system

Abstract

We provide the system. [Solution] A means for automatically accumulating historical information obtained from a call processing device, A means for predicting workload using a specific analytical model based on the aforementioned historical information, A means for generating and outputting the predicted workload results in a visible format, The means of providing the aforementioned visible information to the user, 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, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a call center, there is a problem that it is difficult for newly recruited employees or transferred employees to quickly grasp the current work load and issues. Also, it is difficult to derive effective work improvement measures based on past achievements in a form that can be shared by all staff. As a result, work efficiency decreases, and there is a risk of delays in customer response and degradation of quality.

Means for Solving the Problems

[0005] This invention solves this problem by providing a system that automatically collects historical information from call processing equipment and predicts workload using a specific analysis model. By generating the predicted workload in a visual format and presenting this information concisely to the user, it makes it easier to understand the situation. This makes it easier for new employees and transferred employees in particular to quickly understand the current situation and take appropriate work improvement measures.

[0006] A "call processing system" is a general term for the equipment and software used in call centers to receive, answer, and manage calls.

[0007] "Historical information" refers to past data related to operations at the call center, and specifically includes information such as the number of calls, response rate, and response time.

[0008] "Accumulation" refers to the act of gathering multiple data points in one place, organizing them, and storing them.

[0009] An "analytical model" refers to algorithms and methods used to analyze past data, extract useful information, and make future predictions or analyze trends.

[0010] "Workload" refers to the amount of work and resource consumption required in a call center within a specific period.

[0011] "Visual format" means representing data and information in a way that is easy to understand visually, such as using graphs or charts.

[0012] "User" refers to individuals or organizations that use the system or its functions, and in this context, specifically the call center staff. [Brief explanation of the drawing]

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

Embodiments for Carrying Out the Invention

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

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

[0016] 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.

[0017] 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.

[0018] 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.

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

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

[0021] [First Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0034] This invention is a support system aimed at improving operational efficiency in call centers. This system consists of a server, terminals, and users, and automates the monitoring of call center operational status and the generation of reports.

[0035] The server first periodically collects historical data from the call center. This includes call volume, response rate, utilization rate, and CPH (Calls Per Hour). Next, the server analyzes this data using a specific analytical model to predict workload. This analysis highlights key foundational information for new employees and those transferring to other departments.

[0036] The analysis results are generated by the server in a visible format, such as a dashboard or a PDF report. This report includes specific advice that can contribute to business improvement, as well as predicted increases in the number of incoming calls.

[0037] The terminal receives reports generated by the server and provides them to call center users. By referring to these reports, users can quickly grasp the current state of operations and concerns, and easily take appropriate countermeasures.

[0038] For example, it becomes possible to prepare in advance to cope with a sudden surge in incoming calls from users (new employees), and to develop appropriate action plans in consultation with supervisors based on predictions from the server. This is expected to improve the quality of customer service at the call center and enhance overall operational efficiency.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] The server automatically collects historical performance data from various call processing units in the call center. This data includes the number of incoming calls, response rate, utilization rate, and CPH (Call Processing Frequency), and is obtained via APIs and log files.

[0042] Step 2:

[0043] The server performs necessary preprocessing before analyzing the collected data. This includes imputing missing values, removing outliers, and standardizing the data format. This improves the accuracy of the analysis and enables reliable predictions.

[0044] Step 3:

[0045] The server runs a specific analysis model using pre-processed data. This model predicts workload and detects potential issues based on historical data. The analysis results predict fluctuations in the next call volume and response rate, and these trends are reflected in the report.

[0046] Step 4:

[0047] The server generates analysis results in a report that is easy to understand visually. Specifically, it publishes workload predictions and improvement suggestions in graph and chart format. This report can also be output in PDF or dashboard format.

[0048] Step 5:

[0049] The terminal displays reports received from the server to call center users. Customized information tailored to each employee's role is also provided, allowing new employees and those transferred to other departments to quickly understand their work situation.

[0050] Step 6:

[0051] Users review their work processes based on the report's content and identify necessary improvements. By observing the effectiveness of the implemented improvements and sending feedback to the server, they contribute to further improving system accuracy.

[0052] (Example 1)

[0053] 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."

[0054] In call centers, improving operational efficiency and optimizing workload are crucial challenges, but traditional methods have made it difficult to achieve this quickly and accurately. Furthermore, complex data analysis is challenging without specialized technical skills, often resulting in an inability to obtain the necessary information for business improvement. This leads to delays in response, inappropriate resource allocation, and a decline in overall operational efficiency.

[0055] 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.

[0056] In this invention, the server includes means for automatically formatting past business information collected from a communication processing device, means for analyzing workload using a machine learning model based on the formatted business information, and means for generating and providing the results of the workload analysis in a visualized format. This makes it possible to quickly grasp the current state of operations and analyze future workload using a predictive model. In addition, by utilizing the visualized information, even users without specialized knowledge can intuitively understand the information and take effective business improvement measures.

[0057] A "communication processing device" is a device used in a call center to manage calls and data communications and to collect historical information.

[0058] "Business information" refers to all operational data related to the call center, such as the number of calls, response rate, and utilization rate.

[0059] "Automatic formatting" refers to the process of processing collected data into a format suitable for analysis, such as removing noise or imputing missing values.

[0060] A "machine learning model" refers to an algorithm or method that is trained on past data and used to analyze patterns and make predictions from new data.

[0061] "Workload" refers to the volume of inquiries and calls handled by a call center over a certain period, and is an indicator used as a basis for determining the necessary resources for operation.

[0062] "Analysis results" refer to conclusions and trends derived from data obtained using machine learning models.

[0063] A "visualized format" refers to a visual representation of analyzed data in the form of graphs, charts, dashboards, etc., converted into a format that is easy for users to understand intuitively.

[0064] This invention is a system for improving operational efficiency in call centers, and mainly consists of a server, terminals, and users.

[0065] The server first collects historical business information through a communication processing unit. This information includes metrics such as the number of calls, response rate, and uptime. The server then performs data preprocessing to properly format this data. In this process, libraries such as Python's Pandas and NumPy are used to automatically perform noise reduction and imputation of missing values.

[0066] Next, the server uses the formatted business information to perform analysis using machine learning models. The analysis utilizes models such as ARIMA and LSTM for time-series analysis. This allows for the prediction of workload and the generation of information useful for future operational resource management.

[0067] The server then uses the analysis results to create a visualized report. Visualization tools such as Power BI and Tableau are used to create this report, transforming the information into an intuitively understandable format using graphs and charts.

[0068] The terminal receives visualization reports sent from the server and provides them to call center users. A dedicated application is installed on the terminal, through which users access the information.

[0069] Users use their devices to review received data and understand the current state of their work and anticipated challenges. Furthermore, they utilize a generative AI model to input prompts such as, "How should we respond to the expected increase in incoming calls due to next month's new promotion?" Based on the information obtained from the generative AI model, they can consult with their supervisors to develop effective action plans, thereby improving their work processes.

[0070] In this way, each component of this system works in conjunction to efficiently execute a series of processes, from data collection and analysis to the proposal of improvement measures. Based on the information obtained, users can make accurate decisions and plans, thereby improving the overall operational efficiency of the call center.

[0071] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0072] Step 1:

[0073] The server collects historical call center data through a communication processing unit. Specifically, it retrieves data including the number of calls, response rate, and utilization rate. This raw data is the input. To properly format this data, the server retrieves it from a database via an API and prepares it for subsequent processing.

[0074] Step 2:

[0075] The server preprocesses the collected data. The input is the raw, unprocessed data obtained in step 1. In this process, the server uses the Python Pandas library to remove noise from the data and impute missing values. The output is a clean dataset suitable for analysis. This provides high-quality data for the model to function properly.

[0076] Step 3:

[0077] The server analyzes the preprocessed data using a machine learning model. The input is the preprocessed data that is the output of step 2. In this step, the server applies ARIMA or LSTM models for time series analysis to predict workload. This outputs predictive data regarding future workload conditions.

[0078] Step 4:

[0079] The server creates a visualized report based on the analysis results. The input is the analysis results from step 3. The server uses Power BI or Tableau to convert the obtained data into graphs and charts and generate a dashboard-style report. The output is a visualized report that is intuitively understandable to the user.

[0080] Step 5:

[0081] The terminal receives a visualized report sent from the server. The input is the report generated in step 4. The terminal displays the report through a dedicated application and prepares it for the user. Specifically, it retrieves the report over the network and makes it available for viewing in the local environment.

[0082] Step 6:

[0083] Users refer to reports provided through their terminals to understand the current state of operations and anticipated challenges. Based on this information, users input prompts into the generating AI model, such as, "How should we respond to the expected increase in incoming calls due to next month's new promotion?" As output, the generating AI model presents specific recommended actions, helping users develop actionable plans. As a result, improved operational efficiency in the call center is expected.

[0084] (Application Example 1)

[0085] 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."

[0086] In conventional security systems, necessary information was often not provided in real time in situations requiring rapid response on-site. As a result, problems arose such as delays and inaccuracies in emergency responses. Therefore, there is a need for means to enable effective collection of recorded information, improvement of work efficiency through predictive models, and immediate provision of information in security systems.

[0087] 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.

[0088] In this invention, the server includes means for automatically accumulating recorded information acquired from a detection device, means for predicting the workload using a specific analysis model based on the recorded information, and means for generating and outputting the predicted workload in a visual format. This enables on-site security staff to receive important information in real time and respond quickly and accurately.

[0089] "Detection device" refers to all hardware used to acquire security information and recorded information, including cameras and sensors.

[0090] "Recorded information" refers to data and logs related to security events, which are used for anomaly detection and workload prediction.

[0091] An "analysis model" is a model constructed using machine learning algorithms and data analysis techniques, and is used to perform predictions and anomaly detection based on recorded information.

[0092] "Workload" refers to the amount of work that security staff face, and this load can be predicted and managed by acquiring and analyzing information.

[0093] A "visual format" refers to a format that displays data and analysis results in an intuitively easy-to-understand way, such as graphs and dashboards.

[0094] "Notifications" are a means of communication that delivers important information and alerts to security staff in real time, enabling a swift response.

[0095] To implement this invention, the following hardware and software are used.

[0096] The server first collects recorded information from detection devices. These detection devices include cameras and sensors. This recorded information includes security event data and logs, which are then used as input for an analysis model that predicts workload. The analysis model uses a machine learning framework such as TENSORFLOW®. This model is used to process the data and discover anomaly patterns and make predictions.

[0097] The analysis results are generated in a visual format. This involves creating dashboards using data visualization tools such as Tableau and communicating the visualized information to security staff. Users can receive this visualized data in real time through visual devices such as smart glasses.

[0098] As a concrete example, security staff at a large-scale event venue can use smart glasses to monitor crowd conditions and any anomalies in real time. The staff can then utilize the visual information transmitted from the server to take swift and accurate countermeasures.

[0099] For example, a prompt message for a generative AI model might be, "Build a machine learning model to monitor the security situation at this event venue in real time and detect any anomalies." This would improve safety at the site.

[0100] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0101] Step 1:

[0102] The server collects recorded information from detection devices. The input is raw data provided by cameras and sensors. This data is converted into a log format and stored in an appropriate database to prepare for subsequent analysis.

[0103] Step 2:

[0104] The server inputs the collected record information into an analysis model. This record information includes metadata such as the type, time, and location of events. Here, a machine learning model is executed using TensorFlow to detect anomalies and predict workload. The output is data on anomaly patterns and estimated congestion and risk states.

[0105] Step 3:

[0106] The server processes the analysis results into a visual format. The input consists of anomaly patterns and predicted data obtained through the analysis. This information is then converted into dashboards and graphs using Tableau, making it easily visible. This visual information is then generated in a format usable by security staff.

[0107] Step 4:

[0108] The terminal receives visual information transmitted from the server and notifies the user. The input is visual data transmitted from the server. The terminal displays this in real time on smart glasses, helping the user understand the situation. The output is visual information that the user can immediately confirm.

[0109] Step 5:

[0110] Users access visual information through smart glasses and take swift action. The input is visual data provided by the device. Based on this information, users determine the necessary response on-site and take appropriate action. The output is the improved response behavior.

[0111] 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.

[0112] This invention is a system designed to improve the efficiency and quality of operations in call centers, and in particular aims to further enhance the quality of customer service by incorporating emotion recognition functionality. This system combines a server, terminal, user, and emotion engine, and provides information that contributes to business improvement through the analysis of call history and the recognition of emotional states.

[0113] The server first automatically collects call center history data from the call processing unit. This includes past call content, number of incoming calls, answer rate, utilization rate, and voice data from calls. Based on this history information and voice data, the server uses a specific analytical model to predict workload and customer emotional state. In particular, the emotion engine analyzes voice patterns to identify customer emotions, such as satisfaction, dissatisfaction, and tension. This identified information provides guidance for improving user service.

[0114] The server generates a report of predicted workload and emotional state in a visual and emotionally conscious format, and provides it to the user via a terminal. By referring to this report, users can understand the status of customer service and devise appropriate improvement measures. For example, if a customer expresses dissatisfaction during a call, this information is quickly shared with the user, and the server can automatically propose specific actions to resolve the problem. In this way, it can contribute to information sharing and improvement of customer service within the call center.

[0115] For example, if the emotion engine determines that a customer the user is currently on a call with is expressing dissatisfaction, the server will notify the user of this information via the terminal, assisting the user in taking appropriate action quickly. This can improve the quality of service and enhance customer satisfaction.

[0116] The following describes the processing flow.

[0117] Step 1:

[0118] The server automatically collects past call history information and voice data from the call processing unit. This information includes call duration, call content, number of incoming calls, handling record, and voice tone.

[0119] Step 2:

[0120] The server performs preprocessing on the collected data for analysis. Specifically, it cleans audio data, standardizes text data formats, and removes noise. This improves analysis accuracy and yields more reliable results.

[0121] Step 3:

[0122] The server runs the emotion engine using pre-processed data. The emotion engine analyzes the user's emotional state from the voice data and identifies emotions such as satisfaction, dissatisfaction, and tension. These emotions are categorized and integrated with predictions about workload by the analysis model.

[0123] Step 4:

[0124] The server generates reports in an easy-to-understand format for users, based on sentiment analysis results and workload predictions. These reports include a summary of emotional states, visualizations of times when customer dissatisfaction is high, and suggestions for specific countermeasures.

[0125] Step 5:

[0126] The terminal delivers the generated reports to the user. During this process, it provides real-time notifications to help the user quickly adjust customer responses.

[0127] Step 6:

[0128] Users improve their communication with customers based on reports provided by their devices. In particular, they consult with their supervisors and colleagues about specific response methods based on the results of the emotional state assessment. This improves the quality of customer service and increases operational efficiency.

[0129] (Example 2)

[0130] 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".

[0131] Call center operations require both improving the quality of customer service and accurately predicting workload. However, traditional systems have struggled to accurately grasp customers' emotional states and take prompt action based on that understanding. This can lead to decreased customer satisfaction and reduced operational efficiency.

[0132] 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.

[0133] In this invention, the server includes means for automatically accumulating historical information acquired from a communication device, means for identifying emotions using a generated AI model based on the historical information and voice data, and means for generating and outputting the emotion identification and workload prediction results in a visible format. This makes it possible to grasp the emotional state of customers in real time and take quick and appropriate countermeasures based on that.

[0134] A "communication device" is a device that manages calls in a call center and has the function of generating, storing, and providing call records and related data.

[0135] "Historical information" refers to record data related to past communications, including call content, number of incoming calls, response rate, and operational rate.

[0136] A "generative AI model" is a model that uses machine learning techniques to learn specific patterns from input data and make predictions about emotions, workload, and other factors.

[0137] "Means of identifying emotions" refers to a technological process that analyzes voice data to identify the emotional state of a customer.

[0138] "Workload prediction results" refer to predicted values ​​that numerically or graphically represent the future workload based on collected historical information.

[0139] "Visual format" refers to a format in which analysis results and predictions are presented in a visually easy-to-understand way, such as in dashboards or reports.

[0140] This invention is a system aimed at improving the efficiency of call center operations and enhancing the quality of customer service. To implement this system, the server, terminals, and users must work together in coordination.

[0141] First, the server automatically collects historical information from the communication device. This historical information includes past call content, response rates, uptime, and voice data from calls. This data is managed using a database management system (e.g., MySQL® or PostgreSQL).

[0142] Next, the server uses a generative AI model to identify emotions based on the collected historical information and voice data. Emotion identification utilizes machine learning frameworks (e.g., TensorFlow and PyTorch) and analyzes voice patterns using neural networks. This makes it possible to classify the customer's emotional state into categories such as satisfaction, dissatisfaction, and tension.

[0143] The sentiment identification results and workload prediction results are generated by the server as a visual report. This report is designed to be displayed in graph and dashboard format using data visualization tools (e.g., Tableau or Power BI).

[0144] This allows users to receive visual reports through their devices and use them to make decisions about improving customer service. By using this information to quickly take action, users can improve customer satisfaction.

[0145] As a concrete example, if the server uses its emotion engine to detect customer dissatisfaction during a call, it transmits that information to the terminal in real time and notifies the user. Upon receiving this notification, the user can prepare to respond quickly. For example, by using prompts such as, "Please provide the analysis results for the call where the customer is expressing dissatisfaction," it becomes possible to consider further improvements.

[0146] Thus, the present invention contributes to improving the quality of customer service and increasing the operational efficiency of call centers.

[0147] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0148] Step 1:

[0149] The server collects historical information from communication devices. Inputs include call content, number of incoming calls, response rate, uptime, and voice data. This data is stored in a database. Specifically, the server uses a database management system to access the database and retrieves the necessary data by issuing SQL queries.

[0150] Step 2:

[0151] The server inputs historical information and audio data into a generating AI model to identify emotions. The input is waveform information from the audio data, and the output is the customer's emotional state (e.g., satisfied, dissatisfied, tense). Here, a machine learning library is used to analyze the audio data, and a neural network is used to detect emotional patterns.

[0152] Step 3:

[0153] The server predicts workload based on historical information. It uses historical data such as past utilization rates and response rates as input, and generates predicted values ​​for future workload as output. Specifically, it implements an algorithm for regression analysis and makes predictions by analyzing data trends.

[0154] Step 4:

[0155] The server integrates emotion identification results and workload prediction results to generate a visual report. Emotional states and predicted values ​​are used as input, and a visual dashboard-style report is created as output. This includes specific actions such as creating graphs and charts using data visualization tools.

[0156] Step 5:

[0157] The terminal notifies the user of reports from the server. Based on the report information received as input, it displays the report content on the screen as output. Specifically, the user interface provides pop-up notifications and links to detailed dashboards, allowing the user to access the information immediately.

[0158] Step 6:

[0159] Users refer to reports received via their devices and consider ways to improve customer service. The output is a development of an action plan for improvement. Specific actions involved include analyzing the data in the provided report and prompting the server for necessary countermeasures.

[0160] (Application Example 2)

[0161] 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".

[0162] Balancing the quality of customer service and operational efficiency in call centers is an extremely difficult challenge. In particular, accurately recognizing customers' emotional states and responding promptly is crucial for improving customer satisfaction. However, current systems cannot utilize the context or emotional state of call content, making it difficult to predict workload and accurately assess customer emotions. Therefore, there is a need for a new system that integrates more advanced emotion recognition and workload prediction.

[0163] 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.

[0164] In this invention, the server includes means for automatically accumulating historical data acquired from a call processing unit, means for recognizing the emotional state of a user by analyzing voice information, and means for generating and outputting the predicted workload and emotional state in a visible format. This makes it possible to grasp the customer's emotional state in real time and visualize it together with the workload.

[0165] "Historical data" refers to the collection of information obtained from call processing equipment, such as past call content, inquiry volume, and response rate.

[0166] "Analysis method" refers to specific algorithms and statistical techniques used to predict workload and analyze inquiry trends based on historical data and voice information.

[0167] "Emotion recognition means" refers to devices and technologies that identify the emotional state of customers or users by analyzing voice patterns during a phone call.

[0168] "Workload" refers to the quantity and quality of tasks that a call center must handle, as well as the associated personnel and time requirements.

[0169] "Visual format" refers to a data format that visually represents the analysis results in a way that is easy for humans to understand.

[0170] "Security-related anomalies" refer to suspicious behavior or statements that deviate from normal business operations, detected from the customer's emotional state or the content of their calls.

[0171] "Recommendations for business improvement" refer to specific action plans recommended based on actual data to improve business efficiency and the quality of customer service.

[0172] To implement this invention, the server, terminal, and user each play specific roles in the call center system. The server automatically collects historical data from the call processing unit. This historical data includes information such as past call content, inquiry volume, and response rate. The server uses this data to perform analysis to predict the workload. The server is also equipped with emotion recognition means to analyze voice information and recognize the customer's emotional state. The emotion recognition means uses an AI model to analyze voice patterns and identify different emotional states such as customer satisfaction, dissatisfaction, and tension.

[0173] The server generates predicted workload and emotional states in a visual format and outputs them as a report. This visual information is provided to the user via a terminal. Based on the information displayed on the terminal, the user can quickly take appropriate actions to improve customer service.

[0174] For example, if the emotion engine detects a customer's anxiety during a call, the server immediately notifies the terminal of this information. This information is based, for instance, on the results of an analysis of voice data suggesting that the user is feeling anxious. By referring to this information, the user can provide appropriate follow-up to the customer.

[0175] When using a generative AI model to analyze emotional states, the following prompt can be used: "Please suggest a course of action if anger or fear is detected during a customer call."

[0176] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0177] Step 1:

[0178] The server automatically retrieves historical data from the call processing unit. Inputs include past call content, inquiry volume, and response rate. By aggregating this data, a historical database is generated.

[0179] Step 2:

[0180] The server uses historical data to perform analysis and predict workload. The input is historical data, and the data analysis algorithm calculates query volume trends and peak workload, outputting this as predicted data.

[0181] Step 3:

[0182] The server acquires audio data during a call and analyzes the customer's emotional state using emotion recognition technology. The input is real-time audio data, and by analyzing the audio patterns with a generating AI model, it identifies the customer's emotional state (e.g., satisfaction, dissatisfaction, tension, etc.) and outputs the result as emotion data.

[0183] Step 4:

[0184] The server generates information in a visual format and creates reports based on predictive and sentiment data. It takes predictive and sentiment data as input, integrates this data into graphs and charts, and outputs it as easy-to-understand report data.

[0185] Step 5:

[0186] The terminal provides the user with report data received from the server. The input is report data, which is displayed on the user interface and provided as reference information for the user to make decisions regarding improvements to customer service.

[0187] Step 6:

[0188] Based on the reports displayed on their devices, users decide on specific actions to improve customer service. In this step, users determine what actions they should take based on the reports and then reflect those decisions in their actual interactions with customers.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] [Second Embodiment]

[0193] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0194] 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.

[0195] 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).

[0196] 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.

[0197] 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.

[0198] 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).

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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".

[0205] This invention is a support system aimed at improving operational efficiency in call centers. This system consists of a server, terminals, and users, and automates the monitoring of call center operational status and the generation of reports.

[0206] The server first periodically collects historical data from the call center. This includes call volume, response rate, utilization rate, and CPH (Calls Per Hour). Next, the server analyzes this data using a specific analytical model to predict workload. This analysis highlights key foundational information for new employees and those transferring to other departments.

[0207] The analysis results are generated by the server in a visible format, such as a dashboard or a PDF report. This report includes specific advice that can contribute to business improvement, as well as predicted increases in the number of incoming calls.

[0208] The terminal receives reports generated by the server and provides them to call center users. By referring to these reports, users can quickly grasp the current state of operations and concerns, and easily take appropriate countermeasures.

[0209] For example, it becomes possible to prepare in advance to cope with a sudden surge in incoming calls from users (new employees), and to develop appropriate action plans in consultation with supervisors based on predictions from the server. This is expected to improve the quality of customer service at the call center and enhance overall operational efficiency.

[0210] The following describes the processing flow.

[0211] Step 1:

[0212] The server automatically collects historical performance data from various call processing units in the call center. This data includes the number of incoming calls, response rate, utilization rate, and CPH (Call Processing Frequency), and is obtained via APIs and log files.

[0213] Step 2:

[0214] The server performs necessary preprocessing before analyzing the collected data. This includes imputing missing values, removing outliers, and standardizing the data format. This improves the accuracy of the analysis and enables reliable predictions.

[0215] Step 3:

[0216] The server runs a specific analysis model using pre-processed data. This model predicts workload and detects potential issues based on historical data. The analysis results predict fluctuations in the next call volume and response rate, and these trends are reflected in the report.

[0217] Step 4:

[0218] The server generates analysis results in a report that is easy to understand visually. Specifically, it publishes workload predictions and improvement suggestions in graph and chart format. This report can also be output in PDF or dashboard format.

[0219] Step 5:

[0220] The terminal displays reports received from the server to call center users. Customized information tailored to each employee's role is also provided, allowing new employees and those transferred to other departments to quickly understand their work situation.

[0221] Step 6:

[0222] Users review their work processes based on the report's content and identify necessary improvements. By observing the effectiveness of the implemented improvements and sending feedback to the server, they contribute to further improving system accuracy.

[0223] (Example 1)

[0224] 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."

[0225] In call centers, improving operational efficiency and optimizing workload are crucial challenges, but traditional methods have made it difficult to achieve this quickly and accurately. Furthermore, complex data analysis is challenging without specialized technical skills, often resulting in an inability to obtain the necessary information for business improvement. This leads to delays in response, inappropriate resource allocation, and a decline in overall operational efficiency.

[0226] 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.

[0227] In this invention, the server includes means for automatically formatting past business information collected from a communication processing device, means for analyzing workload using a machine learning model based on the formatted business information, and means for generating and providing the results of the workload analysis in a visualized format. This makes it possible to quickly grasp the current state of operations and analyze future workload using a predictive model. In addition, by utilizing the visualized information, even users without specialized knowledge can intuitively understand the information and take effective business improvement measures.

[0228] A "communication processing device" is a device used in a call center to manage calls and data communications and to collect historical information.

[0229] "Business information" refers to all operational data related to the call center, such as the number of calls, response rate, and utilization rate.

[0230] "Automatic formatting" refers to the process of processing collected data into a format suitable for analysis, such as removing noise or imputing missing values.

[0231] A "machine learning model" refers to an algorithm or method that is trained on past data and used to analyze patterns and make predictions from new data.

[0232] "Workload" refers to the volume of inquiries and calls handled by a call center over a certain period, and is an indicator used as a basis for determining the necessary resources for operation.

[0233] "Analysis results" refer to conclusions and trends derived from data obtained using machine learning models.

[0234] A "visualized format" refers to a visual representation of analyzed data in the form of graphs, charts, dashboards, etc., converted into a format that is easy for users to understand intuitively.

[0235] This invention is a system for improving operational efficiency in call centers, and mainly consists of a server, terminals, and users.

[0236] The server first collects historical business information through a communication processing unit. This information includes metrics such as the number of calls, response rate, and uptime. The server then performs data preprocessing to properly format this data. In this process, libraries such as Python's Pandas and NumPy are used to automatically perform noise reduction and imputation of missing values.

[0237] Next, the server uses the formatted business information to perform analysis using machine learning models. The analysis utilizes models such as ARIMA and LSTM for time-series analysis. This allows for the prediction of workload and the generation of information useful for future operational resource management.

[0238] The server then uses the analysis results to create a visualized report. Visualization tools such as Power BI and Tableau are used to create this report, transforming the information into an intuitively understandable format using graphs and charts.

[0239] The terminal receives visualization reports sent from the server and provides them to call center users. A dedicated application is installed on the terminal, through which users access the information.

[0240] Users use their devices to review received data and understand the current state of their work and anticipated challenges. Furthermore, they utilize a generative AI model to input prompts such as, "How should we respond to the expected increase in incoming calls due to next month's new promotion?" Based on the information obtained from the generative AI model, they can consult with their supervisors to develop effective action plans, thereby improving their work processes.

[0241] In this way, each component of this system works in conjunction to efficiently execute a series of processes, from data collection and analysis to the proposal of improvement measures. Based on the information obtained, users can make accurate decisions and plans, thereby improving the overall operational efficiency of the call center.

[0242] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0243] Step 1:

[0244] The server collects historical call center data through a communication processing unit. Specifically, it retrieves data including the number of calls, response rate, and utilization rate. This raw data is the input. To properly format this data, the server retrieves it from a database via an API and prepares it for subsequent processing.

[0245] Step 2:

[0246] The server preprocesses the collected data. The input is the raw, unprocessed data obtained in step 1. In this process, the server uses the Python Pandas library to remove noise from the data and impute missing values. The output is a clean dataset suitable for analysis. This provides high-quality data for the model to function properly.

[0247] Step 3:

[0248] The server analyzes the preprocessed data using a machine learning model. The input is the preprocessed data that is the output of step 2. In this step, the server applies ARIMA or LSTM models for time series analysis to predict workload. This outputs predictive data regarding future workload conditions.

[0249] Step 4:

[0250] The server creates a visualized report based on the analysis results. The input is the analysis results from step 3. The server uses Power BI or Tableau to convert the obtained data into graphs and charts and generate a dashboard-style report. The output is a visualized report that is intuitively understandable to the user.

[0251] Step 5:

[0252] The terminal receives a visualized report sent from the server. The input is the report generated in step 4. The terminal displays the report through a dedicated application and prepares it for the user. Specifically, it retrieves the report over the network and makes it available for viewing in the local environment.

[0253] Step 6:

[0254] Users refer to reports provided through their terminals to understand the current state of operations and anticipated challenges. Based on this information, users input prompts into the generating AI model, such as, "How should we respond to the expected increase in incoming calls due to next month's new promotion?" As output, the generating AI model presents specific recommended actions, helping users develop actionable plans. As a result, improved operational efficiency in the call center is expected.

[0255] (Application Example 1)

[0256] 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."

[0257] In conventional security systems, necessary information was often not provided in real time in situations requiring rapid response on-site. As a result, problems arose such as delays and inaccuracies in emergency responses. Therefore, there is a need for means to enable effective collection of recorded information, improvement of work efficiency through predictive models, and immediate provision of information in security systems.

[0258] 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.

[0259] In this invention, the server includes means for automatically accumulating recorded information acquired from a detection device, means for predicting the workload using a specific analysis model based on the recorded information, and means for generating and outputting the predicted workload in a visual format. This enables on-site security staff to receive important information in real time and respond quickly and accurately.

[0260] "Detection device" refers to all hardware used to acquire security information and recorded information, including cameras and sensors.

[0261] "Recorded information" refers to data and logs related to security events, which are used for anomaly detection and workload prediction.

[0262] An "analysis model" is a model constructed using machine learning algorithms and data analysis techniques, and is used to perform predictions and anomaly detection based on recorded information.

[0263] "Workload" refers to the amount of work that security staff face, and this load can be predicted and managed by acquiring and analyzing information.

[0264] A "visual format" refers to a format that displays data and analysis results in an intuitively easy-to-understand way, such as graphs and dashboards.

[0265] "Notifications" are a means of communication that delivers important information and alerts to security staff in real time, enabling a swift response.

[0266] To implement this invention, the following hardware and software are used.

[0267] The server first collects recorded information from detection devices. These detection devices include cameras and sensors. This recorded information includes security event data and logs, which are then used as input for an analysis model that predicts workload. The analysis model uses a machine learning framework such as TensorFlow. This model is used to process the data and discover anomalous patterns and make predictions.

[0268] The analysis results are generated in a visual format. This involves creating dashboards using data visualization tools such as Tableau and communicating the visualized information to security staff. Users can receive this visualized data in real time through visual devices such as smart glasses.

[0269] As a concrete example, security staff at a large-scale event venue can use smart glasses to monitor crowd conditions and any anomalies in real time. The staff can then utilize the visual information transmitted from the server to take swift and accurate countermeasures.

[0270] For example, a prompt message for a generative AI model might be, "Build a machine learning model to monitor the security situation at this event venue in real time and detect any anomalies." This would improve safety at the site.

[0271] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0272] Step 1:

[0273] The server collects recorded information from detection devices. The input is raw data provided by cameras and sensors. This data is converted into a log format and stored in an appropriate database to prepare for subsequent analysis.

[0274] Step 2:

[0275] The server inputs the collected record information into an analysis model. This record information includes metadata such as the type, time, and location of events. Here, a machine learning model is executed using TensorFlow to detect anomalies and predict workload. The output is data on anomaly patterns and estimated congestion and risk states.

[0276] Step 3:

[0277] The server processes the analysis results into a visual format. The input consists of anomaly patterns and predicted data obtained through the analysis. This information is then converted into dashboards and graphs using Tableau, making it easily visible. This visual information is then generated in a format usable by security staff.

[0278] Step 4:

[0279] The terminal receives the visual information sent from the server and notifies the user. The input is the visual data sent from the server. The terminal displays this in real time on the smart glasses to assist the user in easily grasping the situation. The output is visual information that the user can immediately confirm.

[0280] Step 5:

[0281] The user checks the visual information through the smart glasses and quickly takes countermeasures. The input is the visual data provided by the terminal. Based on this information, the user determines the necessary responses on-site and executes appropriate actions. The output is improved response behavior.

[0282] Furthermore, an emotion engine for estimating the user's emotions may be combined. That is, the specific processing unit 290 may estimate the user's emotions using the emotion recognition model 59 and perform specific processing using the user's emotions.

[0283] The present invention is a system for improving the efficiency and quality of operations in a call center, and particularly aims to further enhance the quality of customer response by incorporating an emotion recognition function. This system combines a server, a terminal, a user, and an emotion engine, and provides information contributing to business improvement through the analysis of call history and the recognition of emotional states.

[0284] The server first automatically accumulates the history data of the call center from the call processing device. This includes the content of past calls, the number of incoming calls, the response rate, the operation rate, and the voice data during the calls. Then, based on the history information and voice data, the server predicts the business load and the customer's emotional state using a specific analysis model. In particular, the emotion engine analyzes the voice pattern and identifies the customer's emotions, such as satisfaction, dissatisfaction, tension, etc. This identification information indicates guidelines for improving the user's response.

[0285] The server reports the results of the predicted workload and emotional state in a visual and emotion - considerate format and provides them to the user through the terminal. By referring to this report, the user can grasp the status of customer service and devise appropriate improvement measures. For example, if a customer expresses dissatisfaction during a call, that information is quickly shared with the user, and the server can automatically propose specific action plans for problem - solving. In this way, it can contribute to information sharing within the call center and improvement of response quality.

[0286] As a specific example, when the emotion engine determines that a customer during a call is showing dissatisfied emotions, the server notifies the user of this information via the terminal and assists the user to quickly take appropriate countermeasures. Thereby, the quality of the service and customer satisfaction can be improved.

[0287] The following describes the processing flow.

[0288] Step 1:

[0289] The server automatically collects past call history information and voice data from the call processing device. This information includes call time, call content, incoming call count, handling results, voice tone, etc.

[0290] Step 2:

[0291] The server performs pre - processing for analyzing the collected data. Specifically, it conducts cleaning of voice data, unification of text data formats, noise removal, etc. Thereby, the analysis accuracy is improved and reliable results can be obtained.

[0292] Step 3:

[0293] The server runs the emotion engine using pre-processed data. The emotion engine analyzes the user's emotional state from the voice data and identifies emotions such as satisfaction, dissatisfaction, and tension. These emotions are categorized and integrated with predictions about workload by the analysis model.

[0294] Step 4:

[0295] The server generates reports in an easy-to-understand format for users, based on sentiment analysis results and workload predictions. These reports include a summary of emotional states, visualizations of times when customer dissatisfaction is high, and suggestions for specific countermeasures.

[0296] Step 5:

[0297] The terminal delivers the generated reports to the user. During this process, it provides real-time notifications to help the user quickly adjust customer responses.

[0298] Step 6:

[0299] Users improve their communication with customers based on reports provided by their devices. In particular, they consult with their supervisors and colleagues about specific response methods based on the results of the emotional state assessment. This improves the quality of customer service and increases operational efficiency.

[0300] (Example 2)

[0301] 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".

[0302] Call center operations require both improving the quality of customer service and accurately predicting workload. However, traditional systems have struggled to accurately grasp customers' emotional states and take prompt action based on that understanding. This can lead to decreased customer satisfaction and reduced operational efficiency.

[0303] The specific processing by the specific processing unit 290 of the data processing apparatus 12 in Example 2 is realized by the following means.

[0304] In this invention, the server includes means for automatically accumulating the history information acquired from the communication device, means for identifying emotions by utilizing an AI model generated based on the history information and voice data, and means for generating and outputting the emotion identification and the prediction result of the workload in a visible form. Thereby, it becomes possible to grasp the emotional state of the customer in real time and take prompt and appropriate countermeasures based on it.

[0305] The "communication device" is a device that manages calls in a call center and has functions of generating, storing, and providing call records and related data.

[0306] The "history information" is recorded data related to past communications and includes call content, incoming call numbers, response rates, operation rates, and the like.

[0307] The "generated AI model" is a model using machine learning technology, which learns specific patterns from the input data and is used for predicting emotions, workloads, and the like.

[0308] The "means for identifying emotions" refers to a technical process for analyzing voice data and specifying the emotional state of the customer.

[0309] The "prediction result of the workload" indicates a predicted value that numerically or graphically represents the future workload based on the collected history information.

[0310] The "visible form" refers to a form provided as a dashboard or a report in a form that is easy to visually understand the analysis result and the prediction.

[0311] This invention is a system aimed at improving the efficiency of call center operations and enhancing the quality of customer service. To implement this system, the server, terminals, and users must work together in coordination.

[0312] First, the server automatically collects historical information from the communication device. This historical information includes past call content, response rates, uptime, and voice data from the call. This data is managed using a database management system (e.g., MySQL or PostgreSQL).

[0313] Next, the server uses a generative AI model to identify emotions based on the collected historical information and voice data. Emotion identification utilizes machine learning frameworks (e.g., TensorFlow and PyTorch) and analyzes voice patterns using neural networks. This makes it possible to classify the customer's emotional state into categories such as satisfaction, dissatisfaction, and tension.

[0314] The sentiment identification results and workload prediction results are generated by the server as a visual report. This report is designed to be displayed in graph and dashboard format using data visualization tools (e.g., Tableau or Power BI).

[0315] This allows users to receive visual reports through their devices and use them to make decisions about improving customer service. By using this information to quickly take action, users can improve customer satisfaction.

[0316] As a concrete example, if the server uses its emotion engine to detect customer dissatisfaction during a call, it transmits that information to the terminal in real time and notifies the user. Upon receiving this notification, the user can prepare to respond quickly. For example, by using prompts such as, "Please provide the analysis results for the call where the customer is expressing dissatisfaction," it becomes possible to consider further improvements.

[0317] Thus, the present invention contributes to improving the quality of customer service and increasing the operational efficiency of call centers.

[0318] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0319] Step 1:

[0320] The server collects historical information from communication devices. Inputs include call content, number of incoming calls, response rate, uptime, and voice data. This data is stored in a database. Specifically, the server uses a database management system to access the database and retrieves the necessary data by issuing SQL queries.

[0321] Step 2:

[0322] The server inputs historical information and audio data into a generating AI model to identify emotions. The input is waveform information from the audio data, and the output is the customer's emotional state (e.g., satisfied, dissatisfied, tense). Here, a machine learning library is used to analyze the audio data, and a neural network is used to detect emotional patterns.

[0323] Step 3:

[0324] The server predicts workload based on historical information. It uses historical data such as past utilization rates and response rates as input, and generates predicted values ​​for future workload as output. Specifically, it implements an algorithm for regression analysis and makes predictions by analyzing data trends.

[0325] Step 4:

[0326] The server integrates emotion identification results and workload prediction results to generate a visual report. Emotional states and predicted values ​​are used as input, and a visual dashboard-style report is created as output. This includes specific actions such as creating graphs and charts using data visualization tools.

[0327] Step 5:

[0328] The terminal notifies the user of reports from the server. Based on the report information received as input, it displays the report content on the screen as output. Specifically, the user interface provides pop-up notifications and links to detailed dashboards, allowing the user to access the information immediately.

[0329] Step 6:

[0330] Users refer to reports received via their devices and consider ways to improve customer service. The output is a development of an action plan for improvement. Specific actions involved include analyzing the data in the provided report and prompting the server for necessary countermeasures.

[0331] (Application Example 2)

[0332] 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."

[0333] Balancing the quality of customer service and operational efficiency in call centers is an extremely difficult challenge. In particular, accurately recognizing customers' emotional states and responding promptly is crucial for improving customer satisfaction. However, current systems cannot utilize the context or emotional state of call content, making it difficult to predict workload and accurately assess customer emotions. Therefore, there is a need for a new system that integrates more advanced emotion recognition and workload prediction.

[0334] 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.

[0335] In this invention, the server includes means for automatically accumulating historical data acquired from a call processing unit, means for recognizing the emotional state of a user by analyzing voice information, and means for generating and outputting the predicted workload and emotional state in a visible format. This makes it possible to grasp the customer's emotional state in real time and visualize it together with the workload.

[0336] "Historical data" refers to the collection of information obtained from call processing equipment, such as past call content, inquiry volume, and response rate.

[0337] "Analysis method" refers to specific algorithms and statistical techniques used to predict workload and analyze inquiry trends based on historical data and voice information.

[0338] "Emotion recognition means" refers to devices and technologies that identify the emotional state of customers or users by analyzing voice patterns during a phone call.

[0339] "Workload" refers to the quantity and quality of tasks that a call center must handle, as well as the associated personnel and time requirements.

[0340] "Visual format" refers to a data format that visually represents the analysis results in a way that is easy for humans to understand.

[0341] "Security-related anomalies" refer to suspicious behavior or statements that deviate from normal business operations, detected from the customer's emotional state or the content of their calls.

[0342] "Recommendations for business improvement" refer to specific action plans recommended based on actual data to improve business efficiency and the quality of customer service.

[0343] To implement this invention, the server, terminal, and user each play specific roles in the call center system. The server automatically collects historical data from the call processing unit. This historical data includes information such as past call content, inquiry volume, and response rate. The server uses this data to perform analysis to predict the workload. The server is also equipped with emotion recognition means to analyze voice information and recognize the customer's emotional state. The emotion recognition means uses an AI model to analyze voice patterns and identify different emotional states such as customer satisfaction, dissatisfaction, and tension.

[0344] The server generates predicted workload and emotional states in a visual format and outputs them as a report. This visual information is provided to the user via a terminal. Based on the information displayed on the terminal, the user can quickly take appropriate actions to improve customer service.

[0345] For example, if the emotion engine detects a customer's anxiety during a call, the server immediately notifies the terminal of this information. This information is based, for instance, on the results of an analysis of voice data suggesting that the user is feeling anxious. By referring to this information, the user can provide appropriate follow-up to the customer.

[0346] When using a generative AI model to analyze emotional states, the following prompt can be used: "Please suggest a course of action if anger or fear is detected during a customer call."

[0347] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0348] Step 1:

[0349] The server automatically retrieves historical data from the call processing unit. Inputs include past call content, inquiry volume, and response rate. By aggregating this data, a historical database is generated.

[0350] Step 2:

[0351] The server uses historical data to perform analysis and predict workload. The input is historical data, and the data analysis algorithm calculates query volume trends and peak workload, outputting this as predicted data.

[0352] Step 3:

[0353] The server acquires audio data during a call and analyzes the customer's emotional state using emotion recognition technology. The input is real-time audio data, and by analyzing the audio patterns with a generating AI model, it identifies the customer's emotional state (e.g., satisfaction, dissatisfaction, tension, etc.) and outputs the result as emotion data.

[0354] Step 4:

[0355] The server generates information in a visual format and creates reports based on predictive and sentiment data. It takes predictive and sentiment data as input, integrates this data into graphs and charts, and outputs it as easy-to-understand report data.

[0356] Step 5:

[0357] The terminal provides the user with report data received from the server. The input is report data, which is displayed on the user interface and provided as reference information for the user to make decisions regarding improvements to customer service.

[0358] Step 6:

[0359] Based on the reports displayed on their devices, users decide on specific actions to improve customer service. In this step, users determine what actions they should take based on the reports and then reflect those decisions in their actual interactions with customers.

[0360] 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.

[0361] 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.

[0362] 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.

[0363] [Third Embodiment]

[0364] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0365] 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.

[0366] 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).

[0367] 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.

[0368] 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.

[0369] 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).

[0370] 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.

[0371] 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.

[0372] 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.

[0373] 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.

[0374] 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.

[0375] 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".

[0376] This invention is a support system aimed at improving operational efficiency in call centers. This system consists of a server, terminals, and users, and automates the monitoring of call center operational status and the generation of reports.

[0377] The server first periodically collects historical data from the call center. This includes call volume, response rate, utilization rate, and CPH (Calls Per Hour). Next, the server analyzes this data using a specific analytical model to predict workload. This analysis highlights key foundational information for new employees and those transferring to other departments.

[0378] The analysis results are generated by the server in a visible format, such as a dashboard or a PDF report. This report includes specific advice that can contribute to business improvement, as well as predicted increases in the number of incoming calls.

[0379] The terminal receives reports generated by the server and provides them to call center users. By referring to these reports, users can quickly grasp the current state of operations and concerns, and easily take appropriate countermeasures.

[0380] For example, it becomes possible to prepare in advance to cope with a sudden surge in incoming calls from users (new employees), and to develop appropriate action plans in consultation with supervisors based on predictions from the server. This is expected to improve the quality of customer service at the call center and enhance overall operational efficiency.

[0381] The following describes the processing flow.

[0382] Step 1:

[0383] The server automatically collects historical performance data from various call processing units in the call center. This data includes the number of incoming calls, response rate, utilization rate, and CPH (Call Processing Frequency), and is obtained via APIs and log files.

[0384] Step 2:

[0385] The server performs necessary preprocessing before analyzing the collected data. This includes imputing missing values, removing outliers, and standardizing the data format. This improves the accuracy of the analysis and enables reliable predictions.

[0386] Step 3:

[0387] The server runs a specific analysis model using pre-processed data. This model predicts workload and detects potential issues based on historical data. The analysis results predict fluctuations in the next call volume and response rate, and these trends are reflected in the report.

[0388] Step 4:

[0389] The server generates analysis results in a report that is easy to understand visually. Specifically, it publishes workload predictions and improvement suggestions in graph and chart format. This report can also be output in PDF or dashboard format.

[0390] Step 5:

[0391] The terminal displays reports received from the server to call center users. Customized information tailored to each employee's role is also provided, allowing new employees and those transferred to other departments to quickly understand their work situation.

[0392] Step 6:

[0393] Users review their work processes based on the report's content and identify necessary improvements. By observing the effectiveness of the implemented improvements and sending feedback to the server, they contribute to further improving system accuracy.

[0394] (Example 1)

[0395] 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."

[0396] In call centers, improving operational efficiency and optimizing workload are crucial challenges, but traditional methods have made it difficult to achieve this quickly and accurately. Furthermore, complex data analysis is challenging without specialized technical skills, often resulting in an inability to obtain the necessary information for business improvement. This leads to delays in response, inappropriate resource allocation, and a decline in overall operational efficiency.

[0397] 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.

[0398] In this invention, the server includes means for automatically formatting past business information collected from a communication processing device, means for analyzing workload using a machine learning model based on the formatted business information, and means for generating and providing the results of the workload analysis in a visualized format. This makes it possible to quickly grasp the current state of operations and analyze future workload using a predictive model. In addition, by utilizing the visualized information, even users without specialized knowledge can intuitively understand the information and take effective business improvement measures.

[0399] A "communication processing device" is a device used in a call center to manage calls and data communications and to collect historical information.

[0400] "Business information" refers to all operational data related to the call center, such as the number of calls, response rate, and utilization rate.

[0401] "Automatic formatting" refers to the process of processing collected data into a format suitable for analysis, such as removing noise or imputing missing values.

[0402] A "machine learning model" refers to an algorithm or method that is trained on past data and used to analyze patterns and make predictions from new data.

[0403] "Workload" refers to the volume of inquiries and calls handled by a call center over a certain period, and is an indicator used as a basis for determining the necessary resources for operation.

[0404] "Analysis results" refer to conclusions and trends derived from data obtained using machine learning models.

[0405] A "visualized format" refers to a visual representation of analyzed data in the form of graphs, charts, dashboards, etc., converted into a format that is easy for users to understand intuitively.

[0406] This invention is a system for improving operational efficiency in call centers, and mainly consists of a server, terminals, and users.

[0407] The server first collects historical business information through a communication processing unit. This information includes metrics such as the number of calls, response rate, and uptime. The server then performs data preprocessing to properly format this data. In this process, libraries such as Python's Pandas and NumPy are used to automatically perform noise reduction and imputation of missing values.

[0408] Next, the server uses the formatted business information to perform analysis using machine learning models. The analysis utilizes models such as ARIMA and LSTM for time-series analysis. This allows for the prediction of workload and the generation of information useful for future operational resource management.

[0409] The server then uses the analysis results to create a visualized report. Visualization tools such as Power BI and Tableau are used to create this report, transforming the information into an intuitively understandable format using graphs and charts.

[0410] The terminal receives visualization reports sent from the server and provides them to call center users. A dedicated application is installed on the terminal, through which users access the information.

[0411] Users use their devices to review received data and understand the current state of their work and anticipated challenges. Furthermore, they utilize a generative AI model to input prompts such as, "How should we respond to the expected increase in incoming calls due to next month's new promotion?" Based on the information obtained from the generative AI model, they can consult with their supervisors to develop effective action plans, thereby improving their work processes.

[0412] In this way, each component of this system works in conjunction to efficiently execute a series of processes, from data collection and analysis to the proposal of improvement measures. Based on the information obtained, users can make accurate decisions and plans, thereby improving the overall operational efficiency of the call center.

[0413] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0414] Step 1:

[0415] The server collects historical call center data through a communication processing unit. Specifically, it retrieves data including the number of calls, response rate, and utilization rate. This raw data is the input. To properly format this data, the server retrieves it from a database via an API and prepares it for subsequent processing.

[0416] Step 2:

[0417] The server preprocesses the collected data. The input is the raw, unprocessed data obtained in step 1. In this process, the server uses the Python Pandas library to remove noise from the data and impute missing values. The output is a clean dataset suitable for analysis. This provides high-quality data for the model to function properly.

[0418] Step 3:

[0419] The server analyzes the preprocessed data using a machine learning model. The input is the preprocessed data that is the output of step 2. In this step, the server applies ARIMA or LSTM models for time series analysis to predict workload. This outputs predictive data regarding future workload conditions.

[0420] Step 4:

[0421] The server creates a visualized report based on the analysis results. The input is the analysis results from step 3. The server uses Power BI or Tableau to convert the obtained data into graphs and charts and generate a dashboard-style report. The output is a visualized report that is intuitively understandable to the user.

[0422] Step 5:

[0423] The terminal receives a visualized report sent from the server. The input is the report generated in step 4. The terminal displays the report through a dedicated application and prepares it for the user. Specifically, it retrieves the report over the network and makes it available for viewing in the local environment.

[0424] Step 6:

[0425] Users refer to reports provided through their terminals to understand the current state of operations and anticipated challenges. Based on this information, users input prompts into the generating AI model, such as, "How should we respond to the expected increase in incoming calls due to next month's new promotion?" As output, the generating AI model presents specific recommended actions, helping users develop actionable plans. As a result, improved operational efficiency in the call center is expected.

[0426] (Application Example 1)

[0427] 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."

[0428] In conventional security systems, necessary information was often not provided in real time in situations requiring rapid response on-site. As a result, problems arose such as delays and inaccuracies in emergency responses. Therefore, there is a need for means to enable effective collection of recorded information, improvement of work efficiency through predictive models, and immediate provision of information in security systems.

[0429] 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.

[0430] In this invention, the server includes means for automatically accumulating recorded information acquired from a detection device, means for predicting the workload using a specific analysis model based on the recorded information, and means for generating and outputting the predicted workload in a visual format. This enables on-site security staff to receive important information in real time and respond quickly and accurately.

[0431] "Detection device" refers to all hardware used to acquire security information and recorded information, including cameras and sensors.

[0432] "Recorded information" refers to data and logs related to security events, which are used for anomaly detection and workload prediction.

[0433] An "analysis model" is a model constructed using machine learning algorithms and data analysis techniques, and is used to perform predictions and anomaly detection based on recorded information.

[0434] "Workload" refers to the amount of work that security staff face, and this load can be predicted and managed by acquiring and analyzing information.

[0435] A "visual format" refers to a format that displays data and analysis results in an intuitively easy-to-understand way, such as graphs and dashboards.

[0436] "Notifications" are a means of communication that delivers important information and alerts to security staff in real time, enabling a swift response.

[0437] To implement this invention, the following hardware and software are used.

[0438] The server first collects recorded information from detection devices. These detection devices include cameras and sensors. This recorded information includes security event data and logs, which are then used as input for an analysis model that predicts workload. The analysis model uses a machine learning framework such as TensorFlow. This model is used to process the data and discover anomalous patterns and make predictions.

[0439] The analysis results are generated in a visual format. This involves creating dashboards using data visualization tools such as Tableau and communicating the visualized information to security staff. Users can receive this visualized data in real time through visual devices such as smart glasses.

[0440] As a concrete example, security staff at a large-scale event venue can use smart glasses to monitor crowd conditions and any anomalies in real time. The staff can then utilize the visual information transmitted from the server to take swift and accurate countermeasures.

[0441] For example, a prompt message for a generative AI model might be, "Build a machine learning model to monitor the security situation at this event venue in real time and detect any anomalies." This would improve safety at the site.

[0442] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0443] Step 1:

[0444] The server collects recorded information from detection devices. The input is raw data provided by cameras and sensors. This data is converted into a log format and stored in an appropriate database to prepare for subsequent analysis.

[0445] Step 2:

[0446] The server inputs the collected record information into an analysis model. This record information includes metadata such as the type, time, and location of events. Here, a machine learning model is executed using TensorFlow to detect anomalies and predict workload. The output is data on anomaly patterns and estimated congestion and risk states.

[0447] Step 3:

[0448] The server processes the analysis results into a visual format. The input consists of anomaly patterns and predicted data obtained through the analysis. This information is then converted into dashboards and graphs using Tableau, making it easily visible. This visual information is then generated in a format usable by security staff.

[0449] Step 4:

[0450] The terminal receives visual information transmitted from the server and notifies the user. The input is visual data transmitted from the server. The terminal displays this in real time on smart glasses, helping the user understand the situation. The output is visual information that the user can immediately confirm.

[0451] Step 5:

[0452] Users access visual information through smart glasses and take swift action. The input is visual data provided by the device. Based on this information, users determine the necessary response on-site and take appropriate action. The output is the improved response behavior.

[0453] 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.

[0454] This invention is a system designed to improve the efficiency and quality of operations in call centers, and in particular aims to further enhance the quality of customer service by incorporating emotion recognition functionality. This system combines a server, terminal, user, and emotion engine, and provides information that contributes to business improvement through the analysis of call history and the recognition of emotional states.

[0455] The server first automatically collects call center history data from the call processing unit. This includes past call content, number of incoming calls, answer rate, utilization rate, and voice data from calls. Based on this history information and voice data, the server uses a specific analytical model to predict workload and customer emotional state. In particular, the emotion engine analyzes voice patterns to identify customer emotions, such as satisfaction, dissatisfaction, and tension. This identified information provides guidance for improving user service.

[0456] The server generates a report of predicted workload and emotional state in a visual and emotionally conscious format, and provides it to the user via a terminal. By referring to this report, users can understand the status of customer service and devise appropriate improvement measures. For example, if a customer expresses dissatisfaction during a call, this information is quickly shared with the user, and the server can automatically propose specific actions to resolve the problem. In this way, it can contribute to information sharing and improvement of customer service within the call center.

[0457] For example, if the emotion engine determines that a customer the user is currently on a call with is expressing dissatisfaction, the server will notify the user of this information via the terminal, assisting the user in taking appropriate action quickly. This can improve the quality of service and enhance customer satisfaction.

[0458] The following describes the processing flow.

[0459] Step 1:

[0460] The server automatically collects past call history information and voice data from the call processing unit. This information includes call duration, call content, number of incoming calls, handling record, and voice tone.

[0461] Step 2:

[0462] The server performs preprocessing on the collected data for analysis. Specifically, it cleans audio data, standardizes text data formats, and removes noise. This improves analysis accuracy and yields more reliable results.

[0463] Step 3:

[0464] The server runs the emotion engine using pre-processed data. The emotion engine analyzes the user's emotional state from the voice data and identifies emotions such as satisfaction, dissatisfaction, and tension. These emotions are categorized and integrated with predictions about workload by the analysis model.

[0465] Step 4:

[0466] The server generates reports in an easy-to-understand format for users, based on sentiment analysis results and workload predictions. These reports include a summary of emotional states, visualizations of times when customer dissatisfaction is high, and suggestions for specific countermeasures.

[0467] Step 5:

[0468] The terminal delivers the generated reports to the user. During this process, it provides real-time notifications to help the user quickly adjust customer responses.

[0469] Step 6:

[0470] Users improve their communication with customers based on reports provided by their devices. In particular, they consult with their supervisors and colleagues about specific response methods based on the results of the emotional state assessment. This improves the quality of customer service and increases operational efficiency.

[0471] (Example 2)

[0472] 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."

[0473] Call center operations require both improving the quality of customer service and accurately predicting workload. However, traditional systems have struggled to accurately grasp customers' emotional states and take prompt action based on that understanding. This can lead to decreased customer satisfaction and reduced operational efficiency.

[0474] 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.

[0475] In this invention, the server includes means for automatically accumulating historical information acquired from a communication device, means for identifying emotions using a generated AI model based on the historical information and voice data, and means for generating and outputting the emotion identification and workload prediction results in a visible format. This makes it possible to grasp the emotional state of customers in real time and take quick and appropriate countermeasures based on that.

[0476] A "communication device" is a device that manages calls in a call center and has the function of generating, storing, and providing call records and related data.

[0477] "Historical information" refers to record data related to past communications, including call content, number of incoming calls, response rate, and operational rate.

[0478] A "generative AI model" is a model that uses machine learning techniques to learn specific patterns from input data and make predictions about emotions, workload, and other factors.

[0479] "Means of identifying emotions" refers to a technological process that analyzes voice data to identify the emotional state of a customer.

[0480] "Workload prediction results" refer to predicted values ​​that numerically or graphically represent the future workload based on collected historical information.

[0481] "Visual format" refers to a format in which analysis results and predictions are presented in a visually easy-to-understand way, such as in dashboards or reports.

[0482] This invention is a system aimed at improving the efficiency of call center operations and enhancing the quality of customer service. To implement this system, the server, terminals, and users must work together in coordination.

[0483] First, the server automatically collects historical information from the communication device. This historical information includes past call content, response rates, uptime, and voice data from the call. This data is managed using a database management system (e.g., MySQL or PostgreSQL).

[0484] Next, the server uses a generative AI model to identify emotions based on the collected historical information and voice data. Emotion identification utilizes machine learning frameworks (e.g., TensorFlow and PyTorch) and analyzes voice patterns using neural networks. This makes it possible to classify the customer's emotional state into categories such as satisfaction, dissatisfaction, and tension.

[0485] The sentiment identification results and workload prediction results are generated by the server as a visual report. This report is designed to be displayed in graph and dashboard format using data visualization tools (e.g., Tableau or Power BI).

[0486] This allows users to receive visual reports through their devices and use them to make decisions about improving customer service. By using this information to quickly take action, users can improve customer satisfaction.

[0487] As a concrete example, if the server uses its emotion engine to detect customer dissatisfaction during a call, it transmits that information to the terminal in real time and notifies the user. Upon receiving this notification, the user can prepare to respond quickly. For example, by using prompts such as, "Please provide the analysis results for the call where the customer is expressing dissatisfaction," it becomes possible to consider further improvements.

[0488] Thus, the present invention contributes to improving the quality of customer service and increasing the operational efficiency of call centers.

[0489] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0490] Step 1:

[0491] The server collects historical information from communication devices. Inputs include call content, number of incoming calls, response rate, uptime, and voice data. This data is stored in a database. Specifically, the server uses a database management system to access the database and retrieves the necessary data by issuing SQL queries.

[0492] Step 2:

[0493] The server inputs historical information and audio data into a generating AI model to identify emotions. The input is waveform information from the audio data, and the output is the customer's emotional state (e.g., satisfied, dissatisfied, tense). Here, a machine learning library is used to analyze the audio data, and a neural network is used to detect emotional patterns.

[0494] Step 3:

[0495] The server predicts workload based on historical information. It uses historical data such as past utilization rates and response rates as input, and generates predicted values ​​for future workload as output. Specifically, it implements an algorithm for regression analysis and makes predictions by analyzing data trends.

[0496] Step 4:

[0497] The server integrates emotion identification results and workload prediction results to generate a visual report. Emotional states and predicted values ​​are used as input, and a visual dashboard-style report is created as output. This includes specific actions such as creating graphs and charts using data visualization tools.

[0498] Step 5:

[0499] The terminal notifies the user of reports from the server. Based on the report information received as input, it displays the report content on the screen as output. Specifically, the user interface provides pop-up notifications and links to detailed dashboards, allowing the user to access the information immediately.

[0500] Step 6:

[0501] Users refer to reports received via their devices and consider ways to improve customer service. The output is a development of an action plan for improvement. Specific actions involved include analyzing the data in the provided report and prompting the server for necessary countermeasures.

[0502] (Application Example 2)

[0503] 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."

[0504] Balancing the quality of customer service and operational efficiency in call centers is an extremely difficult challenge. In particular, accurately recognizing customers' emotional states and responding promptly is crucial for improving customer satisfaction. However, current systems cannot utilize the context or emotional state of call content, making it difficult to predict workload and accurately assess customer emotions. Therefore, there is a need for a new system that integrates more advanced emotion recognition and workload prediction.

[0505] 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.

[0506] In this invention, the server includes means for automatically accumulating historical data acquired from a call processing unit, means for recognizing the emotional state of a user by analyzing voice information, and means for generating and outputting the predicted workload and emotional state in a visible format. This makes it possible to grasp the customer's emotional state in real time and visualize it together with the workload.

[0507] "Historical data" refers to the collection of information obtained from call processing equipment, such as past call content, inquiry volume, and response rate.

[0508] "Analysis method" refers to specific algorithms and statistical techniques used to predict workload and analyze inquiry trends based on historical data and voice information.

[0509] "Emotion recognition means" refers to devices and technologies that identify the emotional state of customers or users by analyzing voice patterns during a phone call.

[0510] "Workload" refers to the quantity and quality of tasks that a call center must handle, as well as the associated personnel and time requirements.

[0511] "Visual format" refers to a data format that visually represents the analysis results in a way that is easy for humans to understand.

[0512] "Security-related anomalies" refer to suspicious behavior or statements that deviate from normal business operations, detected from the customer's emotional state or the content of their calls.

[0513] "Recommendations for business improvement" refer to specific action plans recommended based on actual data to improve business efficiency and the quality of customer service.

[0514] To implement this invention, the server, terminal, and user each play specific roles in the call center system. The server automatically collects historical data from the call processing unit. This historical data includes information such as past call content, inquiry volume, and response rate. The server uses this data to perform analysis to predict the workload. The server is also equipped with emotion recognition means to analyze voice information and recognize the customer's emotional state. The emotion recognition means uses an AI model to analyze voice patterns and identify different emotional states such as customer satisfaction, dissatisfaction, and tension.

[0515] The server generates predicted workload and emotional states in a visual format and outputs them as a report. This visual information is provided to the user via a terminal. Based on the information displayed on the terminal, the user can quickly take appropriate actions to improve customer service.

[0516] For example, if the emotion engine detects a customer's anxiety during a call, the server immediately notifies the terminal of this information. This information is based, for instance, on the results of an analysis of voice data suggesting that the user is feeling anxious. By referring to this information, the user can provide appropriate follow-up to the customer.

[0517] When using a generative AI model to analyze emotional states, the following prompt can be used: "Please suggest a course of action if anger or fear is detected during a customer call."

[0518] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0519] Step 1:

[0520] The server automatically retrieves historical data from the call processing unit. Inputs include past call content, inquiry volume, and response rate. By aggregating this data, a historical database is generated.

[0521] Step 2:

[0522] The server uses historical data to perform analysis and predict workload. The input is historical data, and the data analysis algorithm calculates query volume trends and peak workload, outputting this as predicted data.

[0523] Step 3:

[0524] The server acquires audio data during a call and analyzes the customer's emotional state using emotion recognition technology. The input is real-time audio data, and by analyzing the audio patterns with a generating AI model, it identifies the customer's emotional state (e.g., satisfaction, dissatisfaction, tension, etc.) and outputs the result as emotion data.

[0525] Step 4:

[0526] The server generates information in a visual format and creates reports based on predictive and sentiment data. It takes predictive and sentiment data as input, integrates this data into graphs and charts, and outputs it as easy-to-understand report data.

[0527] Step 5:

[0528] The terminal provides the user with report data received from the server. The input is report data, which is displayed on the user interface and provided as reference information for the user to make decisions regarding improvements to customer service.

[0529] Step 6:

[0530] Based on the reports displayed on their devices, users decide on specific actions to improve customer service. In this step, users determine what actions they should take based on the reports and then reflect those decisions in their actual interactions with customers.

[0531] 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.

[0532] 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.

[0533] 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.

[0534] [Fourth Embodiment]

[0535] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0536] 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.

[0537] 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).

[0538] 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.

[0539] 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.

[0540] 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).

[0541] 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.

[0542] 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.

[0543] 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.

[0544] 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.

[0545] 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.

[0546] 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.

[0547] 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".

[0548] This invention is a support system aimed at improving operational efficiency in call centers. This system consists of a server, terminals, and users, and automates the monitoring of call center operational status and the generation of reports.

[0549] The server first periodically collects historical data from the call center. This includes call volume, response rate, utilization rate, and CPH (Calls Per Hour). Next, the server analyzes this data using a specific analytical model to predict workload. This analysis highlights key foundational information for new employees and those transferring to other departments.

[0550] The analysis results are generated by the server in a visible format, such as a dashboard or a PDF report. This report includes specific advice that can contribute to business improvement, as well as predicted increases in the number of incoming calls.

[0551] The terminal receives reports generated by the server and provides them to call center users. By referring to these reports, users can quickly grasp the current state of operations and concerns, and easily take appropriate countermeasures.

[0552] For example, it becomes possible to prepare in advance to cope with a sudden surge in incoming calls from users (new employees), and to develop appropriate action plans in consultation with supervisors based on predictions from the server. This is expected to improve the quality of customer service at the call center and enhance overall operational efficiency.

[0553] The following describes the processing flow.

[0554] Step 1:

[0555] The server automatically collects historical performance data from various call processing units in the call center. This data includes the number of incoming calls, response rate, utilization rate, and CPH (Call Processing Frequency), and is obtained via APIs and log files.

[0556] Step 2:

[0557] The server performs necessary preprocessing before analyzing the collected data. This includes imputing missing values, removing outliers, and standardizing the data format. This improves the accuracy of the analysis and enables reliable predictions.

[0558] Step 3:

[0559] The server runs a specific analysis model using pre-processed data. This model predicts workload and detects potential issues based on historical data. The analysis results predict fluctuations in the next call volume and response rate, and these trends are reflected in the report.

[0560] Step 4:

[0561] The server generates analysis results in a report that is easy to understand visually. Specifically, it publishes workload predictions and improvement suggestions in graph and chart format. This report can also be output in PDF or dashboard format.

[0562] Step 5:

[0563] The terminal displays reports received from the server to call center users. Customized information tailored to each employee's role is also provided, allowing new employees and those transferred to other departments to quickly understand their work situation.

[0564] Step 6:

[0565] Users review their work processes based on the report's content and identify necessary improvements. By observing the effectiveness of the implemented improvements and sending feedback to the server, they contribute to further improving system accuracy.

[0566] (Example 1)

[0567] 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".

[0568] In call centers, improving operational efficiency and optimizing workload are crucial challenges, but traditional methods have made it difficult to achieve this quickly and accurately. Furthermore, complex data analysis is challenging without specialized technical skills, often resulting in an inability to obtain the necessary information for business improvement. This leads to delays in response, inappropriate resource allocation, and a decline in overall operational efficiency.

[0569] 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.

[0570] In this invention, the server includes means for automatically formatting past business information collected from a communication processing device, means for analyzing workload using a machine learning model based on the formatted business information, and means for generating and providing the results of the workload analysis in a visualized format. This makes it possible to quickly grasp the current state of operations and analyze future workload using a predictive model. In addition, by utilizing the visualized information, even users without specialized knowledge can intuitively understand the information and take effective business improvement measures.

[0571] A "communication processing device" is a device used in a call center to manage calls and data communications and to collect historical information.

[0572] "Business information" refers to all operational data related to the call center, such as the number of calls, response rate, and utilization rate.

[0573] "Automatic formatting" refers to the process of processing collected data into a format suitable for analysis, such as removing noise or imputing missing values.

[0574] A "machine learning model" refers to an algorithm or method that is trained on past data and used to analyze patterns and make predictions from new data.

[0575] "Workload" refers to the volume of inquiries and calls handled by a call center over a certain period, and is an indicator used as a basis for determining the necessary resources for operation.

[0576] "Analysis results" refer to conclusions and trends derived from data obtained using machine learning models.

[0577] A "visualized format" refers to a visual representation of analyzed data in the form of graphs, charts, dashboards, etc., converted into a format that is easy for users to understand intuitively.

[0578] This invention is a system for improving operational efficiency in call centers, and mainly consists of a server, terminals, and users.

[0579] The server first collects historical business information through a communication processing unit. This information includes metrics such as the number of calls, response rate, and uptime. The server then performs data preprocessing to properly format this data. In this process, libraries such as Python's Pandas and NumPy are used to automatically perform noise reduction and imputation of missing values.

[0580] Next, the server uses the formatted business information to perform analysis using machine learning models. The analysis utilizes models such as ARIMA and LSTM for time-series analysis. This allows for the prediction of workload and the generation of information useful for future operational resource management.

[0581] The server then uses the analysis results to create a visualized report. Visualization tools such as Power BI and Tableau are used to create this report, transforming the information into an intuitively understandable format using graphs and charts.

[0582] The terminal receives visualization reports sent from the server and provides them to call center users. A dedicated application is installed on the terminal, through which users access the information.

[0583] Users use their devices to review received data and understand the current state of their work and anticipated challenges. Furthermore, they utilize a generative AI model to input prompts such as, "How should we respond to the expected increase in incoming calls due to next month's new promotion?" Based on the information obtained from the generative AI model, they can consult with their supervisors to develop effective action plans, thereby improving their work processes.

[0584] In this way, each component of this system works in conjunction to efficiently execute a series of processes, from data collection and analysis to the proposal of improvement measures. Based on the information obtained, users can make accurate decisions and plans, thereby improving the overall operational efficiency of the call center.

[0585] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0586] Step 1:

[0587] The server collects historical call center data through a communication processing unit. Specifically, it retrieves data including the number of calls, response rate, and utilization rate. This raw data is the input. To properly format this data, the server retrieves it from a database via an API and prepares it for subsequent processing.

[0588] Step 2:

[0589] The server preprocesses the collected data. The input is the raw, unprocessed data obtained in step 1. In this process, the server uses the Python Pandas library to remove noise from the data and impute missing values. The output is a clean dataset suitable for analysis. This provides high-quality data for the model to function properly.

[0590] Step 3:

[0591] The server analyzes the preprocessed data using a machine learning model. The input is the preprocessed data that is the output of step 2. In this step, the server applies ARIMA or LSTM models for time series analysis to predict workload. This outputs predictive data regarding future workload conditions.

[0592] Step 4:

[0593] The server creates a visualized report based on the analysis results. The input is the analysis results from step 3. The server uses Power BI or Tableau to convert the obtained data into graphs and charts and generate a dashboard-style report. The output is a visualized report that is intuitively understandable to the user.

[0594] Step 5:

[0595] The terminal receives a visualized report sent from the server. The input is the report generated in step 4. The terminal displays the report through a dedicated application and prepares it for the user. Specifically, it retrieves the report over the network and makes it available for viewing in the local environment.

[0596] Step 6:

[0597] Users refer to reports provided through their terminals to understand the current state of operations and anticipated challenges. Based on this information, users input prompts into the generating AI model, such as, "How should we respond to the expected increase in incoming calls due to next month's new promotion?" As output, the generating AI model presents specific recommended actions, helping users develop actionable plans. As a result, improved operational efficiency in the call center is expected.

[0598] (Application Example 1)

[0599] 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".

[0600] In conventional security systems, necessary information was often not provided in real time in situations requiring rapid response on-site. As a result, problems arose such as delays and inaccuracies in emergency responses. Therefore, there is a need for means to enable effective collection of recorded information, improvement of work efficiency through predictive models, and immediate provision of information in security systems.

[0601] 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.

[0602] In this invention, the server includes means for automatically accumulating recorded information acquired from a detection device, means for predicting the workload using a specific analysis model based on the recorded information, and means for generating and outputting the predicted workload in a visual format. This enables on-site security staff to receive important information in real time and respond quickly and accurately.

[0603] "Detection device" refers to all hardware used to acquire security information and recorded information, including cameras and sensors.

[0604] "Recorded information" refers to data and logs related to security events, which are used for anomaly detection and workload prediction.

[0605] An "analysis model" is a model constructed using machine learning algorithms and data analysis techniques, and is used to perform predictions and anomaly detection based on recorded information.

[0606] "Workload" refers to the amount of work that security staff face, and this load can be predicted and managed by acquiring and analyzing information.

[0607] A "visual format" refers to a format that displays data and analysis results in an intuitively easy-to-understand way, such as graphs and dashboards.

[0608] "Notifications" are a means of communication that delivers important information and alerts to security staff in real time, enabling a swift response.

[0609] To implement this invention, the following hardware and software are used.

[0610] The server first collects recorded information from detection devices. These detection devices include cameras and sensors. This recorded information includes security event data and logs, which are then used as input for an analysis model that predicts workload. The analysis model uses a machine learning framework such as TensorFlow. This model is used to process the data and discover anomalous patterns and make predictions.

[0611] The analysis results are generated in a visual format. This involves creating dashboards using data visualization tools such as Tableau and communicating the visualized information to security staff. Users can receive this visualized data in real time through visual devices such as smart glasses.

[0612] As a concrete example, security staff at a large-scale event venue can use smart glasses to monitor crowd conditions and any anomalies in real time. The staff can then utilize the visual information transmitted from the server to take swift and accurate countermeasures.

[0613] For example, a prompt message for a generative AI model might be, "Build a machine learning model to monitor the security situation at this event venue in real time and detect any anomalies." This would improve safety at the site.

[0614] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0615] Step 1:

[0616] The server collects recorded information from detection devices. The input is raw data provided by cameras and sensors. This data is converted into a log format and stored in an appropriate database to prepare for subsequent analysis.

[0617] Step 2:

[0618] The server inputs the collected record information into an analysis model. This record information includes metadata such as the type, time, and location of events. Here, a machine learning model is executed using TensorFlow to detect anomalies and predict workload. The output is data on anomaly patterns and estimated congestion and risk states.

[0619] Step 3:

[0620] The server processes the analysis results into a visual format. The input consists of anomaly patterns and predicted data obtained through the analysis. This information is then converted into dashboards and graphs using Tableau, making it easily visible. This visual information is then generated in a format usable by security staff.

[0621] Step 4:

[0622] The terminal receives visual information transmitted from the server and notifies the user. The input is visual data transmitted from the server. The terminal displays this in real time on smart glasses, helping the user understand the situation. The output is visual information that the user can immediately confirm.

[0623] Step 5:

[0624] Users access visual information through smart glasses and take swift action. The input is visual data provided by the device. Based on this information, users determine the necessary response on-site and take appropriate action. The output is the improved response behavior.

[0625] 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.

[0626] This invention is a system designed to improve the efficiency and quality of operations in call centers, and in particular aims to further enhance the quality of customer service by incorporating emotion recognition functionality. This system combines a server, terminal, user, and emotion engine, and provides information that contributes to business improvement through the analysis of call history and the recognition of emotional states.

[0627] The server first automatically collects call center history data from the call processing unit. This includes past call content, number of incoming calls, answer rate, utilization rate, and voice data from calls. Based on this history information and voice data, the server uses a specific analytical model to predict workload and customer emotional state. In particular, the emotion engine analyzes voice patterns to identify customer emotions, such as satisfaction, dissatisfaction, and tension. This identified information provides guidance for improving user service.

[0628] The server generates a report of predicted workload and emotional state in a visual and emotionally conscious format, and provides it to the user via a terminal. By referring to this report, users can understand the status of customer service and devise appropriate improvement measures. For example, if a customer expresses dissatisfaction during a call, this information is quickly shared with the user, and the server can automatically propose specific actions to resolve the problem. In this way, it can contribute to information sharing and improvement of customer service within the call center.

[0629] For example, if the emotion engine determines that a customer the user is currently on a call with is expressing dissatisfaction, the server will notify the user of this information via the terminal, assisting the user in taking appropriate action quickly. This can improve the quality of service and enhance customer satisfaction.

[0630] The following describes the processing flow.

[0631] Step 1:

[0632] The server automatically collects past call history information and voice data from the call processing unit. This information includes call duration, call content, number of incoming calls, handling record, and voice tone.

[0633] Step 2:

[0634] The server performs preprocessing on the collected data for analysis. Specifically, it cleans audio data, standardizes text data formats, and removes noise. This improves analysis accuracy and yields more reliable results.

[0635] Step 3:

[0636] The server runs the emotion engine using pre-processed data. The emotion engine analyzes the user's emotional state from the voice data and identifies emotions such as satisfaction, dissatisfaction, and tension. These emotions are categorized and integrated with predictions about workload by the analysis model.

[0637] Step 4:

[0638] The server generates reports in an easy-to-understand format for users, based on sentiment analysis results and workload predictions. These reports include a summary of emotional states, visualizations of times when customer dissatisfaction is high, and suggestions for specific countermeasures.

[0639] Step 5:

[0640] The terminal delivers the generated reports to the user. During this process, it provides real-time notifications to help the user quickly adjust customer responses.

[0641] Step 6:

[0642] Users improve their communication with customers based on reports provided by their devices. In particular, they consult with their supervisors and colleagues about specific response methods based on the results of the emotional state assessment. This improves the quality of customer service and increases operational efficiency.

[0643] (Example 2)

[0644] 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".

[0645] Call center operations require both improving the quality of customer service and accurately predicting workload. However, traditional systems have struggled to accurately grasp customers' emotional states and take prompt action based on that understanding. This can lead to decreased customer satisfaction and reduced operational efficiency.

[0646] 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.

[0647] In this invention, the server includes means for automatically accumulating historical information acquired from a communication device, means for identifying emotions using a generated AI model based on the historical information and voice data, and means for generating and outputting the emotion identification and workload prediction results in a visible format. This makes it possible to grasp the emotional state of customers in real time and take quick and appropriate countermeasures based on that.

[0648] A "communication device" is a device that manages calls in a call center and has the function of generating, storing, and providing call records and related data.

[0649] "Historical information" refers to record data related to past communications, including call content, number of incoming calls, response rate, and operational rate.

[0650] A "generative AI model" is a model that uses machine learning techniques to learn specific patterns from input data and make predictions about emotions, workload, and other factors.

[0651] "Means of identifying emotions" refers to a technological process that analyzes voice data to identify the emotional state of a customer.

[0652] "Workload prediction results" refer to predicted values ​​that numerically or graphically represent the future workload based on collected historical information.

[0653] "Visual format" refers to a format in which analysis results and predictions are presented in a visually easy-to-understand way, such as in dashboards or reports.

[0654] This invention is a system aimed at improving the efficiency of call center operations and enhancing the quality of customer service. To implement this system, the server, terminals, and users must work together in coordination.

[0655] First, the server automatically collects historical information from the communication device. This historical information includes past call content, response rates, uptime, and voice data from the call. This data is managed using a database management system (e.g., MySQL or PostgreSQL).

[0656] Next, the server uses a generative AI model to identify emotions based on the collected historical information and voice data. Emotion identification utilizes machine learning frameworks (e.g., TensorFlow and PyTorch) and analyzes voice patterns using neural networks. This makes it possible to classify the customer's emotional state into categories such as satisfaction, dissatisfaction, and tension.

[0657] The sentiment identification results and workload prediction results are generated by the server as a visual report. This report is designed to be displayed in graph and dashboard format using data visualization tools (e.g., Tableau or Power BI).

[0658] This allows users to receive visual reports through their devices and use them to make decisions about improving customer service. By using this information to quickly take action, users can improve customer satisfaction.

[0659] As a concrete example, if the server uses its emotion engine to detect customer dissatisfaction during a call, it transmits that information to the terminal in real time and notifies the user. Upon receiving this notification, the user can prepare to respond quickly. For example, by using prompts such as, "Please provide the analysis results for the call where the customer is expressing dissatisfaction," it becomes possible to consider further improvements.

[0660] Thus, the present invention contributes to improving the quality of customer service and increasing the operational efficiency of call centers.

[0661] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0662] Step 1:

[0663] The server collects historical information from communication devices. Inputs include call content, number of incoming calls, response rate, uptime, and voice data. This data is stored in a database. Specifically, the server uses a database management system to access the database and retrieves the necessary data by issuing SQL queries.

[0664] Step 2:

[0665] The server inputs historical information and audio data into a generating AI model to identify emotions. The input is waveform information from the audio data, and the output is the customer's emotional state (e.g., satisfied, dissatisfied, tense). Here, a machine learning library is used to analyze the audio data, and a neural network is used to detect emotional patterns.

[0666] Step 3:

[0667] The server predicts workload based on historical information. It uses historical data such as past utilization rates and response rates as input, and generates predicted values ​​for future workload as output. Specifically, it implements an algorithm for regression analysis and makes predictions by analyzing data trends.

[0668] Step 4:

[0669] The server integrates emotion identification results and workload prediction results to generate a visual report. Emotional states and predicted values ​​are used as input, and a visual dashboard-style report is created as output. This includes specific actions such as creating graphs and charts using data visualization tools.

[0670] Step 5:

[0671] The terminal notifies the user of reports from the server. Based on the report information received as input, it displays the report content on the screen as output. Specifically, the user interface provides pop-up notifications and links to detailed dashboards, allowing the user to access the information immediately.

[0672] Step 6:

[0673] Users refer to reports received via their devices and consider ways to improve customer service. The output is a development of an action plan for improvement. Specific actions involved include analyzing the data in the provided report and prompting the server for necessary countermeasures.

[0674] (Application Example 2)

[0675] 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".

[0676] Balancing the quality of customer service and operational efficiency in call centers is an extremely difficult challenge. In particular, accurately recognizing customers' emotional states and responding promptly is crucial for improving customer satisfaction. However, current systems cannot utilize the context or emotional state of call content, making it difficult to predict workload and accurately assess customer emotions. Therefore, there is a need for a new system that integrates more advanced emotion recognition and workload prediction.

[0677] 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.

[0678] In this invention, the server includes means for automatically accumulating historical data acquired from a call processing unit, means for recognizing the emotional state of a user by analyzing voice information, and means for generating and outputting the predicted workload and emotional state in a visible format. This makes it possible to grasp the customer's emotional state in real time and visualize it together with the workload.

[0679] "Historical data" refers to the collection of information obtained from call processing equipment, such as past call content, inquiry volume, and response rate.

[0680] "Analysis method" refers to specific algorithms and statistical techniques used to predict workload and analyze inquiry trends based on historical data and voice information.

[0681] "Emotion recognition means" refers to devices and technologies that identify the emotional state of customers or users by analyzing voice patterns during a phone call.

[0682] "Workload" refers to the quantity and quality of tasks that a call center must handle, as well as the associated personnel and time requirements.

[0683] "Visual format" refers to a data format that visually represents the analysis results in a way that is easy for humans to understand.

[0684] "Security-related anomalies" refer to suspicious behavior or statements that deviate from normal business operations, detected from the customer's emotional state or the content of their calls.

[0685] "Recommendations for business improvement" refer to specific action plans recommended based on actual data to improve business efficiency and the quality of customer service.

[0686] To implement this invention, the server, terminal, and user each play specific roles in the call center system. The server automatically collects historical data from the call processing unit. This historical data includes information such as past call content, inquiry volume, and response rate. The server uses this data to perform analysis to predict the workload. The server is also equipped with emotion recognition means to analyze voice information and recognize the customer's emotional state. The emotion recognition means uses an AI model to analyze voice patterns and identify different emotional states such as customer satisfaction, dissatisfaction, and tension.

[0687] The server generates predicted workload and emotional states in a visual format and outputs them as a report. This visual information is provided to the user via a terminal. Based on the information displayed on the terminal, the user can quickly take appropriate actions to improve customer service.

[0688] For example, if the emotion engine detects a customer's anxiety during a call, the server immediately notifies the terminal of this information. This information is based, for instance, on the results of an analysis of voice data suggesting that the user is feeling anxious. By referring to this information, the user can provide appropriate follow-up to the customer.

[0689] When using a generative AI model to analyze emotional states, the following prompt can be used: "Please suggest a course of action if anger or fear is detected during a customer call."

[0690] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0691] Step 1:

[0692] The server automatically retrieves historical data from the call processing unit. Inputs include past call content, inquiry volume, and response rate. By aggregating this data, a historical database is generated.

[0693] Step 2:

[0694] The server uses historical data to perform analysis and predict workload. The input is historical data, and the data analysis algorithm calculates query volume trends and peak workload, outputting this as predicted data.

[0695] Step 3:

[0696] The server acquires audio data during a call and analyzes the customer's emotional state using emotion recognition technology. The input is real-time audio data, and by analyzing the audio patterns with a generating AI model, it identifies the customer's emotional state (e.g., satisfaction, dissatisfaction, tension, etc.) and outputs the result as emotion data.

[0697] Step 4:

[0698] The server generates information in a visual format and creates reports based on predictive and sentiment data. It takes predictive and sentiment data as input, integrates this data into graphs and charts, and outputs it as easy-to-understand report data.

[0699] Step 5:

[0700] The terminal provides the user with report data received from the server. The input is report data, which is displayed on the user interface and provided as reference information for the user to make decisions regarding improvements to customer service.

[0701] Step 6:

[0702] Based on the reports displayed on their devices, users decide on specific actions to improve customer service. In this step, users determine what actions they should take based on the reports and then reflect those decisions in their actual interactions with customers.

[0703] 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.

[0704] 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.

[0705] 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.

[0706] 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.

[0707] 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.

[0708] 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.

[0709] 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.

[0710] 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.

[0711] 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."

[0712] 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.

[0713] 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.

[0714] 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.

[0715] 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.

[0716] 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.

[0717] 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.

[0718] 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.

[0719] 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.

[0720] 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.

[0721] 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.

[0722] 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.

[0723] 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.

[0724] The following is further disclosed regarding the embodiments described above.

[0725] (Claim 1)

[0726] A means for automatically accumulating historical information obtained from a call processing device,

[0727] A means for predicting workload using a specific analytical model based on the aforementioned historical information,

[0728] A means for generating and outputting the predicted workload results in a visible format,

[0729] The means of providing the aforementioned visible information to the user,

[0730] A system that includes this.

[0731] (Claim 2)

[0732] The system according to claim 1, wherein the analysis model analyzes the trend of the number of inquiries over a specific period based on the historical information.

[0733] (Claim 3)

[0734] The system according to claim 1, wherein the information in the visible format includes recommendations and advice for business improvement based on performance data.

[0735] "Example 1"

[0736] (Claim 1)

[0737] A means for automatically formatting past business information collected from communication processing equipment,

[0738] A means for analyzing workload using a machine learning model based on the aforementioned formatted business information,

[0739] A means for generating and providing the results of the aforementioned workload analysis in a visualized format,

[0740] A means for presenting the output of the visualized format to the user,

[0741] A system that includes this.

[0742] (Claim 2)

[0743] The system according to claim 1, wherein the machine learning model evaluates patterns of the number of inquiries within a period based on the business information.

[0744] (Claim 3)

[0745] The system according to claim 1, wherein the output of the visualized format includes recommendations for improvement measures based on past business data.

[0746] "Application Example 1"

[0747] (Claim 1)

[0748] A means for automatically accumulating recorded information acquired from a detection device,

[0749] A means for predicting the workload using a specific analytical model based on the aforementioned recorded information,

[0750] A means for generating and outputting the predicted workload results in a visual format,

[0751] Means for providing the aforementioned visual information to the operating entity,

[0752] Means for notifying the visual device used by the operating entity in real time,

[0753] A system that includes this.

[0754] (Claim 2)

[0755] The system according to claim 1, wherein the analysis model examines the trend of the number of requests over a specific period based on the recorded information.

[0756] (Claim 3)

[0757] The system according to claim 1, wherein the visual information includes recommendations and advice for work improvement based on performance data.

[0758] "Example 2 of combining an emotion engine"

[0759] (Claim 1)

[0760] A means for automatically accumulating historical information acquired from a communication device,

[0761] A means for identifying emotions by utilizing a generated AI model based on the aforementioned historical information and voice data,

[0762] A means for generating and outputting the aforementioned emotion recognition and workload prediction results in a visible format,

[0763] The means of providing the aforementioned visible information to the user via a terminal,

[0764] A system that includes this.

[0765] (Claim 2)

[0766] The system according to claim 1, wherein the analysis model analyzes the trend of the number of communications over a specific period based on the historical information and presents countermeasures based on emotional state in the form of prompt messages.

[0767] (Claim 3)

[0768] The system according to claim 1, wherein the information in the visible form includes recommended advice for business improvement based on sentiment analysis data.

[0769] "Application example 2 when combining with an emotional engine"

[0770] (Claim 1)

[0771] A means for automatically accumulating historical data acquired from a call processing unit,

[0772] A means for predicting workload using a specific analytical method based on the aforementioned historical data,

[0773] An emotion recognition means that analyzes voice information to recognize the user's emotional state,

[0774] A means for generating and outputting the predicted workload and emotional state in a visible format,

[0775] Means for providing the aforementioned visible information to the user,

[0776] A system that includes this.

[0777] (Claim 2)

[0778] The system according to claim 1, wherein the analysis method analyzes the trend of inquiry volume over a specific period based on the historical data and detects security-related anomalies in emotional states.

[0779] (Claim 3)

[0780] The system according to claim 1, wherein the information in the visible format includes recommendations for business improvement based on performance data and warning information regarding suspicious behavior. [Explanation of Symbols]

[0781] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for automatically accumulating historical information obtained from a call processing device, A means for predicting workload using a specific analytical model based on the aforementioned historical information, A means for generating and outputting the predicted workload results in a visible format, The means of providing the aforementioned visible information to the user, A system that includes this.

2. The system according to claim 1, wherein the analysis model analyzes the trend of the number of inquiries over a specific period based on the historical information.

3. The system according to claim 1, wherein the information in the visible format includes recommendations and advice for business improvement based on performance data.

Images