system

Abstract

Provide a system. A means for recording audio data; A means for converting the recorded voice data into text data; means for transmitting text data and contract information to a server; a means for using generative artificial intelligence to analyze text data; means for generating advice based on the analysis results; means for converting the generated advice into audio data; means for transmitting advice and voice data to the terminal; Means for receiving, displaying and playing advice and audio data at a terminal A system including:

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Currently, there is a lack of resources to effectively train and guide individual crew members in sales and marketing. Training methods such as group training and role-playing do not provide sufficient feedback to individual crew members, which is one of the factors that hinders the improvement of customer service skills. An effective system is needed to solve this problem and improve crew success rates. [Means for solving the problem]

[0005] The present invention records user customer service behavior by providing a means for recording voice data, a means for converting the recorded voice data into text data, and a means for transmitting the text data and sales information to a server. The system also provides a means for analyzing the text data using generative artificial intelligence on the server side, generating advice based on the results, and converting the generated advice into voice data. The system further provides a means for transmitting the advice and voice data to a terminal, and receiving, displaying, and playing them back on the terminal. By using a data analysis means for comparing and analyzing data from across the country and a neural network for generating advice and voice data, it is possible to provide optimal training and guidance to individual crew members. This can improve each crew member's customer service skills and increase the sales success rate.

[0006] "Means for recording voice data" refers to devices or functions that allow users to record their own customer service or sales talk.

[0007] "Means for converting recorded audio data into text data" refers to speech recognition technology or software for transcribing recorded audio files and converting them into text data.

[0008] "Means for transmitting text data and transaction information to a server" refers to a transmission function for uploading the generated text data and transaction information to a server via an internet connection.

[0009] "Means using generative artificial intelligence" refers to artificial intelligence techniques, in particular generative models (e.g., neural networks), that are used to analyze received text data and generate optimal advice.

[0010] "Means for generating advice based on analysis results" refers to technologies and systems that automatically generate specific feedback and advice for improving customer service based on the results of text data analyzed by generative artificial intelligence.

[0011] The "means for converting advice into voice data" refers to a system or software for converting the generated text advice into voice data using voice synthesis technology.

[0012] "Means for transmitting advice and voice data to a terminal" refers to communication technology and network functions for transmitting the generated advice and its voice data to a user terminal.

[0013] "Means for receiving, displaying, and playing advice and audio data at a terminal" refers to functions or applications that allow a user terminal to receive advice and audio data sent from a server and display or play it.

[0014] "Data analysis tools" refers to data analysis techniques and software used to compare and analyze data collected from crews across the country and provide optimal advice to individual crew members.

[0015] A "neural network" is a type of artificial intelligence that is an algorithm that learns from large amounts of data and performs pattern recognition and prediction. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6]FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0020] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 1, a 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.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the 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.

[0030] 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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] The present invention is a voice recording and analysis system for improving the customer service skills of crew members. With this system, users can record their own customer service, send the recording data to a server, and receive appropriate feedback, allowing them to receive personalized guidance.

[0038] Overall system configuration

[0039] This system consists of a device that records the user's customer service, a server that analyzes the recorded data, and generative artificial intelligence to generate and provide feedback.

[0040] User operations

[0041] The user uses their smartphone, tablet, or other device to launch an application to record the customer service interaction. They tap the record button to start recording the interaction, and when they're done, they tap the stop recording button. They then name and save the recorded audio file, select the audio file within the app, and upload it to the server. At this time, they also enter information on whether the transaction was successful or not.

[0042] Terminal handling

[0043] The terminal uses a voice recognition engine (such as Google® Speech-to-Text) to convert the recorded voice file into text data, transcribes the voice file, and sends the generated text data and transaction information to the server.

[0044] Server Processing

[0045] The server analyzes the received text data and sales information. The analysis is performed using generative AI, and customer service skills are evaluated based on the content of the text data. The generative AI learns from a large amount of crew data and is able to generate optimal feedback.

[0046] Generate feedback

[0047] The server generates advice and suggestions for improving customer service based on the analysis results. For example, if the generative AI finds an area for improvement such as "You need to ask customers more specifically about their requests," it can generate advice such as "You should try to ask customers more specific questions."

[0048] Conversion to audio data

[0049] The generated advice is then converted into voice data using speech synthesis technology. This voice data is sent to the device and can be played back and listened to by the user. For example, specific advice such as "Try to listen more slowly when the customer speaks" can be generated using speech synthesis and provided to the user.

[0050] Receive feedback on your device

[0051] The device receives the advice and audio data sent from the server and displays and plays it back within the app. By checking this feedback and playing it back aloud, users can understand where they need to improve and use it for their next customer service encounter.

[0052] As a concrete example, if user Tanaka records a sales conversation, the audio data is converted into text such as "Hello, how can I help you today?" Tanaka's smartphone sends the text data and the sales contract information to the server, which then generates advice such as "You should listen more slowly to what the customer is saying." This advice is converted into audio data and sent to Tanaka's smartphone. Tanaka can check the advice through the app and play it back as audio to improve his customer service skills.

[0053] This system allows us to provide optimal feedback to individual crew members and improve their customer service skills. By collecting and comparing data on a nationwide scale, we can provide more accurate advice and expect to improve our success rate.

[0054] The processing flow will be explained below.

[0055] Step 1:

[0056] User

[0057] The user launches the app and starts recording the customer service. Specifically, the user taps the "Start Recording" button and starts voice input.

[0058] Step 2:

[0059] User

[0060] Once the customer service is finished, the user taps the "Stop Recording" button to end the recording. Then, the recording file is saved with a name, for example, "20231005_Customer Service Recording."

[0061] Step 3:

[0062] User

[0063] Select the recorded file in the app and enter the transaction information (e.g., "Sold" or "Not Sold" and any comments). Next, tap the upload button to send the audio file and transaction information to the server.

[0064] Step 4:

[0065] Terminal

[0066] The device receives the recorded audio file and converts it into text data by calling a speech recognition engine (such as Google Speech-to-Text). The recognized text data is generated.

[0067] Step 5:

[0068] Terminal

[0069] The converted text data and the contract information are sent to the server. If the transmission is successful, the user is notified within the app.

[0070] Step 6:

[0071] server

[0072] The server analyzes the received text data and contract information. Using generative artificial intelligence (e.g., a deep learning model), the received data is analyzed to evaluate customer service and identify areas for improvement.

[0073] Step 7:

[0074] server

[0075] Based on the analysis results, the system generates optimal advice, such as "You need to show more empathy for your customers."

[0076] Step 8:

[0077] server

[0078] The generated advice is passed to a speech synthesis engine and converted into voice data, such as "It is important to show empathy to customers."

[0079] Step 9:

[0080] server

[0081] The generated advice and audio data are sent to the device. If the transfer is successful, the user is notified within the app.

[0082] Step 10:

[0083] Terminal

[0084] The device receives the advice and audio data sent from the server, displays it so that the user can check the feedback within the app, and provides an audio playback function.

[0085] Step 11:

[0086] User

[0087] Users can check the feedback in the app and receive specific advice by playing back the audio data. For example, they can receive advice such as "When listening to a customer, take a pause before responding," which they can use to improve their next customer service experience.

[0088] Through this series of steps, users can record their own customer service interactions and receive accurate feedback through AI analysis, enabling them to provide tailored training and guidance to individual crew members and improve their customer service skills.

[0089] Example 1

[0090] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0091] Using voice data to improve customer service skills has been difficult to do efficiently with conventional approaches. Providing timely and accurate individual feedback is particularly important. Furthermore, there is a lack of data for nationwide comparative analysis of customer service quality, and no standard method for improving customer service skills has been established.

[0092] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0093] In this invention, the server includes means for recording voice data, means for converting the recorded voice data into text data, means for transmitting the text data and contract information to the server, means for using generative artificial intelligence to analyze the text data, means for generating advice based on the analysis results, means for converting the generated advice into voice data, means for transmitting the advice and voice data to a terminal, and means for receiving, displaying, and playing the advice and voice data on the terminal. This allows users to efficiently receive individual feedback and improve their customer service skills. Furthermore, analysis by the generative artificial intelligence allows data to be compared and analyzed on a nationwide scale, establishing a standard method for improving customer service skills.

[0094] "Voice data" is digital data that records the user's speech or voice.

[0095] "Recording" is the operation or process of storing audio data in digital form.

[0096] "Text data" refers to character string data obtained by transcribing voice data.

[0097] "Deal information" is information indicating whether the user's customer service resulted in a deal or not.

[0098] A "server" is a computer system that receives, analyzes, and transmits data over a network.

[0099] "Generative artificial intelligence" is an AI technology that learns using large amounts of data, analyzes text data, and generates feedback.

[0100] "Analyzing" is the process of analyzing the content of text data and extracting important elements.

[0101] "Feedback" refers to advice and information on improvements provided to users based on the analysis results.

[0102] "Speech synthesis" is a technology that converts text data into voice data.

[0103] A "terminal" is a device that is directly operated by a user, such as a smartphone or tablet.

[0104] "Reception" refers to an operation in which a terminal acquires data from a server or the like.

[0105] "Display" refers to the ability to show text and graphical information to the user on the terminal.

[0106] "Playback" is a function that converts voice data into an acoustic signal on the terminal and allows the user to hear it.

[0107] The present invention is a voice recording and analysis system for improving the customer service skills of crew members. The configuration and specific operation of this system will be described below.

[0108] Overall system configuration

[0109] This system includes a terminal that records the user's voice during customer service, a server that analyzes the recorded data, and generative artificial intelligence to generate and provide feedback.

[0110] User operations

[0111] The user launches the voice recording application on their smartphone or tablet. They tap the record button to record the customer service voice, and when they're done, they tap the stop recording button. They then name and save the audio file, and upload it to the server within the app. At this time, they also enter deal information such as whether the deal was closed or not.

[0112] Terminal handling

[0113] The device converts the saved voice file into text data using a voice recognition engine (e.g., Google Speech-to-Text). For example, the recorded voice data "Hello, how can I help you today?" is converted into text data. The generated text data and the contract information are then sent to the server.

[0114] Server Processing

[0115] The server analyzes the received text data and the contract information. Generative artificial intelligence (such as ChatGPT (registered trademark)) is used for the analysis. The server evaluates customer service skills based on the text data and generates an analysis result. For example, the analysis result may be, "You need to listen more specifically to the customer's request."

[0116] Generate feedback

[0117] Based on the analysis results, the server generates advice and suggestions for improving customer service. For example, it generates feedback such as, "It would be good if you try to ask customers more specific questions." This feedback is converted into audio data using a speech synthesis engine (for example, Google Text-to-Speech). Specifically, the advice text is sent to a speech synthesis API, and the generated audio file is obtained.

[0118] Receive feedback on your device

[0119] The device receives the advice and audio data sent from the server and displays and plays it back within the app. The user can check this feedback and understand specific areas for improvement. For example, the user may receive audio feedback through the app such as, "Please try to listen to the customer more slowly."

[0120] Specific examples

[0121] When user Tanaka records a sales conversation, the audio data is converted into text, such as "Hello, how can I help you today?" Tanaka's smartphone sends the text data and the closing information to the server, which then generates advice such as "You should listen more slowly to what the customer is saying." This advice is converted into audio data and sent to Tanaka's smartphone. Tanaka can review the advice through the app and play it back as audio to improve his customer service skills.

[0122] Prompt Sentence Examples

[0123] "I recorded my customer service. Please transcribe this audio and give me feedback on my customer service skills."

[0124] By using this system, users can efficiently receive individual feedback and improve their customer service skills. Furthermore, by collecting and comparing data on a national scale, it is expected that more accurate advice can be provided and customer service skills can be standardized and improved overall.

[0125] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0126] Step 1:

[0127] The user starts the application on their smartphone or tablet and taps the record button to record the voice of the customer service. The input is the user's voice while the customer service is being served, and the output is the recorded voice data. For example, the user presses the "Start Recording" button and speaks the contents of the customer service.

[0128] Step 2:

[0129] When the user taps the stop recording button, the device saves the recorded audio data to local storage. The input is the recorded audio data, and the output is the saved audio file. The user names the file. For example, the audio file is saved as "Sales Talk_20231001".

[0130] Step 3:

[0131] The device converts the saved audio file into text data using a speech recognition engine (e.g., Google Speech-to-Text). The input is the saved audio file, and the output is the generated text data. For example, the recorded "Hello, how can I help you today?" is converted into text data.

[0132] Step 4:

[0133] The terminal sends the generated text data and the contract information together to the server. The input is the text data and the contract information, and the output is a POST request to the server. For example, the text data and the contract information "unconcluded" are sent to the server.

[0134] Step 5:

[0135] The server analyzes the received text data and contract information. This analysis is performed using generative artificial intelligence (for example, ChatGPT). The input is the text data and contract information, and the output is the analysis result. For example, the analysis result may be, "We need to listen more specifically to the customer's requests."

[0136] Step 6:

[0137] Based on the analysis results, the server uses generative artificial intelligence to generate improvements and advice for customer service. The input is the analysis results, and the output is the generated feedback text. For example, it generates advice such as, "It would be a good idea to try to ask customers more specific questions."

[0138] Step 7:

[0139] The server converts the generated feedback into voice data using a speech synthesis engine (e.g., Google Text-to-Speech). The input is the feedback text, and the output is voice data. For example, voice data such as "Please try to listen more slowly to what the customer is saying" is generated.

[0140] Step 8:

[0141] The terminal receives the voice data and feedback text sent from the server. The input is the response data from the server, and the output is the received voice data and feedback text. For example, the terminal receives feedback from the server.

[0142] Step 9:

[0143] The user checks the feedback text and audio displayed in the app and plays it back. The input is the received audio data and feedback text, and the output is the recognized feedback. For example, the user checks and plays back advice such as "Try to listen more slowly to what the customer is saying."

[0144] (Application example 1)

[0145] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0146] In the modern hospitality industry, individual feedback is essential for store crew members to effectively improve their customer service skills. However, there are currently few ways to efficiently provide such feedback in daily work. Furthermore, there is no established system for obtaining consistent, high-quality feedback, which slows down crew members' growth.

[0147] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0148] In this invention, the server includes: [means for generating advice based on the analysis results using generative artificial intelligence]; [means for playing back the generated advice as advice using voice synthesis]; and [means including data analysis means for comparing and analyzing data from across the country.] This enables [crew members to receive consistent, high-quality feedback to efficiently and effectively improve their customer service skills].

[0149] "Audio data" refers to data that records the audio information uttered by the crew when serving customers.

[0150] "Text data" refers to digital text data that has been transcribed from voice data using a voice recognition engine.

[0151] "Contract information" refers to information regarding whether or not a contract has been concluded and the details of the contract obtained through customer service.

[0152] "Generative AI" is an AI technology that learns from large amounts of data and performs analysis and generates feedback according to specific purposes.

[0153] "Speech synthesis" is a technology that converts text data into voice data.

[0154] A "terminal" is a digital device used by a user, such as a smartphone, tablet, or computer.

[0155] The "data analysis means" is a technology that analyzes the received text data and contract information and generates various statistical data.

[0156] "Analysis results" refer to the evaluations and insights that generative artificial intelligence obtains by analyzing text data.

[0157] "Advice" refers to specific suggestions and guidance generated based on the analysis results to improve the crew's customer service skills.

[0158] The present invention is a voice recording and analysis system for crew members to improve their customer service skills. This system consists of the following main hardware and software:

[0159] Hardware usage example

[0160] 1. Device: A smartphone, tablet, or computer. These devices are used by crew members to record customer service audio and receive feedback.

[0161] 2. Server: A powerful computing device that analyzes data and generates feedback.

[0162] Software usage examples

[0163] 1. Speech recognition engine: Uses the Google Cloud Speech-to-Text API to convert recorded voice data into text data.

[0164] 2. Generative Artificial Intelligence: Using OpenAI (registered trademark) GPT-3 (registered trademark) or similar AI models, we analyze text data and generate appropriate advice.

[0165] 3. Speech synthesis engine: Uses the Google Text-to-Speech API to convert text-based advice into audio data.

[0166] 4. Server-side framework: A framework for managing APIs and sending and receiving data, such as Flask.

[0167] Program processing flow

[0168] 1. Voice recording and transcription:

[0169] The user starts a voice recording application on the device and records the conversation during the customer service session.

[0170] The device converts the recorded audio data into text data using the Google Cloud Speech-to-Text API.

[0171] 2. Data transmission and analysis:

[0172] The converted text data and the contract information are sent to a server via the Internet.

[0173] The server analyzes the received text data using OpenAI GPT-3 generative artificial intelligence.

[0174] 3. Feedback generation and submission:

[0175] Generative AI generates feedback based on the analysis, which is then converted into audio data using the Google Text-to-Speech API.

[0176] The server transmits the generated feedback and voice data to the terminal.

[0177] 4. Receiving and Viewing Feedback:

[0178] The device displays and plays the received feedback and audio data within the application.

[0179] The user reads the displayed feedback and understands specific improvements through audio playback.

[0180] Explanation through concrete examples

[0181] For example, one of the crew members records a customer service response, "Hello, how can I help you today?" This voice data is converted into text data, and a specific prompt, "Generate feedback for this response: Hello, how can I help you today?", is sent to the server. The generative AI analyzes the data and generates feedback such as, "You should listen to the customer more slowly." This feedback is converted into audio data using the Google Text-to-Speech API and sent to the user's device. The user can review this feedback through the application and improve their customer service skills by playing the audio back.

[0182] This allows users to consistently receive high-quality feedback to effectively improve their customer service skills.

[0183] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0184] Step 1:

[0185] The user starts a voice recording application on the device and records the conversation during the customer service session.

[0186] Input: Crew member's voice

[0187] Output: Recorded audio data

[0188] Specific operation: The user taps the "Start Recording" button on the recording app to record the customer conversation. When recording is finished, the user taps the "Stop Recording" button to save the audio data.

[0189] Step 2:

[0190] The device converts the recorded audio data into text data using the Google Cloud Speech-to-Text API.

[0191] Input: Recorded audio data

[0192] Output: Converted text data

[0193] Specific operation: Sends recorded audio data to the Google Cloud Speech-to-Text API, performs speech recognition, and receives text data returned by the API.

[0194] Step 3:

[0195] The terminal transmits the converted text data and the transaction information to the server.

[0196] Input: Text data and contract information

[0197] Output: Data sent to the server

[0198] Specific operation: The user enters the transaction information into the app, and the device sends the text data and transaction information together to the server as an HTTP request.

[0199] Step 4:

[0200] The server analyzes the received text data using generative artificial intelligence.

[0201] Input: Received text data

[0202] Output: Analysis results and feedback text

[0203] Specific operation: The server calls OpenAI GPT-3, inputs the prompt "Generate feedback for this customer service: [text data]", and obtains the analysis results.

[0204] Step 5:

[0205] The server converts the generated feedback into audio data using the Google Text-to-Speech API.

[0206] Input: Feedback text

[0207] Output: Generated feedback audio data

[0208] Specific operation: The parsed feedback text is sent to the Google Text-to-Speech API to generate audio data.

[0209] Step 6:

[0210] The server transmits the generated feedback and voice data to the terminal.

[0211] Input: Feedback text and audio data

[0212] Output: Data sent to the terminal

[0213] Specific operation: The server sends the generated feedback text and audio data to the device as an HTTP response.

[0214] Step 7:

[0215] The device displays and plays the received feedback and audio data within the application.

[0216] Input: Received feedback text and audio data

[0217] Output: User feedback viewing and playback

[0218] Specific behavior: The device displays the feedback text on the screen and provides a button to play the audio data. When the user taps the button, the audio feedback is played.

[0219] This allows users to record themselves, have the audio data analyzed, and receive feedback to improve their customer service skills.

[0220] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0221] The present invention is a voice recording, analysis, and feedback system for improving crew customer service skills, combined with user emotion recognition, which allows for more personalized advice based on the user's emotions.

[0222] Overall system configuration

[0223] This system consists of a device that records the user's customer service, a server that analyzes the recorded data, a generative artificial intelligence to generate and provide feedback, and an emotion engine that recognizes the user's emotions.

[0224] User operations

[0225] The user uses their smartphone, tablet, or other device to launch an application to record the customer service interaction. They tap the record button to start recording the interaction, and when they're done, they tap the stop recording button. They then name and save the recorded audio file, select the audio file within the app, and upload it to the server. At this time, they also enter information on whether the transaction was successful or not.

[0226] Terminal handling

[0227] The device uses a speech recognition engine (such as Google Speech-to-Text) to convert the recorded audio file into text data, generating recognized text data. It also uses an emotion engine to detect the user's emotions from the recorded audio and text data. For example, it can recognize emotions such as "joy," "anger," and "sadness" by analyzing the user's tone of voice and phrasing.

[0228] Server Processing

[0229] The server analyzes the received text data, sales information, and emotional information. Generative AI is used for the analysis, and customer service skills are evaluated based on the content of the text data and the user's emotions. The generative AI learns from a large amount of crew data and is able to generate optimal feedback.

[0230] Generate feedback

[0231] Based on the analysis results, the server generates optimal advice that takes into account emotional information. For example, if the user expresses anger, the server can generate specific advice such as "respond in a calm tone."

[0232] Conversion to audio data

[0233] The generated advice is then converted into voice data using speech synthesis technology. This voice data is sent to the device and can be played back and listened to by the user. For example, specific advice such as "Try to listen more slowly when the customer speaks" can be generated using speech synthesis and provided to the user.

[0234] Receive feedback on your device

[0235] The device receives the advice and audio data sent from the server and displays and plays it back within the app. By checking this feedback and playing it back aloud, users can understand where they need to improve and use it for their next customer service encounter.

[0236] As a concrete example, if user Tanaka records a sales pitch, the audio data is converted into text such as "Hello, how can I help you today?", and at the same time, the emotion engine recognizes Tanaka's emotion as "slightly nervous." Tanaka's smartphone sends the text data, emotional information, and sales information to the server, which then generates advice such as "Take a more relaxed attitude toward customers." This advice is converted into audio data and sent to Tanaka's smartphone. Tanaka can check the advice through the app, play back the audio, and improve on the "relaxed conversation with customers" aspect, which can be used for the next customer service encounter.

[0237] This system allows users to understand their own emotional state while improving their customer service skills, and makes it possible to provide optimized training and guidance to individual crew members. By collecting and comparing data on a national scale, it is expected that more accurate advice can be provided, leading to an improved closing rate.

[0238] The processing flow will be explained below.

[0239] Step 1:

[0240] User

[0241] The user launches the app and starts recording the conversation. Specifically, the user taps the "Start Recording" button to record the conversation.

[0242] Step 2:

[0243] User

[0244] Once the customer service is finished, the user taps the "Stop Recording" button to end the recording. The recording file is saved with a name. For example, it can be saved as "20231005_Customer Service Recording".

[0245] Step 3:

[0246] User

[0247] Select the recorded audio file in the app and enter the deal information (e.g., "Sold" or "Not Sold"), then tap the upload button to send the audio file and the deal information to the server.

[0248] Step 4:

[0249] Terminal

[0250] The device receives the recorded audio file and calls a speech recognition engine (such as Google Speech-to-Text) to convert the audio file into text data, which is then stored on the device.

[0251] Step 5:

[0252] Terminal

[0253] The recorded voice file is passed to the emotion engine, which analyzes the user's emotions. The emotion engine analyzes the user's tone of voice and vocabulary to identify emotions such as "joy," "anger," and "sadness."

[0254] Step 6:

[0255] Terminal

[0256] The converted text data, the recognized emotion information, and the transaction information are sent to the server. The app notifies you whether the transmission was successful or not.

[0257] Step 7:

[0258] server

[0259] The server analyzes the received text data, sentiment information, and sales information. A generative artificial intelligence (AI model) analyzes this data and identifies areas for improvement, such as "listening more specifically to what the customer is saying."

[0260] Step 8:

[0261] server

[0262] Based on the analysis results, the system generates optimal advice, taking emotional information into account, such as "Try to maintain a relaxed atmosphere when interacting with customers."

[0263] Step 9:

[0264] server

[0265] The generated advice is passed to a speech synthesis engine and converted into voice data. For example, voice data such as "Try to listen more carefully to what the customer is saying" is generated.

[0266] Step 10:

[0267] server

[0268] The generated advice and its audio data are sent to the device. The server checks whether the transmission was successful.

[0269] Step 11:

[0270] Terminal

[0271] The device receives the advice and audio data sent from the server and makes them available for display and playback within the app. Specifically, the text-format advice is displayed and the audio-format advice is played back.

[0272] Step 12:

[0273] User

[0274] Review the feedback provided by the user within the app. Play back the audio data to understand areas for improvement. For example, take the advice "Take more time to pause when responding to customers" into consideration and use it for your next customer service encounter.

[0275] Through these processing steps, users can record their own customer service interactions, undergo detailed analysis including sentiment analysis, and receive accurate and personalized feedback. This series of processes enables optimized training and guidance for individual crew members, aiming to improve their customer service skills.

[0276] Example 2

[0277] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0278] In customer service, voice recording, analysis, and feedback are necessary to improve the customer service skills of crew members, and more personalized advice is required by combining it with emotion recognition functions. It is also important to collect and compare data on a national scale to provide more accurate feedback and improve the closing rate.

[0279] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: [means for recording voice data]; [means for converting the recorded voice data into text data]; [means for using an emotion recognition engine to detect emotions from the voice data and the converted text data]; [means for transmitting the text data, contract information, and emotion information to the server]; [means for using generative artificial intelligence to analyze the text data and emotion information]; [means for generating advice based on the analysis results]; [means for converting the generated advice into voice data]; [means for transmitting the advice and voice data to the terminal]; and [means for receiving, displaying, and playing the advice and voice data at the terminal]. This makes it possible to receive appropriate feedback while understanding the user's emotional state and improve customer service skills.

[0280] "Audio data" is data that represents in digital form the audio recorded by a user using a terminal.

[0281] "Text data" refers to data obtained by converting voice data into text format using a voice recognition engine.

[0282] An "emotion recognition engine" is software that analyzes a user's tone of voice and vocabulary from voice and text data to detect emotions.

[0283] "Generative AI" is an AI technology that learns from past data and generates feedback based on the analysis results.

[0284] "Feedback" refers to advice for improvement based on the user's customer service experience and emotional state.

[0285] A "voice recognition engine" is software that analyzes voice data and converts it into corresponding character data (text data).

[0286] "Speech synthesis technology" is a technology that analyzes text data and generates its contents as voice data.

[0287] "Device" means a device (such as a smartphone or tablet) for recording, storing, and transmitting audio data, and for receiving and playing feedback.

[0288] A "server" is a computing system that analyzes various types of data (voice data, text data, emotional information), generates feedback, and manages communication with terminals.

[0289] "Advice" refers to instructions and suggestions for improvement generated based on customer service content and emotional data analyzed by generative artificial intelligence.

[0290] "Contract information" is data indicating whether the customer service resulted in a contract.

[0291] MODE FOR CARRYING OUT THE INVENTION

[0292] The present invention is a voice recording, analysis, and feedback system for improving crew customer service performance, which combines emotion recognition functionality. This system enables personalized advice based on the user's emotions. Specific embodiments for implementing the present invention are described below.

[0293] Overall system configuration

[0294] This system consists of a device that records the user's customer service, a server that analyzes the recorded data, generative artificial intelligence to generate and provide feedback, and an emotion recognition engine that recognizes the user's emotions.

[0295] User operations

[0296] The user uses their smartphone, tablet, or other device to launch an application to record the customer service interaction. They tap the record button to start recording the interaction, and when they're done, they tap the stop recording button. They then name and save the recorded audio file, select the audio file within the app, and upload it to the server. At this time, they also enter information on whether the transaction was successful or not.

[0297] Terminal handling

[0298] The device uses a speech recognition engine (such as Google Speech-to-Text) to convert the recorded audio file into text data, generating recognized text data. It also uses an emotion recognition engine to detect the user's emotions from the recorded audio and text data. For example, it can recognize emotions such as "joy," "anger," and "sadness" by analyzing the user's tone of voice and phrasing.

[0299] Server Processing

[0300] The server analyzes the received text data, sales information, and emotional information. Generative AI is used for the analysis, and customer service skills are evaluated based on the content of the text data and the user's emotions. This generative AI learns from a large amount of crew data and is able to generate optimal feedback.

[0301] Generate feedback

[0302] Based on the analysis results, the server generates optimal advice that takes into account emotional information. For example, if the user expresses anger, the server can generate specific advice such as "respond in a calm tone."

[0303] Conversion to audio data

[0304] The generated advice is then converted into voice data using speech synthesis technology. This voice data is sent to the device and can be played back and listened to by the user. For example, specific advice such as "Try to listen more slowly when the customer speaks" can be generated using speech synthesis and provided to the user.

[0305] Receive feedback on your device

[0306] The device receives the advice and audio data sent from the server and displays and plays it back within the app. By checking this feedback and playing it back aloud, users can understand where they need to improve and use it for their next customer service encounter.

[0307] Specific examples

[0308] For example, if user Tanaka records a sales pitch, the audio data is converted into text such as "Hello, how can I help you today?", and at the same time, the emotion recognition engine recognizes Tanaka's emotion as "slightly nervous." Tanaka's smartphone sends the text data, emotional information, and sales information to the server, which then generates advice such as "Take a more relaxed attitude toward customers." This advice is converted into audio data and sent to Tanaka's smartphone. Tanaka can review the advice through the app, play back the audio, and improve on the "relaxed conversation with customers" aspect, which can be applied to the next customer service encounter.

[0309] Examples of prompt statements

[0310] The following prompt sentences can be input to the generative AI model:

[0311] "Analyze customer service speech and generate effective feedback that includes the user's emotional information. For example, give advice based on the language and tone used during the conversation."

[0312] As described above, by using this system, users can improve their customer service skills while understanding their own emotional state. In addition, the system provides optimized education and guidance for individual crew members, and by collecting and comparing data on a national scale, it is possible to improve the success rate.

[0313] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0314] Step 1:

[0315] Users simply launch the application on their smartphone or tablet and tap the record button to record the audio of their customer service.

[0316] What it does: Your phone will use the device's microphone to record audio in real time and store it as a digital audio file in the background.

[0317] Input: Tap action to start recording.

[0318] Output: The audio data being recorded.

[0319] Step 2:

[0320] When the user has finished serving the customer, they tap the stop recording button and save the recorded audio file.

[0321] Specific operation: The device detects the tap action of the stop recording button, saves the audio data recorded up to that point as a temporary file, and prompts the user to enter a file name.

[0322] Input: Tap action to stop recording and input file name.

[0323] Output: The named audio file.

[0324] Step 3:

[0325] Users select an audio file within the app, upload it to the server, and enter information about successful and unsuccessful transactions.

[0326] Specific operation: The terminal encodes the audio file selected by the user and the transaction information and sends them to the server.

[0327] Input: Select an audio file and enter deal information.

[0328] Output: Sending audio files and deal information to the server.

[0329] Step 4:

[0330] The server uses a speech recognition engine (such as Google Speech-to-Text) to convert the received audio file into text data.

[0331] Specific operation: The server passes the voice data to the voice recognition engine and obtains the recognized text data as the result.

[0332] Input: An audio file.

[0333] Output: Text data.

[0334] Step 5:

[0335] The server uses an emotion recognition engine to detect the user's emotions from the audio file and text data.

[0336] Specific operation: The server analyzes the tone of the voice data and the content of the text data, and uses an emotion recognition engine to identify emotions such as "joy," "anger," and "sadness."

[0337] Input: Audio files and text data.

[0338] Output: Emotional information.

[0339] Step 6:

[0340] The server uses generative artificial intelligence to analyze the received text data, closing information, and sentiment information.

[0341] Specific operation: The server inputs data into a generative artificial intelligence (AI model) and performs analysis, which evaluates customer service skills.

[0342] Input: Text data, closing information, and sentiment information.

[0343] Output: Customer service skills evaluation results.

[0344] Step 7:

[0345] Based on the analysis results, the server generates optimal advice that takes emotional information into consideration.

[0346] Specific operation: The generative artificial intelligence generates appropriate feedback in text format from the analysis results.

[0347] Input: Customer service skills evaluation results.

[0348] Output: Advice in text format.

[0349] Step 8:

[0350] The server converts the generated advice into voice data using voice synthesis technology.

[0351] Specific operation: The server passes the generated text advice to a speech synthesis engine (such as Google Text-to-Speech) to generate it as audio data.

[0352] Input: Advice in text format.

[0353] Output: Audio data.

[0354] Step 9:

[0355] The device receives the advice and audio data sent from the server and displays and plays it back within the app.

[0356] Specific behavior: The device displays the received data within the app and provides an interface for playing audio advice.

[0357] Input: Advice and audio data received from the server.

[0358] Output: The displayed advice and the audio data played.

[0359] This process flow allows the user to obtain feedback to efficiently improve their customer service skills.

[0360] (Application example 2)

[0361] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0362] Conventional customer service training systems have problems: it takes time to improve a crew's customer service skills, and it is difficult to provide personalized feedback because they do not take into account factors such as emotion recognition.Furthermore, it is not possible to compare data nationwide, making it difficult to propose effective improvement measures based on a wide range of data.

[0363] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0364] In this invention, the server includes: [means for generating advice based on the analysis results]; [means for converting the generated advice into voice data]; and [means for using an emotion recognition engine that recognizes emotions from the user's tone of voice and vocabulary]. This makes it possible to efficiently provide personalized advice that takes into account the emotional state of each crew member in order to improve customer service skills. In addition, by comparing and analyzing nationwide data, it becomes possible to propose more accurate improvement measures.

[0365] "Means for recording voice data" refers to a device or software for recording the voice of the crew member providing service as digital data.

[0366] "Means for converting recorded voice data into text data" refers to technology that uses a voice recognition engine to convert recorded voice data into text.

[0367] The "means for transmitting the text data and the transaction information to the server" refers to a communication device or protocol for sending the converted text data and the transaction information to the server via the Internet.

[0368] "Means using generative artificial intelligence to analyze text data" refers to artificial intelligence techniques used to analyze the content of text data and generate optimal feedback.

[0369] "Means for generating advice based on analysis results" refers to the process of creating specific advice for improving customer service skills from the analysis results of generative artificial intelligence.

[0370] The "means for converting the generated advice into voice data" refers to using a voice synthesis technique to output the generated advice in text format as voice.

[0371] "Means for transmitting advice and voice data to a terminal" refers to a communication means for transmitting the generated advice and voice data to the terminal of the crew member who served the customer.

[0372] "Means for receiving, displaying and playing advice and audio data at the terminal" refers to a playback function that displays the advice and audio data received on the terminal and allows the user to listen to it aloud.

[0373] "Using an emotion recognition engine to recognize emotions from a user's tone of voice and phrasing" refers to algorithms or systems used to analyze and recognize a user's emotions from voice or text data.

[0374] The "means for generating feedback based on emotion recognition results" refers to a process for providing specific feedback based on the user's emotions, based on the analysis results of the emotion recognition engine.

[0375] "Data analysis tools for comparing and analyzing nationwide data" refers to software or algorithms used to statistically compare and analyze collected customer service data on a nationwide scale.

[0376] "Means using neural networks to generate advice and voice data" refers to a process that utilizes deep learning-based neural network algorithms to generate advice and optimize voice data.

[0377] This invention is a voice recording, analysis and feedback system for improving the customer service skills of crew members, and is characterized by its incorporation of a user emotion recognition function. This system is realized using a voice recognition engine, generative artificial intelligence, an emotion recognition engine and voice synthesis technology.

[0378] Overall system configuration

[0379] This system consists of a device that records the user's customer service speech, a server that analyzes the recorded data, and a generative artificial intelligence and emotion engine that generate and provide feedback. By linking these elements together, advanced support for improving customer service skills is realized.

[0380] User operations

[0381] The user launches a dedicated application to record the audio of customer service using their own device, such as a smartphone or tablet. They tap the record button to record the audio of the customer service, and then tap the stop recording button when they are finished. They then name and save the recorded audio file, select the audio file within the app, and upload it to the server. At this time, they also enter information on whether the deal was successful or not.

[0382] Terminal handling

[0383] The device converts the recorded audio file into text data using a speech recognition engine (e.g., Google Speech-to-Text). It also uses an emotion recognition engine to detect the user's emotions from the recorded audio and text data. For example, it can recognize emotions such as "joy," "anger," and "sadness" by analyzing the user's tone of voice and phrasing.

[0384] Server Processing

[0385] The server analyzes the received text data, sales information, and emotional information. Generative AI (e.g., a neural network using deep learning) is used for the analysis, and customer service skills are evaluated based on the content of the text data and the user's emotions. Generative AI learns from large amounts of data and is able to generate optimal feedback.

[0386] Generate feedback

[0387] Based on the analysis results, the server generates optimal advice that takes into account the user's emotional information. For example, if the user expresses anger, the server generates specific advice such as "respond in a calm tone."

[0388] Conversion to audio data

[0389] The generated advice is converted into voice data using voice synthesis technology, which is then sent to the terminal and played back for the user to listen to.

[0390] Receive feedback on your device

[0391] The device receives advice and audio data sent from the server and can display and play it back within the app. By checking this feedback and playing it back aloud, users can understand what they need to improve and use it for their next customer service encounter.

[0392] Specific examples

[0393] For example, when a user is explaining a product, the recorded voice data is converted into text such as "The features of this product are...", and at the same time, the emotion recognition engine recognizes the user's emotion as "not confident." Based on this text data and emotional information, the server generates advice such as "If you explain the product's features in more detail, I will be able to speak with more confidence," converts this into voice data, and sends it to the user's smartphone. The user can check this advice through the app, play back the audio, and use it for their next customer service encounter.

[0394] Prompt Sentence Examples

[0395] "Customer service: The features of this product are...

[0396] Customer sentiment: Unsure

[0397] Tip: Explain your product's features in more detail to help you feel more confident.

[0398] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0399] Step 1:

[0400] The user starts a recording application on their smartphone or tablet and records the voice of the customer while serving the customer. They tap the record button to record the voice of the customer, and press the stop recording button when finished. At this time, the input is the customer service voice data, and the recorded voice file is saved as the output.

[0401] Step 2:

[0402] The device converts the recorded audio file into text data using a speech recognition engine (such as Google Speech-to-Text). The input is an audio file, and text data is generated as output. This text data includes what was said during the customer service.

[0403] Step 3:

[0404] Using an emotion recognition engine, the device detects the user's emotions from the recorded voice data and converted text data. The input is voice and text data, and the output is the emotion recognition results, which include emotional information such as "joy," "anger," and "sadness."

[0405] Step 4:

[0406] The terminal transmits the generated text data, closing information, and emotion information to the server. The input is the text data, closing information, and emotion information, and the output is uploaded to the server.

[0407] Step 5:

[0408] The server analyzes the received text data, sales information, and emotional information using generative artificial intelligence (a neural network using deep learning). The input is text data, sales information, and emotional information, and the output is an evaluation of customer service skills. The analysis evaluates which parts are effective and which parts have room for improvement.

[0409] Step 6:

[0410] The server generates optimal advice based on the analysis results, taking into account emotional information. For example, if the emotion of "anger" is detected, specific advice such as "respond in a calm tone" is generated. The input is the analysis results and emotional information, and the output is text data of the advice.

[0411] Step 7:

[0412] The generated advice is converted into voice data by the server using voice synthesis technology. The input is text data of the advice, and the output is voice data of the advice.

[0413] Step 8:

[0414] The server sends the generated advice and voice data to the terminal. The input is the voice data and text data of the advice, and these are sent to the terminal as output.

[0415] Step 9:

[0416] The device receives the advice and audio data sent from the server and displays and plays it back within the app. The user can check this feedback and play it back aloud to understand their own customer service skills and apply them to their next customer service encounter. The input is the advice audio data and text data, and the output is display and audio playback.

[0417] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0418] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0419] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0420] [Second embodiment]

[0421] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0422] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0423] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0424] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0425] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0426] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0427] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0428] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0429] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0430] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0431] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0432] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0433] The present invention is a voice recording and analysis system for improving the customer service skills of crew members. With this system, users can record their own customer service, send the recording data to a server, and receive appropriate feedback, allowing them to receive personalized guidance.

[0434] Overall system configuration

[0435] This system consists of a device that records the user's customer service, a server that analyzes the recorded data, and generative artificial intelligence to generate and provide feedback.

[0436] User operations

[0437] The user uses their smartphone, tablet, or other device to launch an application to record the customer service interaction. They tap the record button to start recording the interaction, and when they're done, they tap the stop recording button. They then name and save the recorded audio file, select the audio file within the app, and upload it to the server. At this time, they also enter information on whether the transaction was successful or not.

[0438] Terminal handling

[0439] The device uses a speech recognition engine (such as Google Speech-to-Text) to convert the recorded audio file into text data, transcribes the audio file, and sends the generated text data and transaction information to the server.

[0440] Server Processing

[0441] The server analyzes the received text data and sales information. The analysis is performed using generative AI, and customer service skills are evaluated based on the content of the text data. The generative AI learns from a large amount of crew data and is able to generate optimal feedback.

[0442] Generate feedback

[0443] The server generates advice and suggestions for improving customer service based on the analysis results. For example, if the generative AI finds an area for improvement such as "You need to ask customers more specifically about their requests," it can generate advice such as "You should try to ask customers more specific questions."

[0444] Conversion to audio data

[0445] The generated advice is then converted into voice data using speech synthesis technology. This voice data is sent to the device and can be played back and listened to by the user. For example, specific advice such as "Try to listen more slowly when the customer speaks" can be generated using speech synthesis and provided to the user.

[0446] Receive feedback on your device

[0447] The device receives the advice and audio data sent from the server and displays and plays it back within the app. By checking this feedback and playing it back aloud, users can understand where they need to improve and use it for their next customer service encounter.

[0448] As a concrete example, if user Tanaka records a sales conversation, the audio data is converted into text such as "Hello, how can I help you today?" Tanaka's smartphone sends the text data and the sales contract information to the server, which then generates advice such as "You should listen more slowly to what the customer is saying." This advice is converted into audio data and sent to Tanaka's smartphone. Tanaka can check the advice through the app and play it back as audio to improve his customer service skills.

[0449] This system allows us to provide optimal feedback to individual crew members and improve their customer service skills. By collecting and comparing data on a nationwide scale, we can provide more accurate advice and expect to improve our success rate.

[0450] The processing flow will be explained below.

[0451] Step 1:

[0452] User

[0453] The user launches the app and starts recording the customer service. Specifically, the user taps the "Start Recording" button and starts voice input.

[0454] Step 2:

[0455] User

[0456] Once the customer service is finished, the user taps the "Stop Recording" button to end the recording. Then, the recording file is saved with a name, for example, "20231005_Customer Service Recording."

[0457] Step 3:

[0458] User

[0459] Select the recorded file in the app and enter the transaction information (e.g., "Sold" or "Not Sold" and any comments). Next, tap the upload button to send the audio file and transaction information to the server.

[0460] Step 4:

[0461] Terminal

[0462] The device receives the recorded audio file and converts it into text data by calling a speech recognition engine (such as Google Speech-to-Text). The recognized text data is generated.

[0463] Step 5:

[0464] Terminal

[0465] The converted text data and the contract information are sent to the server. If the transmission is successful, the user is notified within the app.

[0466] Step 6:

[0467] server

[0468] The server analyzes the received text data and contract information. Using generative artificial intelligence (e.g., a deep learning model), the received data is analyzed to evaluate customer service and identify areas for improvement.

[0469] Step 7:

[0470] server

[0471] Based on the analysis results, the system generates optimal advice, such as "You need to show more empathy for your customers."

[0472] Step 8:

[0473] server

[0474] The generated advice is passed to a speech synthesis engine and converted into voice data, such as "It is important to show empathy to customers."

[0475] Step 9:

[0476] server

[0477] The generated advice and audio data are sent to the device. If the transfer is successful, the user is notified within the app.

[0478] Step 10:

[0479] Terminal

[0480] The device receives the advice and audio data sent from the server, displays it so that the user can check the feedback within the app, and provides an audio playback function.

[0481] Step 11:

[0482] User

[0483] Users can check the feedback in the app and receive specific advice by playing back the audio data. For example, they can receive advice such as "When listening to a customer, take a pause before responding," which they can use to improve their next customer service experience.

[0484] Through this series of steps, users can record their own customer service interactions and receive accurate feedback through AI analysis, enabling them to provide tailored training and guidance to individual crew members and improve their customer service skills.

[0485] Example 1

[0486] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0487] Using voice data to improve customer service skills has been difficult to do efficiently with conventional approaches. Providing timely and accurate individual feedback is particularly important. Furthermore, there is a lack of data for nationwide comparative analysis of customer service quality, and no standard method for improving customer service skills has been established.

[0488] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0489] In this invention, the server includes means for recording voice data, means for converting the recorded voice data into text data, means for transmitting the text data and contract information to the server, means for using generative artificial intelligence to analyze the text data, means for generating advice based on the analysis results, means for converting the generated advice into voice data, means for transmitting the advice and voice data to a terminal, and means for receiving, displaying, and playing the advice and voice data on the terminal. This allows users to efficiently receive individual feedback and improve their customer service skills. Furthermore, analysis by the generative artificial intelligence allows data to be compared and analyzed on a nationwide scale, establishing a standard method for improving customer service skills.

[0490] "Voice data" is digital data that records the user's speech or voice.

[0491] "Recording" is the operation or process of storing audio data in digital form.

[0492] "Text data" refers to character string data obtained by transcribing voice data.

[0493] "Deal information" is information indicating whether the user's customer service resulted in a deal or not.

[0494] A "server" is a computer system that receives, analyzes, and transmits data over a network.

[0495] "Generative artificial intelligence" is an AI technology that learns using large amounts of data, analyzes text data, and generates feedback.

[0496] "Analyzing" is the process of analyzing the content of text data and extracting important elements.

[0497] "Feedback" refers to advice and information on improvements provided to users based on the analysis results.

[0498] "Speech synthesis" is a technology that converts text data into voice data.

[0499] A "terminal" is a device that is directly operated by a user, such as a smartphone or tablet.

[0500] "Reception" refers to an operation in which a terminal acquires data from a server or the like.

[0501] "Display" refers to the ability to show text and graphical information to the user on the terminal.

[0502] "Playback" is a function that converts voice data into an acoustic signal on the terminal and allows the user to hear it.

[0503] The present invention is a voice recording and analysis system for improving the customer service skills of crew members. The configuration and specific operation of this system will be described below.

[0504] Overall system configuration

[0505] This system includes a terminal that records the user's voice during customer service, a server that analyzes the recorded data, and generative artificial intelligence to generate and provide feedback.

[0506] User operations

[0507] The user launches the voice recording application on their smartphone or tablet. They tap the record button to record the customer service voice, and when they're done, they tap the stop recording button. They then name and save the audio file, and upload it to the server within the app. At this time, they also enter deal information such as whether the deal was closed or not.

[0508] Terminal handling

[0509] The device converts the saved voice file into text data using a voice recognition engine (e.g., Google Speech-to-Text). For example, the recorded voice data "Hello, how can I help you today?" is converted into text data. The generated text data and the contract information are then sent to the server.

[0510] Server Processing

[0511] The server analyzes the received text data and closing information. Generative artificial intelligence (such as ChatGPT) is used for the analysis. The server evaluates customer service skills based on the text data and generates an analysis result. For example, the analysis result may be, "You need to ask the customer for more specific information about their request."

[0512] Generate feedback

[0513] Based on the analysis results, the server generates advice and suggestions for improving customer service. For example, it generates feedback such as, "It would be good if you try to ask customers more specific questions." This feedback is converted into audio data using a speech synthesis engine (for example, Google Text-to-Speech). Specifically, the advice text is sent to a speech synthesis API, and the generated audio file is obtained.

[0514] Receive feedback on your device

[0515] The device receives the advice and audio data sent from the server and displays and plays it back within the app. The user can check this feedback and understand specific areas for improvement. For example, the user may receive audio feedback through the app such as, "Please try to listen to the customer more slowly."

[0516] Specific examples

[0517] When user Tanaka records a sales conversation, the audio data is converted into text, such as "Hello, how can I help you today?" Tanaka's smartphone sends the text data and the closing information to the server, which then generates advice such as "You should listen more slowly to what the customer is saying." This advice is converted into audio data and sent to Tanaka's smartphone. Tanaka can review the advice through the app and play it back as audio to improve his customer service skills.

[0518] Prompt Sentence Examples

[0519] "I recorded my customer service. Please transcribe this audio and give me feedback on my customer service skills."

[0520] By using this system, users can efficiently receive individual feedback and improve their customer service skills. Furthermore, by collecting and comparing data on a national scale, it is expected that more accurate advice can be provided and customer service skills can be standardized and improved overall.

[0521] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0522] Step 1:

[0523] The user starts the application on their smartphone or tablet and taps the record button to record the voice of the customer service. The input is the user's voice while the customer service is being served, and the output is the recorded voice data. For example, the user presses the "Start Recording" button and speaks the contents of the customer service.

[0524] Step 2:

[0525] When the user taps the stop recording button, the device saves the recorded audio data to local storage. The input is the recorded audio data, and the output is the saved audio file. The user names the file. For example, the audio file is saved as "Sales Talk_20231001".

[0526] Step 3:

[0527] The device converts the saved audio file into text data using a speech recognition engine (e.g., Google Speech-to-Text). The input is the saved audio file, and the output is the generated text data. For example, the recorded "Hello, how can I help you today?" is converted into text data.

[0528] Step 4:

[0529] The terminal sends the generated text data and the contract information together to the server. The input is the text data and the contract information, and the output is a POST request to the server. For example, the text data and the contract information "unconcluded" are sent to the server.

[0530] Step 5:

[0531] The server analyzes the received text data and contract information. This analysis is performed using generative artificial intelligence (for example, ChatGPT). The input is the text data and contract information, and the output is the analysis result. For example, the analysis result may be, "We need to listen more specifically to the customer's requests."

[0532] Step 6:

[0533] Based on the analysis results, the server uses generative artificial intelligence to generate improvements and advice for customer service. The input is the analysis results, and the output is the generated feedback text. For example, it generates advice such as, "It would be a good idea to try to ask customers more specific questions."

[0534] Step 7:

[0535] The server converts the generated feedback into voice data using a speech synthesis engine (e.g., Google Text-to-Speech). The input is the feedback text, and the output is voice data. For example, voice data such as "Please try to listen more slowly to what the customer is saying" is generated.

[0536] Step 8:

[0537] The terminal receives the voice data and feedback text sent from the server. The input is the response data from the server, and the output is the received voice data and feedback text. For example, the terminal receives feedback from the server.

[0538] Step 9:

[0539] The user checks the feedback text and audio displayed in the app and plays it back. The input is the received audio data and feedback text, and the output is the recognized feedback. For example, the user checks and plays back advice such as "Try to listen more slowly to what the customer is saying."

[0540] (Application example 1)

[0541] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0542] In the modern hospitality industry, individual feedback is essential for store crew members to effectively improve their customer service skills. However, there are currently few ways to efficiently provide such feedback in daily work. Furthermore, there is no established system for obtaining consistent, high-quality feedback, which slows down crew members' growth.

[0543] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0544] In this invention, the server includes: [means for generating advice based on the analysis results using generative artificial intelligence]; [means for playing back the generated advice as advice using voice synthesis]; and [means including data analysis means for comparing and analyzing data from across the country.] This enables [crew members to receive consistent, high-quality feedback to efficiently and effectively improve their customer service skills].

[0545] "Audio data" refers to data that records the audio information uttered by the crew when serving customers.

[0546] "Text data" refers to digital text data that has been transcribed from voice data using a voice recognition engine.

[0547] "Contract information" refers to information regarding whether or not a contract has been concluded and the details of the contract obtained through customer service.

[0548] "Generative AI" is an AI technology that learns from large amounts of data and performs analysis and generates feedback according to specific purposes.

[0549] "Speech synthesis" is a technology that converts text data into voice data.

[0550] A "terminal" is a digital device used by a user, such as a smartphone, tablet, or computer.

[0551] The "data analysis means" is a technology that analyzes the received text data and contract information and generates various statistical data.

[0552] "Analysis results" refer to the evaluations and insights that generative artificial intelligence obtains by analyzing text data.

[0553] "Advice" refers to specific suggestions and guidance generated based on the analysis results to improve the crew's customer service skills.

[0554] The present invention is a voice recording and analysis system for crew members to improve their customer service skills. This system consists of the following main hardware and software:

[0555] Hardware usage example

[0556] 1. Device: A smartphone, tablet, or computer. These devices are used by crew members to record customer service audio and receive feedback.

[0557] 2. Server: A powerful computing device that analyzes data and generates feedback.

[0558] Software usage examples

[0559] 1. Speech recognition engine: Uses the Google Cloud Speech-to-Text API to convert recorded voice data into text data.

[0560] 2. Generative AI: Uses OpenAI GPT-3 or similar AI models to analyze text data and generate appropriate advice.

[0561] 3. Speech synthesis engine: Uses the Google Text-to-Speech API to convert text-based advice into audio data.

[0562] 4. Server-side framework: A framework for managing APIs and sending and receiving data, such as Flask.

[0563] Program processing flow

[0564] 1. Voice recording and transcription:

[0565] The user starts a voice recording application on the device and records the conversation during the customer service session.

[0566] The device converts the recorded audio data into text data using the Google Cloud Speech-to-Text API.

[0567] 2. Data transmission and analysis:

[0568] The converted text data and the contract information are sent to a server via the Internet.

[0569] The server analyzes the received text data using OpenAI GPT-3 generative artificial intelligence.

[0570] 3. Feedback generation and submission:

[0571] Generative AI generates feedback based on the analysis, which is then converted into audio data using the Google Text-to-Speech API.

[0572] The server transmits the generated feedback and voice data to the terminal.

[0573] 4. Receiving and Viewing Feedback:

[0574] The device displays and plays the received feedback and audio data within the application.

[0575] The user reads the displayed feedback and understands specific improvements through audio playback.

[0576] Explanation through concrete examples

[0577] For example, one of the crew members records a customer service response, "Hello, how can I help you today?" This voice data is converted into text data, and a specific prompt, "Generate feedback for this response: Hello, how can I help you today?", is sent to the server. The generative AI analyzes the data and generates feedback such as, "You should listen to the customer more slowly." This feedback is converted into audio data using the Google Text-to-Speech API and sent to the user's device. The user can review this feedback through the application and improve their customer service skills by playing the audio back.

[0578] This allows users to consistently receive high-quality feedback to effectively improve their customer service skills.

[0579] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0580] Step 1:

[0581] The user starts a voice recording application on the device and records the conversation during the customer service session.

[0582] Input: Crew member's voice

[0583] Output: Recorded audio data

[0584] Specific operation: The user taps the "Start Recording" button on the recording app to record the customer conversation. When recording is finished, the user taps the "Stop Recording" button to save the audio data.

[0585] Step 2:

[0586] The device converts the recorded audio data into text data using the Google Cloud Speech-to-Text API.

[0587] Input: Recorded audio data

[0588] Output: Converted text data

[0589] Specific operation: Sends recorded audio data to the Google Cloud Speech-to-Text API, performs speech recognition, and receives text data returned by the API.

[0590] Step 3:

[0591] The terminal transmits the converted text data and the transaction information to the server.

[0592] Input: Text data and contract information

[0593] Output: Data sent to the server

[0594] Specific operation: The user enters the transaction information into the app, and the device sends the text data and transaction information together to the server as an HTTP request.

[0595] Step 4:

[0596] The server analyzes the received text data using generative artificial intelligence.

[0597] Input: Received text data

[0598] Output: Analysis results and feedback text

[0599] Specific operation: The server calls OpenAI GPT-3, inputs the prompt "Generate feedback for this customer service: [text data]", and obtains the analysis results.

[0600] Step 5:

[0601] The server converts the generated feedback into audio data using the Google Text-to-Speech API.

[0602] Input: Feedback text

[0603] Output: Generated feedback audio data

[0604] Specific operation: The parsed feedback text is sent to the Google Text-to-Speech API to generate audio data.

[0605] Step 6:

[0606] The server transmits the generated feedback and voice data to the terminal.

[0607] Input: Feedback text and audio data

[0608] Output: Data sent to the terminal

[0609] Specific operation: The server sends the generated feedback text and audio data to the device as an HTTP response.

[0610] Step 7:

[0611] The device displays and plays the received feedback and audio data within the application.

[0612] Input: Received feedback text and audio data

[0613] Output: User feedback viewing and playback

[0614] Specific behavior: The device displays the feedback text on the screen and provides a button to play the audio data. When the user taps the button, the audio feedback is played.

[0615] This allows users to record themselves, have the audio data analyzed, and receive feedback to improve their customer service skills.

[0616] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0617] The present invention is a voice recording, analysis, and feedback system for improving crew customer service skills, combined with user emotion recognition, which allows for more personalized advice based on the user's emotions.

[0618] Overall system configuration

[0619] This system consists of a device that records the user's customer service, a server that analyzes the recorded data, a generative artificial intelligence to generate and provide feedback, and an emotion engine that recognizes the user's emotions.

[0620] User operations

[0621] The user uses their smartphone, tablet, or other device to launch an application to record the customer service interaction. They tap the record button to start recording the interaction, and when they're done, they tap the stop recording button. They then name and save the recorded audio file, select the audio file within the app, and upload it to the server. At this time, they also enter information on whether the transaction was successful or not.

[0622] Terminal handling

[0623] The device uses a speech recognition engine (such as Google Speech-to-Text) to convert the recorded audio file into text data, generating recognized text data. It also uses an emotion engine to detect the user's emotions from the recorded audio and text data. For example, it can recognize emotions such as "joy," "anger," and "sadness" by analyzing the user's tone of voice and phrasing.

[0624] Server Processing

[0625] The server analyzes the received text data, sales information, and emotional information. Generative AI is used for the analysis, and customer service skills are evaluated based on the content of the text data and the user's emotions. The generative AI learns from a large amount of crew data and is able to generate optimal feedback.

[0626] Generate feedback

[0627] Based on the analysis results, the server generates optimal advice that takes into account emotional information. For example, if the user expresses anger, the server can generate specific advice such as "respond in a calm tone."

[0628] Conversion to audio data

[0629] The generated advice is then converted into voice data using speech synthesis technology. This voice data is sent to the device and can be played back and listened to by the user. For example, specific advice such as "Try to listen more slowly when the customer speaks" can be generated using speech synthesis and provided to the user.

[0630] Receive feedback on your device

[0631] The device receives the advice and audio data sent from the server and displays and plays it back within the app. By checking this feedback and playing it back aloud, users can understand where they need to improve and use it for their next customer service encounter.

[0632] As a concrete example, if user Tanaka records a sales pitch, the audio data is converted into text such as "Hello, how can I help you today?", and at the same time, the emotion engine recognizes Tanaka's emotion as "slightly nervous." Tanaka's smartphone sends the text data, emotional information, and sales information to the server, which then generates advice such as "Take a more relaxed attitude toward customers." This advice is converted into audio data and sent to Tanaka's smartphone. Tanaka can check the advice through the app, play back the audio, and improve on the "relaxed conversation with customers" aspect, which can be used for the next customer service encounter.

[0633] This system allows users to understand their own emotional state while improving their customer service skills, and makes it possible to provide optimized training and guidance to individual crew members. By collecting and comparing data on a national scale, it is expected that more accurate advice can be provided, leading to an improved closing rate.

[0634] The processing flow will be explained below.

[0635] Step 1:

[0636] User

[0637] The user launches the app and starts recording the conversation. Specifically, the user taps the "Start Recording" button to record the conversation.

[0638] Step 2:

[0639] User

[0640] Once the customer service is finished, the user taps the "Stop Recording" button to end the recording. The recording file is saved with a name. For example, it can be saved as "20231005_Customer Service Recording".

[0641] Step 3:

[0642] User

[0643] Select the recorded audio file in the app and enter the deal information (e.g., "Sold" or "Not Sold"), then tap the upload button to send the audio file and the deal information to the server.

[0644] Step 4:

[0645] Terminal

[0646] The device receives the recorded audio file and calls a speech recognition engine (such as Google Speech-to-Text) to convert the audio file into text data, which is then stored on the device.

[0647] Step 5:

[0648] Terminal

[0649] The recorded voice file is passed to the emotion engine, which analyzes the user's emotions. The emotion engine analyzes the user's tone of voice and vocabulary to identify emotions such as "joy," "anger," and "sadness."

[0650] Step 6:

[0651] Terminal

[0652] The converted text data, the recognized emotion information, and the transaction information are sent to the server. The app notifies you whether the transmission was successful or not.

[0653] Step 7:

[0654] server

[0655] The server analyzes the received text data, sentiment information, and sales information. A generative artificial intelligence (AI model) analyzes this data and identifies areas for improvement, such as "listening more specifically to what the customer is saying."

[0656] Step 8:

[0657] server

[0658] Based on the analysis results, the system generates optimal advice, taking emotional information into account, such as "Try to maintain a relaxed atmosphere when interacting with customers."

[0659] Step 9:

[0660] server

[0661] The generated advice is passed to a speech synthesis engine and converted into voice data. For example, voice data such as "Try to listen more carefully to what the customer is saying" is generated.

[0662] Step 10:

[0663] server

[0664] The generated advice and its audio data are sent to the device. The server checks whether the transmission was successful.

[0665] Step 11:

[0666] Terminal

[0667] The device receives the advice and audio data sent from the server and makes them available for display and playback within the app. Specifically, the text-format advice is displayed and the audio-format advice is played back.

[0668] Step 12:

[0669] User

[0670] Review the feedback provided by the user within the app. Play back the audio data to understand areas for improvement. For example, take the advice "Take more time to pause when responding to customers" into consideration and use it for your next customer service encounter.

[0671] Through these processing steps, users can record their own customer service interactions, undergo detailed analysis including sentiment analysis, and receive accurate and personalized feedback. This series of processes enables optimized training and guidance for individual crew members, aiming to improve their customer service skills.

[0672] Example 2

[0673] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0674] In customer service, voice recording, analysis, and feedback are necessary to improve the customer service skills of crew members, and more personalized advice is required by combining it with emotion recognition functions. It is also important to collect and compare data on a national scale to provide more accurate feedback and improve the closing rate.

[0675] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: [means for recording voice data]; [means for converting the recorded voice data into text data]; [means for using an emotion recognition engine to detect emotions from the voice data and the converted text data]; [means for transmitting the text data, contract information, and emotion information to the server]; [means for using generative artificial intelligence to analyze the text data and emotion information]; [means for generating advice based on the analysis results]; [means for converting the generated advice into voice data]; [means for transmitting the advice and voice data to the terminal]; and [means for receiving, displaying, and playing the advice and voice data at the terminal]. This makes it possible to receive appropriate feedback while understanding the user's emotional state and improve customer service skills.

[0676] "Audio data" is data that represents in digital form the audio recorded by a user using a terminal.

[0677] "Text data" refers to data obtained by converting voice data into text format using a voice recognition engine.

[0678] An "emotion recognition engine" is software that analyzes a user's tone of voice and vocabulary from voice and text data to detect emotions.

[0679] "Generative AI" is an AI technology that learns from past data and generates feedback based on the analysis results.

[0680] "Feedback" refers to advice for improvement based on the user's customer service experience and emotional state.

[0681] A "voice recognition engine" is software that analyzes voice data and converts it into corresponding character data (text data).

[0682] "Speech synthesis technology" is a technology that analyzes text data and generates its contents as voice data.

[0683] "Device" means a device (such as a smartphone or tablet) for recording, storing, and transmitting audio data, and for receiving and playing feedback.

[0684] A "server" is a computing system that analyzes various types of data (voice data, text data, emotional information), generates feedback, and manages communication with terminals.

[0685] "Advice" refers to instructions and suggestions for improvement generated based on customer service content and emotional data analyzed by generative artificial intelligence.

[0686] "Contract information" is data indicating whether the customer service resulted in a contract.

[0687] MODE FOR CARRYING OUT THE INVENTION

[0688] The present invention is a voice recording, analysis, and feedback system for improving crew customer service performance, which combines emotion recognition functionality. This system enables personalized advice based on the user's emotions. Specific embodiments for implementing the present invention are described below.

[0689] Overall system configuration

[0690] This system consists of a device that records the user's customer service, a server that analyzes the recorded data, generative artificial intelligence to generate and provide feedback, and an emotion recognition engine that recognizes the user's emotions.

[0691] User operations

[0692] The user uses their smartphone, tablet, or other device to launch an application to record the customer service interaction. They tap the record button to start recording the interaction, and when they're done, they tap the stop recording button. They then name and save the recorded audio file, select the audio file within the app, and upload it to the server. At this time, they also enter information on whether the transaction was successful or not.

[0693] Terminal handling

[0694] The device uses a speech recognition engine (such as Google Speech-to-Text) to convert the recorded audio file into text data, generating recognized text data. It also uses an emotion recognition engine to detect the user's emotions from the recorded audio and text data. For example, it can recognize emotions such as "joy," "anger," and "sadness" by analyzing the user's tone of voice and phrasing.

[0695] Server Processing

[0696] The server analyzes the received text data, sales information, and emotional information. Generative AI is used for the analysis, and customer service skills are evaluated based on the content of the text data and the user's emotions. This generative AI learns from a large amount of crew data and is able to generate optimal feedback.

[0697] Generate feedback

[0698] Based on the analysis results, the server generates optimal advice that takes into account emotional information. For example, if the user expresses anger, the server can generate specific advice such as "respond in a calm tone."

[0699] Conversion to audio data

[0700] The generated advice is then converted into voice data using speech synthesis technology. This voice data is sent to the device and can be played back and listened to by the user. For example, specific advice such as "Try to listen more slowly when the customer speaks" can be generated using speech synthesis and provided to the user.

[0701] Receive feedback on your device

[0702] The device receives the advice and audio data sent from the server and displays and plays it back within the app. By checking this feedback and playing it back aloud, users can understand where they need to improve and use it for their next customer service encounter.

[0703] Specific examples

[0704] For example, if user Tanaka records a sales pitch, the audio data is converted into text such as "Hello, how can I help you today?", and at the same time, the emotion recognition engine recognizes Tanaka's emotion as "slightly nervous." Tanaka's smartphone sends the text data, emotional information, and sales information to the server, which then generates advice such as "Take a more relaxed attitude toward customers." This advice is converted into audio data and sent to Tanaka's smartphone. Tanaka can review the advice through the app, play back the audio, and improve on the "relaxed conversation with customers" aspect, which can be applied to the next customer service encounter.

[0705] Examples of prompt statements

[0706] The following prompt sentences can be input to the generative AI model:

[0707] "Analyze customer service speech and generate effective feedback that includes the user's emotional information. For example, give advice based on the language and tone used during the conversation."

[0708] As described above, by using this system, users can improve their customer service skills while understanding their own emotional state. In addition, the system provides optimized education and guidance for individual crew members, and by collecting and comparing data on a national scale, it is possible to improve the success rate.

[0709] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0710] Step 1:

[0711] Users simply launch the application on their smartphone or tablet and tap the record button to record the audio of their customer service.

[0712] What it does: Your phone will use the device's microphone to record audio in real time and store it as a digital audio file in the background.

[0713] Input: Tap action to start recording.

[0714] Output: The audio data being recorded.

[0715] Step 2:

[0716] When the user has finished serving the customer, they tap the stop recording button and save the recorded audio file.

[0717] Specific operation: The device detects the tap action of the stop recording button, saves the audio data recorded up to that point as a temporary file, and prompts the user to enter a file name.

[0718] Input: Tap action to stop recording and input file name.

[0719] Output: The named audio file.

[0720] Step 3:

[0721] Users select an audio file within the app, upload it to the server, and enter information about successful and unsuccessful transactions.

[0722] Specific operation: The terminal encodes the audio file selected by the user and the transaction information and sends them to the server.

[0723] Input: Select an audio file and enter deal information.

[0724] Output: Sending audio files and deal information to the server.

[0725] Step 4:

[0726] The server uses a speech recognition engine (such as Google Speech-to-Text) to convert the received audio file into text data.

[0727] Specific operation: The server passes the voice data to the voice recognition engine and obtains the recognized text data as the result.

[0728] Input: An audio file.

[0729] Output: Text data.

[0730] Step 5:

[0731] The server uses an emotion recognition engine to detect the user's emotions from the audio file and text data.

[0732] Specific operation: The server analyzes the tone of the voice data and the content of the text data, and uses an emotion recognition engine to identify emotions such as "joy," "anger," and "sadness."

[0733] Input: Audio files and text data.

[0734] Output: Emotional information.

[0735] Step 6:

[0736] The server uses generative artificial intelligence to analyze the received text data, closing information, and sentiment information.

[0737] Specific operation: The server inputs data into a generative artificial intelligence (AI model) and performs analysis, which evaluates customer service skills.

[0738] Input: Text data, closing information, and sentiment information.

[0739] Output: Customer service skills evaluation results.

[0740] Step 7:

[0741] Based on the analysis results, the server generates optimal advice that takes emotional information into consideration.

[0742] Specific operation: The generative artificial intelligence generates appropriate feedback in text format from the analysis results.

[0743] Input: Customer service skills evaluation results.

[0744] Output: Advice in text format.

[0745] Step 8:

[0746] The server converts the generated advice into voice data using voice synthesis technology.

[0747] Specific operation: The server passes the generated text advice to a speech synthesis engine (such as Google Text-to-Speech) to generate it as audio data.

[0748] Input: Advice in text format.

[0749] Output: Audio data.

[0750] Step 9:

[0751] The device receives the advice and audio data sent from the server and displays and plays it back within the app.

[0752] Specific behavior: The device displays the received data within the app and provides an interface for playing audio advice.

[0753] Input: Advice and audio data received from the server.

[0754] Output: The displayed advice and the audio data played.

[0755] This process flow allows the user to obtain feedback to efficiently improve their customer service skills.

[0756] (Application example 2)

[0757] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0758] Conventional customer service training systems have problems: it takes time to improve a crew's customer service skills, and it is difficult to provide personalized feedback because they do not take into account factors such as emotion recognition.Furthermore, it is not possible to compare data nationwide, making it difficult to propose effective improvement measures based on a wide range of data.

[0759] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0760] In this invention, the server includes: [means for generating advice based on the analysis results]; [means for converting the generated advice into voice data]; and [means for using an emotion recognition engine that recognizes emotions from the user's tone of voice and vocabulary]. This makes it possible to efficiently provide personalized advice that takes into account the emotional state of each crew member in order to improve customer service skills. In addition, by comparing and analyzing nationwide data, it becomes possible to propose more accurate improvement measures.

[0761] "Means for recording voice data" refers to a device or software for recording the voice of the crew member providing service as digital data.

[0762] "Means for converting recorded voice data into text data" refers to technology that uses a voice recognition engine to convert recorded voice data into text.

[0763] The "means for transmitting the text data and the transaction information to the server" refers to a communication device or protocol for sending the converted text data and the transaction information to the server via the Internet.

[0764] "Means using generative artificial intelligence to analyze text data" refers to artificial intelligence techniques used to analyze the content of text data and generate optimal feedback.

[0765] "Means for generating advice based on analysis results" refers to the process of creating specific advice for improving customer service skills from the analysis results of generative artificial intelligence.

[0766] The "means for converting the generated advice into voice data" refers to using a voice synthesis technique to output the generated advice in text format as voice.

[0767] "Means for transmitting advice and voice data to a terminal" refers to a communication means for transmitting the generated advice and voice data to the terminal of the crew member who served the customer.

[0768] "Means for receiving, displaying and playing advice and audio data at the terminal" refers to a playback function that displays the advice and audio data received on the terminal and allows the user to listen to it aloud.

[0769] "Using an emotion recognition engine to recognize emotions from a user's tone of voice and phrasing" refers to algorithms or systems used to analyze and recognize a user's emotions from voice or text data.

[0770] The "means for generating feedback based on emotion recognition results" refers to a process for providing specific feedback based on the user's emotions, based on the analysis results of the emotion recognition engine.

[0771] "Data analysis tools for comparing and analyzing nationwide data" refers to software or algorithms used to statistically compare and analyze collected customer service data on a nationwide scale.

[0772] "Means using neural networks to generate advice and voice data" refers to a process that utilizes deep learning-based neural network algorithms to generate advice and optimize voice data.

[0773] This invention is a voice recording, analysis and feedback system for improving the customer service skills of crew members, and is characterized by its incorporation of a user emotion recognition function. This system is realized using a voice recognition engine, generative artificial intelligence, an emotion recognition engine and voice synthesis technology.

[0774] Overall system configuration

[0775] This system consists of a device that records the user's customer service speech, a server that analyzes the recorded data, and a generative artificial intelligence and emotion engine that generate and provide feedback. By linking these elements together, advanced support for improving customer service skills is realized.

[0776] User operations

[0777] The user launches a dedicated application to record the audio of customer service using their own device, such as a smartphone or tablet. They tap the record button to record the audio of the customer service, and then tap the stop recording button when they are finished. They then name and save the recorded audio file, select the audio file within the app, and upload it to the server. At this time, they also enter information on whether the deal was successful or not.

[0778] Terminal handling

[0779] The device converts the recorded audio file into text data using a speech recognition engine (e.g., Google Speech-to-Text). It also uses an emotion recognition engine to detect the user's emotions from the recorded audio and text data. For example, it can recognize emotions such as "joy," "anger," and "sadness" by analyzing the user's tone of voice and phrasing.

[0780] Server Processing

[0781] The server analyzes the received text data, sales information, and emotional information. Generative AI (e.g., a neural network using deep learning) is used for the analysis, and customer service skills are evaluated based on the content of the text data and the user's emotions. Generative AI learns from large amounts of data and is able to generate optimal feedback.

[0782] Generate feedback

[0783] Based on the analysis results, the server generates optimal advice that takes into account the user's emotional information. For example, if the user expresses anger, the server generates specific advice such as "respond in a calm tone."

[0784] Conversion to audio data

[0785] The generated advice is converted into voice data using voice synthesis technology, which is then sent to the terminal and played back for the user to listen to.

[0786] Receive feedback on your device

[0787] The device receives advice and audio data sent from the server and can display and play it back within the app. By checking this feedback and playing it back aloud, users can understand what they need to improve and use it for their next customer service encounter.

[0788] Specific examples

[0789] For example, when a user is explaining a product, the recorded voice data is converted into text such as "The features of this product are...", and at the same time, the emotion recognition engine recognizes the user's emotion as "not confident." Based on this text data and emotional information, the server generates advice such as "If you explain the product's features in more detail, I will be able to speak with more confidence," converts this into voice data, and sends it to the user's smartphone. The user can check this advice through the app, play back the audio, and use it for their next customer service encounter.

[0790] Prompt Sentence Examples

[0791] "Customer service: The features of this product are...

[0792] Customer sentiment: Unsure

[0793] Tip: Explain your product's features in more detail to help you feel more confident.

[0794] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0795] Step 1:

[0796] The user starts a recording application on their smartphone or tablet and records the voice of the customer while serving the customer. They tap the record button to record the voice of the customer, and press the stop recording button when finished. At this time, the input is the customer service voice data, and the recorded voice file is saved as the output.

[0797] Step 2:

[0798] The device converts the recorded audio file into text data using a speech recognition engine (such as Google Speech-to-Text). The input is an audio file, and text data is generated as output. This text data includes what was said during the customer service.

[0799] Step 3:

[0800] Using an emotion recognition engine, the device detects the user's emotions from the recorded voice data and converted text data. The input is voice and text data, and the output is the emotion recognition results, which include emotional information such as "joy," "anger," and "sadness."

[0801] Step 4:

[0802] The terminal transmits the generated text data, closing information, and emotion information to the server. The input is the text data, closing information, and emotion information, and the output is uploaded to the server.

[0803] Step 5:

[0804] The server analyzes the received text data, sales information, and emotional information using generative artificial intelligence (a neural network using deep learning). The input is text data, sales information, and emotional information, and the output is an evaluation of customer service skills. The analysis evaluates which parts are effective and which parts have room for improvement.

[0805] Step 6:

[0806] The server generates optimal advice based on the analysis results, taking into account emotional information. For example, if the emotion of "anger" is detected, specific advice such as "respond in a calm tone" is generated. The input is the analysis results and emotional information, and the output is text data of the advice.

[0807] Step 7:

[0808] The generated advice is converted into voice data by the server using voice synthesis technology. The input is text data of the advice, and the output is voice data of the advice.

[0809] Step 8:

[0810] The server sends the generated advice and voice data to the terminal. The input is the voice data and text data of the advice, and these are sent to the terminal as output.

[0811] Step 9:

[0812] The device receives the advice and audio data sent from the server and displays and plays it back within the app. The user can check this feedback and play it back aloud to understand their own customer service skills and apply them to their next customer service encounter. The input is the advice audio data and text data, and the output is display and audio playback.

[0813] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0814] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0815] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0816] [Third embodiment]

[0817] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0818] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0819] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0820] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0821] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0822] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0823] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0824] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0825] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0826] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0827] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0828] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0829] The present invention is a voice recording and analysis system for improving the customer service skills of crew members. With this system, users can record their own customer service, send the recording data to a server, and receive appropriate feedback, allowing them to receive personalized guidance.

[0830] Overall system configuration

[0831] This system consists of a device that records the user's customer service, a server that analyzes the recorded data, and generative artificial intelligence to generate and provide feedback.

[0832] User operations

[0833] The user uses their smartphone, tablet, or other device to launch an application to record the customer service interaction. They tap the record button to start recording the interaction, and when they're done, they tap the stop recording button. They then name and save the recorded audio file, select the audio file within the app, and upload it to the server. At this time, they also enter information on whether the transaction was successful or not.

[0834] Terminal handling

[0835] The device uses a speech recognition engine (such as Google Speech-to-Text) to convert the recorded audio file into text data, transcribes the audio file, and sends the generated text data and transaction information to the server.

[0836] Server Processing

[0837] The server analyzes the received text data and sales information. The analysis is performed using generative AI, and customer service skills are evaluated based on the content of the text data. The generative AI learns from a large amount of crew data and is able to generate optimal feedback.

[0838] Generate feedback

[0839] The server generates advice and suggestions for improving customer service based on the analysis results. For example, if the generative AI finds an area for improvement such as "You need to ask customers more specifically about their requests," it can generate advice such as "You should try to ask customers more specific questions."

[0840] Conversion to audio data

[0841] The generated advice is then converted into voice data using speech synthesis technology. This voice data is sent to the device and can be played back and listened to by the user. For example, specific advice such as "Try to listen more slowly when the customer speaks" can be generated using speech synthesis and provided to the user.

[0842] Receive feedback on your device

[0843] The device receives the advice and audio data sent from the server and displays and plays it back within the app. By checking this feedback and playing it back aloud, users can understand where they need to improve and use it for their next customer service encounter.

[0844] As a concrete example, if user Tanaka records a sales conversation, the audio data is converted into text such as "Hello, how can I help you today?" Tanaka's smartphone sends the text data and the sales contract information to the server, which then generates advice such as "You should listen more slowly to what the customer is saying." This advice is converted into audio data and sent to Tanaka's smartphone. Tanaka can check the advice through the app and play it back as audio to improve his customer service skills.

[0845] This system allows us to provide optimal feedback to individual crew members and improve their customer service skills. By collecting and comparing data on a nationwide scale, we can provide more accurate advice and expect to improve our success rate.

[0846] The processing flow will be explained below.

[0847] Step 1:

[0848] User

[0849] The user launches the app and starts recording the customer service. Specifically, the user taps the "Start Recording" button and starts voice input.

[0850] Step 2:

[0851] User

[0852] Once the customer service is finished, the user taps the "Stop Recording" button to end the recording. Then, the recording file is saved with a name, for example, "20231005_Customer Service Recording."

[0853] Step 3:

[0854] User

[0855] Select the recorded file in the app and enter the transaction information (e.g., "Sold" or "Not Sold" and any comments). Next, tap the upload button to send the audio file and transaction information to the server.

[0856] Step 4:

[0857] Terminal

[0858] The device receives the recorded audio file and converts it into text data by calling a speech recognition engine (such as Google Speech-to-Text). The recognized text data is generated.

[0859] Step 5:

[0860] Terminal

[0861] The converted text data and the contract information are sent to the server. If the transmission is successful, the user is notified within the app.

[0862] Step 6:

[0863] server

[0864] The server analyzes the received text data and contract information. Using generative artificial intelligence (e.g., a deep learning model), the received data is analyzed to evaluate customer service and identify areas for improvement.

[0865] Step 7:

[0866] server

[0867] Based on the analysis results, the system generates optimal advice, such as "You need to show more empathy for your customers."

[0868] Step 8:

[0869] server

[0870] The generated advice is passed to a speech synthesis engine and converted into voice data, such as "It is important to show empathy to customers."

[0871] Step 9:

[0872] server

[0873] The generated advice and audio data are sent to the device. If the transfer is successful, the user is notified within the app.

[0874] Step 10:

[0875] Terminal

[0876] The device receives the advice and audio data sent from the server, displays it so that the user can check the feedback within the app, and provides an audio playback function.

[0877] Step 11:

[0878] User

[0879] Users can check the feedback in the app and receive specific advice by playing back the audio data. For example, they can receive advice such as "When listening to a customer, take a pause before responding," which they can use to improve their next customer service experience.

[0880] Through this series of steps, users can record their own customer service interactions and receive accurate feedback through AI analysis, enabling them to provide tailored training and guidance to individual crew members and improve their customer service skills.

[0881] Example 1

[0882] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0883] Using voice data to improve customer service skills has been difficult to do efficiently with conventional approaches. Providing timely and accurate individual feedback is particularly important. Furthermore, there is a lack of data for nationwide comparative analysis of customer service quality, and no standard method for improving customer service skills has been established.

[0884] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0885] In this invention, the server includes means for recording voice data, means for converting the recorded voice data into text data, means for transmitting the text data and contract information to the server, means for using generative artificial intelligence to analyze the text data, means for generating advice based on the analysis results, means for converting the generated advice into voice data, means for transmitting the advice and voice data to a terminal, and means for receiving, displaying, and playing the advice and voice data on the terminal. This allows users to efficiently receive individual feedback and improve their customer service skills. Furthermore, analysis by the generative artificial intelligence allows data to be compared and analyzed on a nationwide scale, establishing a standard method for improving customer service skills.

[0886] "Voice data" is digital data that records the user's speech or voice.

[0887] "Recording" is the operation or process of storing audio data in digital form.

[0888] "Text data" refers to character string data obtained by transcribing voice data.

[0889] "Deal information" is information indicating whether the user's customer service resulted in a deal or not.

[0890] A "server" is a computer system that receives, analyzes, and transmits data over a network.

[0891] "Generative artificial intelligence" is an AI technology that learns using large amounts of data, analyzes text data, and generates feedback.

[0892] "Analyzing" is the process of analyzing the content of text data and extracting important elements.

[0893] "Feedback" refers to advice and information on improvements provided to users based on the analysis results.

[0894] "Speech synthesis" is a technology that converts text data into voice data.

[0895] A "terminal" is a device that is directly operated by a user, such as a smartphone or tablet.

[0896] "Reception" refers to an operation in which a terminal acquires data from a server or the like.

[0897] "Display" refers to the ability to show text and graphical information to the user on the terminal.

[0898] "Playback" is a function that converts voice data into an acoustic signal on the terminal and allows the user to hear it.

[0899] The present invention is a voice recording and analysis system for improving the customer service skills of crew members. The configuration and specific operation of this system will be described below.

[0900] Overall system configuration

[0901] This system includes a terminal that records the user's voice during customer service, a server that analyzes the recorded data, and generative artificial intelligence to generate and provide feedback.

[0902] User operations

[0903] The user launches the voice recording application on their smartphone or tablet. They tap the record button to record the customer service voice, and when they're done, they tap the stop recording button. They then name and save the audio file, and upload it to the server within the app. At this time, they also enter deal information such as whether the deal was closed or not.

[0904] Terminal handling

[0905] The device converts the saved voice file into text data using a voice recognition engine (e.g., Google Speech-to-Text). For example, the recorded voice data "Hello, how can I help you today?" is converted into text data. The generated text data and the contract information are then sent to the server.

[0906] Server Processing

[0907] The server analyzes the received text data and closing information. Generative artificial intelligence (such as ChatGPT) is used for the analysis. The server evaluates customer service skills based on the text data and generates an analysis result. For example, the analysis result may be, "You need to ask the customer for more specific information about their request."

[0908] Generate feedback

[0909] Based on the analysis results, the server generates advice and suggestions for improving customer service. For example, it generates feedback such as, "It would be good if you try to ask customers more specific questions." This feedback is converted into audio data using a speech synthesis engine (for example, Google Text-to-Speech). Specifically, the advice text is sent to a speech synthesis API, and the generated audio file is obtained.

[0910] Receive feedback on your device

[0911] The device receives the advice and audio data sent from the server and displays and plays it back within the app. The user can check this feedback and understand specific areas for improvement. For example, the user may receive audio feedback through the app such as, "Please try to listen to the customer more slowly."

[0912] Specific examples

[0913] When user Tanaka records a sales conversation, the audio data is converted into text, such as "Hello, how can I help you today?" Tanaka's smartphone sends the text data and the closing information to the server, which then generates advice such as "You should listen more slowly to what the customer is saying." This advice is converted into audio data and sent to Tanaka's smartphone. Tanaka can review the advice through the app and play it back as audio to improve his customer service skills.

[0914] Prompt Sentence Examples

[0915] "I recorded my customer service. Please transcribe this audio and give me feedback on my customer service skills."

[0916] By using this system, users can efficiently receive individual feedback and improve their customer service skills. Furthermore, by collecting and comparing data on a national scale, it is expected that more accurate advice can be provided and customer service skills can be standardized and improved overall.

[0917] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0918] Step 1:

[0919] The user starts the application on their smartphone or tablet and taps the record button to record the voice of the customer service. The input is the user's voice while the customer service is being served, and the output is the recorded voice data. For example, the user presses the "Start Recording" button and speaks the contents of the customer service.

[0920] Step 2:

[0921] When the user taps the stop recording button, the device saves the recorded audio data to local storage. The input is the recorded audio data, and the output is the saved audio file. The user names the file. For example, the audio file is saved as "Sales Talk_20231001".

[0922] Step 3:

[0923] The device converts the saved audio file into text data using a speech recognition engine (e.g., Google Speech-to-Text). The input is the saved audio file, and the output is the generated text data. For example, the recorded "Hello, how can I help you today?" is converted into text data.

[0924] Step 4:

[0925] The terminal sends the generated text data and the contract information together to the server. The input is the text data and the contract information, and the output is a POST request to the server. For example, the text data and the contract information "unconcluded" are sent to the server.

[0926] Step 5:

[0927] The server analyzes the received text data and contract information. This analysis is performed using generative artificial intelligence (for example, ChatGPT). The input is the text data and contract information, and the output is the analysis result. For example, the analysis result may be, "We need to listen more specifically to the customer's requests."

[0928] Step 6:

[0929] Based on the analysis results, the server uses generative artificial intelligence to generate improvements and advice for customer service. The input is the analysis results, and the output is the generated feedback text. For example, it generates advice such as, "It would be a good idea to try to ask customers more specific questions."

[0930] Step 7:

[0931] The server converts the generated feedback into voice data using a speech synthesis engine (e.g., Google Text-to-Speech). The input is the feedback text, and the output is voice data. For example, voice data such as "Please try to listen more slowly to what the customer is saying" is generated.

[0932] Step 8:

[0933] The terminal receives the voice data and feedback text sent from the server. The input is the response data from the server, and the output is the received voice data and feedback text. For example, the terminal receives feedback from the server.

[0934] Step 9:

[0935] The user checks the feedback text and audio displayed in the app and plays it back. The input is the received audio data and feedback text, and the output is the recognized feedback. For example, the user checks and plays back advice such as "Try to listen more slowly to what the customer is saying."

[0936] (Application example 1)

[0937] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0938] In the modern hospitality industry, individual feedback is essential for store crew members to effectively improve their customer service skills. However, there are currently few ways to efficiently provide such feedback in daily work. Furthermore, there is no established system for obtaining consistent, high-quality feedback, which slows down crew members' growth.

[0939] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0940] In this invention, the server includes: [means for generating advice based on the analysis results using generative artificial intelligence]; [means for playing back the generated advice as advice using voice synthesis]; and [means including data analysis means for comparing and analyzing data from across the country.] This enables [crew members to receive consistent, high-quality feedback to efficiently and effectively improve their customer service skills].

[0941] "Audio data" refers to data that records the audio information uttered by the crew when serving customers.

[0942] "Text data" refers to digital text data that has been transcribed from voice data using a voice recognition engine.

[0943] "Contract information" refers to information regarding whether or not a contract has been concluded and the details of the contract obtained through customer service.

[0944] "Generative AI" is an AI technology that learns from large amounts of data and performs analysis and generates feedback according to specific purposes.

[0945] "Speech synthesis" is a technology that converts text data into voice data.

[0946] A "terminal" is a digital device used by a user, such as a smartphone, tablet, or computer.

[0947] The "data analysis means" is a technology that analyzes the received text data and contract information and generates various statistical data.

[0948] "Analysis results" refer to the evaluations and insights that generative artificial intelligence obtains by analyzing text data.

[0949] "Advice" refers to specific suggestions and guidance generated based on the analysis results to improve the crew's customer service skills.

[0950] The present invention is a voice recording and analysis system for crew members to improve their customer service skills. This system consists of the following main hardware and software:

[0951] Hardware usage example

[0952] 1. Device: A smartphone, tablet, or computer. These devices are used by crew members to record customer service audio and receive feedback.

[0953] 2. Server: A powerful computing device that analyzes data and generates feedback.

[0954] Software usage examples

[0955] 1. Speech recognition engine: Uses the Google Cloud Speech-to-Text API to convert recorded voice data into text data.

[0956] 2. Generative AI: Uses OpenAI GPT-3 or similar AI models to analyze text data and generate appropriate advice.

[0957] 3. Speech synthesis engine: Uses the Google Text-to-Speech API to convert text-based advice into audio data.

[0958] 4. Server-side framework: A framework for managing APIs and sending and receiving data, such as Flask.

[0959] Program processing flow

[0960] 1. Voice recording and transcription:

[0961] The user starts a voice recording application on the device and records the conversation during the customer service session.

[0962] The device converts the recorded audio data into text data using the Google Cloud Speech-to-Text API.

[0963] 2. Data transmission and analysis:

[0964] The converted text data and the contract information are sent to a server via the Internet.

[0965] The server analyzes the received text data using OpenAI GPT-3 generative artificial intelligence.

[0966] 3. Feedback generation and submission:

[0967] Generative AI generates feedback based on the analysis, which is then converted into audio data using the Google Text-to-Speech API.

[0968] The server transmits the generated feedback and voice data to the terminal.

[0969] 4. Receiving and Viewing Feedback:

[0970] The device displays and plays the received feedback and audio data within the application.

[0971] The user reads the displayed feedback and understands specific improvements through audio playback.

[0972] Explanation through concrete examples

[0973] For example, one of the crew members records a customer service response, "Hello, how can I help you today?" This voice data is converted into text data, and a specific prompt, "Generate feedback for this response: Hello, how can I help you today?", is sent to the server. The generative AI analyzes the data and generates feedback such as, "You should listen to the customer more slowly." This feedback is converted into audio data using the Google Text-to-Speech API and sent to the user's device. The user can review this feedback through the application and improve their customer service skills by playing the audio back.

[0974] This allows users to consistently receive high-quality feedback to effectively improve their customer service skills.

[0975] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0976] Step 1:

[0977] The user starts a voice recording application on the device and records the conversation during the customer service session.

[0978] Input: Crew member's voice

[0979] Output: Recorded audio data

[0980] Specific operation: The user taps the "Start Recording" button on the recording app to record the customer conversation. When recording is finished, the user taps the "Stop Recording" button to save the audio data.

[0981] Step 2:

[0982] The device converts the recorded audio data into text data using the Google Cloud Speech-to-Text API.

[0983] Input: Recorded audio data

[0984] Output: Converted text data

[0985] Specific operation: Sends recorded audio data to the Google Cloud Speech-to-Text API, performs speech recognition, and receives text data returned by the API.

[0986] Step 3:

[0987] The terminal transmits the converted text data and the transaction information to the server.

[0988] Input: Text data and contract information

[0989] Output: Data sent to the server

[0990] Specific operation: The user enters the transaction information into the app, and the device sends the text data and transaction information together to the server as an HTTP request.

[0991] Step 4:

[0992] The server analyzes the received text data using generative artificial intelligence.

[0993] Input: Received text data

[0994] Output: Analysis results and feedback text

[0995] Specific operation: The server calls OpenAI GPT-3, inputs the prompt "Generate feedback for this customer service: [text data]", and obtains the analysis results.

[0996] Step 5:

[0997] The server converts the generated feedback into audio data using the Google Text-to-Speech API.

[0998] Input: Feedback text

[0999] Output: Generated feedback audio data

[1000] Specific operation: The parsed feedback text is sent to the Google Text-to-Speech API to generate audio data.

[1001] Step 6:

[1002] The server transmits the generated feedback and voice data to the terminal.

[1003] Input: Feedback text and audio data

[1004] Output: Data sent to the terminal

[1005] Specific operation: The server sends the generated feedback text and audio data to the device as an HTTP response.

[1006] Step 7:

[1007] The device displays and plays the received feedback and audio data within the application.

[1008] Input: Received feedback text and audio data

[1009] Output: User feedback viewing and playback

[1010] Specific behavior: The device displays the feedback text on the screen and provides a button to play the audio data. When the user taps the button, the audio feedback is played.

[1011] This allows users to record themselves, have the audio data analyzed, and receive feedback to improve their customer service skills.

[1012] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1013] The present invention is a voice recording, analysis, and feedback system for improving crew customer service skills, combined with user emotion recognition, which allows for more personalized advice based on the user's emotions.

[1014] Overall system configuration

[1015] This system consists of a device that records the user's customer service, a server that analyzes the recorded data, a generative artificial intelligence to generate and provide feedback, and an emotion engine that recognizes the user's emotions.

[1016] User operations

[1017] The user uses their smartphone, tablet, or other device to launch an application to record the customer service interaction. They tap the record button to start recording the interaction, and when they're done, they tap the stop recording button. They then name and save the recorded audio file, select the audio file within the app, and upload it to the server. At this time, they also enter information on whether the transaction was successful or not.

[1018] Terminal handling

[1019] The device uses a speech recognition engine (such as Google Speech-to-Text) to convert the recorded audio file into text data, generating recognized text data. It also uses an emotion engine to detect the user's emotions from the recorded audio and text data. For example, it can recognize emotions such as "joy," "anger," and "sadness" by analyzing the user's tone of voice and phrasing.

[1020] Server Processing

[1021] The server analyzes the received text data, sales information, and emotional information. Generative AI is used for the analysis, and customer service skills are evaluated based on the content of the text data and the user's emotions. The generative AI learns from a large amount of crew data and is able to generate optimal feedback.

[1022] Generate feedback

[1023] Based on the analysis results, the server generates optimal advice that takes into account emotional information. For example, if the user expresses anger, the server can generate specific advice such as "respond in a calm tone."

[1024] Conversion to audio data

[1025] The generated advice is then converted into voice data using speech synthesis technology. This voice data is sent to the device and can be played back and listened to by the user. For example, specific advice such as "Try to listen more slowly when the customer speaks" can be generated using speech synthesis and provided to the user.

[1026] Receive feedback on your device

[1027] The device receives the advice and audio data sent from the server and displays and plays it back within the app. By checking this feedback and playing it back aloud, users can understand where they need to improve and use it for their next customer service encounter.

[1028] As a concrete example, if user Tanaka records a sales pitch, the audio data is converted into text such as "Hello, how can I help you today?", and at the same time, the emotion engine recognizes Tanaka's emotion as "slightly nervous." Tanaka's smartphone sends the text data, emotional information, and sales information to the server, which then generates advice such as "Take a more relaxed attitude toward customers." This advice is converted into audio data and sent to Tanaka's smartphone. Tanaka can check the advice through the app, play back the audio, and improve on the "relaxed conversation with customers" aspect, which can be used for the next customer service encounter.

[1029] This system allows users to understand their own emotional state while improving their customer service skills, and makes it possible to provide optimized training and guidance to individual crew members. By collecting and comparing data on a national scale, it is expected that more accurate advice can be provided, leading to an improved closing rate.

[1030] The processing flow will be explained below.

[1031] Step 1:

[1032] User

[1033] The user launches the app and starts recording the conversation. Specifically, the user taps the "Start Recording" button to record the conversation.

[1034] Step 2:

[1035] User

[1036] Once the customer service is finished, the user taps the "Stop Recording" button to end the recording. The recording file is saved with a name. For example, it can be saved as "20231005_Customer Service Recording".

[1037] Step 3:

[1038] User

[1039] Select the recorded audio file in the app and enter the deal information (e.g., "Sold" or "Not Sold"), then tap the upload button to send the audio file and the deal information to the server.

[1040] Step 4:

[1041] Terminal

[1042] The device receives the recorded audio file and calls a speech recognition engine (such as Google Speech-to-Text) to convert the audio file into text data, which is then stored on the device.

[1043] Step 5:

[1044] Terminal

[1045] The recorded voice file is passed to the emotion engine, which analyzes the user's emotions. The emotion engine analyzes the user's tone of voice and vocabulary to identify emotions such as "joy," "anger," and "sadness."

[1046] Step 6:

[1047] Terminal

[1048] The converted text data, the recognized emotion information, and the transaction information are sent to the server. The app notifies you whether the transmission was successful or not.

[1049] Step 7:

[1050] server

[1051] The server analyzes the received text data, sentiment information, and sales information. A generative artificial intelligence (AI model) analyzes this data and identifies areas for improvement, such as "listening more specifically to what the customer is saying."

[1052] Step 8:

[1053] server

[1054] Based on the analysis results, the system generates optimal advice, taking emotional information into account, such as "Try to maintain a relaxed atmosphere when interacting with customers."

[1055] Step 9:

[1056] server

[1057] The generated advice is passed to a speech synthesis engine and converted into voice data. For example, voice data such as "Try to listen more carefully to what the customer is saying" is generated.

[1058] Step 10:

[1059] server

[1060] The generated advice and its audio data are sent to the device. The server checks whether the transmission was successful.

[1061] Step 11:

[1062] Terminal

[1063] The device receives the advice and audio data sent from the server and makes them available for display and playback within the app. Specifically, the text-format advice is displayed and the audio-format advice is played back.

[1064] Step 12:

[1065] User

[1066] Review the feedback provided by the user within the app. Play back the audio data to understand areas for improvement. For example, take the advice "Take more time to pause when responding to customers" into consideration and use it for your next customer service encounter.

[1067] Through these processing steps, users can record their own customer service interactions, undergo detailed analysis including sentiment analysis, and receive accurate and personalized feedback. This series of processes enables optimized training and guidance for individual crew members, aiming to improve their customer service skills.

[1068] Example 2

[1069] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1070] In customer service, voice recording, analysis, and feedback are necessary to improve the customer service skills of crew members, and more personalized advice is required by combining it with emotion recognition functions. It is also important to collect and compare data on a national scale to provide more accurate feedback and improve the closing rate.

[1071] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: [means for recording voice data]; [means for converting the recorded voice data into text data]; [means for using an emotion recognition engine to detect emotions from the voice data and the converted text data]; [means for transmitting the text data, contract information, and emotion information to the server]; [means for using generative artificial intelligence to analyze the text data and emotion information]; [means for generating advice based on the analysis results]; [means for converting the generated advice into voice data]; [means for transmitting the advice and voice data to the terminal]; and [means for receiving, displaying, and playing the advice and voice data at the terminal]. This makes it possible to receive appropriate feedback while understanding the user's emotional state and improve customer service skills.

[1072] "Audio data" is data that represents in digital form the audio recorded by a user using a terminal.

[1073] "Text data" refers to data obtained by converting voice data into text format using a voice recognition engine.

[1074] An "emotion recognition engine" is software that analyzes a user's tone of voice and vocabulary from voice and text data to detect emotions.

[1075] "Generative AI" is an AI technology that learns from past data and generates feedback based on the analysis results.

[1076] "Feedback" refers to advice for improvement based on the user's customer service experience and emotional state.

[1077] A "voice recognition engine" is software that analyzes voice data and converts it into corresponding character data (text data).

[1078] "Speech synthesis technology" is a technology that analyzes text data and generates its contents as voice data.

[1079] "Device" means a device (such as a smartphone or tablet) for recording, storing, and transmitting audio data, and for receiving and playing feedback.

[1080] A "server" is a computing system that analyzes various types of data (voice data, text data, emotional information), generates feedback, and manages communication with terminals.

[1081] "Advice" refers to instructions and suggestions for improvement generated based on customer service content and emotional data analyzed by generative artificial intelligence.

[1082] "Contract information" is data indicating whether the customer service resulted in a contract.

[1083] MODE FOR CARRYING OUT THE INVENTION

[1084] The present invention is a voice recording, analysis, and feedback system for improving crew customer service performance, which combines emotion recognition functionality. This system enables personalized advice based on the user's emotions. Specific embodiments for implementing the present invention are described below.

[1085] Overall system configuration

[1086] This system consists of a device that records the user's customer service, a server that analyzes the recorded data, generative artificial intelligence to generate and provide feedback, and an emotion recognition engine that recognizes the user's emotions.

[1087] User operations

[1088] The user uses their smartphone, tablet, or other device to launch an application to record the customer service interaction. They tap the record button to start recording the interaction, and when they're done, they tap the stop recording button. They then name and save the recorded audio file, select the audio file within the app, and upload it to the server. At this time, they also enter information on whether the transaction was successful or not.

[1089] Terminal handling

[1090] The device uses a speech recognition engine (such as Google Speech-to-Text) to convert the recorded audio file into text data, generating recognized text data. It also uses an emotion recognition engine to detect the user's emotions from the recorded audio and text data. For example, it can recognize emotions such as "joy," "anger," and "sadness" by analyzing the user's tone of voice and phrasing.

[1091] Server Processing

[1092] The server analyzes the received text data, sales information, and emotional information. Generative AI is used for the analysis, and customer service skills are evaluated based on the content of the text data and the user's emotions. This generative AI learns from a large amount of crew data and is able to generate optimal feedback.

[1093] Generate feedback

[1094] Based on the analysis results, the server generates optimal advice that takes into account emotional information. For example, if the user expresses anger, the server can generate specific advice such as "respond in a calm tone."

[1095] Conversion to audio data

[1096] The generated advice is then converted into voice data using speech synthesis technology. This voice data is sent to the device and can be played back and listened to by the user. For example, specific advice such as "Try to listen more slowly when the customer speaks" can be generated using speech synthesis and provided to the user.

[1097] Receive feedback on your device

[1098] The device receives the advice and audio data sent from the server and displays and plays it back within the app. By checking this feedback and playing it back aloud, users can understand where they need to improve and use it for their next customer service encounter.

[1099] Specific examples

[1100] For example, if user Tanaka records a sales pitch, the audio data is converted into text such as "Hello, how can I help you today?", and at the same time, the emotion recognition engine recognizes Tanaka's emotion as "slightly nervous." Tanaka's smartphone sends the text data, emotional information, and sales information to the server, which then generates advice such as "Take a more relaxed attitude toward customers." This advice is converted into audio data and sent to Tanaka's smartphone. Tanaka can review the advice through the app, play back the audio, and improve on the "relaxed conversation with customers" aspect, which can be applied to the next customer service encounter.

[1101] Examples of prompt statements

[1102] The following prompt sentences can be input to the generative AI model:

[1103] "Analyze customer service speech and generate effective feedback that includes the user's emotional information. For example, give advice based on the language and tone used during the conversation."

[1104] As described above, by using this system, users can improve their customer service skills while understanding their own emotional state. In addition, the system provides optimized education and guidance for individual crew members, and by collecting and comparing data on a national scale, it is possible to improve the success rate.

[1105] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1106] Step 1:

[1107] Users simply launch the application on their smartphone or tablet and tap the record button to record the audio of their customer service.

[1108] What it does: Your phone will use the device's microphone to record audio in real time and store it as a digital audio file in the background.

[1109] Input: Tap action to start recording.

[1110] Output: The audio data being recorded.

[1111] Step 2:

[1112] When the user has finished serving the customer, they tap the stop recording button and save the recorded audio file.

[1113] Specific operation: The device detects the tap action of the stop recording button, saves the audio data recorded up to that point as a temporary file, and prompts the user to enter a file name.

[1114] Input: Tap action to stop recording and input file name.

[1115] Output: The named audio file.

[1116] Step 3:

[1117] Users select an audio file within the app, upload it to the server, and enter information about successful and unsuccessful transactions.

[1118] Specific operation: The terminal encodes the audio file selected by the user and the transaction information and sends them to the server.

[1119] Input: Select an audio file and enter deal information.

[1120] Output: Sending audio files and deal information to the server.

[1121] Step 4:

[1122] The server uses a speech recognition engine (such as Google Speech-to-Text) to convert the received audio file into text data.

[1123] Specific operation: The server passes the voice data to the voice recognition engine and obtains the recognized text data as the result.

[1124] Input: An audio file.

[1125] Output: Text data.

[1126] Step 5:

[1127] The server uses an emotion recognition engine to detect the user's emotions from the audio file and text data.

[1128] Specific operation: The server analyzes the tone of the voice data and the content of the text data, and uses an emotion recognition engine to identify emotions such as "joy," "anger," and "sadness."

[1129] Input: Audio files and text data.

[1130] Output: Emotional information.

[1131] Step 6:

[1132] The server uses generative artificial intelligence to analyze the received text data, closing information, and sentiment information.

[1133] Specific operation: The server inputs data into a generative artificial intelligence (AI model) and performs analysis, which evaluates customer service skills.

[1134] Input: Text data, closing information, and sentiment information.

[1135] Output: Customer service skills evaluation results.

[1136] Step 7:

[1137] Based on the analysis results, the server generates optimal advice that takes emotional information into consideration.

[1138] Specific operation: The generative artificial intelligence generates appropriate feedback in text format from the analysis results.

[1139] Input: Customer service skills evaluation results.

[1140] Output: Advice in text format.

[1141] Step 8:

[1142] The server converts the generated advice into voice data using voice synthesis technology.

[1143] Specific operation: The server passes the generated text advice to a speech synthesis engine (such as Google Text-to-Speech) to generate it as audio data.

[1144] Input: Advice in text format.

[1145] Output: Audio data.

[1146] Step 9:

[1147] The device receives the advice and audio data sent from the server and displays and plays it back within the app.

[1148] Specific behavior: The device displays the received data within the app and provides an interface for playing audio advice.

[1149] Input: Advice and audio data received from the server.

[1150] Output: The displayed advice and the audio data played.

[1151] This process flow allows the user to obtain feedback to efficiently improve their customer service skills.

[1152] (Application example 2)

[1153] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1154] Conventional customer service training systems have problems: it takes time to improve a crew's customer service skills, and it is difficult to provide personalized feedback because they do not take into account factors such as emotion recognition.Furthermore, it is not possible to compare data nationwide, making it difficult to propose effective improvement measures based on a wide range of data.

[1155] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1156] In this invention, the server includes: [means for generating advice based on the analysis results]; [means for converting the generated advice into voice data]; and [means for using an emotion recognition engine that recognizes emotions from the user's tone of voice and vocabulary]. This makes it possible to efficiently provide personalized advice that takes into account the emotional state of each crew member in order to improve customer service skills. In addition, by comparing and analyzing nationwide data, it becomes possible to propose more accurate improvement measures.

[1157] "Means for recording voice data" refers to a device or software for recording the voice of the crew member providing service as digital data.

[1158] "Means for converting recorded voice data into text data" refers to technology that uses a voice recognition engine to convert recorded voice data into text.

[1159] The "means for transmitting the text data and the transaction information to the server" refers to a communication device or protocol for sending the converted text data and the transaction information to the server via the Internet.

[1160] "Means using generative artificial intelligence to analyze text data" refers to artificial intelligence techniques used to analyze the content of text data and generate optimal feedback.

[1161] "Means for generating advice based on analysis results" refers to the process of creating specific advice for improving customer service skills from the analysis results of generative artificial intelligence.

[1162] The "means for converting the generated advice into voice data" refers to using a voice synthesis technique to output the generated advice in text format as voice.

[1163] "Means for transmitting advice and voice data to a terminal" refers to a communication means for transmitting the generated advice and voice data to the terminal of the crew member who served the customer.

[1164] "Means for receiving, displaying and playing advice and audio data at the terminal" refers to a playback function that displays the advice and audio data received on the terminal and allows the user to listen to it aloud.

[1165] "Using an emotion recognition engine to recognize emotions from a user's tone of voice and phrasing" refers to algorithms or systems used to analyze and recognize a user's emotions from voice or text data.

[1166] The "means for generating feedback based on emotion recognition results" refers to a process for providing specific feedback based on the user's emotions, based on the analysis results of the emotion recognition engine.

[1167] "Data analysis tools for comparing and analyzing nationwide data" refers to software or algorithms used to statistically compare and analyze collected customer service data on a nationwide scale.

[1168] "Means using neural networks to generate advice and voice data" refers to a process that utilizes deep learning-based neural network algorithms to generate advice and optimize voice data.

[1169] This invention is a voice recording, analysis and feedback system for improving the customer service skills of crew members, and is characterized by its incorporation of a user emotion recognition function. This system is realized using a voice recognition engine, generative artificial intelligence, an emotion recognition engine and voice synthesis technology.

[1170] Overall system configuration

[1171] This system consists of a device that records the user's customer service speech, a server that analyzes the recorded data, and a generative artificial intelligence and emotion engine that generate and provide feedback. By linking these elements together, advanced support for improving customer service skills is realized.

[1172] User operations

[1173] The user launches a dedicated application to record the audio of customer service using their own device, such as a smartphone or tablet. They tap the record button to record the audio of the customer service, and then tap the stop recording button when they are finished. They then name and save the recorded audio file, select the audio file within the app, and upload it to the server. At this time, they also enter information on whether the deal was successful or not.

[1174] Terminal handling

[1175] The device converts the recorded audio file into text data using a speech recognition engine (e.g., Google Speech-to-Text). It also uses an emotion recognition engine to detect the user's emotions from the recorded audio and text data. For example, it can recognize emotions such as "joy," "anger," and "sadness" by analyzing the user's tone of voice and phrasing.

[1176] Server Processing

[1177] The server analyzes the received text data, sales information, and emotional information. Generative AI (e.g., a neural network using deep learning) is used for the analysis, and customer service skills are evaluated based on the content of the text data and the user's emotions. Generative AI learns from large amounts of data and is able to generate optimal feedback.

[1178] Generate feedback

[1179] Based on the analysis results, the server generates optimal advice that takes into account the user's emotional information. For example, if the user expresses anger, the server generates specific advice such as "respond in a calm tone."

[1180] Conversion to audio data

[1181] The generated advice is converted into voice data using voice synthesis technology, which is then sent to the terminal and played back for the user to listen to.

[1182] Receive feedback on your device

[1183] The device receives advice and audio data sent from the server and can display and play it back within the app. By checking this feedback and playing it back aloud, users can understand what they need to improve and use it for their next customer service encounter.

[1184] Specific examples

[1185] For example, when a user is explaining a product, the recorded voice data is converted into text such as "The features of this product are...", and at the same time, the emotion recognition engine recognizes the user's emotion as "not confident." Based on this text data and emotional information, the server generates advice such as "If you explain the product's features in more detail, I will be able to speak with more confidence," converts this into voice data, and sends it to the user's smartphone. The user can check this advice through the app, play back the audio, and use it for their next customer service encounter.

[1186] Prompt Sentence Examples

[1187] "Customer service: The features of this product are...

[1188] Customer sentiment: Unsure

[1189] Tip: Explain your product's features in more detail to help you feel more confident.

[1190] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1191] Step 1:

[1192] The user starts a recording application on their smartphone or tablet and records the voice of the customer while serving the customer. They tap the record button to record the voice of the customer, and press the stop recording button when finished. At this time, the input is the customer service voice data, and the recorded voice file is saved as the output.

[1193] Step 2:

[1194] The device converts the recorded audio file into text data using a speech recognition engine (such as Google Speech-to-Text). The input is an audio file, and text data is generated as output. This text data includes what was said during the customer service.

[1195] Step 3:

[1196] Using an emotion recognition engine, the device detects the user's emotions from the recorded voice data and converted text data. The input is voice and text data, and the output is the emotion recognition results, which include emotional information such as "joy," "anger," and "sadness."

[1197] Step 4:

[1198] The terminal transmits the generated text data, closing information, and emotion information to the server. The input is the text data, closing information, and emotion information, and the output is uploaded to the server.

[1199] Step 5:

[1200] The server analyzes the received text data, sales information, and emotional information using generative artificial intelligence (a neural network using deep learning). The input is text data, sales information, and emotional information, and the output is an evaluation of customer service skills. The analysis evaluates which parts are effective and which parts have room for improvement.

[1201] Step 6:

[1202] The server generates optimal advice based on the analysis results, taking into account emotional information. For example, if the emotion of "anger" is detected, specific advice such as "respond in a calm tone" is generated. The input is the analysis results and emotional information, and the output is text data of the advice.

[1203] Step 7:

[1204] The generated advice is converted into voice data by the server using voice synthesis technology. The input is text data of the advice, and the output is voice data of the advice.

[1205] Step 8:

[1206] The server sends the generated advice and voice data to the terminal. The input is the voice data and text data of the advice, and these are sent to the terminal as output.

[1207] Step 9:

[1208] The device receives the advice and audio data sent from the server and displays and plays it back within the app. The user can check this feedback and play it back aloud to understand their own customer service skills and apply them to their next customer service encounter. The input is the advice audio data and text data, and the output is display and audio playback.

[1209] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1210] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1211] 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 the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1212] [Fourth embodiment]

[1213] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1214] 7, a 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.

[1215] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1216] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1217] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1218] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1219] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1220] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1221] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1222] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1223] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1224] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1225] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1226] The present invention is a voice recording and analysis system for improving the customer service skills of crew members. With this system, users can record their own customer service, send the recording data to a server, and receive appropriate feedback, allowing them to receive personalized guidance.

[1227] Overall system configuration

[1228] This system consists of a device that records the user's customer service, a server that analyzes the recorded data, and generative artificial intelligence to generate and provide feedback.

[1229] User operations

[1230] The user uses their smartphone, tablet, or other device to launch an application to record the customer service interaction. They tap the record button to start recording the interaction, and when they're done, they tap the stop recording button. They then name and save the recorded audio file, select the audio file within the app, and upload it to the server. At this time, they also enter information on whether the transaction was successful or not.

[1231] Terminal handling

[1232] The device uses a speech recognition engine (such as Google Speech-to-Text) to convert the recorded audio file into text data, transcribes the audio file, and sends the generated text data and transaction information to the server.

[1233] Server Processing

[1234] The server analyzes the received text data and sales information. The analysis is performed using generative AI, and customer service skills are evaluated based on the content of the text data. The generative AI learns from a large amount of crew data and is able to generate optimal feedback.

[1235] Generate feedback

[1236] The server generates advice and suggestions for improving customer service based on the analysis results. For example, if the generative AI finds an area for improvement such as "You need to ask customers more specifically about their requests," it can generate advice such as "You should try to ask customers more specific questions."

[1237] Conversion to audio data

[1238] The generated advice is then converted into voice data using speech synthesis technology. This voice data is sent to the device and can be played back and listened to by the user. For example, specific advice such as "Try to listen more slowly when the customer speaks" can be generated using speech synthesis and provided to the user.

[1239] Receive feedback on your device

[1240] The device receives the advice and audio data sent from the server and displays and plays it back within the app. By checking this feedback and playing it back aloud, users can understand where they need to improve and use it for their next customer service encounter.

[1241] As a concrete example, if user Tanaka records a sales conversation, the audio data is converted into text such as "Hello, how can I help you today?" Tanaka's smartphone sends the text data and the sales contract information to the server, which then generates advice such as "You should listen more slowly to what the customer is saying." This advice is converted into audio data and sent to Tanaka's smartphone. Tanaka can check the advice through the app and play it back as audio to improve his customer service skills.

[1242] This system allows us to provide optimal feedback to individual crew members and improve their customer service skills. By collecting and comparing data on a nationwide scale, we can provide more accurate advice and expect to improve our success rate.

[1243] The processing flow will be explained below.

[1244] Step 1:

[1245] User

[1246] The user launches the app and starts recording the customer service. Specifically, the user taps the "Start Recording" button and starts voice input.

[1247] Step 2:

[1248] User

[1249] Once the customer service is finished, the user taps the "Stop Recording" button to end the recording. Then, the recording file is saved with a name, for example, "20231005_Customer Service Recording."

[1250] Step 3:

[1251] User

[1252] Select the recorded file in the app and enter the transaction information (e.g., "Sold" or "Not Sold" and any comments). Next, tap the upload button to send the audio file and transaction information to the server.

[1253] Step 4:

[1254] Terminal

[1255] The device receives the recorded audio file and converts it into text data by calling a speech recognition engine (such as Google Speech-to-Text). The recognized text data is generated.

[1256] Step 5:

[1257] Terminal

[1258] The converted text data and the contract information are sent to the server. If the transmission is successful, the user is notified within the app.

[1259] Step 6:

[1260] server

[1261] The server analyzes the received text data and contract information. Using generative artificial intelligence (e.g., a deep learning model), the received data is analyzed to evaluate customer service and identify areas for improvement.

[1262] Step 7:

[1263] server

[1264] Based on the analysis results, the system generates optimal advice, such as "You need to show more empathy for your customers."

[1265] Step 8:

[1266] server

[1267] The generated advice is passed to a speech synthesis engine and converted into voice data, such as "It is important to show empathy to customers."

[1268] Step 9:

[1269] server

[1270] The generated advice and audio data are sent to the device. If the transfer is successful, the user is notified within the app.

[1271] Step 10:

[1272] Terminal

[1273] The device receives the advice and audio data sent from the server, displays it so that the user can check the feedback within the app, and provides an audio playback function.

[1274] Step 11:

[1275] User

[1276] Users can check the feedback in the app and receive specific advice by playing back the audio data. For example, they can receive advice such as "When listening to a customer, take a pause before responding," which they can use to improve their next customer service experience.

[1277] Through this series of steps, users can record their own customer service interactions and receive accurate feedback through AI analysis, enabling them to provide tailored training and guidance to individual crew members and improve their customer service skills.

[1278] Example 1

[1279] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1280] Using voice data to improve customer service skills has been difficult to do efficiently with conventional approaches. Providing timely and accurate individual feedback is particularly important. Furthermore, there is a lack of data for nationwide comparative analysis of customer service quality, and no standard method for improving customer service skills has been established.

[1281] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1282] In this invention, the server includes means for recording voice data, means for converting the recorded voice data into text data, means for transmitting the text data and contract information to the server, means for using generative artificial intelligence to analyze the text data, means for generating advice based on the analysis results, means for converting the generated advice into voice data, means for transmitting the advice and voice data to a terminal, and means for receiving, displaying, and playing the advice and voice data on the terminal. This allows users to efficiently receive individual feedback and improve their customer service skills. Furthermore, analysis by the generative artificial intelligence allows data to be compared and analyzed on a nationwide scale, establishing a standard method for improving customer service skills.

[1283] "Voice data" is digital data that records the user's speech or voice.

[1284] "Recording" is the operation or process of storing audio data in digital form.

[1285] "Text data" refers to character string data obtained by transcribing voice data.

[1286] "Deal information" is information indicating whether the user's customer service resulted in a deal or not.

[1287] A "server" is a computer system that receives, analyzes, and transmits data over a network.

[1288] "Generative artificial intelligence" is an AI technology that learns using large amounts of data, analyzes text data, and generates feedback.

[1289] "Analyzing" is the process of analyzing the content of text data and extracting important elements.

[1290] "Feedback" refers to advice and information on improvements provided to users based on the analysis results.

[1291] "Speech synthesis" is a technology that converts text data into voice data.

[1292] A "terminal" is a device that is directly operated by a user, such as a smartphone or tablet.

[1293] "Reception" refers to an operation in which a terminal acquires data from a server or the like.

[1294] "Display" refers to the ability to show text and graphical information to the user on the terminal.

[1295] "Playback" is a function that converts voice data into an acoustic signal on the terminal and allows the user to hear it.

[1296] The present invention is a voice recording and analysis system for improving the customer service skills of crew members. The configuration and specific operation of this system will be described below.

[1297] Overall system configuration

[1298] This system includes a terminal that records the user's voice during customer service, a server that analyzes the recorded data, and generative artificial intelligence to generate and provide feedback.

[1299] User operations

[1300] The user launches the voice recording application on their smartphone or tablet. They tap the record button to record the customer service voice, and when they're done, they tap the stop recording button. They then name and save the audio file, and upload it to the server within the app. At this time, they also enter deal information such as whether the deal was closed or not.

[1301] Terminal handling

[1302] The device converts the saved voice file into text data using a voice recognition engine (e.g., Google Speech-to-Text). For example, the recorded voice data "Hello, how can I help you today?" is converted into text data. The generated text data and the contract information are then sent to the server.

[1303] Server Processing

[1304] The server analyzes the received text data and closing information. Generative artificial intelligence (such as ChatGPT) is used for the analysis. The server evaluates customer service skills based on the text data and generates an analysis result. For example, the analysis result may be, "You need to ask the customer for more specific information about their request."

[1305] Generate feedback

[1306] Based on the analysis results, the server generates advice and suggestions for improving customer service. For example, it generates feedback such as, "It would be good if you try to ask customers more specific questions." This feedback is converted into audio data using a speech synthesis engine (for example, Google Text-to-Speech). Specifically, the advice text is sent to a speech synthesis API, and the generated audio file is obtained.

[1307] Receive feedback on your device

[1308] The device receives the advice and audio data sent from the server and displays and plays it back within the app. The user can check this feedback and understand specific areas for improvement. For example, the user may receive audio feedback through the app such as, "Please try to listen to the customer more slowly."

[1309] Specific examples

[1310] When user Tanaka records a sales conversation, the audio data is converted into text, such as "Hello, how can I help you today?" Tanaka's smartphone sends the text data and the closing information to the server, which then generates advice such as "You should listen more slowly to what the customer is saying." This advice is converted into audio data and sent to Tanaka's smartphone. Tanaka can review the advice through the app and play it back as audio to improve his customer service skills.

[1311] Prompt Sentence Examples

[1312] "I recorded my customer service. Please transcribe this audio and give me feedback on my customer service skills."

[1313] By using this system, users can efficiently receive individual feedback and improve their customer service skills. Furthermore, by collecting and comparing data on a national scale, it is expected that more accurate advice can be provided and customer service skills can be standardized and improved overall.

[1314] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1315] Step 1:

[1316] The user starts the application on their smartphone or tablet and taps the record button to record the voice of the customer service. The input is the user's voice while the customer service is being served, and the output is the recorded voice data. For example, the user presses the "Start Recording" button and speaks the contents of the customer service.

[1317] Step 2:

[1318] When the user taps the stop recording button, the device saves the recorded audio data to local storage. The input is the recorded audio data, and the output is the saved audio file. The user names the file. For example, the audio file is saved as "Sales Talk_20231001".

[1319] Step 3:

[1320] The device converts the saved audio file into text data using a speech recognition engine (e.g., Google Speech-to-Text). The input is the saved audio file, and the output is the generated text data. For example, the recorded "Hello, how can I help you today?" is converted into text data.

[1321] Step 4:

[1322] The terminal sends the generated text data and the contract information together to the server. The input is the text data and the contract information, and the output is a POST request to the server. For example, the text data and the contract information "unconcluded" are sent to the server.

[1323] Step 5:

[1324] The server analyzes the received text data and contract information. This analysis is performed using generative artificial intelligence (for example, ChatGPT). The input is the text data and contract information, and the output is the analysis result. For example, the analysis result may be, "We need to listen more specifically to the customer's requests."

[1325] Step 6:

[1326] Based on the analysis results, the server uses generative artificial intelligence to generate improvements and advice for customer service. The input is the analysis results, and the output is the generated feedback text. For example, it generates advice such as, "It would be a good idea to try to ask customers more specific questions."

[1327] Step 7:

[1328] The server converts the generated feedback into voice data using a speech synthesis engine (e.g., Google Text-to-Speech). The input is the feedback text, and the output is voice data. For example, voice data such as "Please try to listen more slowly to what the customer is saying" is generated.

[1329] Step 8:

[1330] The terminal receives the voice data and feedback text sent from the server. The input is the response data from the server, and the output is the received voice data and feedback text. For example, the terminal receives feedback from the server.

[1331] Step 9:

[1332] The user checks the feedback text and audio displayed in the app and plays it back. The input is the received audio data and feedback text, and the output is the recognized feedback. For example, the user checks and plays back advice such as "Try to listen more slowly to what the customer is saying."

[1333] (Application example 1)

[1334] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1335] In the modern hospitality industry, individual feedback is essential for store crew members to effectively improve their customer service skills. However, there are currently few ways to efficiently provide such feedback in daily work. Furthermore, there is no established system for obtaining consistent, high-quality feedback, which slows down crew members' growth.

[1336] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1337] In this invention, the server includes: [means for generating advice based on the analysis results using generative artificial intelligence]; [means for playing back the generated advice as advice using voice synthesis]; and [means including data analysis means for comparing and analyzing data from across the country.] This enables [crew members to receive consistent, high-quality feedback to efficiently and effectively improve their customer service skills].

[1338] "Audio data" refers to data that records the audio information uttered by the crew when serving customers.

[1339] "Text data" refers to digital text data that has been transcribed from voice data using a voice recognition engine.

[1340] "Contract information" refers to information regarding whether or not a contract has been concluded and the details of the contract obtained through customer service.

[1341] "Generative AI" is an AI technology that learns from large amounts of data and performs analysis and generates feedback according to specific purposes.

[1342] "Speech synthesis" is a technology that converts text data into voice data.

[1343] A "terminal" is a digital device used by a user, such as a smartphone, tablet, or computer.

[1344] The "data analysis means" is a technology that analyzes the received text data and contract information and generates various statistical data.

[1345] "Analysis results" refer to the evaluations and insights that generative artificial intelligence obtains by analyzing text data.

[1346] "Advice" refers to specific suggestions and guidance generated based on the analysis results to improve the crew's customer service skills.

[1347] The present invention is a voice recording and analysis system for crew members to improve their customer service skills. This system consists of the following main hardware and software:

[1348] Hardware usage example

[1349] 1. Device: A smartphone, tablet, or computer. These devices are used by crew members to record customer service audio and receive feedback.

[1350] 2. Server: A powerful computing device that analyzes data and generates feedback.

[1351] Software usage examples

[1352] 1. Speech recognition engine: Uses the Google Cloud Speech-to-Text API to convert recorded voice data into text data.

[1353] 2. Generative AI: Uses OpenAI GPT-3 or similar AI models to analyze text data and generate appropriate advice.

[1354] 3. Speech synthesis engine: Uses the Google Text-to-Speech API to convert text-based advice into audio data.

[1355] 4. Server-side framework: A framework for managing APIs and sending and receiving data, such as Flask.

[1356] Program processing flow

[1357] 1. Voice recording and transcription:

[1358] The user starts a voice recording application on the device and records the conversation during the customer service session.

[1359] The device converts the recorded audio data into text data using the Google Cloud Speech-to-Text API.

[1360] 2. Data transmission and analysis:

[1361] The converted text data and the contract information are sent to a server via the Internet.

[1362] The server analyzes the received text data using OpenAI GPT-3 generative artificial intelligence.

[1363] 3. Feedback generation and submission:

[1364] Generative AI generates feedback based on the analysis, which is then converted into audio data using the Google Text-to-Speech API.

[1365] The server transmits the generated feedback and voice data to the terminal.

[1366] 4. Receiving and Viewing Feedback:

[1367] The device displays and plays the received feedback and audio data within the application.

[1368] The user reads the displayed feedback and understands specific improvements through audio playback.

[1369] Explanation through concrete examples

[1370] For example, one of the crew members records a customer service response, "Hello, how can I help you today?" This voice data is converted into text data, and a specific prompt, "Generate feedback for this response: Hello, how can I help you today?", is sent to the server. The generative AI analyzes the data and generates feedback such as, "You should listen to the customer more slowly." This feedback is converted into audio data using the Google Text-to-Speech API and sent to the user's device. The user can review this feedback through the application and improve their customer service skills by playing the audio back.

[1371] This allows users to consistently receive high-quality feedback to effectively improve their customer service skills.

[1372] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1373] Step 1:

[1374] The user starts a voice recording application on the device and records the conversation during the customer service session.

[1375] Input: Crew member's voice

[1376] Output: Recorded audio data

[1377] Specific operation: The user taps the "Start Recording" button on the recording app to record the customer conversation. When recording is finished, the user taps the "Stop Recording" button to save the audio data.

[1378] Step 2:

[1379] The device converts the recorded audio data into text data using the Google Cloud Speech-to-Text API.

[1380] Input: Recorded audio data

[1381] Output: Converted text data

[1382] Specific operation: Sends recorded audio data to the Google Cloud Speech-to-Text API, performs speech recognition, and receives text data returned by the API.

[1383] Step 3:

[1384] The terminal transmits the converted text data and the transaction information to the server.

[1385] Input: Text data and contract information

[1386] Output: Data sent to the server

[1387] Specific operation: The user enters the transaction information into the app, and the device sends the text data and transaction information together to the server as an HTTP request.

[1388] Step 4:

[1389] The server analyzes the received text data using generative artificial intelligence.

[1390] Input: Received text data

[1391] Output: Analysis results and feedback text

[1392] Specific operation: The server calls OpenAI GPT-3, inputs the prompt "Generate feedback for this customer service: [text data]", and obtains the analysis results.

[1393] Step 5:

[1394] The server converts the generated feedback into audio data using the Google Text-to-Speech API.

[1395] Input: Feedback text

[1396] Output: Generated feedback audio data

[1397] Specific operation: The parsed feedback text is sent to the Google Text-to-Speech API to generate audio data.

[1398] Step 6:

[1399] The server transmits the generated feedback and voice data to the terminal.

[1400] Input: Feedback text and audio data

[1401] Output: Data sent to the terminal

[1402] Specific operation: The server sends the generated feedback text and audio data to the device as an HTTP response.

[1403] Step 7:

[1404] The device displays and plays the received feedback and audio data within the application.

[1405] Input: Received feedback text and audio data

[1406] Output: User feedback viewing and playback

[1407] Specific behavior: The device displays the feedback text on the screen and provides a button to play the audio data. When the user taps the button, the audio feedback is played.

[1408] This allows users to record themselves, have the audio data analyzed, and receive feedback to improve their customer service skills.

[1409] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1410] The present invention is a voice recording, analysis, and feedback system for improving crew customer service skills, combined with user emotion recognition, which allows for more personalized advice based on the user's emotions.

[1411] Overall system configuration

[1412] This system consists of a device that records the user's customer service, a server that analyzes the recorded data, a generative artificial intelligence to generate and provide feedback, and an emotion engine that recognizes the user's emotions.

[1413] User operations

[1414] The user uses their smartphone, tablet, or other device to launch an application to record the customer service interaction. They tap the record button to start recording the interaction, and when they're done, they tap the stop recording button. They then name and save the recorded audio file, select the audio file within the app, and upload it to the server. At this time, they also enter information on whether the transaction was successful or not.

[1415] Terminal handling

[1416] The device uses a speech recognition engine (such as Google Speech-to-Text) to convert the recorded audio file into text data, generating recognized text data. It also uses an emotion engine to detect the user's emotions from the recorded audio and text data. For example, it can recognize emotions such as "joy," "anger," and "sadness" by analyzing the user's tone of voice and phrasing.

[1417] Server Processing

[1418] The server analyzes the received text data, sales information, and emotional information. Generative AI is used for the analysis, and customer service skills are evaluated based on the content of the text data and the user's emotions. The generative AI learns from a large amount of crew data and is able to generate optimal feedback.

[1419] Generate feedback

[1420] Based on the analysis results, the server generates optimal advice that takes into account emotional information. For example, if the user expresses anger, the server can generate specific advice such as "respond in a calm tone."

[1421] Conversion to audio data

[1422] The generated advice is then converted into voice data using speech synthesis technology. This voice data is sent to the device and can be played back and listened to by the user. For example, specific advice such as "Try to listen more slowly when the customer speaks" can be generated using speech synthesis and provided to the user.

[1423] Receive feedback on your device

[1424] The device receives the advice and audio data sent from the server and displays and plays it back within the app. By checking this feedback and playing it back aloud, users can understand where they need to improve and use it for their next customer service encounter.

[1425] As a concrete example, if user Tanaka records a sales pitch, the audio data is converted into text such as "Hello, how can I help you today?", and at the same time, the emotion engine recognizes Tanaka's emotion as "slightly nervous." Tanaka's smartphone sends the text data, emotional information, and sales information to the server, which then generates advice such as "Take a more relaxed attitude toward customers." This advice is converted into audio data and sent to Tanaka's smartphone. Tanaka can check the advice through the app, play back the audio, and improve on the "relaxed conversation with customers" aspect, which can be used for the next customer service encounter.

[1426] This system allows users to understand their own emotional state while improving their customer service skills, and makes it possible to provide optimized training and guidance to individual crew members. By collecting and comparing data on a national scale, it is expected that more accurate advice can be provided, leading to an improved closing rate.

[1427] The processing flow will be explained below.

[1428] Step 1:

[1429] User

[1430] The user launches the app and starts recording the conversation. Specifically, the user taps the "Start Recording" button to record the conversation.

[1431] Step 2:

[1432] User

[1433] Once the customer service is finished, the user taps the "Stop Recording" button to end the recording. The recording file is saved with a name. For example, it can be saved as "20231005_Customer Service Recording".

[1434] Step 3:

[1435] User

[1436] Select the recorded audio file in the app and enter the deal information (e.g., "Sold" or "Not Sold"), then tap the upload button to send the audio file and the deal information to the server.

[1437] Step 4:

[1438] Terminal

[1439] The device receives the recorded audio file and calls a speech recognition engine (such as Google Speech-to-Text) to convert the audio file into text data, which is then stored on the device.

[1440] Step 5:

[1441] Terminal

[1442] The recorded voice file is passed to the emotion engine, which analyzes the user's emotions. The emotion engine analyzes the user's tone of voice and vocabulary to identify emotions such as "joy," "anger," and "sadness."

[1443] Step 6:

[1444] Terminal

[1445] The converted text data, the recognized emotion information, and the transaction information are sent to the server. The app notifies you whether the transmission was successful or not.

[1446] Step 7:

[1447] server

[1448] The server analyzes the received text data, sentiment information, and sales information. A generative artificial intelligence (AI model) analyzes this data and identifies areas for improvement, such as "listening more specifically to what the customer is saying."

[1449] Step 8:

[1450] server

[1451] Based on the analysis results, the system generates optimal advice, taking emotional information into account, such as "Try to maintain a relaxed atmosphere when interacting with customers."

[1452] Step 9:

[1453] server

[1454] The generated advice is passed to a speech synthesis engine and converted into voice data. For example, voice data such as "Try to listen more carefully to what the customer is saying" is generated.

[1455] Step 10:

[1456] server

[1457] The generated advice and its audio data are sent to the device. The server checks whether the transmission was successful.

[1458] Step 11:

[1459] Terminal

[1460] The device receives the advice and audio data sent from the server and makes them available for display and playback within the app. Specifically, the text-format advice is displayed and the audio-format advice is played back.

[1461] Step 12:

[1462] User

[1463] Review the feedback provided by the user within the app. Play back the audio data to understand areas for improvement. For example, take the advice "Take more time to pause when responding to customers" into consideration and use it for your next customer service encounter.

[1464] Through these processing steps, users can record their own customer service interactions, undergo detailed analysis including sentiment analysis, and receive accurate and personalized feedback. This series of processes enables optimized training and guidance for individual crew members, aiming to improve their customer service skills.

[1465] Example 2

[1466] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1467] In customer service, voice recording, analysis, and feedback are necessary to improve the customer service skills of crew members, and more personalized advice is required by combining it with emotion recognition functions. It is also important to collect and compare data on a national scale to provide more accurate feedback and improve the closing rate.

[1468] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: [means for recording voice data]; [means for converting the recorded voice data into text data]; [means for using an emotion recognition engine to detect emotions from the voice data and the converted text data]; [means for transmitting the text data, contract information, and emotion information to the server]; [means for using generative artificial intelligence to analyze the text data and emotion information]; [means for generating advice based on the analysis results]; [means for converting the generated advice into voice data]; [means for transmitting the advice and voice data to the terminal]; and [means for receiving, displaying, and playing the advice and voice data at the terminal]. This makes it possible to receive appropriate feedback while understanding the user's emotional state and improve customer service skills.

[1469] "Audio data" is data that represents in digital form the audio recorded by a user using a terminal.

[1470] "Text data" refers to data obtained by converting voice data into text format using a voice recognition engine.

[1471] An "emotion recognition engine" is software that analyzes a user's tone of voice and vocabulary from voice and text data to detect emotions.

[1472] "Generative AI" is an AI technology that learns from past data and generates feedback based on the analysis results.

[1473] "Feedback" refers to advice for improvement based on the user's customer service experience and emotional state.

[1474] A "voice recognition engine" is software that analyzes voice data and converts it into corresponding character data (text data).

[1475] "Speech synthesis technology" is a technology that analyzes text data and generates its contents as voice data.

[1476] "Device" means a device (such as a smartphone or tablet) for recording, storing, and transmitting audio data, and for receiving and playing feedback.

[1477] A "server" is a computing system that analyzes various types of data (voice data, text data, emotional information), generates feedback, and manages communication with terminals.

[1478] "Advice" refers to instructions and suggestions for improvement generated based on customer service content and emotional data analyzed by generative artificial intelligence.

[1479] "Contract information" is data indicating whether the customer service resulted in a contract.

[1480] MODE FOR CARRYING OUT THE INVENTION

[1481] The present invention is a voice recording, analysis, and feedback system for improving crew customer service performance, which combines emotion recognition functionality. This system enables personalized advice based on the user's emotions. Specific embodiments for implementing the present invention are described below.

[1482] Overall system configuration

[1483] This system consists of a device that records the user's customer service, a server that analyzes the recorded data, generative artificial intelligence to generate and provide feedback, and an emotion recognition engine that recognizes the user's emotions.

[1484] User operations

[1485] The user uses their smartphone, tablet, or other device to launch an application to record the customer service interaction. They tap the record button to start recording the interaction, and when they're done, they tap the stop recording button. They then name and save the recorded audio file, select the audio file within the app, and upload it to the server. At this time, they also enter information on whether the transaction was successful or not.

[1486] Terminal handling

[1487] The device uses a speech recognition engine (such as Google Speech-to-Text) to convert the recorded audio file into text data, generating recognized text data. It also uses an emotion recognition engine to detect the user's emotions from the recorded audio and text data. For example, it can recognize emotions such as "joy," "anger," and "sadness" by analyzing the user's tone of voice and phrasing.

[1488] Server Processing

[1489] The server analyzes the received text data, sales information, and emotional information. Generative AI is used for the analysis, and customer service skills are evaluated based on the content of the text data and the user's emotions. This generative AI learns from a large amount of crew data and is able to generate optimal feedback.

[1490] Generate feedback

[1491] Based on the analysis results, the server generates optimal advice that takes into account emotional information. For example, if the user expresses anger, the server can generate specific advice such as "respond in a calm tone."

[1492] Conversion to audio data

[1493] The generated advice is then converted into voice data using speech synthesis technology. This voice data is sent to the device and can be played back and listened to by the user. For example, specific advice such as "Try to listen more slowly when the customer speaks" can be generated using speech synthesis and provided to the user.

[1494] Receive feedback on your device

[1495] The device receives the advice and audio data sent from the server and displays and plays it back within the app. By checking this feedback and playing it back aloud, users can understand where they need to improve and use it for their next customer service encounter.

[1496] Specific examples

[1497] For example, if user Tanaka records a sales pitch, the audio data is converted into text such as "Hello, how can I help you today?", and at the same time, the emotion recognition engine recognizes Tanaka's emotion as "slightly nervous." Tanaka's smartphone sends the text data, emotional information, and sales information to the server, which then generates advice such as "Take a more relaxed attitude toward customers." This advice is converted into audio data and sent to Tanaka's smartphone. Tanaka can review the advice through the app, play back the audio, and improve on the "relaxed conversation with customers" aspect, which can be applied to the next customer service encounter.

[1498] Examples of prompt statements

[1499] The following prompt sentences can be input to the generative AI model:

[1500] "Analyze customer service speech and generate effective feedback that includes the user's emotional information. For example, give advice based on the language and tone used during the conversation."

[1501] As described above, by using this system, users can improve their customer service skills while understanding their own emotional state. In addition, the system provides optimized education and guidance for individual crew members, and by collecting and comparing data on a national scale, it is possible to improve the success rate.

[1502] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1503] Step 1:

[1504] Users simply launch the application on their smartphone or tablet and tap the record button to record the audio of their customer service.

[1505] What it does: Your phone will use the device's microphone to record audio in real time and store it as a digital audio file in the background.

[1506] Input: Tap action to start recording.

[1507] Output: The audio data being recorded.

[1508] Step 2:

[1509] When the user has finished serving the customer, they tap the stop recording button and save the recorded audio file.

[1510] Specific operation: The device detects the tap action of the stop recording button, saves the audio data recorded up to that point as a temporary file, and prompts the user to enter a file name.

[1511] Input: Tap action to stop recording and input file name.

[1512] Output: The named audio file.

[1513] Step 3:

[1514] Users select an audio file within the app, upload it to the server, and enter information about successful and unsuccessful transactions.

[1515] Specific operation: The terminal encodes the audio file selected by the user and the transaction information and sends them to the server.

[1516] Input: Select an audio file and enter deal information.

[1517] Output: Sending audio files and deal information to the server.

[1518] Step 4:

[1519] The server uses a speech recognition engine (such as Google Speech-to-Text) to convert the received audio file into text data.

[1520] Specific operation: The server passes the voice data to the voice recognition engine and obtains the recognized text data as the result.

[1521] Input: An audio file.

[1522] Output: Text data.

[1523] Step 5:

[1524] The server uses an emotion recognition engine to detect the user's emotions from the audio file and text data.

[1525] Specific operation: The server analyzes the tone of the voice data and the content of the text data, and uses an emotion recognition engine to identify emotions such as "joy," "anger," and "sadness."

[1526] Input: Audio files and text data.

[1527] Output: Emotional information.

[1528] Step 6:

[1529] The server uses generative artificial intelligence to analyze the received text data, closing information, and sentiment information.

[1530] Specific operation: The server inputs data into a generative artificial intelligence (AI model) and performs analysis, which evaluates customer service skills.

[1531] Input: Text data, closing information, and sentiment information.

[1532] Output: Customer service skills evaluation results.

[1533] Step 7:

[1534] Based on the analysis results, the server generates optimal advice that takes emotional information into consideration.

[1535] Specific operation: The generative artificial intelligence generates appropriate feedback in text format from the analysis results.

[1536] Input: Customer service skills evaluation results.

[1537] Output: Advice in text format.

[1538] Step 8:

[1539] The server converts the generated advice into voice data using voice synthesis technology.

[1540] Specific operation: The server passes the generated text advice to a speech synthesis engine (such as Google Text-to-Speech) to generate it as audio data.

[1541] Input: Advice in text format.

[1542] Output: Audio data.

[1543] Step 9:

[1544] The device receives the advice and audio data sent from the server and displays and plays it back within the app.

[1545] Specific behavior: The device displays the received data within the app and provides an interface for playing audio advice.

[1546] Input: Advice and audio data received from the server.

[1547] Output: The displayed advice and the audio data played.

[1548] This process flow allows the user to obtain feedback to efficiently improve their customer service skills.

[1549] (Application example 2)

[1550] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1551] Conventional customer service training systems have problems: it takes time to improve a crew's customer service skills, and it is difficult to provide personalized feedback because they do not take into account factors such as emotion recognition.Furthermore, it is not possible to compare data nationwide, making it difficult to propose effective improvement measures based on a wide range of data.

[1552] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1553] In this invention, the server includes: [means for generating advice based on the analysis results]; [means for converting the generated advice into voice data]; and [means for using an emotion recognition engine that recognizes emotions from the user's tone of voice and vocabulary]. This makes it possible to efficiently provide personalized advice that takes into account the emotional state of each crew member in order to improve customer service skills. In addition, by comparing and analyzing nationwide data, it becomes possible to propose more accurate improvement measures.

[1554] "Means for recording voice data" refers to a device or software for recording the voice of the crew member providing service as digital data.

[1555] "Means for converting recorded voice data into text data" refers to technology that uses a voice recognition engine to convert recorded voice data into text.

[1556] The "means for transmitting the text data and the transaction information to the server" refers to a communication device or protocol for sending the converted text data and the transaction information to the server via the Internet.

[1557] "Means using generative artificial intelligence to analyze text data" refers to artificial intelligence techniques used to analyze the content of text data and generate optimal feedback.

[1558] "Means for generating advice based on analysis results" refers to the process of creating specific advice for improving customer service skills from the analysis results of generative artificial intelligence.

[1559] The "means for converting the generated advice into voice data" refers to using a voice synthesis technique to output the generated advice in text format as voice.

[1560] "Means for transmitting advice and voice data to a terminal" refers to a communication means for transmitting the generated advice and voice data to the terminal of the crew member who served the customer.

[1561] "Means for receiving, displaying and playing advice and audio data at the terminal" refers to a playback function that displays the advice and audio data received on the terminal and allows the user to listen to it aloud.

[1562] "Using an emotion recognition engine to recognize emotions from a user's tone of voice and phrasing" refers to algorithms or systems used to analyze and recognize a user's emotions from voice or text data.

[1563] The "means for generating feedback based on emotion recognition results" refers to a process for providing specific feedback based on the user's emotions, based on the analysis results of the emotion recognition engine.

[1564] "Data analysis tools for comparing and analyzing nationwide data" refers to software or algorithms used to statistically compare and analyze collected customer service data on a nationwide scale.

[1565] "Means using neural networks to generate advice and voice data" refers to a process that utilizes deep learning-based neural network algorithms to generate advice and optimize voice data.

[1566] This invention is a voice recording, analysis and feedback system for improving the customer service skills of crew members, and is characterized by its incorporation of a user emotion recognition function. This system is realized using a voice recognition engine, generative artificial intelligence, an emotion recognition engine and voice synthesis technology.

[1567] Overall system configuration

[1568] This system consists of a device that records the user's customer service speech, a server that analyzes the recorded data, and a generative artificial intelligence and emotion engine that generate and provide feedback. By linking these elements together, advanced support for improving customer service skills is realized.

[1569] User operations

[1570] The user launches a dedicated application to record the audio of customer service using their own device, such as a smartphone or tablet. They tap the record button to record the audio of the customer service, and then tap the stop recording button when they are finished. They then name and save the recorded audio file, select the audio file within the app, and upload it to the server. At this time, they also enter information on whether the deal was successful or not.

[1571] Terminal handling

[1572] The device converts the recorded audio file into text data using a speech recognition engine (e.g., Google Speech-to-Text). It also uses an emotion recognition engine to detect the user's emotions from the recorded audio and text data. For example, it can recognize emotions such as "joy," "anger," and "sadness" by analyzing the user's tone of voice and phrasing.

[1573] Server Processing

[1574] The server analyzes the received text data, sales information, and emotional information. Generative AI (e.g., a neural network using deep learning) is used for the analysis, and customer service skills are evaluated based on the content of the text data and the user's emotions. Generative AI learns from large amounts of data and is able to generate optimal feedback.

[1575] Generate feedback

[1576] Based on the analysis results, the server generates optimal advice that takes into account the user's emotional information. For example, if the user expresses anger, the server generates specific advice such as "respond in a calm tone."

[1577] Conversion to audio data

[1578] The generated advice is converted into voice data using voice synthesis technology, which is then sent to the terminal and played back for the user to listen to.

[1579] Receive feedback on your device

[1580] The device receives advice and audio data sent from the server and can display and play it back within the app. By checking this feedback and playing it back aloud, users can understand what they need to improve and use it for their next customer service encounter.

[1581] Specific examples

[1582] For example, when a user is explaining a product, the recorded voice data is converted into text such as "The features of this product are...", and at the same time, the emotion recognition engine recognizes the user's emotion as "not confident." Based on this text data and emotional information, the server generates advice such as "If you explain the product's features in more detail, I will be able to speak with more confidence," converts this into voice data, and sends it to the user's smartphone. The user can check this advice through the app, play back the audio, and use it for their next customer service encounter.

[1583] Prompt Sentence Examples

[1584] "Customer service: The features of this product are...

[1585] Customer sentiment: Unsure

[1586] Tip: Explain your product's features in more detail to help you feel more confident.

[1587] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1588] Step 1:

[1589] The user starts a recording application on their smartphone or tablet and records the voice of the customer while serving the customer. They tap the record button to record the voice of the customer, and press the stop recording button when finished. At this time, the input is the customer service voice data, and the recorded voice file is saved as the output.

[1590] Step 2:

[1591] The device converts the recorded audio file into text data using a speech recognition engine (such as Google Speech-to-Text). The input is an audio file, and text data is generated as output. This text data includes what was said during the customer service.

[1592] Step 3:

[1593] Using an emotion recognition engine, the device detects the user's emotions from the recorded voice data and converted text data. The input is voice and text data, and the output is the emotion recognition results, which include emotional information such as "joy," "anger," and "sadness."

[1594] Step 4:

[1595] The terminal transmits the generated text data, closing information, and emotion information to the server. The input is the text data, closing information, and emotion information, and the output is uploaded to the server.

[1596] Step 5:

[1597] The server analyzes the received text data, sales information, and emotional information using generative artificial intelligence (a neural network using deep learning). The input is text data, sales information, and emotional information, and the output is an evaluation of customer service skills. The analysis evaluates which parts are effective and which parts have room for improvement.

[1598] Step 6:

[1599] The server generates optimal advice based on the analysis results, taking into account emotional information. For example, if the emotion of "anger" is detected, specific advice such as "respond in a calm tone" is generated. The input is the analysis results and emotional information, and the output is text data of the advice.

[1600] Step 7:

[1601] The generated advice is converted into voice data by the server using voice synthesis technology. The input is text data of the advice, and the output is voice data of the advice.

[1602] Step 8:

[1603] The server sends the generated advice and voice data to the terminal. The input is the voice data and text data of the advice, and these are sent to the terminal as output.

[1604] Step 9:

[1605] The device receives the advice and audio data sent from the server and displays and plays it back within the app. The user can check this feedback and play it back aloud to understand their own customer service skills and apply them to their next customer service encounter. The input is the advice audio data and text data, and the output is display and audio playback.

[1606] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1607] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1608] 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 the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1609] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1610] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1611] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1612] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1613] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1614] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1615] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1616] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1617] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1618] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1619] 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.

[1620] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1621] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1622] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific processing may be a single processor.

[1623] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1624] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1625] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1626] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1627] The following is further disclosed regarding the above embodiment.

[1628] (Claim 1)

[1629] [means for recording audio data;

[1630] [Means for converting recorded voice data into text data;

[1631] [Means for transmitting text data and contract information to a server;

[1632] [Means using generative artificial intelligence to analyze text data;

[1633] [means for generating advice based on the analysis results;

[1634] [Means for converting the generated advice into audio data;

[1635] [means for transmitting advice and audio data to the terminal;

[1636] [Means for receiving, displaying and playing advice and audio data on a terminal]

[1637] A system including:

[1638] (Claim 2)

[1639] The system according to claim 1, further comprising a data analysis means for comparing and analyzing data nationwide based on the analysis results.

[1640] (Claim 3)

[1641] [The system of claim 1, which uses a neural network to generate advice and voice data.

[1642] "Example 1"

[1643] (Claim 1)

[1644] [means for recording audio data;

[1645] [Means for converting recorded voice data into text data;

[1646] [Means for transmitting text data and contract information to a server;

[1647] [Means using generative artificial intelligence to analyze text data;

[1648] [means for generating advice based on the analysis results;

[1649] [Means for converting the generated advice into audio data;

[1650] [means for transmitting advice and audio data to the terminal;

[1651] [Means for receiving, displaying and playing advice and audio data on a terminal]

[1652] A system including:

[1653] (Claim 2)

[1654] The system according to claim 1, further comprising a data analysis means for comparing and analyzing data nationwide based on the analysis results.

[1655] (Claim 3)

[1656] [The system of claim 1, which uses a neural network to generate advice and voice data.

[1657] "Application Example 1"

[1658] (Claim 1)

[1659] [means for recording audio data;

[1660] [Means for converting recorded voice data into text data;

[1661] [Means for transmitting text data and contract information to a server;

[1662] [Means using generative artificial intelligence to analyze text data;

[1663] [means for generating advice based on the analysis results;

[1664] [Means for converting the generated advice into audio data;

[1665] [means for transmitting advice and audio data to the terminal;

[1666] [Means for receiving, displaying, and playing advice and audio data at a terminal;

[1667] [Means for entering contract information;

[1668] [Method of reproducing feedback generated by generative artificial intelligence as advice through voice synthesis]

[1669] A system including:

[1670] (Claim 2)

[1671] The system according to claim 1, further comprising a data analysis means for comparing and analyzing data nationwide based on the analysis results.

[1672] (Claim 3)

[1673] [The system of claim 1, which uses a neural network to generate advice and voice data.

[1674] "Example 2: Combining Emotion Engines"

[1675] (Claim 1)

[1676] [means for recording audio data;

[1677] [Means for converting recorded voice data into text data;

[1678] [Means using an emotion recognition engine to detect emotions from the voice data and the converted text data;

[1679] [Means for transmitting text data, contract information, and emotion information to a server;

[1680] [Means using generative artificial intelligence to analyze text data and emotional information;

[1681] [means for generating advice based on the analysis results;

[1682] [Means for converting the generated advice into audio data;

[1683] [means for transmitting advice and audio data to the terminal;

[1684] [Means for receiving, displaying and playing advice and audio data on a terminal]

[1685] A system including:

[1686] (Claim 2)

[1687] The system according to claim 1, further comprising a data analysis means for comparing and analyzing data nationwide based on the analysis results.

[1688] (Claim 3)

[1689] [The system of claim 1, which uses a neural network to generate advice and voice data.

[1690] "Application example 2 when combining emotion engines"

[1691] (Claim 1)

[1692] [means for recording audio data;

[1693] [Means for converting recorded voice data into text data;

[1694] [Means for transmitting text data and contract information to a server;

[1695] [Means using generative artificial intelligence to analyze text data;

[1696] [means for generating advice based on the analysis results;

[1697] [Means for converting the generated advice into audio data;

[1698] [means for transmitting advice and audio data to the terminal;

[1699] [Means for receiving, displaying and playing advice and audio data on a terminal]

[1700] [Means for using an emotion recognition engine to recognize emotions from the user's tone of voice and phrasing;

[1701] [Means for generating feedback based on emotion recognition results]

[1702] A system including:

[1703] (Claim 2)

[1704] The system according to claim 1, further comprising a data analysis means for comparing and analyzing data nationwide based on the analysis results.

[1705] (Claim 3)

[1706] [The system of claim 1, which uses a neural network to generate advice and voice data. [Explanation of symbols]

[1707] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for recording audio data; A means for converting the recorded voice data into text data; means for transmitting text data and contract information to a server; a means for using generative artificial intelligence to analyze text data; means for generating advice based on the analysis results; means for converting the generated advice into audio data; means for transmitting advice and voice data to the terminal; Means for receiving, displaying and playing advice and audio data at a terminal A system including:

2. 2. The system according to claim 1, further comprising a data analysis means for comparing and analyzing nationwide data based on the analysis results.

3. 10. The system of claim 1, wherein the advice and audio data are generated using a neural network.

Images