skills and knowledge possessed by an expert.

[0099] An "expert" is a person who possesses advanced knowledge and skills in a particular field.

[0100] "Communication" is the process of exchanging information through voice or text.

[0101] "Suspicious activity" refers to actions or situations that are not normal and may pose a safety risk.

[0102] A "safety officer" is a person responsible for taking action to maintain safety in a facility or area.

[0103] A "knowledge base" is a collection of data that stores past response histories and solutions, and is used to improve systems and address issues.

[0104] The system of this invention is designed to provide security alerts quickly and effectively. Its implementation utilizes a server and user terminals. The server operates in a cloud computing environment, and the terminals are mobile devices owned by the user, such as smartphones and tablets.

[0105] When a user discovers suspicious activity, they report it using their device. Information reported via voice input is quickly converted into text using the Google Cloud Speech-to-Text API on the device. This text is sent to a server and analyzed using natural language processing techniques. Specifically, the intent of the inquiry is extracted from the text using the SpaCy library.

[0106] Subsequently, the server refers to past response history based on the extracted intent and identifies the most suitable security officer using an AI model (built using TENSORFLOW®). This AI model evaluates the officer's capabilities, performs skill mapping, and determines the urgency associated with the suspicious activity.

[0107] The identified personnel are automatically forwarded with notifications of suspicious activity. This process enables a quick response to security issues. Furthermore, the reported information and response results are stored in a PostgreSQL database and used as a knowledge base for the future.

[0108] As a concrete example, if suspicious behavior is observed in the parking lot of a residence, the user can initiate a report using their device. When they say, "I saw a suspicious person in the parking lot," the voice is converted into text and analyzed as an attempt to identify a suspicious person. The necessary security personnel are then immediately notified.

[0109] Examples of prompt statements are as follows:

[0110] "I want to report suspicious activity in the parking lot. How do I go about reporting it?"

[0111] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0112] Step 1:

[0113] When a user discovers suspicious activity, they initiate a report using their device. The device acquires the user's voice information as input. Specifically, the user launches an application on their device and begins voice input.

[0114] Step 2:

[0115] The device sends the acquired audio information to the Google Cloud Speech-to-Text API, where it is converted into text. It receives audio information as input and generates text information as output. This text information is in the format necessary for analyzing the content of the report.

[0116] Step 3:

[0117] Text information is sent from the terminal to the server. The server uses natural language processing technology to analyze the text information and extract the intent of the query. It receives text information as input and obtains the intent of the query as output. Specifically, it uses the SpaCy library to extract important keywords from the text information.

[0118] Step 4:

[0119] The server refers to past response history based on the extracted intent and evaluates the appropriate response. An AI model (using TensorFlow) identifies the most suitable safety officer. It receives the intent of the inquiry as input and obtains the identified safety officer as output. In operation, the AI ​​model performs skill mapping and evaluates the officer's capabilities.

[0120] Step 5:

[0121] The server automatically forwards communications to the identified security officer. It receives the identified officer's information as input and sends a notification as output. Specifically, it sends a notification to the officer's mobile device or communication terminal to prompt quick confirmation and response.

[0122] Step 6:

[0123] The report content and response results are recorded in a PostgreSQL database by the server. It receives communication content and response results as input and outputs them as knowledge base data. Operationally, this information is stored in the database and used for future responses and analysis.

[0124] 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.

[0125] This invention combines a conventional inquiry handling system with an emotion engine to enable responses that take user emotions into consideration. Specifically, it acquires text data from voice data and performs analysis using natural language processing technology, while simultaneously analyzing the user's emotions using an emotion engine, and utilizing the results in the response.

[0126] When a user makes a call, the server receives the voice data and processes it in streaming format. The server then sends the voice data to an emotion engine in real time, which analyzes the user's emotions.

[0127] The audio data is converted to text on the device using the Google Cloud Speech-to-Text API. This text data is then analyzed by the server's natural language processing module to extract the user's intent and simultaneously capture the user's sentiment data.

[0128] Based on the extracted intent and emotional information of the inquiry, the server identifies the most suitable representative by referring to past interaction history and a skills database. For example, if a customer is dissatisfied, a representative with high skill in handling that specific emotion will be selected.

[0129] Once the appropriate person to handle the call is identified, the server automatically transfers the call to that person. At this time, the server also provides the person with emotional data to help them respond more appropriately.

[0130] At the end of a call, the server records the interaction history, including the content of the conversation and the user's emotional changes, and updates the system's database with this data to help improve accuracy in future interactions.

[0131] For example, if a user complains that their order was canceled while feeling angry, the emotion engine recognizes the emotion of "anger" and selects a representative with the necessary skills to handle that emotion. As a result, appropriate and considerate responses are provided quickly, leading to increased user satisfaction. In this way, an advanced customer service system incorporating emotional data is realized.

[0132] The following describes the processing flow.

[0133] Step 1:

[0134] The user makes a phone call. The server receives this call and begins capturing audio data.

[0135] Step 2:

[0136] The server transfers the received audio data to the emotion engine in real time, which analyzes the user's emotions from their voice.

[0137] Step 3:

[0138] The server simultaneously sends audio data to the device, which then uses the Google Cloud Speech-to-Text API to convert the audio into text data. This text data is then sent back to the server.

[0139] Step 4:

[0140] The server analyzes text data using natural language processing techniques to extract the user's intent. Sentimental data is also combined with this analysis.

[0141] Step 5:

[0142] The server uses extracted intent and sentiment data to refer to past interaction history and a skills database. Using AI technology, it identifies the most suitable representative for the user's inquiry and emotions.

[0143] Step 6:

[0144] The server automatically transfers the call to the selected representative. When the call is transferred, the representative is also informed of the analyzed sentiment data.

[0145] Step 7:

[0146] A representative will respond to user inquiries and resolve the issues. Users can receive prompt assistance thanks to the representative's appropriate skills.

[0147] Step 8:

[0148] After a call ends, the server records emotional information along with the call history. This data is stored in the system's learning database and used to improve the quality of future interactions.

[0149] (Example 2)

[0150] 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".

[0151] Conventional customer service systems often fail to adequately consider user emotions, making it difficult to improve user satisfaction and resolve problems quickly. Therefore, there is a need to analyze the user's emotional state from voice data and select the most suitable representative based on the results to provide more appropriate responses.

[0152] 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.

[0153] In this invention, the server includes means for acquiring voice information and converting it into text information, means for analyzing the converted text information and extracting the purpose of the inquiry, and means for analyzing the emotional state from the voice information. This enables the identification of the most suitable person to handle the inquiry based on the user's intent and further considering their emotional state, allowing for a quick and appropriate response.

[0154] "Voice information" refers to voice data transmitted by the user, which is input processed by speech recognition technology.

[0155] "Textual information" refers to text data obtained by processing and converting audio information, and is a data format used to analyze the intent of an inquiry.

[0156] "Purpose of inquiry" refers to the intentions or requests that the user wants to convey through voice information, and is information extracted through natural language processing.

[0157] "Ability" refers to the level of technical skills and knowledge an employee possesses in a specific field, based on their past service history and skills database.

[0158] A "responsible person" is an individual identified based on the user's inquiry and emotional state, whose role is to provide the most appropriate response.

[0159] "Emotional state" refers to the user's emotions and psychological state as analyzed from voice information, and is a factor considered in order to improve the quality of service.

[0160] An "information processing device" refers to the entire system used to process audio and text information and update correspondence history and learning information.

[0161] This invention is a system that processes voice information in real time and optimizes inquiry responses while considering the user's emotional state. When a user makes a phone call, the server receives the voice information. The server sends this voice information to the terminal and converts it into text information using speech recognition technology. Specifically, the terminal converts the voice information into text using the Google Cloud Speech-to-Text API.

[0162] The server analyzes the converted text information using natural language processing techniques to extract the purpose of the query. This process involves text tokenization and syntactic analysis. Furthermore, the server performs sentiment analysis on the audio information to analyze the user's emotional state. By using an emotion engine, the server determines the user's emotions (e.g., anger or joy) and uses this information in the next step.

[0163] Based on the analysis results, the server refers to past interaction history and a skills database to identify the most suitable agent. Emotional states are particularly considered, and the system is designed to select an agent with the skills to address specific emotions. The call is automatically transferred to the identified agent, and emotional information is provided simultaneously to support appropriate responses.

[0164] This system records the interaction history, including call content and emotional changes, and updates the information processing device with this information to improve the accuracy of future inquiries.

[0165] For example, when a user complains angrily that their order has been canceled, the system uses emotion analysis to determine that the user is angry, selects a representative with the appropriate skills, and responds quickly. This process increases customer satisfaction.

[0166] Examples of prompts for a generative AI model include the following:

[0167] "Please explain in detail the process of the system that uses speech recognition to optimize customer service."

[0168] "Please explain how to select personnel using an emotional engine."

[0169] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0170] Step 1:

[0171] When a user makes a call, the server receives the call. The input is the user's voice information, and the server prepares to process it in streaming format. Specifically, the server sends the voice information to the terminal in the appropriate format.

[0172] Step 2:

[0173] The device receives audio information sent from the server and converts it into text information using the Google Cloud Speech-to-Text API. The input is audio information, and the output is text information. This conversion involves data processing, such as detecting words and phrases from the audio and converting them into text format.

[0174] Step 3:

[0175] The server analyzes the text information received from the terminal using natural language processing techniques. The input is text information, and the output is the purpose of the query. Specifically, the server performs word tokenization, syntactic analysis, and semantic analysis to identify the user's intent. The purpose of the query is extracted during this process.

[0176] Step 4:

[0177] The server analyzes emotional states from voice information. The input is the voice information itself, and the output is the user's emotional state. The server uses an emotion engine to analyze the tone and speed of the voice and determine the emotion. This emotional data will be used for future support.

[0178] Step 5:

[0179] The server identifies the most suitable agent based on the extracted inquiry's purpose and sentiment information. The input is the purpose and sentiment information, and the output is the agent's information. The server refers to past interaction history and a skills database to select an agent with the appropriate skills.

[0180] Step 6:

[0181] The server automatically transfers the call to the designated person in charge, simultaneously providing sentiment information. The input is the person in charge's information and sentiment data, and the output is the transferred call. Specifically, the server connects the call line to the person in charge, improving the efficiency of support.

[0182] Step 7:

[0183] Once a call ends, the server records the call content and emotional changes, updating the database as learning information for the information processing device. The input is the call content and emotional changes, and the output is the updated response history. This record enables more accurate responses to future inquiries.

[0184] (Application Example 2)

[0185] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0186] Traditional customer service systems often fail to consider user emotions, resulting in uniform responses. This can lead to decreased customer satisfaction, highlighting the need for further improvement. Furthermore, the inability to quickly transfer inquiries to the most appropriate representatives also contributes to inefficient responses. Therefore, a system capable of flexible responses that reflect user emotions and that quickly and appropriately identifies the right representative is required.

[0187] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0188] In this invention, the server includes means for acquiring audio signals and converting them into text data, means for analyzing the converted text data and extracting the purpose of the inquiry, and means for acquiring emotional data, which includes an emotion engine for analyzing the user's emotional state. This enables flexible responses that take the user's emotions into consideration and quick transfer to the most suitable person in charge.

[0189] An "audio signal" is data obtained by electrically converting the vibrations of sound emitted from a sound source.

[0190] "Character data" refers to information where audio signals or other forms of data are represented as characters.

[0191] "Analysis" is the process of examining data in detail according to a specific purpose and extracting the necessary information.

[0192] The "purpose of the inquiry" refers to the user's intentions and requests regarding what they want from the system.

[0193] An "emotion engine" is a technology or device that analyzes and identifies emotions from a user's way of speaking and the content of their speech.

[0194] "Emotional data" refers to information that expresses a user's emotional state as a numerical value or category.

[0195] "Skills" refer to the specialized knowledge and abilities necessary for a particular task or response.

[0196] A "person in charge" refers to an individual or team responsible for performing a specific task or handling customer inquiries.

[0197] "Communication" refers to the means and protocols used to send and receive information.

[0198] A "system" is a mechanical or electronic configuration in which multiple elements are integrated and designed to achieve a specific function.

[0199] The system for implementing this invention mainly consists of three elements: a server, a terminal, and a user. The server is responsible for acquiring audio signals and converting them into text data. Specifically, the terminal uses the Google Cloud Speech-to-Text API to convert audio into text with high accuracy. The converted text data is sent to the server. The server uses the Python NLTK library as a natural language interpretation technology to analyze the text data and extract the purpose of the query. Furthermore, IBM Watson® Natural Language Understanding is used to analyze the user's emotional state and acquire emotional data. This enables the server to provide flexible responses that take the user's emotions into consideration.

[0200] The server identifies the most suitable agent based on extracted purpose and sentiment data. This identification uses data learned from past interaction history. The communication is automatically forwarded to the identified agent, enabling appropriate customer service. This interaction is recorded as communication content and interaction history, and continuously updated within the system as learning information for business transactions.

[0201] As a concrete example, suppose a user contacts the system feeling anxious because "the item I ordered yesterday hasn't arrived." In this case, the server can immediately recognize this emotion and take appropriate action or provide guidance to alleviate the anxiety. Another example of a prompt message to an AI model generated using this system would be a user utterance such as, "The item I ordered yesterday hasn't arrived. Can you check on it immediately?" In this way, a system is built that supports dynamic responses in response to the user's emotions.

[0202] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0203] Step 1:

[0204] The device acquires voice input from the user through the microphone. The voice signal is the input, and the device converts this into text data in real time using the Google Cloud Speech-to-Text API. The output is data representing the conversation in text format.

[0205] Step 2:

[0206] The server receives character data sent from the terminal. This text data is the input. The server utilizes Python's NLTK library to analyze the character data using natural language interpretation techniques to identify the purpose of the user's inquiry. As a result of the data processing, the user's specific requests and desires are extracted as output.

[0207] Step 3:

[0208] The server simultaneously sends the text data to IBM Watson Natural Language Understanding for analysis by its emotion engine. This input is the text data from step 2. The emotion analysis yields the user's emotional state as output, which is represented as a category or score.

[0209] Step 4:

[0210] The server integrates the objective data from step 2 and the sentiment data from step 3 to identify the most skilled agent from the past interaction history database. This integrated data is the input. The output is information about the identified agent, which is then used to automatically select an agent.

[0211] Step 5:

[0212] The server automatically forwards communications to the selected representative. Here, the result of step 4 is the input. This forwarding ensures that user inquiries are directly connected to the representative, resulting in a quick and accurate response. The output is the trigger that allows the representative to initiate new communication with the customer.

[0213] Step 6:

[0214] The server records all communication content and response history in a database and updates it with the latest learning information for the system. The communication information with the person identified in Step 4 is the input. This update enables learning to improve the accuracy of future responses. The output is historical data of productive responses, which will serve as the basis for improving responses in the future.

[0215] 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.

[0216] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0217] 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.

[0218] [Second Embodiment]

[0219] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0220] 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.

[0221] 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).

[0222] 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.

[0223] 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.

[0224] 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).

[0225] 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.

[0226] 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.

[0227] 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.

[0228] 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.

[0229] 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.

[0230] 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".

[0231] This invention is a system for efficiently and quickly processing customer calls, specifically a system that performs a series of operations from acquiring and analyzing voice data to automatically transferring the call to the most suitable person and recording the call history. The following describes the embodiments for carrying out the invention.

[0232] When a user makes a call, the server receives the call and retrieves the audio data. The server then starts streaming this audio data to process it in real time.

[0233] The audio data is sent from the device to Google Cloud's Speech-to-Text API. The device uses this API to quickly convert the audio data into text data.

[0234] The server, upon receiving the text data, analyzes it using natural language processing techniques. The server extracts keywords and phrases from the text to clarify the user's intent.

[0235] Based on the extracted intent, the server refers to a database of past interaction history. The server uses AI and machine learning models to identify the person with the skills best suited to the intent. Skill mapping technology is used to evaluate the capabilities of the person in question.

[0236] Once a suitable representative is identified, the server automatically transfers the call to that representative. This process is designed to be completed in the shortest possible time from the time the user initiates the inquiry.

[0237] Once the interaction is complete, the server records the details of the call and the solution. This data is then stored as training data for future use, helping to improve the system's accuracy.

[0238] For example, if a user requests support regarding an internet connection problem, the server extracts keywords such as "internet" and "connection" from the voice. A technical support representative who has handled similar cases in the past is identified, and the call is transferred. The representative quickly resolves the user's problem, and the result is recorded. In this way, the system is configured to provide efficient customer support.

[0239] The following describes the processing flow.

[0240] Step 1:

[0241] The user makes a phone call. The server receives the call and begins streaming the audio data.

[0242] Step 2:

[0243] The server sends the audio data to the Google Cloud Speech-to-Text API and instructs the device to convert it into text data in real time.

[0244] Step 3:

[0245] The device receives the audio data and converts it into text data using the Speech-to-Text API. The converted text data is then sent to the server.

[0246] Step 4:

[0247] The server analyzes the received text data using natural language processing techniques. Through this analysis, it extracts keywords and important phrases from the text to identify the user's intent behind their inquiry.

[0248] Step 5:

[0249] Based on the identified intent, the server searches a database of past interactions and uses AI to identify the most suitable person with the appropriate skills. Past history and skill mapping assist in the decision-making process.

[0250] Step 6:

[0251] The server automatically transfers the call to the designated contact person. The server takes into account the contact person's availability and other factors to ensure the most optimal transfer.

[0252] Step 7:

[0253] The user speaks with a representative, and the problem is resolved. The server records the content of this call and the problem-solving process.

[0254] Step 8:

[0255] The server saves recorded call history and resolution information to a learning database, updating the system's overall learning data. This improves the accuracy of future responses.

[0256] (Example 1)

[0257] 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."

[0258] In voice-based customer support, efficiently handling customer calls and quickly connecting them to the appropriate representative is often considered difficult. Therefore, there is a need to improve customer satisfaction and streamline operations. Traditional methods often involve manual call transfers and history recording, which can be time-consuming and increase the risk of human error. Furthermore, the criteria for identifying the correct representative are often ambiguous, resulting in customers' requests not being properly understood.

[0259] 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.

[0260] In this invention, the server includes technical means for acquiring voice information and converting it into text information, technical means for analyzing the converted text information and extracting the purpose of the request, and technical means for identifying a business person with the most suitable capabilities. This enables voice inquiries to be processed quickly and accurately, and to be automatically transferred to the appropriate business person.

[0261] "Voice information" refers to information or data transmitted through voice, such as during phone calls.

[0262] "Textual information" refers to information obtained by converting audio information into text format, and is data that is stored in a format that can be analyzed.

[0263] "Technical means" refers to a technical approach, such as devices or methods, used to achieve a specific purpose or function.

[0264] A "business representative" refers to a person who possesses specific skills and knowledge and is engaged in duties such as providing services to customers or solving problems.

[0265] A "machine learning model" refers to an algorithm or method used to make predictions or classifications by analyzing data and learning patterns.

[0266] "Natural language processing technology" refers to the technology that enables computers to understand human language and analyze its meaning and structure.

[0267] "Real-time processing" refers to a process that processes input information immediately without delay after it is generated and outputs the results instantly.

[0268] This invention is a system aimed at efficiently and quickly responding to customer inquiries made by voice. When a user makes an inquiry by phone, the server receives the call and acquires voice information. The server immediately sends the voice information to the terminal in order to start streaming processing in real time. This terminal converts the voice information into text information using an API that uses general speech recognition technology (for example, an API for a voice recognition cloud service).

[0269] The converted text information is sent to the server, where it is analyzed using natural language processing technology. The server then extracts the purpose of the request from the data obtained through the analysis, understanding the content of the inquiry based on specific keywords and phrases. Accuracy is improved by utilizing generative AI models in this process.

[0270] The server uses past interaction history and newly extracted data, along with machine learning models, to identify the most suitable person to handle the call. Once the person is identified, the server automatically transfers the call to that person. This allows the user to receive a quick and appropriate response.

[0271] Once the interaction is complete, the server meticulously records the call content and solution, storing it as learning data for future use. This process helps improve the system's accuracy.

[0272] For example, if a user inquires about an issue such as "unstable network connection," the server will quickly identify the appropriate person in charge based on keywords such as "network" and "connection," and transfer the call. Furthermore, the system's operation can be verified by inputting prompts such as, "Please extract specific keywords from the voice data and show how to transfer the call to a person with the relevant skills," into the generative AI model.

[0273] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0274] Step 1:

[0275] When a user makes a call, the server receives the call. The server takes the audio information as input and begins streaming it in real time. This initial processing prepares the audio information for uninterrupted transmission to the next stage.

[0276] Step 2:

[0277] The server sends audio information to the terminal. The terminal forwards the received audio information to a speech recognition API. Specifically, the terminal uses this API to perform calculations that convert the audio information into text information. As a result, text data is generated as output.

[0278] Step 3:

[0279] The terminal sends the generated text information to the server. The server begins analyzing the received text information using natural language processing technology. During the analysis process, the server extracts keywords and phrases and obtains the data requested by the user as output.

[0280] Step 4:

[0281] The server uses the information obtained through analysis to confirm the purpose of the request as input. The server uses the past response history data and the generative AI model to perform data processing for identifying the most suitable staff member. Through this process, the output of the appropriate staff member is obtained.

[0282] Step 5:

[0283] The server automatically transfers the call to the identified staff member. In this step, the call between the identified staff member and the user as input is used. By transferring the call, the server enables prompt customer response.

[0284] Step 6:

[0285] When the response is completed, the server records the call content and the solution in detail. The original call content and the processing result are used as input, and this information is stored as the learning data of the system as output. This data is utilized for future service improvement.

[0286] (Application Example 1)

[0287] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0288] It is important to quickly respond to suspicious activities and emergencies in residential areas and commercial facilities. However, the conventional manual reporting system has the problem that it takes time from reporting to response, and it is difficult to immediately solve urgent problems.

[0289] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following respective means.

[0290] In this invention, the server includes means for acquiring voice information and converting it into text information, means for analyzing the converted text information and extracting the intent of the inquiry, means for identifying an expert with the most suitable capabilities based on the extracted intent, and means for analyzing suspicious activity and immediately notifying security personnel. This enables a rapid response to suspicious activity and emergencies.

[0291] "Voice information" refers to the acquisition of voice data generated by the user.

[0292] "Text information" refers to audio information converted into a string of characters.

[0293] "Analysis" is the process of processing acquired text information and extracting useful information and intent from it.

[0294] "Ability" refers to the level of specific skills and knowledge possessed by an expert.

[0295] An "expert" is a person who possesses advanced knowledge and skills in a particular field.

[0296] "Communication" is the process of exchanging information through voice or text.

[0297] "Suspicious activity" refers to actions or situations that are not normal and may pose a safety risk.

[0298] A "safety officer" is a person responsible for taking action to maintain safety in a facility or area.

[0299] A "knowledge base" is a collection of data that stores past response histories and solutions, and is used to improve systems and address issues.

[0300] The system of this invention is designed to provide security alerts quickly and effectively. Its implementation utilizes a server and user terminals. The server operates in a cloud computing environment, and the terminals are mobile devices owned by the user, such as smartphones and tablets.

[0301] When a user discovers suspicious activity, they report it using their device. Information reported via voice input is quickly converted into text using the Google Cloud Speech-to-Text API on the device. This text is sent to a server and analyzed using natural language processing techniques. Specifically, the intent of the inquiry is extracted from the text using the SpaCy library.

[0302] Subsequently, the server refers to past response history based on the extracted intent and identifies the most suitable security officer using an AI model (built using TensorFlow). This AI model evaluates the officer's capabilities, performs skill mapping, and determines the urgency associated with the suspicious activity.

[0303] The identified personnel are automatically forwarded with notifications of suspicious activity. This process enables a quick response to security issues. Furthermore, the reported information and response results are stored in a PostgreSQL database and used as a knowledge base for the future.

[0304] As a concrete example, if suspicious behavior is observed in the parking lot of a residence, the user can initiate a report using their device. When they say, "I saw a suspicious person in the parking lot," the voice is converted into text and analyzed as an attempt to identify a suspicious person. The necessary security personnel are then immediately notified.

[0305] Examples of prompt statements are as follows:

[0306] "I want to report suspicious activity in the parking lot. How do I go about reporting it?"

[0307] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0308] Step 1:

[0309] When the user discovers a suspicious activity, the user starts a report using the terminal. As input, the voice information of the user is acquired by the terminal. As a specific operation, the user launches the application on the terminal and starts voice input.

[0310] Step 2:

[0311] The terminal transmits the acquired voice information to the Google Cloud Speech-to-Text API and converts it into text information. The terminal receives the voice information as input and generates the text information as output. This text information is in the format necessary for analyzing the report content.

[0312] Step 3:

[0313] The text information is transmitted from the terminal to the server. The server uses natural language processing technology to analyze the text information and extract the intention of the inquiry. The server receives the text information as input and obtains the intention of the inquiry as output. As a specific operation, important keywords are extracted from the text information using the SpaCy library.

[0314] Step 4:

[0315] The server refers to the past response history based on the extracted intention and evaluates the countermeasures. An optimal security officer is identified by an AI model (using TensorFlow). The server receives the intention of the inquiry as input and obtains the identified security officer as output. As an operation, the AI model performs skill mapping and evaluates the capabilities of the officers.

[0316] Step 5:

[0317] The server automatically forwards communications to the identified security officer. It receives the identified officer's information as input and sends a notification as output. Specifically, it sends a notification to the officer's mobile device or communication terminal to prompt quick confirmation and response.

[0318] Step 6:

[0319] The report content and response results are recorded in a PostgreSQL database by the server. It receives communication content and response results as input and outputs them as knowledge base data. Operationally, this information is stored in the database and used for future responses and analysis.

[0320] 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.

[0321] This invention combines a conventional inquiry handling system with an emotion engine to enable responses that take user emotions into consideration. Specifically, it acquires text data from voice data and performs analysis using natural language processing technology, while simultaneously analyzing the user's emotions using an emotion engine, and utilizing the results in the response.

[0322] When a user makes a call, the server receives the voice data and processes it in streaming format. The server then sends the voice data to an emotion engine in real time, which analyzes the user's emotions.

[0323] The audio data is converted to text on the device using the Google Cloud Speech-to-Text API. This text data is then analyzed by the server's natural language processing module to extract the user's intent and simultaneously capture the user's sentiment data.

[0324] Based on the extracted intent and emotional information of the inquiry, the server identifies the most suitable representative by referring to past interaction history and a skills database. For example, if a customer is dissatisfied, a representative with high skill in handling that specific emotion will be selected.

[0325] Once the appropriate person to handle the call is identified, the server automatically transfers the call to that person. At this time, the server also provides the person with emotional data to help them respond more appropriately.

[0326] At the end of a call, the server records the interaction history, including the content of the conversation and the user's emotional changes, and updates the system's database with this data to help improve accuracy in future interactions.

[0327] For example, if a user complains that their order was canceled while feeling angry, the emotion engine recognizes the emotion of "anger" and selects a representative with the necessary skills to handle that emotion. As a result, appropriate and considerate responses are provided quickly, leading to increased user satisfaction. In this way, an advanced customer service system incorporating emotional data is realized.

[0328] The following describes the processing flow.

[0329] Step 1:

[0330] The user makes a phone call. The server receives this call and begins capturing audio data.

[0331] Step 2:

[0332] The server transfers the received audio data to the emotion engine in real time, which analyzes the user's emotions from their voice.

[0333] Step 3:

[0334] The server simultaneously sends audio data to the device, which then uses the Google Cloud Speech-to-Text API to convert the audio into text data. This text data is then sent back to the server.

[0335] Step 4:

[0336] The server analyzes text data using natural language processing techniques to extract the user's intent. Sentimental data is also combined with this analysis.

[0337] Step 5:

[0338] The server uses extracted intent and sentiment data to refer to past interaction history and a skills database. Using AI technology, it identifies the most suitable representative for the user's inquiry and emotions.

[0339] Step 6:

[0340] The server automatically transfers the call to the selected representative. When the call is transferred, the representative is also informed of the analyzed sentiment data.

[0341] Step 7:

[0342] A representative will respond to user inquiries and resolve the issues. Users can receive prompt assistance thanks to the representative's appropriate skills.

[0343] Step 8:

[0344] After a call ends, the server records emotional information along with the call history. This data is stored in the system's learning database and used to improve the quality of future interactions.

[0345] (Example 2)

[0346] 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".

[0347] Conventional customer service systems often fail to adequately consider user emotions, making it difficult to improve user satisfaction and resolve problems quickly. Therefore, there is a need to analyze the user's emotional state from voice data and select the most suitable representative based on the results to provide more appropriate responses.

[0348] 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.

[0349] In this invention, the server includes means for acquiring voice information and converting it into text information, means for analyzing the converted text information and extracting the purpose of the inquiry, and means for analyzing the emotional state from the voice information. This enables the identification of the most suitable person to handle the inquiry based on the user's intent and further considering their emotional state, allowing for a quick and appropriate response.

[0350] "Voice information" refers to voice data transmitted by the user, which is input processed by speech recognition technology.

[0351] "Textual information" refers to text data obtained by processing and converting audio information, and is a data format used to analyze the intent of an inquiry.

[0352] "Purpose of inquiry" refers to the intentions or requests that the user wants to convey through voice information, and is information extracted through natural language processing.

[0353] "Ability" refers to the level of technical skills and knowledge an employee possesses in a specific field, based on their past service history and skills database.

[0354] A "responsible person" is an individual identified based on the user's inquiry and emotional state, whose role is to provide the most appropriate response.

[0355] "Emotional state" refers to the user's emotions and psychological state as analyzed from voice information, and is a factor considered in order to improve the quality of service.

[0356] An "information processing device" refers to the entire system used to process audio and text information and update correspondence history and learning information.

[0357] This invention is a system that processes voice information in real time and optimizes inquiry responses while considering the user's emotional state. When a user makes a phone call, the server receives the voice information. The server sends this voice information to the terminal and converts it into text information using speech recognition technology. Specifically, the terminal converts the voice information into text using the Google Cloud Speech-to-Text API.

[0358] The server analyzes the converted text information using natural language processing techniques to extract the purpose of the query. This process involves text tokenization and syntactic analysis. Furthermore, the server performs sentiment analysis on the audio information to analyze the user's emotional state. By using an emotion engine, the server determines the user's emotions (e.g., anger or joy) and uses this information in the next step.

[0359] Based on the analysis results, the server refers to past interaction history and a skills database to identify the most suitable agent. Emotional states are particularly considered, and the system is designed to select an agent with the skills to address specific emotions. The call is automatically transferred to the identified agent, and emotional information is provided simultaneously to support appropriate responses.

[0360] This system records the interaction history, including call content and emotional changes, and updates the information processing device with this information to improve the accuracy of future inquiries.

[0361] For example, when a user complains angrily that their order has been canceled, the system uses emotion analysis to determine that the user is angry, selects a representative with the appropriate skills, and responds quickly. This process increases customer satisfaction.

[0362] Examples of prompts for a generative AI model include the following:

[0363] "Please explain in detail the process of the system that uses speech recognition to optimize customer service."

[0364] "Please explain how to select personnel using an emotional engine."

[0365] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0366] Step 1:

[0367] When a user makes a call, the server receives the call. The input is the user's voice information, and the server prepares to process it in streaming format. Specifically, the server sends the voice information to the terminal in the appropriate format.

[0368] Step 2:

[0369] The device receives audio information sent from the server and converts it into text information using the Google Cloud Speech-to-Text API. The input is audio information, and the output is text information. This conversion involves data processing, such as detecting words and phrases from the audio and converting them into text format.

[0370] Step 3:

[0371] The server analyzes the text information received from the terminal using natural language processing techniques. The input is text information, and the output is the purpose of the query. Specifically, the server performs word tokenization, syntactic analysis, and semantic analysis to identify the user's intent. The purpose of the query is extracted during this process.

[0372] Step 4:

[0373] The server analyzes emotional states from voice information. The input is the voice information itself, and the output is the user's emotional state. The server uses an emotion engine to analyze the tone and speed of the voice and determine the emotion. This emotional data will be used for future support.

[0374] Step 5:

[0375] The server identifies the most suitable agent based on the extracted inquiry's purpose and sentiment information. The input is the purpose and sentiment information, and the output is the agent's information. The server refers to past interaction history and a skills database to select an agent with the appropriate skills.

[0376] Step 6:

[0377] The server automatically transfers the call to the designated person in charge, simultaneously providing sentiment information. The input is the person in charge's information and sentiment data, and the output is the transferred call. Specifically, the server connects the call line to the person in charge, improving the efficiency of support.

[0378] Step 7:

[0379] Once a call ends, the server records the call content and emotional changes, updating the database as learning information for the information processing device. The input is the call content and emotional changes, and the output is the updated response history. This record enables more accurate responses to future inquiries.

[0380] (Application Example 2)

[0381] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0382] Traditional customer service systems often fail to consider user emotions, resulting in uniform responses. This can lead to decreased customer satisfaction, highlighting the need for further improvement. Furthermore, the inability to quickly transfer inquiries to the most appropriate representatives also contributes to inefficient responses. Therefore, a system capable of flexible responses that reflect user emotions and that quickly and appropriately identifies the right representative is required.

[0383] 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.

[0384] In this invention, the server includes means for acquiring audio signals and converting them into text data, means for analyzing the converted text data and extracting the purpose of the inquiry, and means for acquiring emotional data, which includes an emotion engine for analyzing the user's emotional state. This enables flexible responses that take the user's emotions into consideration and quick transfer to the most suitable person in charge.

[0385] An "audio signal" is data obtained by electrically converting the vibrations of sound emitted from a sound source.

[0386] "Character data" refers to information where audio signals or other forms of data are represented as characters.

[0387] "Analysis" is the process of examining data in detail according to a specific purpose and extracting the necessary information.

[0388] The "purpose of the inquiry" refers to the user's intentions and requests regarding what they want from the system.

[0389] An "emotion engine" is a technology or device that analyzes and identifies emotions from a user's way of speaking and the content of their speech.

[0390] "Emotional data" refers to information that expresses a user's emotional state as a numerical value or category.

[0391] "Skills" refer to the specialized knowledge and abilities necessary for a particular task or response.

[0392] A "person in charge" refers to an individual or team responsible for performing a specific task or handling customer inquiries.

[0393] "Communication" refers to the means and protocols used to send and receive information.

[0394] A "system" is a mechanical or electronic configuration in which multiple elements are integrated and designed to achieve a specific function.

[0395] The system for implementing this invention mainly consists of three elements: a server, a terminal, and a user. The server is responsible for acquiring audio signals and converting them into text data. Specifically, the terminal uses the Google Cloud Speech-to-Text API to convert audio into text with high accuracy. The converted text data is sent to the server. The server uses the Python NLTK library as a natural language interpretation technology to analyze the text data and extract the purpose of the query. Furthermore, IBM Watson Natural Language Understanding is used to analyze the user's emotional state and acquire emotional data. This allows the server to provide flexible responses that take the user's emotions into consideration.

[0396] The server identifies the most suitable agent based on extracted purpose and sentiment data. This identification uses data learned from past interaction history. The communication is automatically forwarded to the identified agent, enabling appropriate customer service. This interaction is recorded as communication content and interaction history, and continuously updated within the system as learning information for business transactions.

[0397] As a concrete example, suppose a user contacts the system feeling anxious because "the item I ordered yesterday hasn't arrived." In this case, the server can immediately recognize this emotion and take appropriate action or provide guidance to alleviate the anxiety. Another example of a prompt message to an AI model generated using this system would be a user utterance such as, "The item I ordered yesterday hasn't arrived. Can you check on it immediately?" In this way, a system is built that supports dynamic responses in response to the user's emotions.

[0398] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0399] Step 1:

[0400] The device acquires voice input from the user through the microphone. The voice signal is the input, and the device converts this into text data in real time using the Google Cloud Speech-to-Text API. The output is data representing the conversation in text format.

[0401] Step 2:

[0402] The server receives character data sent from the terminal. This text data is the input. The server utilizes Python's NLTK library to analyze the character data using natural language interpretation techniques to identify the purpose of the user's inquiry. As a result of the data processing, the user's specific requests and desires are extracted as output.

[0403] Step 3:

[0404] The server simultaneously sends the text data to IBM Watson Natural Language Understanding for analysis by its emotion engine. This input is the text data from step 2. The emotion analysis yields the user's emotional state as output, which is represented as a category or score.

[0405] Step 4:

[0406] The server integrates the objective data from step 2 and the sentiment data from step 3 to identify the most skilled agent from the past interaction history database. This integrated data is the input. The output is information about the identified agent, which is then used to automatically select an agent.

[0407] Step 5:

[0408] The server automatically forwards communications to the selected representative. Here, the result of step 4 is the input. This forwarding ensures that user inquiries are directly connected to the representative, resulting in a quick and accurate response. The output is the trigger that allows the representative to initiate new communication with the customer.

[0409] Step 6:

[0410] The server records all communication content and response history in a database and updates it with the latest learning information for the system. The communication information with the person identified in Step 4 is the input. This update enables learning to improve the accuracy of future responses. The output is historical data of productive responses, which will serve as the basis for improving responses in the future.

[0411] 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.

[0412] 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.

[0413] 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.

[0414] [Third Embodiment]

[0415] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0416] 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.

[0417] 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).

[0418] 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.

[0419] 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.

[0420] 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).

[0421] 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.

[0422] 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.

[0423] 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.

[0424] 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.

[0425] 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.

[0426] 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".

[0427] This invention is a system for efficiently and quickly processing customer calls, specifically a system that performs a series of operations from acquiring and analyzing voice data to automatically transferring the call to the most suitable person and recording the call history. The following describes the embodiments for carrying out the invention.

[0428] When a user makes a call, the server receives the call and retrieves the audio data. The server then starts streaming this audio data to process it in real time.

[0429] The audio data is sent from the device to Google Cloud's Speech-to-Text API. The device uses this API to quickly convert the audio data into text data.

[0430] The server, upon receiving the text data, analyzes it using natural language processing techniques. The server extracts keywords and phrases from the text to clarify the user's intent.

[0431] Based on the extracted intent, the server refers to a database of past interaction history. The server uses AI and machine learning models to identify the person with the skills best suited to the intent. Skill mapping technology is used to evaluate the capabilities of the person in question.

[0432] Once a suitable representative is identified, the server automatically transfers the call to that representative. This process is designed to be completed in the shortest possible time from the time the user initiates the inquiry.

[0433] Once the interaction is complete, the server records the details of the call and the solution. This data is then stored as training data for future use, helping to improve the system's accuracy.

[0434] For example, if a user requests support regarding an internet connection problem, the server extracts keywords such as "internet" and "connection" from the voice. A technical support representative who has handled similar cases in the past is identified, and the call is transferred. The representative quickly resolves the user's problem, and the result is recorded. In this way, the system is configured to provide efficient customer support.

[0435] The following describes the processing flow.

[0436] Step 1:

[0437] The user makes a phone call. The server receives the call and begins streaming the audio data.

[0438] Step 2:

[0439] The server sends the audio data to the Google Cloud Speech-to-Text API and instructs the device to convert it into text data in real time.

[0440] Step 3:

[0441] The device receives the audio data and converts it into text data using the Speech-to-Text API. The converted text data is then sent to the server.

[0442] Step 4:

[0443] The server analyzes the received text data using natural language processing techniques. Through this analysis, it extracts keywords and important phrases from the text to identify the user's intent behind their inquiry.

[0444] Step 5:

[0445] Based on the identified intent, the server searches a database of past interactions and uses AI to identify the most suitable person with the appropriate skills. Past history and skill mapping assist in the decision-making process.

[0446] Step 6:

[0447] The server automatically transfers the call to the designated contact person. The server takes into account the contact person's availability and other factors to ensure the most optimal transfer.

[0448] Step 7:

[0449] The user speaks with a representative, and the problem is resolved. The server records the content of this call and the problem-solving process.

[0450] Step 8:

[0451] The server saves recorded call history and resolution information to a learning database, updating the system's overall learning data. This improves the accuracy of future responses.

[0452] (Example 1)

[0453] 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."

[0454] In voice-based customer support, efficiently handling customer calls and quickly connecting them to the appropriate representative is often considered difficult. Therefore, there is a need to improve customer satisfaction and streamline operations. Traditional methods often involve manual call transfers and history recording, which can be time-consuming and increase the risk of human error. Furthermore, the criteria for identifying the correct representative are often ambiguous, resulting in customers' requests not being properly understood.

[0455] 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.

[0456] In this invention, the server includes technical means for acquiring voice information and converting it into text information, technical means for analyzing the converted text information and extracting the purpose of the request, and technical means for identifying a business person with the most suitable capabilities. This enables voice inquiries to be processed quickly and accurately, and to be automatically transferred to the appropriate business person.

[0457] "Voice information" refers to information or data transmitted through voice, such as during phone calls.

[0458] "Textual information" refers to information obtained by converting audio information into text format, and is data that is stored in a format that can be analyzed.

[0459] "Technical means" refers to a technical approach, such as devices or methods, used to achieve a specific purpose or function.

[0460] A "business representative" refers to a person who possesses specific skills and knowledge and is engaged in duties such as providing services to customers or solving problems.

[0461] A "machine learning model" refers to an algorithm or method used to make predictions or classifications by analyzing data and learning patterns.

[0462] "Natural language processing technology" refers to the technology that enables computers to understand human language and analyze its meaning and structure.

[0463] "Real-time processing" refers to a process that processes input information immediately without delay after it is generated and outputs the results instantly.

[0464] This invention is a system aimed at efficiently and quickly responding to customer inquiries made by voice. When a user makes an inquiry by phone, the server receives the call and acquires voice information. The server immediately sends the voice information to the terminal in order to start streaming processing in real time. This terminal converts the voice information into text information using an API that uses general speech recognition technology (for example, an API for a voice recognition cloud service).

[0465] The converted text information is sent to the server, where it is analyzed using natural language processing technology. The server then extracts the purpose of the request from the data obtained through the analysis, understanding the content of the inquiry based on specific keywords and phrases. Accuracy is improved by utilizing generative AI models in this process.

[0466] The server uses past interaction history and newly extracted data, along with machine learning models, to identify the most suitable person to handle the call. Once the person is identified, the server automatically transfers the call to that person. This allows the user to receive a quick and appropriate response.

[0467] Once the interaction is complete, the server meticulously records the call content and solution, storing it as learning data for future use. This process helps improve the system's accuracy.

[0468] For example, if a user inquires about an issue such as "unstable network connection," the server will quickly identify the appropriate person in charge based on keywords such as "network" and "connection," and transfer the call. Furthermore, the system's operation can be verified by inputting prompts such as, "Please extract specific keywords from the voice data and show how to transfer the call to a person with the relevant skills," into the generative AI model.

[0469] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0470] Step 1:

[0471] When a user makes a call, the server receives the call. The server takes the audio information as input and begins streaming it in real time. This initial processing prepares the audio information for uninterrupted transmission to the next stage.

[0472] Step 2:

[0473] The server sends audio information to the terminal. The terminal forwards the received audio information to a speech recognition API. Specifically, the terminal uses this API to perform calculations that convert the audio information into text information. As a result, text data is generated as output.

[0474] Step 3:

[0475] The terminal sends the generated text information to the server. The server begins analyzing the received text information using natural language processing technology. During the analysis process, the server extracts keywords and phrases and obtains the data requested by the user as output.

[0476] Step 4:

[0477] The server uses the information obtained through analysis to confirm the purpose of the request as input. The server uses past response history data and a generated AI model to process the data in order to identify the most suitable person in charge of the task. This process results in output indicating the appropriate person in charge.

[0478] Step 5:

[0479] The server automatically transfers the call to the identified person in charge. This step uses the call between the identified person in charge and the user as input. By transferring the call, the server enables rapid customer response.

[0480] Step 6:

[0481] Once the interaction is complete, the server meticulously records the call content and resolution. The original call content and processing results are used as input, and this information is stored as system training data as output. This data will be used to improve future services.

[0482] (Application Example 1)

[0483] 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."

[0484] Responding quickly to suspicious activity and emergencies in residential areas and commercial facilities is crucial. However, traditional manual reporting systems have the drawback of being slow to respond to reports, making it difficult to resolve urgent issues immediately.

[0485] 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.

[0486] In this invention, the server includes means for acquiring voice information and converting it into text information, means for analyzing the converted text information and extracting the intent of the inquiry, means for identifying an expert with the most suitable capabilities based on the extracted intent, and means for analyzing suspicious activity and immediately notifying security personnel. This enables a rapid response to suspicious activity and emergencies.

[0487] "Voice information" refers to the acquisition of voice data generated by the user.

[0488] "Text information" refers to audio information converted into a string of characters.

[0489] "Analysis" is the process of processing acquired text information and extracting useful information and intent from it.

[0490] "Ability" refers to the level of specific skills and knowledge possessed by an expert.

[0491] An "expert" is a person who possesses advanced knowledge and skills in a particular field.

[0492] "Communication" is the process of exchanging information through voice or text.

[0493] "Suspicious activity" refers to actions or situations that are not normal and may pose a safety risk.

[0494] A "safety officer" is a person responsible for taking action to maintain safety in a facility or area.

[0495] A "knowledge base" is a collection of data that stores past response histories and solutions, and is used to improve systems and address issues.

[0496] The system of this invention is designed to provide security alerts quickly and effectively. Its implementation utilizes a server and user terminals. The server operates in a cloud computing environment, and the terminals are mobile devices owned by the user, such as smartphones and tablets.

[0497] When a user discovers suspicious activity, they report it using their device. Information reported via voice input is quickly converted into text using the Google Cloud Speech-to-Text API on the device. This text is sent to a server and analyzed using natural language processing techniques. Specifically, the intent of the inquiry is extracted from the text using the SpaCy library.

[0498] Subsequently, the server refers to past response history based on the extracted intent and identifies the most suitable security officer using an AI model (built using TensorFlow). This AI model evaluates the officer's capabilities, performs skill mapping, and determines the urgency associated with the suspicious activity.

[0499] The identified personnel are automatically forwarded with notifications of suspicious activity. This process enables a quick response to security issues. Furthermore, the reported information and response results are stored in a PostgreSQL database and used as a knowledge base for the future.

[0500] As a concrete example, if suspicious behavior is observed in the parking lot of a residence, the user can initiate a report using their device. When they say, "I saw a suspicious person in the parking lot," the voice is converted into text and analyzed as an attempt to identify a suspicious person. The necessary security personnel are then immediately notified.

[0501] Examples of prompt statements are as follows:

[0502] "I want to report suspicious activity in the parking lot. How do I go about reporting it?"

[0503] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0504] Step 1:

[0505] When a user discovers suspicious activity, they initiate a report using their device. The device acquires the user's voice information as input. Specifically, the user launches an application on their device and begins voice input.

[0506] Step 2:

[0507] The device sends the acquired audio information to the Google Cloud Speech-to-Text API, where it is converted into text. It receives audio information as input and generates text information as output. This text information is in the format necessary for analyzing the content of the report.

[0508] Step 3:

[0509] Text information is sent from the terminal to the server. The server uses natural language processing technology to analyze the text information and extract the intent of the query. It receives text information as input and obtains the intent of the query as output. Specifically, it uses the SpaCy library to extract important keywords from the text information.

[0510] Step 4:

[0511] The server refers to past response history based on the extracted intent and evaluates the appropriate response. An AI model (using TensorFlow) identifies the most suitable safety officer. It receives the intent of the inquiry as input and obtains the identified safety officer as output. In operation, the AI ​​model performs skill mapping and evaluates the officer's capabilities.

[0512] Step 5:

[0513] The server automatically forwards communications to the identified security officer. It receives the identified officer's information as input and sends a notification as output. Specifically, it sends a notification to the officer's mobile device or communication terminal to prompt quick confirmation and response.

[0514] Step 6:

[0515] The report content and response results are recorded in a PostgreSQL database by the server. It receives communication content and response results as input and outputs them as knowledge base data. Operationally, this information is stored in the database and used for future responses and analysis.

[0516] 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.

[0517] This invention combines a conventional inquiry handling system with an emotion engine to enable responses that take user emotions into consideration. Specifically, it acquires text data from voice data and performs analysis using natural language processing technology, while simultaneously analyzing the user's emotions using an emotion engine, and utilizing the results in the response.

[0518] When a user makes a call, the server receives the voice data and processes it in streaming format. The server then sends the voice data to an emotion engine in real time, which analyzes the user's emotions.

[0519] The audio data is converted to text on the device using the Google Cloud Speech-to-Text API. This text data is then analyzed by the server's natural language processing module to extract the user's intent and simultaneously capture the user's sentiment data.

[0520] Based on the extracted intent and emotional information of the inquiry, the server identifies the most suitable representative by referring to past interaction history and a skills database. For example, if a customer is dissatisfied, a representative with high skill in handling that specific emotion will be selected.

[0521] Once the appropriate person to handle the call is identified, the server automatically transfers the call to that person. At this time, the server also provides the person with emotional data to help them respond more appropriately.

[0522] At the end of a call, the server records the interaction history, including the content of the conversation and the user's emotional changes, and updates the system's database with this data to help improve accuracy in future interactions.

[0523] For example, if a user complains that their order was canceled while feeling angry, the emotion engine recognizes the emotion of "anger" and selects a representative with the necessary skills to handle that emotion. As a result, appropriate and considerate responses are provided quickly, leading to increased user satisfaction. In this way, an advanced customer service system incorporating emotional data is realized.

[0524] The following describes the processing flow.

[0525] Step 1:

[0526] The user makes a phone call. The server receives this call and begins capturing audio data.

[0527] Step 2:

[0528] The server transfers the received audio data to the emotion engine in real time, which analyzes the user's emotions from their voice.

[0529] Step 3:

[0530] The server simultaneously sends audio data to the device, which then uses the Google Cloud Speech-to-Text API to convert the audio into text data. This text data is then sent back to the server.

[0531] Step 4:

[0532] The server analyzes text data using natural language processing techniques to extract the user's intent. Sentimental data is also combined with this analysis.

[0533] Step 5:

[0534] The server uses extracted intent and sentiment data to refer to past interaction history and a skills database. Using AI technology, it identifies the most suitable representative for the user's inquiry and emotions.

[0535] Step 6:

[0536] The server automatically transfers the call to the selected representative. When the call is transferred, the representative is also informed of the analyzed sentiment data.

[0537] Step 7:

[0538] A representative will respond to user inquiries and resolve the issues. Users can receive prompt assistance thanks to the representative's appropriate skills.

[0539] Step 8:

[0540] After a call ends, the server records emotional information along with the call history. This data is stored in the system's learning database and used to improve the quality of future interactions.

[0541] (Example 2)

[0542] 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."

[0543] Conventional customer service systems often fail to adequately consider user emotions, making it difficult to improve user satisfaction and resolve problems quickly. Therefore, there is a need to analyze the user's emotional state from voice data and select the most suitable representative based on the results to provide more appropriate responses.

[0544] 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.

[0545] In this invention, the server includes means for acquiring voice information and converting it into text information, means for analyzing the converted text information and extracting the purpose of the inquiry, and means for analyzing the emotional state from the voice information. This enables the identification of the most suitable person to handle the inquiry based on the user's intent and further considering their emotional state, allowing for a quick and appropriate response.

[0546] "Voice information" refers to voice data transmitted by the user, which is input processed by speech recognition technology.

[0547] "Textual information" refers to text data obtained by processing and converting audio information, and is a data format used to analyze the intent of an inquiry.

[0548] "Purpose of inquiry" refers to the intentions or requests that the user wants to convey through voice information, and is information extracted through natural language processing.

[0549] "Ability" refers to the level of technical skills and knowledge an employee possesses in a specific field, based on their past service history and skills database.

[0550] A "responsible person" is an individual identified based on the user's inquiry and emotional state, whose role is to provide the most appropriate response.

[0551] "Emotional state" refers to the user's emotions and psychological state as analyzed from voice information, and is a factor considered in order to improve the quality of service.

[0552] An "information processing device" refers to the entire system used to process audio and text information and update correspondence history and learning information.

[0553] This invention is a system that processes voice information in real time and optimizes inquiry responses while considering the user's emotional state. When a user makes a phone call, the server receives the voice information. The server sends this voice information to the terminal and converts it into text information using speech recognition technology. Specifically, the terminal converts the voice information into text using the Google Cloud Speech-to-Text API.

[0554] The server analyzes the converted text information using natural language processing techniques to extract the purpose of the query. This process involves text tokenization and syntactic analysis. Furthermore, the server performs sentiment analysis on the audio information to analyze the user's emotional state. By using an emotion engine, the server determines the user's emotions (e.g., anger or joy) and uses this information in the next step.

[0555] Based on the analysis results, the server refers to past interaction history and a skills database to identify the most suitable agent. Emotional states are particularly considered, and the system is designed to select an agent with the skills to address specific emotions. The call is automatically transferred to the identified agent, and emotional information is provided simultaneously to support appropriate responses.

[0556] This system records the interaction history, including call content and emotional changes, and updates the information processing device with this information to improve the accuracy of future inquiries.

[0557] For example, when a user complains angrily that their order has been canceled, the system uses emotion analysis to determine that the user is angry, selects a representative with the appropriate skills, and responds quickly. This process increases customer satisfaction.

[0558] Examples of prompts for a generative AI model include the following:

[0559] "Please explain in detail the process of the system that uses speech recognition to optimize customer service."

[0560] "Please explain how to select personnel using an emotional engine."

[0561] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0562] Step 1:

[0563] When a user makes a call, the server receives the call. The input is the user's voice information, and the server prepares to process it in streaming format. Specifically, the server sends the voice information to the terminal in the appropriate format.

[0564] Step 2:

[0565] The device receives audio information sent from the server and converts it into text information using the Google Cloud Speech-to-Text API. The input is audio information, and the output is text information. This conversion involves data processing, such as detecting words and phrases from the audio and converting them into text format.

[0566] Step 3:

[0567] The server analyzes the text information received from the terminal using natural language processing techniques. The input is text information, and the output is the purpose of the query. Specifically, the server performs word tokenization, syntactic analysis, and semantic analysis to identify the user's intent. The purpose of the query is extracted during this process.

[0568] Step 4:

[0569] The server analyzes emotional states from voice information. The input is the voice information itself, and the output is the user's emotional state. The server uses an emotion engine to analyze the tone and speed of the voice and determine the emotion. This emotional data will be used for future support.

[0570] Step 5:

[0571] The server identifies the most suitable agent based on the extracted inquiry's purpose and sentiment information. The input is the purpose and sentiment information, and the output is the agent's information. The server refers to past interaction history and a skills database to select an agent with the appropriate skills.

[0572] Step 6:

[0573] The server automatically transfers the call to the designated person in charge, simultaneously providing sentiment information. The input is the person in charge's information and sentiment data, and the output is the transferred call. Specifically, the server connects the call line to the person in charge, improving the efficiency of support.

[0574] Step 7:

[0575] Once a call ends, the server records the call content and emotional changes, updating the database as learning information for the information processing device. The input is the call content and emotional changes, and the output is the updated response history. This record enables more accurate responses to future inquiries.

[0576] (Application Example 2)

[0577] 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."

[0578] Traditional customer service systems often fail to consider user emotions, resulting in uniform responses. This can lead to decreased customer satisfaction, highlighting the need for further improvement. Furthermore, the inability to quickly transfer inquiries to the most appropriate representatives also contributes to inefficient responses. Therefore, a system capable of flexible responses that reflect user emotions and that quickly and appropriately identifies the right representative is required.

[0579] 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.

[0580] In this invention, the server includes means for acquiring audio signals and converting them into text data, means for analyzing the converted text data and extracting the purpose of the inquiry, and means for acquiring emotional data, which includes an emotion engine for analyzing the user's emotional state. This enables flexible responses that take the user's emotions into consideration and quick transfer to the most suitable person in charge.

[0581] An "audio signal" is data obtained by electrically converting the vibrations of sound emitted from a sound source.

[0582] "Character data" refers to information where audio signals or other forms of data are represented as characters.

[0583] "Analysis" is the process of examining data in detail according to a specific purpose and extracting the necessary information.

[0584] The "purpose of the inquiry" refers to the user's intentions and requests regarding what they want from the system.

[0585] An "emotion engine" is a technology or device that analyzes and identifies emotions from a user's way of speaking and the content of their speech.

[0586] "Emotional data" refers to information that expresses a user's emotional state as a numerical value or category.

[0587] "Skills" refer to the specialized knowledge and abilities necessary for a particular task or response.

[0588] A "person in charge" refers to an individual or team responsible for performing a specific task or handling customer inquiries.

[0589] "Communication" refers to the means and protocols used to send and receive information.

[0590] A "system" is a mechanical or electronic configuration in which multiple elements are integrated and designed to achieve a specific function.

[0591] The system for implementing this invention mainly consists of three elements: a server, a terminal, and a user. The server is responsible for acquiring audio signals and converting them into text data. Specifically, the terminal uses the Google Cloud Speech-to-Text API to convert audio into text with high accuracy. The converted text data is sent to the server. The server uses the Python NLTK library as a natural language interpretation technology to analyze the text data and extract the purpose of the query. Furthermore, IBM Watson Natural Language Understanding is used to analyze the user's emotional state and acquire emotional data. This allows the server to provide flexible responses that take the user's emotions into consideration.

[0592] The server identifies the most suitable agent based on extracted purpose and sentiment data. This identification uses data learned from past interaction history. The communication is automatically forwarded to the identified agent, enabling appropriate customer service. This interaction is recorded as communication content and interaction history, and continuously updated within the system as learning information for business transactions.

[0593] As a concrete example, suppose a user contacts the system feeling anxious because "the item I ordered yesterday hasn't arrived." In this case, the server can immediately recognize this emotion and take appropriate action or provide guidance to alleviate the anxiety. Another example of a prompt message to an AI model generated using this system would be a user utterance such as, "The item I ordered yesterday hasn't arrived. Can you check on it immediately?" In this way, a system is built that supports dynamic responses in response to the user's emotions.

[0594] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0595] Step 1:

[0596] The device acquires voice input from the user through the microphone. The voice signal is the input, and the device converts this into text data in real time using the Google Cloud Speech-to-Text API. The output is data representing the conversation in text format.

[0597] Step 2:

[0598] The server receives character data sent from the terminal. This text data is the input. The server utilizes Python's NLTK library to analyze the character data using natural language interpretation techniques to identify the purpose of the user's inquiry. As a result of the data processing, the user's specific requests and desires are extracted as output.

[0599] Step 3:

[0600] The server simultaneously sends the text data to IBM Watson Natural Language Understanding for analysis by its emotion engine. This input is the text data from step 2. The emotion analysis yields the user's emotional state as output, which is represented as a category or score.

[0601] Step 4:

[0602] The server integrates the objective data from step 2 and the sentiment data from step 3 to identify the most skilled agent from the past interaction history database. This integrated data is the input. The output is information about the identified agent, which is then used to automatically select an agent.

[0603] Step 5:

[0604] The server automatically forwards communications to the selected representative. Here, the result of step 4 is the input. This forwarding ensures that user inquiries are directly connected to the representative, resulting in a quick and accurate response. The output is the trigger that allows the representative to initiate new communication with the customer.

[0605] Step 6:

[0606] The server records all communication content and response history in a database and updates it with the latest learning information for the system. The communication information with the person identified in Step 4 is the input. This update enables learning to improve the accuracy of future responses. The output is historical data of productive responses, which will serve as the basis for improving responses in the future.

[0607] 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.

[0608] 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.

[0609] 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.

[0610] [Fourth Embodiment]

[0611] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0612] 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.

[0613] 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).

[0614] 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.

[0615] 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.

[0616] 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).

[0617] 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.

[0618] 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.

[0619] 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.

[0620] 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.

[0621] 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.

[0622] 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.

[0623] 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".

[0624] This invention is a system for efficiently and quickly processing customer calls, specifically a system that performs a series of operations from acquiring and analyzing voice data to automatically transferring the call to the most suitable person and recording the call history. The following describes the embodiments for carrying out the invention.

[0625] When a user makes a call, the server receives the call and retrieves the audio data. The server then starts streaming this audio data to process it in real time.

[0626] The audio data is sent from the device to Google Cloud's Speech-to-Text API. The device uses this API to quickly convert the audio data into text data.

[0627] The server, upon receiving the text data, analyzes it using natural language processing techniques. The server extracts keywords and phrases from the text to clarify the user's intent.

[0628] Based on the extracted intent, the server refers to a database of past interaction history. The server uses AI and machine learning models to identify the person with the skills best suited to the intent. Skill mapping technology is used to evaluate the capabilities of the person in question.

[0629] Once a suitable representative is identified, the server automatically transfers the call to that representative. This process is designed to be completed in the shortest possible time from the time the user initiates the inquiry.

[0630] Once the interaction is complete, the server records the details of the call and the solution. This data is then stored as training data for future use, helping to improve the system's accuracy.

[0631] For example, if a user requests support regarding an internet connection problem, the server extracts keywords such as "internet" and "connection" from the voice. A technical support representative who has handled similar cases in the past is identified, and the call is transferred. The representative quickly resolves the user's problem, and the result is recorded. In this way, the system is configured to provide efficient customer support.

[0632] The following describes the processing flow.

[0633] Step 1:

[0634] The user makes a phone call. The server receives the call and begins streaming the audio data.

[0635] Step 2:

[0636] The server sends the audio data to the Google Cloud Speech-to-Text API and instructs the device to convert it into text data in real time.

[0637] Step 3:

[0638] The device receives the audio data and converts it into text data using the Speech-to-Text API. The converted text data is then sent to the server.

[0639] Step 4:

[0640] The server analyzes the received text data using natural language processing techniques. Through this analysis, it extracts keywords and important phrases from the text to identify the user's intent behind their inquiry.

[0641] Step 5:

[0642] Based on the identified intent, the server searches a database of past interactions and uses AI to identify the most suitable person with the appropriate skills. Past history and skill mapping assist in the decision-making process.

[0643] Step 6:

[0644] The server automatically transfers the call to the designated contact person. The server takes into account the contact person's availability and other factors to ensure the most optimal transfer.

[0645] Step 7:

[0646] The user speaks with a representative, and the problem is resolved. The server records the content of this call and the problem-solving process.

[0647] Step 8:

[0648] The server saves recorded call history and resolution information to a learning database, updating the system's overall learning data. This improves the accuracy of future responses.

[0649] (Example 1)

[0650] 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".

[0651] In voice-based customer support, efficiently handling customer calls and quickly connecting them to the appropriate representative is often considered difficult. Therefore, there is a need to improve customer satisfaction and streamline operations. Traditional methods often involve manual call transfers and history recording, which can be time-consuming and increase the risk of human error. Furthermore, the criteria for identifying the correct representative are often ambiguous, resulting in customers' requests not being properly understood.

[0652] 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.

[0653] In this invention, the server includes technical means for acquiring voice information and converting it into text information, technical means for analyzing the converted text information and extracting the purpose of the request, and technical means for identifying a business person with the most suitable capabilities. This enables voice inquiries to be processed quickly and accurately, and to be automatically transferred to the appropriate business person.

[0654] "Voice information" refers to information or data transmitted through voice, such as during phone calls.

[0655] "Textual information" refers to information obtained by converting audio information into text format, and is data that is stored in a format that can be analyzed.

[0656] "Technical means" refers to a technical approach, such as devices or methods, used to achieve a specific purpose or function.

[0657] A "business representative" refers to a person who possesses specific skills and knowledge and is engaged in duties such as providing services to customers or solving problems.

[0658] A "machine learning model" refers to an algorithm or method used to make predictions or classifications by analyzing data and learning patterns.

[0659] "Natural language processing technology" refers to the technology that enables computers to understand human language and analyze its meaning and structure.

[0660] "Real-time processing" refers to a process that processes input information immediately without delay after it is generated and outputs the results instantly.

[0661] This invention is a system aimed at efficiently and quickly responding to customer inquiries made by voice. When a user makes an inquiry by phone, the server receives the call and acquires voice information. The server immediately sends the voice information to the terminal in order to start streaming processing in real time. This terminal converts the voice information into text information using an API that uses general speech recognition technology (for example, an API for a voice recognition cloud service).

[0662] The converted text information is sent to the server, where it is analyzed using natural language processing technology. The server then extracts the purpose of the request from the data obtained through the analysis, understanding the content of the inquiry based on specific keywords and phrases. Accuracy is improved by utilizing generative AI models in this process.

[0663] The server uses past interaction history and newly extracted data, along with machine learning models, to identify the most suitable person to handle the call. Once the person is identified, the server automatically transfers the call to that person. This allows the user to receive a quick and appropriate response.

[0664] Once the interaction is complete, the server meticulously records the call content and solution, storing it as learning data for future use. This process helps improve the system's accuracy.

[0665] For example, if a user inquires about an issue such as "unstable network connection," the server will quickly identify the appropriate person in charge based on keywords such as "network" and "connection," and transfer the call. Furthermore, the system's operation can be verified by inputting prompts such as, "Please extract specific keywords from the voice data and show how to transfer the call to a person with the relevant skills," into the generative AI model.

[0666] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0667] Step 1:

[0668] When a user makes a call, the server receives the call. The server takes the audio information as input and begins streaming it in real time. This initial processing prepares the audio information for uninterrupted transmission to the next stage.

[0669] Step 2:

[0670] The server sends audio information to the terminal. The terminal forwards the received audio information to a speech recognition API. Specifically, the terminal uses this API to perform calculations that convert the audio information into text information. As a result, text data is generated as output.

[0671] Step 3:

[0672] The terminal sends the generated text information to the server. The server begins analyzing the received text information using natural language processing technology. During the analysis process, the server extracts keywords and phrases and obtains the data requested by the user as output.

[0673] Step 4:

[0674] The server uses the information obtained through analysis to confirm the purpose of the request as input. The server uses past response history data and a generated AI model to process the data in order to identify the most suitable person in charge of the task. This process results in output indicating the appropriate person in charge.

[0675] Step 5:

[0676] The server automatically transfers the call to the identified person in charge. This step uses the call between the identified person in charge and the user as input. By transferring the call, the server enables rapid customer response.

[0677] Step 6:

[0678] Once the interaction is complete, the server meticulously records the call content and resolution. The original call content and processing results are used as input, and this information is stored as system training data as output. This data will be used to improve future services.

[0679] (Application Example 1)

[0680] 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".

[0681] Responding quickly to suspicious activity and emergencies in residential areas and commercial facilities is crucial. However, traditional manual reporting systems have the drawback of being slow to respond to reports, making it difficult to resolve urgent issues immediately.

[0682] 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.

[0683] In this invention, the server includes means for acquiring voice information and converting it into text information, means for analyzing the converted text information and extracting the intent of the inquiry, means for identifying an expert with the most suitable capabilities based on the extracted intent, and means for analyzing suspicious activity and immediately notifying security personnel. This enables a rapid response to suspicious activity and emergencies.

[0684] "Voice information" refers to the acquisition of voice data generated by the user.

[0685] "Text information" refers to audio information converted into a string of characters.

[0686] "Analysis" is the process of processing acquired text information and extracting useful information and intent from it.

[0687] "Ability" refers to the level of specific skills and knowledge possessed by an expert.

[0688] An "expert" is a person who possesses advanced knowledge and skills in a particular field.

[0689] "Communication" is the process of exchanging information through voice or text.

[0690] "Suspicious activity" refers to actions or situations that are not normal and may pose a safety risk.

[0691] A "safety officer" is a person responsible for taking action to maintain safety in a facility or area.

[0692] A "knowledge base" is a collection of data that stores past response histories and solutions, and is used to improve systems and address issues.

[0693] The system of this invention is designed to provide security alerts quickly and effectively. Its implementation utilizes a server and user terminals. The server operates in a cloud computing environment, and the terminals are mobile devices owned by the user, such as smartphones and tablets.

[0694] When a user discovers suspicious activity, they report it using their device. Information reported via voice input is quickly converted into text using the Google Cloud Speech-to-Text API on the device. This text is sent to a server and analyzed using natural language processing techniques. Specifically, the intent of the inquiry is extracted from the text using the SpaCy library.

[0695] Subsequently, the server refers to past response history based on the extracted intent and identifies the most suitable security officer using an AI model (built using TensorFlow). This AI model evaluates the officer's capabilities, performs skill mapping, and determines the urgency associated with the suspicious activity.

[0696] The identified personnel are automatically forwarded with notifications of suspicious activity. This process enables a quick response to security issues. Furthermore, the reported information and response results are stored in a PostgreSQL database and used as a knowledge base for the future.

[0697] As a concrete example, if suspicious behavior is observed in the parking lot of a residence, the user can initiate a report using their device. When they say, "I saw a suspicious person in the parking lot," the voice is converted into text and analyzed as an attempt to identify a suspicious person. The necessary security personnel are then immediately notified.

[0698] Examples of prompt statements are as follows:

[0699] "I want to report suspicious activity in the parking lot. How do I go about reporting it?"

[0700] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0701] Step 1:

[0702] When a user discovers suspicious activity, they initiate a report using their device. The device acquires the user's voice information as input. Specifically, the user launches an application on their device and begins voice input.

[0703] Step 2:

[0704] The device sends the acquired audio information to the Google Cloud Speech-to-Text API, where it is converted into text. It receives audio information as input and generates text information as output. This text information is in the format necessary for analyzing the content of the report.

[0705] Step 3:

[0706] Text information is sent from the terminal to the server. The server uses natural language processing technology to analyze the text information and extract the intent of the query. It receives text information as input and obtains the intent of the query as output. Specifically, it uses the SpaCy library to extract important keywords from the text information.

[0707] Step 4:

[0708] The server refers to past response history based on the extracted intent and evaluates the appropriate response. An AI model (using TensorFlow) identifies the most suitable safety officer. It receives the intent of the inquiry as input and obtains the identified safety officer as output. In operation, the AI ​​model performs skill mapping and evaluates the officer's capabilities.

[0709] Step 5:

[0710] The server automatically forwards communications to the identified security officer. It receives the identified officer's information as input and sends a notification as output. Specifically, it sends a notification to the officer's mobile device or communication terminal to prompt quick confirmation and response.

[0711] Step 6:

[0712] The report content and response results are recorded in a PostgreSQL database by the server. It receives communication content and response results as input and outputs them as knowledge base data. Operationally, this information is stored in the database and used for future responses and analysis.

[0713] 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.

[0714] This invention combines a conventional inquiry handling system with an emotion engine to enable responses that take user emotions into consideration. Specifically, it acquires text data from voice data and performs analysis using natural language processing technology, while simultaneously analyzing the user's emotions using an emotion engine, and utilizing the results in the response.

[0715] When a user makes a call, the server receives the voice data and processes it in streaming format. The server then sends the voice data to an emotion engine in real time, which analyzes the user's emotions.

[0716] The audio data is converted to text on the device using the Google Cloud Speech-to-Text API. This text data is then analyzed by the server's natural language processing module to extract the user's intent and simultaneously capture the user's sentiment data.

[0717] Based on the extracted intent and emotional information of the inquiry, the server identifies the most suitable representative by referring to past interaction history and a skills database. For example, if a customer is dissatisfied, a representative with high skill in handling that specific emotion will be selected.

[0718] Once the appropriate person to handle the call is identified, the server automatically transfers the call to that person. At this time, the server also provides the person with emotional data to help them respond more appropriately.

[0719] At the end of a call, the server records the interaction history, including the content of the conversation and the user's emotional changes, and updates the system's database with this data to help improve accuracy in future interactions.

[0720] For example, if a user complains that their order was canceled while feeling angry, the emotion engine recognizes the emotion of "anger" and selects a representative with the necessary skills to handle that emotion. As a result, appropriate and considerate responses are provided quickly, leading to increased user satisfaction. In this way, an advanced customer service system incorporating emotional data is realized.

[0721] The following describes the processing flow.

[0722] Step 1:

[0723] The user makes a phone call. The server receives this call and begins capturing audio data.

[0724] Step 2:

[0725] The server transfers the received audio data to the emotion engine in real time, which analyzes the user's emotions from their voice.

[0726] Step 3:

[0727] The server simultaneously sends audio data to the device, which then uses the Google Cloud Speech-to-Text API to convert the audio into text data. This text data is then sent back to the server.

[0728] Step 4:

[0729] The server analyzes text data using natural language processing techniques to extract the user's intent. Sentimental data is also combined with this analysis.

[0730] Step 5:

[0731] The server uses extracted intent and sentiment data to refer to past interaction history and a skills database. Using AI technology, it identifies the most suitable representative for the user's inquiry and emotions.

[0732] Step 6:

[0733] The server automatically transfers the call to the selected representative. When the call is transferred, the representative is also informed of the analyzed sentiment data.

[0734] Step 7:

[0735] A representative will respond to user inquiries and resolve the issues. Users can receive prompt assistance thanks to the representative's appropriate skills.

[0736] Step 8:

[0737] After a call ends, the server records emotional information along with the call history. This data is stored in the system's learning database and used to improve the quality of future interactions.

[0738] (Example 2)

[0739] 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".

[0740] Conventional customer service systems often fail to adequately consider user emotions, making it difficult to improve user satisfaction and resolve problems quickly. Therefore, there is a need to analyze the user's emotional state from voice data and select the most suitable representative based on the results to provide more appropriate responses.

[0741] 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.

[0742] In this invention, the server includes means for acquiring voice information and converting it into text information, means for analyzing the converted text information and extracting the purpose of the inquiry, and means for analyzing the emotional state from the voice information. This enables the identification of the most suitable person to handle the inquiry based on the user's intent and further considering their emotional state, allowing for a quick and appropriate response.

[0743] "Voice information" refers to voice data transmitted by the user, which is input processed by speech recognition technology.

[0744] "Textual information" refers to text data obtained by processing and converting audio information, and is a data format used to analyze the intent of an inquiry.

[0745] "Purpose of inquiry" refers to the intentions or requests that the user wants to convey through voice information, and is information extracted through natural language processing.

[0746] "Ability" refers to the level of technical skills and knowledge an employee possesses in a specific field, based on their past service history and skills database.

[0747] A "responsible person" is an individual identified based on the user's inquiry and emotional state, whose role is to provide the most appropriate response.

[0748] "Emotional state" refers to the user's emotions and psychological state as analyzed from voice information, and is a factor considered in order to improve the quality of service.

[0749] An "information processing device" refers to the entire system used to process audio and text information and update correspondence history and learning information.

[0750] This invention is a system that processes voice information in real time and optimizes inquiry responses while considering the user's emotional state. When a user makes a phone call, the server receives the voice information. The server sends this voice information to the terminal and converts it into text information using speech recognition technology. Specifically, the terminal converts the voice information into text using the Google Cloud Speech-to-Text API.

[0751] The server analyzes the converted text information using natural language processing techniques to extract the purpose of the query. This process involves text tokenization and syntactic analysis. Furthermore, the server performs sentiment analysis on the audio information to analyze the user's emotional state. By using an emotion engine, the server determines the user's emotions (e.g., anger or joy) and uses this information in the next step.

[0752] Based on the analysis results, the server refers to past interaction history and a skills database to identify the most suitable agent. Emotional states are particularly considered, and the system is designed to select an agent with the skills to address specific emotions. The call is automatically transferred to the identified agent, and emotional information is provided simultaneously to support appropriate responses.

[0753] This system records the interaction history, including call content and emotional changes, and updates the information processing device with this information to improve the accuracy of future inquiries.

[0754] For example, when a user complains angrily that their order has been canceled, the system uses emotion analysis to determine that the user is angry, selects a representative with the appropriate skills, and responds quickly. This process increases customer satisfaction.

[0755] Examples of prompts for a generative AI model include the following:

[0756] "Please explain in detail the process of the system that uses speech recognition to optimize customer service."

[0757] "Please explain how to select personnel using an emotional engine."

[0758] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0759] Step 1:

[0760] When a user makes a call, the server receives the call. The input is the user's voice information, and the server prepares to process it in streaming format. Specifically, the server sends the voice information to the terminal in the appropriate format.

[0761] Step 2:

[0762] The device receives audio information sent from the server and converts it into text information using the Google Cloud Speech-to-Text API. The input is audio information, and the output is text information. This conversion involves data processing, such as detecting words and phrases from the audio and converting them into text format.

[0763] Step 3:

[0764] The server analyzes the text information received from the terminal using natural language processing techniques. The input is text information, and the output is the purpose of the query. Specifically, the server performs word tokenization, syntactic analysis, and semantic analysis to identify the user's intent. The purpose of the query is extracted during this process.

[0765] Step 4:

[0766] The server analyzes emotional states from voice information. The input is the voice information itself, and the output is the user's emotional state. The server uses an emotion engine to analyze the tone and speed of the voice and determine the emotion. This emotional data will be used for future support.

[0767] Step 5:

[0768] The server identifies the most suitable agent based on the extracted inquiry's purpose and sentiment information. The input is the purpose and sentiment information, and the output is the agent's information. The server refers to past interaction history and a skills database to select an agent with the appropriate skills.

[0769] Step 6:

[0770] The server automatically transfers the call to the designated person in charge, simultaneously providing sentiment information. The input is the person in charge's information and sentiment data, and the output is the transferred call. Specifically, the server connects the call line to the person in charge, improving the efficiency of support.

[0771] Step 7:

[0772] Once a call ends, the server records the call content and emotional changes, updating the database as learning information for the information processing device. The input is the call content and emotional changes, and the output is the updated response history. This record enables more accurate responses to future inquiries.

[0773] (Application Example 2)

[0774] 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".

[0775] Traditional customer service systems often fail to consider user emotions, resulting in uniform responses. This can lead to decreased customer satisfaction, highlighting the need for further improvement. Furthermore, the inability to quickly transfer inquiries to the most appropriate representatives also contributes to inefficient responses. Therefore, a system capable of flexible responses that reflect user emotions and that quickly and appropriately identifies the right representative is required.

[0776] 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.

[0777] In this invention, the server includes means for acquiring audio signals and converting them into text data, means for analyzing the converted text data and extracting the purpose of the inquiry, and means for acquiring emotional data, which includes an emotion engine for analyzing the user's emotional state. This enables flexible responses that take the user's emotions into consideration and quick transfer to the most suitable person in charge.

[0778] An "audio signal" is data obtained by electrically converting the vibrations of sound emitted from a sound source.

[0779] "Character data" refers to information where audio signals or other forms of data are represented as characters.

[0780] "Analysis" is the process of examining data in detail according to a specific purpose and extracting the necessary information.

[0781] The "purpose of the inquiry" refers to the user's intentions and requests regarding what they want from the system.

[0782] An "emotion engine" is a technology or device that analyzes and identifies emotions from a user's way of speaking and the content of their speech.

[0783] "Emotional data" refers to information that expresses a user's emotional state as a numerical value or category.

[0784] "Skills" refer to the specialized knowledge and abilities necessary for a particular task or response.

[0785] A "person in charge" refers to an individual or team responsible for performing a specific task or handling customer inquiries.

[0786] "Communication" refers to the means and protocols used to send and receive information.

[0787] A "system" is a mechanical or electronic configuration in which multiple elements are integrated and designed to achieve a specific function.

[0788] The system for implementing this invention mainly consists of three elements: a server, a terminal, and a user. The server is responsible for acquiring audio signals and converting them into text data. Specifically, the terminal uses the Google Cloud Speech-to-Text API to convert audio into text with high accuracy. The converted text data is sent to the server. The server uses the Python NLTK library as a natural language interpretation technology to analyze the text data and extract the purpose of the query. Furthermore, IBM Watson Natural Language Understanding is used to analyze the user's emotional state and acquire emotional data. This allows the server to provide flexible responses that take the user's emotions into consideration.

[0789] The server identifies the most suitable agent based on extracted purpose and sentiment data. This identification uses data learned from past interaction history. The communication is automatically forwarded to the identified agent, enabling appropriate customer service. This interaction is recorded as communication content and interaction history, and continuously updated within the system as learning information for business transactions.

[0790] As a concrete example, suppose a user contacts the system feeling anxious because "the item I ordered yesterday hasn't arrived." In this case, the server can immediately recognize this emotion and take appropriate action or provide guidance to alleviate the anxiety. Another example of a prompt message to an AI model generated using this system would be a user utterance such as, "The item I ordered yesterday hasn't arrived. Can you check on it immediately?" In this way, a system is built that supports dynamic responses in response to the user's emotions.

[0791] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0792] Step 1:

[0793] The device acquires voice input from the user through the microphone. The voice signal is the input, and the device converts this into text data in real time using the Google Cloud Speech-to-Text API. The output is data representing the conversation in text format.

[0794] Step 2:

[0795] The server receives character data sent from the terminal. This text data is the input. The server utilizes Python's NLTK library to analyze the character data using natural language interpretation techniques to identify the purpose of the user's inquiry. As a result of the data processing, the user's specific requests and desires are extracted as output.

[0796] Step 3:

[0797] The server simultaneously sends the text data to IBM Watson Natural Language Understanding for analysis by its emotion engine. This input is the text data from step 2. The emotion analysis yields the user's emotional state as output, which is represented as a category or score.

[0798] Step 4:

[0799] The server integrates the objective data from step 2 and the sentiment data from step 3 to identify the most skilled agent from the past interaction history database. This integrated data is the input. The output is information about the identified agent, which is then used to automatically select an agent.

[0800] Step 5:

[0801] The server automatically forwards communications to the selected representative. Here, the result of step 4 is the input. This forwarding ensures that user inquiries are directly connected to the representative, resulting in a quick and accurate response. The output is the trigger that allows the representative to initiate new communication with the customer.

[0802] Step 6:

[0803] The server records all communication content and response history in a database and updates it with the latest learning information for the system. The communication information with the person identified in Step 4 is the input. This update enables learning to improve the accuracy of future responses. The output is historical data of productive responses, which will serve as the basis for improving responses in the future.

[0804] 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.

[0805] 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.

[0806] 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.

[0807] 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.

[0808] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. In the upper and lower directions of the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. Also, the upper side of the concentric circles is where "pleasant" emotions are located, and the lower side is where "unpleasant" emotions are located. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0809] 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.

[0810] 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.

[0811] 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.

[0812] 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."

[0813] 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.

[0814] 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.

[0815] 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.

[0816] 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.

[0817] 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.

[0818] 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.

[0819] 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.

[0820] 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.

[0821] 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.

[0822] 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.

[0823] 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.

[0824] 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.

[0825] The following is further disclosed regarding the embodiments described above.

[0826] (Claim 1)

[0827] A means of acquiring audio data and converting it into text data,

[0828] A means of analyzing the converted text data and extracting the intent of the inquiry,

[0829] A means of identifying the person with the most suitable skills based on the extracted intent,

[0830] A means of automatically transferring calls to a designated person,

[0831] A system that includes means for recording call content and response history and updating it as system learning data.

[0832] (Claim 2)

[0833] The system according to claim 1, which extracts the intent of a query from text data using natural language processing technology.

[0834] (Claim 3)

[0835] The system according to claim 1, which maps the skills of personnel based on past interaction history and predicts the most suitable personnel.

[0836] "Example 1"

[0837] (Claim 1)

[0838] Technical means for acquiring audio information and converting it into text information,

[0839] Technical means for analyzing the converted character information and extracting the purpose of the request,

[0840] A technical means for identifying the most suitable personnel with the necessary skills based on the extracted objectives,

[0841] A technical means for automatically forwarding calls to a designated person in charge of business operations,

[0842] A technical means for recording call content and work history and updating it as learning information for the system,

[0843] A technology for processing audio information in real time,

[0844] Technical means of using machine learning models to predict the optimal person to perform the task,

[0845] A system that includes this.

[0846] (Claim 2)

[0847] The system according to claim 1, which extracts the purpose of a request from textual information using natural language processing technology.

[0848] (Claim 3)

[0849] The system according to claim 1, which maps the capabilities of task managers from past work history and uses a machine learning model to predict the most suitable task manager.

[0850] "Application Example 1"

[0851] (Claim 1)

[0852] A means of acquiring audio information and converting it into text information,

[0853] A means of analyzing the converted text information and extracting the intent of the inquiry,

[0854] A means of identifying experts with the most suitable capabilities based on the extracted intent,

[0855] A means of automatically forwarding communications to designated specialists,

[0856] A means of recording communication content and response history, and updating it as a knowledge base,

[0857] A means to analyze suspicious activity and immediately notify security personnel,

[0858] A system that includes this.

[0859] (Claim 2)

[0860] The system according to claim 1, which uses natural language processing technology to extract the intent of an inquiry from text information and identify suspicious activity.

[0861] (Claim 3)

[0862] The system according to claim 1, which maps the capabilities of experts based on past response history, predicts the most suitable expert, and provides notification according to the level of urgency.

[0863] "Example 2 of combining an emotion engine"

[0864] (Claim 1)

[0865] A means of acquiring audio information and converting it into text information,

[0866] A means for analyzing the converted character information and extracting the purpose of the query,

[0867] A means of identifying the person with the most suitable capabilities based on the extracted objectives,

[0868] A means of automatically transferring calls to a designated person,

[0869] Methods for analyzing emotional states from audio information,

[0870] A means to optimize the identification of personnel based on emotional state,

[0871] A system that includes means for recording the history of interactions, including call content and emotional changes, and updating it as learning information for an information processing device.

[0872] (Claim 2)

[0873] The system according to claim 1, which uses natural language processing technology to extract the purpose of a query from textual information and uses sentiment analysis technology to determine the user's emotional state.

[0874] (Claim 3)

[0875] The system according to claim 1, which maps the capabilities of an employee based on past interaction history and emotional data, and predicts the most suitable employee.

[0876] "Application example 2 when combining with an emotional engine"

[0877] (Claim 1)

[0878] A means for acquiring audio signals and converting them into text data,

[0879] A means of analyzing the converted character data and extracting the purpose of the query,

[0880] It includes an emotion engine for analyzing the user's emotional state, and means for acquiring emotional data.

[0881] A means of identifying personnel with the most suitable skills based on extracted purpose and sentiment data,

[0882] A means of automatically forwarding communications to a designated person in charge,

[0883] A system that includes means for recording communication content and response history, and updating this information as system learning data.

[0884] (Claim 2)

[0885] The system according to claim 1, which extracts the purpose of a query from text data using natural language interpretation technology and obtains the user's emotions using sentiment analysis technology.

[0886] (Claim 3)

[0887] The system according to claim 1, which maps the skills of personnel based on past interaction history and predicts the most suitable personnel, taking into account emotional data. [Explanation of Symbols]

[0888] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of acquiring audio data and converting it into text data, A means of analyzing the converted text data and extracting the intent of the inquiry, A means of identifying the person with the most suitable skills based on the extracted intent, A means of automatically transferring calls to a designated person, A system that includes means for recording call content and response history and updating it as system learning data.

2. The system according to claim 1, which extracts the intent of a query from text data using natural language processing technology.

3. The system according to claim 1, which maps the skills of personnel based on past interaction history and predicts the most suitable personnel.

Images