system

Abstract

We provide the system. [Solution] A means for the user to input predicted workload data, A means for users to input actual workload data, A server means for storing the input data, A server means that calculates the deviation rate based on stored prediction data and actual data, A server means for analyzing the cause of the discrepancy and extracting specific topics, A server-based method for predicting future workload based on past business data, A means of displaying calculation results and analysis results to the user, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Due to the deviation between the predicted and actual business volumes, it is difficult to allocate appropriate resources. The object of the present invention is to minimize this deviation and improve business efficiency by identifying the cause of the deviation. Another object is to optimize future staffing by accurately predicting future business volumes.

Means for Solving the Problems

[0005] The present invention solves the above problems by a system including the following means.

[0006] The system provides means for users to input predicted workload data and means for users to input actual workload data. This facilitates data collection. Next, it includes a server for storing the input data and performing appropriate data management. Finally, it includes a server for calculating the deviation rate based on the stored predicted and actual data, thereby quantitatively evaluating the discrepancy between predictions and actuals.

[0007] Furthermore, a server mechanism will be introduced to analyze the causes of the discrepancies and extract specific topics. This will allow for the identification of concrete causes. In addition, a server mechanism will be provided to predict future workloads based on past business data, enabling highly accurate predictions of future workloads. Finally, a system will be provided that includes a means for displaying these calculation and analysis results to the user, allowing the user to check the necessary information in real time.

[0008] These measures make it possible to improve operational efficiency and achieve appropriate resource allocation.

[0009] 1. "Means for users to input predicted workload data" refers to an interface for users to input predicted workload values ​​at the beginning of the month into the system.

[0010] 2. "Means for users to input actual workload data" refers to an interface for users to input their actual workload at the end of the month into the system.

[0011] 3. "Server means for storing input data" refers to a server and associated software system for securely storing predictive and historical data provided by the user.

[0012] 4. "Server means for calculating the deviation rate" refers to a server and related algorithms that have the function of calculating the deviation between stored prediction data and actual data.

[0013] 5. "Server means for analyzing the causes of discrepancies and extracting specific topics" refers to an algorithm for analyzing business data and extracting specific topics that cause discrepancies, and a server that executes that analysis.

[0014] 6. "Server-based methods for predicting future workload" refers to a machine learning model that accurately predicts future workload based on past business data, and a server that executes that prediction.

[0015] 7. "Means of displaying to the user" refers to dashboards or interfaces that visually display calculation results and analysis results to the user.

[0016] 8. "System" refers to the comprehensive set of hardware and software necessary to integrate and operate the above means. [Brief explanation of the drawing]

[0017] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map in which a plurality of emotions are mapped. [Figure 10] It shows an emotion map in which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 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 Embodiment 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

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, a processor with a reference numeral (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of a plurality of 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.

[0021] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0022] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0023] 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).

[0024] 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."

[0025] [First Embodiment]

[0026] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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".

[0038] This system is designed to predict workload, identify discrepancies between actual and projected workloads, analyze the causes, and forecast future workloads. A specific implementation of this system is described below.

[0039] 1. Users enter business data.

[0040] Users access the system and utilize an interface to input their projected workload at the beginning of each month. For example, they might input "1000 inquiries are expected" at the start of the month. At the end of the month, they input actual data through a similar interface. For example, they might input "1200 inquiries were the actual number" at the end of the month. This allows users to easily register both projections and actual figures.

[0041] 2. The server saves the data.

[0042] The predicted and actual workload data entered by the user is received by the server. The server verifies that the received data is in the correct format and saves it to the database. This saved data is then used as the basis for subsequent calculations and analyses.

[0043] 3. The server calculates the deviation rate.

[0044] The server calculates the deviation rate based on the stored predicted and actual data. For example, if the predicted workload is 1000 and the actual workload is 1200, the server performs the following calculation: Deviation rate = (Actual workload - Predicted workload) / Predicted workload 100. In this example, the deviation rate is 20%. This calculation result is used to allow users to easily understand performance over a specific period.

[0045] 4. The server identifies the cause of the discrepancy.

[0046] The server analyzes stored business data to identify the cause of the discrepancy. For example, the server can find patterns based on the date, time, and category of inquiries, identifying that inquiries were concentrated on specific days or in specific categories. This allows the server to report the specific cause of the discrepancy to the user.

[0047] 5. The server predicts future workload.

[0048] The server collects historical business data and uses it to build a machine learning model. For example, it uses data on predicted and actual workload for the past six months. This model can accurately predict workload for the next few months. The prediction results are output in the form of, for example, "We predict 1200 inquiries next month and 1100 inquiries the month after."

[0049] 6. Display the results to the user.

[0050] The server generates a report summarizing the results of the deviation rate calculation, the identification of the cause of the deviation, and future workload forecasts. This report is displayed in real time on the user's dashboard. Based on this, users can adjust their work and optimize staffing.

[0051] Specific example

[0052] For example, if a user enters "1000 predicted workloads for this month" and "1200 actual workloads at the end of the month," the server saves this data and calculates that "the discrepancy rate is 20%." Further analysis identifies the cause of the discrepancy, such as "500 inquiries concentrated on a specific day." Based on this, the server refers to past data to predict the workload for the following months and displays to the user, "1200 inquiries are predicted for next month, and 1100 for the month after."

[0053] This allows users to understand their future workload and make appropriate resource allocations and personnel assignments. Each of these methods significantly improves operational efficiency and minimizes discrepancies.

[0054] The following describes the processing flow.

[0055] Step 1:

[0056] Users input workload forecast data.

[0057] Users log in to the system and enter their monthly workload forecast data into a dedicated input form. The input fields include the number of inquiries and other forecast parameters. After entering the data, they press the submit button to send it to the server.

[0058] Step 2:

[0059] The server stores the prediction data.

[0060] The server receives the prediction data submitted by the user and performs a format check (validation). If the data is correct, it executes an SQL command (e.g., INSERT INTO) to save the prediction data to the database. Once the saving is complete, it notifies the user that the data has been successfully saved.

[0061] Step 3:

[0062] Users enter performance data.

[0063] At the end of the month, users log back into the system and enter their actual workload data. The input fields include the actual number of inquiries and other performance parameters. After entering the data, they press the submit button again to send it to the server.

[0064] Step 4:

[0065] The server saves performance data.

[0066] The server receives the performance data submitted by the user and performs a format check (validation). If the data is correct, it executes an SQL command (e.g., INSERT INTO) to save the performance data to the database. Once the saving is complete, it notifies the user that the data has been saved successfully.

[0067] Step 5:

[0068] The server calculates the deviation rate.

[0069] The server retrieves forecast and actual data for the relevant month from the database. Next, it calculates the deviation rate based on this data. The formula is: Deviation Rate = (Actual Workload - Forecasted Workload) / Forecasted Workload 100. The calculation result is stored as internal data.

[0070] Step 6:

[0071] The server identifies the cause of the discrepancy.

[0072] The server analyzes past business data to identify patterns such as concentrated inquiries on specific days or categories. For example, the server might identify a cluster of 500 inquiries on a particular day and extract detailed log data for that day. This information is compiled and reported to the user as the cause of the discrepancy.

[0073] Step 7:

[0074] The server predicts future workload.

[0075] The server collects historical business data from the database and uses it to build a machine learning model (e.g., a regression analysis model). Next, it uses this model to predict the workload for the next few months. For example, it might predict 1200 inquiries next month and 1100 inquiries the month after. This prediction is also stored as internal data.

[0076] Step 8:

[0077] The server displays the calculation results to the user.

[0078] The server generates a report summarizing the results of the deviation rate calculation, the results of identifying the cause of the deviation, and the results of future workload forecasts. This report is displayed on the user's dashboard in real time. Based on this information, users can improve the efficiency of their work and allocate resources appropriately.

[0079] These steps allow users to understand the discrepancy between monthly forecasts and monthly actuals, identify the causes to improve operational efficiency, and allocate resources appropriately based on future workload forecasts.

[0080] (Example 1)

[0081] 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."

[0082] Conventional workload forecasting systems lack sufficient functionality to automatically calculate and analyze discrepancies between forecasts and actual results, making it difficult to identify the causes and improve the accuracy of future workload forecasts. In addition, the lack of an interface that allows users to easily input work data and check the results in real time is also a problem. While this is expected to improve operational efficiency, in reality, it requires a lot of manual work, which is burdensome.

[0083] 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.

[0084] In this invention, the server includes means for the user to input predicted workload data, means for the user to input actual workload data, means for the server device to receive the input data, validate the data format and store it, means for calculating the deviation rate based on the stored predicted and actual data, means for analyzing the cause of the deviation and extracting specific patterns, means for constructing a machine learning model to predict future workload based on past work data and making predictions, and means for displaying the calculation results and analysis results to the user in real time. As a result, the user can immediately check the difference between the predicted and actual workload data they have entered, quickly identify the cause of the deviation, and predict future workload with high accuracy. Consequently, it is possible to adjust operations and optimize personnel allocation, significantly improving overall operational efficiency.

[0085] "The means by which users input workload forecast data" refers to the interface that allows users to input workload forecast data into the system. This interface is designed to allow users to easily input data.

[0086] "The means by which users input actual workload data" refers to the interface that allows users to input data on their actual workload into the system. This is also designed to allow users to input data easily.

[0087] "A means of receiving data via a server device, validating the data format, and storing it" refers to the function where a server receives data sent from a user, verifies whether the data format is correct, and then stores it in a database.

[0088] "Means for calculating the deviation rate based on stored forecast and actual data" refers to a function that calculates the deviation rate using the forecast and actual workload data stored on the server. The deviation rate is a value that expresses the difference between the forecast and the actual results.

[0089] "Means for analyzing the cause of discrepancies and extracting specific patterns" refers to a function in which the server analyzes stored data to identify the cause of discrepancies and extracts patterns based on specific dates, times, or categories.

[0090] "A means of building a machine learning model to predict future workload based on past business data" refers to a function where the server analyzes past business data to build a machine learning model and uses that model to predict future workload.

[0091] "A means of displaying calculation and analysis results to the user in real time" refers to a function that displays the calculated deviation rate, analysis results, and predicted future workload on the user's dashboard in real time.

[0092] This invention is a system for predicting workload, identifying discrepancies between predicted and actual workload, analyzing the causes, and predicting future workload. A specific embodiment of this system is described below.

[0093] The user first inputs predicted and actual workload data. The input interface is provided via a web browser, with a simple form for easy data entry. For example, the user might input "Predicted workload for this month: 1000 items" and "Actual workload at the end of the month: 1200 items." This data is then sent to the server in JSON format.

[0094] The server is implemented using Node.js and receives HTTP requests using the Express framework. It receives the sent JSON data and validates its contents. After successful validation, the data is stored in MongoDB. MongoDB is connected to the server via Mongoose, and predicted workload data and actual workload data are stored in separate collections.

[0095] Based on the stored data, the server calculates the deviation rate. The formula used for the calculation is as follows: Deviation rate = (Actual workload - Forecasted workload) / Forecasted workload 100. For example, if the forecast is 1000 and the actual workload is 1200, the deviation rate will be calculated as 20%. This calculation result is temporarily stored in memory.

[0096] Next, the server analyzes the data to identify the cause of the discrepancy. It runs aggregate queries to find patterns based on specific days or categories, and if, for example, 500 inquiries were concentrated on a particular day, it analyzes the details to identify the cause.

[0097] The server collects business data from the past six months and builds a predictive model using a Python machine learning library (e.g., Scikit-learn). Using the trained model, it predicts future business volume. The prediction results are output in the format of "1200 inquiries are predicted for next month, and 1100 inquiries for the month after."

[0098] The calculation results, analysis results, and prediction results are compiled into a report. The server generates this report in HTML or PDF format and displays it in real time on the user dashboard. Visualization tools such as Grafana are used on the dashboard, and the data is updated in real time. Based on this, users can adjust their work and optimize staffing.

[0099] For example, if a user inputs, "This month's projected workload is 1000 inquiries. The actual workload was 1200. Based on this, calculate the discrepancy rate and identify the cause. Then, predict the workload for next month and the month after," the server will save this data, identify a "20% discrepancy rate," and determine that 500 inquiries were concentrated on a specific day. Subsequently, the server will display to the user in real time the predicted results: 1200 inquiries for the next month and 1100 inquiries for the month after. This allows the user to understand future workloads and make appropriate resource allocations and personnel assignments.

[0100] This invention significantly improves operational efficiency and minimizes the occurrence of discrepancies.

[0101] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0102] Step 1:

[0103] Users input workload forecast data.

[0104] Users access the system and input workload forecast data through the interface. The input data is sent to the server in JSON format. For example, inputting "This month's forecast workload is 1000 items." Input (workload forecast data) → Output (data in JSON format)

[0105] Step 2:

[0106] The server receives the prediction data and performs validation.

[0107] The server is implemented using Node.js and receives HTTP requests using the Express framework. It validates the structure and content of the received JSON data to ensure it is in the correct format. Input (JSON-formatted workload forecast data) → Output (Validation result: Success / Failure)

[0108] Step 3:

[0109] The server stores the prediction data.

[0110] If validation is successful, the server connects to MongoDB via Mongoose and saves the predicted data. When saving, it saves the data to a collection of predicted workload data within the database. Input (validated workload prediction data) → Output (save complete message)

[0111] Step 4:

[0112] Users input actual workload data.

[0113] Users input their actual workload data for the current month through a similar interface. For example, they might input "This month's actual workload is 1200 items." Input (actual workload data) → Output (data in JSON format)

[0114] Step 5:

[0115] The server receives the performance data and performs validation.

[0116] The server receives an HTTP request and validates the structure and content of the received actual workload data. Input (actual workload data in JSON format) → Output (validation result: success / failure)

[0117] Step 6:

[0118] The server saves performance data.

[0119] If validation is successful, the server saves the actual workload data to the MongoDB collection of actual workload data. Input (validated actual workload data) → Output (save complete message)

[0120] Step 7:

[0121] The server calculates the deviation rate.

[0122] The server calculates the deviation rate based on the stored predicted workload data and actual workload data. The formula is as follows: Deviation Rate = (Actual Workload - Predicted Workload) / Predicted Workload 100. Input (Predicted Workload Data, Actual Workload Data) → Output (Deviation Rate)

[0123] Step 8:

[0124] The server analyzes the cause of the discrepancy.

[0125] The server analyzes stored business data to identify the cause of the discrepancy. For example, it uses the Parse function to find patterns based on specific days or categories. Input (business data) → Output (analysis results regarding the cause of the discrepancy)

[0126] Step 9:

[0127] The server predicts future workload.

[0128] The server collects historical business data and builds a predictive model using the Python machine learning library (Scikit-learn). Using the trained model, it predicts the workload for the following two months. Input (historical business data) → Output (future workload prediction)

[0129] Step 10:

[0130] The server compiles the results and generates a report.

[0131] The server generates a report summarizing the calculation results of the deviation rate, the results of identifying the cause of the deviation, and the forecast of future workload. This report is output in HTML or PDF format. Input (calculation results, analysis results, forecast results) → Output (report)

[0132] Step 11:

[0133] The device displays the report.

[0134] The user's device displays reports sent from the server on a dashboard. Visualization tools such as Grafana are used on the dashboard, and data is updated in real time. Input (Report) → Output (Display on Dashboard)

[0135] (Application Example 1)

[0136] 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."

[0137] Traditional logistics centers have struggled to efficiently analyze discrepancies between projected and actual workload forecasts, making it difficult to optimize resource allocation and staffing. Leaving this problem unaddressed leads to decreased operational efficiency, increased costs, and negatively impacts service quality.

[0138] 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.

[0139] In this invention, the server includes means for the user to input predicted workload data, means for the user to input actual workload data, server means for storing the input data, server means for calculating the deviation rate based on the stored predicted and actual data, server means for analyzing the causes of the deviation and extracting specific topics, server means for predicting future workload based on past business data, means for displaying the calculation results and analysis results to the user, means for predicting future workload with high accuracy using a machine learning model, and means for optimizing the allocation of business resources within the logistics center. This enables accurate prediction of workload, efficient deviation analysis, and appropriate resource allocation.

[0140] A "user" is someone who uses the system to input predicted workload data and actual workload data.

[0141] "Predicted workload data" refers to data entered by users at the beginning of the month or other times when they anticipate their workload.

[0142] "Actual workload data" refers to the actual workload data entered by users at the end of each month.

[0143] A "server" is a device or system that stores predicted and actual workload data, calculates deviation rates, analyzes causes, and predicts future workload.

[0144] "Deviation rate" is an indicator that expresses the difference between predicted workload and actual workload as a percentage.

[0145] "Cause of discrepancy" refers to the reason for the difference between the predicted workload and the actual workload.

[0146] "Specific topics" refer to areas of interest or themes that have been identified in order to pinpoint the causes of the discrepancy.

[0147] "Past business data" refers to previously recorded predicted workload data and actual workload data.

[0148] A "machine learning model" is an algorithm used to predict future workloads based on past data.

[0149] "Resource allocation" refers to the appropriate placement of personnel and equipment within a logistics center.

[0150] A system implementing this invention specifically includes an application for predicting workload and managing efficiency in a logistics center. This application allows the user to input operational data, which is then processed, analyzed, and predicted by a server, with the results displayed to the user in real time.

[0151] Users can input predicted and actual workload data using applications installed on smartphones, smart glasses, head-mounted displays, or robots. For example, they might input "1000" for the predicted workload for the month and "1200" for the actual workload at the end of the month.

[0152] The server receives the data, validates its format, and stores it in the database. Based on the stored predicted and actual workload data, the server calculates the deviation rate. For example, if the predicted workload is 1000 and the actual workload is 1200, the deviation rate is 20%. This calculated deviation rate is used to help users easily understand performance over a specific period.

[0153] Furthermore, the server analyzes stored business data to identify the cause of the discrepancy. For example, it might identify that the workload was concentrated on a particular day or in a particular category. This allows the server to report the specific cause of the discrepancy to the user.

[0154] The server also builds machine learning models based on past business data to predict future workloads. These models are trained using, for example, data on predicted and actual workloads over the past six months. This allows for highly accurate predictions of workloads for the following month and the month after. For example, the output might state, "We predict 1200 inquiries next month and 1100 inquiries the month after."

[0155] Calculation and analysis results are displayed in real time on the user's dashboard. Users can use this information to adjust operations and optimize staffing. This dashboard can also be viewed at any time by field workers using smart glasses or head-mounted displays.

[0156] Implementing this system will improve the accuracy of business forecasts, optimize resource allocation, and increase the operational efficiency of the logistics center. Furthermore, the calculation results will be provided to the user as specific prompt messages. For example, the following prompt messages may be generated:

[0157] "Our projected workload for December was 1,000 cases, but the actual volume was 1,500. Please tell us the discrepancy rate and the reasons for it. Also, please provide a workload forecast for next month."

[0158] In this way, users can utilize the system to achieve efficient business operations.

[0159] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0160] Step 1:

[0161] The user enters predicted workload data on a terminal. The entered data is sent to the server as predicted workload data. As an example, the user might enter "This month's predicted workload is 1000 items."

[0162] Step 2:

[0163] Users input actual workload data on their terminals. This data is entered at the end of each month and sent to the server. For example, a user might enter, "This month's actual workload is 1200 items."

[0164] Step 3:

[0165] The server receives predicted and actual workload data and validates its format. After verifying that the data is in a valid format, it is saved to the database.

[0166] Step 4:

[0167] The server calculates the deviation rate based on the stored predicted and actual data. Specifically, it performs the following calculations:

[0168] The deviation rate is calculated as follows: Deviation rate = (Actual workload - Forecasted workload) / Forecasted workload 100. For example, if the forecast is 1000 and the actual workload is 1200, the deviation rate is 20%. The calculation result is output as the deviation rate and stored in the database.

[0169] Step 5:

[0170] The server analyzes stored business data to identify the cause of the discrepancy. For example, it finds patterns based on the date, time, and category of inquiries, identifying that inquiries were concentrated on specific days or in specific categories. Based on these analysis results, it outputs the cause of the discrepancy.

[0171] Step 6:

[0172] The server collects historical business data and uses it to build a machine learning model. The model is trained using data on predicted and actual workloads over the past six months. This allows for highly accurate predictions of future workloads. The output is a predicted workload, such as "1200 cases next month, 1100 cases the month after."

[0173] Step 7:

[0174] The server generates a report summarizing the calculation and analysis results, which is then displayed in real time on the user's dashboard. This dashboard is designed to be accessible to field workers using smart glasses or head-mounted displays. Users can then use this information to adjust operations and optimize staffing.

[0175] Step 8:

[0176] The server generates prompt messages based on user input. For example, it might create a specific prompt message such as, "The predicted workload for December was 1000, but the actual workload was 1500. Please tell me the discrepancy rate and the reason. Also, please provide a workload forecast for next month." Based on this, the user can take actions to achieve efficient business operations.

[0177] 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.

[0178] This system not only predicts workload, identifies discrepancies with actual results, analyzes causes, and forecasts future workload, but also achieves even more accurate analysis and prediction by combining it with an emotion engine that recognizes user emotions. The specific implementation details are described below.

[0179] 1. Users enter business data.

[0180] Users access the system and utilize an interface to input their projected workload at the beginning of each month. For example, they might input "1000 inquiries are expected" at the start of the month. At the end of the month, they input actual data through a similar interface. For example, they might input "1200 inquiries were the actual number" at the end of the month. This allows users to easily register both projections and actual figures.

[0181] 2. The server saves the data.

[0182] The predicted and actual workload data entered by the user is received by the server. The server verifies that the received data is in the correct format and saves it to the database. This saved data is then used as the basis for subsequent calculations and analyses.

[0183] 3. The server calculates the deviation rate.

[0184] The server calculates the deviation rate based on the stored predicted and actual data. For example, if the predicted workload is 1000 and the actual workload is 1200, the server performs the following calculation: Deviation rate = (Actual workload - Predicted workload) / Predicted workload 100. In this example, the deviation rate is 20%. This calculation result is stored as internal data.

[0185] 4. The server collects sentiment data.

[0186] The emotion engine recognizes the user's emotions when they use the system. For example, it analyzes the user's facial expressions and tone of voice when they input business data to collect emotional data such as "stress" and "satisfaction."

[0187] 5. The server identifies the cause of the discrepancy.

[0188] The server further analyzes stored operational data based on the collected emotional data. For example, if the emotional data indicates "stress," it examines detailed logs such as the inquiry status and error count at that time to identify the cause of the discrepancy. This analysis allows the server to consider the emotional factors behind concentrated inquiries on specific days or in specific categories.

[0189] 6. The server predicts future workload.

[0190] The server collects historical business data from the database and integrates it with the sentiment data collected by the sentiment engine to build a machine learning model (e.g., a regression analysis model). This model can accurately predict the workload for the next few months. This prediction result is also stored as internal data.

[0191] 7. The server displays the calculation results to the user.

[0192] The server generates a report summarizing the results of the deviation rate calculation, the results of identifying the cause of the deviation, and the results of future workload forecasts. This report is displayed on the user's dashboard in real time. Based on this information, users can improve the efficiency of their work and allocate resources appropriately.

[0193] Specific example

[0194] For example, if a user enters "1000 predicted workloads for this month" and "1200 actual workloads at the end of the month," the server saves this data and calculates that the "deviation rate is 20%." Further analysis identifies the cause of the deviation as "500 inquiries concentrated on a specific day" and that the user felt "stressed" on that day. Based on this, the server refers to past data to predict the workload for the following months and displays to the user "1200 inquiries are predicted for next month, and 1100 for the month after."

[0195] This allows users to understand their future workload while taking emotional data into account, enabling appropriate resource allocation and process improvements. Each of these methods significantly improves work efficiency and minimizes discrepancies. Utilizing emotional data allows for more flexible responses that take human factors into account.

[0196] The following describes the processing flow.

[0197] Step 1:

[0198] Users input workload forecast data.

[0199] Users log in to the system and enter their monthly workload forecast data into a dedicated input form. The input fields include the number of inquiries and other forecast parameters. After entering the data, they press the submit button to send it to the server.

[0200] Step 2:

[0201] The server stores the prediction data.

[0202] The server receives the prediction data submitted by the user and performs a format check (validation). If the data is correct, it executes an SQL command (e.g., INSERT INTO) to save the prediction data to the database. Once the saving is complete, it notifies the user that the data has been successfully saved.

[0203] Step 3:

[0204] Users enter performance data.

[0205] At the end of the month, users log back into the system and enter their actual workload data. The input fields include the actual number of inquiries and other performance parameters. After entering the data, they press the submit button again to send it to the server.

[0206] Step 4:

[0207] The server saves performance data.

[0208] The server receives the performance data submitted by the user and performs a format check (validation). If the data is correct, it executes an SQL command (e.g., INSERT INTO) to save the performance data to the database. Once the saving is complete, it notifies the user that the data has been saved successfully.

[0209] Step 5:

[0210] The server calculates the deviation rate.

[0211] The server retrieves forecast and actual data for the relevant month from the database. Next, it calculates the deviation rate based on this data. The formula is: Deviation Rate = (Actual Workload - Forecasted Workload) / Forecasted Workload 100. The calculation result is stored as internal data.

[0212] Step 6:

[0213] Recognize user emotions and collect data.

[0214] When a user uses the system, an emotion engine activates, analyzing the user's facial expressions and tone of voice. For example, while a user is operating an input form or entering business data, the system uses a camera and microphone to collect emotion data.

[0215] Step 7:

[0216] The server stores emotional data.

[0217] The collected sentiment data is sent to the server for formatting checks (validation). If the data is correct, an SQL command (e.g., INSERT INTO) is executed to save the sentiment data to the database. Once saved, the sentiment data is integrated with other business data.

[0218] Step 8:

[0219] The server analyzes and identifies the cause of the discrepancy based on emotional data.

[0220] The server analyzes the cause of the discrepancy based on stored emotional and operational data. For example, if it examines data from a specific day and finds that the user was experiencing "stress" on that day, it checks the detailed log data of inquiries that occurred on that day. This allows it to identify why the discrepancy occurred on that day, including the underlying emotional factors.

[0221] Step 9:

[0222] The server predicts future workload based on past data.

[0223] The server integrates historical business data and sentiment data from the database and uses this to build a machine learning model (e.g., a regression analysis model). This model allows for highly accurate predictions of workload for the next few months.

[0224] Step 10:

[0225] The server displays the calculation results and prediction results to the user.

[0226] The server generates a report summarizing the results of the deviation rate calculation, the results of identifying the cause of the deviation, and the results of future workload forecasts. This report is displayed on the user's dashboard in real time. Based on this information, users can improve the efficiency of their work and allocate resources appropriately.

[0227] Specific example

[0228] For example, if a user enters "1000 predicted workloads for this month" and "1200 actual workloads at the end of the month," the server saves this data and calculates that the "deviation rate is 20%." Furthermore, the system senses that the user is experiencing "stress" while entering the data and records this. Analysis identifies the cause of the deviation as "500 inquiries concentrated on a particular day" and that the user was experiencing "stress" on that day. Based on this, the system refers to past data to predict the workload for the following months and displays to the user that "1200 inquiries are predicted for next month, and 1100 for the month after."

[0229] By combining this with an emotion engine, it becomes possible to provide more flexible responses that take human factors into account, further improving work efficiency.

[0230] (Example 2)

[0231] 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".

[0232] Conventional workload forecasting systems have faced challenges in identifying the causes of discrepancies between predicted and actual workloads, as well as in the limited accuracy of future workload forecasts. This has resulted in limitations in improving operational efficiency and appropriate resource allocation. Furthermore, systems that do not consider human emotions make it difficult to comprehensively analyze the impact of actual work processes and users' psychological states.

[0233] 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.

[0234] In this invention, the server includes means for collecting emotional data when a user inputs data, server means for identifying the cause of discrepancies based on the collected emotional data, and server means for predicting future workload based on past work data. This makes it possible to more accurately identify the cause of discrepancies between predicted and actual workload and to predict future workload with high accuracy. Furthermore, by incorporating user emotional data into the analysis, it becomes possible to respond more flexibly, taking human factors into consideration, thereby improving work efficiency and achieving appropriate resource allocation.

[0235] A "user" is a person who uses the system to input workload data and performance data, and performs operations to obtain analysis results and prediction results.

[0236] "Predicted workload data" refers to data about the workload that users expect to occur during a specific period in the future.

[0237] "Actual workload data" refers to data on the actual workload generated by a user during a specific period.

[0238] A "server" is a computing system that receives, stores, and analyzes data entered by users, and provides calculation results, prediction results, and other information.

[0239] "Validation" is the process of verifying whether the format and content of the entered data are correct.

[0240] A "database" is an electronic data storage system for systematically organizing, storing, searching, and managing various types of data.

[0241] The "deviation rate" is the percentage that shows the difference between predicted workload data and actual workload data, and is calculated based on a formula.

[0242] "Emotional data" is data obtained by analyzing a user's emotions from their facial expressions, tone of voice, etc., and it indicates emotional states such as "stress" or "satisfaction."

[0243] A "machine learning model" is an algorithm or mathematical model used to learn from past data and predict future data.

[0244] "Causes of discrepancy" refers to the factors that cause the difference between predicted workload data and actual workload data.

[0245] A "report" is a document that summarizes calculation results, analysis results, and prediction results, and is an aggregation of analytical information provided to the user.

[0246] Modes for carrying out the invention

[0247] The system implementing this invention has a set of functions in which, as a primary means, the user inputs business data, and the server analyzes, stores, and predicts that data. Specifically, the hardware and software used in each step include the following:

[0248] User data entry method

[0249] Users access the system using a dedicated web browser or mobile application via an internet-connected device (e.g., PC, tablet, smartphone). Users log in to the system and input projected workload data at the beginning of the month and actual workload data at the end of the month. For example, they might input "Projected workload for this month: 1000 items" and then "Actual workload: 1200 items" at the end of the month.

[0250] Server-based data storage and validation

[0251] The entered data is sent to the server. The server validates the data format (e.g., confirms that the number of queries is an integer) and displays an error message to the user if there is any inappropriate data. Data in the correct format is stored in the database. This database uses a relational database management system such as SQL.

[0252] Calculation of deviation rate

[0253] The server calculates the deviation rate based on the stored predicted workload data and actual workload data. For example, if the predicted workload is 1000 and the actual workload is 1200, the server calculates the deviation rate as follows: "Deviation Rate = (Actual Workload - Predicted Workload) / Predicted Workload 100". In this example, the deviation rate is calculated to be 20%. The calculation result is stored in the database.

[0254] Collection of user sentiment data

[0255] As the user enters data, the system's built-in emotion engine activates and analyzes the user's facial expressions and voice tone through the webcam and microphone. The emotion engine generates emotional data such as "stress" and "satisfaction" from this input and sends and stores it on the server.

[0256] Identifying the cause of the discrepancy

[0257] The server analyzes stored business data based on the collected sentiment data. For example, if the sentiment data indicates "stress," it investigates the detailed logs for that period and identifies that inquiries concentrated on specific days or categories are causing the discrepancies. This allows for a more detailed analysis of factors hindering business efficiency.

[0258] Predicting future workload

[0259] The server uses historical business data and sentiment data to build a machine learning model (e.g., a regression analysis model) to predict future workload. This model is implemented using programming languages ​​such as Python or R. For example, it might produce results such as, "We predict 1200 inquiries next month and 1100 inquiries the month after."

[0260] Displaying Results

[0261] The server generates a report summarizing the calculated deviation rate, identified deviation causes, and future workload forecasts. This report is displayed on the user's dashboard in real time. Based on this information, users can take actions to improve work efficiency.

[0262] Specific example

[0263] For example, if a user enters "1000 predicted workloads for this month" and "1200 actual workloads at the end of the month," the server saves this data and calculates that the "deviation rate is 20%." Furthermore, it identifies that 500 inquiries were concentrated on a specific day and that the user felt "stressed" on that day. Based on this information, the server predicts the workload for the following months and displays to the user that "1200 inquiries are predicted for next month, and 1100 for the month after."

[0264] Example of a prompt

[0265] "Analyze the discrepancy rate and its causes when the projected workload for this month is 1000 items and the actual workload at the end of the month is 1200 items."

[0266] This allows users to understand their future workload while taking emotional data into account, enabling appropriate resource allocation and process improvements. Each of these methods significantly improves work efficiency and minimizes discrepancies. Utilizing emotional data allows for more flexible responses that take human factors into account.

[0267] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0268] Specific processing steps of the program for this system

[0269] Step 1: The user enters business data.

[0270] input:

[0271] Predicted workload data (e.g., "1000 inquiries are predicted")

[0272] Actual workload data (e.g., "Actual number of inquiries: 1200")

[0273] process:

[0274] Users log in to the system using a web browser or mobile app.

[0275] After logging in, the business data entry screen will be displayed.

[0276] At the beginning of the month, you will enter your projected workload into the input form, and at the end of the month, you will enter your actual workload.

[0277] Click the submit button on the form to send the data to the server.

[0278] output:

[0279] Business data (predicted workload data and actual workload data) is sent to the server.

[0280] Step 2: The server saves the data

[0281] Input:

[0282] Business data sent from the user

[0283] Processing:

[0284] The server validates the data received from the user. For example, it checks whether the number of inquiries is an integer.

[0285] If the validation is successful, the data is saved to the database.

[0286] If the validation fails, an error message is returned to the user.

[0287] Output:

[0288] Business data saved in the database

[0289] Validation result (success / failure)

[0290] Success message or error message

[0291] Step 3: The server calculates the deviation rate

[0292] Input:

[0293] Predicted business volume data and actual business volume data saved in the database

[0294] Processing:

[0295] The server retrieves the predicted business volume data and actual business volume data from the database.

[0296] The deviation rate is calculated by the following formula: "Deviation rate = (Actual business volume - Predicted business volume) / Predicted business volume * 100".

[0297] Save the calculation result to the database.

[0298] Output:

[0299] The deviation rate saved in the database

[0300] Step 4: The server collects emotion data

[0301] Input:

[0302] The expression and voice tone when the user inputs business data (collected through the webcam and microphone)

[0303] Processing:

[0304] The server starts the emotion engine and analyzes the user's expression and voice in real time.

[0305] The emotion engine generates emotion data (e.g., "stress" or "satisfaction").

[0306] Send the generated emotion data to the server and save it to the database.

[0307] Output:

[0308] The emotion data saved in the database

[0309] Step 5: The server identifies the cause of the deviation [[ID=�3]]

[0310] [[ID=�5]]Input:

[0311] The saved emotion data

[0312] The predicted business volume data, the actual business volume data, and the deviation rate

[0313] Processing:

[0314] The server performs analysis based on stored business data and emotional data.

[0315] Extract detailed data on periods when emotional data indicates "stress."

[0316] We will investigate detailed logs of inquiries concentrated on specific days or time periods to identify the cause of the discrepancy.

[0317] output:

[0318] Identified causes of discrepancies

[0319] Step 6: The server predicts future workload.

[0320] input:

[0321] Past business data

[0322] Emotional data

[0323] process:

[0324] The server builds a machine learning model (e.g., a regression analysis model) based on historical data.

[0325] We will use the constructed model to predict future workload.

[0326] Save the prediction results to the database.

[0327] output:

[0328] Future workload forecast results stored in the database

[0329] Step 7: The server displays the calculation results to the user.

[0330] input:

[0331] Deviation rate

[0332] Causes of discrepancy

[0333] Future workload forecast results

[0334] process:

[0335] The server integrates the deviation rate, the cause of the deviation, and the forecast results for future workload to create a report.

[0336] After the report is generated, it will be displayed in real time on the user's dashboard.

[0337] output:

[0338] Reports displayed on the user dashboard

[0339] This allows users to understand their future workload while taking emotional data into account, enabling appropriate resource allocation and process improvements. Each of these methods significantly improves work efficiency and minimizes discrepancies. Furthermore, utilizing emotional data allows for more flexible responses that take human factors into account.

[0340] (Application Example 2)

[0341] 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 device 14 will be referred to as the "terminal."

[0342] Logistics centers need a function to analyze the discrepancy between predicted and actual workloads and to predict future workloads with high accuracy. In particular, there is a need for more accurate predictions, early detection of problems, and efficient resource allocation by utilizing real-time sentiment data of managers. However, conventional systems do not include sentiment data in their analysis, which limits their ability to identify the causes of discrepancies and improve the accuracy of future workload predictions.

[0343] 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.

[0344] In this invention, the server includes means for the user to input predicted workload data, means for the user to input actual workload data, information processing means for storing the input data, information processing means for calculating a deviation rate based on the stored predicted and actual data, means for collecting user emotion data using an emotion recognition engine, information processing means for analyzing the causes of the deviation and extracting specific topics, information processing means for predicting future workload based on past work data, and means for analyzing emotion data and displaying it together with the deviation rate. This makes it possible to analyze the causes of workload deviations, including user emotion data, and improve the accuracy of future workload predictions.

[0345] "Predicted workload data" refers to data that shows the amount of work that users predict will be processed within a certain period.

[0346] "Actual workload data" refers to data that shows the actual amount of work processed within a certain period.

[0347] "Information processing device means" refers to a server or computer system that performs data storage, calculation, analysis, and display.

[0348] The "deviation rate" is a value that expresses the difference between the predicted workload and the actual workload as a percentage.

[0349] An "emotion recognition engine" is software or hardware used to analyze a user's emotions and collect emotional data.

[0350] "Emotional data" refers to data that expresses a user's emotional state using numerical values ​​or categories.

[0351] "Specific topics" refer to specific items or themes extracted from the analysis results of the causes of the discrepancies.

[0352] "Future workload forecasting" is a process of estimating future workloads based on past and present data.

[0353] A "generative AI model" is an artificial intelligence model used to extract features from accumulated data and predict future situations.

[0354] A "prompt" is an instruction or question that is input to a generative AI model.

[0355] As a specific embodiment of this invention, we will explain using a "smart logistics manager" that uses a head-mounted display (HMD) for a logistics center as an example.

[0356] 1. Input of predicted and actual workload.

[0357] The user wears an HMD (Head-Mounted Display) and inputs their projected workload at the beginning of the month. For example, they might input "Projected workload for this month: 10,000 units." Then, at the end of the month, they similarly input their actual workload. For example, they might input "Actual workload: 11,500 units." This allows the user to provide projected and actual workload data to the information processing device.

[0358] 2. Data storage and calculation of deviation rate

[0359] The server receives predicted and actual workload data entered by the user, validates the data format, and then stores it in the information processing device. Based on the stored data, it calculates the deviation rate between the predicted and actual data. For example, if the predicted volume is 10,000 and the actual volume is 11,500, the server calculates the deviation rate as 15% and stores it as internal data.

[0360] 3. Collection of emotional data

[0361] The emotion recognition engine integrated into the HMD analyzes the user's facial expressions and voice tone, collecting emotional data. For example, it quantifies and records the user's stress and satisfaction levels when entering work data. This emotional data is then stored in the information processing device.

[0362] 4. Identifying the causes of the discrepancy and predicting future workload.

[0363] The server further analyzes the stored business data based on the collected emotional data to identify the cause of the discrepancy. For example, it identifies days with a high amount of emotional data indicating stress and analyzes the inquiry status and error count for those days. Next, it integrates past business data and emotional data to build a generative AI model and predict future workload. The results of the future workload prediction are also stored as internal data.

[0364] 5. Creating and displaying reports to users

[0365] The server generates a report summarizing the results of the deviation rate calculation, the results of identifying the cause of the deviation, and the results of future workload forecasts. This report is displayed in real time on the user's HMD, and the user can use this information to make appropriate resource allocations and business improvements.

[0366] Hardware and software to be used

[0367] Hardware: Head-mounted display (e.g., general term)

[0368] Software: Emotion recognition engine, information processing unit, generative AI model

[0369] Specific example

[0370] For example, if an administrator wears an HMD and inputs "Predicted workload for this month is 10,000 units," and then at the end of the month inputs "Actual workload is 11,500 units," the server calculates a discrepancy of 15%. Furthermore, the emotion recognition engine analyzes the collected emotion data and identifies that 500 packages were shipped on a specific day and that the user was feeling stressed on that day. Based on this, the server uses a generative AI model to predict future workload and displays to the administrator that "12,000 packages are predicted for next month, and 11,000 packages for the month after."

[0371] Examples of prompts to input into a generative AI model:

[0372] The user wears an HMD and enters "Predicted workload for this month: 10,000 units." At the end of the month, enter the actual volume as "11,500 units." The system automatically calculates the deviation rate and performs a cause analysis for the specific day based on sentiment data.

[0373] The above describes the "mode for carrying out the invention." By using a head-mounted display, real-time input of business data and collection of sentiment data become possible, enabling highly accurate workload prediction and efficient resource allocation.

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

[0375] Step 1: The user enters the predicted workload data.

[0376] ---

[0377] The user uses a head-mounted display (HMD) to input projected workload data at the beginning of the month. During this process, the user enters information such as "Projected workload for this month: 10,000 units" through the HMD's interface. This input data is then transmitted to an information processing unit.

[0378] Input: Forecasted workload data

[0379] Output: Predicted workload data transmitted to the information processing device.

[0380] Step 2: The user enters actual workload data.

[0381] ---

[0382] At the end of the month, users use a similar HMD to input actual workload data. They enter data such as "Actual workload: 11,500 units," and this data is also sent to the information processing device.

[0383] Input: Actual workload data

[0384] Output: Actual workload data transmitted to the information processing device.

[0385] Step 3: The server saves the data.

[0386] ---

[0387] The server receives predicted and actual workload data sent by the user, verifies that the data format is correct, and stores it in the database of the information processing device.

[0388] Input: Forecasted workload data, actual workload data

[0389] Output: Predicted workload data and actual workload data stored in the database.

[0390] Step 4: The server calculates the deviation rate.

[0391] ---

[0392] The server calculates the deviation rate based on the predicted and actual data stored in the database. For example, if the predicted number of tasks is 10,000 and the actual number is 11,500, the server performs the following calculation: (Actual workload - Predicted workload) / Predicted workload 100. In this example, the deviation rate is 15%. This calculation result is stored as internal data.

[0393] Input: Forecasted workload data, actual workload data

[0394] Output: Calculated deviation rate

[0395] Step 5: The server collects sentiment data.

[0396] ---

[0397] The server uses the emotion recognition engine built into the HMD to analyze the user's facial expressions and voice tone, and collects emotional data. For example, it quantifies and records the user's stress and satisfaction levels when entering work data. This emotional data is then stored on the information processing device.

[0398] Input: User's facial expressions and tone of voice

[0399] Output: Saved sentiment data

[0400] Step 6: The server identifies the cause of the discrepancy.

[0401] ---

[0402] The server analyzes stored business data based on collected emotional data to identify the cause of discrepancies. For example, if the emotional data indicates "stress," it examines the detailed logs at that time to analyze whether there were concentrated inquiries on a specific day or in a specific category.

[0403] Input: Emotional data, business data

[0404] Output: Identified causes of discrepancies

[0405] Step 7: The server predicts future workload.

[0406] ---

[0407] The server builds a generative AI model based on past business data and collected sentiment data to predict future workloads. For example, by applying past data and sentiment scores as input data to the model, it predicts that the workload for next month will be 12,000 and the workload for the month after that will be 11,000. This prediction result is also stored as internal data.

[0408] Input: Past business data, sentiment data

[0409] Output: Future workload forecast data

[0410] Step 8: The server displays the calculation results to the user.

[0411] ---

[0412] The server generates a report summarizing the results of the deviation rate calculation, the results of identifying the cause of the deviation, and the results of future workload forecasts. This report is displayed in real time on the user's HMD, and the user can use this information to make appropriate resource allocations and business improvements.

[0413] Input: Deviation rate calculation result, deviation cause identification result, future workload forecast result

[0414] Output: Report displayed on the HMD

[0415] The above is the flow of specific processing steps of the system based on the application example. Sorry, I'm not sure.

[0416] 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.

[0417] 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.

[0418] 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.

[0419] [Second Embodiment]

[0420] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0421] 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.

[0422] 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).

[0423] 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.

[0424] 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.

[0425] 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).

[0426] 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.

[0427] 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.

[0428] 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.

[0429] 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.

[0430] 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.

[0431] 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".

[0432] This system is designed to predict workload, identify discrepancies between actual and projected workloads, analyze the causes, and forecast future workloads. A specific implementation of this system is described below.

[0433] 1. Users enter business data.

[0434] Users access the system and utilize an interface to input their projected workload at the beginning of each month. For example, they might input "1000 inquiries are expected" at the start of the month. At the end of the month, they input actual data through a similar interface. For example, they might input "1200 inquiries were the actual number" at the end of the month. This allows users to easily register both projections and actual figures.

[0435] 2. The server saves the data.

[0436] The predicted and actual workload data entered by the user is received by the server. The server verifies that the received data is in the correct format and saves it to the database. This saved data is then used as the basis for subsequent calculations and analyses.

[0437] 3. The server calculates the deviation rate.

[0438] The server calculates the deviation rate based on the stored predicted and actual data. For example, if the predicted workload is 1000 and the actual workload is 1200, the server performs the following calculation: Deviation rate = (Actual workload - Predicted workload) / Predicted workload 100. In this example, the deviation rate is 20%. This calculation result is used to allow users to easily understand performance over a specific period.

[0439] 4. The server identifies the cause of the discrepancy.

[0440] The server analyzes stored business data to identify the cause of the discrepancy. For example, the server can find patterns based on the date, time, and category of inquiries, identifying that inquiries were concentrated on specific days or in specific categories. This allows the server to report the specific cause of the discrepancy to the user.

[0441] 5. The server predicts future workload.

[0442] The server collects historical business data and uses it to build a machine learning model. For example, it uses data on predicted and actual workload for the past six months. This model can accurately predict workload for the next few months. The prediction results are output in the form of, for example, "We predict 1200 inquiries next month and 1100 inquiries the month after."

[0443] 6. Display the results to the user.

[0444] The server generates a report summarizing the results of the deviation rate calculation, the identification of the cause of the deviation, and future workload forecasts. This report is displayed in real time on the user's dashboard. Based on this, users can adjust their work and optimize staffing.

[0445] Specific example

[0446] For example, if a user enters "1000 predicted workloads for this month" and "1200 actual workloads at the end of the month," the server saves this data and calculates that "the discrepancy rate is 20%." Further analysis identifies the cause of the discrepancy, such as "500 inquiries concentrated on a specific day." Based on this, the server refers to past data to predict the workload for the following months and displays to the user, "1200 inquiries are predicted for next month, and 1100 for the month after."

[0447] This allows users to understand their future workload and make appropriate resource allocations and personnel assignments. Each of these methods significantly improves operational efficiency and minimizes discrepancies.

[0448] The following describes the processing flow.

[0449] Step 1:

[0450] Users input workload forecast data.

[0451] Users log in to the system and enter their monthly workload forecast data into a dedicated input form. The input fields include the number of inquiries and other forecast parameters. After entering the data, they press the submit button to send it to the server.

[0452] Step 2:

[0453] The server stores the prediction data.

[0454] The server receives the prediction data submitted by the user and performs a format check (validation). If the data is correct, it executes an SQL command (e.g., INSERT INTO) to save the prediction data to the database. Once the saving is complete, it notifies the user that the data has been successfully saved.

[0455] Step 3:

[0456] Users enter performance data.

[0457] At the end of the month, users log back into the system and enter their actual workload data. The input fields include the actual number of inquiries and other performance parameters. After entering the data, they press the submit button again to send it to the server.

[0458] Step 4:

[0459] The server saves performance data.

[0460] The server receives the performance data submitted by the user and performs a format check (validation). If the data is correct, it executes an SQL command (e.g., INSERT INTO) to save the performance data to the database. Once the saving is complete, it notifies the user that the data has been saved successfully.

[0461] Step 5:

[0462] The server calculates the deviation rate.

[0463] The server retrieves forecast and actual data for the relevant month from the database. Next, it calculates the deviation rate based on this data. The formula is: Deviation Rate = (Actual Workload - Forecasted Workload) / Forecasted Workload 100. The calculation result is stored as internal data.

[0464] Step 6:

[0465] The server identifies the cause of the discrepancy.

[0466] The server analyzes past business data to identify patterns such as concentrated inquiries on specific days or categories. For example, the server might identify a cluster of 500 inquiries on a particular day and extract detailed log data for that day. This information is compiled and reported to the user as the cause of the discrepancy.

[0467] Step 7:

[0468] The server predicts future workload.

[0469] The server collects historical business data from the database and uses it to build a machine learning model (e.g., a regression analysis model). Next, it uses this model to predict the workload for the next few months. For example, it might predict 1200 inquiries next month and 1100 inquiries the month after. This prediction is also stored as internal data.

[0470] Step 8:

[0471] The server displays the calculation results to the user.

[0472] The server generates a report summarizing the results of the deviation rate calculation, the results of identifying the cause of the deviation, and the results of future workload forecasts. This report is displayed on the user's dashboard in real time. Based on this information, users can improve the efficiency of their work and allocate resources appropriately.

[0473] These steps allow users to understand the discrepancy between month-end forecasts and month-end actuals, identify the causes to improve operational efficiency, and allocate resources appropriately based on future workload forecasts.

[0474] (Example 1)

[0475] 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."

[0476] Conventional workload forecasting systems lack sufficient functionality to automatically calculate and analyze discrepancies between forecasts and actual results, making it difficult to identify the causes and improve the accuracy of future workload forecasts. In addition, the lack of an interface that allows users to easily input work data and check the results in real time is also a problem. While this is expected to improve operational efficiency, in reality, it requires a lot of manual work, which is burdensome.

[0477] 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.

[0478] In this invention, the server includes means for the user to input predicted workload data, means for the user to input actual workload data, means for the server device to receive the input data, validate the data format and store it, means for calculating the deviation rate based on the stored predicted and actual data, means for analyzing the cause of the deviation and extracting specific patterns, means for constructing a machine learning model to predict future workload based on past work data and making predictions, and means for displaying the calculation results and analysis results to the user in real time. As a result, the user can immediately check the difference between the predicted and actual workload data they have entered, quickly identify the cause of the deviation, and predict future workload with high accuracy. Consequently, it is possible to adjust operations and optimize personnel allocation, significantly improving overall operational efficiency.

[0479] "The means by which users input workload forecast data" refers to the interface that allows users to input workload forecast data into the system. This interface is designed to allow users to easily input data.

[0480] "The means by which users input actual workload data" refers to the interface that allows users to input data on their actual workload into the system. This is also designed to allow users to input data easily.

[0481] "A means of receiving data via a server device, validating the data format, and storing it" refers to the function where a server receives data sent from a user, verifies whether the data format is correct, and then stores it in a database.

[0482] "Means for calculating the deviation rate based on stored forecast and actual data" refers to a function that calculates the deviation rate using the forecast and actual workload data stored on the server. The deviation rate is a value that expresses the difference between the forecast and the actual results.

[0483] "Means for analyzing the cause of discrepancies and extracting specific patterns" refers to a function in which the server analyzes stored data to identify the cause of discrepancies and extracts patterns based on specific dates, times, or categories.

[0484] "A means of building a machine learning model to predict future workload based on past business data" refers to a function where the server analyzes past business data to build a machine learning model and uses that model to predict future workload.

[0485] "A means of displaying calculation and analysis results to the user in real time" refers to a function that displays the calculated deviation rate, analysis results, and predicted future workload on the user's dashboard in real time.

[0486] This invention is a system for predicting workload, identifying discrepancies between actual and projected workload, analyzing the causes of these discrepancies, and predicting future workload. A specific embodiment of this system is described below.

[0487] The user first inputs predicted and actual workload data. The input interface is provided via a web browser, with a simple form for easy data entry. For example, the user might input "Predicted workload for this month: 1000 items" and "Actual workload at the end of the month: 1200 items." This data is then sent to the server in JSON format.

[0488] The server is implemented using Node.js and receives HTTP requests using the Express framework. It receives the sent JSON data and validates its contents. After successful validation, the data is stored in MongoDB. MongoDB is connected to the server via Mongoose, and predicted workload data and actual workload data are stored in separate collections.

[0489] Based on the stored data, the server calculates the deviation rate. The formula used for the calculation is as follows: Deviation rate = (Actual workload - Forecasted workload) / Forecasted workload 100. For example, if the forecast is 1000 and the actual workload is 1200, the deviation rate will be calculated as 20%. This calculation result is temporarily stored in memory.

[0490] Next, the server analyzes the data to identify the cause of the discrepancy. It runs aggregate queries to find patterns based on specific days or categories, and if, for example, 500 inquiries were concentrated on a particular day, it analyzes the details to identify the cause.

[0491] The server collects business data from the past six months and builds a predictive model using a Python machine learning library (e.g., Scikit-learn). Using the trained model, it predicts future business volume. The prediction results are output in the format of "1200 inquiries are predicted for next month, and 1100 inquiries for the month after."

[0492] The calculation results, analysis results, and prediction results are compiled into a report. The server generates this report in HTML or PDF format and displays it in real time on the user dashboard. Visualization tools such as Grafana are used on the dashboard, and the data is updated in real time. Based on this, users can adjust their work and optimize staffing.

[0493] For example, if a user inputs, "This month's projected workload is 1000 inquiries. The actual workload was 1200. Based on this, calculate the discrepancy rate and identify the cause. Then, predict the workload for next month and the month after," the server will save this data, identify a "20% discrepancy rate," and determine that 500 inquiries were concentrated on a specific day. Subsequently, the server will display to the user in real time the predicted results: 1200 inquiries for the next month and 1100 inquiries for the month after. This allows the user to understand future workloads and make appropriate resource allocations and personnel assignments.

[0494] This invention significantly improves operational efficiency and minimizes the occurrence of discrepancies.

[0495] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0496] Step 1:

[0497] Users input workload forecast data.

[0498] Users access the system and input workload forecast data through the interface. The input data is sent to the server in JSON format. For example, inputting "This month's forecast workload is 1000 items." Input (workload forecast data) → Output (data in JSON format)

[0499] Step 2:

[0500] The server receives the prediction data and performs validation.

[0501] The server is implemented using Node.js and receives HTTP requests using the Express framework. It validates the structure and content of the received JSON data to ensure it is in the correct format. Input (JSON-formatted workload forecast data) → Output (Validation result: Success / Failure)

[0502] Step 3:

[0503] The server stores the prediction data.

[0504] If validation is successful, the server connects to MongoDB via Mongoose and saves the predicted data. When saving, it saves the data to a collection of predicted workload data within the database. Input (validated workload prediction data) → Output (save complete message)

[0505] Step 4:

[0506] Users input actual workload data.

[0507] Users input their actual workload data for the current month through a similar interface. For example, they might input "This month's actual workload is 1200 items." Input (actual workload data) → Output (data in JSON format)

[0508] Step 5:

[0509] The server receives the performance data and performs validation.

[0510] The server receives an HTTP request and validates the structure and content of the received actual workload data. Input (actual workload data in JSON format) → Output (validation result: success / failure)

[0511] Step 6:

[0512] The server saves performance data.

[0513] If validation is successful, the server saves the actual workload data to the MongoDB collection of actual workload data. Input (validated actual workload data) → Output (save complete message)

[0514] Step 7:

[0515] The server calculates the deviation rate.

[0516] The server calculates the deviation rate based on the stored predicted workload data and actual workload data. The formula is as follows: Deviation Rate = (Actual Workload - Predicted Workload) / Predicted Workload 100. Input (Predicted Workload Data, Actual Workload Data) → Output (Deviation Rate)

[0517] Step 8:

[0518] The server analyzes the cause of the discrepancy.

[0519] The server analyzes stored business data to identify the cause of the discrepancy. For example, it uses the Parse function to find patterns based on specific days or categories. Input (business data) → Output (analysis results regarding the cause of the discrepancy)

[0520] Step 9:

[0521] The server predicts future workload.

[0522] The server collects historical business data and builds a predictive model using the Python machine learning library (Scikit-learn). Using the trained model, it predicts the workload for the following two months. Input (historical business data) → Output (future workload prediction)

[0523] Step 10:

[0524] The server compiles the results and generates a report.

[0525] The server generates a report summarizing the calculation results of the deviation rate, the results of identifying the cause of the deviation, and the forecast of future workload. This report is output in HTML or PDF format. Input (calculation results, analysis results, forecast results) → Output (report)

[0526] Step 11:

[0527] The device displays the report.

[0528] The user's device displays reports sent from the server on a dashboard. Visualization tools such as Grafana are used on the dashboard, and data is updated in real time. Input (Report) → Output (Display on Dashboard)

[0529] (Application Example 1)

[0530] 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."

[0531] Traditional logistics centers have struggled to efficiently analyze discrepancies between projected and actual workload forecasts, making it difficult to optimize resource allocation and staffing. Leaving this problem unaddressed leads to decreased operational efficiency, increased costs, and negatively impacts service quality.

[0532] 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.

[0533] In this invention, the server includes means for the user to input predicted workload data, means for the user to input actual workload data, server means for storing the input data, server means for calculating the deviation rate based on the stored predicted and actual data, server means for analyzing the causes of the deviation and extracting specific topics, server means for predicting future workload based on past business data, means for displaying the calculation results and analysis results to the user, means for predicting future workload with high accuracy using a machine learning model, and means for optimizing the allocation of business resources within the logistics center. This enables accurate prediction of workload, efficient deviation analysis, and appropriate resource allocation.

[0534] A "user" is someone who uses the system to input predicted workload data and actual workload data.

[0535] "Predicted workload data" refers to data entered by users at the beginning of the month or other times when they anticipate their workload.

[0536] "Actual workload data" refers to the actual workload data entered by users at the end of each month.

[0537] A "server" is a device or system that stores predicted and actual workload data, calculates deviation rates, analyzes causes, and predicts future workload.

[0538] "Deviation rate" is an indicator that expresses the difference between predicted workload and actual workload as a percentage.

[0539] "Cause of discrepancy" refers to the reason for the difference between the predicted workload and the actual workload.

[0540] "Specific topics" refer to areas of interest or themes that have been identified in order to pinpoint the causes of the discrepancy.

[0541] "Past business data" refers to previously recorded predicted workload data and actual workload data.

[0542] A "machine learning model" is an algorithm used to predict future workloads based on past data.

[0543] "Resource allocation" refers to the appropriate placement of personnel and equipment within a logistics center.

[0544] A system implementing this invention specifically includes an application for predicting workload and managing efficiency in a logistics center. This application allows the user to input operational data, which is then processed, analyzed, and predicted by a server, with the results displayed to the user in real time.

[0545] Users can input predicted and actual workload data using applications installed on smartphones, smart glasses, head-mounted displays, or robots. For example, they might input "1000" for the predicted workload for the month and "1200" for the actual workload at the end of the month.

[0546] The server receives the data, validates its format, and stores it in the database. Based on the stored predicted and actual workload data, the server calculates the deviation rate. For example, if the predicted workload is 1000 and the actual workload is 1200, the deviation rate is 20%. This calculated deviation rate is used to help users easily understand performance over a specific period.

[0547] Furthermore, the server analyzes stored business data to identify the cause of the discrepancy. For example, it might identify that the workload was concentrated on a particular day or in a particular category. This allows the server to report the specific cause of the discrepancy to the user.

[0548] The server also builds machine learning models based on past business data to predict future workloads. These models are trained using, for example, data on predicted and actual workloads over the past six months. This allows for highly accurate predictions of workloads for the following month and the month after. For example, the output might state, "We predict 1200 inquiries next month and 1100 inquiries the month after."

[0549] Calculation and analysis results are displayed in real time on the user's dashboard. Users can use this information to adjust operations and optimize staffing. This dashboard can also be viewed at any time by field workers using smart glasses or head-mounted displays.

[0550] Implementing this system will improve the accuracy of business forecasts, optimize resource allocation, and increase the operational efficiency of the logistics center. Furthermore, the calculation results will be provided to the user as specific prompt messages. For example, the following prompt messages may be generated:

[0551] "Our projected workload for December was 1,000 cases, but the actual volume was 1,500. Please tell us the discrepancy rate and the reasons for it. Also, please provide a workload forecast for next month."

[0552] In this way, users can utilize the system to achieve efficient business operations.

[0553] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0554] Step 1:

[0555] The user enters predicted workload data on a terminal. The entered data is sent to the server as predicted workload data. As an example, "This month's predicted workload is 1000 items" is entered.

[0556] Step 2:

[0557] Users input actual workload data on their terminals. This data is entered at the end of each month and sent to the server. For example, a user might enter, "This month's actual workload is 1200 items."

[0558] Step 3:

[0559] The server receives predicted and actual workload data and validates its format. After verifying that the data is in a valid format, it is saved to the database.

[0560] Step 4:

[0561] The server calculates the deviation rate based on the stored predicted and actual data. Specifically, it performs the following calculations:

[0562] The deviation rate is calculated as follows: Deviation rate = (Actual workload - Forecasted workload) / Forecasted workload 100. For example, if the forecast is 1000 and the actual workload is 1200, the deviation rate is 20%. The calculation result is output as the deviation rate and stored in the database.

[0563] Step 5:

[0564] The server analyzes stored business data to identify the cause of the discrepancy. For example, it finds patterns based on the date, time, and category of inquiries, identifying that inquiries were concentrated on specific days or in specific categories. Based on these analysis results, it outputs the cause of the discrepancy.

[0565] Step 6:

[0566] The server collects historical business data and uses it to build a machine learning model. The model is trained using data on predicted and actual workloads over the past six months. This allows for highly accurate predictions of future workloads. The output is a predicted workload, such as "1200 cases next month, 1100 cases the month after."

[0567] Step 7:

[0568] The server generates a report summarizing the calculation and analysis results, which is then displayed in real time on the user's dashboard. This dashboard is designed to be accessible to field workers using smart glasses or head-mounted displays. Users can then use this information to adjust operations and optimize staffing.

[0569] Step 8:

[0570] The server generates prompt messages based on user input. For example, it might create a specific prompt message such as, "The predicted workload for December was 1000, but the actual workload was 1500. Please tell me the discrepancy rate and the reason. Also, please provide a workload forecast for next month." Based on this, the user can take actions to achieve efficient business operations.

[0571] 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.

[0572] This system not only predicts workload, identifies discrepancies with actual results, analyzes causes, and forecasts future workload, but also achieves even more accurate analysis and prediction by combining it with an emotion engine that recognizes user emotions. The specific implementation details are described below.

[0573] 1. Users enter business data.

[0574] Users access the system and utilize an interface to input their projected workload at the beginning of each month. For example, they might input "1000 inquiries are expected" at the start of the month. At the end of the month, they input actual data through a similar interface. For example, they might input "1200 inquiries were the actual number" at the end of the month. This allows users to easily register both projections and actual figures.

[0575] 2. The server saves the data.

[0576] The predicted and actual workload data entered by the user is received by the server. The server verifies that the received data is in the correct format and saves it to the database. This saved data is then used as the basis for subsequent calculations and analyses.

[0577] 3. The server calculates the deviation rate.

[0578] The server calculates the deviation rate based on the stored predicted and actual data. For example, if the predicted workload is 1000 and the actual workload is 1200, the server performs the following calculation: Deviation rate = (Actual workload - Predicted workload) / Predicted workload 100. In this example, the deviation rate is 20%. This calculation result is stored as internal data.

[0579] 4. The server collects sentiment data.

[0580] The emotion engine recognizes the user's emotions when they use the system. For example, it analyzes the user's facial expressions and tone of voice when they input business data to collect emotional data such as "stress" and "satisfaction."

[0581] 5. The server identifies the cause of the discrepancy.

[0582] The server further analyzes stored operational data based on the collected emotional data. For example, if the emotional data indicates "stress," it examines detailed logs such as the inquiry status and error count at that time to identify the cause of the discrepancy. This analysis allows the server to consider the emotional factors behind concentrated inquiries on specific days or in specific categories.

[0583] 6. The server predicts future workload.

[0584] The server collects historical business data from the database and integrates it with the sentiment data collected by the sentiment engine to build a machine learning model (e.g., a regression analysis model). This model can accurately predict the workload for the next few months. This prediction result is also stored as internal data.

[0585] 7. The server displays the calculation results to the user.

[0586] The server generates a report summarizing the results of the deviation rate calculation, the results of identifying the cause of the deviation, and the results of future workload forecasts. This report is displayed on the user's dashboard in real time. Based on this information, users can improve the efficiency of their work and allocate resources appropriately.

[0587] Specific example

[0588] For example, if a user enters "1000 predicted workloads for this month" and "1200 actual workloads at the end of the month," the server saves this data and calculates that the "deviation rate is 20%." Further analysis identifies the cause of the deviation as "500 inquiries concentrated on a specific day" and that the user felt "stressed" on that day. Based on this, the server refers to past data to predict the workload for the following months and displays to the user "1200 inquiries are predicted for next month, and 1100 for the month after."

[0589] This allows users to understand their future workload while taking emotional data into account, enabling appropriate resource allocation and process improvements. Each of these methods significantly improves work efficiency and minimizes discrepancies. Utilizing emotional data allows for more flexible responses that take human factors into account.

[0590] The following describes the processing flow.

[0591] Step 1:

[0592] Users input workload forecast data.

[0593] Users log in to the system and enter their monthly workload forecast data into a dedicated input form. The input fields include the number of inquiries and other forecast parameters. After entering the data, they press the submit button to send it to the server.

[0594] Step 2:

[0595] The server stores the prediction data.

[0596] The server receives the prediction data submitted by the user and performs a format check (validation). If the data is correct, it executes an SQL command (e.g., INSERT INTO) to save the prediction data to the database. Once the saving is complete, it notifies the user that the data has been successfully saved.

[0597] Step 3:

[0598] Users enter performance data.

[0599] At the end of the month, users log back into the system and enter their actual workload data. The input fields include the actual number of inquiries and other performance parameters. After entering the data, they press the submit button again to send it to the server.

[0600] Step 4:

[0601] The server saves performance data.

[0602] The server receives the performance data submitted by the user and performs a format check (validation). If the data is correct, it executes an SQL command (e.g., INSERT INTO) to save the performance data to the database. Once the saving is complete, it notifies the user that the data has been saved successfully.

[0603] Step 5:

[0604] The server calculates the deviation rate.

[0605] The server retrieves forecast and actual data for the relevant month from the database. Next, it calculates the deviation rate based on this data. The formula is: Deviation Rate = (Actual Workload - Forecasted Workload) / Forecasted Workload 100. The calculation result is stored as internal data.

[0606] Step 6:

[0607] Recognize user emotions and collect data.

[0608] When a user uses the system, an emotion engine activates, analyzing the user's facial expressions and tone of voice. For example, while a user is operating an input form or entering business data, the system uses a camera and microphone to collect emotion data.

[0609] Step 7:

[0610] The server stores emotional data.

[0611] The collected sentiment data is sent to the server for formatting checks (validation). If the data is correct, an SQL command (e.g., INSERT INTO) is executed to save the sentiment data to the database. Once saved, the sentiment data is integrated with other business data.

[0612] Step 8:

[0613] The server analyzes and identifies the cause of the discrepancy based on emotional data.

[0614] The server analyzes the cause of the discrepancy based on stored emotional and operational data. For example, if it examines data from a specific day and finds that the user was experiencing "stress" on that day, it checks the detailed log data of inquiries that occurred on that day. This allows it to identify why the discrepancy occurred on that day, including the underlying emotional factors.

[0615] Step 9:

[0616] The server predicts future workload based on past data.

[0617] The server integrates historical business data and sentiment data from the database and uses this to build a machine learning model (e.g., a regression analysis model). This model allows for highly accurate predictions of workload for the next few months.

[0618] Step 10:

[0619] The server displays the calculation results and prediction results to the user.

[0620] The server generates a report summarizing the results of the deviation rate calculation, the results of identifying the cause of the deviation, and the results of future workload forecasts. This report is displayed on the user's dashboard in real time. Based on this information, users can improve the efficiency of their work and allocate resources appropriately.

[0621] Specific example

[0622] For example, if a user enters "1000 predicted workloads for this month" and "1200 actual workloads at the end of the month," the server saves this data and calculates that the "deviation rate is 20%." Furthermore, the system senses that the user is experiencing "stress" while entering the data and records this. Analysis identifies the cause of the deviation as "500 inquiries concentrated on a particular day" and that the user was experiencing "stress" on that day. Based on this, the system refers to past data to predict the workload for the following months and displays to the user that "1200 inquiries are predicted for next month, and 1100 for the month after."

[0623] By combining this with an emotion engine, it becomes possible to provide more flexible responses that take human factors into account, further improving work efficiency.

[0624] (Example 2)

[0625] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0626] Conventional workload forecasting systems have faced challenges in identifying the causes of discrepancies between predicted and actual workloads, as well as in the limited accuracy of future workload forecasts. This has resulted in limitations in improving operational efficiency and appropriate resource allocation. Furthermore, systems that do not consider human emotions make it difficult to comprehensively analyze the impact of actual work processes and users' psychological states.

[0627] 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.

[0628] In this invention, the server includes means for collecting emotional data when a user inputs data, server means for identifying the cause of discrepancies based on the collected emotional data, and server means for predicting future workload based on past work data. This makes it possible to more accurately identify the cause of discrepancies between predicted and actual workload and to predict future workload with high accuracy. Furthermore, by incorporating user emotional data into the analysis, it becomes possible to respond more flexibly, taking human factors into consideration, thereby improving work efficiency and achieving appropriate resource allocation.

[0629] A "user" is a person who uses the system to input workload data and performance data, and performs operations to obtain analysis results and prediction results.

[0630] "Predicted workload data" refers to data about the workload that users expect to occur during a specific period in the future.

[0631] "Actual workload data" refers to data on the actual workload generated by a user during a specific period.

[0632] A "server" is a computing system that receives, stores, and analyzes data entered by users, and provides calculation results, prediction results, and other information.

[0633] "Validation" is the process of verifying whether the format and content of the entered data are correct.

[0634] A "database" is an electronic data storage system for systematically organizing, storing, searching, and managing various types of data.

[0635] The "deviation rate" is the percentage that shows the difference between predicted workload data and actual workload data, and is calculated based on a formula.

[0636] "Emotional data" is data obtained by analyzing a user's emotions from their facial expressions, tone of voice, etc., and it indicates emotional states such as "stress" or "satisfaction."

[0637] A "machine learning model" is an algorithm or mathematical model used to learn from past data and predict future data.

[0638] "Causes of discrepancy" refers to the factors that cause the difference between predicted workload data and actual workload data.

[0639] A "report" is a document that summarizes calculation results, analysis results, and prediction results, and is an aggregation of analytical information provided to the user.

[0640] Modes for carrying out the invention

[0641] The system implementing this invention has a set of functions in which, as a primary means, the user inputs business data, and the server analyzes, stores, and predicts that data. Specifically, the hardware and software used in each step include the following:

[0642] User data entry method

[0643] Users access the system using a dedicated web browser or mobile application via an internet-connected device (e.g., PC, tablet, smartphone). Users log in to the system and input projected workload data at the beginning of the month and actual workload data at the end of the month. For example, they might input "Projected workload for this month: 1000 items" and then "Actual workload: 1200 items" at the end of the month.

[0644] Server-based data storage and validation

[0645] The entered data is sent to the server. The server validates the data format (e.g., confirms that the number of queries is an integer) and displays an error message to the user if there is any inappropriate data. Data in the correct format is stored in the database. This database uses a relational database management system such as SQL.

[0646] Calculation of deviation rate

[0647] The server calculates the deviation rate based on the stored predicted workload data and actual workload data. For example, if the predicted workload is 1000 and the actual workload is 1200, the server calculates the deviation rate as follows: "Deviation Rate = (Actual Workload - Predicted Workload) / Predicted Workload 100". In this example, the deviation rate is calculated to be 20%. The calculation result is stored in the database.

[0648] Collection of user sentiment data

[0649] As the user enters data, the system's built-in emotion engine activates and analyzes the user's facial expressions and voice tone through the webcam and microphone. The emotion engine generates emotional data such as "stress" and "satisfaction" from this input and sends and stores it on the server.

[0650] Identifying the cause of the discrepancy

[0651] The server analyzes stored business data based on the collected sentiment data. For example, if the sentiment data indicates "stress," it investigates the detailed logs for that period and identifies that inquiries concentrated on specific days or categories are causing the discrepancies. This allows for a more detailed analysis of factors hindering business efficiency.

[0652] Predicting future workload

[0653] The server uses historical business data and sentiment data to build a machine learning model (e.g., a regression analysis model) to predict future workload. This model is implemented using programming languages ​​such as Python or R. For example, it might produce results such as, "We predict 1200 inquiries next month and 1100 inquiries the month after."

[0654] Displaying Results

[0655] The server generates a report summarizing the calculated deviation rate, identified deviation causes, and future workload forecasts. This report is displayed on the user's dashboard in real time. Based on this information, users can take actions to improve work efficiency.

[0656] Specific example

[0657] For example, if a user enters "1000 predicted workloads for this month" and "1200 actual workloads at the end of the month," the server saves this data and calculates that the "deviation rate is 20%." Furthermore, it identifies that 500 inquiries were concentrated on a specific day and that the user felt "stressed" on that day. Based on this information, the server predicts the workload for the following months and displays to the user that "1200 inquiries are predicted for next month, and 1100 for the month after."

[0658] Example of a prompt

[0659] "Analyze the discrepancy rate and its causes when the projected workload for this month is 1000 items and the actual workload at the end of the month is 1200 items."

[0660] This allows users to understand their future workload while taking emotional data into account, enabling appropriate resource allocation and process improvements. Each of these methods significantly improves work efficiency and minimizes discrepancies. Utilizing emotional data allows for more flexible responses that take human factors into account.

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

[0662] Specific processing steps of the program for this system

[0663] Step 1: The user enters business data.

[0664] input:

[0665] Predicted workload data (e.g., "1000 inquiries are predicted")

[0666] Actual workload data (e.g., "Actual number of inquiries: 1200")

[0667] process:

[0668] Users log in to the system using a web browser or mobile app.

[0669] After logging in, the business data entry screen will be displayed.

[0670] At the beginning of the month, you will enter your projected workload into the input form, and at the end of the month, you will enter your actual workload.

[0671] Click the submit button on the form to send the data to the server.

[0672] output:

[0673] Business data (predicted workload data and actual workload data) is sent to the server.

[0674] Step 2: The server saves the data.

[0675] input:

[0676] Business data submitted by users

[0677] process:

[0678] The server validates the data received from the user. For example, it checks whether the number of queries is an integer.

[0679] If validation is successful, the data is saved to the database.

[0680] If validation fails, an error message is returned to the user.

[0681] output:

[0682] Business data stored in the database

[0683] Validation result (success / failure)

[0684] Success message or error message

[0685] Step 3: The server calculates the deviation rate.

[0686] input:

[0687] Predicted workload data and actual workload data stored in the database

[0688] process:

[0689] The server retrieves predicted and actual workload data from the database.

[0690] The deviation rate is calculated using the following formula: "Deviation Rate = (Actual Workload - Forecasted Workload) / Forecasted Workload 100".

[0691] Save the calculation results to the database.

[0692] output:

[0693] Deviation rate stored in the database

[0694] Step 4: The server collects sentiment data.

[0695] input:

[0696] Facial expressions and tone of voice (collected via webcam and microphone) when users input business data.

[0697] process:

[0698] The server activates an emotion engine and analyzes the user's facial expressions and voice in real time.

[0699] The emotion engine generates emotion data (e.g., "stress" or "satisfaction").

[0700] The generated emotion data is sent to the server and stored in the database.

[0701] output:

[0702] Emotional data stored in the database

[0703] Step 5: The server identifies the cause of the discrepancy.

[0704] input:

[0705] Saved emotional data

[0706] Predicted workload data, actual workload data, and deviation rate

[0707] process:

[0708] The server performs analysis based on stored business data and emotional data.

[0709] Extract detailed data on periods when emotional data indicates "stress."

[0710] We will investigate detailed logs of inquiries concentrated on specific days or time periods to identify the cause of the discrepancy.

[0711] output:

[0712] Identified causes of discrepancies

[0713] Step 6: The server predicts future workload.

[0714] input:

[0715] Past business data

[0716] Emotional data

[0717] process:

[0718] The server builds a machine learning model (e.g., a regression analysis model) based on historical data.

[0719] We will use the constructed model to predict future workload.

[0720] Save the prediction results to the database.

[0721] output:

[0722] Future workload forecast results stored in the database

[0723] Step 7: The server displays the calculation results to the user.

[0724] input:

[0725] deviation rate

[0726] Causes of discrepancy

[0727] Future workload forecast results

[0728] process:

[0729] The server integrates the deviation rate, the cause of the deviation, and the forecast results for future workload to create a report.

[0730] After the report is generated, it will be displayed in real time on the user's dashboard.

[0731] output:

[0732] Reports displayed on the user dashboard

[0733] This allows users to understand their future workload while taking emotional data into account, enabling appropriate resource allocation and process improvements. Each of these methods significantly improves work efficiency and minimizes discrepancies. Furthermore, utilizing emotional data allows for more flexible responses that take human factors into account.

[0734] (Application Example 2)

[0735] 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."

[0736] Logistics centers need a function to analyze the discrepancy between predicted and actual workloads and to predict future workloads with high accuracy. In particular, there is a need for more accurate predictions, early detection of problems, and efficient resource allocation by utilizing real-time sentiment data of managers. However, conventional systems do not include sentiment data in their analysis, which limits their ability to identify the causes of discrepancies and improve the accuracy of future workload predictions.

[0737] 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.

[0738] In this invention, the server includes means for the user to input predicted workload data, means for the user to input actual workload data, information processing means for storing the input data, information processing means for calculating a deviation rate based on the stored predicted and actual data, means for collecting user emotion data using an emotion recognition engine, information processing means for analyzing the causes of the deviation and extracting specific topics, information processing means for predicting future workload based on past work data, and means for analyzing emotion data and displaying it together with the deviation rate. This makes it possible to analyze the causes of workload deviations, including user emotion data, and improve the accuracy of future workload predictions.

[0739] "Predicted workload data" refers to data that shows the amount of work that users predict will be processed within a certain period.

[0740] "Actual workload data" refers to data that shows the actual amount of work processed within a certain period.

[0741] "Information processing device means" refers to a server or computer system that performs data storage, calculation, analysis, and display.

[0742] The "deviation rate" is a value that expresses the difference between the predicted workload and the actual workload as a percentage.

[0743] An "emotion recognition engine" is software or hardware used to analyze a user's emotions and collect emotional data.

[0744] "Emotional data" refers to data that expresses a user's emotional state using numerical values ​​or categories.

[0745] "Specific topics" refer to specific items or themes extracted from the analysis results of the causes of the discrepancies.

[0746] "Future workload forecasting" is a process of estimating future workloads based on past and present data.

[0747] A "generative AI model" is an artificial intelligence model used to extract features from accumulated data and predict future situations.

[0748] A "prompt" is an instruction or question that is input to a generative AI model.

[0749] As a specific embodiment of this invention, we will explain using a "smart logistics manager" that uses a head-mounted display (HMD) for a logistics center as an example.

[0750] 1. Input of predicted and actual workload.

[0751] The user wears an HMD (Head-Mounted Display) and inputs their projected workload at the beginning of the month. For example, they might input "Projected workload for this month: 10,000 units." Then, at the end of the month, they similarly input their actual workload. For example, they might input "Actual workload: 11,500 units." This allows the user to provide projected and actual workload data to the information processing device.

[0752] 2. Data storage and calculation of deviation rate

[0753] The server receives predicted and actual workload data entered by the user, validates the data format, and then stores it in the information processing device. Based on the stored data, it calculates the deviation rate between the predicted and actual data. For example, if the predicted volume is 10,000 and the actual volume is 11,500, the server calculates the deviation rate as 15% and stores it as internal data.

[0754] 3. Collection of emotional data

[0755] The emotion recognition engine integrated into the HMD analyzes the user's facial expressions and voice tone, collecting emotional data. For example, it quantifies and records the user's stress and satisfaction levels when entering work data. This emotional data is then stored in the information processing device.

[0756] 4. Identifying the causes of the discrepancy and predicting future workload.

[0757] The server further analyzes the stored business data based on the collected emotional data to identify the cause of the discrepancy. For example, it identifies days with a high amount of emotional data indicating stress and analyzes the inquiry status and error count for those days. Next, it integrates past business data and emotional data to build a generative AI model and predict future workload. The results of the future workload prediction are also stored as internal data.

[0758] 5. Creating and displaying reports to users

[0759] The server generates a report summarizing the results of the deviation rate calculation, the results of identifying the cause of the deviation, and the results of future workload forecasts. This report is displayed in real time on the user's HMD, and the user can use this information to make appropriate resource allocations and business improvements.

[0760] Hardware and software to be used

[0761] Hardware: Head-mounted display (e.g., general term)

[0762] Software: Emotion recognition engine, information processing unit, generative AI model

[0763] Specific example

[0764] For example, if an administrator wears an HMD and inputs "Predicted workload for this month is 10,000 units," and then at the end of the month inputs "Actual workload is 11,500 units," the server calculates a discrepancy of 15%. Furthermore, the emotion recognition engine analyzes the collected emotion data and identifies that 500 packages were shipped on a specific day and that the user was feeling stressed on that day. Based on this, the server uses a generative AI model to predict future workload and displays to the administrator that "12,000 packages are predicted for next month, and 11,000 packages for the month after."

[0765] Examples of prompts to input into a generative AI model:

[0766] The user wears an HMD and enters "Predicted workload for this month: 10,000 units." At the end of the month, enter the actual volume as "11,500 units." The system automatically calculates the deviation rate and performs a cause analysis for the specific day based on sentiment data.

[0767] The above describes the "mode for carrying out the invention." By using a head-mounted display, real-time input of work data and collection of emotion data become possible, enabling highly accurate workload prediction and efficient resource allocation.

[0768] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0769] Step 1: The user enters the predicted workload data.

[0770] ---

[0771] The user uses a head-mounted display (HMD) to input projected workload data at the beginning of the month. During this process, the user enters information such as "Projected workload for this month: 10,000 units" through the HMD's interface. This input data is then transmitted to an information processing unit.

[0772] Input: Forecasted workload data

[0773] Output: Predicted workload data transmitted to the information processing device.

[0774] Step 2: The user enters actual workload data.

[0775] ---

[0776] At the end of the month, users use a similar HMD to input actual workload data. They enter data such as "Actual workload: 11,500 units," and this data is also sent to the information processing device.

[0777] Input: Actual workload data

[0778] Output: Actual workload data transmitted to the information processing device.

[0779] Step 3: The server saves the data.

[0780] ---

[0781] The server receives predicted and actual workload data sent by the user, verifies that the data format is correct, and stores it in the database of the information processing device.

[0782] Input: Forecasted workload data, actual workload data

[0783] Output: Predicted workload data and actual workload data stored in the database.

[0784] Step 4: The server calculates the deviation rate.

[0785] ---

[0786] The server calculates the deviation rate based on the predicted and actual data stored in the database. For example, if the predicted number of tasks is 10,000 and the actual number is 11,500, the server performs the following calculation: (Actual workload - Predicted workload) / Predicted workload 100. In this example, the deviation rate is 15%. This calculation result is stored as internal data.

[0787] Input: Forecasted workload data, actual workload data

[0788] Output: Calculated deviation rate

[0789] Step 5: The server collects sentiment data.

[0790] ---

[0791] The server uses the emotion recognition engine built into the HMD to analyze the user's facial expressions and voice tone, and collects emotional data. For example, it quantifies and records the user's stress and satisfaction levels when entering work data. This emotional data is then stored on the information processing device.

[0792] Input: User's facial expressions and tone of voice

[0793] Output: Saved sentiment data

[0794] Step 6: The server identifies the cause of the discrepancy.

[0795] ---

[0796] The server analyzes stored business data based on collected emotional data to identify the cause of discrepancies. For example, if the emotional data indicates "stress," it examines the detailed logs at that time to analyze whether there were concentrated inquiries on a specific day or in a specific category.

[0797] Input: Emotional data, business data

[0798] Output: Identified causes of discrepancies

[0799] Step 7: The server predicts future workload.

[0800] ---

[0801] The server builds a generative AI model based on past business data and collected sentiment data to predict future workloads. For example, by applying past data and sentiment scores as input data to the model, it predicts that the workload for next month will be 12,000 and the workload for the month after that will be 11,000. This prediction result is also stored as internal data.

[0802] Input: Past business data, sentiment data

[0803] Output: Future workload forecast data

[0804] Step 8: The server displays the calculation results to the user.

[0805] ---

[0806] The server generates a report summarizing the results of the deviation rate calculation, the results of identifying the cause of the deviation, and the results of future workload forecasts. This report is displayed in real time on the user's HMD, and the user can use this information to make appropriate resource allocations and business improvements.

[0807] Input: Deviation rate calculation result, deviation cause identification result, future workload forecast result

[0808] Output: Report displayed on the HMD

[0809] The above is the flow of specific processing steps of the system based on the application example. Sorry, I'm not sure.

[0810] 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.

[0811] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An 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.

[0812] 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.

[0813] [Third Embodiment]

[0814] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0815] 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.

[0816] 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).

[0817] 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.

[0818] 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.

[0819] 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).

[0820] 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.

[0821] 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.

[0822] 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.

[0823] 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.

[0824] 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.

[0825] 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".

[0826] This system is designed to predict workload, identify discrepancies between actual and projected workloads, analyze the causes, and forecast future workloads. A specific implementation of this system is described below.

[0827] 1. Users enter business data.

[0828] Users access the system and utilize an interface to input their projected workload at the beginning of each month. For example, they might input "1000 inquiries are expected" at the start of the month. At the end of the month, they input actual data through a similar interface. For example, they might input "1200 inquiries were the actual number" at the end of the month. This allows users to easily register both projections and actual figures.

[0829] 2. The server saves the data.

[0830] The predicted and actual workload data entered by the user is received by the server. The server verifies that the received data is in the correct format and saves it to the database. This saved data is then used as the basis for subsequent calculations and analyses.

[0831] 3. The server calculates the deviation rate.

[0832] The server calculates the deviation rate based on the stored predicted and actual data. For example, if the predicted workload is 1000 and the actual workload is 1200, the server performs the following calculation: Deviation rate = (Actual workload - Predicted workload) / Predicted workload 100. In this example, the deviation rate is 20%. This calculation result is used to allow users to easily understand performance over a specific period.

[0833] 4. The server identifies the cause of the discrepancy.

[0834] The server analyzes stored business data to identify the cause of the discrepancy. For example, the server can find patterns based on the date, time, and category of inquiries, identifying that inquiries were concentrated on specific days or in specific categories. This allows the server to report the specific cause of the discrepancy to the user.

[0835] 5. The server predicts future workload.

[0836] The server collects historical business data and uses it to build a machine learning model. For example, it uses data on predicted and actual workload for the past six months. This model can accurately predict workload for the next few months. The prediction results are output in the form of, for example, "We predict 1200 inquiries next month and 1100 inquiries the month after."

[0837] 6. Display the results to the user.

[0838] The server generates a report summarizing the results of the deviation rate calculation, the identification of the cause of the deviation, and future workload forecasts. This report is displayed in real time on the user's dashboard. Based on this, users can adjust their work and optimize staffing.

[0839] Specific example

[0840] For example, if a user enters "1000 predicted workloads for this month" and "1200 actual workloads at the end of the month," the server saves this data and calculates that "the discrepancy rate is 20%." Further analysis identifies the cause of the discrepancy, such as "500 inquiries concentrated on a specific day." Based on this, the server refers to past data to predict the workload for the following months and displays to the user, "1200 inquiries are predicted for next month, and 1100 for the month after."

[0841] This allows users to understand their future workload and make appropriate resource allocations and personnel assignments. Each of these methods significantly improves operational efficiency and minimizes discrepancies.

[0842] The following describes the processing flow.

[0843] Step 1:

[0844] Users input workload forecast data.

[0845] Users log in to the system and enter their monthly workload forecast data into a dedicated input form. The input fields include the number of inquiries and other forecast parameters. After entering the data, they press the submit button to send it to the server.

[0846] Step 2:

[0847] The server stores the prediction data.

[0848] The server receives the prediction data submitted by the user and performs a format check (validation). If the data is correct, it executes an SQL command (e.g., INSERT INTO) to save the prediction data to the database. Once the saving is complete, it notifies the user that the data has been successfully saved.

[0849] Step 3:

[0850] Users enter performance data.

[0851] At the end of the month, users log back into the system and enter their actual workload data. The input fields include the actual number of inquiries and other performance parameters. After entering the data, they press the submit button again to send it to the server.

[0852] Step 4:

[0853] The server saves performance data.

[0854] The server receives the performance data submitted by the user and performs a format check (validation). If the data is correct, it executes an SQL command (e.g., INSERT INTO) to save the performance data to the database. Once the saving is complete, it notifies the user that the data has been saved successfully.

[0855] Step 5:

[0856] The server calculates the deviation rate.

[0857] The server retrieves forecast and actual data for the relevant month from the database. Next, it calculates the deviation rate based on this data. The formula is: Deviation Rate = (Actual Workload - Forecasted Workload) / Forecasted Workload 100. The calculation result is stored as internal data.

[0858] Step 6:

[0859] The server identifies the cause of the discrepancy.

[0860] The server analyzes past business data to identify patterns such as concentrated inquiries on specific days or categories. For example, the server might identify a cluster of 500 inquiries on a particular day and extract detailed log data for that day. This information is compiled and reported to the user as the cause of the discrepancy.

[0861] Step 7:

[0862] The server predicts future workload.

[0863] The server collects historical business data from the database and uses it to build a machine learning model (e.g., a regression analysis model). Next, it uses this model to predict the workload for the next few months. For example, it might predict 1200 inquiries next month and 1100 inquiries the month after. This prediction is also stored as internal data.

[0864] Step 8:

[0865] The server displays the calculation results to the user.

[0866] The server generates a report summarizing the results of the deviation rate calculation, the results of identifying the cause of the deviation, and the results of future workload forecasts. This report is displayed on the user's dashboard in real time. Based on this information, users can improve the efficiency of their work and allocate resources appropriately.

[0867] These steps allow users to understand the discrepancy between monthly forecasts and monthly actuals, identify the causes to improve operational efficiency, and allocate resources appropriately based on future workload forecasts.

[0868] (Example 1)

[0869] 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."

[0870] Conventional workload forecasting systems lack sufficient functionality to automatically calculate and analyze discrepancies between forecasts and actual results, making it difficult to identify the causes and improve the accuracy of future workload forecasts. In addition, the lack of an interface that allows users to easily input work data and check the results in real time is also a problem. While this is expected to improve operational efficiency, in reality, it requires a lot of manual work, which is burdensome.

[0871] 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.

[0872] In this invention, the server includes means for the user to input predicted workload data, means for the user to input actual workload data, means for the server device to receive the input data, validate the data format and store it, means for calculating the deviation rate based on the stored predicted and actual data, means for analyzing the cause of the deviation and extracting specific patterns, means for constructing a machine learning model to predict future workload based on past work data and making predictions, and means for displaying the calculation results and analysis results to the user in real time. As a result, the user can immediately check the difference between the predicted and actual workload data they have entered, quickly identify the cause of the deviation, and predict future workload with high accuracy. Consequently, it is possible to adjust operations and optimize personnel allocation, significantly improving overall operational efficiency.

[0873] "The means by which users input workload forecast data" refers to the interface that allows users to input workload forecast data into the system. This interface is designed to allow users to easily input data.

[0874] "The means by which users input actual workload data" refers to the interface that allows users to input data on their actual workload into the system. This is also designed to allow users to input data easily.

[0875] "A means of receiving data via a server device, validating the data format, and storing it" refers to the function where a server receives data sent from a user, verifies whether the data format is correct, and then stores it in a database.

[0876] "Means for calculating the deviation rate based on stored forecast and actual data" refers to a function that calculates the deviation rate using the forecast and actual workload data stored on the server. The deviation rate is a value that expresses the difference between the forecast and the actual results.

[0877] "Means for analyzing the cause of discrepancies and extracting specific patterns" refers to a function in which the server analyzes stored data to identify the cause of discrepancies and extracts patterns based on specific dates, times, or categories.

[0878] "A means of building a machine learning model to predict future workload based on past business data" refers to a function where the server analyzes past business data to build a machine learning model and uses that model to predict future workload.

[0879] "A means of displaying calculation and analysis results to the user in real time" refers to a function that displays the calculated deviation rate, analysis results, and predicted future workload on the user's dashboard in real time.

[0880] This invention is a system for predicting workload, identifying discrepancies between actual and projected workload, analyzing the causes of these discrepancies, and predicting future workload. A specific embodiment of this system is described below.

[0881] The user first inputs predicted and actual workload data. The input interface is provided via a web browser, with a simple form for easy data entry. For example, the user might input "Predicted workload for this month: 1000 items" and "Actual workload at the end of the month: 1200 items." This data is then sent to the server in JSON format.

[0882] The server is implemented using Node.js and receives HTTP requests using the Express framework. It receives the sent JSON data and validates its contents. After successful validation, the data is stored in MongoDB. MongoDB is connected to the server via Mongoose, and predicted workload data and actual workload data are stored in separate collections.

[0883] Based on the stored data, the server calculates the deviation rate. The formula used for the calculation is as follows: Deviation rate = (Actual workload - Forecasted workload) / Forecasted workload 100. For example, if the forecast is 1000 and the actual workload is 1200, the deviation rate will be calculated as 20%. This calculation result is temporarily stored in memory.

[0884] Next, the server analyzes the data to identify the cause of the discrepancy. It runs aggregate queries to find patterns based on specific days or categories, and if, for example, 500 inquiries were concentrated on a particular day, it analyzes the details to identify the cause.

[0885] The server collects business data from the past six months and builds a predictive model using a Python machine learning library (e.g., Scikit-learn). Using the trained model, it predicts future business volume. The prediction results are output in the format of "1200 inquiries are predicted for next month, and 1100 inquiries for the month after."

[0886] The calculation results, analysis results, and prediction results are compiled into a report. The server generates this report in HTML or PDF format and displays it in real time on the user dashboard. Visualization tools such as Grafana are used on the dashboard, and the data is updated in real time. Based on this, users can adjust their work and optimize staffing.

[0887] For example, if a user inputs, "This month's projected workload is 1000 inquiries. The actual workload was 1200. Based on this, calculate the discrepancy rate and identify the cause. Then, predict the workload for next month and the month after," the server will save this data, identify a "20% discrepancy rate," and determine that 500 inquiries were concentrated on a specific day. Subsequently, the server will display to the user in real time the predicted results: 1200 inquiries for the next month and 1100 inquiries for the month after. This allows the user to understand future workloads and make appropriate resource allocations and personnel assignments.

[0888] This invention significantly improves operational efficiency and minimizes the occurrence of discrepancies.

[0889] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0890] Step 1:

[0891] Users input workload forecast data.

[0892] Users access the system and input workload forecast data through the interface. The input data is sent to the server in JSON format. For example, inputting "This month's forecast workload is 1000 items." Input (workload forecast data) → Output (data in JSON format)

[0893] Step 2:

[0894] The server receives the prediction data and performs validation.

[0895] The server is implemented using Node.js and receives HTTP requests using the Express framework. It validates the structure and content of the received JSON data to ensure it is in the correct format. Input (JSON-formatted workload forecast data) → Output (Validation result: Success / Failure)

[0896] Step 3:

[0897] The server stores the prediction data.

[0898] If validation is successful, the server connects to MongoDB via Mongoose and saves the predicted data. When saving, it saves the data to a collection of predicted workload data within the database. Input (validated workload prediction data) → Output (save complete message)

[0899] Step 4:

[0900] Users input actual workload data.

[0901] Users input their actual workload data for the current month through a similar interface. For example, they might input "This month's actual workload is 1200 items." Input (actual workload data) → Output (data in JSON format)

[0902] Step 5:

[0903] The server receives the performance data and performs validation.

[0904] The server receives an HTTP request and validates the structure and content of the received actual workload data. Input (actual workload data in JSON format) → Output (validation result: success / failure)

[0905] Step 6:

[0906] The server saves performance data.

[0907] If validation is successful, the server saves the actual workload data to the MongoDB collection of actual workload data. Input (validated actual workload data) → Output (save complete message)

[0908] Step 7:

[0909] The server calculates the deviation rate.

[0910] The server calculates the deviation rate based on the stored predicted workload data and actual workload data. The formula is as follows: Deviation Rate = (Actual Workload - Predicted Workload) / Predicted Workload 100. Input (Predicted Workload Data, Actual Workload Data) → Output (Deviation Rate)

[0911] Step 8:

[0912] The server analyzes the cause of the discrepancy.

[0913] The server analyzes stored business data to identify the cause of the discrepancy. For example, it uses the Parse function to find patterns based on specific days or categories. Input (business data) → Output (analysis results regarding the cause of the discrepancy)

[0914] Step 9:

[0915] The server predicts future workload.

[0916] The server collects historical business data and builds a predictive model using the Python machine learning library (Scikit-learn). Using the trained model, it predicts the workload for the following two months. Input (historical business data) → Output (future workload prediction)

[0917] Step 10:

[0918] The server compiles the results and generates a report.

[0919] The server generates a report summarizing the calculation results of the deviation rate, the results of identifying the cause of the deviation, and the forecast of future workload. This report is output in HTML or PDF format. Input (calculation results, analysis results, forecast results) → Output (report)

[0920] Step 11:

[0921] The device displays the report.

[0922] The user's device displays reports sent from the server on a dashboard. Visualization tools such as Grafana are used on the dashboard, and data is updated in real time. Input (Report) → Output (Display on Dashboard)

[0923] (Application Example 1)

[0924] 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."

[0925] Traditional logistics centers have struggled to efficiently analyze discrepancies between projected and actual workload forecasts, making it difficult to optimize resource allocation and staffing. Leaving this problem unaddressed leads to decreased operational efficiency, increased costs, and negatively impacts service quality.

[0926] 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.

[0927] In this invention, the server includes means for the user to input predicted workload data, means for the user to input actual workload data, server means for storing the input data, server means for calculating the deviation rate based on the stored predicted and actual data, server means for analyzing the causes of the deviation and extracting specific topics, server means for predicting future workload based on past business data, means for displaying the calculation results and analysis results to the user, means for predicting future workload with high accuracy using a machine learning model, and means for optimizing the allocation of business resources within the logistics center. This enables accurate prediction of workload, efficient deviation analysis, and appropriate resource allocation.

[0928] A "user" is someone who uses the system to input predicted workload data and actual workload data.

[0929] "Predicted workload data" refers to data entered by users at the beginning of the month or other times when they anticipate their workload.

[0930] "Actual workload data" refers to the actual workload data entered by users at the end of each month.

[0931] A "server" is a device or system that stores predicted and actual workload data, calculates deviation rates, analyzes causes, and predicts future workload.

[0932] "Deviation rate" is an indicator that expresses the difference between predicted workload and actual workload as a percentage.

[0933] "Cause of discrepancy" refers to the reason for the difference between the predicted workload and the actual workload.

[0934] "Specific topics" refer to areas of interest or themes that have been identified in order to pinpoint the causes of the discrepancy.

[0935] "Past business data" refers to previously recorded predicted workload data and actual workload data.

[0936] A "machine learning model" is an algorithm used to predict future workloads based on past data.

[0937] "Resource allocation" refers to the appropriate placement of personnel and equipment within a logistics center.

[0938] A system implementing this invention specifically includes an application for predicting workload and managing efficiency in a logistics center. This application allows the user to input operational data, which is then processed, analyzed, and predicted by a server, with the results displayed to the user in real time.

[0939] Users can input predicted and actual workload data using applications installed on smartphones, smart glasses, head-mounted displays, or robots. For example, they might input "1000" for the predicted workload for the month and "1200" for the actual workload at the end of the month.

[0940] The server receives the data, validates its format, and stores it in the database. Based on the stored predicted and actual workload data, the server calculates the deviation rate. For example, if the predicted workload is 1000 and the actual workload is 1200, the deviation rate is 20%. This calculated deviation rate is used to help users easily understand performance over a specific period.

[0941] Furthermore, the server analyzes stored business data to identify the cause of the discrepancy. For example, it might identify that the workload was concentrated on a particular day or in a particular category. This allows the server to report the specific cause of the discrepancy to the user.

[0942] The server also builds machine learning models based on past business data to predict future workloads. These models are trained using, for example, data on predicted and actual workloads over the past six months. This allows for highly accurate predictions of workloads for the following month and the month after. For example, the output might state, "We predict 1200 inquiries next month and 1100 inquiries the month after."

[0943] Calculation and analysis results are displayed in real time on the user's dashboard. Users can use this information to adjust operations and optimize staffing. This dashboard can also be viewed at any time by field workers using smart glasses or head-mounted displays.

[0944] Implementing this system will improve the accuracy of business forecasts, optimize resource allocation, and increase the operational efficiency of the logistics center. Furthermore, the calculation results will be provided to the user as specific prompt messages. For example, the following prompt messages may be generated:

[0945] "Our projected workload for December was 1,000 cases, but the actual volume was 1,500. Please tell us the discrepancy rate and the reasons for it. Also, please provide a workload forecast for next month."

[0946] In this way, users can utilize the system to achieve efficient business operations.

[0947] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0948] Step 1:

[0949] The user enters predicted workload data on a terminal. The entered data is sent to the server as predicted workload data. As an example, the user might enter "This month's predicted workload is 1000 items."

[0950] Step 2:

[0951] Users input actual workload data on their terminals. This data is entered at the end of each month and sent to the server. For example, a user might enter, "This month's actual workload is 1200 items."

[0952] Step 3:

[0953] The server receives predicted and actual workload data and validates its format. After verifying that the data is in a valid format, it is saved to the database.

[0954] Step 4:

[0955] The server calculates the deviation rate based on the stored predicted and actual data. Specifically, it performs the following calculations:

[0956] The deviation rate is calculated as follows: Deviation rate = (Actual workload - Forecasted workload) / Forecasted workload 100. For example, if the forecast is 1000 and the actual workload is 1200, the deviation rate is 20%. The calculation result is output as the deviation rate and stored in the database.

[0957] Step 5:

[0958] The server analyzes stored business data to identify the cause of the discrepancy. For example, it finds patterns based on the date, time, and category of inquiries, identifying that inquiries were concentrated on specific days or in specific categories. Based on these analysis results, it outputs the cause of the discrepancy.

[0959] Step 6:

[0960] The server collects historical business data and uses it to build a machine learning model. The model is trained using data on predicted and actual workloads over the past six months. This allows for highly accurate predictions of future workloads. The output is a predicted workload, such as "1200 cases next month, 1100 cases the month after."

[0961] Step 7:

[0962] The server generates a report summarizing the calculation and analysis results, which is then displayed in real time on the user's dashboard. This dashboard is designed to be accessible to field workers using smart glasses or head-mounted displays. Users can then use this information to adjust operations and optimize staffing.

[0963] Step 8:

[0964] The server generates prompt messages based on user input. For example, it might create a specific prompt message such as, "The predicted workload for December was 1000, but the actual workload was 1500. Please tell me the discrepancy rate and the reason. Also, please provide a workload forecast for next month." Based on this, the user can take actions to achieve efficient business operations.

[0965] 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.

[0966] This system not only predicts workload, identifies discrepancies with actual results, analyzes causes, and forecasts future workload, but also achieves even more accurate analysis and prediction by combining it with an emotion engine that recognizes user emotions. The specific implementation details are described below.

[0967] 1. Users enter business data.

[0968] Users access the system and utilize an interface to input their projected workload at the beginning of each month. For example, they might input "1000 inquiries are expected" at the start of the month. At the end of the month, they input actual data through a similar interface. For example, they might input "1200 inquiries were the actual number" at the end of the month. This allows users to easily register both projections and actual figures.

[0969] 2. The server saves the data.

[0970] The predicted and actual workload data entered by the user is received by the server. The server verifies that the received data is in the correct format and saves it to the database. This saved data is then used as the basis for subsequent calculations and analyses.

[0971] 3. The server calculates the deviation rate.

[0972] The server calculates the deviation rate based on the stored predicted and actual data. For example, if the predicted workload is 1000 and the actual workload is 1200, the server performs the following calculation: Deviation rate = (Actual workload - Predicted workload) / Predicted workload 100. In this example, the deviation rate is 20%. This calculation result is stored as internal data.

[0973] 4. The server collects sentiment data.

[0974] The emotion engine recognizes the user's emotions when they use the system. For example, it analyzes the user's facial expressions and tone of voice when they input business data to collect emotional data such as "stress" and "satisfaction."

[0975] 5. The server identifies the cause of the discrepancy.

[0976] The server further analyzes stored operational data based on the collected emotional data. For example, if the emotional data indicates "stress," it examines detailed logs such as the inquiry status and error count at that time to identify the cause of the discrepancy. This analysis allows the server to consider the emotional factors behind concentrated inquiries on specific days or in specific categories.

[0977] 6. The server predicts future workload.

[0978] The server collects historical business data from the database and integrates it with the sentiment data collected by the sentiment engine to build a machine learning model (e.g., a regression analysis model). This model can accurately predict the workload for the next few months. This prediction result is also stored as internal data.

[0979] 7. The server displays the calculation results to the user.

[0980] The server generates a report summarizing the results of the deviation rate calculation, the results of identifying the cause of the deviation, and the results of future workload forecasts. This report is displayed on the user's dashboard in real time. Based on this information, users can improve the efficiency of their work and allocate resources appropriately.

[0981] Specific example

[0982] For example, if a user enters "1000 predicted workloads for this month" and "1200 actual workloads at the end of the month," the server saves this data and calculates that the "deviation rate is 20%." Further analysis identifies the cause of the deviation as "500 inquiries concentrated on a specific day" and that the user felt "stressed" on that day. Based on this, the server refers to past data to predict the workload for the following months and displays to the user "1200 inquiries are predicted for next month, and 1100 for the month after."

[0983] This allows users to understand their future workload while taking emotional data into account, enabling appropriate resource allocation and process improvements. Each of these methods significantly improves work efficiency and minimizes discrepancies. Utilizing emotional data allows for more flexible responses that take human factors into account.

[0984] The following describes the processing flow.

[0985] Step 1:

[0986] Users input workload forecast data.

[0987] Users log in to the system and enter their monthly workload forecast data into a dedicated input form. The input fields include the number of inquiries and other forecast parameters. After entering the data, they press the submit button to send it to the server.

[0988] Step 2:

[0989] The server stores the prediction data.

[0990] The server receives the prediction data submitted by the user and performs a format check (validation). If the data is correct, it executes an SQL command (e.g., INSERT INTO) to save the prediction data to the database. Once the saving is complete, it notifies the user that the data has been successfully saved.

[0991] Step 3:

[0992] Users enter performance data.

[0993] At the end of the month, users log back into the system and enter their actual workload data. The input fields include the actual number of inquiries and other performance parameters. After entering the data, they press the submit button again to send it to the server.

[0994] Step 4:

[0995] The server saves performance data.

[0996] The server receives the performance data submitted by the user and performs a format check (validation). If the data is correct, it executes an SQL command (e.g., INSERT INTO) to save the performance data to the database. Once the saving is complete, it notifies the user that the data has been saved successfully.

[0997] Step 5:

[0998] The server calculates the deviation rate.

[0999] The server retrieves forecast and actual data for the relevant month from the database. Next, it calculates the deviation rate based on this data. The formula is: Deviation Rate = (Actual Workload - Forecasted Workload) / Forecasted Workload 100. The calculation result is stored as internal data.

[1000] Step 6:

[1001] Recognize user emotions and collect data.

[1002] When a user uses the system, an emotion engine activates, analyzing the user's facial expressions and tone of voice. For example, while a user is operating an input form or entering business data, the system uses a camera and microphone to collect emotion data.

[1003] Step 7:

[1004] The server stores emotional data.

[1005] The collected sentiment data is sent to the server for formatting checks (validation). If the data is correct, an SQL command (e.g., INSERT INTO) is executed to save the sentiment data to the database. Once saved, the sentiment data is integrated with other business data.

[1006] Step 8:

[1007] The server analyzes and identifies the cause of the discrepancy based on emotional data.

[1008] The server analyzes the cause of the discrepancy based on stored emotional and operational data. For example, if it examines data from a specific day and finds that the user was experiencing "stress" on that day, it checks the detailed log data of inquiries that occurred on that day. This allows it to identify why the discrepancy occurred on that day, including the underlying emotional factors.

[1009] Step 9:

[1010] The server predicts future workload based on past data.

[1011] The server integrates historical business data and sentiment data from the database and uses this to build a machine learning model (e.g., a regression analysis model). This model allows for highly accurate predictions of workload for the next few months.

[1012] Step 10:

[1013] The server displays the calculation results and prediction results to the user.

[1014] The server generates a report summarizing the results of the deviation rate calculation, the results of identifying the cause of the deviation, and the results of future workload forecasts. This report is displayed on the user's dashboard in real time. Based on this information, users can improve the efficiency of their work and allocate resources appropriately.

[1015] Specific example

[1016] For example, if a user enters "1000 predicted workloads for this month" and "1200 actual workloads at the end of the month," the server saves this data and calculates that the "deviation rate is 20%." Furthermore, the system senses that the user is experiencing "stress" while entering the data and records this. Analysis identifies the cause of the deviation as "500 inquiries concentrated on a particular day" and that the user was experiencing "stress" on that day. Based on this, the system refers to past data to predict the workload for the following months and displays to the user that "1200 inquiries are predicted for next month, and 1100 for the month after."

[1017] By combining this with an emotion engine, it becomes possible to provide more flexible responses that take human factors into account, further improving work efficiency.

[1018] (Example 2)

[1019] 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."

[1020] Conventional workload forecasting systems have faced challenges in identifying the causes of discrepancies between predicted and actual workloads, as well as in the limited accuracy of future workload forecasts. This has resulted in limitations in improving operational efficiency and appropriate resource allocation. Furthermore, systems that do not consider human emotions make it difficult to comprehensively analyze the impact of actual work processes and users' psychological states.

[1021] 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.

[1022] In this invention, the server includes means for collecting emotional data when a user inputs data, server means for identifying the cause of discrepancies based on the collected emotional data, and server means for predicting future workload based on past work data. This makes it possible to more accurately identify the cause of discrepancies between predicted and actual workload and to predict future workload with high accuracy. Furthermore, by incorporating user emotional data into the analysis, it becomes possible to respond more flexibly, taking human factors into consideration, thereby improving work efficiency and achieving appropriate resource allocation.

[1023] A "user" is a person who uses the system to input workload data and performance data, and performs operations to obtain analysis results and prediction results.

[1024] "Predicted workload data" refers to data about the workload that users expect to occur during a specific period in the future.

[1025] "Actual workload data" refers to data on the actual workload generated by a user during a specific period.

[1026] A "server" is a computing system that receives, stores, and analyzes data entered by users, and provides calculation results, prediction results, and other information.

[1027] "Validation" is the process of verifying whether the format and content of the entered data are correct.

[1028] A "database" is an electronic data storage system for systematically organizing, storing, searching, and managing various types of data.

[1029] The "deviation rate" is the percentage that shows the difference between predicted workload data and actual workload data, and is calculated based on a formula.

[1030] "Emotional data" is data obtained by analyzing a user's emotions from their facial expressions, tone of voice, etc., and it indicates emotional states such as "stress" or "satisfaction."

[1031] A "machine learning model" is an algorithm or mathematical model used to learn from past data and predict future data.

[1032] "Causes of discrepancy" refers to the factors that cause the difference between predicted workload data and actual workload data.

[1033] A "report" is a document that summarizes calculation results, analysis results, and prediction results, and is an aggregation of analytical information provided to the user.

[1034] Modes for carrying out the invention

[1035] The system implementing this invention has a set of functions in which, as a primary means, the user inputs business data, and the server analyzes, stores, and predicts that data. Specifically, the hardware and software used in each step include the following:

[1036] User data entry method

[1037] Users access the system using a dedicated web browser or mobile application via an internet-connected device (e.g., PC, tablet, smartphone). Users log in to the system and input projected workload data at the beginning of the month and actual workload data at the end of the month. For example, they might input "Projected workload for this month: 1000 items" and then "Actual workload: 1200 items" at the end of the month.

[1038] Server-based data storage and validation

[1039] The entered data is sent to the server. The server validates the data format (e.g., confirms that the number of queries is an integer) and displays an error message to the user if there is any inappropriate data. Data in the correct format is stored in the database. This database uses a relational database management system such as SQL.

[1040] Calculation of deviation rate

[1041] The server calculates the deviation rate based on the stored predicted workload data and actual workload data. For example, if the predicted workload is 1000 and the actual workload is 1200, the server calculates the deviation rate as follows: "Deviation Rate = (Actual Workload - Predicted Workload) / Predicted Workload 100". In this example, the deviation rate is calculated to be 20%. The calculation result is stored in the database.

[1042] Collection of user sentiment data

[1043] As the user enters data, the system's built-in emotion engine activates and analyzes the user's facial expressions and voice tone through the webcam and microphone. The emotion engine generates emotional data such as "stress" and "satisfaction" from this input and sends and stores it on the server.

[1044] Identifying the cause of the discrepancy

[1045] The server analyzes stored business data based on the collected sentiment data. For example, if the sentiment data indicates "stress," it investigates the detailed logs for that period and identifies that inquiries concentrated on specific days or categories are causing the discrepancies. This allows for a more detailed analysis of factors hindering business efficiency.

[1046] Predicting future workload

[1047] The server uses historical business data and sentiment data to build a machine learning model (e.g., a regression analysis model) to predict future workload. This model is implemented using programming languages ​​such as Python or R. For example, it might produce results such as, "We predict 1200 inquiries next month and 1100 inquiries the month after."

[1048] Displaying Results

[1049] The server generates a report summarizing the calculated deviation rate, identified deviation causes, and future workload forecasts. This report is displayed on the user's dashboard in real time. Based on this information, users can take actions to improve work efficiency.

[1050] Specific example

[1051] For example, if a user enters "1000 predicted workloads for this month" and "1200 actual workloads at the end of the month," the server saves this data and calculates that the "deviation rate is 20%." Furthermore, it identifies that 500 inquiries were concentrated on a specific day and that the user felt "stressed" on that day. Based on this information, the server predicts the workload for the following months and displays to the user that "1200 inquiries are predicted for next month, and 1100 for the month after."

[1052] Example of a prompt

[1053] "Analyze the discrepancy rate and its causes when the projected workload for this month is 1000 items and the actual workload at the end of the month is 1200 items."

[1054] This allows users to understand their future workload while taking emotional data into account, enabling appropriate resource allocation and process improvements. Each of these methods significantly improves work efficiency and minimizes discrepancies. Utilizing emotional data allows for more flexible responses that take human factors into account.

[1055] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1056] Specific processing steps of the program for this system

[1057] Step 1: The user enters business data.

[1058] input:

[1059] Predicted workload data (e.g., "1000 inquiries are predicted")

[1060] Actual workload data (e.g., "Actual number of inquiries: 1200")

[1061] process:

[1062] Users log in to the system using a web browser or mobile app.

[1063] After logging in, the business data entry screen will be displayed.

[1064] At the beginning of the month, you will enter your projected workload into the input form, and at the end of the month, you will enter your actual workload.

[1065] Click the submit button on the form to send the data to the server.

[1066] output:

[1067] Business data (predicted workload data and actual workload data) is sent to the server.

[1068] Step 2: The server saves the data.

[1069] input:

[1070] Business data submitted by users

[1071] process:

[1072] The server validates the data received from the user. For example, it checks whether the number of queries is an integer.

[1073] If validation is successful, the data is saved to the database.

[1074] If validation fails, an error message is returned to the user.

[1075] output:

[1076] Business data stored in the database

[1077] Validation result (success / failure)

[1078] Success message or error message

[1079] Step 3: The server calculates the deviation rate.

[1080] input:

[1081] Predicted workload data and actual workload data stored in the database

[1082] process:

[1083] The server retrieves predicted and actual workload data from the database.

[1084] The deviation rate is calculated using the following formula: "Deviation Rate = (Actual Workload - Forecasted Workload) / Forecasted Workload 100".

[1085] Save the calculation results to the database.

[1086] output:

[1087] Deviation rate stored in the database

[1088] Step 4: The server collects sentiment data.

[1089] input:

[1090] Facial expressions and tone of voice (collected via webcam and microphone) when users input business data.

[1091] process:

[1092] The server activates an emotion engine and analyzes the user's facial expressions and voice in real time.

[1093] The emotion engine generates emotion data (e.g., "stress" or "satisfaction").

[1094] The generated emotion data is sent to the server and stored in the database.

[1095] output:

[1096] Emotional data stored in the database

[1097] Step 5: The server identifies the cause of the discrepancy.

[1098] input:

[1099] Saved emotional data

[1100] Predicted workload data, actual workload data, and deviation rate

[1101] process:

[1102] The server performs analysis based on stored business data and emotional data.

[1103] Extract detailed data on periods when emotional data indicates "stress."

[1104] We will investigate detailed logs of inquiries concentrated on specific days or time periods to identify the cause of the discrepancy.

[1105] output:

[1106] Identified causes of discrepancies

[1107] Step 6: The server predicts future workload.

[1108] input:

[1109] Past business data

[1110] Emotional data

[1111] process:

[1112] The server builds a machine learning model (e.g., a regression analysis model) based on historical data.

[1113] We will use the constructed model to predict future workload.

[1114] Save the prediction results to the database.

[1115] output:

[1116] Future workload forecast results stored in the database

[1117] Step 7: The server displays the calculation results to the user.

[1118] input:

[1119] deviation rate

[1120] Causes of discrepancy

[1121] Future workload forecast results

[1122] process:

[1123] The server integrates the deviation rate, the cause of the deviation, and the forecast results for future workload to create a report.

[1124] After the report is generated, it will be displayed in real time on the user's dashboard.

[1125] output:

[1126] Reports displayed on the user dashboard

[1127] This allows users to understand their future workload while taking emotional data into account, enabling appropriate resource allocation and process improvements. Each of these methods significantly improves work efficiency and minimizes discrepancies. Furthermore, utilizing emotional data allows for more flexible responses that take human factors into account.

[1128] (Application Example 2)

[1129] 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."

[1130] Logistics centers need a function to analyze the discrepancy between predicted and actual workloads and to predict future workloads with high accuracy. In particular, there is a need for more accurate predictions, early detection of problems, and efficient resource allocation by utilizing real-time sentiment data of managers. However, conventional systems do not include sentiment data in their analysis, which limits their ability to identify the causes of discrepancies and improve the accuracy of future workload predictions.

[1131] 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.

[1132] In this invention, the server includes means for the user to input predicted workload data, means for the user to input actual workload data, information processing means for storing the input data, information processing means for calculating a deviation rate based on the stored predicted and actual data, means for collecting user emotion data using an emotion recognition engine, information processing means for analyzing the causes of the deviation and extracting specific topics, information processing means for predicting future workload based on past work data, and means for analyzing emotion data and displaying it together with the deviation rate. This makes it possible to analyze the causes of workload deviations, including user emotion data, and improve the accuracy of future workload predictions.

[1133] "Predicted workload data" refers to data that shows the amount of work that users predict will be processed within a certain period.

[1134] "Actual workload data" refers to data that shows the actual amount of work processed within a certain period.

[1135] "Information processing device means" refers to a server or computer system that performs data storage, calculation, analysis, and display.

[1136] The "deviation rate" is a value that expresses the difference between the predicted workload and the actual workload as a percentage.

[1137] An "emotion recognition engine" is software or hardware used to analyze a user's emotions and collect emotional data.

[1138] "Emotional data" refers to data that expresses a user's emotional state using numerical values ​​or categories.

[1139] "Specific topics" refer to specific items or themes extracted from the analysis results of the causes of the discrepancies.

[1140] "Future workload forecasting" is a process of estimating future workloads based on past and present data.

[1141] A "generative AI model" is an artificial intelligence model used to extract features from accumulated data and predict future situations.

[1142] A "prompt" is an instruction or question that is input to a generative AI model.

[1143] As a specific embodiment of this invention, we will explain using a "smart logistics manager" that uses a head-mounted display (HMD) for a logistics center as an example.

[1144] 1. Input of predicted and actual workload.

[1145] The user wears an HMD (Head-Mounted Display) and inputs their projected workload at the beginning of the month. For example, they might input "Projected workload for this month: 10,000 units." Then, at the end of the month, they similarly input their actual workload. For example, they might input "Actual workload: 11,500 units." This allows the user to provide projected and actual workload data to the information processing device.

[1146] 2. Data storage and calculation of deviation rate

[1147] The server receives predicted and actual workload data entered by the user, validates the data format, and then stores it in the information processing device. Based on the stored data, it calculates the deviation rate between the predicted and actual data. For example, if the predicted volume is 10,000 and the actual volume is 11,500, the server calculates the deviation rate as 15% and stores it as internal data.

[1148] 3. Collection of emotional data

[1149] The emotion recognition engine integrated into the HMD analyzes the user's facial expressions and voice tone, collecting emotional data. For example, it quantifies and records the user's stress and satisfaction levels when entering work data. This emotional data is then stored in the information processing device.

[1150] 4. Identifying the causes of the discrepancy and predicting future workload.

[1151] The server further analyzes the stored business data based on the collected emotional data to identify the cause of the discrepancy. For example, it identifies days with a high amount of emotional data indicating stress and analyzes the inquiry status and error count for those days. Next, it integrates past business data and emotional data to build a generative AI model and predict future workload. The results of the future workload prediction are also stored as internal data.

[1152] 5. Creating and displaying reports to users

[1153] The server generates a report summarizing the results of the deviation rate calculation, the results of identifying the cause of the deviation, and the results of future workload forecasts. This report is displayed in real time on the user's HMD, and the user can use this information to make appropriate resource allocations and business improvements.

[1154] Hardware and software to be used

[1155] Hardware: Head-mounted display (e.g., general term)

[1156] Software: Emotion recognition engine, information processing unit, generative AI model

[1157] Specific example

[1158] For example, if an administrator wears an HMD and inputs "Predicted workload for this month is 10,000 units," and then at the end of the month inputs "Actual workload is 11,500 units," the server calculates a discrepancy of 15%. Furthermore, the emotion recognition engine analyzes the collected emotion data and identifies that 500 packages were shipped on a specific day and that the user was feeling stressed on that day. Based on this, the server uses a generative AI model to predict future workload and displays to the administrator that "12,000 packages are predicted for next month, and 11,000 packages for the month after."

[1159] Examples of prompts to input into a generative AI model:

[1160] The user wears an HMD and enters "Predicted workload for this month: 10,000 units." At the end of the month, enter the actual volume as "11,500 units." The system automatically calculates the deviation rate and performs a cause analysis for the specific day based on sentiment data.

[1161] The above describes the "mode for carrying out the invention." By using a head-mounted display, real-time input of work data and collection of emotion data become possible, enabling highly accurate workload prediction and efficient resource allocation.

[1162] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1163] Step 1: The user enters the predicted workload data.

[1164] ---

[1165] The user uses a head-mounted display (HMD) to input projected workload data at the beginning of the month. During this process, the user enters information such as "Projected workload for this month: 10,000 units" through the HMD's interface. This input data is then transmitted to an information processing unit.

[1166] Input: Forecasted workload data

[1167] Output: Predicted workload data transmitted to the information processing device.

[1168] Step 2: The user enters actual workload data.

[1169] ---

[1170] At the end of the month, users use a similar HMD to input actual workload data. They enter data such as "Actual workload: 11,500 units," and this data is also sent to the information processing device.

[1171] Input: Actual workload data

[1172] Output: Actual workload data transmitted to the information processing device.

[1173] Step 3: The server saves the data.

[1174] ---

[1175] The server receives predicted and actual workload data sent by the user, verifies that the data format is correct, and stores it in the database of the information processing device.

[1176] Input: Forecasted workload data, actual workload data

[1177] Output: Predicted workload data and actual workload data stored in the database.

[1178] Step 4: The server calculates the deviation rate.

[1179] ---

[1180] The server calculates the deviation rate based on the predicted and actual data stored in the database. For example, if the predicted number of tasks is 10,000 and the actual number is 11,500, the server performs the following calculation: (Actual workload - Predicted workload) / Predicted workload 100. In this example, the deviation rate is 15%. This calculation result is stored as internal data.

[1181] Input: Forecasted workload data, actual workload data

[1182] Output: Calculated deviation rate

[1183] Step 5: The server collects sentiment data.

[1184] ---

[1185] The server uses the emotion recognition engine built into the HMD to analyze the user's facial expressions and voice tone, and collects emotional data. For example, it quantifies and records the user's stress and satisfaction levels when entering work data. This emotional data is then stored on the information processing device.

[1186] Input: User's facial expressions and tone of voice

[1187] Output: Saved sentiment data

[1188] Step 6: The server identifies the cause of the discrepancy.

[1189] ---

[1190] The server analyzes stored business data based on collected emotional data to identify the cause of discrepancies. For example, if the emotional data indicates "stress," it examines the detailed logs at that time to analyze whether there were concentrated inquiries on a specific day or in a specific category.

[1191] Input: Emotional data, business data

[1192] Output: Identified causes of discrepancies

[1193] Step 7: The server predicts future workload.

[1194] ---

[1195] The server builds a generative AI model based on past business data and collected sentiment data to predict future workloads. For example, by applying past data and sentiment scores as input data to the model, it predicts that the workload for next month will be 12,000 and the workload for the month after that will be 11,000. This prediction result is also stored as internal data.

[1196] Input: Past business data, sentiment data

[1197] Output: Future workload forecast data

[1198] Step 8: The server displays the calculation results to the user.

[1199] ---

[1200] The server generates a report summarizing the results of the deviation rate calculation, the results of identifying the cause of the deviation, and the results of future workload forecasts. This report is displayed in real time on the user's HMD, and the user can use this information to make appropriate resource allocations and business improvements.

[1201] Input: Deviation rate calculation result, deviation cause identification result, future workload forecast result

[1202] Output: Report displayed on the HMD

[1203] The above is the flow of specific processing steps of the system based on the application example. I want to know what I'm saying.

[1204] 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.

[1205] 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.

[1206] 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.

[1207] [Fourth Embodiment]

[1208] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1209] 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.

[1210] 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).

[1211] 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.

[1212] 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.

[1213] 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).

[1214] 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.

[1215] 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.

[1216] 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.

[1217] 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.

[1218] 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.

[1219] 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.

[1220] 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".

[1221] This system is designed to predict workload, identify discrepancies between actual and projected workloads, analyze the causes, and forecast future workloads. A specific implementation of this system is described below.

[1222] 1. Users enter business data.

[1223] Users access the system and utilize an interface to input their projected workload at the beginning of each month. For example, they might input "1000 inquiries are expected" at the start of the month. At the end of the month, they input actual data through a similar interface. For example, they might input "1200 inquiries were the actual number" at the end of the month. This allows users to easily register both projections and actual figures.

[1224] 2. The server saves the data.

[1225] The predicted and actual workload data entered by the user is received by the server. The server verifies that the received data is in the correct format and saves it to the database. This saved data is then used as the basis for subsequent calculations and analyses.

[1226] 3. The server calculates the deviation rate.

[1227] The server calculates the deviation rate based on the stored predicted and actual data. For example, if the predicted workload is 1000 and the actual workload is 1200, the server performs the following calculation: Deviation rate = (Actual workload - Predicted workload) / Predicted workload 100. In this example, the deviation rate is 20%. This calculation result is used to allow users to easily understand performance over a specific period.

[1228] 4. The server identifies the cause of the discrepancy.

[1229] The server analyzes stored business data to identify the cause of the discrepancy. For example, the server can find patterns based on the date, time, and category of inquiries, identifying that inquiries were concentrated on specific days or in specific categories. This allows the server to report the specific cause of the discrepancy to the user.

[1230] 5. The server predicts future workload.

[1231] The server collects historical business data and uses it to build a machine learning model. For example, it uses data on predicted and actual workload for the past six months. This model can accurately predict workload for the next few months. The prediction results are output in the form of, for example, "We predict 1200 inquiries next month and 1100 inquiries the month after."

[1232] 6. Display the results to the user.

[1233] The server generates a report summarizing the results of the deviation rate calculation, the identification of the cause of the deviation, and future workload forecasts. This report is displayed in real time on the user's dashboard. Based on this, users can adjust their work and optimize staffing.

[1234] Specific example

[1235] For example, if a user enters "1000 predicted workloads for this month" and "1200 actual workloads at the end of the month," the server saves this data and calculates that "the discrepancy rate is 20%." Further analysis identifies the cause of the discrepancy, such as "500 inquiries concentrated on a specific day." Based on this, the server refers to past data to predict the workload for the following months and displays to the user, "1200 inquiries are predicted for next month, and 1100 for the month after."

[1236] This allows users to understand their future workload and make appropriate resource allocations and personnel assignments. Each of these methods significantly improves operational efficiency and minimizes discrepancies.

[1237] The following describes the processing flow.

[1238] Step 1:

[1239] Users input workload forecast data.

[1240] Users log in to the system and enter their monthly workload forecast data into a dedicated input form. The input fields include the number of inquiries and other forecast parameters. After entering the data, they press the submit button to send it to the server.

[1241] Step 2:

[1242] The server stores the prediction data.

[1243] The server receives the prediction data submitted by the user and performs a format check (validation). If the data is correct, it executes an SQL command (e.g., INSERT INTO) to save the prediction data to the database. Once the saving is complete, it notifies the user that the data has been successfully saved.

[1244] Step 3:

[1245] Users enter performance data.

[1246] At the end of the month, users log back into the system and enter their actual workload data. The input fields include the actual number of inquiries and other performance parameters. After entering the data, they press the submit button again to send it to the server.

[1247] Step 4:

[1248] The server saves performance data.

[1249] The server receives the performance data submitted by the user and performs a format check (validation). If the data is correct, it executes an SQL command (e.g., INSERT INTO) to save the performance data to the database. Once the saving is complete, it notifies the user that the data has been saved successfully.

[1250] Step 5:

[1251] The server calculates the deviation rate.

[1252] The server retrieves forecast and actual data for the relevant month from the database. Next, it calculates the deviation rate based on this data. The formula is: Deviation Rate = (Actual Workload - Forecasted Workload) / Forecasted Workload 100. The calculation result is stored as internal data.

[1253] Step 6:

[1254] The server identifies the cause of the discrepancy.

[1255] The server analyzes past business data to identify patterns such as concentrated inquiries on specific days or categories. For example, the server might identify a cluster of 500 inquiries on a particular day and extract detailed log data for that day. This information is compiled and reported to the user as the cause of the discrepancy.

[1256] Step 7:

[1257] The server predicts future workload.

[1258] The server collects historical business data from the database and uses it to build a machine learning model (e.g., a regression analysis model). Next, it uses this model to predict the workload for the next few months. For example, it might predict 1200 inquiries next month and 1100 inquiries the month after. This prediction is also stored as internal data.

[1259] Step 8:

[1260] The server displays the calculation results to the user.

[1261] The server generates a report summarizing the results of the deviation rate calculation, the results of identifying the cause of the deviation, and the results of future workload forecasts. This report is displayed on the user's dashboard in real time. Based on this information, users can improve the efficiency of their work and allocate resources appropriately.

[1262] These steps allow users to understand the discrepancy between month-end forecasts and month-end actuals, identify the causes to improve operational efficiency, and allocate resources appropriately based on future workload forecasts.

[1263] (Example 1)

[1264] 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".

[1265] Conventional workload forecasting systems lack sufficient functionality to automatically calculate and analyze discrepancies between forecasts and actual results, making it difficult to identify the causes and improve the accuracy of future workload forecasts. In addition, the lack of an interface that allows users to easily input work data and check the results in real time is also a problem. While this is expected to improve operational efficiency, in reality, it requires a lot of manual work, which is burdensome.

[1266] 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.

[1267] In this invention, the server includes means for the user to input predicted workload data, means for the user to input actual workload data, means for the server device to receive the input data, validate the data format and store it, means for calculating the deviation rate based on the stored predicted and actual data, means for analyzing the cause of the deviation and extracting specific patterns, means for constructing a machine learning model to predict future workload based on past work data and making predictions, and means for displaying the calculation results and analysis results to the user in real time. As a result, the user can immediately check the difference between the predicted and actual workload data they have entered, quickly identify the cause of the deviation, and predict future workload with high accuracy. Consequently, it is possible to adjust operations and optimize personnel allocation, significantly improving overall operational efficiency.

[1268] "The means by which users input workload forecast data" refers to the interface that allows users to input workload forecast data into the system. This interface is designed to allow users to easily input data.

[1269] "The means by which users input actual workload data" refers to the interface that allows users to input data on their actual workload into the system. This is also designed to allow users to input data easily.

[1270] "A means of receiving data via a server device, validating the data format, and storing it" refers to the function in which a server receives data sent from a user, verifies whether the data format is correct, and then stores it in a database.

[1271] "Means for calculating the deviation rate based on stored forecast and actual data" refers to a function that calculates the deviation rate using the forecast and actual workload data stored on the server. The deviation rate is a value that expresses the difference between the forecast and the actual results.

[1272] "Means for analyzing the cause of discrepancies and extracting specific patterns" refers to a function where the server analyzes stored data to identify the cause of the discrepancy and extracts patterns based on specific dates, times, or categories.

[1273] "A means of building a machine learning model to predict future workload based on past business data" refers to a function where the server analyzes past business data to build a machine learning model and uses that model to predict future workload.

[1274] "A means of displaying calculation and analysis results to the user in real time" refers to a function that displays the calculated deviation rate, analysis results, and predicted future workload on the user's dashboard in real time.

[1275] This invention is a system for predicting workload, identifying discrepancies between actual and projected workload, analyzing the causes of these discrepancies, and predicting future workload. A specific embodiment of this system is described below.

[1276] The user first inputs predicted and actual workload data. The input interface is provided via a web browser, with a simple form for easy data entry. For example, the user might input "Predicted workload for this month: 1000 items" and "Actual workload at the end of the month: 1200 items." This data is then sent to the server in JSON format.

[1277] The server is implemented using Node.js and receives HTTP requests using the Express framework. It receives the sent JSON data and validates its contents. After successful validation, the data is stored in MongoDB. MongoDB is connected to the server via Mongoose, and predicted workload data and actual workload data are stored in separate collections.

[1278] Based on the stored data, the server calculates the deviation rate. The formula used for the calculation is as follows: Deviation rate = (Actual workload - Forecasted workload) / Forecasted workload 100. For example, if the forecast is 1000 and the actual workload is 1200, the deviation rate will be calculated as 20%. This calculation result is temporarily stored in memory.

[1279] Next, the server analyzes the data to identify the cause of the discrepancy. It runs aggregate queries to find patterns based on specific days or categories, and if, for example, 500 inquiries were concentrated on a particular day, it analyzes the details to identify the cause.

[1280] The server collects business data from the past six months and builds a predictive model using a Python machine learning library (e.g., Scikit-learn). Using the trained model, it predicts future business volume. The prediction results are output in the format of "1200 inquiries are predicted for next month, and 1100 inquiries for the month after."

[1281] The calculation results, analysis results, and prediction results are compiled into a report. The server generates this report in HTML or PDF format and displays it in real time on the user dashboard. Visualization tools such as Grafana are used on the dashboard, and the data is updated in real time. Based on this, users can adjust their work and optimize staffing.

[1282] For example, if a user inputs, "This month's projected workload is 1000 inquiries. The actual workload was 1200. Based on this, calculate the discrepancy rate and identify the cause. Then, predict the workload for next month and the month after," the server will save this data, identify a "20% discrepancy rate," and determine that 500 inquiries were concentrated on a specific day. Subsequently, the server will display to the user in real time the predicted results: 1200 inquiries for the next month and 1100 inquiries for the month after. This allows the user to understand future workloads and make appropriate resource allocations and personnel assignments.

[1283] This invention significantly improves operational efficiency and minimizes the occurrence of discrepancies.

[1284] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1285] Step 1:

[1286] Users input workload forecast data.

[1287] Users access the system and input workload forecast data through the interface. The input data is sent to the server in JSON format. For example, inputting "This month's forecast workload is 1000 items." Input (workload forecast data) → Output (data in JSON format)

[1288] Step 2:

[1289] The server receives the prediction data and performs validation.

[1290] The server is implemented using Node.js and receives HTTP requests using the Express framework. It validates the structure and content of the received JSON data to ensure it is in the correct format. Input (JSON-formatted workload forecast data) → Output (Validation result: Success / Failure)

[1291] Step 3:

[1292] The server stores the prediction data.

[1293] If validation is successful, the server connects to MongoDB via Mongoose and saves the predicted data. When saving, it saves the data to a collection of predicted workload data within the database. Input (validated workload prediction data) → Output (save complete message)

[1294] Step 4:

[1295] Users input actual workload data.

[1296] Users input their actual workload data for the current month through a similar interface. For example, they might input "This month's actual workload is 1200 items." Input (actual workload data) → Output (data in JSON format)

[1297] Step 5:

[1298] The server receives the performance data and performs validation.

[1299] The server receives an HTTP request and validates the structure and content of the received actual workload data. Input (actual workload data in JSON format) → Output (validation result: success / failure)

[1300] Step 6:

[1301] The server saves performance data.

[1302] If validation is successful, the server saves the actual workload data to the MongoDB collection of actual workload data. Input (validated actual workload data) → Output (save complete message)

[1303] Step 7:

[1304] The server calculates the deviation rate.

[1305] The server calculates the deviation rate based on the stored predicted workload data and actual workload data. The formula is as follows: Deviation Rate = (Actual Workload - Predicted Workload) / Predicted Workload 100. Input (Predicted Workload Data, Actual Workload Data) → Output (Deviation Rate)

[1306] Step 8:

[1307] The server analyzes the cause of the discrepancy.

[1308] The server analyzes stored business data to identify the cause of the discrepancy. For example, it uses the Parse function to find patterns based on specific days or categories. Input (business data) → Output (analysis results regarding the cause of the discrepancy)

[1309] Step 9:

[1310] The server predicts future workload.

[1311] The server collects historical business data and builds a predictive model using the Python machine learning library (Scikit-learn). Using the trained model, it predicts the workload for the following two months. Input (historical business data) → Output (future workload prediction)

[1312] Step 10:

[1313] The server compiles the results and generates a report.

[1314] The server generates a report summarizing the calculation results of the deviation rate, the results of identifying the cause of the deviation, and the forecast of future workload. This report is output in HTML or PDF format. Input (calculation results, analysis results, forecast results) → Output (report)

[1315] Step 11:

[1316] The device displays the report.

[1317] The user's device displays reports sent from the server on a dashboard. Visualization tools such as Grafana are used on the dashboard, and data is updated in real time. Input (Report) → Output (Display on Dashboard)

[1318] (Application Example 1)

[1319] 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".

[1320] Traditional logistics centers have struggled to efficiently analyze discrepancies between projected and actual workload forecasts, making it difficult to optimize resource allocation and staffing. Leaving this problem unaddressed leads to decreased operational efficiency, increased costs, and negatively impacts service quality.

[1321] 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.

[1322] In this invention, the server includes means for the user to input predicted workload data, means for the user to input actual workload data, server means for storing the input data, server means for calculating the deviation rate based on the stored predicted and actual data, server means for analyzing the causes of the deviation and extracting specific topics, server means for predicting future workload based on past business data, means for displaying the calculation results and analysis results to the user, means for predicting future workload with high accuracy using a machine learning model, and means for optimizing the allocation of business resources within the logistics center. This enables accurate prediction of workload, efficient deviation analysis, and appropriate resource allocation.

[1323] A "user" is someone who uses the system to input predicted workload data and actual workload data.

[1324] "Predicted workload data" refers to data entered by users at the beginning of the month or other times when they anticipate their workload.

[1325] "Actual workload data" refers to the actual workload data entered by users at the end of each month.

[1326] A "server" is a device or system that stores predicted and actual workload data, calculates deviation rates, analyzes causes, and predicts future workload.

[1327] "Deviation rate" is an indicator that expresses the difference between predicted workload and actual workload as a percentage.

[1328] "Cause of discrepancy" refers to the reason for the difference between the predicted workload and the actual workload.

[1329] "Specific topics" refer to areas of interest or themes that have been identified in order to pinpoint the causes of the discrepancy.

[1330] "Past business data" refers to previously recorded predicted workload data and actual workload data.

[1331] A "machine learning model" is an algorithm used to predict future workloads based on past data.

[1332] "Resource allocation" refers to the appropriate placement of personnel and equipment within a logistics center.

[1333] A system implementing this invention specifically includes an application for predicting workload and managing efficiency in a logistics center. This application allows the user to input operational data, which is then processed, analyzed, and predicted by a server, with the results displayed to the user in real time.

[1334] Users can input predicted and actual workload data using applications installed on smartphones, smart glasses, head-mounted displays, or robots. For example, they might input "1000" for the predicted workload for the month and "1200" for the actual workload at the end of the month.

[1335] The server receives the data, validates its format, and stores it in the database. Based on the stored predicted and actual workload data, the server calculates the deviation rate. For example, if the predicted workload is 1000 and the actual workload is 1200, the deviation rate is 20%. This calculated deviation rate is used to help users easily understand performance over a specific period.

[1336] Furthermore, the server analyzes stored business data to identify the cause of the discrepancy. For example, it might identify that the workload was concentrated on a particular day or in a particular category. This allows the server to report the specific cause of the discrepancy to the user.

[1337] The server also builds machine learning models based on past business data to predict future workloads. These models are trained using, for example, data on predicted and actual workloads over the past six months. This allows for highly accurate predictions of workloads for the following month and the month after. For example, the output might state, "We predict 1200 inquiries next month and 1100 inquiries the month after."

[1338] Calculation and analysis results are displayed in real time on the user's dashboard. Users can use this information to adjust operations and optimize staffing. This dashboard can also be viewed at any time by field workers using smart glasses or head-mounted displays.

[1339] Implementing this system will improve the accuracy of business forecasts, optimize resource allocation, and increase the operational efficiency of the logistics center. Furthermore, the calculation results will be provided to the user as specific prompt messages. For example, the following prompt messages may be generated:

[1340] "Our projected workload for December was 1,000 cases, but the actual volume was 1,500. Please tell us the discrepancy rate and the reasons for it. Also, please provide a workload forecast for next month."

[1341] In this way, users can utilize the system to achieve efficient business operations.

[1342] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1343] Step 1:

[1344] The user enters predicted workload data on a terminal. The entered data is sent to the server as predicted workload data. As an example, the user might enter "This month's predicted workload is 1000 items."

[1345] Step 2:

[1346] Users input actual workload data on their terminals. This data is entered at the end of each month and sent to the server. For example, a user might enter, "This month's actual workload is 1200 items."

[1347] Step 3:

[1348] The server receives predicted and actual workload data and validates its format. After verifying that the data is in a valid format, it is saved to the database.

[1349] Step 4:

[1350] The server calculates the deviation rate based on the stored predicted and actual data. Specifically, it performs the following calculations:

[1351] The deviation rate is calculated as follows: Deviation rate = (Actual workload - Forecasted workload) / Forecasted workload 100. For example, if the forecast is 1000 and the actual workload is 1200, the deviation rate is 20%. The calculation result is output as the deviation rate and stored in the database.

[1352] Step 5:

[1353] The server analyzes stored business data to identify the cause of the discrepancy. For example, it finds patterns based on the date, time, and category of inquiries, identifying that inquiries were concentrated on specific days or in specific categories. Based on these analysis results, it outputs the cause of the discrepancy.

[1354] Step 6:

[1355] The server collects historical business data and uses it to build a machine learning model. The model is trained using data on predicted and actual workloads over the past six months. This allows for highly accurate predictions of future workloads. The output is a predicted workload, such as "1200 cases next month, 1100 cases the month after."

[1356] Step 7:

[1357] The server generates a report summarizing the calculation and analysis results, which is then displayed in real time on the user's dashboard. This dashboard is designed to be accessible to field workers using smart glasses or head-mounted displays. Users can then use this information to adjust operations and optimize staffing.

[1358] Step 8:

[1359] The server generates prompt messages based on user input. For example, it might create a specific prompt message such as, "The predicted workload for December was 1000, but the actual workload was 1500. Please tell me the discrepancy rate and the reason. Also, please provide a workload forecast for next month." Based on this, the user can take actions to achieve efficient business operations.

[1360] 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.

[1361] This system not only predicts workload, identifies discrepancies with actual results, analyzes causes, and forecasts future workload, but also achieves even more accurate analysis and prediction by combining it with an emotion engine that recognizes user emotions. The specific implementation details are described below.

[1362] 1. Users enter business data.

[1363] Users access the system and utilize an interface to input their projected workload at the beginning of each month. For example, they might input "1000 inquiries are expected" at the start of the month. At the end of the month, they input actual data through a similar interface. For example, they might input "1200 inquiries were the actual number" at the end of the month. This allows users to easily register both projections and actual figures.

[1364] 2. The server saves the data.

[1365] The predicted and actual workload data entered by the user is received by the server. The server verifies that the received data is in the correct format and saves it to the database. This saved data is then used as the basis for subsequent calculations and analyses.

[1366] 3. The server calculates the deviation rate.

[1367] The server calculates the deviation rate based on the stored predicted and actual data. For example, if the predicted workload is 1000 and the actual workload is 1200, the server performs the following calculation: Deviation rate = (Actual workload - Predicted workload) / Predicted workload 100. In this example, the deviation rate is 20%. This calculation result is stored as internal data.

[1368] 4. The server collects sentiment data.

[1369] The emotion engine recognizes the user's emotions when they use the system. For example, it analyzes the user's facial expressions and tone of voice when they input business data to collect emotional data such as "stress" and "satisfaction."

[1370] 5. The server identifies the cause of the discrepancy.

[1371] The server further analyzes stored operational data based on the collected emotional data. For example, if the emotional data indicates "stress," it examines detailed logs such as the inquiry status and error count at that time to identify the cause of the discrepancy. This analysis allows the server to consider the emotional factors behind concentrated inquiries on specific days or in specific categories.

[1372] 6. The server predicts future workload.

[1373] The server collects historical business data from the database and integrates it with the sentiment data collected by the sentiment engine to build a machine learning model (e.g., a regression analysis model). This model can accurately predict the workload for the next few months. This prediction result is also stored as internal data.

[1374] 7. The server displays the calculation results to the user.

[1375] The server generates a report summarizing the results of the deviation rate calculation, the results of identifying the cause of the deviation, and the results of future workload forecasts. This report is displayed on the user's dashboard in real time. Based on this information, users can improve the efficiency of their work and allocate resources appropriately.

[1376] Specific example

[1377] For example, if a user enters "1000 predicted workloads for this month" and "1200 actual workloads at the end of the month," the server saves this data and calculates that the "deviation rate is 20%." Further analysis identifies the cause of the deviation as "500 inquiries concentrated on a specific day" and that the user felt "stressed" on that day. Based on this, the server refers to past data to predict the workload for the following months and displays to the user "1200 inquiries are predicted for next month, and 1100 for the month after."

[1378] This allows users to understand their future workload while taking emotional data into account, enabling appropriate resource allocation and process improvements. Each of these methods significantly improves work efficiency and minimizes discrepancies. Utilizing emotional data allows for more flexible responses that take human factors into account.

[1379] The following describes the processing flow.

[1380] Step 1:

[1381] Users input workload forecast data.

[1382] Users log in to the system and enter their monthly workload forecast data into a dedicated input form. The input fields include the number of inquiries and other forecast parameters. After entering the data, they press the submit button to send it to the server.

[1383] Step 2:

[1384] The server stores the prediction data.

[1385] The server receives the prediction data submitted by the user and performs a format check (validation). If the data is correct, it executes an SQL command (e.g., INSERT INTO) to save the prediction data to the database. Once the saving is complete, it notifies the user that the data has been successfully saved.

[1386] Step 3:

[1387] Users enter performance data.

[1388] At the end of the month, users log back into the system and enter their actual workload data. The input fields include the actual number of inquiries and other performance parameters. After entering the data, they press the submit button again to send it to the server.

[1389] Step 4:

[1390] The server saves performance data.

[1391] The server receives the performance data submitted by the user and performs a format check (validation). If the data is correct, it executes an SQL command (e.g., INSERT INTO) to save the performance data to the database. Once the saving is complete, it notifies the user that the data has been saved successfully.

[1392] Step 5:

[1393] The server calculates the deviation rate.

[1394] The server retrieves forecast and actual data for the relevant month from the database. Next, it calculates the deviation rate based on this data. The formula is: Deviation Rate = (Actual Workload - Forecasted Workload) / Forecasted Workload 100. The calculation result is stored as internal data.

[1395] Step 6:

[1396] Recognize user emotions and collect data.

[1397] When a user uses the system, an emotion engine activates, analyzing the user's facial expressions and tone of voice. For example, while a user is operating an input form or entering business data, the system uses a camera and microphone to collect emotion data.

[1398] Step 7:

[1399] The server stores emotional data.

[1400] The collected sentiment data is sent to the server for formatting checks (validation). If the data is correct, an SQL command (e.g., INSERT INTO) is executed to save the sentiment data to the database. Once saved, the sentiment data is integrated with other business data.

[1401] Step 8:

[1402] The server analyzes and identifies the cause of the discrepancy based on emotional data.

[1403] The server analyzes the cause of the discrepancy based on stored emotional and operational data. For example, if it examines data from a specific day and finds that the user was experiencing "stress" on that day, it checks the detailed log data of inquiries that occurred on that day. This allows it to identify why the discrepancy occurred on that day, including the underlying emotional factors.

[1404] Step 9:

[1405] The server predicts future workload based on past data.

[1406] The server integrates historical business data and sentiment data from the database and uses this to build a machine learning model (e.g., a regression analysis model). This model allows for highly accurate predictions of workload for the next few months.

[1407] Step 10:

[1408] The server displays the calculation results and prediction results to the user.

[1409] The server generates a report summarizing the results of the deviation rate calculation, the results of identifying the cause of the deviation, and the results of future workload forecasts. This report is displayed on the user's dashboard in real time. Based on this information, users can improve the efficiency of their work and allocate resources appropriately.

[1410] Specific example

[1411] For example, if a user enters "1000 predicted workloads for this month" and "1200 actual workloads at the end of the month," the server saves this data and calculates that the "deviation rate is 20%." Furthermore, the system senses that the user is experiencing "stress" while entering the data and records this. Analysis identifies the cause of the deviation as "500 inquiries concentrated on a particular day" and that the user was experiencing "stress" on that day. Based on this, the system refers to past data to predict the workload for the following months and displays to the user that "1200 inquiries are predicted for next month, and 1100 for the month after."

[1412] By combining this with an emotion engine, it becomes possible to provide more flexible responses that take human factors into account, further improving work efficiency.

[1413] (Example 2)

[1414] 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".

[1415] Conventional workload forecasting systems have faced challenges in identifying the causes of discrepancies between predicted and actual workloads, as well as in the limited accuracy of future workload forecasts. This has resulted in limitations in improving operational efficiency and appropriate resource allocation. Furthermore, systems that do not consider human emotions make it difficult to comprehensively analyze the impact of actual work processes and users' psychological states.

[1416] 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.

[1417] In this invention, the server includes means for collecting emotional data when a user inputs data, server means for identifying the cause of discrepancies based on the collected emotional data, and server means for predicting future workload based on past work data. This makes it possible to more accurately identify the cause of discrepancies between predicted and actual workload and to predict future workload with high accuracy. Furthermore, by incorporating user emotional data into the analysis, it becomes possible to respond more flexibly, taking human factors into consideration, thereby improving work efficiency and achieving appropriate resource allocation.

[1418] A "user" is a person who uses the system to input workload data and performance data, and performs operations to obtain analysis results and prediction results.

[1419] "Predicted workload data" refers to data about the workload that users expect to occur during a specific period in the future.

[1420] "Actual workload data" refers to data on the actual workload generated by a user during a specific period.

[1421] A "server" is a computing system that receives, stores, and analyzes data entered by users, and provides calculation results, prediction results, and other information.

[1422] "Validation" is the process of verifying whether the format and content of the entered data are correct.

[1423] A "database" is an electronic data storage system for systematically organizing, storing, searching, and managing various types of data.

[1424] The "deviation rate" is the percentage that shows the difference between predicted workload data and actual workload data, and is calculated based on a formula.

[1425] "Emotional data" is data obtained by analyzing a user's emotions from their facial expressions, tone of voice, etc., and it indicates emotional states such as "stress" or "satisfaction."

[1426] A "machine learning model" is an algorithm or mathematical model used to learn from past data and predict future data.

[1427] "Causes of discrepancy" refers to the factors that cause the difference between predicted workload data and actual workload data.

[1428] A "report" is a document that summarizes calculation results, analysis results, and prediction results, and is an aggregation of analytical information provided to the user.

[1429] Modes for carrying out the invention

[1430] The system implementing this invention has a set of functions in which, as a primary means, the user inputs business data, and the server analyzes, stores, and predicts that data. Specifically, the hardware and software used in each step include the following:

[1431] User data entry method

[1432] Users access the system using a dedicated web browser or mobile application via an internet-connected device (e.g., PC, tablet, smartphone). Users log in to the system and input projected workload data at the beginning of the month and actual workload data at the end of the month. For example, they might input "Projected workload for this month: 1000 items" and then "Actual workload: 1200 items" at the end of the month.

[1433] Server-based data storage and validation

[1434] The entered data is sent to the server. The server validates the data format (e.g., confirms that the number of queries is an integer) and displays an error message to the user if there is any inappropriate data. Data in the correct format is stored in the database. This database uses a relational database management system such as SQL.

[1435] Calculation of deviation rate

[1436] The server calculates the deviation rate based on the stored predicted workload data and actual workload data. For example, if the predicted workload is 1000 and the actual workload is 1200, the server calculates the deviation rate as follows: "Deviation Rate = (Actual Workload - Predicted Workload) / Predicted Workload 100". In this example, the deviation rate is calculated to be 20%. The calculation result is stored in the database.

[1437] Collection of user sentiment data

[1438] As the user enters data, the system's built-in emotion engine activates and analyzes the user's facial expressions and voice tone through the webcam and microphone. The emotion engine generates emotional data such as "stress" and "satisfaction" from this input and sends and stores it on the server.

[1439] Identifying the cause of the discrepancy

[1440] The server analyzes stored business data based on the collected sentiment data. For example, if the sentiment data indicates "stress," it investigates the detailed logs for that period and identifies that inquiries concentrated on specific days or categories are causing the discrepancies. This allows for a more detailed analysis of factors hindering business efficiency.

[1441] Predicting future workload

[1442] The server uses historical business data and sentiment data to build a machine learning model (e.g., a regression analysis model) to predict future workload. This model is implemented using programming languages ​​such as Python or R. For example, it might produce results such as, "We predict 1200 inquiries next month and 1100 inquiries the month after."

[1443] Displaying Results

[1444] The server generates a report summarizing the calculated deviation rate, identified deviation causes, and future workload forecasts. This report is displayed on the user's dashboard in real time. Based on this information, users can take actions to improve work efficiency.

[1445] Specific example

[1446] For example, if a user enters "1000 predicted workloads for this month" and "1200 actual workloads at the end of the month," the server saves this data and calculates that the "deviation rate is 20%." Furthermore, it identifies that 500 inquiries were concentrated on a specific day and that the user felt "stressed" on that day. Based on this information, the server predicts the workload for the following months and displays to the user that "1200 inquiries are predicted for next month, and 1100 for the month after."

[1447] Example of a prompt

[1448] "Analyze the discrepancy rate and its causes when the projected workload for this month is 1000 items and the actual workload at the end of the month is 1200 items."

[1449] This allows users to understand their future workload while taking emotional data into account, enabling appropriate resource allocation and process improvements. Each of these methods significantly improves work efficiency and minimizes discrepancies. Utilizing emotional data allows for more flexible responses that take human factors into account.

[1450] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1451] Specific processing steps of the program for this system

[1452] Step 1: The user enters business data.

[1453] input:

[1454] Predicted workload data (e.g., "1000 inquiries are predicted")

[1455] Actual workload data (e.g., "Actual number of inquiries: 1200")

[1456] process:

[1457] Users log in to the system using a web browser or mobile app.

[1458] After logging in, the business data entry screen will be displayed.

[1459] At the beginning of the month, you will enter your projected workload into the input form, and at the end of the month, you will enter your actual workload.

[1460] Click the submit button on the form to send the data to the server.

[1461] output:

[1462] Business data (predicted workload data and actual workload data) is sent to the server.

[1463] Step 2: The server saves the data.

[1464] input:

[1465] Business data submitted by users

[1466] process:

[1467] The server validates the data received from the user. For example, it checks whether the number of queries is an integer.

[1468] If validation is successful, the data is saved to the database.

[1469] If validation fails, an error message is returned to the user.

[1470] output:

[1471] Business data stored in the database

[1472] Validation result (success / failure)

[1473] Success message or error message

[1474] Step 3: The server calculates the deviation rate.

[1475] input:

[1476] Predicted workload data and actual workload data stored in the database

[1477] process:

[1478] The server retrieves predicted and actual workload data from the database.

[1479] The deviation rate is calculated using the following formula: "Deviation Rate = (Actual Workload - Forecasted Workload) / Forecasted Workload 100".

[1480] Save the calculation results to the database.

[1481] output:

[1482] Deviation rate stored in the database

[1483] Step 4: The server collects sentiment data.

[1484] input:

[1485] Facial expressions and tone of voice (collected via webcam and microphone) when users input business data.

[1486] process:

[1487] The server activates an emotion engine and analyzes the user's facial expressions and voice in real time.

[1488] The emotion engine generates emotion data (e.g., "stress" or "satisfaction").

[1489] The generated emotion data is sent to the server and stored in the database.

[1490] output:

[1491] Emotional data stored in the database

[1492] Step 5: The server identifies the cause of the discrepancy.

[1493] input:

[1494] Saved emotional data

[1495] Predicted workload data, actual workload data, and deviation rate

[1496] process:

[1497] The server performs analysis based on stored business data and emotional data.

[1498] Extract detailed data on periods when emotional data indicates "stress."

[1499] We will investigate detailed logs of inquiries concentrated on specific days or time periods to identify the cause of the discrepancy.

[1500] output:

[1501] Identified causes of discrepancies

[1502] Step 6: The server predicts future workload.

[1503] input:

[1504] Past business data

[1505] Emotional data

[1506] process:

[1507] The server builds a machine learning model (e.g., a regression analysis model) based on historical data.

[1508] We will use the constructed model to predict future workload.

[1509] Save the prediction results to the database.

[1510] output:

[1511] Future workload forecast results stored in the database

[1512] Step 7: The server displays the calculation results to the user.

[1513] input:

[1514] deviation rate

[1515] Causes of discrepancy

[1516] Future workload forecast results

[1517] process:

[1518] The server integrates the deviation rate, the cause of the deviation, and the forecast results for future workload to create a report.

[1519] After the report is generated, it will be displayed in real time on the user's dashboard.

[1520] output:

[1521] Reports displayed on the user dashboard

[1522] This allows users to understand their future workload while taking emotional data into account, enabling appropriate resource allocation and process improvements. Each of these methods significantly improves work efficiency and minimizes discrepancies. Furthermore, utilizing emotional data allows for more flexible responses that take human factors into account.

[1523] (Application Example 2)

[1524] 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".

[1525] Logistics centers need a function to analyze the discrepancy between predicted and actual workloads and to predict future workloads with high accuracy. In particular, there is a need for more accurate predictions, early detection of problems, and efficient resource allocation by utilizing real-time sentiment data of managers. However, conventional systems do not include sentiment data in their analysis, which limits their ability to identify the causes of discrepancies and improve the accuracy of future workload predictions.

[1526] 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.

[1527] In this invention, the server includes means for the user to input predicted workload data, means for the user to input actual workload data, information processing means for storing the input data, information processing means for calculating a deviation rate based on the stored predicted and actual data, means for collecting user emotion data using an emotion recognition engine, information processing means for analyzing the causes of the deviation and extracting specific topics, information processing means for predicting future workload based on past work data, and means for analyzing emotion data and displaying it together with the deviation rate. This makes it possible to analyze the causes of workload deviations, including user emotion data, and improve the accuracy of future workload predictions.

[1528] "Predicted workload data" refers to data that shows the amount of work that users predict will be processed within a certain period.

[1529] "Actual workload data" refers to data that shows the actual amount of work processed within a certain period.

[1530] "Information processing device means" refers to a server or computer system that performs data storage, calculation, analysis, and display.

[1531] The "deviation rate" is a value that expresses the difference between the predicted workload and the actual workload as a percentage.

[1532] An "emotion recognition engine" is software or hardware used to analyze a user's emotions and collect emotional data.

[1533] "Emotional data" refers to data that expresses a user's emotional state using numerical values ​​or categories.

[1534] "Specific topics" refer to specific items or themes extracted from the analysis results of the causes of the discrepancies.

[1535] "Future workload forecasting" is a process of estimating future workloads based on past and present data.

[1536] A "generative AI model" is an artificial intelligence model used to extract features from accumulated data and predict future situations.

[1537] A "prompt" is an instruction or question that is input to a generative AI model.

[1538] As a specific embodiment of this invention, we will explain using a "smart logistics manager" that uses a head-mounted display (HMD) for a logistics center as an example.

[1539] 1. Input of predicted and actual workload.

[1540] The user wears an HMD (Head-Mounted Display) and inputs their projected workload at the beginning of the month. For example, they might input "Projected workload for this month: 10,000 units." Then, at the end of the month, they similarly input their actual workload. For example, they might input "Actual workload: 11,500 units." This allows the user to provide projected and actual workload data to the information processing device.

[1541] 2. Data storage and calculation of deviation rate

[1542] The server receives predicted and actual workload data entered by the user, validates the data format, and then stores it in the information processing device. Based on the stored data, it calculates the deviation rate between the predicted and actual data. For example, if the predicted volume is 10,000 and the actual volume is 11,500, the server calculates the deviation rate as 15% and stores it as internal data.

[1543] 3. Collection of emotional data

[1544] The emotion recognition engine integrated into the HMD analyzes the user's facial expressions and voice tone, collecting emotional data. For example, it quantifies and records the user's stress and satisfaction levels when entering work data. This emotional data is then stored in the information processing device.

[1545] 4. Identifying the causes of the discrepancy and predicting future workload.

[1546] The server further analyzes the stored business data based on the collected emotional data to identify the cause of the discrepancy. For example, it identifies days with a high amount of emotional data indicating stress and analyzes the inquiry status and error count for those days. Next, it integrates past business data and emotional data to build a generative AI model and predict future workload. The results of the future workload prediction are also stored as internal data.

[1547] 5. Creating and displaying reports to users

[1548] The server generates a report summarizing the results of the deviation rate calculation, the results of identifying the cause of the deviation, and the results of future workload forecasts. This report is displayed in real time on the user's HMD, and the user can use this information to make appropriate resource allocations and business improvements.

[1549] Hardware and software to be used

[1550] Hardware: Head-mounted display (e.g., general term)

[1551] Software: Emotion recognition engine, information processing unit, generative AI model

[1552] Specific example

[1553] For example, if an administrator wears an HMD and inputs "Predicted workload for this month is 10,000 units," and then at the end of the month inputs "Actual workload is 11,500 units," the server calculates a discrepancy of 15%. Furthermore, the emotion recognition engine analyzes the collected emotion data and identifies that 500 packages were shipped on a specific day and that the user was feeling stressed on that day. Based on this, the server uses a generative AI model to predict future workload and displays to the administrator that "12,000 packages are predicted for next month, and 11,000 packages for the month after."

[1554] Examples of prompts to input into a generative AI model:

[1555] The user wears an HMD and enters "Predicted workload for this month: 10,000 units." At the end of the month, enter the actual volume as "11,500 units." The system automatically calculates the deviation rate and performs a cause analysis for the specific day based on sentiment data.

[1556] The above describes the "mode for carrying out the invention." By using a head-mounted display, real-time input of work data and collection of emotion data become possible, enabling highly accurate workload prediction and efficient resource allocation.

[1557] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1558] Step 1: The user enters the predicted workload data.

[1559] ---

[1560] The user uses a head-mounted display (HMD) to input projected workload data at the beginning of the month. During this process, the user enters information such as "Projected workload for this month: 10,000 units" through the HMD's interface. This input data is then transmitted to an information processing unit.

[1561] Input: Forecasted workload data

[1562] Output: Predicted workload data transmitted to the information processing device.

[1563] Step 2: The user enters actual workload data.

[1564] ---

[1565] At the end of the month, users use a similar HMD to input actual workload data. They enter data such as "Actual workload: 11,500 units," and this data is also sent to the information processing device.

[1566] Input: Actual workload data

[1567] Output: Actual workload data transmitted to the information processing device.

[1568] Step 3: The server saves the data.

[1569] ---

[1570] The server receives predicted and actual workload data sent by the user, verifies that the data format is correct, and stores it in the database of the information processing device.

[1571] Input: Forecasted workload data, actual workload data

[1572] Output: Predicted workload data and actual workload data stored in the database.

[1573] Step 4: The server calculates the deviation rate.

[1574] ---

[1575] The server calculates the deviation rate based on the predicted and actual data stored in the database. For example, if the predicted number of tasks is 10,000 and the actual number is 11,500, the server performs the following calculation: (Actual workload - Predicted workload) / Predicted workload 100. In this example, the deviation rate is 15%. This calculation result is stored as internal data.

[1576] Input: Forecasted workload data, actual workload data

[1577] Output: Calculated deviation rate

[1578] Step 5: The server collects sentiment data.

[1579] ---

[1580] The server uses the emotion recognition engine built into the HMD to analyze the user's facial expressions and voice tone, and collects emotional data. For example, it quantifies and records the user's stress and satisfaction levels when entering work data. This emotional data is then stored on the information processing device.

[1581] Input: User's facial expressions and tone of voice

[1582] Output: Saved sentiment data

[1583] Step 6: The server identifies the cause of the discrepancy.

[1584] ---

[1585] The server analyzes stored business data based on collected emotional data to identify the cause of discrepancies. For example, if the emotional data indicates "stress," it examines the detailed logs at that time to analyze whether there were concentrated inquiries on a specific day or in a specific category.

[1586] Input: Emotional data, business data

[1587] Output: Identified causes of discrepancies

[1588] Step 7: The server predicts future workload.

[1589] ---

[1590] The server builds a generative AI model based on past business data and collected sentiment data to predict future workloads. For example, by applying past data and sentiment scores as input data to the model, it predicts that the workload for next month will be 12,000 and the workload for the month after that will be 11,000. This prediction result is also stored as internal data.

[1591] Input: Past business data, sentiment data

[1592] Output: Future workload forecast data

[1593] Step 8: The server displays the calculation results to the user.

[1594] ---

[1595] The server generates a report summarizing the results of the deviation rate calculation, the results of identifying the cause of the deviation, and the results of future workload forecasts. This report is displayed in real time on the user's HMD, and the user can use this information to make appropriate resource allocations and business improvements.

[1596] Input: Deviation rate calculation result, deviation cause identification result, future workload forecast result

[1597] Output: Report displayed on the HMD

[1598] The above is the flow of specific processing steps of the system based on the application example. Sorry, I'm not sure.

[1599] 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.

[1600] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An 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.

[1601] 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.

[1602] 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.

[1603] 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.

[1604] 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.

[1605] 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.

[1606] 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.

[1607] 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."

[1608] 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.

[1609] 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.

[1610] 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.

[1611] 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.

[1612] 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.

[1613] 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.

[1614] 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.

[1615] 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.

[1616] 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.

[1617] 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.

[1618] 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.

[1619] 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.

[1620] The following is further disclosed regarding the embodiments described above.

[1621] (Claim 1)

[1622] A means for users to input predicted workload data,

[1623] A means for users to input actual workload data,

[1624] A server means for storing the input data,

[1625] A server means that calculates the deviation rate based on stored prediction data and actual data,

[1626] A server means for analyzing the cause of the discrepancy and extracting specific topics,

[1627] A server-based method for predicting future workload based on past business data,

[1628] A means of displaying calculation results and analysis results to the user,

[1629] A system that includes this.

[1630] (Claim 2)

[1631] The system according to claim 1, comprising means for analyzing patterns that depend on specific dates and categories as causes of discrepancies.

[1632] (Claim 3)

[1633] The system according to claim 1, comprising means for predicting future workload by applying a machine learning model based on past data.

[1634] "Example 1"

[1635] (Claim 1)

[1636] A means for users to input workload forecast data,

[1637] A means for users to input actual workload data,

[1638] A means for receiving input data via a server device, validating the data format, and storing it,

[1639] A method for calculating the deviation rate based on stored prediction data and actual data,

[1640] A means to analyze the cause of the discrepancy and extract specific patterns,

[1641] We will build a machine learning model that predicts future workload based on past business data, and develop a means to make such predictions.

[1642] A means of displaying calculation results and analysis results to the user in real time,

[1643] A system that includes this.

[1644] (Claim 2)

[1645] The system according to claim 1, comprising means for analyzing patterns that depend on specific dates or categories as causes of discrepancies.

[1646] (Claim 3)

[1647] The system according to claim 1, comprising means for predicting future workload by applying a machine learning model based on past data.

[1648] "Application Example 1"

[1649] (Claim 1)

[1650] A means for users to input predicted workload data,

[1651] A means for users to input actual workload data,

[1652] A server means for storing the input data,

[1653] A server means that calculates the deviation rate based on stored prediction data and actual data,

[1654] A server means for analyzing the cause of the discrepancy and extracting specific topics,

[1655] A server-based method for predicting future workload based on past business data,

[1656] A means of displaying calculation results and analysis results to the user,

[1657] A method for accurately predicting future workload using machine learning models,

[1658] Means for optimizing the allocation of operational resources within a logistics center,

[1659] A system that includes this.

[1660] (Claim 2)

[1661] The system according to claim 1, comprising means for analyzing patterns that depend on specific dates and categories as causes of discrepancies.

[1662] (Claim 3)

[1663] The system according to claim 1, which includes means for applying a machine learning model based on past data to predict future workload and displaying it in real time on a dashboard.

[1664] "Example 2 of combining an emotion engine"

[1665] (Claim 1)

[1666] A means for users to input predicted workload data,

[1667] A means for users to input actual workload data,

[1668] A server means for storing the input data,

[1669] A server means that calculates the deviation rate based on stored prediction data and actual data,

[1670] A server means for analyzing the cause of the discrepancy and extracting specific topics,

[1671] A server-based method for predicting future workload based on past business data,

[1672] A means of collecting emotional data when users input data,

[1673] A server mechanism that identifies the cause of discrepancy based on collected emotional data,

[1674] A means of displaying calculation results and analysis results to the user,

[1675] A system that includes this.

[1676] (Claim 2)

[1677] The system according to claim 1, comprising means for analyzing patterns that depend on specific dates and categories as causes of discrepancies.

[1678] (Claim 3)

[1679] The system according to claim 1, comprising means for predicting future workload by applying a machine learning model based on past data.

[1680] "Application example 2 when combining with an emotional engine"

[1681] (Claim 1)

[1682] A means for users to input predicted workload data,

[1683] A means for users to input actual workload data,

[1684] Information processing device means for storing input data,

[1685] An information processing device means that calculates the deviation rate based on stored prediction data and actual data,

[1686] An information processing device means for analyzing the cause of the discrepancy and extracting specific topics,

[1687] An information processing device that predicts future workload based on past business data,

[1688] A means of collecting user emotion data using an emotion recognition engine,

[1689] A means of analyzing emotional data and displaying it along with the deviation rate,

[1690] A system that includes this.

[1691] (Claim 2)

[1692] The system according to claim 1, comprising means for analyzing patterns that depend on specific dates and categories as causes of discrepancies.

[1693] (Claim 3)

[1694] The system according to claim 1, comprising means for predicting future workload by applying a generated AI model based on past data. [Explanation of symbols]

[1695] 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 users to input predicted workload data, A means for users to input actual workload data, A server means for storing the input data, A server means that calculates the deviation rate based on stored prediction data and actual data, A server means for analyzing the cause of the discrepancy and extracting specific topics, A server-based method for predicting future workload based on past business data, A means of displaying calculation results and analysis results to the user, A system that includes this.

2. The system according to claim 1, comprising means for analyzing patterns that depend on specific dates and categories as causes of discrepancies.

3. The system according to claim 1, comprising means for predicting future workload by applying a machine learning model based on past data.

Images