system

Abstract

We provide the system. [Solution] Means for acquiring audio data, A means of converting audio data to text data, A method for analyzing text data to determine emotional state, A means of quantifying customer satisfaction based on the determined emotional state, A means of providing quantified information as feedback to the operator, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the work of telephone reception operators, failure to achieve the power reception target due to claim handling and business concentration is an issue. In such a situation, it is difficult to efficiently evaluate the performance of operators, and it is required to solve the problem that the improvement of customer satisfaction is hindered.

Means for Solving the Problems

[0005] This invention employs means for acquiring voice data and converting it into text data. Furthermore, it includes means for analyzing the text data to determine the customer's emotional state and quantifying customer satisfaction based on the determined emotional state. By feeding this quantified information back to the operator, performance is improved. The invention also includes means for identifying calls that may be complaints based on the emotional state and evaluation indicators, thereby improving customer satisfaction through prompt responses. Furthermore, it has a function to present improvement suggestions to the operator based on the feedback.

[0006] "Voice data" refers to the digital format of voice information acquired during a phone call.

[0007] "Text data" refers to a digital form of written information obtained by converting audio data using speech recognition technology.

[0008] "Emotional state" refers to the customer's emotional state, such as positive, negative, or neutral, inferred from the analyzed text and audio data.

[0009] "Customer satisfaction" is an indicator that shows how satisfied customers are with the services and treatment they receive, and is usually expressed numerically.

[0010] "Evaluation metrics" are quantified standards used to assess the performance of operators and the quality of customer service.

[0011] "Feedback" refers to the evaluation results and improvement suggestions that the system provides to the operator.

[0012] "Potential for complaints" refers to a call status that the system has determined may potentially result in customer complaints or dissatisfaction.

[0013] "Improvement suggestions" refer to specific actions or methods suggested by the system to improve the quality of operator responses and operational efficiency. [Brief explanation of the drawing]

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

Embodiments for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

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

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

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

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

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

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

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0031] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] This invention relates to a system for efficiently evaluating the work of telephone reception operators and improving customer satisfaction. This system acquires voice data, transcribes the voice data into text, analyzes emotional states, quantifies customer satisfaction, identifies potential complaints, and provides feedback and improvement suggestions.

[0036] First, when a user makes an inquiry by phone, the audio is collected in real time by a server. Next, the server converts the collected audio data into text data using speech recognition technology. This converted text data is then analyzed by a generative AI model to determine the customer's emotional state. Here, keywords in the text, as well as the tone and speed of the voice, are taken into consideration.

[0037] Subsequently, the server quantifies customer satisfaction based on emotional state and evaluates the operator's performance. Furthermore, the server can compare this with past call data to evaluate the operator's work in more depth. Based on this evaluation, the server provides feedback to the operator and notifies them of areas for improvement. If there are many negative keywords in the call, the server determines that the call may be a complaint and notifies the manager.

[0038] For example, if a user frequently uses phrases like "I'll consider using it again" or "I'm dissatisfied," the server will record the call as one requiring special attention and notify the administrator that immediate action is needed. On the other hand, if a user uses positive language such as "thank you" or "that was helpful" during routine interactions, the server will use that information to provide positive feedback to the operator and share it as an example of good service.

[0039] Thus, the present invention provides a system that can improve the quality of telephone reception operators' responses and increase customer satisfaction.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] When a user makes a call to the customer service center, the server collects the audio data in real time. First, the server connects to the telephone system and prepares to acquire the audio stream of the call.

[0043] Step 2:

[0044] The server sends the acquired audio data to the speech recognition engine, which converts the audio data into text format. The converted text data is stored in a database on the server and prepared for the next process.

[0045] Step 3:

[0046] The server uses a generative AI model to analyze the converted text data. This analysis includes keyword extraction and sentiment analysis from the text. The server determines whether the customer's statements indicate a positive, negative, or neutral emotional state.

[0047] Step 4:

[0048] The server analyzes the characteristics of the voice data (such as tone, pitch, and speed) and combines them with the results of text analysis to determine the customer's overall emotional state. This allows for a more accurate assessment of customer satisfaction.

[0049] Step 5:

[0050] The server quantifies customer satisfaction using response time and sentiment scores derived from text and voice analysis. Simultaneously, it evaluates operator performance based on this quantified rating and identifies areas for improvement.

[0051] Step 6:

[0052] The server identifies calls that could potentially lead to complaints based on customer satisfaction scores and sentiment analysis results. If the negative score exceeds a certain value, the call is notified to the management system as a potential complaint.

[0053] Step 7:

[0054] The server provides feedback to the operator. Specifically, it identifies what went well and what needs improvement so that the operator can use this feedback for future calls. It also provides specific suggestions for improvement aimed at increasing customer satisfaction.

[0055] (Example 1)

[0056] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0057] Traditional telephone support operations lacked methods for objectively evaluating the quality of operator responses and efficiently incorporating customer feedback. This made it difficult to improve customer satisfaction, and in particular, led to delays in the early detection and resolution of complaints.

[0058] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0059] In this invention, the server includes means for acquiring voice information, means for converting voice information into text information, and means for analyzing the text information to determine the emotional state. This makes it possible to evaluate operator responses in real time and quantify customer satisfaction. It also makes it possible to quickly identify complaints based on specific keywords and notify the appropriate department.

[0060] "Means for acquiring voice information" refers to technology or equipment for receiving phone calls made by users in real time and collecting that voice data on a server.

[0061] "Means of converting audio information to text information" refers to a process that uses speech recognition technology to convert acquired audio data into text data, thereby converting audio into text data.

[0062] "Means of analyzing textual information to determine emotional state" refers to an algorithm or system that analyzes text data and determines the user's emotions based on the keywords and contextual information contained therein.

[0063] "Methods for quantifying user satisfaction" refer to methods for quantitatively measuring user experience and satisfaction by performing statistical or numerical evaluations based on the determined emotional state.

[0064] "Methods for returning information to those responsible for operations" refers to the process of communicating quantified information and evaluation results to operators and those responsible for operations, and using that information to improve and evaluate their work.

[0065] "Means for evaluating work performance" refers to a system or method for evaluating the work performance of operators or staff by comparing and analyzing past call information with current evaluations.

[0066] "Means for identifying calls as complaints" refers to a function that analyzes the frequency and context of negative keywords contained in the call content to recognize that the call has the potential to be a complaint and to notify the relevant parties.

[0067] This invention is a system for efficiently evaluating operators' telephone handling skills and improving customer satisfaction. The following describes a specific implementation of this system.

[0068] When a user makes an inquiry by phone, the audio is captured in real time by the server. The server is connected to a microphone and receiving device for audio data acquisition. The captured audio data is converted into text data on the server using Google® Cloud Speech-to-Text or a similar service. After conversion to text data, the server inputs the resulting text information into a generating AI model.

[0069] This generative AI model performs sentiment analysis as part of natural language processing technology, determining the user's emotional state from keywords and context contained within the text. For example, the server detects negative keywords such as "dissatisfied" and "high number of inquiries," while also analyzing positive keywords such as "satisfied" and "helpful."

[0070] Next, the server quantifies user satisfaction based on the determined emotional state. This quantified satisfaction level is provided to the service provider as feedback. This feedback is used to evaluate service performance by comparing it with past call information. Furthermore, the server can identify specific calls as complaints based on the frequency of negative keywords, thereby prompting administrators to take prompt action.

[0071] For example, if a user makes a statement such as "I'm dissatisfied with this service," the server immediately identifies this as a negative keyword and provides appropriate feedback to the relevant person in charge.

[0072] Examples of prompts for a generative AI model include the following:

[0073] "Based on the text data from this call, please analyze the customer's emotional state. Consider the keywords and their tone to identify the emotions being expressed."

[0074] In this way, the server can collect and analyze important data to improve the quality of operator responses, ultimately aiming to increase customer satisfaction.

[0075] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0076] Step 1:

[0077] As soon as a user makes a phone call and the call begins, the audio is streamed to the server in real time. The server receives the audio data through a microphone and receiving hardware. The input audio data is then stored directly in the server's memory.

[0078] Step 2:

[0079] The server converts the acquired audio data into text data using speech recognition technology. This process uses a speech recognition API such as Google Cloud Speech-to-Text. The server sends the audio file to the API and receives the converted text data. The input is audio data, and the output is the corresponding text data.

[0080] Step 3:

[0081] The server analyzes text data transformed using a generative AI model to determine the emotional state. It receives text data as input, processes it with prompts, and inputs it into the generative AI model. The output the server receives from the model includes emotional state scores and keyword analysis results. Specifically, it identifies and scores negative and positive keywords within the text.

[0082] Step 4:

[0083] The server quantifies customer satisfaction based on the determined emotional state score. It converts the emotional score into a quantitative evaluation and outputs it as user satisfaction. The input is the emotional score, and the output is the quantified customer satisfaction. Based on this quantified result, the server performs a comparative evaluation with past data.

[0084] Step 5:

[0085] The server provides feedback to the business personnel based on the evaluation results. Based on the entered customer satisfaction scores and past evaluations, it generates improvement suggestions and positive feedback as text and sends them to the business personnel. The output is a feedback document including improvement suggestions.

[0086] Step 6:

[0087] The server analyzes the frequency of negative keywords in the call content and, if necessary, identifies the call as a complaint. This process compares the current call with past negative response patterns and generates an alert if a threshold is exceeded. The output is a complaint alert directed to the administrator.

[0088] (Application Example 1)

[0089] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0090] In telephone customer service, there is a problem in that it is difficult to appropriately grasp the customer's emotional state and satisfaction level and provide immediate feedback to operators. Furthermore, there is a lack of mechanisms to quickly identify and address calls that may be complaints.

[0091] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0092] In this invention, the server includes means for acquiring voice information, means for converting the voice information into a transcript, means for analyzing the transcript to determine the emotional state, means for evaluating customer satisfaction based on the determined emotional state, means for providing the evaluated information to the guide, and means including an application installed on a mobile terminal that displays the evaluation results in real time. This allows operators to grasp the customer's emotions in real time and provide immediate feedback and make improvements.

[0093] "Voice information" refers to the audio data of conversations between customers and operators.

[0094] "Means of acquisition" refers to the device or process for collecting audio information in digital format and storing it on a server.

[0095] "Methods for converting to transcription" refers to the process of using speech recognition technology to convert audio information into text data.

[0096] "Means of analyzing transcripts to determine emotional states" refers to algorithms or devices that analyze text data to determine a customer's emotions and attitudes.

[0097] "Methods for evaluating customer satisfaction" refers to the process of quantifying or scoring customer satisfaction based on the determined emotional state.

[0098] "Means of providing information to the guide" refers to an interface or process for transmitting analysis results and feedback to the operator.

[0099] "Applications installed on mobile devices that display data in real time" refers to software installed on portable information terminals such as smartphones and tablets that instantly displays analysis results.

[0100] To implement this invention, the server first plays the role of acquiring audio information. The audio information is input from a device that collects customer-operator conversations in real time. Next, the server uses speech recognition technology to convert the audio information into a transcript. This process uses a speech recognition API such as "Google Cloud Speech-to-Text".

[0101] Next, using a generative AI model, the server analyzes the converted text data to determine the customer's emotional state. Specifically, it analyzes keywords and context within the text, and also takes into account auditory information such as tone and speed of voice. The evaluated customer satisfaction information is provided to the information desk staff in real time. This information is displayed on a specific application installed on a mobile device such as a smartphone or tablet, making it easier for the operator to adjust their response on the spot.

[0102] For example, if an operator receives feedback from a customer stating, "I'm unhappy with the wait," the server immediately analyzes this information and displays an alert on the operator's mobile device indicating that "the customer is likely dissatisfied." Based on this notification, the operator can then improve their customer service.

[0103] Furthermore, an example of a prompt sentence for the AI ​​model generated by this application is: "Predict the customer's emotional state from this sentence: 'The service is great, but the response is slow.'" By utilizing this prompt sentence, it becomes possible to analyze the customer's emotional state appropriately.

[0104] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0105] Step 1:

[0106] The server acquires voice information in real time during a call. This voice information consists of audio data spoken by the user via telephone, which is stored on the server in digital format. The input is voice information, and the output is the digital audio data stored on the server.

[0107] Step 2:

[0108] The server uses a speech recognition API to convert the acquired audio information into text data. This process uses "Google Cloud Speech-to-Text". The input is the digital audio data saved in step 1, and the output is text data.

[0109] Step 3:

[0110] The server analyzes the converted text data using a generative AI model. Specifically, it predicts the user's emotional state based on keywords and context contained in the text. At this time, the choice, frequency, and phrasing of words in the text are considered. The input is the text data generated in step 2, and the output is the determined emotional state.

[0111] Step 4:

[0112] The server evaluates and quantifies customer satisfaction based on the determined emotional state. At this stage, the emotional state is classified into positive, negative, neutral, etc., and summarized as a numerical score. The input is the emotional state obtained in step 3, and the output is the numerical score of customer satisfaction.

[0113] Step 5:

[0114] The server transmits the evaluated customer satisfaction information to the mobile device in real time. The application installed on the device then provides feedback to the operator. The input is the numerical customer satisfaction score obtained in step 4, and the output is the feedback information displayed on the device.

[0115] Step 6:

[0116] The operator adjusts their response to the customer based on real-time feedback information. Specifically, they respond quickly to feedback and take measures to improve service as needed. The input is the feedback information displayed on the terminal in step 5, and the output is the operator's adapted actions.

[0117] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0118] This invention relates to a system that combines an emotion engine, which recognizes user emotions from acquired voice data, in order to evaluate the work of telephone reception operators with greater accuracy and improve the quality of customer service.

[0119] When a user makes an inquiry or consultation by phone, the server collects voice data in real time. This voice data is converted into text data by the server's speech recognition engine. The converted text data is stored in a database and used for subsequent analysis.

[0120] The server then utilizes an emotion engine to recognize the user's emotions based on text data and information such as tone, pitch, and speed of voice. This process allows for a highly accurate determination of whether the user is experiencing positive, negative, or neutral emotions.

[0121] The results of emotion recognition are directly used to quantify customer satisfaction. Based on these results, the server evaluates operator performance and, if particularly strong negative emotions are expressed, determines that a complaint is likely and notifies the manager. This notification enables a quick response and helps resolve customer dissatisfaction early.

[0122] Furthermore, feedback is provided to operators in real time and can be used as a response guide that includes suggestions for improvement. For example, if a user says "I don't understand" or "I'm having trouble," the server will interpret this as a sign of dissatisfaction and provide the operator with specific ways to respond. In this way, the system supports operators in taking appropriate responses, ultimately aiming to improve customer satisfaction.

[0123] Through the system of this invention, the quality of operator responses can be precisely evaluated, enabling efficient and effective customer service. This leads to an overall improvement in the service level of telephone support.

[0124] The following describes the processing flow.

[0125] Step 1:

[0126] When a user contacts the customer service center by phone, the server acquires the audio data of the call in real time. The server connects to the phone system and makes the necessary preparations to begin audio streaming.

[0127] Step 2:

[0128] The server sends the acquired audio data to a speech recognition engine, which converts the audio into text data. This converted text data is stored in a database on the server for use in subsequent processes.

[0129] Step 3:

[0130] The server uses an emotion engine to analyze text and audio data. Specifically, it determines the user's emotions based on keywords in the text, tone of voice, speaking speed, and other factors. Based on this determination, the user's emotional state is classified as positive, negative, or neutral.

[0131] Step 4:

[0132] The server quantifies customer satisfaction based on the determined emotional state. This quantified data is directly linked to operator performance evaluation and used for further analysis.

[0133] Step 5:

[0134] The server identifies potentially problematic calls based on emotional state and quantified ratings. Identified calls immediately notify administrators, allowing for prompt action as needed.

[0135] Step 6:

[0136] The server provides operators with real-time feedback. This feedback includes what went well, areas for improvement, and even specific suggestions for improvement. This allows operators to use this feedback to provide better service in future calls.

[0137] This series of processes allows the server to analyze user emotions in detail, thereby improving the quality of service provided by telephone operators and increasing customer satisfaction.

[0138] (Example 2)

[0139] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0140] Conventional voice communication systems have the challenge of making it difficult to objectively evaluate the quality of operator responses based on actual customer emotions and satisfaction levels. Furthermore, they lacked the means to proactively identify potential complaints and address them quickly. As a result, improvements in customer satisfaction and the early resolution of complaints were not fully achieved.

[0141] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0142] In this invention, the server includes means for collecting acoustic information, means for converting acoustic information into text information, means for analyzing the characteristics of the text information and acoustic information to identify emotions, means for calculating an evaluation index based on the identified emotions, means for providing the calculated evaluation index to the communication operator, means for identifying communications that have the potential to generate dissatisfaction, and means for presenting measures to improve service to the communication operator. This enables precise evaluation of the operator's response quality based on customer emotions and satisfaction, allowing for the early detection of potential complaints and prompt response.

[0143] "Acoustic information" refers to data related to voice or sound, and in particular, to voice signals acquired from the user during communication.

[0144] "Textual information" refers to data in text format obtained by converting acoustic information using speech recognition technology.

[0145] "Analysis" refers to the process of evaluating the characteristics of acoustic and textual information to identify the user's emotions.

[0146] "Means of identifying emotions" refers to technical means that analyze a user's emotional state and classify it as positive, negative, or neutral.

[0147] "Evaluation metrics" refer to numerical values ​​that quantify customer satisfaction or operator service quality, calculated based on identified emotions.

[0148] "Communications personnel" refers to operators who handle acoustic information or individuals engaged in such work.

[0149] "Means for identifying communications that may generate dissatisfaction" refers to a function that uses analyzed sentiment information and evaluation metrics to identify communications that may potentially generate complaints.

[0150] "Means of providing solutions for improving customer service" refers to a systemic function that allows communications personnel to provide specific advice and instructions on how to improve their interactions with customers.

[0151] This invention provides a technology for improving the quality of operator responses in a voice communication system by analyzing the user's emotions. Specific embodiments for carrying out this invention are described below.

[0152] The server collects the user's acoustic information through a communication device. This acoustic information is converted into text information using software equipped with speech recognition technology. A common example of speech recognition software is a speech recognition engine.

[0153] The converted text information is stored in a database by the server. The server then uses an emotion analysis engine to analyze the characteristics of the text and audio information and identify the user's emotions. Natural language processing techniques and machine learning algorithms can be used as the emotion analysis engine.

[0154] The results of emotion identification are quantified as evaluation metrics and provided to the communications operator by the server. These metrics indicate operator performance and customer satisfaction. The server can also notify administrators of potentially dissatisfying communications based on the identified emotions. This feature facilitates a quicker response.

[0155] Furthermore, the server provides communication personnel with real-time suggestions for improving their responses. This allows operators to communicate effectively with customers and resolve problems quickly.

[0156] As a concrete example, consider a scenario where a user calls customer support and says, "I don't know how to use the product." The server collects this statement as acoustic information, converts it to text information, and then analyzes it. If the analysis determines that the user's statement suggests confusion or dissatisfaction, the server notifies the operator and instructs them to provide specific instructions on how to use the product. It is also conceivable to use a generative AI model to create prompts related to optimizing communication. An example of such a prompt might be, "Please describe a system that analyzes customer voice data, identifies emotions, and suggests appropriate responses to operators."

[0157] In this way, this invention enables communication systems to provide more effective and satisfying customer service.

[0158] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0159] Step 1:

[0160] When a user calls customer support, the server collects acoustic information in real time via a communication device. The input data is the user's voice, and this voice data is sent to the server.

[0161] Step 2:

[0162] The server uses a speech recognition engine to convert the collected acoustic information (audio data) into text information. This process extracts the content of the speech as a string of characters. The input is acoustic information, and the output is text information.

[0163] Step 3:

[0164] The converted text information is stored in the server's database. Simultaneously, the server sends the stored text information and acoustic information characteristics (tone, pitch, speed, etc.) to the emotion analysis engine. The input consists of text information and acoustic information characteristics, and emotion is analyzed based on these.

[0165] Step 4:

[0166] The server uses an emotion analysis engine to identify the user's emotion as positive, negative, or neutral. The emotion identification result is quantified as an evaluation metric and used for the next process. The input here is the result of the data analysis in the previous step, and the output is the metric value indicating the emotion.

[0167] Step 5:

[0168] The server determines the potential for a user complaint based on evaluation metrics obtained through sentiment analysis. If strong negative emotions are detected, it sends a notification to the communications officer and their manager. The input is identified sentiment information, and the output is a notification and response instructions.

[0169] Step 6:

[0170] The server provides communication personnel with real-time suggestions for improving their responses. These suggestions include specific advice and procedures to support the operators' current handling of calls. Inputs are evaluation metrics and identified sentiment information, while outputs are response guidelines.

[0171] Step 7:

[0172] The server evaluates the communication operator's performance based on the feedback. This evaluation is recorded to help improve future responses. Inputs are the communication results and feedback information, while outputs are the improved response methods and records.

[0173] This series of processes enables effective responses that are tailored to the user's emotions, leading to improved operator service quality and customer satisfaction.

[0174] (Application Example 2)

[0175] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0176] In telephone reception operations, operators are required to appropriately assess customer emotions and respond quickly to improve customer satisfaction. Providing real-time feedback and concrete improvement suggestions is a key challenge in this context.

[0177] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0178] In this invention, the server includes means for acquiring voice information, means for converting voice information into text information, means for analyzing the text information to determine the emotional state, and means for providing improvement recommendations to the operator in real time based on the emotional state. This enables the operator to understand the customer's emotions in real time and take appropriate action.

[0179] "Voice information" refers to the content of conversations with customers during telephone reception operations, and is data acquired through operations performed by operators.

[0180] "Textual information" refers to data obtained by converting audio information into text, and is a format used for subsequent data analysis.

[0181] "Emotional status" refers to the state of a customer's emotions, analyzed based on audio and textual information, and is an indicator that shows positive, negative, or neutral.

[0182] "Customer satisfaction" is a numerical indicator of customer satisfaction based on analyzed emotional states, and is used to evaluate the quality of services.

[0183] An "operator" is a person who is responsible for telephone reception and customer service, and is the entity that receives feedback from the system.

[0184] "Providing real-time improvement recommendations" means having a function that allows operators to immediately provide suggestions and instructions during customer calls, prompting them to take appropriate action.

[0185] The system that implements this application is designed to allow operators handling telephone reception duties to receive real-time feedback and improvement suggestions while interacting with customers. This system uses a smartphone as the terminal for acquiring voice information. The smartphone acquires the customer's call content as voice information in real time.

[0186] The acquired audio information is converted into text information using a speech recognition engine on the server. For example, Google Cloud Speech-to-Text is used as this speech recognition engine. The converted text information is further analyzed by an emotion engine on the server. For example, IBM Watson® Tone Analyzer is used as this emotion engine. The emotion engine analyzes the text information and determines the customer's emotional state based on the audio characteristic data.

[0187] The determined emotional state is quantified by the server and statistically processed as user satisfaction. This information is sent back to the operator via a dedicated application, allowing the operator to receive real-time recommendations for improving customer service. For example, if a customer expresses dissatisfaction, the application will provide the operator with specific countermeasures.

[0188] For example, if a customer says they are "concerned about the content of their inquiry," the operator will receive advice such as, "The customer is feeling anxious. Please calmly explain the situation and promise to take prompt action if necessary." In this way, the operator can ensure that they take appropriate action.

[0189] An example of a prompt might be: "Perform a sentiment analysis on the customer's statements and provide necessary improvement advice. Audio data: 'Customer statements audio data'."

[0190] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0191] Step 1:

[0192] A smartphone acquires audio information during a call with a customer. The input is the audio of the conversation with the customer, and the output is digitized audio data. The audio data is collected via the microphone and temporarily stored in a database.

[0193] Step 2:

[0194] The server uses a speech recognition engine to convert the acquired speech information into text information. The input is speech data, and the output is converted text data. This process uses technologies such as Google Cloud Speech-to-Text to analyze the speech data and convert it to text.

[0195] Step 3:

[0196] The server analyzes text data and speech characteristic data (tone, pitch, speed, etc.) using an emotion engine to determine the emotional state. The input is text information and speech characteristic data, and the output is an emotional state indicating either positive, negative, or neutral. Emotion analysis is performed using tools such as IBM Watson Tone Analyzer.

[0197] Step 4:

[0198] The server quantifies the emotional state it determines and generates a user satisfaction index. The input is the emotional state, and the output is quantified satisfaction data. This index is statistically processed using a mathematical algorithm.

[0199] Step 5:

[0200] Based on quantified user satisfaction data, real-time feedback is provided to operators through a dedicated application. The input is satisfaction data, and the output is improvement recommendations and specific countermeasures. For example, a message such as, "The customer is feeling uneasy. Please explain calmly," might be provided.

[0201] Step 6:

[0202] The operator utilizes a generative AI model based on the prompt text to formulate further countermeasures. The input consists of feedback and the prompt text from the generative AI model, and the output is a customized response suggestion. For example, the prompt "Perform sentiment analysis on the customer's statement and provide necessary improvement advice" can be entered to receive suggestions from the model.

[0203] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0204] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0205] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0206] [Second Embodiment]

[0207] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0208] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0209] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0210] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0211] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0212] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0213] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0214] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0215] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0216] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0217] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0218] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0219] This invention relates to a system for efficiently evaluating the work of telephone reception operators and improving customer satisfaction. This system acquires voice data, transcribes the voice data into text, analyzes emotional states, quantifies customer satisfaction, identifies potential complaints, and provides feedback and improvement suggestions.

[0220] First, when a user makes an inquiry by phone, the audio is collected in real time by a server. Next, the server converts the collected audio data into text data using speech recognition technology. This converted text data is then analyzed by a generative AI model to determine the customer's emotional state. Here, keywords in the text, as well as the tone and speed of the voice, are taken into consideration.

[0221] Subsequently, the server quantifies customer satisfaction based on emotional state and evaluates the operator's performance. Furthermore, the server can compare this with past call data to evaluate the operator's work in more depth. Based on this evaluation, the server provides feedback to the operator and notifies them of areas for improvement. If there are many negative keywords in the call, the server determines that the call may be a complaint and notifies the manager.

[0222] For example, if a user frequently uses phrases like "I'll consider using it again" or "I'm dissatisfied," the server will record the call as one requiring special attention and notify the administrator that immediate action is needed. On the other hand, if a user uses positive language such as "thank you" or "that was helpful" during routine interactions, the server will use that information to provide positive feedback to the operator and share it as an example of good service.

[0223] Thus, the present invention provides a system that can improve the quality of telephone reception operators' responses and increase customer satisfaction.

[0224] The following describes the processing flow.

[0225] Step 1:

[0226] When a user makes a call to the customer service center, the server collects the audio data in real time. First, the server connects to the telephone system and prepares to acquire the audio stream of the call.

[0227] Step 2:

[0228] The server sends the acquired audio data to the speech recognition engine, which converts the audio data into text format. The converted text data is stored in a database on the server and prepared for the next process.

[0229] Step 3:

[0230] The server uses a generative AI model to analyze the converted text data. This analysis includes keyword extraction and sentiment analysis from the text. The server determines whether the customer's statements indicate a positive, negative, or neutral emotional state.

[0231] Step 4:

[0232] The server analyzes the characteristics of the voice data (such as tone, pitch, and speed) and combines them with the results of text analysis to determine the customer's overall emotional state. This allows for a more accurate assessment of customer satisfaction.

[0233] Step 5:

[0234] The server quantifies customer satisfaction using response time and sentiment scores derived from text and voice analysis. Simultaneously, it evaluates operator performance based on this quantified rating and identifies areas for improvement.

[0235] Step 6:

[0236] The server identifies calls that could potentially lead to complaints based on customer satisfaction scores and sentiment analysis results. If the negative score exceeds a certain value, the call is notified to the management system as a potential complaint.

[0237] Step 7:

[0238] The server provides feedback to the operator. Specifically, it identifies what went well and what needs improvement so that the operator can use this feedback for future calls. It also provides specific suggestions for improvement aimed at increasing customer satisfaction.

[0239] (Example 1)

[0240] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0241] Traditional telephone support operations lacked methods for objectively evaluating the quality of operator responses and efficiently incorporating customer feedback. This made it difficult to improve customer satisfaction, and in particular, led to delays in the early detection and resolution of complaints.

[0242] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0243] In this invention, the server includes means for acquiring voice information, means for converting voice information into text information, and means for analyzing the text information to determine the emotional state. This makes it possible to evaluate operator responses in real time and quantify customer satisfaction. It also makes it possible to quickly identify complaints based on specific keywords and notify the appropriate department.

[0244] "Means for acquiring voice information" refers to technology or equipment for receiving phone calls made by users in real time and collecting that voice data on a server.

[0245] "Means of converting audio information to text information" refers to a process that uses speech recognition technology to convert acquired audio data into text data, thereby converting audio into text data.

[0246] "Means of analyzing textual information to determine emotional state" refers to an algorithm or system that analyzes text data and determines the user's emotions based on the keywords and contextual information contained therein.

[0247] "Methods for quantifying user satisfaction" refer to methods for quantitatively measuring user experience and satisfaction by performing statistical or numerical evaluations based on the determined emotional state.

[0248] "Methods for returning information to those responsible for operations" refers to the process of communicating quantified information and evaluation results to operators and those responsible for operations, and using that information to improve and evaluate their work.

[0249] "Means for evaluating work performance" refers to a system or method for evaluating the work performance of operators or staff by comparing and analyzing past call information with current evaluations.

[0250] "Means for identifying calls as complaints" refers to a function that analyzes the frequency and context of negative keywords contained in the call content to recognize that the call has the potential to be a complaint and to notify the relevant parties.

[0251] This invention is a system for efficiently evaluating operators' telephone handling skills and improving customer satisfaction. The following describes a specific implementation of this system.

[0252] When a user makes a phone inquiry, the audio is captured in real time by the server. The server is connected to a microphone and receiving device for audio data acquisition. The captured audio data is converted into text data on the server using Google Cloud Speech-to-Text or a similar service. After conversion to text data, the server inputs the resulting text information into a generating AI model.

[0253] This generative AI model performs sentiment analysis as part of natural language processing technology, determining the user's emotional state from keywords and context contained within the text. For example, the server detects negative keywords such as "dissatisfied" and "high number of inquiries," while also analyzing positive keywords such as "satisfied" and "helpful."

[0254] Next, the server quantifies user satisfaction based on the determined emotional state. This quantified satisfaction level is provided to the service provider as feedback. This feedback is used to evaluate service performance by comparing it with past call information. Furthermore, the server can identify specific calls as complaints based on the frequency of negative keywords, thereby prompting administrators to take prompt action.

[0255] For example, if a user makes a statement such as "I'm dissatisfied with this service," the server immediately identifies this as a negative keyword and provides appropriate feedback to the relevant person in charge.

[0256] Examples of prompts for a generative AI model include the following:

[0257] "Based on the text data from this call, please analyze the customer's emotional state. Consider the keywords and their tone to identify the emotions being expressed."

[0258] In this way, the server can collect and analyze important data to improve the quality of operator responses, ultimately aiming to increase customer satisfaction.

[0259] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0260] Step 1:

[0261] As soon as a user makes a phone call and the call begins, the audio is streamed to the server in real time. The server receives the audio data through a microphone and receiving hardware. The input audio data is then stored directly in the server's memory.

[0262] Step 2:

[0263] The server converts the acquired audio data into text data using speech recognition technology. This process uses a speech recognition API such as Google Cloud Speech-to-Text. The server sends the audio file to the API and receives the converted text data. The input is audio data, and the output is the corresponding text data.

[0264] Step 3:

[0265] The server analyzes text data transformed using a generative AI model to determine the emotional state. It receives text data as input, processes it with prompts, and inputs it into the generative AI model. The output the server receives from the model includes emotional state scores and keyword analysis results. Specifically, it identifies and scores negative and positive keywords within the text.

[0266] Step 4:

[0267] The server quantifies customer satisfaction based on the determined emotional state score. It converts the emotional score into a quantitative evaluation and outputs it as user satisfaction. The input is the emotional score, and the output is the quantified customer satisfaction. Based on this quantified result, the server performs a comparative evaluation with past data.

[0268] Step 5:

[0269] The server provides feedback to the business personnel based on the evaluation results. Based on the entered customer satisfaction scores and past evaluations, it generates improvement suggestions and positive feedback as text and sends them to the business personnel. The output is a feedback document including improvement suggestions.

[0270] Step 6:

[0271] The server analyzes the frequency of negative keywords in the call content and, if necessary, identifies the call as a complaint. This process compares the current call with past negative response patterns and generates an alert if a threshold is exceeded. The output is a complaint alert directed to the administrator.

[0272] (Application Example 1)

[0273] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0274] In telephone customer service, there is a problem in that it is difficult to appropriately grasp the customer's emotional state and satisfaction level and provide immediate feedback to operators. Furthermore, there is a lack of mechanisms to quickly identify and address calls that may be complaints.

[0275] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0276] In this invention, the server includes means for acquiring voice information, means for converting the voice information into a transcript, means for analyzing the transcript to determine the emotional state, means for evaluating customer satisfaction based on the determined emotional state, means for providing the evaluated information to the guide, and means including an application installed on a mobile terminal that displays the evaluation results in real time. This allows operators to grasp the customer's emotions in real time and provide immediate feedback and make improvements.

[0277] "Voice information" refers to the voice data of calls conducted between customers and operators.

[0278] "Means for acquisition" means a device or process for collecting voice information in digital form on a server.

[0279] "Means for converting to a transcript" refers to a process using speech recognition technology to convert voice information into text data.

[0280] "Means for analyzing the transcript to determine the emotional state" refers to an algorithm or device for analyzing text data to discriminate the emotions and attitudes of customers.

[0281] "Means for evaluating customer satisfaction" refers to a process for quantifying or scoring customer satisfaction based on the determined emotional state.

[0282] "Means for providing information to the operator" refers to an interface or process for transmitting the analysis results and feedback to the operator.

[0283] "Application installed on a mobile terminal for real-time display" refers to software provided on a portable information terminal such as a smartphone or tablet for immediately displaying the analysis results.

[0284] To implement this invention, first, the server plays the role of acquiring voice information. The voice information is input from a device that collects the calls between customers and operators in real time. Next, using speech recognition technology, the server converts the voice information into a transcript. For this process, a speech recognition API such as "Google Cloud Speech-to-Text" is used.

[0285] Subsequently, by leveraging the generative AI model, the server analyzes the converted text data to determine the customer's emotional state. Specifically, it analyzes keywords and context within the text, and also takes into account auditory information such as the tone and speed of the voice. The evaluated customer satisfaction information is provided to the guide staff in real time. This information is displayed on a specific application installed on a mobile terminal such as a smartphone or tablet, making it easier for the operator to adjust their response on the spot.

[0286] As a specific example, when an operator receives feedback from a customer such as "I'm dissatisfied with waiting," the server immediately analyzes this information and issues an alert on the operator's mobile terminal such as "There is a high possibility that the customer is dissatisfied." Based on this notification, the operator can improve their response to the customer.

[0287] Also, as an example of a prompt sentence for the generative AI model of this application, a format such as "Predict the customer's emotional state from this sentence: 'The service is great, but the response is slow.'" can be cited. By utilizing this prompt sentence, appropriate analysis of the emotional state becomes possible.

[0288] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0289] Step 1:

[0290] The server acquires the voice information during the call in real time. The voice information is the voice data emitted by the user through the phone, and this is saved in the server in digital format. The input is the voice information, and the output is the digital voice data stored in the server.

[0291] Step 2:

[0292] The server uses a speech recognition API to convert the acquired audio information into text data. This process uses "Google Cloud Speech-to-Text". The input is the digital audio data saved in step 1, and the output is text data.

[0293] Step 3:

[0294] The server analyzes the converted text data using a generative AI model. Specifically, it predicts the user's emotional state based on keywords and context contained in the text. At this time, the choice, frequency, and phrasing of words in the text are considered. The input is the text data generated in step 2, and the output is the determined emotional state.

[0295] Step 4:

[0296] The server evaluates and quantifies customer satisfaction based on the determined emotional state. At this stage, the emotional state is classified into positive, negative, neutral, etc., and summarized as a numerical score. The input is the emotional state obtained in step 3, and the output is the numerical score of customer satisfaction.

[0297] Step 5:

[0298] The server transmits the evaluated customer satisfaction information to the mobile device in real time. The application installed on the device then provides feedback to the operator. The input is the numerical customer satisfaction score obtained in step 4, and the output is the feedback information displayed on the device.

[0299] Step 6:

[0300] The operator adjusts their response to the customer based on real-time feedback information. Specifically, they respond quickly to feedback and take measures to improve service as needed. The input is the feedback information displayed on the terminal in step 5, and the output is the operator's adapted actions.

[0301] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0302] This invention relates to a system that combines an emotion engine, which recognizes user emotions from acquired voice data, in order to evaluate the work of telephone reception operators with greater accuracy and improve the quality of customer service.

[0303] When a user makes an inquiry or consultation by phone, the server collects voice data in real time. This voice data is converted into text data by the server's speech recognition engine. The converted text data is stored in a database and used for subsequent analysis.

[0304] The server then utilizes an emotion engine to recognize the user's emotions based on text data and information such as tone, pitch, and speed of voice. This process allows for a highly accurate determination of whether the user is experiencing positive, negative, or neutral emotions.

[0305] The results of emotion recognition are directly used to quantify customer satisfaction. Based on these results, the server evaluates operator performance and, if particularly strong negative emotions are expressed, determines that a complaint is likely and notifies the manager. This notification enables a quick response and helps resolve customer dissatisfaction early.

[0306] Furthermore, the feedback is provided to the operator in real time and can be used as a response guide including improvement suggestions. For example, when the user says "I don't understand" or "I'm in trouble", the server catches this as a sign of dissatisfaction and presents specific response methods to the operator. In this way, the system supports the operator to take appropriate responses and aims to improve customer satisfaction as a result.

[0307] Through the system of the present invention, the response quality of the operator can be precisely evaluated, and efficient and effective customer response can be realized. This leads to an improvement in the overall service level in telephone response.

[0308] The following describes the processing flow.

[0309] Step 1:

[0310] When the user contacts the window by phone, the server acquires the voice data of the call in real time. The server connects to the telephone system and prepares the necessary preparations to start voice streaming.

[0311] Step 2:

[0312] The server sends the acquired voice data to the voice recognition engine to convert the voice into text data. This converted text data is stored in the database in the server for use in subsequent processes.

[0313] Step 3:

[0314] The server uses the emotion engine to analyze the text data and voice data. Specifically, the emotion of the user is determined based on keywords in the text, tone of voice, speed of speaking, etc. By this determination, the emotional state of the user is classified as positive, negative, or neutral.

[0315] Step 4:

[0316] The server quantifies customer satisfaction based on the determined emotional state. This quantified data is directly linked to operator performance evaluation and used for further analysis.

[0317] Step 5:

[0318] The server identifies potentially problematic calls based on emotional state and quantified ratings. Identified calls immediately notify administrators, allowing for prompt action as needed.

[0319] Step 6:

[0320] The server provides operators with real-time feedback. This feedback includes what went well, areas for improvement, and even specific suggestions for improvement. This allows operators to use this feedback to provide better service in future calls.

[0321] This series of processes allows the server to analyze user emotions in detail, thereby improving the quality of service provided by telephone operators and increasing customer satisfaction.

[0322] (Example 2)

[0323] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0324] Conventional voice communication systems have the challenge of making it difficult to objectively evaluate the quality of operator responses based on actual customer emotions and satisfaction levels. Furthermore, they lacked the means to proactively identify potential complaints and address them quickly. As a result, improvements in customer satisfaction and the early resolution of complaints were not fully achieved.

[0325] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0326] In this invention, the server includes means for collecting acoustic information, means for converting acoustic information into text information, means for analyzing the characteristics of the text information and acoustic information to identify emotions, means for calculating an evaluation index based on the identified emotions, means for providing the calculated evaluation index to the communication operator, means for identifying communications that have the potential to generate dissatisfaction, and means for presenting measures to improve service to the communication operator. This enables precise evaluation of the operator's response quality based on customer emotions and satisfaction, allowing for the early detection of potential complaints and prompt response.

[0327] "Acoustic information" refers to data related to voice or sound, and in particular, to voice signals acquired from the user during communication.

[0328] "Textual information" refers to data in text format obtained by converting acoustic information using speech recognition technology.

[0329] "Analysis" refers to the process of evaluating the characteristics of acoustic and textual information to identify the user's emotions.

[0330] "Means of identifying emotions" refers to technical means that analyze a user's emotional state and classify it as positive, negative, or neutral.

[0331] "Evaluation metrics" refer to numerical values ​​that quantify customer satisfaction or operator service quality, calculated based on identified emotions.

[0332] "Communications personnel" refers to operators who handle acoustic information or individuals engaged in such work.

[0333] "Means for identifying communications that may generate dissatisfaction" refers to a function that uses analyzed sentiment information and evaluation metrics to identify communications that may potentially generate complaints.

[0334] "Means of providing solutions for improving customer service" refers to a systemic function that allows communications personnel to provide specific advice and instructions on how to improve their interactions with customers.

[0335] This invention provides a technology for improving the quality of operator responses in a voice communication system by analyzing the user's emotions. Specific embodiments for carrying out this invention are described below.

[0336] The server collects the user's acoustic information through a communication device. This acoustic information is converted into text information using software equipped with speech recognition technology. A common example of speech recognition software is a speech recognition engine.

[0337] The converted text information is stored in a database by the server. The server then uses an emotion analysis engine to analyze the characteristics of the text and audio information and identify the user's emotions. Natural language processing techniques and machine learning algorithms can be used as the emotion analysis engine.

[0338] The results of emotion identification are quantified as evaluation metrics and provided to the communications operator by the server. These metrics indicate operator performance and customer satisfaction. The server can also notify administrators of potentially dissatisfying communications based on the identified emotions. This feature facilitates a quicker response.

[0339] Furthermore, the server provides communication personnel with real-time suggestions for improving their responses. This allows operators to communicate effectively with customers and resolve problems quickly.

[0340] As a concrete example, consider a scenario where a user calls customer support and says, "I don't know how to use the product." The server collects this statement as acoustic information, converts it to text information, and then analyzes it. If the analysis determines that the user's statement suggests confusion or dissatisfaction, the server notifies the operator and instructs them to provide specific instructions on how to use the product. It is also conceivable to use a generative AI model to create prompts related to optimizing communication. An example of such a prompt might be, "Please describe a system that analyzes customer voice data, identifies emotions, and suggests appropriate responses to operators."

[0341] In this way, this invention enables communication systems to provide more effective and satisfying customer service.

[0342] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0343] Step 1:

[0344] When a user calls customer support, the server collects acoustic information in real time via a communication device. The input data is the user's voice, and this voice data is sent to the server.

[0345] Step 2:

[0346] The server uses a speech recognition engine to convert the collected acoustic information (audio data) into text information. This process extracts the content of the speech as a string of characters. The input is acoustic information, and the output is text information.

[0347] Step 3:

[0348] The converted text information is stored in the server's database. Simultaneously, the server sends the stored text information and acoustic information characteristics (tone, pitch, speed, etc.) to the emotion analysis engine. The input consists of text information and acoustic information characteristics, and emotion is analyzed based on these.

[0349] Step 4:

[0350] The server uses an emotion analysis engine to identify the user's emotion as positive, negative, or neutral. The emotion identification result is quantified as an evaluation metric and used for the next process. The input here is the result of the data analysis in the previous step, and the output is the metric value indicating the emotion.

[0351] Step 5:

[0352] The server determines the potential for a user complaint based on evaluation metrics obtained through sentiment analysis. If strong negative emotions are detected, it sends a notification to the communications officer and their manager. The input is identified sentiment information, and the output is a notification and response instructions.

[0353] Step 6:

[0354] The server provides communication personnel with real-time suggestions for improving their responses. These suggestions include specific advice and procedures to support the operators' current handling of calls. Inputs are evaluation metrics and identified sentiment information, while outputs are response guidelines.

[0355] Step 7:

[0356] The server evaluates the communication operator's performance based on the feedback. This evaluation is recorded to help improve future responses. Inputs are the communication results and feedback information, while outputs are the improved response methods and records.

[0357] This series of processes enables effective responses that are tailored to the user's emotions, leading to improved operator service quality and customer satisfaction.

[0358] (Application Example 2)

[0359] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0360] In telephone reception operations, operators are required to appropriately assess customer emotions and respond quickly to improve customer satisfaction. Providing real-time feedback and concrete improvement suggestions is a key challenge in this context.

[0361] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0362] In this invention, the server includes means for acquiring voice information, means for converting voice information into text information, means for analyzing the text information to determine the emotional state, and means for providing improvement recommendations to the operator in real time based on the emotional state. This enables the operator to understand the customer's emotions in real time and take appropriate action.

[0363] "Voice information" refers to the content of conversations with customers during telephone reception operations, and is data acquired through operations performed by operators.

[0364] "Textual information" refers to data obtained by converting audio information into text, and is a format used for subsequent data analysis.

[0365] "Emotional status" refers to the state of a customer's emotions, analyzed based on audio and textual information, and is an indicator that shows positive, negative, or neutral.

[0366] "Customer satisfaction" is a numerical indicator of customer satisfaction based on analyzed emotional states, and is used to evaluate the quality of services.

[0367] An "operator" is a person who is responsible for telephone reception and customer service, and is the entity that receives feedback from the system.

[0368] "Providing real-time improvement recommendations" means having a function that allows operators to immediately provide suggestions and instructions during customer calls, prompting them to take appropriate action.

[0369] The system that implements this application is designed to allow operators handling telephone reception duties to receive real-time feedback and improvement suggestions while interacting with customers. This system uses a smartphone as the terminal for acquiring voice information. The smartphone acquires the customer's call content as voice information in real time.

[0370] The acquired audio information is converted into text information using a speech recognition engine on the server. For example, Google Cloud Speech-to-Text is used as this speech recognition engine. The converted text information is further analyzed by an emotion engine on the server. For example, IBM Watson Tone Analyzer is used as this emotion engine. The emotion engine analyzes the text information and determines the customer's emotional state based on the audio characteristic data.

[0371] The determined emotional state is quantified by the server and statistically processed as user satisfaction. This information is sent back to the operator via a dedicated application, allowing the operator to receive real-time recommendations for improving customer service. For example, if a customer expresses dissatisfaction, the application will provide the operator with specific countermeasures.

[0372] For example, if a customer says they are "concerned about the content of their inquiry," the operator will receive advice such as, "The customer is feeling anxious. Please calmly explain the situation and promise to take prompt action if necessary." In this way, the operator can ensure that they take appropriate action.

[0373] An example of a prompt might be: "Perform a sentiment analysis on the customer's statements and provide necessary improvement advice. Audio data: 'Customer statements audio data'."

[0374] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0375] Step 1:

[0376] A smartphone acquires audio information during a call with a customer. The input is the audio of the conversation with the customer, and the output is digitized audio data. The audio data is collected via the microphone and temporarily stored in a database.

[0377] Step 2:

[0378] The server uses a speech recognition engine to convert the acquired speech information into text information. The input is speech data, and the output is converted text data. This process uses technologies such as Google Cloud Speech-to-Text to analyze the speech data and convert it to text.

[0379] Step 3:

[0380] The server analyzes text data and speech characteristic data (tone, pitch, speed, etc.) using an emotion engine to determine the emotional state. The input is text information and speech characteristic data, and the output is an emotional state indicating either positive, negative, or neutral. Emotion analysis is performed using tools such as IBM Watson Tone Analyzer.

[0381] Step 4:

[0382] The server quantifies the emotional state it determines and generates a user satisfaction index. The input is the emotional state, and the output is quantified satisfaction data. This index is statistically processed using a mathematical algorithm.

[0383] Step 5:

[0384] Based on quantified user satisfaction data, real-time feedback is provided to operators through a dedicated application. The input is satisfaction data, and the output is improvement recommendations and specific countermeasures. For example, a message such as, "The customer is feeling uneasy. Please explain calmly," might be provided.

[0385] Step 6:

[0386] The operator utilizes a generative AI model based on the prompt text to formulate further countermeasures. The input consists of feedback and the prompt text from the generative AI model, and the output is a customized response suggestion. For example, the prompt "Perform sentiment analysis on the customer's statement and provide necessary improvement advice" can be entered to receive suggestions from the model.

[0387] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0388] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0389] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0390] [Third Embodiment]

[0391] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0392] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0393] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0394] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0395] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0396] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0397] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0398] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0399] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0400] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0401] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0402] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0403] This invention relates to a system for efficiently evaluating the work of telephone reception operators and improving customer satisfaction. This system acquires voice data, transcribes the voice data into text, analyzes emotional states, quantifies customer satisfaction, identifies potential complaints, and provides feedback and improvement suggestions.

[0404] First, when a user makes an inquiry by phone, the audio is collected in real time by a server. Next, the server converts the collected audio data into text data using speech recognition technology. This converted text data is then analyzed by a generative AI model to determine the customer's emotional state. Here, keywords in the text, as well as the tone and speed of the voice, are taken into consideration.

[0405] Subsequently, the server quantifies customer satisfaction based on emotional state and evaluates the operator's performance. Furthermore, the server can compare this with past call data to evaluate the operator's work in more depth. Based on this evaluation, the server provides feedback to the operator and notifies them of areas for improvement. If there are many negative keywords in the call, the server determines that the call may be a complaint and notifies the manager.

[0406] For example, if a user frequently uses phrases like "I'll consider using it again" or "I'm dissatisfied," the server will record the call as one requiring special attention and notify the administrator that immediate action is needed. On the other hand, if a user uses positive language such as "thank you" or "that was helpful" during routine interactions, the server will use that information to provide positive feedback to the operator and share it as an example of good service.

[0407] Thus, the present invention provides a system that can improve the quality of telephone reception operators' responses and increase customer satisfaction.

[0408] The following describes the processing flow.

[0409] Step 1:

[0410] When a user makes a call to the customer service center, the server collects the audio data in real time. First, the server connects to the telephone system and prepares to acquire the audio stream of the call.

[0411] Step 2:

[0412] The server sends the acquired audio data to the speech recognition engine, which converts the audio data into text format. The converted text data is stored in a database on the server and prepared for the next process.

[0413] Step 3:

[0414] The server uses a generative AI model to analyze the converted text data. This analysis includes keyword extraction and sentiment analysis from the text. The server determines whether the customer's statements indicate a positive, negative, or neutral emotional state.

[0415] Step 4:

[0416] The server analyzes the characteristics of the voice data (such as tone, pitch, and speed) and combines them with the results of text analysis to determine the customer's overall emotional state. This allows for a more accurate assessment of customer satisfaction.

[0417] Step 5:

[0418] The server quantifies customer satisfaction using response time and sentiment scores derived from text and voice analysis. Simultaneously, it evaluates operator performance based on this quantified rating and identifies areas for improvement.

[0419] Step 6:

[0420] The server identifies calls that could potentially lead to complaints based on customer satisfaction scores and sentiment analysis results. If the negative score exceeds a certain value, the call is notified to the management system as a potential complaint.

[0421] Step 7:

[0422] The server provides feedback to the operator. Specifically, it identifies what went well and what needs improvement so that the operator can use this feedback for future calls. It also provides specific suggestions for improvement aimed at increasing customer satisfaction.

[0423] (Example 1)

[0424] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0425] Traditional telephone support operations lacked methods for objectively evaluating the quality of operator responses and efficiently incorporating customer feedback. This made it difficult to improve customer satisfaction, and in particular, led to delays in the early detection and resolution of complaints.

[0426] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0427] In this invention, the server includes means for acquiring voice information, means for converting voice information into text information, and means for analyzing the text information to determine the emotional state. This makes it possible to evaluate operator responses in real time and quantify customer satisfaction. It also makes it possible to quickly identify complaints based on specific keywords and notify the appropriate department.

[0428] "Means for acquiring voice information" refers to technology or equipment for receiving phone calls made by users in real time and collecting that voice data on a server.

[0429] "Means of converting audio information to text information" refers to a process that uses speech recognition technology to convert acquired audio data into text data, thereby converting audio into text data.

[0430] "Means of analyzing textual information to determine emotional state" refers to an algorithm or system that analyzes text data and determines the user's emotions based on the keywords and contextual information contained therein.

[0431] "Methods for quantifying user satisfaction" refer to methods for quantitatively measuring user experience and satisfaction by performing statistical or numerical evaluations based on the determined emotional state.

[0432] "Methods for returning information to those responsible for operations" refers to the process of communicating quantified information and evaluation results to operators and those responsible for operations, and using that information to improve and evaluate their work.

[0433] "Means for evaluating work performance" refers to a system or method for evaluating the work performance of operators or staff by comparing and analyzing past call information with current evaluations.

[0434] "Means for identifying calls as complaints" refers to a function that analyzes the frequency and context of negative keywords contained in the call content to recognize that the call has the potential to be a complaint and to notify the relevant parties.

[0435] This invention is a system for efficiently evaluating operators' telephone handling skills and improving customer satisfaction. The following describes a specific implementation of this system.

[0436] When a user makes a phone inquiry, the audio is captured in real time by the server. The server is connected to a microphone and receiving device for audio data acquisition. The captured audio data is converted into text data on the server using Google Cloud Speech-to-Text or a similar service. After conversion to text data, the server inputs the resulting text information into a generating AI model.

[0437] This generative AI model performs sentiment analysis as part of natural language processing technology, determining the user's emotional state from keywords and context contained within the text. For example, the server detects negative keywords such as "dissatisfied" and "high number of inquiries," while also analyzing positive keywords such as "satisfied" and "helpful."

[0438] Next, the server quantifies user satisfaction based on the determined emotional state. This quantified satisfaction level is provided to the service provider as feedback. This feedback is used to evaluate service performance by comparing it with past call information. Furthermore, the server can identify specific calls as complaints based on the frequency of negative keywords, thereby prompting administrators to take prompt action.

[0439] For example, if a user makes a statement such as "I'm dissatisfied with this service," the server immediately identifies this as a negative keyword and provides appropriate feedback to the relevant person in charge.

[0440] Examples of prompts for a generative AI model include the following:

[0441] "Based on the text data from this call, please analyze the customer's emotional state. Consider the keywords and their tone to identify the emotions being expressed."

[0442] In this way, the server can collect and analyze important data to improve the quality of operator responses, ultimately aiming to increase customer satisfaction.

[0443] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0444] Step 1:

[0445] As soon as a user makes a phone call and the call begins, the audio is streamed to the server in real time. The server receives the audio data through a microphone and receiving hardware. The input audio data is then stored directly in the server's memory.

[0446] Step 2:

[0447] The server converts the acquired audio data into text data using speech recognition technology. This process uses a speech recognition API such as Google Cloud Speech-to-Text. The server sends the audio file to the API and receives the converted text data. The input is audio data, and the output is the corresponding text data.

[0448] Step 3:

[0449] The server analyzes text data transformed using a generative AI model to determine the emotional state. It receives text data as input, processes it with prompts, and inputs it into the generative AI model. The output the server receives from the model includes emotional state scores and keyword analysis results. Specifically, it identifies and scores negative and positive keywords within the text.

[0450] Step 4:

[0451] The server quantifies customer satisfaction based on the determined emotional state score. It converts the emotional score into a quantitative evaluation and outputs it as user satisfaction. The input is the emotional score, and the output is the quantified customer satisfaction. Based on this quantified result, the server performs a comparative evaluation with past data.

[0452] Step 5:

[0453] The server provides feedback to the business personnel based on the evaluation results. Based on the entered customer satisfaction scores and past evaluations, it generates improvement suggestions and positive feedback as text and sends them to the business personnel. The output is a feedback document including improvement suggestions.

[0454] Step 6:

[0455] The server analyzes the frequency of negative keywords in the call content and, if necessary, identifies the call as a complaint. This process compares the current call with past negative response patterns and generates an alert if a threshold is exceeded. The output is a complaint alert directed to the administrator.

[0456] (Application Example 1)

[0457] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0458] In telephone customer service, there is a problem in that it is difficult to appropriately grasp the customer's emotional state and satisfaction level and provide immediate feedback to operators. Furthermore, there is a lack of mechanisms to quickly identify and address calls that may be complaints.

[0459] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0460] In this invention, the server includes means for acquiring voice information, means for converting the voice information into a transcript, means for analyzing the transcript to determine the emotional state, means for evaluating customer satisfaction based on the determined emotional state, means for providing the evaluated information to the guide, and means including an application installed on a mobile terminal that displays the evaluation results in real time. This allows operators to grasp the customer's emotions in real time and provide immediate feedback and make improvements.

[0461] "Voice information" refers to the audio data of conversations between customers and operators.

[0462] "Means of acquisition" refers to the device or process for collecting audio information in digital format and storing it on a server.

[0463] "Methods for converting to transcription" refers to the process of using speech recognition technology to convert audio information into text data.

[0464] "Means of analyzing transcripts to determine emotional states" refers to algorithms or devices that analyze text data to determine a customer's emotions and attitudes.

[0465] "Methods for evaluating customer satisfaction" refers to the process of quantifying or scoring customer satisfaction based on the determined emotional state.

[0466] "Means of providing information to the guide" refers to an interface or process for transmitting analysis results and feedback to the operator.

[0467] "Applications installed on mobile devices that display data in real time" refers to software installed on portable information terminals such as smartphones and tablets that instantly displays analysis results.

[0468] To implement this invention, the server first plays the role of acquiring audio information. The audio information is input from a device that collects customer-operator conversations in real time. Next, the server uses speech recognition technology to convert the audio information into a transcript. This process uses a speech recognition API such as "Google Cloud Speech-to-Text".

[0469] Next, using a generative AI model, the server analyzes the converted text data to determine the customer's emotional state. Specifically, it analyzes keywords and context within the text, and also takes into account auditory information such as tone and speed of voice. The evaluated customer satisfaction information is provided to the information desk staff in real time. This information is displayed on a specific application installed on a mobile device such as a smartphone or tablet, making it easier for the operator to adjust their response on the spot.

[0470] For example, if an operator receives feedback from a customer stating, "I'm unhappy with the wait," the server immediately analyzes this information and displays an alert on the operator's mobile device indicating that "the customer is likely dissatisfied." Based on this notification, the operator can then improve their customer service.

[0471] Furthermore, an example of a prompt sentence for the AI ​​model generated by this application is: "Predict the customer's emotional state from this sentence: 'The service is great, but the response is slow.'" By utilizing this prompt sentence, it becomes possible to analyze the customer's emotional state appropriately.

[0472] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0473] Step 1:

[0474] The server acquires voice information in real time during a call. This voice information consists of audio data spoken by the user via telephone, which is stored on the server in digital format. The input is voice information, and the output is the digital audio data stored on the server.

[0475] Step 2:

[0476] The server uses a speech recognition API to convert the acquired audio information into text data. This process uses "Google Cloud Speech-to-Text". The input is the digital audio data saved in step 1, and the output is text data.

[0477] Step 3:

[0478] The server analyzes the converted text data using a generative AI model. Specifically, it predicts the user's emotional state based on keywords and context contained in the text. At this time, the choice, frequency, and phrasing of words in the text are considered. The input is the text data generated in step 2, and the output is the determined emotional state.

[0479] Step 4:

[0480] The server evaluates and quantifies customer satisfaction based on the determined emotional state. At this stage, the emotional state is classified into positive, negative, neutral, etc., and summarized as a numerical score. The input is the emotional state obtained in step 3, and the output is the numerical score of customer satisfaction.

[0481] Step 5:

[0482] The server transmits the evaluated customer satisfaction information to the mobile device in real time. The application installed on the device then provides feedback to the operator. The input is the numerical customer satisfaction score obtained in step 4, and the output is the feedback information displayed on the device.

[0483] Step 6:

[0484] The operator adjusts their response to the customer based on real-time feedback information. Specifically, they respond quickly to feedback and take measures to improve service as needed. The input is the feedback information displayed on the terminal in step 5, and the output is the operator's adapted actions.

[0485] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0486] This invention relates to a system that combines an emotion engine, which recognizes user emotions from acquired voice data, in order to evaluate the work of telephone reception operators with greater accuracy and improve the quality of customer service.

[0487] When a user makes an inquiry or consultation by phone, the server collects voice data in real time. This voice data is converted into text data by the server's speech recognition engine. The converted text data is stored in a database and used for subsequent analysis.

[0488] The server then utilizes an emotion engine to recognize the user's emotions based on text data and information such as tone, pitch, and speed of voice. This process allows for a highly accurate determination of whether the user is experiencing positive, negative, or neutral emotions.

[0489] The results of emotion recognition are directly used to quantify customer satisfaction. Based on these results, the server evaluates operator performance and, if particularly strong negative emotions are expressed, determines that a complaint is likely and notifies the manager. This notification enables a quick response and helps resolve customer dissatisfaction early.

[0490] Furthermore, feedback is provided to operators in real time and can be used as a response guide that includes suggestions for improvement. For example, if a user says "I don't understand" or "I'm having trouble," the server will interpret this as a sign of dissatisfaction and provide the operator with specific ways to respond. In this way, the system supports operators in taking appropriate responses, ultimately aiming to improve customer satisfaction.

[0491] Through the system of this invention, the quality of operator responses can be precisely evaluated, enabling efficient and effective customer service. This leads to an overall improvement in the service level of telephone support.

[0492] The following describes the processing flow.

[0493] Step 1:

[0494] When a user contacts the customer service center by phone, the server acquires the audio data of the call in real time. The server connects to the phone system and makes the necessary preparations to begin audio streaming.

[0495] Step 2:

[0496] The server sends the acquired audio data to a speech recognition engine, which converts the audio into text data. This converted text data is stored in a database on the server for use in subsequent processes.

[0497] Step 3:

[0498] The server uses an emotion engine to analyze text and audio data. Specifically, it determines the user's emotions based on keywords in the text, tone of voice, speaking speed, and other factors. Based on this determination, the user's emotional state is classified as positive, negative, or neutral.

[0499] Step 4:

[0500] The server quantifies customer satisfaction based on the determined emotional state. This quantified data is directly linked to operator performance evaluation and used for further analysis.

[0501] Step 5:

[0502] The server identifies potentially problematic calls based on emotional state and quantified ratings. Identified calls immediately notify administrators, allowing for prompt action as needed.

[0503] Step 6:

[0504] The server provides operators with real-time feedback. This feedback includes what went well, areas for improvement, and even specific suggestions for improvement. This allows operators to use this feedback to provide better service in future calls.

[0505] This series of processes allows the server to analyze user emotions in detail, thereby improving the quality of service provided by telephone operators and increasing customer satisfaction.

[0506] (Example 2)

[0507] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0508] Conventional voice communication systems have the challenge of making it difficult to objectively evaluate the quality of operator responses based on actual customer emotions and satisfaction levels. Furthermore, they lacked the means to proactively identify potential complaints and address them quickly. As a result, improvements in customer satisfaction and the early resolution of complaints were not fully achieved.

[0509] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0510] In this invention, the server includes means for collecting acoustic information, means for converting acoustic information into text information, means for analyzing the characteristics of the text information and acoustic information to identify emotions, means for calculating an evaluation index based on the identified emotions, means for providing the calculated evaluation index to the communication operator, means for identifying communications that have the potential to generate dissatisfaction, and means for presenting measures to improve service to the communication operator. This enables precise evaluation of the operator's response quality based on customer emotions and satisfaction, allowing for the early detection of potential complaints and prompt response.

[0511] "Acoustic information" refers to data related to voice or sound, and in particular, to voice signals acquired from the user during communication.

[0512] "Textual information" refers to data in text format obtained by converting acoustic information using speech recognition technology.

[0513] "Analysis" refers to the process of evaluating the characteristics of acoustic and textual information to identify the user's emotions.

[0514] "Means of identifying emotions" refers to technical means that analyze a user's emotional state and classify it as positive, negative, or neutral.

[0515] "Evaluation metrics" refer to numerical values ​​that quantify customer satisfaction or operator service quality, calculated based on identified emotions.

[0516] "Communications personnel" refers to operators who handle acoustic information or individuals engaged in such work.

[0517] "Means for identifying communications that may generate dissatisfaction" refers to a function that uses analyzed sentiment information and evaluation metrics to identify communications that may potentially generate complaints.

[0518] "Means of providing solutions for improving customer service" refers to a systemic function that allows communications personnel to provide specific advice and instructions on how to improve their interactions with customers.

[0519] This invention provides a technology for improving the quality of operator responses in a voice communication system by analyzing the user's emotions. Specific embodiments for carrying out this invention are described below.

[0520] The server collects the user's acoustic information through a communication device. This acoustic information is converted into text information using software equipped with speech recognition technology. A common example of speech recognition software is a speech recognition engine.

[0521] The converted text information is stored in a database by the server. The server then uses an emotion analysis engine to analyze the characteristics of the text and audio information and identify the user's emotions. Natural language processing techniques and machine learning algorithms can be used as the emotion analysis engine.

[0522] The results of emotion identification are quantified as evaluation metrics and provided to the communications operator by the server. These metrics indicate operator performance and customer satisfaction. The server can also notify administrators of potentially dissatisfying communications based on the identified emotions. This feature facilitates a quicker response.

[0523] Furthermore, the server provides communication personnel with real-time suggestions for improving their responses. This allows operators to communicate effectively with customers and resolve problems quickly.

[0524] As a concrete example, consider a scenario where a user calls customer support and says, "I don't know how to use the product." The server collects this statement as acoustic information, converts it to text information, and then analyzes it. If the analysis determines that the user's statement suggests confusion or dissatisfaction, the server notifies the operator and instructs them to provide specific instructions on how to use the product. It is also conceivable to use a generative AI model to create prompts related to optimizing communication. An example of such a prompt might be, "Please describe a system that analyzes customer voice data, identifies emotions, and suggests appropriate responses to operators."

[0525] In this way, this invention enables communication systems to provide more effective and satisfying customer service.

[0526] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0527] Step 1:

[0528] When a user calls customer support, the server collects acoustic information in real time via a communication device. The input data is the user's voice, and this voice data is sent to the server.

[0529] Step 2:

[0530] The server uses a speech recognition engine to convert the collected acoustic information (audio data) into text information. This process extracts the content of the speech as a string of characters. The input is acoustic information, and the output is text information.

[0531] Step 3:

[0532] The converted text information is stored in the server's database. Simultaneously, the server sends the stored text information and acoustic information characteristics (tone, pitch, speed, etc.) to the emotion analysis engine. The input consists of text information and acoustic information characteristics, and emotion is analyzed based on these.

[0533] Step 4:

[0534] The server uses an emotion analysis engine to identify the user's emotion as positive, negative, or neutral. The emotion identification result is quantified as an evaluation metric and used for the next process. The input here is the result of the data analysis in the previous step, and the output is the metric value indicating the emotion.

[0535] Step 5:

[0536] The server determines the potential for a user complaint based on evaluation metrics obtained through sentiment analysis. If strong negative emotions are detected, it sends a notification to the communications officer and their manager. The input is identified sentiment information, and the output is a notification and response instructions.

[0537] Step 6:

[0538] The server provides communication personnel with real-time suggestions for improving their responses. These suggestions include specific advice and procedures to support the operators' current handling of calls. Inputs are evaluation metrics and identified sentiment information, while outputs are response guidelines.

[0539] Step 7:

[0540] The server evaluates the communication operator's performance based on the feedback. This evaluation is recorded to help improve future responses. Inputs are the communication results and feedback information, while outputs are the improved response methods and records.

[0541] This series of processes enables effective responses that are tailored to the user's emotions, leading to improved operator service quality and customer satisfaction.

[0542] (Application Example 2)

[0543] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0544] In telephone reception operations, operators are required to appropriately assess customer emotions and respond quickly to improve customer satisfaction. Providing real-time feedback and concrete improvement suggestions is a key challenge in this context.

[0545] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0546] In this invention, the server includes means for acquiring voice information, means for converting voice information into text information, means for analyzing the text information to determine the emotional state, and means for providing improvement recommendations to the operator in real time based on the emotional state. This enables the operator to understand the customer's emotions in real time and take appropriate action.

[0547] "Voice information" refers to the content of conversations with customers during telephone reception operations, and is data acquired through operations performed by operators.

[0548] "Textual information" refers to data obtained by converting audio information into text, and is a format used for subsequent data analysis.

[0549] "Emotional status" refers to the state of a customer's emotions, analyzed based on audio and textual information, and is an indicator that shows positive, negative, or neutral.

[0550] "Customer satisfaction" is a numerical indicator of customer satisfaction based on analyzed emotional states, and is used to evaluate the quality of services.

[0551] An "operator" is a person who is responsible for telephone reception and customer service, and is the entity that receives feedback from the system.

[0552] "Providing real-time improvement recommendations" means having a function that allows operators to immediately provide suggestions and instructions during customer calls, prompting them to take appropriate action.

[0553] The system that implements this application is designed to allow operators handling telephone reception duties to receive real-time feedback and improvement suggestions while interacting with customers. This system uses a smartphone as the terminal for acquiring voice information. The smartphone acquires the customer's call content as voice information in real time.

[0554] The acquired audio information is converted into text information using a speech recognition engine on the server. For example, Google Cloud Speech-to-Text is used as this speech recognition engine. The converted text information is further analyzed by an emotion engine on the server. For example, IBM Watson Tone Analyzer is used as this emotion engine. The emotion engine analyzes the text information and determines the customer's emotional state based on the audio characteristic data.

[0555] The determined emotional state is quantified by the server and statistically processed as user satisfaction. This information is sent back to the operator via a dedicated application, allowing the operator to receive real-time recommendations for improving customer service. For example, if a customer expresses dissatisfaction, the application will provide the operator with specific countermeasures.

[0556] For example, if a customer says they are "concerned about the content of their inquiry," the operator will receive advice such as, "The customer is feeling anxious. Please calmly explain the situation and promise to take prompt action if necessary." In this way, the operator can ensure that they take appropriate action.

[0557] An example of a prompt might be: "Perform a sentiment analysis on the customer's statements and provide necessary improvement advice. Audio data: 'Customer statements audio data'."

[0558] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0559] Step 1:

[0560] A smartphone acquires audio information during a call with a customer. The input is the audio of the conversation with the customer, and the output is digitized audio data. The audio data is collected via the microphone and temporarily stored in a database.

[0561] Step 2:

[0562] The server uses a speech recognition engine to convert the acquired speech information into text information. The input is speech data, and the output is converted text data. This process uses technologies such as Google Cloud Speech-to-Text to analyze the speech data and convert it to text.

[0563] Step 3:

[0564] The server analyzes text data and speech characteristic data (tone, pitch, speed, etc.) using an emotion engine to determine the emotional state. The input is text information and speech characteristic data, and the output is an emotional state indicating either positive, negative, or neutral. Emotion analysis is performed using tools such as IBM Watson Tone Analyzer.

[0565] Step 4:

[0566] The server quantifies the emotional state it determines and generates a user satisfaction index. The input is the emotional state, and the output is quantified satisfaction data. This index is statistically processed using a mathematical algorithm.

[0567] Step 5:

[0568] Based on quantified user satisfaction data, real-time feedback is provided to operators through a dedicated application. The input is satisfaction data, and the output is improvement recommendations and specific countermeasures. For example, a message such as, "The customer is feeling uneasy. Please explain calmly," might be provided.

[0569] Step 6:

[0570] The operator utilizes a generative AI model based on the prompt text to formulate further countermeasures. The input consists of feedback and the prompt text from the generative AI model, and the output is a customized response suggestion. For example, the prompt "Perform sentiment analysis on the customer's statement and provide necessary improvement advice" can be entered to receive suggestions from the model.

[0571] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0572] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0573] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0574] [Fourth Embodiment]

[0575] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0576] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0577] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0578] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0579] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0580] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0581] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0582] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0583] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0584] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0585] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0586] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0587] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0588] This invention relates to a system for efficiently evaluating the work of telephone reception operators and improving customer satisfaction. This system acquires voice data, transcribes the voice data into text, analyzes emotional states, quantifies customer satisfaction, identifies potential complaints, and provides feedback and improvement suggestions.

[0589] First, when a user makes an inquiry by phone, the audio is collected in real time by a server. Next, the server converts the collected audio data into text data using speech recognition technology. This converted text data is then analyzed by a generative AI model to determine the customer's emotional state. Here, keywords in the text, as well as the tone and speed of the voice, are taken into consideration.

[0590] Subsequently, the server quantifies customer satisfaction based on emotional state and evaluates the operator's performance. Furthermore, the server can compare this with past call data to evaluate the operator's work in more depth. Based on this evaluation, the server provides feedback to the operator and notifies them of areas for improvement. If there are many negative keywords in the call, the server determines that the call may be a complaint and notifies the manager.

[0591] For example, if a user frequently uses phrases like "I'll consider using it again" or "I'm dissatisfied," the server will record the call as one requiring special attention and notify the administrator that immediate action is needed. On the other hand, if a user uses positive language such as "thank you" or "that was helpful" during routine interactions, the server will use that information to provide positive feedback to the operator and share it as an example of good service.

[0592] Thus, the present invention provides a system that can improve the quality of telephone reception operators' responses and increase customer satisfaction.

[0593] The following describes the processing flow.

[0594] Step 1:

[0595] When a user makes a call to the customer service center, the server collects the audio data in real time. First, the server connects to the telephone system and prepares to acquire the audio stream of the call.

[0596] Step 2:

[0597] The server sends the acquired audio data to the speech recognition engine, which converts the audio data into text format. The converted text data is stored in a database on the server and prepared for the next process.

[0598] Step 3:

[0599] The server uses a generative AI model to analyze the converted text data. This analysis includes keyword extraction and sentiment analysis from the text. The server determines whether the customer's statements indicate a positive, negative, or neutral emotional state.

[0600] Step 4:

[0601] The server analyzes the characteristics of the voice data (such as tone, pitch, and speed) and combines them with the results of text analysis to determine the customer's overall emotional state. This allows for a more accurate assessment of customer satisfaction.

[0602] Step 5:

[0603] The server quantifies customer satisfaction using response time and sentiment scores derived from text and voice analysis. Simultaneously, it evaluates operator performance based on this quantified rating and identifies areas for improvement.

[0604] Step 6:

[0605] The server identifies calls that could potentially lead to complaints based on customer satisfaction scores and sentiment analysis results. If the negative score exceeds a certain value, the call is notified to the management system as a potential complaint.

[0606] Step 7:

[0607] The server provides feedback to the operator. Specifically, it identifies what went well and what needs improvement so that the operator can use this feedback for future calls. It also provides specific suggestions for improvement aimed at increasing customer satisfaction.

[0608] (Example 1)

[0609] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0610] Traditional telephone support operations lacked methods for objectively evaluating the quality of operator responses and efficiently incorporating customer feedback. This made it difficult to improve customer satisfaction, and in particular, led to delays in the early detection and resolution of complaints.

[0611] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0612] In this invention, the server includes means for acquiring voice information, means for converting voice information into text information, and means for analyzing the text information to determine the emotional state. This makes it possible to evaluate operator responses in real time and quantify customer satisfaction. It also makes it possible to quickly identify complaints based on specific keywords and notify the appropriate department.

[0613] "Means for acquiring voice information" refers to technology or equipment for receiving phone calls made by users in real time and collecting that voice data on a server.

[0614] "Means of converting audio information to text information" refers to a process that uses speech recognition technology to convert acquired audio data into text data, thereby converting audio into text data.

[0615] "Means of analyzing textual information to determine emotional state" refers to an algorithm or system that analyzes text data and determines the user's emotions based on the keywords and contextual information contained therein.

[0616] "Methods for quantifying user satisfaction" refer to methods for quantitatively measuring user experience and satisfaction by performing statistical or numerical evaluations based on the determined emotional state.

[0617] "Methods for returning information to those responsible for operations" refers to the process of communicating quantified information and evaluation results to operators and those responsible for operations, and using that information to improve and evaluate their work.

[0618] "Means for evaluating work performance" refers to a system or method for evaluating the work performance of operators or staff by comparing and analyzing past call information with current evaluations.

[0619] "Means for identifying calls as complaints" refers to a function that analyzes the frequency and context of negative keywords contained in the call content to recognize that the call has the potential to be a complaint and to notify the relevant parties.

[0620] This invention is a system for efficiently evaluating operators' telephone handling skills and improving customer satisfaction. The following describes a specific implementation of this system.

[0621] When a user makes a phone inquiry, the audio is captured in real time by the server. The server is connected to a microphone and receiving device for audio data acquisition. The captured audio data is converted into text data on the server using Google Cloud Speech-to-Text or a similar service. After conversion to text data, the server inputs the resulting text information into a generating AI model.

[0622] This generative AI model performs sentiment analysis as part of natural language processing technology, determining the user's emotional state from keywords and context contained within the text. For example, the server detects negative keywords such as "dissatisfied" and "high number of inquiries," while also analyzing positive keywords such as "satisfied" and "helpful."

[0623] Next, the server quantifies user satisfaction based on the determined emotional state. This quantified satisfaction level is provided to the service provider as feedback. This feedback is used to evaluate service performance by comparing it with past call information. Furthermore, the server can identify specific calls as complaints based on the frequency of negative keywords, thereby prompting administrators to take prompt action.

[0624] For example, if a user makes a statement such as "I'm dissatisfied with this service," the server immediately identifies this as a negative keyword and provides appropriate feedback to the relevant person in charge.

[0625] Examples of prompts for a generative AI model include the following:

[0626] "Based on the text data from this call, please analyze the customer's emotional state. Consider the keywords and their tone to identify the emotions being expressed."

[0627] In this way, the server can collect and analyze important data to improve the quality of operator responses, ultimately aiming to increase customer satisfaction.

[0628] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0629] Step 1:

[0630] As soon as a user makes a phone call and the call begins, the audio is streamed to the server in real time. The server receives the audio data through a microphone and receiving hardware. The input audio data is then stored directly in the server's memory.

[0631] Step 2:

[0632] The server converts the acquired audio data into text data using speech recognition technology. This process uses a speech recognition API such as Google Cloud Speech-to-Text. The server sends the audio file to the API and receives the converted text data. The input is audio data, and the output is the corresponding text data.

[0633] Step 3:

[0634] The server analyzes text data transformed using a generative AI model to determine the emotional state. It receives text data as input, processes it with prompts, and inputs it into the generative AI model. The output the server receives from the model includes emotional state scores and keyword analysis results. Specifically, it identifies and scores negative and positive keywords within the text.

[0635] Step 4:

[0636] The server quantifies customer satisfaction based on the determined emotional state score. It converts the emotional score into a quantitative evaluation and outputs it as user satisfaction. The input is the emotional score, and the output is the quantified customer satisfaction. Based on this quantified result, the server performs a comparative evaluation with past data.

[0637] Step 5:

[0638] The server provides feedback to the business personnel based on the evaluation results. Based on the entered customer satisfaction scores and past evaluations, it generates improvement suggestions and positive feedback as text and sends them to the business personnel. The output is a feedback document including improvement suggestions.

[0639] Step 6:

[0640] The server analyzes the frequency of negative keywords in the call content and, if necessary, identifies the call as a complaint. This process compares the current call with past negative response patterns and generates an alert if a threshold is exceeded. The output is a complaint alert directed to the administrator.

[0641] (Application Example 1)

[0642] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0643] In telephone customer service, there is a problem in that it is difficult to appropriately grasp the customer's emotional state and satisfaction level and provide immediate feedback to operators. Furthermore, there is a lack of mechanisms to quickly identify and address calls that may be complaints.

[0644] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0645] In this invention, the server includes means for acquiring voice information, means for converting the voice information into a transcript, means for analyzing the transcript to determine the emotional state, means for evaluating customer satisfaction based on the determined emotional state, means for providing the evaluated information to the guide, and means including an application installed on a mobile terminal that displays the evaluation results in real time. This allows operators to grasp the customer's emotions in real time and provide immediate feedback and make improvements.

[0646] "Voice information" refers to the audio data of conversations between customers and operators.

[0647] "Means of acquisition" refers to the device or process for collecting audio information in digital format and storing it on a server.

[0648] "Methods for converting to transcription" refers to the process of using speech recognition technology to convert audio information into text data.

[0649] "Means of analyzing transcripts to determine emotional states" refers to algorithms or devices that analyze text data to determine a customer's emotions and attitudes.

[0650] "Methods for evaluating customer satisfaction" refers to the process of quantifying or scoring customer satisfaction based on the determined emotional state.

[0651] "Means of providing information to the guide" refers to an interface or process for transmitting analysis results and feedback to the operator.

[0652] "Applications installed on mobile devices that display data in real time" refers to software installed on portable information terminals such as smartphones and tablets that instantly displays analysis results.

[0653] To implement this invention, the server first plays the role of acquiring audio information. The audio information is input from a device that collects customer-operator conversations in real time. Next, the server uses speech recognition technology to convert the audio information into a transcript. This process uses a speech recognition API such as "Google Cloud Speech-to-Text".

[0654] Next, using a generative AI model, the server analyzes the converted text data to determine the customer's emotional state. Specifically, it analyzes keywords and context within the text, and also takes into account auditory information such as tone and speed of voice. The evaluated customer satisfaction information is provided to the information desk staff in real time. This information is displayed on a specific application installed on a mobile device such as a smartphone or tablet, making it easier for the operator to adjust their response on the spot.

[0655] For example, if an operator receives feedback from a customer stating, "I'm unhappy with the wait," the server immediately analyzes this information and displays an alert on the operator's mobile device indicating that "the customer is likely dissatisfied." Based on this notification, the operator can then improve their customer service.

[0656] Furthermore, an example of a prompt sentence for the AI ​​model generated by this application is: "Predict the customer's emotional state from this sentence: 'The service is great, but the response is slow.'" By utilizing this prompt sentence, it becomes possible to analyze the customer's emotional state appropriately.

[0657] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0658] Step 1:

[0659] The server acquires voice information in real time during a call. This voice information consists of audio data spoken by the user via telephone, which is stored on the server in digital format. The input is voice information, and the output is the digital audio data stored on the server.

[0660] Step 2:

[0661] The server uses a speech recognition API to convert the acquired audio information into text data. This process uses "Google Cloud Speech-to-Text". The input is the digital audio data saved in step 1, and the output is text data.

[0662] Step 3:

[0663] The server analyzes the converted text data using a generative AI model. Specifically, it predicts the user's emotional state based on keywords and context contained in the text. At this time, the choice, frequency, and phrasing of words in the text are considered. The input is the text data generated in step 2, and the output is the determined emotional state.

[0664] Step 4:

[0665] The server evaluates and quantifies customer satisfaction based on the determined emotional state. At this stage, the emotional state is classified into positive, negative, neutral, etc., and summarized as a numerical score. The input is the emotional state obtained in step 3, and the output is the numerical score of customer satisfaction.

[0666] Step 5:

[0667] The server transmits the evaluated customer satisfaction information to the mobile device in real time. The application installed on the device then provides feedback to the operator. The input is the numerical customer satisfaction score obtained in step 4, and the output is the feedback information displayed on the device.

[0668] Step 6:

[0669] The operator adjusts their response to the customer based on real-time feedback information. Specifically, they respond quickly to feedback and take measures to improve service as needed. The input is the feedback information displayed on the terminal in step 5, and the output is the operator's adapted actions.

[0670] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0671] This invention relates to a system that combines an emotion engine, which recognizes user emotions from acquired voice data, in order to evaluate the work of telephone reception operators with greater accuracy and improve the quality of customer service.

[0672] When a user makes an inquiry or consultation by phone, the server collects voice data in real time. This voice data is converted into text data by the server's speech recognition engine. The converted text data is stored in a database and used for subsequent analysis.

[0673] The server then utilizes an emotion engine to recognize the user's emotions based on text data and information such as tone, pitch, and speed of voice. This process allows for a highly accurate determination of whether the user is experiencing positive, negative, or neutral emotions.

[0674] The results of emotion recognition are directly used to quantify customer satisfaction. Based on these results, the server evaluates operator performance and, if particularly strong negative emotions are expressed, determines that a complaint is likely and notifies the manager. This notification enables a quick response and helps resolve customer dissatisfaction early.

[0675] Furthermore, feedback is provided to operators in real time and can be used as a response guide that includes suggestions for improvement. For example, if a user says "I don't understand" or "I'm having trouble," the server will interpret this as a sign of dissatisfaction and provide the operator with specific ways to respond. In this way, the system supports operators in taking appropriate responses, ultimately aiming to improve customer satisfaction.

[0676] Through the system of this invention, the quality of operator responses can be precisely evaluated, enabling efficient and effective customer service. This leads to an overall improvement in the service level of telephone support.

[0677] The following describes the processing flow.

[0678] Step 1:

[0679] When a user contacts the customer service center by phone, the server acquires the audio data of the call in real time. The server connects to the phone system and makes the necessary preparations to begin audio streaming.

[0680] Step 2:

[0681] The server sends the acquired audio data to a speech recognition engine, which converts the audio into text data. This converted text data is stored in a database on the server for use in subsequent processes.

[0682] Step 3:

[0683] The server uses an emotion engine to analyze text and audio data. Specifically, it determines the user's emotions based on keywords in the text, tone of voice, speaking speed, and other factors. Based on this determination, the user's emotional state is classified as positive, negative, or neutral.

[0684] Step 4:

[0685] The server quantifies customer satisfaction based on the determined emotional state. This quantified data is directly linked to operator performance evaluation and used for further analysis.

[0686] Step 5:

[0687] The server identifies potentially problematic calls based on emotional state and quantified ratings. Identified calls immediately notify administrators, allowing for prompt action as needed.

[0688] Step 6:

[0689] The server provides operators with real-time feedback. This feedback includes what went well, areas for improvement, and even specific suggestions for improvement. This allows operators to use this feedback to provide better service in future calls.

[0690] This series of processes allows the server to analyze user emotions in detail, thereby improving the quality of service provided by telephone operators and increasing customer satisfaction.

[0691] (Example 2)

[0692] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0693] Conventional voice communication systems have the challenge of making it difficult to objectively evaluate the quality of operator responses based on actual customer emotions and satisfaction levels. Furthermore, they lacked the means to proactively identify potential complaints and address them quickly. As a result, improvements in customer satisfaction and the early resolution of complaints were not fully achieved.

[0694] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0695] In this invention, the server includes means for collecting acoustic information, means for converting acoustic information into text information, means for analyzing the characteristics of the text information and acoustic information to identify emotions, means for calculating an evaluation index based on the identified emotions, means for providing the calculated evaluation index to the communication operator, means for identifying communications that have the potential to generate dissatisfaction, and means for presenting measures to improve service to the communication operator. This enables precise evaluation of the operator's response quality based on customer emotions and satisfaction, allowing for the early detection of potential complaints and prompt response.

[0696] "Acoustic information" refers to data related to voice or sound, and in particular, to voice signals acquired from the user during communication.

[0697] "Textual information" refers to data in text format obtained by converting acoustic information using speech recognition technology.

[0698] "Analysis" refers to the process of evaluating the characteristics of acoustic and textual information to identify the user's emotions.

[0699] "Means of identifying emotions" refers to technical means that analyze a user's emotional state and classify it as positive, negative, or neutral.

[0700] "Evaluation metrics" refer to numerical values ​​that quantify customer satisfaction or operator service quality, calculated based on identified emotions.

[0701] "Communications personnel" refers to operators who handle acoustic information or individuals engaged in such work.

[0702] "Means for identifying communications that may generate dissatisfaction" refers to a function that uses analyzed sentiment information and evaluation metrics to identify communications that may potentially generate complaints.

[0703] "Means of providing solutions for improving customer service" refers to a systemic function that allows communications personnel to provide specific advice and instructions on how to improve their interactions with customers.

[0704] This invention provides a technology for improving the quality of operator responses in a voice communication system by analyzing the user's emotions. Specific embodiments for carrying out this invention are described below.

[0705] The server collects the user's acoustic information through a communication device. This acoustic information is converted into text information using software equipped with speech recognition technology. A common example of speech recognition software is a speech recognition engine.

[0706] The converted text information is stored in a database by the server. The server then uses an emotion analysis engine to analyze the characteristics of the text and audio information and identify the user's emotions. Natural language processing techniques and machine learning algorithms can be used as the emotion analysis engine.

[0707] The results of emotion identification are quantified as evaluation metrics and provided to the communications operator by the server. These metrics indicate operator performance and customer satisfaction. The server can also notify administrators of potentially dissatisfying communications based on the identified emotions. This feature facilitates a quicker response.

[0708] Furthermore, the server provides communication personnel with real-time suggestions for improving their responses. This allows operators to communicate effectively with customers and resolve problems quickly.

[0709] As a concrete example, consider a scenario where a user calls customer support and says, "I don't know how to use the product." The server collects this statement as acoustic information, converts it to text information, and then analyzes it. If the analysis determines that the user's statement suggests confusion or dissatisfaction, the server notifies the operator and instructs them to provide specific instructions on how to use the product. It is also conceivable to use a generative AI model to create prompts related to optimizing communication. An example of such a prompt might be, "Please describe a system that analyzes customer voice data, identifies emotions, and suggests appropriate responses to operators."

[0710] In this way, this invention enables communication systems to provide more effective and satisfying customer service.

[0711] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0712] Step 1:

[0713] When a user calls customer support, the server collects acoustic information in real time via a communication device. The input data is the user's voice, and this voice data is sent to the server.

[0714] Step 2:

[0715] The server uses a speech recognition engine to convert the collected acoustic information (audio data) into text information. This process extracts the content of the speech as a string of characters. The input is acoustic information, and the output is text information.

[0716] Step 3:

[0717] The converted text information is stored in the server's database. Simultaneously, the server sends the stored text information and acoustic information characteristics (tone, pitch, speed, etc.) to the emotion analysis engine. The input consists of text information and acoustic information characteristics, and emotion is analyzed based on these.

[0718] Step 4:

[0719] The server uses an emotion analysis engine to identify the user's emotion as positive, negative, or neutral. The emotion identification result is quantified as an evaluation metric and used for the next process. The input here is the result of the data analysis in the previous step, and the output is the metric value indicating the emotion.

[0720] Step 5:

[0721] The server determines the potential for a user complaint based on evaluation metrics obtained through sentiment analysis. If strong negative emotions are detected, it sends a notification to the communications officer and their manager. The input is identified sentiment information, and the output is a notification and response instructions.

[0722] Step 6:

[0723] The server provides communication personnel with real-time suggestions for improving their responses. These suggestions include specific advice and procedures to support the operators' current handling of calls. Inputs are evaluation metrics and identified sentiment information, while outputs are response guidelines.

[0724] Step 7:

[0725] The server evaluates the communication operator's performance based on the feedback. This evaluation is recorded to help improve future responses. Inputs are the communication results and feedback information, while outputs are the improved response methods and records.

[0726] This series of processes enables effective responses that are tailored to the user's emotions, leading to improved operator service quality and customer satisfaction.

[0727] (Application Example 2)

[0728] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0729] In telephone reception operations, operators are required to appropriately assess customer emotions and respond quickly to improve customer satisfaction. Providing real-time feedback and concrete improvement suggestions is a key challenge in this context.

[0730] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0731] In this invention, the server includes means for acquiring voice information, means for converting voice information into text information, means for analyzing the text information to determine the emotional state, and means for providing improvement recommendations to the operator in real time based on the emotional state. This enables the operator to understand the customer's emotions in real time and take appropriate action.

[0732] "Voice information" refers to the content of conversations with customers during telephone reception operations, and is data acquired through operations performed by operators.

[0733] "Textual information" refers to data obtained by converting audio information into text, and is a format used for subsequent data analysis.

[0734] "Emotional status" refers to the state of a customer's emotions, analyzed based on audio and textual information, and is an indicator that shows positive, negative, or neutral.

[0735] "Customer satisfaction" is a numerical indicator of customer satisfaction based on analyzed emotional states, and is used to evaluate the quality of services.

[0736] An "operator" is a person who is responsible for telephone reception and customer service, and is the entity that receives feedback from the system.

[0737] "Providing real-time improvement recommendations" means having a function that allows operators to immediately provide suggestions and instructions during customer calls, prompting them to take appropriate action.

[0738] The system that implements this application is designed to allow operators handling telephone reception duties to receive real-time feedback and improvement suggestions while interacting with customers. This system uses a smartphone as the terminal for acquiring voice information. The smartphone acquires the customer's call content as voice information in real time.

[0739] The acquired audio information is converted into text information using a speech recognition engine on the server. For example, Google Cloud Speech-to-Text is used as this speech recognition engine. The converted text information is further analyzed by an emotion engine on the server. For example, IBM Watson Tone Analyzer is used as this emotion engine. The emotion engine analyzes the text information and determines the customer's emotional state based on the audio characteristic data.

[0740] The determined emotional state is quantified by the server and statistically processed as user satisfaction. This information is sent back to the operator via a dedicated application, allowing the operator to receive real-time recommendations for improving customer service. For example, if a customer expresses dissatisfaction, the application will provide the operator with specific countermeasures.

[0741] For example, if a customer says they are "concerned about the content of their inquiry," the operator will receive advice such as, "The customer is feeling anxious. Please calmly explain the situation and promise to take prompt action if necessary." In this way, the operator can ensure that they take appropriate action.

[0742] An example of a prompt might be: "Perform a sentiment analysis on the customer's statements and provide necessary improvement advice. Audio data: 'Customer statements audio data'."

[0743] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0744] Step 1:

[0745] A smartphone acquires audio information during a call with a customer. The input is the audio of the conversation with the customer, and the output is digitized audio data. The audio data is collected via the microphone and temporarily stored in a database.

[0746] Step 2:

[0747] The server uses a speech recognition engine to convert the acquired speech information into text information. The input is speech data, and the output is converted text data. This process uses technologies such as Google Cloud Speech-to-Text to analyze the speech data and convert it to text.

[0748] Step 3:

[0749] The server analyzes text data and speech characteristic data (tone, pitch, speed, etc.) using an emotion engine to determine the emotional state. The input is text information and speech characteristic data, and the output is an emotional state indicating either positive, negative, or neutral. Emotion analysis is performed using tools such as IBM Watson Tone Analyzer.

[0750] Step 4:

[0751] The server quantifies the emotional state it determines and generates a user satisfaction index. The input is the emotional state, and the output is quantified satisfaction data. This index is statistically processed using a mathematical algorithm.

[0752] Step 5:

[0753] Based on quantified user satisfaction data, real-time feedback is provided to operators through a dedicated application. The input is satisfaction data, and the output is improvement recommendations and specific countermeasures. For example, a message such as, "The customer is feeling uneasy. Please explain calmly," might be provided.

[0754] Step 6:

[0755] The operator utilizes a generative AI model based on the prompt text to formulate further countermeasures. The input consists of feedback and the prompt text from the generative AI model, and the output is a customized response suggestion. For example, the prompt "Perform sentiment analysis on the customer's statement and provide necessary improvement advice" can be entered to receive suggestions from the model.

[0756] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0757] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0758] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0759] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0760] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0761] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0762] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0763] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0764] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0765] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0766] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0767] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0768] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0769] 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.

[0770] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0771] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0772] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0773] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0774] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0775] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0776] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0777] The following is further disclosed regarding the embodiments described above.

[0778] (Claim 1)

[0779] Means for acquiring audio data,

[0780] A means of converting audio data to text data,

[0781] A method for analyzing text data to determine emotional state,

[0782] A means of quantifying customer satisfaction based on the determined emotional state,

[0783] A means of providing quantified information as feedback to the operator,

[0784] A system that includes this.

[0785] (Claim 2)

[0786] The system according to claim 1, comprising means for identifying a call that may be a claim based on the determined emotional state and evaluation index.

[0787] (Claim 3)

[0788] The system according to claim 1, comprising means for presenting improvement suggestions to the operator based on feedback.

[0789] "Example 1"

[0790] (Claim 1)

[0791] Means for acquiring audio information,

[0792] A means of converting audio information into text information,

[0793] A means of analyzing textual information to determine emotional state,

[0794] A means of quantifying user satisfaction based on the determined emotional state,

[0795] A means of returning quantified information to the person in charge of the business,

[0796] A means of evaluating the work content of the person in charge by comparing it with past call information,

[0797] A method for identifying calls as complaints based on the frequency of negative keywords,

[0798] A system that includes this.

[0799] (Claim 2)

[0800] The system according to claim 1, comprising means for identifying potentially abnormal calls based on the determined emotional state and evaluation index.

[0801] (Claim 3)

[0802] The system according to claim 1, comprising means for presenting improvement suggestions to the person in charge of operations based on feedback.

[0803] "Application Example 1"

[0804] (Claim 1)

[0805] Means for acquiring audio information,

[0806] A method for converting audio information into a transcript,

[0807] A method for analyzing transcripts to determine emotional states,

[0808] A means of evaluating customer satisfaction based on the determined emotional state,

[0809] A means of providing the evaluated information to the guide,

[0810] A means including an application installed on a mobile device that displays evaluation results in real time,

[0811] A system that includes this.

[0812] (Claim 2)

[0813] The system according to claim 1, comprising means for identifying a call that may be a complaint based on the determined emotional state and evaluation index.

[0814] (Claim 3)

[0815] The system according to claim 1, comprising means for presenting improvement suggestions to the guide based on the information provided.

[0816] "Example 2 of combining an emotion engine"

[0817] (Claim 1)

[0818] Means for collecting acoustic information,

[0819] A means of converting acoustic information into textual information,

[0820] A means for identifying emotions by analyzing the characteristics of textual and auditory information,

[0821] A means for calculating an evaluation index based on identified emotions,

[0822] A means of providing the calculated evaluation indicators to the communications officer,

[0823] A system that includes this.

[0824] (Claim 2)

[0825] The system according to claim 1, comprising means for identifying communications that have the potential to generate dissatisfaction based on identified emotions and evaluation criteria.

[0826] (Claim 3)

[0827] The system according to claim 1, comprising means for presenting the communications officer with measures to improve the response based on the information provided.

[0828] "Application example 2 when combining with an emotional engine"

[0829] (Claim 1)

[0830] Means for acquiring audio information,

[0831] A means of converting audio information into text information,

[0832] A means of analyzing textual information to determine emotional state,

[0833] A means of quantifying user satisfaction based on the determined emotional state,

[0834] A means of returning quantified information to the operator,

[0835] A means of providing operators with real-time improvement recommendations based on their emotional state,

[0836] A system that includes this.

[0837] (Claim 2)

[0838] The system according to claim 1, comprising means for identifying potentially problematic communications based on determined emotional states and evaluation criteria.

[0839] (Claim 3)

[0840] The system according to claim 1, comprising means for presenting improvement recommendations to the operator based on the return. [Explanation of Symbols]

[0841] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means for acquiring audio data, A means of converting audio data to text data, A method for analyzing text data to determine emotional state, A means of quantifying customer satisfaction based on the determined emotional state, A means of providing quantified information as feedback to the operator, A system that includes this.

2. The system according to claim 1, comprising means for identifying a call that may be a claim based on the determined emotional state and evaluation index.

3. The system according to claim 1, further comprising means for presenting improvement suggestions to the operator based on feedback.

Images