system

Abstract

We provide the system. [Solution] A means for collecting and integrating past communication history information and external condition information, Based on the aforementioned integrated information, a means for making highly accurate predictions about future communications, A means for optimizing the allocation of human resources between multiple locations using the aforementioned communication forecast, A means for automatically sending instructions to each location based on the optimized arrangement, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern communication processing bases, the prediction of future communication demands based on communication history information and external condition information has low accuracy and becomes an obstacle to efficient operation. Also, since the appropriate allocation instructions of human resources at multiple bases are manually performed, they lack speed and flexibility, resulting in waste of resources and deterioration of the quality of customer service. Furthermore, it is difficult to respond immediately to real-time demand fluctuations, while the burden on managers increases. It is required to improve such a situation and realize highly efficient and highly accurate operation.

Means for Solving the Problems

[0005] The present invention provides a system that includes means for collecting and integrating past communication history information and external condition information, means for making highly accurate predictions of future communications based on said information, means for optimizing the allocation of human resources at multiple locations using the communication predictions, and means for automatically sending instructions to each location based on the optimized allocation. Furthermore, by providing means for updating allocation instructions in real time based on the execution status of the instructions, and means for displaying the results of the predictions and allocation optimization on an operating terminal to provide decision-making support to the administrator, the efficiency and effectiveness of communication base operations are improved.

[0006] "Communication history information" refers to data related to communications recorded in the past, including indicators such as the number of incoming calls, response time, and customer service results.

[0007] "External condition information" refers to information about external factors that affect communication demand, such as weather, holidays, and events.

[0008] "Communication forecasting" is the process of predicting future communication demand based on past communication history information and external condition information.

[0009] "Human resource allocation" refers to the process of appropriately allocating and assigning the personnel necessary to perform a task.

[0010] "Optimization" refers to methods and procedures for efficiently allocating limited resources to achieve maximum effectiveness.

[0011] "Real-time" refers to the act of responding to or processing an event immediately as it occurs.

[0012] An "operating terminal" is a device used to operate a system, and usually refers to a computer or monitor.

[0013] "Decision-making support" refers to the act of assisting managers in making optimal decisions by providing information and presenting analytical results. [Brief explanation of the drawing]

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

MODE FOR CARRYING OUT THE INVENTION

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

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

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

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

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

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

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

[0022] [First Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0035] This invention is a system aimed at improving the operational efficiency of call centers and similar communication processing facilities. This system uses communication history information and external condition information to predict future communications and automates the optimal allocation of human resources.

[0036] The server first collects communication history information and external condition information, integrates it, and stores it in a database. This data is analyzed using machine learning algorithms and used to predict future communication demand with high accuracy. Based on the communication demand forecast results obtained using the prediction model, the server calculates the optimal allocation of human resources needed at each location.

[0037] Subsequently, the server sends optimized staffing instructions to terminals at each location. Based on the instructions received from the server, the terminals update operator assignments and shift schedules. This ensures that each location operates efficiently and is ready to meet predicted communication demands.

[0038] For example, if a server predicts an increase in traffic during a specific holiday season, it can automatically send instructions to terminals to increase the number of personnel assigned to that period. Furthermore, if extreme weather events occur as external condition information, the system can reflect the resulting changes in predicted demand and implement countermeasures quickly.

[0039] Users (administrators) can refer to the forecast results and staffing recommendations displayed on the terminal, and make further detailed settings and manual adjustments. This enables flexible operation in response to the situation that arises, improving service quality and reducing costs.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The server collects communication history information and external condition information. This process periodically retrieves data from terminals at each location and integrates it into a database. The data collected includes past call volume, response time, business event information, and weather data.

[0043] Step 2:

[0044] The server preprocesses the collected raw data into a format that can be analyzed. Specifically, it performs data formatting such as imputing missing values, detecting and correcting outliers, and converting categorical data into numerical values.

[0045] Step 3:

[0046] The server trains a communication prediction model using machine learning algorithms based on the formatted data. This model is designed to predict future communication demand and utilizes past patterns and external conditions as input.

[0047] Step 4:

[0048] The server uses a trained communication prediction model to forecast future communication demand. The forecast results, such as the number of incoming calls per time period and the number of personnel required to handle them, are displayed on a management dashboard.

[0049] Step 5:

[0050] The server optimizes staffing based on the prediction results. This process uses a resource allocation algorithm to calculate staffing plans for each location and formulate appropriate shift assignments.

[0051] Step 6:

[0052] The server sends staffing instructions generated based on the optimization results to terminals at each location. This allows the terminals at each location to automatically adjust operator shifts and assign additional staff as needed.

[0053] Step 7:

[0054] Users can view forecast data and staffing instructions provided by the server on their terminals and make manual adjustments as needed. This enables optimal operations based on forecasts.

[0055] (Example 1)

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

[0057] Call centers and communication processing centers require the optimal allocation of human resources in response to fluctuations in communication volume. However, existing systems lacked real-time capabilities and insufficient accuracy in demand forecasting. As a result, problems such as increased costs due to surpluses or shortages of human resources and a decline in service quality occurred. Furthermore, many of these issues relied on manual responses, placing a burden on administrators.

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

[0059] In this invention, the server includes means for acquiring past communication history information and external condition information, integrating and storing it in a database; means for predicting future communication demand with high accuracy using a machine learning algorithm based on the integrated information; and means for optimizing the allocation of human resources between multiple locations using operations research techniques based on the communication demand forecast. This enables efficient allocation of human resources in real time and the provision of information to support administrator decision-making.

[0060] "Communication history information" refers to a history of past communication data, including detailed data on communication time, call content, response time, and so on.

[0061] "External conditions information" refers to data related to factors that affect communication demand, including external factors such as weather information and economic indicators.

[0062] A "database" is an information management system used to organize and store acquired information, and refers to a centralized location where information used for later analysis and retrieval is aggregated.

[0063] A "machine learning algorithm" is a computational method for analyzing data, finding patterns, and making predictions and judgments; it is a technology that builds models based on empirical data.

[0064] "Communication demand forecasting" refers to the estimation of future communication demands, which is calculated using the aforementioned machine learning algorithms.

[0065] Operations research techniques are methods that use mathematical approaches to optimize organizational management and are techniques used to efficiently allocate human resources.

[0066] An "output terminal" refers to a device or interface that displays information provided by a system, and is used by an administrator as an operating terminal.

[0067] To implement this invention, the server first collects communication history information and external condition information. Communication history information includes past communication times, call content, and response times, while external condition information includes weather information and economic indicators. This data collection is performed using Python's requests library or an ETL tool (e.g., Apache® NiFi). The collected information is integrated and stored in a database management system (e.g., PostgreSQL).

[0068] Next, the server uses machine learning algorithms to predict future communication demand with high accuracy. In this process, historical data is used as training data, and a predictive model is generated using libraries such as Scikit-learn and TENSORFLOW®. Based on this predictive model, the server estimates how communication demand will fluctuate and uses this information to optimize human resources.

[0069] Optimization employs operations research techniques to ensure efficient allocation of human resources. This step utilizes optimization libraries such as Opalytics and Google® OR-Tools to efficiently allocate human resources.

[0070] Next, the optimized deployment instructions are automatically distributed to terminals at each location in a data format (e.g., JSON). The HTTP protocol is used for this distribution.

[0071] The terminal functions as an interface for receiving instructions sent from the server and updating operator shift schedules based on those instructions. The terminal displays predicted communication demand and optimized staffing in real time to support administrator decision-making.

[0072] Users, or administrators, can refer to the information displayed on the terminal and manually adjust settings as needed. This allows for flexible responses to specific events and fluctuating circumstances.

[0073] For example, if the server predicts high communication demand on a particular day, a deployment instruction is automatically sent to the terminal to increase the number of staff on that day compared to normal. This allows users to deploy staff efficiently, leading to improved service quality.

[0074] An example of a prompt message would be: "Please explain how to predict future communication demand using communication history information and external condition information. Also, please provide a model for the optimal allocation of human resources based on that."

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

[0076] Step 1:

[0077] The server retrieves historical communication history information and external condition information from each communication point. Communication history information includes communication time, call content, and response time, while external condition information includes weather and economic indicators. This information is collected via an API using the Python requests library. The collected data is preprocessed for integration and stored in a database. The input here is raw data from various APIs, and the output is a preprocessed dataset.

[0078] Step 2:

[0079] The server retrieves preprocessed datasets from an integrated database and performs analysis using machine learning algorithms. Specifically, it uses Scikit-learn and TensorFlow to create models that predict future communication demand from historical data. It cleans the data and applies classification and regression algorithms to make predictions. In this step, the input is a preprocessed dataset, and the output is a forecast of future communication demand.

[0080] Step 3:

[0081] The server calculates the optimal allocation of human resources using operations research techniques based on predicted communication demand. Opalytics and Google OR-Tools are used to solve the human resource allocation problem as an optimization issue. Resource allocation and scheduling are performed to ensure efficient allocation of human resources at each location. The input is the communication demand forecast, and the output is the optimized human resource allocation plan.

[0082] Step 4:

[0083] The server converts the calculated optimized placement plan into a data format (e.g., JSON) and automatically sends it to terminals at each location using the HTTP protocol. The terminals parse this data and update operator schedules and placements. The input here is the optimized placement plan, and the output is the updated actual operational schedule at each location.

[0084] Step 5:

[0085] The terminal updates the operator's shift schedule in real time based on placement instructions received from the server. The updated information is displayed in the user interface, providing a foundation for administrators and relevant parties to manage the schedule. The input is placement instructions from the server, and the output is visualized schedule information.

[0086] Step 6:

[0087] The user (administrator) makes additional settings or manual adjustments as needed based on the information displayed on the terminal. For example, if an unexpected event occurs, measures can be taken to prevent it. In this step, the input is the visualized information on the terminal, and the output is the adjusted operation.

[0088] (Application Example 1)

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

[0090] Modern business locations require real-time, optimal resource allocation based on historical trends and environmental conditions. However, conventional systems lack the mechanisms to efficiently analyze these factors, accurately predict future operational states, and automatically instruct optimal resource allocation based on those predictions. As a result, in many cases, there is a shortage or surplus of human resources, leading to challenges such as decreased operational efficiency and deterioration of service quality.

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

[0092] In this invention, the server includes means for collecting and integrating past trend information and environmental condition information, means for making highly accurate predictions of future operating conditions based on the integrated information, and means for optimizing resource allocation between multiple locations using the operating condition predictions. This enables optimal resource allocation in real time and efficient business operations.

[0093] "Trend information" refers to data about past activities and events, and is used to analyze specific trends and patterns.

[0094] "Environmental conditions information" refers to data about the external environment, including relevant factors such as weather conditions and social events.

[0095] "Operating status forecasting" refers to the process of predicting the future operating status of systems and business locations, and supports decision-making for efficient operations.

[0096] "Resource allocation" refers to the process of optimally distributing available resources across multiple locations, and is an important method for improving operational efficiency.

[0097] A "control device" refers to hardware or software used to manage the operation of a system or device, and is responsible for executing optimized instructions.

[0098] An "operating device" refers to a device that provides an interface used by the user to control the system or to view information.

[0099] The system for implementing this invention mainly consists of a server, a control device, and an operating device. The server has the function of collecting and integrating historical trend information and environmental condition information. Specifically, it collects data from sensors and external databases, integrates them, and stores them in an SQL database.

[0100] The server uses machine learning software such as TensorFlow to predict its operating state based on stored information. Based on this prediction, the generative AI model calculates the optimal resource allocation and generates instructions for each control unit. The optimized instructions are automatically sent to the control units, enabling automated operation based on those instructions.

[0101] The control system displays information from the server to the user in real time, supporting decision-making. This allows users to manage resources under optimal conditions and establish efficient business operations. For example, by predicting the occurrence of security events during a festival and deploying the appropriate number of security guards, it is possible to ensure adequate security without excess or deficiency.

[0102] An example of a prompt message is: "Based on the patterns of security events during the festival period, use data from the past three years to optimize staffing for next week. As a requirement, designate a specific area during the summer as a monitoring priority area and consider deploying at least 20 operators." This prompt message enables users to effectively utilize the system and support their decision-making.

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

[0104] Step 1:

[0105] The server collects historical trend information and environmental condition information from sensors and external databases via the network. The input to this process is real-time data and historical log data, and the output is an integrated dataset. The server stores this data in an SQL database, making it available for subsequent analysis.

[0106] Step 2:

[0107] The server uses TensorFlow to predict its operational status based on the stored dataset. The integrated dataset collected in the previous step is used as input and analyzed by a generative AI model. The output is a prediction of future operational status. This allows the server to estimate its operational status for specific periods and conditions.

[0108] Step 3:

[0109] The server executes a process to optimize resource allocation based on the prediction results. The input is the result of the operational status prediction, and the output is a specific resource allocation instruction to the control unit. The generated instructions are processed in real time.

[0110] Step 4:

[0111] The server sends the generated instructions to the control unit. Based on these instructions, the control unit initiates automated processes as needed. The input is the resource allocation instructions obtained in the previous step, and the output is the status update of the control unit.

[0112] Step 5:

[0113] Users can check the server's operational status predictions and resource allocation results in real time via the control device. Input is evaluation data sent from the server, and output is notifications and decision support information for the user. Based on this, users can adjust settings as needed, generate prompt statements as required, and issue additional instructions to the system.

[0114] 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.

[0115] This invention provides a system for call centers and similar communication processing centers to perform communication prediction and optimal allocation of human resources based on communication history information and external condition information. Furthermore, this system incorporates an emotion engine that recognizes user emotions and utilizes that information to achieve more advanced prediction and optimization.

[0116] The server first collects and integrates communication history information and external condition information, and stores it in a database. This information includes past communication activity data, business event information, weather information, etc. Based on this information, the server uses machine learning algorithms to predict future communication demand.

[0117] Next, the server operates the emotion engine. The emotion engine analyzes the interaction between the user and the operator and extracts emotion data. This emotion data is calculated based on the operator's voice tone and customer feedback. The server then incorporates this emotion data into the communication prediction model to improve the accuracy of the predictions.

[0118] Subsequently, the server optimizes the allocation of human resources based on the prediction results and sentiment data. For example, if the sentiment engine detects a high level of negative sentiment, it adjusts the allocation strategy, such as assigning experienced operators to specific time slots. These allocation instructions are sent to terminals at each location, and the shift schedule is automatically updated.

[0119] Users (administrators) can review the communication forecast data, sentiment analysis results, and staffing suggestions displayed on the terminal and make manual adjustments as needed. This allows administrators to operate with consideration not only for numerical data but also for the emotions of customers and operators, contributing to improved service quality.

[0120] The following describes the processing flow.

[0121] Step 1:

[0122] The server periodically collects communication history information and external condition information from terminals at the base station and stores it in an integrated database. The information collected includes past call volume, operator response time, customer satisfaction data, sales campaign information, and external factors such as season and weather.

[0123] Step 2:

[0124] The server uses an emotion engine to analyze the emotions of operators and customers during calls in real time. This emotion data is extracted using speech recognition and natural language processing technologies and quantified as positive, negative, or neutral emotions.

[0125] Step 3:

[0126] The server integrates communication history information, external condition information, and sentiment data, and applies machine learning algorithms to predict future communication demand. The resulting predictions are generated as data indicating highly accurate estimates of incoming call volume and the number of operators needed.

[0127] Step 4:

[0128] The server optimizes the allocation of human resources at each location based on the obtained communication prediction data and sentiment data. For example, it decides to assign experienced operators during times when high stress is predicted.

[0129] Step 5:

[0130] The server transmits the results of the optimization of human resource allocation to terminals at each location. Based on these optimization instructions, the terminals automatically adjust operator shifts and assignments.

[0131] Step 6:

[0132] The user (administrator) can review the communication forecast, sentiment analysis results, and deployment instructions displayed on the terminal, and make manual adjustments as needed. This allows the user to incorporate their own judgment as an administrator, in addition to the system's automated processes.

[0133] (Example 2)

[0134] 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".

[0135] Conventional communication forecasting systems only consider past communication history and external conditions, making it difficult to improve the accuracy of predictions that include emotional factors and optimize human resource allocation. Furthermore, the limited real-time updates of deployment instructions and support for administrator decision-making can negatively impact service quality.

[0136] 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.

[0137] In this invention, the server includes means for collecting and integrating past communication history information and external condition information, means for making highly accurate predictions of future communications using machine learning algorithms, and means for analyzing user emotions and extracting emotional data. This enables communication prediction and optimization of human resource allocation that take emotional factors into consideration.

[0138] "Communication history information" refers to data about communication activities that have occurred in the past, including information such as the date and time, call duration, recipient of the call, and content of the call.

[0139] "External condition information" refers to data on external factors that affect the communication environment and conditions, such as weather information, event information, and economic indicators.

[0140] A "machine learning algorithm" is a method for learning patterns in data to make predictions or classifications, and includes, for example, regression analysis and cluster analysis.

[0141] "Communication forecasting" is the process of estimating future communication volume and patterns based on past data and current conditions.

[0142] "Emotional data" refers to information that expresses the emotional state of users and operators as numerical values ​​or categories, and is extracted based on voice tone and text analysis.

[0143] "Human resource allocation" is the process of optimally allocating personnel and skills in order to perform tasks effectively and efficiently.

[0144] "Real-time" means reacting or processing immediately without delay, referring to a state where information is updated instantaneously.

[0145] The system for implementing this invention aims to optimize data processing and human resource allocation for efficient operation at communication base stations. The specific implementation method is described below.

[0146] The server first collects communication history information and external condition information. This includes past communication activity data, weather information, and economic indicators, which are obtained through APIs and database queries. The collected information is integrated and stored in a database. In this process, relational database management systems such as MySQL (registered trademark) are often used as the database.

[0147] Next, the server uses machine learning algorithms based on the collected data to predict communication trends. This often involves using Python libraries such as Scikit-learn, and typically includes linear regression and time series analysis. This allows for highly accurate predictions of future communication demand.

[0148] Furthermore, the server operates an emotion engine to extract emotional data from user-operator interactions. This involves using tools such as voice analysis to analyze user emotions from voice tone and text-based feedback. This data is then incorporated into communication predictions, enabling more accurate human resource allocation.

[0149] The terminal receives communication forecast data and human resource allocation instructions sent from the server, and automatically updates the shift schedule based on this information. The terminal has a real-time data update function and always maintains the latest allocation information.

[0150] Users, specifically administrators, review this information via their terminals and manually adjust schedules as needed. This system allows administrators to achieve efficient staffing and high-quality service delivery while considering the feelings of both customers and operators.

[0151] As a concrete example, the server can assign experienced operators to appropriate time slots based on customer sentiment data during peak periods such as the year-end and New Year holidays. Another example of a prompt for the generating AI model could be the question, "What are the best practices for developing a model that incorporates sentiment data into communication demand forecasting?"

[0152] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0153] Step 1:

[0154] The server collects communication history information and external condition information. Inputs include historical communication activity data and weather information collected using APIs and database queries. The collected data is integrated into the server and recorded in a database such as MySQL. The output is this integrated dataset.

[0155] Step 2:

[0156] The server builds a machine learning model based on integrated data to predict communication demand. The input is the dataset created in the previous step. The server uses the Python Scikit-learn library to analyze the data through methods such as linear regression. The output is a prediction of future communication demand.

[0157] Step 3:

[0158] The server operates an emotion engine to analyze user-operator interactions and extract emotion data. Inputs include voice data and text feedback. Sentiment analysis is performed using tools such as Google Cloud's Natural Language API. Output is quantified emotion data.

[0159] Step 4:

[0160] The server optimizes human resource allocation by combining communication prediction results and sentiment data. The inputs are prediction values ​​and sentiment data. The server considers operator skills and availability to generate the optimal allocation strategy. The output is the optimized allocation instruction.

[0161] Step 5:

[0162] The terminal receives placement instructions from the server and automatically updates the shift schedule. The input is the placement strategy. The terminal adjusts each operator's working hours based on these instructions. The output is the updated shift schedule.

[0163] Step 6:

[0164] The user (administrator) reviews the communication forecast and sentiment analysis results displayed on the terminal and makes manual adjustments as needed. The input is the displayed data. The administrator reflects the feasible changes in the system. The output is the final shift schedule and deployment strategy.

[0165] (Application Example 2)

[0166] 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".

[0167] In recent years, communication processing centers have been required to effectively allocate limited human resources in order to respond quickly and appropriately to diverse customer needs. However, conventional systems, which allocate human resources based solely on communication forecasts, could not take into account emotional factors that could not be addressed, resulting in inconsistent response quality. Furthermore, it was difficult to respond flexibly to real-time changes in circumstances. Solving these problems is the objective of the present invention.

[0168] 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.

[0169] In this invention, the server includes means for collecting and integrating past communication history information and external condition information; means for making highly accurate predictions of future communications based on the integrated information; and means for optimizing the allocation of human resources between multiple locations based on an analysis combining the communication predictions and user sentiment data. This makes it possible to optimize the allocation of human resources considering not only communication predictions but also customer sentiment data, thereby improving the uniformity and flexibility of customer service.

[0170] "Communication history information" refers to data related to past communication activities, including the date and time of call initiation and reception, duration, and connection status.

[0171] "External conditions information" refers to data about external factors that may affect communication activities, and includes information such as weather conditions, social events, and the situation during a specific period.

[0172] "User sentiment data" refers to data that indicates a user's emotional state, and includes information such as voice tone and sentiment identification results based on text analysis.

[0173] "Human resource allocation" refers to the process of assigning and placing available personnel in the most suitable work positions, taking various factors into consideration and aiming to place the right personnel in the right tasks.

[0174] A "security response operator" refers to a person with the technical skills to respond to security issues and incidents at a communications processing center.

[0175] An "operating terminal" refers to a digital device used by users to view data or issue instructions, and typically includes a screen and input devices.

[0176] "Decision support" refers to the information and tools provided to users to make better decisions, supporting decision-making through data analysis, prediction, simulation, and other means.

[0177] The system to realize this application example will have the following configuration: The server first collects past communication history information and external condition information, and integrates this data. This allows information that takes into account past communication patterns and external factors such as weather and events to be stored in the database. Subsequently, a machine learning algorithm is used to predict future communication demand from this integrated information.

[0178] Next, the server operates an emotion engine to analyze user emotion data in real time. Using speech recognition technology, it extracts emotions from the tone of the user's voice during communication and acquires this as emotion data. This data is incorporated into a communication prediction model, enabling more accurate optimization of human resource allocation.

[0179] Furthermore, the server develops an optimal operator deployment strategy based on predicted communication demand and sentiment analysis results. This deployment plan is displayed on the operating terminal, providing decision-making support to administrators and security response operators. Administrators can review this plan and make modifications as needed to achieve more appropriate staffing.

[0180] For example, if the emotion engine detects a high level of user anxiety when severe weather is predicted in a certain area, it can automatically adjust the shift schedule to assign experienced operators to that time slot, enabling a quick response.

[0181] An example of a prompt message to input to a generative AI model is: "Based on the user's voice data, analyze the emotions expressed in this call and propose an appropriate operator deployment plan accordingly."

[0182] In this way, servers can leverage data obtained from both communication prediction and sentiment analysis to improve the quality of security responses and increase user trust.

[0183] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0184] Step 1:

[0185] The server collects historical communication history information and external condition information. Specifically, it retrieves past call records, connection status, weather, and event information from the database and integrates them. The input is communication history information and external condition information, and the output is integrated information data. This data forms the basis for the next prediction step.

[0186] Step 2:

[0187] The server uses machine learning algorithms to predict communication based on integrated information. The input is the integrated information data obtained in the previous step, and the data calculations performed are inputting data into the prediction model and calculating output prediction values. The output is prediction data indicating future communication demand. This prediction data is used to optimize human resource allocation.

[0188] Step 3:

[0189] The server analyzes emotions in real time during communication with the user, using speech recognition technology to convert speech data into emotion data. The input is the user's speech data, and the output is the emotion data obtained through analysis. The data processing performed here involves analyzing the tone and speed of the voice and calculating the emotional state using an emotion engine.

[0190] Step 4:

[0191] The server combines communication prediction data and sentiment data to determine the optimal placement of operators. The inputs are communication prediction data and sentiment data, and the output is placement strategy data. Data calculations involve inputting data into a placement model and formulating an output placement strategy. This optimizes appropriate personnel allocation across multiple locations.

[0192] Step 5:

[0193] The terminal displays an optimized deployment strategy to administrators and security response operators. The input is deployment strategy data, and the output is visualized information. Specifically, the terminal screen displays activity and personnel deployment suggestions for each location, allowing administrators and operators to make decisions based on this information.

[0194] Step 6:

[0195] Users modify the deployment strategy as needed via the control terminal, and the updated instructions are sent to the server in real time. Input is the modification instructions from the administrator, and output is the updated deployment data. This operation enables flexible personnel deployment tailored to on-site conditions.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] [Second Embodiment]

[0200] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0201] 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.

[0202] 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).

[0203] 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.

[0204] 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.

[0205] 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).

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] 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.

[0211] 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".

[0212] This invention is a system aimed at improving the operational efficiency of call centers and similar communication processing facilities. This system uses communication history information and external condition information to predict future communications and automates the optimal allocation of human resources.

[0213] The server first collects communication history information and external condition information, integrates it, and stores it in a database. This data is analyzed using machine learning algorithms and used to predict future communication demand with high accuracy. Based on the communication demand forecast results obtained using the prediction model, the server calculates the optimal allocation of human resources needed at each location.

[0214] Subsequently, the server sends optimized staffing instructions to terminals at each location. Based on the instructions received from the server, the terminals update operator assignments and shift schedules. This ensures that each location operates efficiently and is ready to meet predicted communication demands.

[0215] For example, if a server predicts an increase in traffic during a specific holiday season, it can automatically send instructions to terminals to increase the number of personnel assigned to that period. Furthermore, if extreme weather events occur as external condition information, the system can reflect the resulting changes in predicted demand and implement countermeasures quickly.

[0216] Users (administrators) can refer to the forecast results and staffing recommendations displayed on the terminal, and make further detailed settings and manual adjustments. This enables flexible operation in response to the situation that arises, improving service quality and reducing costs.

[0217] The following describes the processing flow.

[0218] Step 1:

[0219] The server collects communication history information and external condition information. This process periodically retrieves data from terminals at each location and integrates it into a database. The data collected includes past call volume, response time, business event information, and weather data.

[0220] Step 2:

[0221] The server preprocesses the collected raw data into a format that can be analyzed. Specifically, it performs data formatting such as imputing missing values, detecting and correcting outliers, and converting categorical data into numerical values.

[0222] Step 3:

[0223] The server trains a communication prediction model using machine learning algorithms based on the formatted data. This model is designed to predict future communication demand and utilizes past patterns and external conditions as input.

[0224] Step 4:

[0225] The server uses a trained communication prediction model to forecast future communication demand. The forecast results, such as the number of incoming calls per time period and the number of personnel required to handle them, are displayed on a management dashboard.

[0226] Step 5:

[0227] The server optimizes staffing based on the prediction results. This process uses a resource allocation algorithm to calculate staffing plans for each location and formulate appropriate shift assignments.

[0228] Step 6:

[0229] The server sends staffing instructions generated based on the optimization results to terminals at each location. This allows the terminals at each location to automatically adjust operator shifts and assign additional staff as needed.

[0230] Step 7:

[0231] Users can view forecast data and staffing instructions provided by the server on their terminals and make manual adjustments as needed. This enables optimal operations based on forecasts.

[0232] (Example 1)

[0233] 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."

[0234] Call centers and communication processing centers require the optimal allocation of human resources in response to fluctuations in communication volume. However, existing systems lacked real-time capabilities and insufficient accuracy in demand forecasting. As a result, problems such as increased costs due to surpluses or shortages of human resources and a decline in service quality occurred. Furthermore, many of these issues relied on manual responses, placing a burden on administrators.

[0235] 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.

[0236] In this invention, the server includes means for acquiring past communication history information and external condition information, integrating and storing it in a database; means for predicting future communication demand with high accuracy using a machine learning algorithm based on the integrated information; and means for optimizing the allocation of human resources between multiple locations using operations research techniques based on the communication demand forecast. This enables efficient allocation of human resources in real time and the provision of information to support administrator decision-making.

[0237] "Communication history information" refers to a history of past communication data, including detailed data on communication time, call content, response time, and so on.

[0238] "External conditions information" refers to data related to factors that affect communication demand, including external factors such as weather information and economic indicators.

[0239] A "database" is an information management system used to organize and store acquired information, and refers to a centralized location where information used for later analysis and retrieval is aggregated.

[0240] A "machine learning algorithm" is a computational method for analyzing data, finding patterns, and making predictions and judgments; it is a technology that builds models based on empirical data.

[0241] "Communication demand forecasting" refers to the estimation of future communication demands, which is calculated using the aforementioned machine learning algorithms.

[0242] Operations research techniques are methods that use mathematical approaches to optimize organizational management and are techniques used to efficiently allocate human resources.

[0243] An "output terminal" refers to a device or interface that displays information provided by a system, and is used by an administrator as an operating terminal.

[0244] To implement this invention, the server first collects communication history information and external condition information. Communication history information includes past communication times, call content, and response times, while external condition information includes weather information and economic indicators. This data collection is performed using Python's requests library or an ETL tool (e.g., Apache NiFi). The collected information is integrated and stored in a database management system (e.g., PostgreSQL).

[0245] Next, the server uses machine learning algorithms to predict future communication demand with high accuracy. In this process, historical data is used as training data, and a predictive model is generated using libraries such as Scikit-learn and TensorFlow. Based on this predictive model, the server estimates how communication demand will fluctuate and uses this information to optimize human resources.

[0246] Optimization employs operations research techniques to ensure efficient allocation of human resources. This step utilizes optimization libraries such as Opalytics and Google OR-Tools to efficiently allocate human resources.

[0247] Next, the optimized deployment instructions are automatically distributed to terminals at each location in a data format (e.g., JSON). The HTTP protocol is used for this distribution.

[0248] The terminal functions as an interface for receiving instructions sent from the server and updating operator shift schedules based on those instructions. The terminal displays predicted communication demand and optimized staffing in real time to support administrator decision-making.

[0249] Users, or administrators, can refer to the information displayed on the terminal and manually adjust settings as needed. This allows for flexible responses to specific events and fluctuating circumstances.

[0250] For example, if the server predicts high communication demand on a particular day, a deployment instruction is automatically sent to the terminal to increase the number of staff on that day compared to normal. This allows users to deploy staff efficiently, leading to improved service quality.

[0251] An example of a prompt message would be: "Please explain how to predict future communication demand using communication history information and external condition information. Also, please provide a model for the optimal allocation of human resources based on that."

[0252] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0253] Step 1:

[0254] The server retrieves historical communication history information and external condition information from each communication point. Communication history information includes communication time, call content, and response time, while external condition information includes weather and economic indicators. This information is collected via an API using the Python requests library. The collected data is preprocessed for integration and stored in a database. The input here is raw data from various APIs, and the output is a preprocessed dataset.

[0255] Step 2:

[0256] The server retrieves preprocessed datasets from an integrated database and performs analysis using machine learning algorithms. Specifically, it uses Scikit-learn and TensorFlow to create models that predict future communication demand from historical data. It cleans the data and applies classification and regression algorithms to make predictions. In this step, the input is a preprocessed dataset, and the output is a forecast of future communication demand.

[0257] Step 3:

[0258] The server calculates the optimal allocation of human resources using operations research techniques based on predicted communication demand. Opalytics and Google OR-Tools are used to solve the human resource allocation problem as an optimization issue. Resource allocation and scheduling are performed to ensure efficient allocation of human resources at each location. The input is the communication demand forecast, and the output is the optimized human resource allocation plan.

[0259] Step 4:

[0260] The server converts the calculated optimized placement plan into a data format (e.g., JSON) and automatically sends it to terminals at each location using the HTTP protocol. The terminals parse this data and update operator schedules and placements. The input here is the optimized placement plan, and the output is the updated actual operational schedule at each location.

[0261] Step 5:

[0262] The terminal updates the operator's shift schedule in real time based on placement instructions received from the server. The updated information is displayed in the user interface, providing a foundation for administrators and relevant parties to manage the schedule. The input is placement instructions from the server, and the output is visualized schedule information.

[0263] Step 6:

[0264] The user (administrator) makes additional settings or manual adjustments as needed based on the information displayed on the terminal. For example, if an unexpected event occurs, measures can be taken to prevent it. In this step, the input is the visualized information on the terminal, and the output is the adjusted operation.

[0265] (Application Example 1)

[0266] 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."

[0267] Modern business locations require real-time, optimal resource allocation based on historical trends and environmental conditions. However, conventional systems lack the mechanisms to efficiently analyze these factors, accurately predict future operational states, and automatically instruct optimal resource allocation based on those predictions. As a result, in many cases, there is a shortage or surplus of human resources, leading to challenges such as decreased operational efficiency and deterioration of service quality.

[0268] 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.

[0269] In this invention, the server includes means for collecting and integrating past trend information and environmental condition information, means for making highly accurate predictions of future operating conditions based on the integrated information, and means for optimizing resource allocation between multiple locations using the operating condition predictions. This enables optimal resource allocation in real time and efficient business operations.

[0270] "Trend information" refers to data about past activities and events, and is used to analyze specific trends and patterns.

[0271] "Environmental conditions information" refers to data about the external environment, including relevant factors such as weather conditions and social events.

[0272] "Operating status forecasting" refers to the process of predicting the future operating status of systems and business locations, and supports decision-making for efficient operations.

[0273] "Resource allocation" refers to the process of optimally distributing available resources across multiple locations, and is an important method for improving operational efficiency.

[0274] A "control device" refers to hardware or software used to manage the operation of a system or device, and is responsible for executing optimized instructions.

[0275] An "operating device" refers to a device that provides an interface used by the user to control the system or to view information.

[0276] The system for implementing this invention mainly consists of a server, a control device, and an operating device. The server has the function of collecting and integrating historical trend information and environmental condition information. Specifically, it collects data from sensors and external databases, integrates them, and stores them in an SQL database.

[0277] The server uses machine learning software such as TensorFlow to predict its operating state based on stored information. Based on this prediction, the generative AI model calculates the optimal resource allocation and generates instructions for each control unit. The optimized instructions are automatically sent to the control units, enabling automated operation based on those instructions.

[0278] The control system displays information from the server to the user in real time, supporting decision-making. This allows users to manage resources under optimal conditions and establish efficient business operations. For example, by predicting the occurrence of security events during a festival and deploying the appropriate number of security guards, it is possible to ensure adequate security without excess or deficiency.

[0279] As an example of a prompt sentence, "Please optimize the staffing for next week using the data from the past three years based on the occurrence pattern of security events during the festival period. As a mandatory condition, consider monitoring a specific area in summer as a key monitoring area and arranging more than 20 operators." can be cited. With this prompt sentence, the user can effectively utilize the system and support decision-making.

[0280] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0281] Step 1:

[0282] The server collects past trend information and environmental condition information from sensors and external databases via the network. The input for this process is real-time data and past log data, and the output is an integrated dataset. The server saves this in an SQL database and makes it available for subsequent analysis.

[0283] Step 2:

[0284] Based on the saved dataset, the server uses TensorFlow to predict the operating status. As the input, the integrated dataset collected in the previous step is used and analyzed with a generative AI model. The output is a prediction result indicating the future operating status. Thereby, the server can make a projection of the operation under specific periods and conditions.

[0285] Step 3:

[0286] The server executes a process to optimize resource allocation based on the prediction result. The input is the result of the operating status prediction, and the output is a specific resource allocation instruction to the control device. The generated instruction is processed in real time.

[0287] Step 4:

[0288] The server sends the generated instructions to the control unit. Based on these instructions, the control unit initiates automated processes as needed. The input is the resource allocation instructions obtained in the previous step, and the output is the status update of the control unit.

[0289] Step 5:

[0290] Users can check the server's operational status predictions and resource allocation results in real time via the control device. Input is evaluation data sent from the server, and output is notifications and decision support information for the user. Based on this, users can adjust settings as needed, generate prompt statements as required, and issue additional instructions to the system.

[0291] 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.

[0292] This invention provides a system for call centers and similar communication processing centers to perform communication prediction and optimal allocation of human resources based on communication history information and external condition information. Furthermore, this system incorporates an emotion engine that recognizes user emotions and utilizes that information to achieve more advanced prediction and optimization.

[0293] The server first collects and integrates communication history information and external condition information, and stores it in a database. This information includes past communication activity data, business event information, weather information, etc. Based on this information, the server uses machine learning algorithms to predict future communication demand.

[0294] Next, the server operates the emotion engine. The emotion engine analyzes the interaction between the user and the operator and extracts emotion data. This emotion data is calculated based on the operator's voice tone and customer feedback. The server then incorporates this emotion data into the communication prediction model to improve the accuracy of the predictions.

[0295] Subsequently, the server optimizes the allocation of human resources based on the prediction results and sentiment data. For example, if the sentiment engine detects a high level of negative sentiment, it adjusts the allocation strategy, such as assigning experienced operators to specific time slots. These allocation instructions are sent to terminals at each location, and the shift schedule is automatically updated.

[0296] Users (administrators) can review the communication forecast data, sentiment analysis results, and staffing suggestions displayed on the terminal and make manual adjustments as needed. This allows administrators to operate with consideration not only for numerical data but also for the emotions of customers and operators, contributing to improved service quality.

[0297] The following describes the processing flow.

[0298] Step 1:

[0299] The server periodically collects communication history information and external condition information from terminals at the base station and stores it in an integrated database. The information collected includes past call volume, operator response time, customer satisfaction data, sales campaign information, and external factors such as season and weather.

[0300] Step 2:

[0301] The server uses an emotion engine to analyze the emotions of operators and customers during calls in real time. This emotion data is extracted using speech recognition and natural language processing technologies and quantified as positive, negative, or neutral emotions.

[0302] Step 3:

[0303] The server integrates communication history information, external condition information, and sentiment data, and applies machine learning algorithms to predict future communication demand. The resulting predictions are generated as data indicating highly accurate estimates of incoming call volume and the number of operators needed.

[0304] Step 4:

[0305] Based on the obtained communication prediction data and sentiment data, the server optimizes the human resource allocation at each site. For example, at times when high stress is predicted, a decision is made to allocate experienced operators.

[0306] Step 5:

[0307] The server sends the optimization results of the human resource allocation to the terminals at each site. Based on this optimization instruction, the terminals automatically adjust the shifts and allocations of the operators.

[0308] Step 6:

[0309] The user (administrator) checks the details of the communication prediction, sentiment analysis results, and allocation instructions displayed on the terminal and makes manual adjustments if necessary. This allows the user to reflect their judgment as an administrator in addition to the automated processing of the system.

[0310] (Example 2)

[0311] Next, Example 2 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0312] In a conventional communication prediction system, since only past communication histories and external conditions are considered, there is a problem that it is difficult to improve the accuracy of predictions including emotional factors and optimize human resource allocation. In addition, since the update of allocation instructions in real time and the support for decision-making by administrators are limited, it may affect the quality of the service.

[0313] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0314] In this invention, the server includes means for collecting and integrating past communication history information and external condition information, means for making highly accurate predictions of future communications using machine learning algorithms, and means for analyzing user emotions and extracting emotional data. This enables communication prediction and optimization of human resource allocation that take emotional factors into consideration.

[0315] "Communication history information" refers to data about communication activities that have occurred in the past, including information such as the date and time, call duration, recipient of the call, and content of the call.

[0316] "External condition information" refers to data on external factors that affect the communication environment and conditions, such as weather information, event information, and economic indicators.

[0317] A "machine learning algorithm" is a method for learning patterns in data to make predictions or classifications, and includes, for example, regression analysis and cluster analysis.

[0318] "Communication forecasting" is the process of estimating future communication volume and patterns based on past data and current conditions.

[0319] "Emotional data" refers to information that expresses the emotional state of users and operators as numerical values ​​or categories, and is extracted based on voice tone and text analysis.

[0320] "Human resource allocation" is the process of optimally allocating personnel and skills in order to perform tasks effectively and efficiently.

[0321] "Real-time" means reacting or processing immediately without delay, referring to a state where information is updated instantaneously.

[0322] The system for implementing this invention aims to optimize data processing and human resource allocation for efficient operation at communication base stations. The specific implementation method is described below.

[0323] The server first collects communication history information and external condition information. This includes past communication activity data, weather information, and economic indicators, which are obtained through APIs or database queries. The collected information is integrated and stored in a database. In this process, relational database management systems such as MySQL are often used as the database.

[0324] Next, the server uses machine learning algorithms based on the collected data to predict communication trends. This often involves using Python libraries such as Scikit-learn, and typically includes linear regression and time series analysis. This allows for highly accurate predictions of future communication demand.

[0325] Furthermore, the server operates an emotion engine to extract emotional data from user-operator interactions. This involves using tools such as voice analysis to analyze user emotions from voice tone and text-based feedback. This data is then incorporated into communication predictions, enabling more accurate human resource allocation.

[0326] The terminal receives communication forecast data and human resource allocation instructions sent from the server, and automatically updates the shift schedule based on this information. The terminal has a real-time data update function and always maintains the latest allocation information.

[0327] Users, specifically administrators, review this information via their terminals and manually adjust schedules as needed. This system allows administrators to achieve efficient staffing and high-quality service delivery while considering the feelings of both customers and operators.

[0328] As a concrete example, the server can assign experienced operators to appropriate time slots based on customer sentiment data during peak periods such as the year-end and New Year holidays. Another example of a prompt for the generating AI model could be the question, "What are the best practices for developing a model that incorporates sentiment data into communication demand forecasting?"

[0329] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0330] Step 1:

[0331] The server collects communication history information and external condition information. Inputs include historical communication activity data and weather information collected using APIs and database queries. The collected data is integrated into the server and recorded in a database such as MySQL. The output is this integrated dataset.

[0332] Step 2:

[0333] The server builds a machine learning model based on integrated data to predict communication demand. The input is the dataset created in the previous step. The server uses the Python Scikit-learn library to analyze the data through methods such as linear regression. The output is a prediction of future communication demand.

[0334] Step 3:

[0335] The server operates an emotion engine to analyze user-operator interactions and extract emotion data. Inputs include voice data and text feedback. Sentiment analysis is performed using tools such as Google Cloud's Natural Language API. Output is quantified emotion data.

[0336] Step 4:

[0337] The server optimizes human resource allocation by combining communication prediction results and sentiment data. The inputs are prediction values ​​and sentiment data. The server considers operator skills and availability to generate the optimal allocation strategy. The output is the optimized allocation instruction.

[0338] Step 5:

[0339] The terminal receives placement instructions from the server and automatically updates the shift schedule. The input is the placement strategy. The terminal adjusts each operator's working hours based on these instructions. The output is the updated shift schedule.

[0340] Step 6:

[0341] The user (administrator) reviews the communication forecast and sentiment analysis results displayed on the terminal and makes manual adjustments as needed. The input is the displayed data. The administrator reflects the feasible changes in the system. The output is the final shift schedule and deployment strategy.

[0342] (Application Example 2)

[0343] 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."

[0344] In recent years, communication processing centers have been required to effectively allocate limited human resources in order to respond quickly and appropriately to diverse customer needs. However, conventional systems, which allocate human resources based solely on communication forecasts, could not take into account emotional factors that could not be addressed, resulting in inconsistent response quality. Furthermore, it was difficult to respond flexibly to real-time changes in circumstances. Solving these problems is the objective of the present invention.

[0345] 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.

[0346] In this invention, the server includes means for collecting and integrating past communication history information and external condition information; means for making highly accurate predictions of future communications based on the integrated information; and means for optimizing the allocation of human resources between multiple locations based on an analysis combining the communication predictions and user sentiment data. This makes it possible to optimize the allocation of human resources considering not only communication predictions but also customer sentiment data, thereby improving the uniformity and flexibility of customer service.

[0347] "Communication history information" refers to data related to past communication activities, including the date and time of call initiation and reception, duration, and connection status.

[0348] "External conditions information" refers to data about external factors that may affect communication activities, and includes information such as weather conditions, social events, and the situation during a specific period.

[0349] "User sentiment data" refers to data that indicates a user's emotional state, and includes information such as voice tone and sentiment identification results based on text analysis.

[0350] "Human resource allocation" refers to the process of assigning and placing available personnel in the most suitable work positions, taking various factors into consideration and aiming to place the right personnel in the right tasks.

[0351] A "security response operator" refers to a person with the technical skills to respond to security issues and incidents at a communications processing center.

[0352] An "operating terminal" refers to a digital device used by users to view data or issue instructions, and typically includes a screen and input devices.

[0353] "Decision support" refers to the information and tools provided to users to make better decisions, supporting decision-making through data analysis, prediction, simulation, and other means.

[0354] The system to realize this application example will have the following configuration: The server first collects past communication history information and external condition information, and integrates this data. This allows information that takes into account past communication patterns and external factors such as weather and events to be stored in the database. Subsequently, a machine learning algorithm is used to predict future communication demand from this integrated information.

[0355] Next, the server operates an emotion engine to analyze user emotion data in real time. Using speech recognition technology, it extracts emotions from the tone of the user's voice during communication and acquires this as emotion data. This data is incorporated into a communication prediction model, enabling more accurate optimization of human resource allocation.

[0356] Furthermore, the server develops an optimal operator deployment strategy based on predicted communication demand and sentiment analysis results. This deployment plan is displayed on the operating terminal, providing decision-making support to administrators and security response operators. Administrators can review this plan and make modifications as needed to achieve more appropriate staffing.

[0357] For example, if the emotion engine detects a high level of user anxiety when severe weather is predicted in a certain area, it can automatically adjust the shift schedule to assign experienced operators to that time slot, enabling a quick response.

[0358] An example of a prompt message to input to a generative AI model is: "Based on the user's voice data, analyze the emotions expressed in this call and propose an appropriate operator deployment plan accordingly."

[0359] In this way, servers can leverage data obtained from both communication prediction and sentiment analysis to improve the quality of security responses and increase user trust.

[0360] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0361] Step 1:

[0362] The server collects historical communication history information and external condition information. Specifically, it retrieves past call records, connection status, weather, and event information from the database and integrates them. The input is communication history information and external condition information, and the output is integrated information data. This data forms the basis for the next prediction step.

[0363] Step 2:

[0364] The server uses machine learning algorithms to predict communication based on integrated information. The input is the integrated information data obtained in the previous step, and the data calculations performed are inputting data into the prediction model and calculating output prediction values. The output is prediction data indicating future communication demand. This prediction data is used to optimize human resource allocation.

[0365] Step 3:

[0366] The server analyzes emotions in real time during communication with the user, using speech recognition technology to convert speech data into emotion data. The input is the user's speech data, and the output is the emotion data obtained through analysis. The data processing performed here involves analyzing the tone and speed of the voice and calculating the emotional state using an emotion engine.

[0367] Step 4:

[0368] The server combines communication prediction data and sentiment data to determine the optimal placement of operators. The inputs are communication prediction data and sentiment data, and the output is placement strategy data. Data calculations involve inputting data into a placement model and formulating an output placement strategy. This optimizes appropriate personnel allocation across multiple locations.

[0369] Step 5:

[0370] The terminal displays an optimized deployment strategy to administrators and security response operators. The input is deployment strategy data, and the output is visualized information. Specifically, the terminal screen displays activity and personnel deployment suggestions for each location, allowing administrators and operators to make decisions based on this information.

[0371] Step 6:

[0372] Users modify the deployment strategy as needed via the control terminal, and the updated instructions are sent to the server in real time. Input is the modification instructions from the administrator, and output is the updated deployment data. This operation enables flexible personnel deployment tailored to on-site conditions.

[0373] 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.

[0374] 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.

[0375] 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.

[0376] [Third Embodiment]

[0377] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0378] 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.

[0379] 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).

[0380] 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.

[0381] 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.

[0382] 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).

[0383] 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.

[0384] 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.

[0385] 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.

[0386] 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.

[0387] 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.

[0388] 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".

[0389] This invention is a system aimed at improving the operational efficiency of call centers and similar communication processing facilities. This system uses communication history information and external condition information to predict future communications and automates the optimal allocation of human resources.

[0390] The server first collects communication history information and external condition information, integrates it, and stores it in a database. This data is analyzed using machine learning algorithms and used to predict future communication demand with high accuracy. Based on the communication demand forecast results obtained using the prediction model, the server calculates the optimal allocation of human resources needed at each location.

[0391] Subsequently, the server sends optimized staffing instructions to terminals at each location. Based on the instructions received from the server, the terminals update operator assignments and shift schedules. This ensures that each location operates efficiently and is ready to meet predicted communication demands.

[0392] For example, if a server predicts an increase in traffic during a specific holiday season, it can automatically send instructions to terminals to increase the number of personnel assigned to that period. Furthermore, if extreme weather events occur as external condition information, the system can reflect the resulting changes in predicted demand and implement countermeasures quickly.

[0393] Users (administrators) can refer to the forecast results and staffing recommendations displayed on the terminal, and make further detailed settings and manual adjustments. This enables flexible operation in response to the situation that arises, improving service quality and reducing costs.

[0394] The following describes the processing flow.

[0395] Step 1:

[0396] The server collects communication history information and external condition information. This process periodically retrieves data from terminals at each location and integrates it into a database. The data collected includes past call volume, response time, business event information, and weather data.

[0397] Step 2:

[0398] The server preprocesses the collected raw data into a format that can be analyzed. Specifically, it performs data formatting such as imputing missing values, detecting and correcting outliers, and converting categorical data into numerical values.

[0399] Step 3:

[0400] The server trains a communication prediction model using machine learning algorithms based on the formatted data. This model is designed to predict future communication demand and utilizes past patterns and external conditions as input.

[0401] Step 4:

[0402] The server uses a trained communication prediction model to forecast future communication demand. The forecast results, such as the number of incoming calls per time period and the number of personnel required to handle them, are displayed on a management dashboard.

[0403] Step 5:

[0404] The server optimizes staffing based on the prediction results. This process uses a resource allocation algorithm to calculate staffing plans for each location and formulate appropriate shift assignments.

[0405] Step 6:

[0406] The server sends staffing instructions generated based on the optimization results to terminals at each location. This allows the terminals at each location to automatically adjust operator shifts and assign additional staff as needed.

[0407] Step 7:

[0408] Users can view forecast data and staffing instructions provided by the server on their terminals and make manual adjustments as needed. This enables optimal operations based on forecasts.

[0409] (Example 1)

[0410] 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."

[0411] Call centers and communication processing centers require the optimal allocation of human resources in response to fluctuations in communication volume. However, existing systems lacked real-time capabilities and insufficient accuracy in demand forecasting. As a result, problems such as increased costs due to surpluses or shortages of human resources and a decline in service quality occurred. Furthermore, many of these issues relied on manual responses, placing a burden on administrators.

[0412] 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.

[0413] In this invention, the server includes means for acquiring past communication history information and external condition information, integrating and storing it in a database; means for predicting future communication demand with high accuracy using a machine learning algorithm based on the integrated information; and means for optimizing the allocation of human resources between multiple locations using operations research techniques based on the communication demand forecast. This enables efficient allocation of human resources in real time and the provision of information to support administrator decision-making.

[0414] "Communication history information" refers to a history of past communication data, including detailed data on communication time, call content, response time, and so on.

[0415] "External conditions information" refers to data related to factors that affect communication demand, including external factors such as weather information and economic indicators.

[0416] A "database" is an information management system used to organize and store acquired information, and refers to a centralized location where information used for later analysis and retrieval is aggregated.

[0417] A "machine learning algorithm" is a computational method for analyzing data, finding patterns, and making predictions and judgments; it is a technology that builds models based on empirical data.

[0418] "Communication demand forecasting" refers to the estimation of future communication demands, which is calculated using the aforementioned machine learning algorithms.

[0419] Operations research techniques are methods that use mathematical approaches to optimize organizational management and are techniques used to efficiently allocate human resources.

[0420] An "output terminal" refers to a device or interface that displays information provided by a system, and is used by an administrator as an operating terminal.

[0421] To implement this invention, the server first collects communication history information and external condition information. Communication history information includes past communication times, call content, and response times, while external condition information includes weather information and economic indicators. This data collection is performed using Python's requests library or an ETL tool (e.g., Apache NiFi). The collected information is integrated and stored in a database management system (e.g., PostgreSQL).

[0422] Next, the server uses machine learning algorithms to predict future communication demand with high accuracy. In this process, historical data is used as training data, and a predictive model is generated using libraries such as Scikit-learn and TensorFlow. Based on this predictive model, the server estimates how communication demand will fluctuate and uses this information to optimize human resources.

[0423] Optimization employs operations research techniques to ensure efficient allocation of human resources. This step utilizes optimization libraries such as Opalytics and Google OR-Tools to efficiently allocate human resources.

[0424] Next, the optimized deployment instructions are automatically distributed to terminals at each location in a data format (e.g., JSON). The HTTP protocol is used for this distribution.

[0425] The terminal functions as an interface for receiving instructions sent from the server and updating operator shift schedules based on those instructions. The terminal displays predicted communication demand and optimized staffing in real time to support administrator decision-making.

[0426] Users, or administrators, can refer to the information displayed on the terminal and manually adjust settings as needed. This allows for flexible responses to specific events and fluctuating circumstances.

[0427] For example, if the server predicts high communication demand on a particular day, a deployment instruction is automatically sent to the terminal to increase the number of staff on that day compared to normal. This allows users to deploy staff efficiently, leading to improved service quality.

[0428] An example of a prompt message would be: "Please explain how to predict future communication demand using communication history information and external condition information. Also, please provide a model for the optimal allocation of human resources based on that."

[0429] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0430] Step 1:

[0431] The server retrieves historical communication history information and external condition information from each communication point. Communication history information includes communication time, call content, and response time, while external condition information includes weather and economic indicators. This information is collected via an API using the Python requests library. The collected data is preprocessed for integration and stored in a database. The input here is raw data from various APIs, and the output is a preprocessed dataset.

[0432] Step 2:

[0433] The server retrieves preprocessed datasets from an integrated database and performs analysis using machine learning algorithms. Specifically, it uses Scikit-learn and TensorFlow to create models that predict future communication demand from historical data. It cleans the data and applies classification and regression algorithms to make predictions. In this step, the input is a preprocessed dataset, and the output is a forecast of future communication demand.

[0434] Step 3:

[0435] The server calculates the optimal allocation of human resources using operations research techniques based on predicted communication demand. Opalytics and Google OR-Tools are used to solve the human resource allocation problem as an optimization issue. Resource allocation and scheduling are performed to ensure efficient allocation of human resources at each location. The input is the communication demand forecast, and the output is the optimized human resource allocation plan.

[0436] Step 4:

[0437] The server converts the calculated optimized placement plan into a data format (e.g., JSON) and automatically sends it to terminals at each location using the HTTP protocol. The terminals parse this data and update operator schedules and placements. The input here is the optimized placement plan, and the output is the updated actual operational schedule at each location.

[0438] Step 5:

[0439] The terminal updates the operator's shift schedule in real time based on placement instructions received from the server. The updated information is displayed in the user interface, providing a foundation for administrators and relevant parties to manage the schedule. The input is placement instructions from the server, and the output is visualized schedule information.

[0440] Step 6:

[0441] The user (administrator) makes additional settings or manual adjustments as needed based on the information displayed on the terminal. For example, if an unexpected event occurs, measures can be taken to prevent it. In this step, the input is the visualized information on the terminal, and the output is the adjusted operation.

[0442] (Application Example 1)

[0443] 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."

[0444] Modern business locations require real-time, optimal resource allocation based on historical trends and environmental conditions. However, conventional systems lack the mechanisms to efficiently analyze these factors, accurately predict future operational states, and automatically instruct optimal resource allocation based on those predictions. As a result, in many cases, there is a shortage or surplus of human resources, leading to challenges such as decreased operational efficiency and deterioration of service quality.

[0445] 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.

[0446] In this invention, the server includes means for collecting and integrating past trend information and environmental condition information, means for making highly accurate predictions of future operating conditions based on the integrated information, and means for optimizing resource allocation between multiple locations using the operating condition predictions. This enables optimal resource allocation in real time and efficient business operations.

[0447] "Trend information" refers to data about past activities and events, and is used to analyze specific trends and patterns.

[0448] "Environmental conditions information" refers to data about the external environment, including relevant factors such as weather conditions and social events.

[0449] "Operating status forecasting" refers to the process of predicting the future operating status of systems and business locations, and supports decision-making for efficient operations.

[0450] "Resource allocation" refers to the process of optimally distributing available resources across multiple locations, and is an important method for improving operational efficiency.

[0451] A "control device" refers to hardware or software used to manage the operation of a system or device, and is responsible for executing optimized instructions.

[0452] An "operating device" refers to a device that provides an interface used by the user to control the system or to view information.

[0453] The system for implementing this invention mainly consists of a server, a control device, and an operating device. The server has the function of collecting and integrating historical trend information and environmental condition information. Specifically, it collects data from sensors and external databases, integrates them, and stores them in an SQL database.

[0454] The server uses machine learning software such as TensorFlow to predict its operating state based on stored information. Based on this prediction, the generative AI model calculates the optimal resource allocation and generates instructions for each control unit. The optimized instructions are automatically sent to the control units, enabling automated operation based on those instructions.

[0455] The control system displays information from the server to the user in real time, supporting decision-making. This allows users to manage resources under optimal conditions and establish efficient business operations. For example, by predicting the occurrence of security events during a festival and deploying the appropriate number of security guards, it is possible to ensure adequate security without excess or deficiency.

[0456] An example of a prompt message is: "Based on the patterns of security events during the festival period, use data from the past three years to optimize staffing for next week. As a requirement, designate a specific area during the summer as a monitoring priority area and consider deploying at least 20 operators." This prompt message enables users to effectively utilize the system and support their decision-making.

[0457] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0458] Step 1:

[0459] The server collects historical trend information and environmental condition information from sensors and external databases via the network. The input to this process is real-time data and historical log data, and the output is an integrated dataset. The server stores this data in an SQL database, making it available for subsequent analysis.

[0460] Step 2:

[0461] The server uses TensorFlow to predict its operational status based on the stored dataset. The integrated dataset collected in the previous step is used as input and analyzed by a generative AI model. The output is a prediction of future operational status. This allows the server to estimate its operational status for specific periods and conditions.

[0462] Step 3:

[0463] The server executes a process to optimize resource allocation based on the prediction results. The input is the result of the operational status prediction, and the output is a specific resource allocation instruction to the control unit. The generated instructions are processed in real time.

[0464] Step 4:

[0465] The server sends the generated instructions to the control unit. Based on these instructions, the control unit initiates automated processes as needed. The input is the resource allocation instructions obtained in the previous step, and the output is the status update of the control unit.

[0466] Step 5:

[0467] Users can check the server's operational status predictions and resource allocation results in real time via the control device. Input is evaluation data sent from the server, and output is notifications and decision support information for the user. Based on this, users can adjust settings as needed, generate prompt statements as required, and issue additional instructions to the system.

[0468] 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.

[0469] This invention provides a system for call centers and similar communication processing centers to perform communication prediction and optimal allocation of human resources based on communication history information and external condition information. Furthermore, this system incorporates an emotion engine that recognizes user emotions and utilizes that information to achieve more advanced prediction and optimization.

[0470] The server first collects and integrates communication history information and external condition information, and stores it in a database. This information includes past communication activity data, business event information, weather information, etc. Based on this information, the server uses machine learning algorithms to predict future communication demand.

[0471] Next, the server operates the emotion engine. The emotion engine analyzes the interaction between the user and the operator and extracts emotion data. This emotion data is calculated based on the operator's voice tone and customer feedback. The server then incorporates this emotion data into the communication prediction model to improve the accuracy of the predictions.

[0472] Subsequently, the server optimizes the allocation of human resources based on the prediction results and sentiment data. For example, if the sentiment engine detects a high level of negative sentiment, it adjusts the allocation strategy, such as assigning experienced operators to specific time slots. These allocation instructions are sent to terminals at each location, and the shift schedule is automatically updated.

[0473] Users (administrators) can review the communication forecast data, sentiment analysis results, and staffing suggestions displayed on the terminal and make manual adjustments as needed. This allows administrators to operate with consideration not only for numerical data but also for the emotions of customers and operators, contributing to improved service quality.

[0474] The following describes the processing flow.

[0475] Step 1:

[0476] The server periodically collects communication history information and external condition information from terminals at the base station and stores it in an integrated database. The information collected includes past call volume, operator response time, customer satisfaction data, sales campaign information, and external factors such as season and weather.

[0477] Step 2:

[0478] The server uses an emotion engine to analyze the emotions of operators and customers during calls in real time. This emotion data is extracted using speech recognition and natural language processing technologies and quantified as positive, negative, or neutral emotions.

[0479] Step 3:

[0480] The server integrates communication history information, external condition information, and sentiment data, and applies machine learning algorithms to predict future communication demand. The resulting predictions are generated as data indicating highly accurate estimates of incoming call volume and the number of operators needed.

[0481] Step 4:

[0482] The server optimizes the allocation of human resources at each location based on the obtained communication prediction data and sentiment data. For example, it decides to assign experienced operators during times when high stress is predicted.

[0483] Step 5:

[0484] The server transmits the results of the optimization of human resource allocation to terminals at each location. Based on these optimization instructions, the terminals automatically adjust operator shifts and assignments.

[0485] Step 6:

[0486] The user (administrator) can review the communication forecast, sentiment analysis results, and deployment instructions displayed on the terminal, and make manual adjustments as needed. This allows the user to incorporate their own judgment as an administrator, in addition to the system's automated processes.

[0487] (Example 2)

[0488] 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."

[0489] Conventional communication forecasting systems only consider past communication history and external conditions, making it difficult to improve the accuracy of predictions that include emotional factors and optimize human resource allocation. Furthermore, the limited real-time updates of deployment instructions and support for administrator decision-making can negatively impact service quality.

[0490] 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.

[0491] In this invention, the server includes means for collecting and integrating past communication history information and external condition information, means for making highly accurate predictions of future communications using machine learning algorithms, and means for analyzing user emotions and extracting emotional data. This enables communication prediction and optimization of human resource allocation that take emotional factors into consideration.

[0492] "Communication history information" refers to data about communication activities that have occurred in the past, including information such as the date and time, call duration, recipient of the call, and content of the call.

[0493] "External condition information" refers to data on external factors that affect the communication environment and conditions, such as weather information, event information, and economic indicators.

[0494] A "machine learning algorithm" is a method for learning patterns in data to make predictions or classifications, and includes, for example, regression analysis and cluster analysis.

[0495] "Communication forecasting" is the process of estimating future communication volume and patterns based on past data and current conditions.

[0496] "Emotional data" refers to information that expresses the emotional state of users and operators as numerical values ​​or categories, and is extracted based on voice tone and text analysis.

[0497] "Human resource allocation" is the process of optimally allocating personnel and skills in order to perform tasks effectively and efficiently.

[0498] "Real-time" means reacting or processing immediately without delay, referring to a state where information is updated instantaneously.

[0499] The system for implementing this invention aims to optimize data processing and human resource allocation for efficient operation at communication base stations. The specific implementation method is described below.

[0500] The server first collects communication history information and external condition information. This includes past communication activity data, weather information, and economic indicators, which are obtained through APIs or database queries. The collected information is integrated and stored in a database. In this process, relational database management systems such as MySQL are often used as the database.

[0501] Next, the server uses machine learning algorithms based on the collected data to predict communication trends. This often involves using Python libraries such as Scikit-learn, and typically includes linear regression and time series analysis. This allows for highly accurate predictions of future communication demand.

[0502] Furthermore, the server operates an emotion engine to extract emotional data from user-operator interactions. This involves using tools such as voice analysis to analyze user emotions from voice tone and text-based feedback. This data is then incorporated into communication predictions, enabling more accurate human resource allocation.

[0503] The terminal receives communication forecast data and human resource allocation instructions sent from the server, and automatically updates the shift schedule based on this information. The terminal has a real-time data update function and always maintains the latest allocation information.

[0504] Users, specifically administrators, review this information via their terminals and manually adjust schedules as needed. This system allows administrators to achieve efficient staffing and high-quality service delivery while considering the feelings of both customers and operators.

[0505] As a concrete example, the server can assign experienced operators to appropriate time slots based on customer sentiment data during peak periods such as the year-end and New Year holidays. Another example of a prompt for the generating AI model could be the question, "What are the best practices for developing a model that incorporates sentiment data into communication demand forecasting?"

[0506] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0507] Step 1:

[0508] The server collects communication history information and external condition information. Inputs include historical communication activity data and weather information collected using APIs and database queries. The collected data is integrated into the server and recorded in a database such as MySQL. The output is this integrated dataset.

[0509] Step 2:

[0510] The server builds a machine learning model based on integrated data to predict communication demand. The input is the dataset created in the previous step. The server uses the Python Scikit-learn library to analyze the data through methods such as linear regression. The output is a prediction of future communication demand.

[0511] Step 3:

[0512] The server operates an emotion engine to analyze user-operator interactions and extract emotion data. Inputs include voice data and text feedback. Sentiment analysis is performed using tools such as Google Cloud's Natural Language API. Output is quantified emotion data.

[0513] Step 4:

[0514] The server optimizes human resource allocation by combining communication prediction results and sentiment data. The inputs are prediction values ​​and sentiment data. The server considers operator skills and availability to generate the optimal allocation strategy. The output is the optimized allocation instruction.

[0515] Step 5:

[0516] The terminal receives placement instructions from the server and automatically updates the shift schedule. The input is the placement strategy. The terminal adjusts each operator's working hours based on these instructions. The output is the updated shift schedule.

[0517] Step 6:

[0518] The user (administrator) reviews the communication forecast and sentiment analysis results displayed on the terminal and makes manual adjustments as needed. The input is the displayed data. The administrator reflects the feasible changes in the system. The output is the final shift schedule and deployment strategy.

[0519] (Application Example 2)

[0520] 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."

[0521] In recent years, communication processing centers have been required to effectively allocate limited human resources in order to respond quickly and appropriately to diverse customer needs. However, conventional systems, which allocate human resources based solely on communication forecasts, could not take into account emotional factors that could not be addressed, resulting in inconsistent response quality. Furthermore, it was difficult to respond flexibly to real-time changes in circumstances. Solving these problems is the objective of the present invention.

[0522] 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.

[0523] In this invention, the server includes means for collecting and integrating past communication history information and external condition information; means for making highly accurate predictions of future communications based on the integrated information; and means for optimizing the allocation of human resources between multiple locations based on an analysis combining the communication predictions and user sentiment data. This makes it possible to optimize the allocation of human resources considering not only communication predictions but also customer sentiment data, thereby improving the uniformity and flexibility of customer service.

[0524] "Communication history information" refers to data related to past communication activities, including the date and time of call initiation and reception, duration, and connection status.

[0525] "External conditions information" refers to data about external factors that may affect communication activities, and includes information such as weather conditions, social events, and the situation during a specific period.

[0526] "User sentiment data" refers to data that indicates a user's emotional state, and includes information such as voice tone and sentiment identification results based on text analysis.

[0527] "Human resource allocation" refers to the process of assigning and placing available personnel in the most suitable work positions, taking various factors into consideration and aiming to place the right personnel in the right tasks.

[0528] A "security response operator" refers to a person with the technical skills to respond to security issues and incidents at a communications processing center.

[0529] An "operating terminal" refers to a digital device used by users to view data or issue instructions, and typically includes a screen and input devices.

[0530] "Decision support" refers to the information and tools provided to users to make better decisions, supporting decision-making through data analysis, prediction, simulation, and other means.

[0531] The system to realize this application example will have the following configuration: The server first collects past communication history information and external condition information, and integrates this data. This allows information that takes into account past communication patterns and external factors such as weather and events to be stored in the database. Subsequently, a machine learning algorithm is used to predict future communication demand from this integrated information.

[0532] Next, the server operates an emotion engine to analyze user emotion data in real time. Using speech recognition technology, it extracts emotions from the tone of the user's voice during communication and acquires this as emotion data. This data is incorporated into a communication prediction model, enabling more accurate optimization of human resource allocation.

[0533] Furthermore, the server develops an optimal operator deployment strategy based on predicted communication demand and sentiment analysis results. This deployment plan is displayed on the operating terminal, providing decision-making support to administrators and security response operators. Administrators can review this plan and make modifications as needed to achieve more appropriate staffing.

[0534] For example, if the emotion engine detects a high level of user anxiety when severe weather is predicted in a certain area, it can automatically adjust the shift schedule to assign experienced operators to that time slot, enabling a quick response.

[0535] An example of a prompt message to input to a generative AI model is: "Based on the user's voice data, analyze the emotions expressed in this call and propose an appropriate operator deployment plan accordingly."

[0536] In this way, servers can leverage data obtained from both communication prediction and sentiment analysis to improve the quality of security responses and increase user trust.

[0537] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0538] Step 1:

[0539] The server collects historical communication history information and external condition information. Specifically, it retrieves past call records, connection status, weather, and event information from the database and integrates them. The input is communication history information and external condition information, and the output is integrated information data. This data forms the basis for the next prediction step.

[0540] Step 2:

[0541] The server uses machine learning algorithms to predict communication based on integrated information. The input is the integrated information data obtained in the previous step, and the data calculations performed are inputting data into the prediction model and calculating output prediction values. The output is prediction data indicating future communication demand. This prediction data is used to optimize human resource allocation.

[0542] Step 3:

[0543] The server analyzes emotions in real time during communication with the user, using speech recognition technology to convert speech data into emotion data. The input is the user's speech data, and the output is the emotion data obtained through analysis. The data processing performed here involves analyzing the tone and speed of the voice and calculating the emotional state using an emotion engine.

[0544] Step 4:

[0545] The server combines communication prediction data and sentiment data to determine the optimal placement of operators. The inputs are communication prediction data and sentiment data, and the output is placement strategy data. Data calculations involve inputting data into a placement model and formulating an output placement strategy. This optimizes appropriate personnel allocation across multiple locations.

[0546] Step 5:

[0547] The terminal displays an optimized deployment strategy to administrators and security response operators. The input is deployment strategy data, and the output is visualized information. Specifically, the terminal screen displays activity and personnel deployment suggestions for each location, allowing administrators and operators to make decisions based on this information.

[0548] Step 6:

[0549] Users modify the deployment strategy as needed via the control terminal, and the updated instructions are sent to the server in real time. Input is the modification instructions from the administrator, and output is the updated deployment data. This operation enables flexible personnel deployment tailored to on-site conditions.

[0550] 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.

[0551] 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.

[0552] 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.

[0553] [Fourth Embodiment]

[0554] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0555] 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.

[0556] 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).

[0557] 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.

[0558] 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.

[0559] 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).

[0560] 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.

[0561] 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.

[0562] 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.

[0563] 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.

[0564] 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.

[0565] 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.

[0566] 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".

[0567] This invention is a system aimed at improving the operational efficiency of call centers and similar communication processing facilities. This system uses communication history information and external condition information to predict future communications and automates the optimal allocation of human resources.

[0568] The server first collects communication history information and external condition information, integrates it, and stores it in a database. This data is analyzed using machine learning algorithms and used to predict future communication demand with high accuracy. Based on the communication demand forecast results obtained using the prediction model, the server calculates the optimal allocation of human resources needed at each location.

[0569] Subsequently, the server sends optimized staffing instructions to terminals at each location. Based on the instructions received from the server, the terminals update operator assignments and shift schedules. This ensures that each location operates efficiently and is ready to meet predicted communication demands.

[0570] For example, if a server predicts an increase in traffic during a specific holiday season, it can automatically send instructions to terminals to increase the number of personnel assigned to that period. Furthermore, if extreme weather events occur as external condition information, the system can reflect the resulting changes in predicted demand and implement countermeasures quickly.

[0571] Users (administrators) can refer to the forecast results and staffing recommendations displayed on the terminal, and make further detailed settings and manual adjustments. This enables flexible operation in response to the situation that arises, improving service quality and reducing costs.

[0572] The following describes the processing flow.

[0573] Step 1:

[0574] The server collects communication history information and external condition information. This process periodically retrieves data from terminals at each location and integrates it into a database. The data collected includes past call volume, response time, business event information, and weather data.

[0575] Step 2:

[0576] The server preprocesses the collected raw data into a format that can be analyzed. Specifically, it performs data formatting such as imputing missing values, detecting and correcting outliers, and converting categorical data into numerical values.

[0577] Step 3:

[0578] The server trains a communication prediction model using machine learning algorithms based on the formatted data. This model is designed to predict future communication demand and utilizes past patterns and external conditions as input.

[0579] Step 4:

[0580] The server uses a trained communication prediction model to forecast future communication demand. The forecast results, such as the number of incoming calls per time period and the number of personnel required to handle them, are displayed on a management dashboard.

[0581] Step 5:

[0582] The server optimizes staffing based on the prediction results. This process uses a resource allocation algorithm to calculate staffing plans for each location and formulate appropriate shift assignments.

[0583] Step 6:

[0584] The server sends staffing instructions generated based on the optimization results to terminals at each location. This allows the terminals at each location to automatically adjust operator shifts and assign additional staff as needed.

[0585] Step 7:

[0586] Users can view forecast data and staffing instructions provided by the server on their terminals and make manual adjustments as needed. This enables optimal operations based on forecasts.

[0587] (Example 1)

[0588] 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".

[0589] Call centers and communication processing centers require the optimal allocation of human resources in response to fluctuations in communication volume. However, existing systems lacked real-time capabilities and insufficient accuracy in demand forecasting. As a result, problems such as increased costs due to surpluses or shortages of human resources and a decline in service quality occurred. Furthermore, many of these issues relied on manual responses, placing a burden on administrators.

[0590] 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.

[0591] In this invention, the server includes means for acquiring past communication history information and external condition information, integrating and storing it in a database; means for predicting future communication demand with high accuracy using a machine learning algorithm based on the integrated information; and means for optimizing the allocation of human resources between multiple locations using operations research techniques based on the communication demand forecast. This enables efficient allocation of human resources in real time and the provision of information to support administrator decision-making.

[0592] "Communication history information" refers to a history of past communication data, including detailed data on communication time, call content, response time, and so on.

[0593] "External conditions information" refers to data related to factors that affect communication demand, including external factors such as weather information and economic indicators.

[0594] A "database" is an information management system used to organize and store acquired information, and refers to a centralized location where information used for later analysis and retrieval is aggregated.

[0595] A "machine learning algorithm" is a computational method for analyzing data, finding patterns, and making predictions and judgments; it is a technology that builds models based on empirical data.

[0596] "Communication demand forecasting" refers to the estimation of future communication demands, which is calculated using the aforementioned machine learning algorithms.

[0597] Operations research techniques are methods that use mathematical approaches to optimize organizational management and are techniques used to efficiently allocate human resources.

[0598] An "output terminal" refers to a device or interface that displays information provided by a system, and is used by an administrator as an operating terminal.

[0599] To implement this invention, the server first collects communication history information and external condition information. Communication history information includes past communication times, call content, and response times, while external condition information includes weather information and economic indicators. This data collection is performed using Python's requests library or an ETL tool (e.g., Apache NiFi). The collected information is integrated and stored in a database management system (e.g., PostgreSQL).

[0600] Next, the server uses machine learning algorithms to predict future communication demand with high accuracy. In this process, historical data is used as training data, and a predictive model is generated using libraries such as Scikit-learn and TensorFlow. Based on this predictive model, the server estimates how communication demand will fluctuate and uses this information to optimize human resources.

[0601] Optimization employs operations research techniques to ensure efficient allocation of human resources. This step utilizes optimization libraries such as Opalytics and Google OR-Tools to efficiently allocate human resources.

[0602] Next, the optimized deployment instructions are automatically distributed to terminals at each location in a data format (e.g., JSON). The HTTP protocol is used for this distribution.

[0603] The terminal functions as an interface for receiving instructions sent from the server and updating operator shift schedules based on those instructions. The terminal displays predicted communication demand and optimized staffing in real time to support administrator decision-making.

[0604] Users, or administrators, can refer to the information displayed on the terminal and manually adjust settings as needed. This allows for flexible responses to specific events and fluctuating circumstances.

[0605] For example, if the server predicts high communication demand on a particular day, a deployment instruction is automatically sent to the terminal to increase the number of staff on that day compared to normal. This allows users to deploy staff efficiently, leading to improved service quality.

[0606] An example of a prompt message would be: "Please explain how to predict future communication demand using communication history information and external condition information. Also, please provide a model for the optimal allocation of human resources based on that."

[0607] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0608] Step 1:

[0609] The server retrieves historical communication history information and external condition information from each communication point. Communication history information includes communication time, call content, and response time, while external condition information includes weather and economic indicators. This information is collected via an API using the Python requests library. The collected data is preprocessed for integration and stored in a database. The input here is raw data from various APIs, and the output is a preprocessed dataset.

[0610] Step 2:

[0611] The server retrieves preprocessed datasets from an integrated database and performs analysis using machine learning algorithms. Specifically, it uses Scikit-learn and TensorFlow to create models that predict future communication demand from historical data. It cleans the data and applies classification and regression algorithms to make predictions. In this step, the input is a preprocessed dataset, and the output is a forecast of future communication demand.

[0612] Step 3:

[0613] The server calculates the optimal allocation of human resources using operations research techniques based on predicted communication demand. Opalytics and Google OR-Tools are used to solve the human resource allocation problem as an optimization issue. Resource allocation and scheduling are performed to ensure efficient allocation of human resources at each location. The input is the communication demand forecast, and the output is the optimized human resource allocation plan.

[0614] Step 4:

[0615] The server converts the calculated optimized placement plan into a data format (e.g., JSON) and automatically sends it to terminals at each location using the HTTP protocol. The terminals parse this data and update operator schedules and placements. The input here is the optimized placement plan, and the output is the updated actual operational schedule at each location.

[0616] Step 5:

[0617] The terminal updates the operator's shift schedule in real time based on placement instructions received from the server. The updated information is displayed in the user interface, providing a foundation for administrators and relevant parties to manage the schedule. The input is placement instructions from the server, and the output is visualized schedule information.

[0618] Step 6:

[0619] The user (administrator) makes additional settings or manual adjustments as needed based on the information displayed on the terminal. For example, if an unexpected event occurs, measures can be taken to prevent it. In this step, the input is the visualized information on the terminal, and the output is the adjusted operation.

[0620] (Application Example 1)

[0621] 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".

[0622] Modern business locations require real-time, optimal resource allocation based on historical trends and environmental conditions. However, conventional systems lack the mechanisms to efficiently analyze these factors, accurately predict future operational states, and automatically instruct optimal resource allocation based on those predictions. As a result, in many cases, there is a shortage or surplus of human resources, leading to challenges such as decreased operational efficiency and deterioration of service quality.

[0623] 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.

[0624] In this invention, the server includes means for collecting and integrating past trend information and environmental condition information, means for making highly accurate predictions of future operating conditions based on the integrated information, and means for optimizing resource allocation between multiple locations using the operating condition predictions. This enables optimal resource allocation in real time and efficient business operations.

[0625] "Trend information" refers to data about past activities and events, and is used to analyze specific trends and patterns.

[0626] "Environmental conditions information" refers to data about the external environment, including relevant factors such as weather conditions and social events.

[0627] "Operating status forecasting" refers to the process of predicting the future operating status of systems and business locations, and supports decision-making for efficient operations.

[0628] "Resource allocation" refers to the process of optimally distributing available resources across multiple locations, and is an important method for improving operational efficiency.

[0629] A "control device" refers to hardware or software used to manage the operation of a system or device, and is responsible for executing optimized instructions.

[0630] An "operating device" refers to a device that provides an interface used by the user to control the system or to view information.

[0631] The system for implementing this invention mainly consists of a server, a control device, and an operating device. The server has the function of collecting and integrating historical trend information and environmental condition information. Specifically, it collects data from sensors and external databases, integrates them, and stores them in an SQL database.

[0632] The server uses machine learning software such as TensorFlow to predict its operating state based on stored information. Based on this prediction, the generative AI model calculates the optimal resource allocation and generates instructions for each control unit. The optimized instructions are automatically sent to the control units, enabling automated operation based on those instructions.

[0633] The control system displays information from the server to the user in real time, supporting decision-making. This allows users to manage resources under optimal conditions and establish efficient business operations. For example, by predicting the occurrence of security events during a festival and deploying the appropriate number of security guards, it is possible to ensure adequate security without excess or deficiency.

[0634] An example of a prompt message is: "Based on the patterns of security events during the festival period, use data from the past three years to optimize staffing for next week. As a requirement, designate a specific area during the summer as a monitoring priority area and consider deploying at least 20 operators." This prompt message enables users to effectively utilize the system and support their decision-making.

[0635] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0636] Step 1:

[0637] The server collects historical trend information and environmental condition information from sensors and external databases via the network. The input to this process is real-time data and historical log data, and the output is an integrated dataset. The server stores this data in an SQL database, making it available for subsequent analysis.

[0638] Step 2:

[0639] The server uses TensorFlow to predict its operational status based on the stored dataset. The integrated dataset collected in the previous step is used as input and analyzed by a generative AI model. The output is a prediction of future operational status. This allows the server to estimate its operational status for specific periods and conditions.

[0640] Step 3:

[0641] The server executes a process to optimize resource allocation based on the prediction results. The input is the result of the operational status prediction, and the output is a specific resource allocation instruction to the control unit. The generated instructions are processed in real time.

[0642] Step 4:

[0643] The server sends the generated instructions to the control unit. Based on these instructions, the control unit initiates automated processes as needed. The input is the resource allocation instructions obtained in the previous step, and the output is the status update of the control unit.

[0644] Step 5:

[0645] Users can check the server's operational status predictions and resource allocation results in real time via the control device. Input is evaluation data sent from the server, and output is notifications and decision support information for the user. Based on this, users can adjust settings as needed, generate prompt statements as required, and issue additional instructions to the system.

[0646] 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.

[0647] This invention provides a system for call centers and similar communication processing centers to perform communication prediction and optimal allocation of human resources based on communication history information and external condition information. Furthermore, this system incorporates an emotion engine that recognizes user emotions and utilizes that information to achieve more advanced prediction and optimization.

[0648] The server first collects and integrates communication history information and external condition information, and stores it in a database. This information includes past communication activity data, business event information, weather information, etc. Based on this information, the server uses machine learning algorithms to predict future communication demand.

[0649] Next, the server operates the emotion engine. The emotion engine analyzes the interaction between the user and the operator and extracts emotion data. This emotion data is calculated based on the operator's voice tone and customer feedback. The server then incorporates this emotion data into the communication prediction model to improve the accuracy of the predictions.

[0650] Subsequently, the server optimizes the allocation of human resources based on the prediction results and sentiment data. For example, if the sentiment engine detects a high level of negative sentiment, it adjusts the allocation strategy, such as assigning experienced operators to specific time slots. These allocation instructions are sent to terminals at each location, and the shift schedule is automatically updated.

[0651] Users (administrators) can review the communication forecast data, sentiment analysis results, and staffing suggestions displayed on the terminal and make manual adjustments as needed. This allows administrators to operate with consideration not only for numerical data but also for the emotions of customers and operators, contributing to improved service quality.

[0652] The following describes the processing flow.

[0653] Step 1:

[0654] The server periodically collects communication history information and external condition information from terminals at the base station and stores it in an integrated database. The information collected includes past call volume, operator response time, customer satisfaction data, sales campaign information, and external factors such as season and weather.

[0655] Step 2:

[0656] The server uses an emotion engine to analyze the emotions of operators and customers during calls in real time. This emotion data is extracted using speech recognition and natural language processing technologies and quantified as positive, negative, or neutral emotions.

[0657] Step 3:

[0658] The server integrates communication history information, external condition information, and sentiment data, and applies machine learning algorithms to predict future communication demand. The resulting predictions are generated as data indicating highly accurate estimates of incoming call volume and the number of operators needed.

[0659] Step 4:

[0660] The server optimizes the allocation of human resources at each location based on the obtained communication prediction data and sentiment data. For example, it decides to assign experienced operators during times when high stress is predicted.

[0661] Step 5:

[0662] The server transmits the results of the optimization of human resource allocation to terminals at each location. Based on these optimization instructions, the terminals automatically adjust operator shifts and assignments.

[0663] Step 6:

[0664] The user (administrator) can review the communication forecast, sentiment analysis results, and deployment instructions displayed on the terminal, and make manual adjustments as needed. This allows the user to incorporate their own judgment as an administrator, in addition to the system's automated processes.

[0665] (Example 2)

[0666] 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".

[0667] Conventional communication forecasting systems only consider past communication history and external conditions, making it difficult to improve the accuracy of predictions that include emotional factors and optimize human resource allocation. Furthermore, the limited real-time updates of deployment instructions and support for administrator decision-making can negatively impact service quality.

[0668] 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.

[0669] In this invention, the server includes means for collecting and integrating past communication history information and external condition information, means for making highly accurate predictions of future communications using machine learning algorithms, and means for analyzing user emotions and extracting emotional data. This enables communication prediction and optimization of human resource allocation that take emotional factors into consideration.

[0670] "Communication history information" refers to data about communication activities that have occurred in the past, including information such as the date and time, call duration, recipient of the call, and content of the call.

[0671] "External condition information" refers to data on external factors that affect the communication environment and conditions, such as weather information, event information, and economic indicators.

[0672] A "machine learning algorithm" is a method for learning patterns in data to make predictions or classifications, and includes, for example, regression analysis and cluster analysis.

[0673] "Communication forecasting" is the process of estimating future communication volume and patterns based on past data and current conditions.

[0674] "Emotional data" refers to information that expresses the emotional state of users and operators as numerical values ​​or categories, and is extracted based on voice tone and text analysis.

[0675] "Human resource allocation" is the process of optimally allocating personnel and skills in order to perform tasks effectively and efficiently.

[0676] "Real-time" means reacting or processing immediately without delay, referring to a state where information is updated instantaneously.

[0677] The system for implementing this invention aims to optimize data processing and human resource allocation for efficient operation at communication base stations. The specific implementation method is described below.

[0678] The server first collects communication history information and external condition information. This includes past communication activity data, weather information, and economic indicators, which are obtained through APIs or database queries. The collected information is integrated and stored in a database. In this process, relational database management systems such as MySQL are often used as the database.

[0679] Next, the server uses machine learning algorithms based on the collected data to predict communication trends. This often involves using Python libraries such as Scikit-learn, and typically includes linear regression and time series analysis. This allows for highly accurate predictions of future communication demand.

[0680] Furthermore, the server operates an emotion engine to extract emotional data from user-operator interactions. This involves using tools such as voice analysis to analyze user emotions from voice tone and text-based feedback. This data is then incorporated into communication predictions, enabling more accurate human resource allocation.

[0681] The terminal receives communication forecast data and human resource allocation instructions sent from the server, and automatically updates the shift schedule based on this information. The terminal has a real-time data update function and always maintains the latest allocation information.

[0682] Users, specifically administrators, review this information via their terminals and manually adjust schedules as needed. This system allows administrators to achieve efficient staffing and high-quality service delivery while considering the feelings of both customers and operators.

[0683] As a concrete example, the server can assign experienced operators to appropriate time slots based on customer sentiment data during peak periods such as the year-end and New Year holidays. Another example of a prompt for the generating AI model could be the question, "What are the best practices for developing a model that incorporates sentiment data into communication demand forecasting?"

[0684] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0685] Step 1:

[0686] The server collects communication history information and external condition information. Inputs include historical communication activity data and weather information collected using APIs and database queries. The collected data is integrated into the server and recorded in a database such as MySQL. The output is this integrated dataset.

[0687] Step 2:

[0688] The server builds a machine learning model based on integrated data to predict communication demand. The input is the dataset created in the previous step. The server uses the Python Scikit-learn library to analyze the data through methods such as linear regression. The output is a prediction of future communication demand.

[0689] Step 3:

[0690] The server operates an emotion engine to analyze user-operator interactions and extract emotion data. Inputs include voice data and text feedback. Sentiment analysis is performed using tools such as Google Cloud's Natural Language API. Output is quantified emotion data.

[0691] Step 4:

[0692] The server optimizes human resource allocation by combining communication prediction results and sentiment data. The inputs are prediction values ​​and sentiment data. The server considers operator skills and availability to generate the optimal allocation strategy. The output is the optimized allocation instruction.

[0693] Step 5:

[0694] The terminal receives placement instructions from the server and automatically updates the shift schedule. The input is the placement strategy. The terminal adjusts each operator's working hours based on these instructions. The output is the updated shift schedule.

[0695] Step 6:

[0696] The user (administrator) reviews the communication forecast and sentiment analysis results displayed on the terminal and makes manual adjustments as needed. The input is the displayed data. The administrator reflects the feasible changes in the system. The output is the final shift schedule and deployment strategy.

[0697] (Application Example 2)

[0698] 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".

[0699] In recent years, communication processing centers have been required to effectively allocate limited human resources in order to respond quickly and appropriately to diverse customer needs. However, conventional systems, which allocate human resources based solely on communication forecasts, could not take into account emotional factors that could not be addressed, resulting in inconsistent response quality. Furthermore, it was difficult to respond flexibly to real-time changes in circumstances. Solving these problems is the objective of the present invention.

[0700] 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.

[0701] In this invention, the server includes means for collecting and integrating past communication history information and external condition information; means for making highly accurate predictions of future communications based on the integrated information; and means for optimizing the allocation of human resources between multiple locations based on an analysis combining the communication predictions and user sentiment data. This makes it possible to optimize the allocation of human resources considering not only communication predictions but also customer sentiment data, thereby improving the uniformity and flexibility of customer service.

[0702] "Communication history information" refers to data related to past communication activities, including the date and time of call initiation and reception, duration, and connection status.

[0703] "External conditions information" refers to data about external factors that may affect communication activities, and includes information such as weather conditions, social events, and the situation during a specific period.

[0704] "User sentiment data" refers to data that indicates a user's emotional state, and includes information such as voice tone and sentiment identification results based on text analysis.

[0705] "Human resource allocation" refers to the process of assigning and placing available personnel in the most suitable work positions, taking various factors into consideration and aiming to place the right personnel in the right tasks.

[0706] A "security response operator" refers to a person with the technical skills to respond to security issues and incidents at a communications processing center.

[0707] An "operating terminal" refers to a digital device used by users to view data or issue instructions, and typically includes a screen and input devices.

[0708] "Decision support" refers to the information and tools provided to users to make better decisions, supporting decision-making through data analysis, prediction, simulation, and other means.

[0709] The system to realize this application example will have the following configuration: The server first collects past communication history information and external condition information, and integrates this data. This allows information that takes into account past communication patterns and external factors such as weather and events to be stored in the database. Subsequently, a machine learning algorithm is used to predict future communication demand from this integrated information.

[0710] Next, the server operates an emotion engine to analyze user emotion data in real time. Using speech recognition technology, it extracts emotions from the tone of the user's voice during communication and acquires this as emotion data. This data is incorporated into a communication prediction model, enabling more accurate optimization of human resource allocation.

[0711] Furthermore, the server develops an optimal operator deployment strategy based on predicted communication demand and sentiment analysis results. This deployment plan is displayed on the operating terminal, providing decision-making support to administrators and security response operators. Administrators can review this plan and make modifications as needed to achieve more appropriate staffing.

[0712] For example, if the emotion engine detects a high level of user anxiety when severe weather is predicted in a certain area, it can automatically adjust the shift schedule to assign experienced operators to that time slot, enabling a quick response.

[0713] An example of a prompt message to input to a generative AI model is: "Based on the user's voice data, analyze the emotions expressed in this call and propose an appropriate operator deployment plan accordingly."

[0714] In this way, servers can leverage data obtained from both communication prediction and sentiment analysis to improve the quality of security responses and increase user trust.

[0715] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0716] Step 1:

[0717] The server collects historical communication history information and external condition information. Specifically, it retrieves past call records, connection status, weather, and event information from the database and integrates them. The input is communication history information and external condition information, and the output is integrated information data. This data forms the basis for the next prediction step.

[0718] Step 2:

[0719] The server uses machine learning algorithms to predict communication based on integrated information. The input is the integrated information data obtained in the previous step, and the data calculations performed are inputting data into the prediction model and calculating output prediction values. The output is prediction data indicating future communication demand. This prediction data is used to optimize human resource allocation.

[0720] Step 3:

[0721] The server analyzes emotions in real time during communication with the user, using speech recognition technology to convert speech data into emotion data. The input is the user's speech data, and the output is the emotion data obtained through analysis. The data processing performed here involves analyzing the tone and speed of the voice and calculating the emotional state using an emotion engine.

[0722] Step 4:

[0723] The server combines communication prediction data and sentiment data to determine the optimal placement of operators. The inputs are communication prediction data and sentiment data, and the output is placement strategy data. Data calculations involve inputting data into a placement model and formulating an output placement strategy. This optimizes appropriate personnel allocation across multiple locations.

[0724] Step 5:

[0725] The terminal displays an optimized deployment strategy to administrators and security response operators. The input is deployment strategy data, and the output is visualized information. Specifically, the terminal screen displays activity and personnel deployment suggestions for each location, allowing administrators and operators to make decisions based on this information.

[0726] Step 6:

[0727] Users modify the deployment strategy as needed via the control terminal, and the updated instructions are sent to the server in real time. Input is the modification instructions from the administrator, and output is the updated deployment data. This operation enables flexible personnel deployment tailored to on-site conditions.

[0728] 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.

[0729] 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.

[0730] 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.

[0731] 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.

[0732] 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.

[0733] 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.

[0734] 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.

[0735] 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.

[0736] 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."

[0737] 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.

[0738] 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.

[0739] 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.

[0740] 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.

[0741] 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.

[0742] 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.

[0743] 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.

[0744] 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.

[0745] 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.

[0746] 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.

[0747] 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.

[0748] 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.

[0749] The following is further disclosed regarding the embodiments described above.

[0750] (Claim 1)

[0751] A means for collecting and integrating past communication history information and external condition information,

[0752] Based on the aforementioned integrated information, a means for making highly accurate predictions about future communications,

[0753] A means for optimizing the allocation of human resources between multiple locations using the aforementioned communication forecast,

[0754] A means for automatically sending instructions to each location based on the optimized arrangement,

[0755] A system that includes this.

[0756] (Claim 2)

[0757] The system according to claim 1, further comprising means for updating placement instructions in real time based on the execution status of the aforementioned instructions.

[0758] (Claim 3)

[0759] The system according to claim 1, further comprising means for displaying the results of the communication prediction and placement optimization on an operating terminal and providing decision support to the administrator.

[0760] "Example 1"

[0761] (Claim 1)

[0762] A means of acquiring past communication history information and external condition information, and integrating and storing it in a database,

[0763] Based on the aforementioned integrated information, a means for accurately predicting future communication demand using a machine learning algorithm,

[0764] Based on the aforementioned communication demand forecast, a means for optimizing the allocation of human resources between multiple locations using operations research techniques,

[0765] A means for automatically distributing instructions to each location in data format based on the aforementioned optimized arrangement,

[0766] A system that includes this.

[0767] (Claim 2)

[0768] The system according to claim 1, further comprising means for dynamically updating placement instructions in real time based on the execution history of the aforementioned instructions.

[0769] (Claim 3)

[0770] The system according to claim 1, further comprising means for displaying the results of the communication prediction and placement optimization on an output terminal and providing the administrator with guidance for adjusting settings.

[0771] "Application Example 1"

[0772] (Claim 1)

[0773] A means of collecting and integrating past trend information and environmental condition information,

[0774] Based on the aforementioned integrated information, a means for accurately predicting future operating conditions,

[0775] A means for optimizing resource allocation between multiple locations using the aforementioned operational status prediction,

[0776] A means for automatically transmitting instructions to each control device based on the optimized assignment,

[0777] A system that includes this.

[0778] (Claim 2)

[0779] The system according to claim 1, further comprising means for updating the assigned instructions in real time based on the execution status of the aforementioned instructions.

[0780] (Claim 3)

[0781] The system according to claim 1, further comprising means for displaying the results of the operational status prediction and allocation optimization on an operating device and providing decision support to the administrator.

[0782] "Example 2 of combining an emotion engine"

[0783] (Claim 1)

[0784] A means for collecting and integrating past communication history information and external condition information,

[0785] Based on the aforementioned integrated information, a means for making highly accurate predictions of future communications using a machine learning algorithm,

[0786] A means of analyzing user emotions and extracting emotional data,

[0787] A means for optimizing the allocation of human resources between multiple locations using the aforementioned communication prediction and sentiment data,

[0788] A means for automatically sending instructions to each location based on the optimized arrangement,

[0789] A system that includes this.

[0790] (Claim 2)

[0791] The system according to claim 1, further comprising means for updating placement instructions in real time based on the execution status of the instructions and the results of user sentiment analysis.

[0792] (Claim 3)

[0793] The system according to claim 1, further comprising means for displaying the results of the communication prediction and placement optimization, and the results of user sentiment analysis, on an operating terminal, and providing decision support to the administrator.

[0794] "Application example 2 of combining emotional engines"

[0795] (Claim 1)

[0796] A means for collecting and integrating past communication history information and external condition information,

[0797] Based on the aforementioned integrated information, a means for making highly accurate predictions about future communications,

[0798] Based on the analysis combining the aforementioned communication forecast and user sentiment data, a means for optimizing the allocation of human resources across multiple locations,

[0799] A means for automatically sending instructions to each location based on the optimized arrangement,

[0800] A method for analyzing emotions in real time from user voice input,

[0801] The analysis results are displayed on the operating terminal, providing a means to support decision-making for security response operators.

[0802] A system that includes this.

[0803] (Claim 2)

[0804] The system according to claim 1, further comprising means for updating placement instructions in real time based on the execution status of the aforementioned instructions.

[0805] (Claim 3)

[0806] The system according to claim 1, further comprising means for displaying the results of the optimization of placement based on the aforementioned communication prediction and sentiment analysis on an operating terminal, and providing decision support to the administrator. [Explanation of Symbols]

[0807] 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 collecting and integrating past communication history information and external condition information, Based on the aforementioned integrated information, a means for making highly accurate predictions about future communications, A means for optimizing the allocation of human resources between multiple locations using the aforementioned communication forecast, A means for automatically sending instructions to each location based on the optimized arrangement, A system that includes this.

2. The system according to claim 1, further comprising means for updating placement instructions in real time based on the execution status of the aforementioned instructions.

3. The system according to claim 1, further comprising means for displaying the results of the communication prediction and placement optimization on an operating terminal and providing decision support to the administrator.

Images