system

Abstract

Provide a system. 【Solution means】 Means for automatically collecting business data and performing preprocessing; Means for constructing and training a prediction model for business processing based on the preprocessed data; Means for predicting future business processing load using the prediction model; Means for generating a business schedule based on the prediction result; Means for optimally allocating resources based on the business schedule; Means for notifying the user of the generated schedule and resource allocation; Means for monitoring business progress in real time and proposing adjustments as necessary; A system including the above.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In formulating business plans, there are problems such as prediction uncertainty, human error, complexity of plan changes, and shortages or surpluses of resources, which are factors causing a decline in business efficiency and waste of resources. Also, it is difficult to grasp the real-time progress of business operations, and there is a problem that efficient resource allocation based on the plan cannot be achieved. As a result, it becomes difficult for enterprises to perform optimal business operations and maintain compliance, and the productivity of the entire organization decreases.

Means for Solving the Problems

[0005] This invention provides a system equipped with a function to automatically collect and analyze business performance data and predict future workloads. Using the resulting predicted data, it enables the creation of an optimal work schedule and efficient allocation of various resources. Furthermore, it allows for real-time monitoring of work progress and issues alerts if there is a gap between predictions and actual progress, enabling rapid response. In this way, it achieves flexible adjustments during planning and operation, improving overall efficiency and accuracy.

[0006] "Business data" refers to a collection of data that records information about business activities and processes, including date and time, processing volume, and resources used.

[0007] "Data preprocessing" refers to the process of preparing data to be suitable for analysis and model building, and includes techniques such as imputing missing values, correcting outliers, and normalizing data.

[0008] A "predictive model" is a logical framework built using mathematical or machine learning algorithms to estimate future events based on past data.

[0009] "Workload" refers to the amount of human and material resources required to perform a task, and it fluctuates from hour to hour.

[0010] A "work schedule" is a timeline that places a plan for business processes on specific dates and times, and is designed to distribute the workload and improve efficiency.

[0011] "Resource allocation" refers to the act of optimally distributing the resources required to carry out business operations and adjusting the amount needed for each task.

[0012] "Real-time monitoring" refers to the act of observation to immediately grasp the current status of business progress, and is a process that utilizes sensors and data analysis for the purpose of early detection of delays and failures.

[0013] An "alert" is a notification issued when there is a discrepancy between predictions and actual results, and is used as a means to encourage early detection and response to problems. [Brief explanation of the drawing]

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

Embodiments for Carrying Out the Invention

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

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

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

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

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

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

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

[0022] [First Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0035] The business efficiency system of this invention is based on a software program that enables the automatic collection, analysis, prediction, scheduling, and resource allocation of business data.

[0036] The server first accesses the company's business database to collect data on past business process counts and resource usage. APIs and ETL (Extract, Transform, Load) processes are used for this data collection.

[0037] Subsequently, the server preprocesses the acquired data, filling in missing values ​​and correcting outliers. Data normalization and format conversion are also performed at this stage. Based on this prepared data, the server builds a predictive model using machine learning algorithms. This model learns from past trends and predicts future workloads with high accuracy.

[0038] Based on the predicted workload, the server automatically generates a work schedule. This schedule is designed to avoid peak workloads, distribute the load evenly, and allocate resources effectively. In addition, resource allocation is performed simultaneously, specifically determining the number of personnel and equipment required.

[0039] The user will be notified of the created schedule and resource allocation details via their device. The user can review these proposals and make modifications as needed.

[0040] Furthermore, during actual work, the server monitors the progress in real time. This monitoring triggers alerts to the user via their terminal if there is a discrepancy between predictions and actual results. This allows users to quickly fine-tune their work schedules.

[0041] As a concrete example, one manufacturing company used this system to create production plans, preventing production disruptions during peak seasons. The server performed demand forecasts, and terminals presented optimal production plans to administrators, resulting in efficient personnel allocation and a reduction in excess inventory. In this way, the company's overall operational efficiency improved, enabling it to maintain its competitiveness.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The server connects to the company's business database and automatically extracts data on past business transaction counts, hourly load, and resource usage. Database queries and APIs are used for this extraction.

[0045] Step 2:

[0046] The server performs preprocessing on the acquired data. Preprocessing includes imputing missing values, removing outliers, normalizing the data, and standardizing date and time formats.

[0047] Step 3:

[0048] Based on the data stored on the server, machine learning algorithms are applied to build predictive models for business processes. Algorithm selection utilizes technologies aligned with past trends (e.g., ARIMA, LSTM, etc.).

[0049] Step 4:

[0050] The server uses a predictive model to forecast future workload. This forecast evaluates the load at specific time intervals and identifies peak times for business operations.

[0051] Step 5:

[0052] The server generates an optimal work schedule based on the prediction results. The schedule is designed to equalize the workload and ensure efficient use of resources.

[0053] Step 6:

[0054] The server plans resource allocation based on predictions and determines the number of personnel and materials needed. This ensures that no resources are in excess or insufficient.

[0055] Step 7:

[0056] The terminal notifies the user of the generated work schedule and resource allocation plan. The notification includes specific work plans and the underlying forecast information.

[0057] Step 8:

[0058] The server monitors the actual progress of the work in real time. It acquires necessary data from sensors and management systems as the work progresses.

[0059] Step 9:

[0060] If the server detects a discrepancy between predictions and actual results, it will send an alert to the user via their terminal. This alert is intended to prompt a quick response.

[0061] Step 10:

[0062] Review the schedules and resource allocations received by the user and make adjustments as needed. By incorporating the user's suggested revisions, the work plan can be flexibly adjusted.

[0063] (Example 1)

[0064] 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."

[0065] Amidst increasing operational complexity and market fluctuations, efficient operational management and resource allocation are becoming difficult, necessitating the provision of comprehensive systems to address these challenges. Specifically, there is a need for means to enable rapid response through the collection, forecasting, scheduling, and real-time feedback of operational data.

[0066] 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.

[0067] In this invention, the server includes means for automatically acquiring business-related information and preparing data, means for constructing a predictive structure for business processing based on the pre-processed information and turning it into knowledge, and means for predicting future workload using the predictive structure. This enables efficient and effective business planning, optimal resource allocation, and real-time adjustment of business progress.

[0068] "Business-related information" refers to data related to the operations of a company or organization, including information such as the number of transactions processed and resource usage.

[0069] "Data preparation" is the process of imputing missing values ​​and correcting outliers in collected data, and it also includes normalization and format conversion.

[0070] A "predictive structure" is a model built to learn rules and patterns derived from past data, and is used to predict future workloads.

[0071] A "work plan" is a schedule generated based on predicted workload, with the aim of avoiding peak workloads and distributing the load evenly.

[0072] "Resource allocation" refers to the process of appropriately allocating necessary personnel and equipment based on a work plan, and is essential for achieving efficient work execution.

[0073] "Real-time feedback" refers to a system that monitors the progress of work in real time, issues immediate alerts as needed, and prompts adjustments.

[0074] The business efficiency system of this invention is designed to automatically collect business-related information and optimize business plans based on that information. The following is a description of a specific embodiment.

[0075] This system uses a server as the core of its data processing. The server automatically retrieves business-related information from the company's database using APIs and ETL (Extract, Transform, Load) processes. This process utilizes data processing libraries such as Python's pandas and NumPy. The collected data undergoes preprocessing, including the imputation of missing values ​​and the correction of outliers.

[0076] Based on preprocessed data, the server constructs a prediction structure using machine learning libraries such as scikit-learn and TENSORFLOW®. This enables the server to accurately predict future workloads and generate effective work plans. Flexible algorithms applicable to production management and personnel scheduling are used for developing work plans.

[0077] Along with the generated work plan, the server optimizes resource allocation and determines the placement of necessary personnel and equipment. This information is provided to the user via a terminal, and the user can view details through a dashboard or alert email. The user can also provide feedback on the presented plan and make modifications as needed.

[0078] During the work process, the server tracks progress in real time and, if it detects a discrepancy between the planned and actual progress, it quickly sends an alert to the user via their terminal. This feedback allows the user to immediately adjust their work plan.

[0079] As a concrete example, in the manufacturing industry, this system has been used to forecast demand and develop production plans, enabling efficient resource allocation. An example of a prompt message would be, "Please propose a method for optimizing demand forecasting and resource allocation in the manufacturing industry." This allows companies to improve operational efficiency and maintain their competitiveness.

[0080] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0081] Step 1:

[0082] The server connects to the company's database and automatically retrieves business-related information using APIs and ETL processes. The data collected includes historical transaction counts, resource usage, and sales data. Input is raw data retrieved from various databases, and output is a raw dataset for data preprocessing. This process is scheduled to run periodically.

[0083] Step 2:

[0084] The server performs preprocessing on the collected raw dataset. This preprocessing uses the Python pandas library to impute missing values ​​and correct outliers. Data normalization and formatting are also performed, organizing the data into a user-friendly format. Specifically, numerical data is scaled and categorical data is encoded. The input is the raw dataset obtained in step 1, and the output is the prepared dataset.

[0085] Step 3:

[0086] Based on a pre-configured dataset, a prediction structure is built using machine learning libraries such as scikit-learn and TensorFlow. This prediction structure is a model designed to predict future workload by learning past trends. The specific operation involves using the output dataset from step 2 as training data and applying algorithms to train the model. The input is a pre-processed dataset, and the output is the trained prediction model.

[0087] Step 4:

[0088] The server uses a predictive model to generate an optimal work plan to address future workloads. This plan aims to evenly distribute peak loads. Specifically, resource allocation is optimized through simulations using a generative AI model. The inputs are the predictive model and real-time status data, and the outputs are the work schedule and resource allocation plan.

[0089] Step 5:

[0090] The terminal receives output information from the server and notifies the user. Notification methods include visualization on a dashboard and sending alert emails. The user can review the provided information and provide feedback. Specifically, this involves accessing a user interface for reviewing, modifying, and approving plans. Inputs are work schedules and resource allocation plans, while output is user feedback.

[0091] Step 6:

[0092] The server tracks the progress of tasks in real time and issues alerts if predictions and actual results deviate. This allows users to quickly adjust their work plans. Specific operations include data collection from IoT devices and sensors, comparative analysis, and alert notifications. Input is real-time data, and output is updated work plans or alert notifications.

[0093] (Application Example 1)

[0094] 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."

[0095] To improve operational efficiency in logistics centers, it is necessary to collect diverse data and formulate appropriate work schedules and resource allocations. However, conventional systems perform these tasks individually, resulting in time-consuming data integration and analysis, making rapid decision-making difficult. To solve this problem, it is necessary to monitor the progress of operations in real time and make adjustments as needed.

[0096] 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.

[0097] In this invention, the server includes a device that automatically collects and preprocesses business information, a device that develops and trains a predictive model for business processing using the preprocessed information, and a device that monitors business progress in real time and proposes adjustments as needed. This enables the rapid and accurate formulation of business plans and the optimal allocation of resources.

[0098] "Operational information" refers to all data related to the operation of the logistics center, including work progress, resource usage, and past work history.

[0099] "Preprocessing" is the process of converting collected raw data into an analyzable format, including imputing missing values ​​and correcting outliers.

[0100] A "predictive model" refers to a mathematical or statistical model used to predict future workloads based on past business data.

[0101] A "work plan" is a detailed schedule and resource allocation plan for efficiently carrying out future business activities at a logistics center.

[0102] "Resources" refers to the personnel, equipment, and other necessary elements required to carry out the operations of a logistics center.

[0103] "Monitoring" refers to the process of tracking the progress of operations in real time and immediately detecting any anomalies.

[0104] "Adjustment" refers to actions taken to maximize operational efficiency by making necessary changes to work plans and resource allocations.

[0105] "Device" refers to the hardware and software components necessary to perform each of the above functions.

[0106] The system implementing this invention aims to improve the operational efficiency of a logistics center, with a server, terminals, and users playing key roles. The server automatically collects operational information and preprocesses the data using Python and related libraries. Specifically, it uses Pandas to impute missing values ​​and correct outliers. The preprocessed data is fed into a predictive model using TensorFlow to predict future workload.

[0107] The server generates an optimal work plan based on the predicted workload. This plan is created using optimization algorithms such as linear programming. The generated work plan is then pushed to the device via an application built with React Native and communicated to the user.

[0108] Users can review the plan presented through their terminal and make adjustments as needed. During actual work, the server uses AWS® to monitor operations in real time and issues warnings if the predicted results deviate from actual results. This allows users to respond quickly and fine-tune their operations.

[0109] As a concrete example, to prevent congestion at logistics centers during the year-end period when consumption increases, it becomes possible to arrange additional personnel in advance. An example of a prompt message to the generated AI model is, "Based on past operational data of the logistics center, predict the workload for the next three months and propose the optimal staffing arrangement."

[0110] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0111] Step 1:

[0112] The server automatically collects business information from various data sources using APIs. It receives data from various databases and sensors as input, and outputs an integrated dataset. This integrated data forms the basis for subsequent analysis.

[0113] Step 2:

[0114] The server performs preprocessing on the collected dataset. Specifically, it uses the Pandas library to impute missing values ​​with the mean and correct outliers. It accepts an integrated raw dataset as input and outputs a clean, analyzable dataset.

[0115] Step 3:

[0116] The server uses a generative AI model based on TensorFlow to make predictions, utilizing pre-processed data to train the predictive model. A clean dataset is fed into the model as input, and the output predicts future workload. This allows for the prediction of business needs and peak times.

[0117] Step 4:

[0118] The server uses linear programming to generate an optimal workload plan based on the predicted workload. It receives the prediction results as input and creates a detailed schedule and resource allocation plan as output. This plan enables the optimal allocation of resources.

[0119] Step 5:

[0120] The device notifies the user of the work plan generated through an application built with React Native. It receives the work plan from the server as input and communicates the information to the user via push notifications as output. The user then uses this information to respond to the work situation.

[0121] Step 6:

[0122] Users review the plan presented via their terminal and make adjustments as needed. They review the work plan generated as input and make necessary changes or approvals as output. This allows for plan adjustments that are adapted to the actual situation on site.

[0123] Step 7:

[0124] The server uses AWS to monitor business progress in real time and issues warnings when discrepancies between actual results and forecasts are detected. It receives real-time data as input and notifies the user of warning alerts when discrepancies are detected as output. This allows users to take quick action.

[0125] 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.

[0126] This invention is a business efficiency system that takes into account the emotional state of the user. It not only collects and analyzes business data, but also provides a function to recognize the user's emotions in real time and adjust the business plan based on those emotions.

[0127] The server first connects to the company's business database and collects historical business processing data and resource usage. This data is then preprocessed to generate a standardized dataset. The data created here forms the basis for predictive models of business processes.

[0128] Next, the server uses machine learning algorithms to build a predictive model of business processes, thereby predicting future workloads. Based on these predictions, an optimal work schedule is generated, and resource allocation is planned to avoid peak workloads.

[0129] The emotion engine, a key feature of this invention, recognizes the user's emotional state in real time, and this emotional data is analyzed by a server. Based on the user's emotional data, the server evaluates the stress level and motivation level, and adjusts the workload and resource allocation as needed to reduce the user's workload and ensure appropriate resource allocation.

[0130] The generated work schedule and resource allocation are notified to the user via their terminal. The user can review this information and provide situation-appropriate feedback. The results of the emotion engine are also notified, allowing the user to understand their own emotional state.

[0131] Furthermore, by having the server monitor the progress of tasks in real time, if there is a discrepancy between predictions and actual results, a prompt alert is sent to the user via the terminal. Once the user approves, the server implements the proposed adjustments and immediately updates the task schedule and resource allocation.

[0132] As a concrete example, one customer support center implemented a system utilizing this emotion engine, which enabled them to regularly monitor the stress levels of their staff. When the emotion engine data indicated high stress levels, the server automatically took measures to reduce the workload, resulting in improved work efficiency while maintaining staff motivation. This allowed the company to simultaneously maintain service quality and improve employee satisfaction.

[0133] The following describes the processing flow.

[0134] Step 1:

[0135] The server connects to the business management system and automatically collects historical business processing data. This data includes the number of items processed, processing time, and resources used.

[0136] Step 2:

[0137] The server preprocesses the acquired data. This includes imputing missing values, detecting and correcting outliers, and normalizing the data.

[0138] Step 3:

[0139] The server uses pre-processed data to build predictive models for business processes using machine learning algorithms. Specifically, it performs trend analysis and learns seasonal patterns.

[0140] Step 4:

[0141] The server uses a predictive model to forecast future business processing loads. These forecasts include identifying daily or weekly load peaks.

[0142] Step 5:

[0143] The server generates an optimal work schedule based on the prediction results, planning for the equal use of resources during each work period.

[0144] Step 6:

[0145] The server plans resource allocation and optimally assigns the necessary personnel and equipment, thereby avoiding resource surpluses or shortages.

[0146] Step 7:

[0147] The terminal notifies the user of the generated work schedule and resource allocation. The notification includes a detailed schedule and forecast background.

[0148] Step 8:

[0149] The device detects the user's emotional state in real time via an emotion engine. The data is used to measure stress levels and motivation levels.

[0150] Step 9:

[0151] The server analyzes emotional data and readjusts workload if user stress levels are high. If necessary, it proposes a reallocation of personnel.

[0152] Step 10:

[0153] The server monitors the progress of operations in real time, and if there is a discrepancy between predictions and actual results, it sends an alert to the user via the terminal.

[0154] Step 11:

[0155] The user reviews the alert and approves any necessary adjustments to the work schedule or resource allocation. Based on the user's approval, the server automatically executes the adjustments.

[0156] (Example 2)

[0157] 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".

[0158] In today's work environment, predicting workload and allocating resources appropriately are difficult, hindering efficient operations. Furthermore, the lack of consideration for employees' emotional states leads to stress and decreased motivation, resulting in reduced work efficiency. Under these circumstances, there is a need to achieve both high work efficiency and employee satisfaction.

[0159] 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.

[0160] In this invention, the server includes means for automatically collecting and standardizing business data, means for building and training a predictive model of business processing based on the pre-processed data, and means for estimating future workload using the predictive model. This enables efficient business management and flexible business adjustments that take into account the emotional state of users.

[0161] "Business data" refers to information about the execution status of business processes and resource usage, and is used for business planning, analysis, and forecasting.

[0162] "Standardization" refers to the process of converting collected data into a unified format or standard, and is a technique used to maintain consistency in data analysis and model building.

[0163] A "predictive model" is a model that combines mathematical or computational methods to estimate future workload based on past data.

[0164] A "work plan" refers to an optimized schedule of tasks that takes into account the resources and time required to execute those tasks.

[0165] "Resource allocation" is the process of most effectively allocating available resources (such as personnel and equipment) to tasks with the aim of efficiently carrying out those tasks.

[0166] "Users" refers to individuals or organizations that operate the system, receive various information related to their work, and provide feedback.

[0167] "Emotional information" refers to data that indicates the user's psychological and physiological state, such as their stress level and motivation.

[0168] "Real-time monitoring" refers to the continuous tracking of business processes and user status in real time, providing information in real time.

[0169] A "warning" is a notification issued by the system when it detects an abnormal condition or a discrepancy between predictions and actual results, and is intended to prompt a quick response.

[0170] "Correction" refers to the act of improving and adjusting business plans and resource allocation when there is a discrepancy between predictions and the current situation.

[0171] This invention is a system that collects, analyzes, and predicts business data in order to improve operational efficiency. Each process is carried out through the collaboration of a server, terminals, and users.

[0172] First, the server connects to the company's database to collect data on business processes and resource usage. This operation utilizes techniques that access the database using SQL queries. The data is then aggregated on the server and cleansed and standardized using Python or other data processing languages. This data preparation creates the dataset that forms the basis of the predictive model.

[0173] Next, the server uses a machine learning platform (e.g., scikit-learn or TensorFlow) to build a predictive model for business processes. This model allows for the estimation of future workload and the planning of optimal resource allocation.

[0174] Furthermore, a crucial aspect of this system is the real-time recognition of the user's emotional state. Wearable devices and applications used by the user collect data such as heart rate, sweating, and facial expressions, and send it to a server. The server analyzes this data and quantifies the user's stress level and motivation.

[0175] The terminal is a device that provides users with notifications and alerts from the server. On the terminal, users can check their work schedule and proposed adjustments, and input feedback on the spot. Notifications are provided as text messages and pop-up alerts.

[0176] As a concrete example, one customer support center adjusts workloads based on the emotional state of its staff. For instance, if emotional analysis determines that a particular staff member is experiencing high stress levels, the server automatically takes measures to reduce their workload. This allows for flexible resource allocation through schedule adjustments, enabling both improved operational efficiency and increased employee satisfaction.

[0177] An example of a prompt is: "Consider the user's emotional state and suggest ways to adjust next week's work schedule and optimize resource allocation." The system will then generate an optimized solution and propose it to the user.

[0178] As described above, the present invention provides a mechanism for improving work efficiency and appropriately managing the emotional state of users, and is expected to be used in a variety of work environments.

[0179] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0180] Step 1:

[0181] The server connects to the business database. It retrieves historical business processing data and resource usage information from the database as input. The server then collects the data and performs cleansing and standardization processes. It converts the raw data received from the database into a consistent format and outputs it as a dataset ready for the predictive model. Specifically, this involves extracting necessary information using SQL queries.

[0182] Step 2:

[0183] The server uses machine learning libraries to build a predictive model of business processes based on a dataset. The server uses a prepared dataset as input. It applies machine learning algorithms (e.g., regression analysis, time series forecasting) to output a model that estimates future workload. This model establishes the foundation for developing business plans. A concrete example of this is the execution of a script using Python.

[0184] Step 3:

[0185] The server creates a work plan and resource allocation based on the output from a predictive model. Predicted workload data is used as input. The server generates a work schedule to reduce inefficient workload peaks and optimize resource allocation. This schedule is output in a way that supports the smooth execution of operations. Specifically, this involves the application of a scheduling algorithm.

[0186] Step 4:

[0187] Users record their emotional state using provided wearable devices and apps, and send this data to a server via their devices. Emotional data is input as heart rate and skin electrical responses. The server analyzes this data, evaluates stress levels, quantifies motivation, and outputs the results. Specific actions include data transmission and app operation.

[0188] Step 5:

[0189] The terminal notifies the user of the work schedule and sentiment analysis results received from the server. The input consists of analysis results and work plans from the server. The terminal provides this information to the user, allowing them to check the situation immediately. The notified information is output as a basis for user confirmation and feedback. Specific actions include displaying alerts and sending messages.

[0190] Step 6:

[0191] The server monitors the progress of tasks in real time and proposes adjustments via terminals as needed. It processes data on the progress of tasks as input. The server analyzes the difference between predictions and actual results from this input and outputs necessary alerts and adjustment proposals to the user. Specifically, it integrates with the monitoring system and performs data analysis.

[0192] Step 7:

[0193] The user approves or modifies the proposed adjustments via their terminal and provides feedback, which is then sent to the server. Receiving user instructions as input, the server modifies the work plan and resource allocation. This creates an optimal work environment that reflects the user's needs and outputs it as an actionable plan. Specifically, this involves filling out a feedback form.

[0194] (Application Example 2)

[0195] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0196] In modern households, an individual's emotional state significantly impacts the efficiency of daily life. However, a system that effectively manages this and optimizes household tasks and daily schedules still lacks a solution. Therefore, there is a need for flexible scheduling adjustments that take into account the well-being of all family members.

[0197] 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.

[0198] In this invention, the server includes means for automatically collecting and preprocessing business data, means for building and training a predictive model for business processing based on the preprocessed data, and means for adjusting household tasks and daily schedules based on an individual's emotional state. This enables flexible schedule adjustments that reflect the emotional state of family members.

[0199] "Business data" refers to a collection of information related to business activities, and is a general term for data including past business processing data and resource usage status.

[0200] "Preprocessing" refers to the process of performing necessary modifications on collected raw data, including tasks such as data standardization and noise reduction.

[0201] A "predictive model" is a mathematical model built using machine learning algorithms to derive new insights from data, and it estimates future trends in business processes.

[0202] A "work schedule" is a plan created based on the predicted workload, and it defines the time allocation necessary to optimally carry out work activities.

[0203] "Resource allocation" refers to the appropriate distribution of resources such as people, materials, money, and information in order to carry out tasks efficiently.

[0204] "Monitoring" refers to activities that involve monitoring the progress of work in real time and understanding the status of that progress.

[0205] "Adjustment" refers to proposing and implementing changes to planned schedules and resource allocations as necessary.

[0206] "Emotional state" refers to an individual's psychological state and is used to evaluate indicators such as stress levels and feelings of well-being.

[0207] "Household tasks" refer to everyday tasks performed at home, including activities related to daily life such as cleaning, cooking, and shopping.

[0208] To realize this invention, a system involving three main parties—a server, a terminal, and a user—is necessary. The server collects various data from within the home, preprocesses it, and then builds a predictive model using a machine learning algorithm. Specifically, the server integrates various business and emotional data from within the home and predicts future task loads based on this data.

[0209] The server uses emotion recognition APIs (such as EmotionAPI) to analyze the user's emotional state and processes the emotional data in real time. Based on this analysis, it adjusts the allocation of household task schedules. It also uses machine learning platforms such as TensorFlow to predict the behavioral patterns of the entire family and create an optimal daily schedule.

[0210] The device delivers various notifications to the user and provides suggested task schedules and emotional state feedback on the electronic screen. Based on this feedback, the user can understand their emotional state and request adjustments from the system as needed.

[0211] When performing various tasks within the home, users receive suggestions based on emotional data provided by the server, which helps them manage their family's daily life smoothly. For example, if a user is tired in the morning, the server might suggest, "You seem particularly tired today. How about preparing a hot coffee and a slightly larger, more nutritious breakfast?"

[0212] An example of a prompt message might be: "Based on the user's emotional data, suggest an optimal morning routine for when their stress level is high."

[0213] In this way, the present invention makes it possible to optimize the lives of individuals and families as a whole through the recognition of emotions within the home.

[0214] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0215] Step 1:

[0216] The server collects business and emotional data from various sensors and devices within the home. Inputs include emotional data acquired from cameras and microphones, and environmental data from temperature and humidity sensors. At this stage, the data is collected in raw format and stored in a database.

[0217] Step 2:

[0218] The server preprocesses the collected raw data, particularly by removing noise and standardizing it. The input is raw data, and the output is a clean, consistent dataset. This process includes imputing missing values ​​and removing outliers.

[0219] Step 3:

[0220] The server builds and trains a predictive model based on preprocessed data. Specifically, it uses a machine learning algorithm based on TensorFlow. The input is the preprocessed data, and the output is the predictive model. The model learns family emotional tendencies and patterns of daily tasks to predict future situations.

[0221] Step 4:

[0222] The server uses a built predictive model to forecast future household task loads. Inputs are the predictive model and current sentiment data; output is the future task load forecast. This provides information useful for improving the efficiency of daily life.

[0223] Step 5:

[0224] The server adjusts the household task schedule considering the user's emotional state and notifies the user of the suggestions via the terminal. Inputs are future task load predictions and emotional data, while output is the suggested schedule. In this step, the suggestions are generated by a generative AI model, and prompt statements are also referenced.

[0225] Step 6:

[0226] Users review the proposals from their devices and approve or modify the system's schedule by providing feedback. Here, the input is the proposed schedule, and the output is the user's feedback. Specifically, this involves confirmation and response on a smartphone or tablet.

[0227] Step 7:

[0228] The server receives user feedback and updates task schedules and resource allocations as needed. These updates are reflected in the system in real time, resulting in an optimized home task schedule as output.

[0229] 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.

[0230] 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.

[0231] 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.

[0232] [Second Embodiment]

[0233] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0234] 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.

[0235] 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).

[0236] 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.

[0237] 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.

[0238] 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).

[0239] 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.

[0240] 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.

[0241] 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.

[0242] 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.

[0243] 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.

[0244] 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".

[0245] The business efficiency system of this invention is based on a software program that enables the automatic collection, analysis, prediction, scheduling, and resource allocation of business data.

[0246] The server first accesses the company's business database to collect data on past business process counts and resource usage. APIs and ETL (Extract, Transform, Load) processes are used for this data collection.

[0247] Subsequently, the server preprocesses the acquired data, filling in missing values ​​and correcting outliers. Data normalization and format conversion are also performed at this stage. Based on this prepared data, the server builds a predictive model using machine learning algorithms. This model learns from past trends and predicts future workloads with high accuracy.

[0248] Based on the predicted workload, the server automatically generates a work schedule. This schedule is designed to avoid peak workloads, distribute the load evenly, and allocate resources effectively. In addition, resource allocation is performed simultaneously, specifically determining the number of personnel and equipment required.

[0249] The user will be notified of the created schedule and resource allocation details via their device. The user can review these proposals and make modifications as needed.

[0250] Furthermore, during actual work, the server monitors the progress in real time. This monitoring triggers alerts to the user via their terminal if there is a discrepancy between predictions and actual results. This allows users to quickly fine-tune their work schedules.

[0251] As a concrete example, one manufacturing company used this system to create production plans, preventing production disruptions during peak seasons. The server performed demand forecasts, and terminals presented optimal production plans to administrators, resulting in efficient personnel allocation and a reduction in excess inventory. In this way, the company's overall operational efficiency improved, enabling it to maintain its competitiveness.

[0252] The following describes the processing flow.

[0253] Step 1:

[0254] The server connects to the company's business database and automatically extracts data on past business transaction counts, hourly load, and resource usage. Database queries and APIs are used for this extraction.

[0255] Step 2:

[0256] The server performs preprocessing on the acquired data. Preprocessing includes imputing missing values, removing outliers, normalizing the data, and standardizing date and time formats.

[0257] Step 3:

[0258] Based on the data stored on the server, machine learning algorithms are applied to build predictive models for business processes. Algorithm selection utilizes technologies aligned with past trends (e.g., ARIMA, LSTM, etc.).

[0259] Step 4:

[0260] The server uses a predictive model to forecast future workload. This forecast evaluates the load at specific time intervals and identifies peak times for business operations.

[0261] Step 5:

[0262] The server generates an optimal work schedule based on the prediction results. The schedule is designed to equalize the workload and ensure efficient use of resources.

[0263] Step 6:

[0264] The server plans resource allocation based on predictions and determines the number of personnel and materials needed. This ensures that no resources are in excess or insufficient.

[0265] Step 7:

[0266] The terminal notifies the user of the generated work schedule and resource allocation plan. The notification includes specific work plans and the underlying forecast information.

[0267] Step 8:

[0268] The server monitors the actual progress of the work in real time. It acquires necessary data from sensors and management systems as the work progresses.

[0269] Step 9:

[0270] If the server detects a discrepancy between predictions and actual results, it will send an alert to the user via their terminal. This alert is intended to prompt a quick response.

[0271] Step 10:

[0272] Review the schedules and resource allocations received by the user and make adjustments as needed. By incorporating the user's suggested revisions, the work plan can be flexibly adjusted.

[0273] (Example 1)

[0274] 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."

[0275] Amidst increasing operational complexity and market fluctuations, efficient operational management and resource allocation are becoming difficult, necessitating the provision of comprehensive systems to address these challenges. Specifically, there is a need for means to enable rapid response through the collection, forecasting, scheduling, and real-time feedback of operational data.

[0276] 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.

[0277] In this invention, the server includes means for automatically acquiring business-related information and performing data preparation, means for constructing and knowledge-izing a prediction structure for business processing based on the preprocessed information, and means for predicting future business loads using the prediction structure. As a result, it becomes possible to efficiently and effectively formulate a business plan, achieve optimal allocation of resources, and adjust the progress of business in real time.

[0278] "Business-related information" refers to data related to the business of an enterprise or organization, and includes information such as the number of processed cases and resource usage status.

[0279] "Data preparation" is a process of complementing missing values and correcting abnormal values for the collected data, and also includes normalization and format conversion.

[0280] "Prediction structure" is a model constructed to learn rules and patterns obtained from past data, and is used to predict future business loads.

[0281] "Business plan" is a schedule generated based on the predicted business load, and is aimed at evenly distributing the load while avoiding business peaks.

[0282] "Resource allocation" is to appropriately arrange the necessary personnel and equipment based on the business plan, and is a process for realizing the efficient execution of business.

[0283] "Real-time feedback" is a mechanism for monitoring the progress of business in real time, and immediately issuing an alert and prompting adjustment as needed.

[0284] The business efficiency improvement system of this invention is designed to automatically collect business-related information and optimize the business plan based on it. The following is an explanation of specific embodiments.

[0285] This system uses a server as the core of data processing. The server automatically retrieves business-related information from the enterprise database using APIs and ETL (Extract, Transform, Load) processes. Data processing libraries such as Python's pandas and NumPy are used for this process. The collected data is preprocessed, including imputing missing values and correcting outliers.

[0286] Based on the preprocessed data, the server constructs a prediction model using machine learning libraries such as scikit-learn and TensorFlow. This enables the server to accurately predict future business loads and generate effective business plans. Flexible algorithms applicable to production management and personnel scheduling are utilized in formulating the business plan.

[0287] Along with the generated business plan, the server optimizes resource allocation and determines the deployment of required personnel and equipment. This information is provided to the user via the terminal, and the user can check the details through dashboards or alert emails. Additionally, the user can provide feedback on the presented plan and make modifications as needed.

[0288] During business operations, if the server tracks the progress in real time and detects a deviation between the plan and the actual performance, it promptly sends an alert to the user through the terminal. This feedback enables the user to immediately adjust the business plan.

[0289] As a specific example, there is a case where demand forecasting is performed using this system in the manufacturing industry and a production plan is formulated, enabling efficient resource allocation. An example of a prompt sentence is "Please propose an optimization method for demand forecasting and resource allocation in the manufacturing industry." This enables enterprises to improve business efficiency and maintain competitiveness.

[0290] [[ID=第十九]] The flow of the specific process in Example

[0291] Step 1:

[0292] The server connects to the company's database and automatically retrieves business-related information using APIs and ETL processes. The data collected includes historical transaction counts, resource usage, and sales data. Input is raw data retrieved from various databases, and output is a raw dataset for data preprocessing. This process is scheduled to run periodically.

[0293] Step 2:

[0294] The server performs preprocessing on the collected raw dataset. This preprocessing uses the Python pandas library to impute missing values ​​and correct outliers. Data normalization and formatting are also performed, organizing the data into a user-friendly format. Specifically, numerical data is scaled and categorical data is encoded. The input is the raw dataset obtained in step 1, and the output is the prepared dataset.

[0295] Step 3:

[0296] Based on a pre-configured dataset, a prediction structure is built using machine learning libraries such as scikit-learn and TensorFlow. This prediction structure is a model designed to predict future workload by learning past trends. The specific operation involves using the output dataset from step 2 as training data and applying algorithms to train the model. The input is a pre-processed dataset, and the output is the trained prediction model.

[0297] Step 4:

[0298] The server uses a predictive model to generate an optimal work plan to address future workloads. This plan aims to evenly distribute peak loads. Specifically, resource allocation is optimized through simulations using a generative AI model. The inputs are the predictive model and real-time status data, and the outputs are the work schedule and resource allocation plan.

[0299] Step 5:

[0300] The terminal receives output information from the server and notifies the user. Notification methods include visualization on a dashboard and sending alert emails. The user can review the provided information and provide feedback. Specifically, this involves accessing a user interface for reviewing, modifying, and approving plans. Inputs are work schedules and resource allocation plans, while output is user feedback.

[0301] Step 6:

[0302] The server tracks the progress of tasks in real time and issues alerts if predictions and actual results deviate. This allows users to quickly adjust their work plans. Specific operations include data collection from IoT devices and sensors, comparative analysis, and alert notifications. Input is real-time data, and output is updated work plans or alert notifications.

[0303] (Application Example 1)

[0304] 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."

[0305] When aiming to improve the operational efficiency in a logistics center, it is required to collect various types of data and formulate appropriate business schedules and allocate resources. However, in conventional systems, since these are carried out individually, it takes time for data integration and analysis, making rapid decision-making difficult. To solve this problem, it is necessary to monitor the progress of operations in real time and make appropriate adjustments.

[0306] The specific processing by the specific processing unit 290 of the data processing apparatus 12 in Application Example 1 is realized by the following respective means.

[0307] In this invention, the server includes a device that automatically collects business information and performs preprocessing, a device that develops and trains a prediction model for business processing by utilizing the preprocessed information, and a device that monitors the progress of business in real time and proposes adjustments as necessary. Thereby, it becomes possible to formulate a business plan quickly and accurately and optimize the allocation of resources.

[0308] "Business information" refers to all data related to the operation of the logistics center, which includes the progress of work, the usage status of resources, past work history, etc.

[0309] "Preprocessing" is a process of converting the collected raw data into an analyzable form, which performs the complementation of missing values and the correction of abnormal values.

[0310] "Prediction model" refers to a mathematical or statistical model used to predict future business loads based on past business data.

[0311] "Business plan" is a specific schedule and resource allocation plan for efficiently performing future business activities in the logistics center.

[0312] "Resources" refer to the personnel, equipment, and other necessary elements required for the business execution of the logistics center.

[0313] "Monitoring" refers to the process of tracking the progress of operations in real time and immediately detecting any anomalies.

[0314] "Adjustment" refers to actions taken to maximize operational efficiency by making necessary changes to work plans and resource allocations.

[0315] "Device" refers to the hardware and software components necessary to perform each of the above functions.

[0316] The system implementing this invention aims to improve the operational efficiency of a logistics center, with a server, terminals, and users playing key roles. The server automatically collects operational information and preprocesses the data using Python and related libraries. Specifically, it uses Pandas to impute missing values ​​and correct outliers. The preprocessed data is fed into a predictive model using TensorFlow to predict future workload.

[0317] The server generates an optimal work plan based on the predicted workload. This plan is created using optimization algorithms such as linear programming. The generated work plan is then pushed to the device via an application built with React Native and communicated to the user.

[0318] Users can review the plan presented through their terminal and make adjustments as needed. During actual work, the server uses AWS to monitor operations in real time and issues warnings if the predicted results deviate from actual results. This allows users to respond quickly and fine-tune their operations.

[0319] As a concrete example, to prevent congestion at logistics centers during the year-end period when consumption increases, it becomes possible to arrange additional personnel in advance. An example of a prompt message to the generated AI model is, "Based on past operational data of the logistics center, predict the workload for the next three months and propose the optimal staffing arrangement."

[0320] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0321] Step 1:

[0322] The server automatically collects business information from various data sources using APIs. It receives data from various databases and sensors as input, and outputs an integrated dataset. This integrated data forms the basis for subsequent analysis.

[0323] Step 2:

[0324] The server performs preprocessing on the collected dataset. Specifically, it uses the Pandas library to impute missing values ​​with the mean and correct outliers. It accepts an integrated raw dataset as input and outputs a clean, analyzable dataset.

[0325] Step 3:

[0326] The server uses a generative AI model based on TensorFlow to make predictions, utilizing pre-processed data to train the predictive model. A clean dataset is fed into the model as input, and the output predicts future workload. This allows for the prediction of business needs and peak times.

[0327] Step 4:

[0328] The server uses linear programming to generate an optimal workload plan based on the predicted workload. It receives the prediction results as input and creates a detailed schedule and resource allocation plan as output. This plan enables the optimal allocation of resources.

[0329] Step 5:

[0330] The device notifies the user of the work plan generated through an application built with React Native. It receives the work plan from the server as input and communicates the information to the user via push notifications as output. The user then uses this information to respond to the work situation.

[0331] Step 6:

[0332] Users review the plan presented via their terminal and make adjustments as needed. They review the work plan generated as input and make necessary changes or approvals as output. This allows for plan adjustments that are adapted to the actual situation on site.

[0333] Step 7:

[0334] The server uses AWS to monitor business progress in real time and issues warnings when discrepancies between actual results and forecasts are detected. It receives real-time data as input and notifies the user of warning alerts when discrepancies are detected as output. This allows users to take quick action.

[0335] 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.

[0336] This invention is a business efficiency system that takes into account the emotional state of the user. It not only collects and analyzes business data, but also provides a function to recognize the user's emotions in real time and adjust the business plan based on those emotions.

[0337] The server first connects to the company's business database and collects historical business processing data and resource usage. This data is then preprocessed to generate a standardized dataset. The data created here forms the basis for predictive models of business processes.

[0338] Next, the server uses machine learning algorithms to build a predictive model of business processes, thereby predicting future workloads. Based on these predictions, an optimal work schedule is generated, and resource allocation is planned to avoid peak workloads.

[0339] The emotion engine, a key feature of this invention, recognizes the user's emotional state in real time, and this emotional data is analyzed by a server. Based on the user's emotional data, the server evaluates the stress level and motivation level, and adjusts the workload and resource allocation as needed to reduce the user's workload and ensure appropriate resource allocation.

[0340] The generated work schedule and resource allocation are notified to the user via their terminal. The user can review this information and provide situation-appropriate feedback. The results of the emotion engine are also notified, allowing the user to understand their own emotional state.

[0341] Furthermore, by having the server monitor the progress of tasks in real time, if there is a discrepancy between predictions and actual results, a prompt alert is sent to the user via the terminal. Once the user approves, the server implements the proposed adjustments and immediately updates the task schedule and resource allocation.

[0342] As a concrete example, one customer support center implemented a system utilizing this emotion engine, which enabled them to regularly monitor the stress levels of their staff. When the emotion engine data indicated high stress levels, the server automatically took measures to reduce the workload, resulting in improved work efficiency while maintaining staff motivation. This allowed the company to simultaneously maintain service quality and improve employee satisfaction.

[0343] The following describes the processing flow.

[0344] Step 1:

[0345] The server connects to the business management system and automatically collects historical business processing data. This data includes the number of items processed, processing time, and resources used.

[0346] Step 2:

[0347] The server preprocesses the acquired data. This includes imputing missing values, detecting and correcting outliers, and normalizing the data.

[0348] Step 3:

[0349] The server uses pre-processed data to build predictive models for business processes using machine learning algorithms. Specifically, it performs trend analysis and learns seasonal patterns.

[0350] Step 4:

[0351] The server uses a predictive model to forecast future business processing loads. These forecasts include identifying daily or weekly load peaks.

[0352] Step 5:

[0353] The server generates an optimal work schedule based on the prediction results, planning for the equal use of resources during each work period.

[0354] Step 6:

[0355] The server plans resource allocation and optimally assigns the necessary personnel and equipment, thereby avoiding resource surpluses or shortages.

[0356] Step 7:

[0357] The terminal notifies the user of the generated work schedule and resource allocation. The notification includes a detailed schedule and forecast background.

[0358] Step 8:

[0359] The device detects the user's emotional state in real time via an emotion engine. The data is used to measure stress levels and motivation levels.

[0360] Step 9:

[0361] The server analyzes emotional data and readjusts workload if user stress levels are high. If necessary, it proposes a reallocation of personnel.

[0362] Step 10:

[0363] The server monitors the progress of operations in real time, and if there is a discrepancy between predictions and actual results, it sends an alert to the user via the terminal.

[0364] Step 11:

[0365] The user reviews the alert and approves any necessary adjustments to the work schedule or resource allocation. Based on the user's approval, the server automatically executes the adjustments.

[0366] (Example 2)

[0367] 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".

[0368] In today's work environment, predicting workload and allocating resources appropriately are difficult, hindering efficient operations. Furthermore, the lack of consideration for employees' emotional states leads to stress and decreased motivation, resulting in reduced work efficiency. Under these circumstances, there is a need to achieve both high work efficiency and employee satisfaction.

[0369] 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.

[0370] In this invention, the server includes means for automatically collecting and standardizing business data, means for building and training a predictive model of business processing based on the pre-processed data, and means for estimating future workload using the predictive model. This enables efficient business management and flexible business adjustments that take into account the emotional state of users.

[0371] "Business data" refers to information about the execution status of business processes and resource usage, and is used for business planning, analysis, and forecasting.

[0372] "Standardization" refers to the process of converting collected data into a unified format or standard, and is a technique used to maintain consistency in data analysis and model building.

[0373] A "predictive model" is a model that combines mathematical or computational methods to estimate future workload based on past data.

[0374] A "work plan" refers to an optimized schedule of tasks that takes into account the resources and time required to execute those tasks.

[0375] "Resource allocation" is the process of most effectively allocating available resources (such as personnel and equipment) to tasks with the aim of efficiently carrying out those tasks.

[0376] "Users" refers to individuals or organizations that operate the system, receive various information related to their work, and provide feedback.

[0377] "Emotional information" refers to data that indicates the user's psychological and physiological state, such as their stress level and motivation.

[0378] "Real-time monitoring" refers to the continuous tracking of business processes and user status in real time, providing information in real time.

[0379] A "warning" is a notification issued by the system when it detects an abnormal condition or a discrepancy between predictions and actual results, and is intended to prompt a quick response.

[0380] "Correction" refers to the act of improving and adjusting business plans and resource allocation when there is a discrepancy between predictions and the current situation.

[0381] This invention is a system that collects, analyzes, and predicts business data in order to improve operational efficiency. Each process is carried out through the collaboration of a server, terminals, and users.

[0382] First, the server connects to the company's database to collect data on business processes and resource usage. This operation utilizes techniques that access the database using SQL queries. The data is then aggregated on the server and cleansed and standardized using Python or other data processing languages. This data preparation creates the dataset that forms the basis of the predictive model.

[0383] Next, the server uses a machine learning platform (e.g., scikit-learn or TensorFlow) to build a predictive model for business processes. This model allows for the estimation of future workload and the planning of optimal resource allocation.

[0384] Furthermore, a crucial aspect of this system is the real-time recognition of the user's emotional state. Wearable devices and applications used by the user collect data such as heart rate, sweating, and facial expressions, and send it to a server. The server analyzes this data and quantifies the user's stress level and motivation.

[0385] The terminal is a device that provides users with notifications and alerts from the server. On the terminal, users can check their work schedule and proposed adjustments, and input feedback on the spot. Notifications are provided as text messages and pop-up alerts.

[0386] As a concrete example, one customer support center adjusts workloads based on the emotional state of its staff. For instance, if emotional analysis determines that a particular staff member is experiencing high stress levels, the server automatically takes measures to reduce their workload. This allows for flexible resource allocation through schedule adjustments, enabling both improved operational efficiency and increased employee satisfaction.

[0387] An example of a prompt is: "Consider the user's emotional state and suggest ways to adjust next week's work schedule and optimize resource allocation." The system will then generate an optimized solution and propose it to the user.

[0388] As described above, the present invention provides a mechanism for improving work efficiency and appropriately managing the emotional state of users, and is expected to be used in a variety of work environments.

[0389] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0390] Step 1:

[0391] The server connects to the business database. It retrieves historical business processing data and resource usage information from the database as input. The server then collects the data and performs cleansing and standardization processes. It converts the raw data received from the database into a consistent format and outputs it as a dataset ready for the predictive model. Specifically, this involves extracting necessary information using SQL queries.

[0392] Step 2:

[0393] The server uses machine learning libraries to build a predictive model of business processes based on a dataset. The server uses a prepared dataset as input. It applies machine learning algorithms (e.g., regression analysis, time series forecasting) to output a model that estimates future workload. This model establishes the foundation for developing business plans. A concrete example of this is the execution of a script using Python.

[0394] Step 3:

[0395] The server creates a work plan and resource allocation based on the output from a predictive model. Predicted workload data is used as input. The server generates a work schedule to reduce inefficient workload peaks and optimize resource allocation. This schedule is output in a way that supports the smooth execution of operations. Specifically, this involves the application of a scheduling algorithm.

[0396] Step 4:

[0397] Users record their emotional state using provided wearable devices and apps, and send this data to a server via their devices. Emotional data is input as heart rate and skin electrical responses. The server analyzes this data, evaluates stress levels, quantifies motivation, and outputs the results. Specific actions include data transmission and app operation.

[0398] Step 5:

[0399] The terminal notifies the user of the work schedule and sentiment analysis results received from the server. The input consists of analysis results and work plans from the server. The terminal provides this information to the user, allowing them to check the situation immediately. The notified information is output as a basis for user confirmation and feedback. Specific actions include displaying alerts and sending messages.

[0400] Step 6:

[0401] The server monitors the progress of tasks in real time and proposes adjustments via terminals as needed. It processes data on the progress of tasks as input. The server analyzes the difference between predictions and actual results from this input and outputs necessary alerts and adjustment proposals to the user. Specifically, it integrates with the monitoring system and performs data analysis.

[0402] Step 7:

[0403] The user approves or modifies the proposed adjustments via their terminal and provides feedback, which is then sent to the server. Receiving user instructions as input, the server modifies the work plan and resource allocation. This creates an optimal work environment that reflects the user's needs and outputs it as an actionable plan. Specifically, this involves filling out a feedback form.

[0404] (Application Example 2)

[0405] 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."

[0406] In modern households, an individual's emotional state significantly impacts the efficiency of daily life. However, a system that effectively manages this and optimizes household tasks and daily schedules still lacks a solution. Therefore, there is a need for flexible scheduling adjustments that take into account the well-being of all family members.

[0407] 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.

[0408] In this invention, the server includes means for automatically collecting and preprocessing business data, means for building and training a predictive model for business processing based on the preprocessed data, and means for adjusting household tasks and daily schedules based on an individual's emotional state. This enables flexible schedule adjustments that reflect the emotional state of family members.

[0409] "Business data" refers to a collection of information related to business activities, and is a general term for data including past business processing data and resource usage status.

[0410] "Preprocessing" refers to the process of performing necessary modifications on collected raw data, including tasks such as data standardization and noise reduction.

[0411] A "predictive model" is a mathematical model built using machine learning algorithms to derive new insights from data, and it estimates future trends in business processes.

[0412] A "work schedule" is a plan created based on the predicted workload, and it defines the time allocation necessary to optimally carry out work activities.

[0413] "Resource allocation" refers to the appropriate distribution of resources such as people, materials, money, and information in order to carry out tasks efficiently.

[0414] "Monitoring" refers to activities that involve monitoring the progress of work in real time and understanding the status of that progress.

[0415] "Adjustment" refers to proposing and implementing changes to planned schedules and resource allocations as necessary.

[0416] "Emotional state" refers to an individual's psychological state and is used to evaluate indicators such as stress levels and feelings of well-being.

[0417] "Household tasks" refer to everyday tasks performed at home, including activities related to daily life such as cleaning, cooking, and shopping.

[0418] To realize this invention, a system involving three main parties—a server, a terminal, and a user—is necessary. The server collects various data from within the home, preprocesses it, and then builds a predictive model using a machine learning algorithm. Specifically, the server integrates various business and emotional data from within the home and predicts future task loads based on this data.

[0419] The server uses emotion recognition APIs (such as EmotionAPI) to analyze the user's emotional state and processes the emotional data in real time. Based on this analysis, it adjusts the allocation of household task schedules. It also uses machine learning platforms such as TensorFlow to predict the behavioral patterns of the entire family and create an optimal daily schedule.

[0420] The device delivers various notifications to the user and provides suggested task schedules and emotional state feedback on the electronic screen. Based on this feedback, the user can understand their emotional state and request adjustments from the system as needed.

[0421] When performing various tasks within the home, users receive suggestions based on emotional data provided by the server, which helps them manage their family's daily life smoothly. For example, if a user is tired in the morning, the server might suggest, "You seem particularly tired today. How about preparing a hot coffee and a slightly larger, more nutritious breakfast?"

[0422] An example of a prompt message might be: "Based on the user's emotional data, suggest an optimal morning routine for when their stress level is high."

[0423] In this way, the present invention makes it possible to optimize the lives of individuals and families as a whole through the recognition of emotions within the home.

[0424] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0425] Step 1:

[0426] The server collects business and emotional data from various sensors and devices within the home. Inputs include emotional data acquired from cameras and microphones, and environmental data from temperature and humidity sensors. At this stage, the data is collected in raw format and stored in a database.

[0427] Step 2:

[0428] The server preprocesses the collected raw data, particularly by removing noise and standardizing it. The input is raw data, and the output is a clean, consistent dataset. This process includes imputing missing values ​​and removing outliers.

[0429] Step 3:

[0430] The server builds and trains a predictive model based on preprocessed data. Specifically, it uses a machine learning algorithm based on TensorFlow. The input is the preprocessed data, and the output is the predictive model. The model learns family emotional tendencies and patterns of daily tasks to predict future situations.

[0431] Step 4:

[0432] The server uses a built predictive model to forecast future household task loads. Inputs are the predictive model and current sentiment data; output is the future task load forecast. This provides information useful for improving the efficiency of daily life.

[0433] Step 5:

[0434] The server adjusts the household task schedule considering the user's emotional state and notifies the user of the suggestions via the terminal. Inputs are future task load predictions and emotional data, while output is the suggested schedule. In this step, the suggestions are generated by a generative AI model, and prompt statements are also referenced.

[0435] Step 6:

[0436] Users review the proposals from their devices and approve or modify the system's schedule by providing feedback. Here, the input is the proposed schedule, and the output is the user's feedback. Specifically, this involves confirmation and response on a smartphone or tablet.

[0437] Step 7:

[0438] The server receives user feedback and updates task schedules and resource allocations as needed. These updates are reflected in the system in real time, resulting in an optimized home task schedule as output.

[0439] 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.

[0440] 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.

[0441] 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.

[0442] [Third Embodiment]

[0443] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0444] 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.

[0445] 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).

[0446] 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.

[0447] 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.

[0448] 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).

[0449] 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.

[0450] 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.

[0451] 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.

[0452] 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.

[0453] 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.

[0454] 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".

[0455] The business efficiency system of this invention is based on a software program that enables the automatic collection, analysis, prediction, scheduling, and resource allocation of business data.

[0456] The server first accesses the company's business database to collect data on past business process counts and resource usage. APIs and ETL (Extract, Transform, Load) processes are used for this data collection.

[0457] Subsequently, the server preprocesses the acquired data, filling in missing values ​​and correcting outliers. Data normalization and format conversion are also performed at this stage. Based on this prepared data, the server builds a predictive model using machine learning algorithms. This model learns from past trends and predicts future workloads with high accuracy.

[0458] Based on the predicted workload, the server automatically generates a work schedule. This schedule is designed to avoid peak workloads, distribute the load evenly, and allocate resources effectively. In addition, resource allocation is performed simultaneously, specifically determining the number of personnel and equipment required.

[0459] The user will be notified of the created schedule and resource allocation details via their device. The user can review these proposals and make modifications as needed.

[0460] Furthermore, during actual work, the server monitors the progress in real time. This monitoring triggers alerts to the user via their terminal if there is a discrepancy between predictions and actual results. This allows users to quickly fine-tune their work schedules.

[0461] As a concrete example, one manufacturing company used this system to create production plans, preventing production disruptions during peak seasons. The server performed demand forecasts, and terminals presented optimal production plans to administrators, resulting in efficient personnel allocation and a reduction in excess inventory. In this way, the company's overall operational efficiency improved, enabling it to maintain its competitiveness.

[0462] The following describes the processing flow.

[0463] Step 1:

[0464] The server connects to the company's business database and automatically extracts data on past business transaction counts, hourly load, and resource usage. Database queries and APIs are used for this extraction.

[0465] Step 2:

[0466] The server performs preprocessing on the acquired data. Preprocessing includes imputing missing values, removing outliers, normalizing the data, and standardizing date and time formats.

[0467] Step 3:

[0468] Based on the data stored on the server, machine learning algorithms are applied to build predictive models for business processes. Algorithm selection utilizes technologies aligned with past trends (e.g., ARIMA, LSTM, etc.).

[0469] Step 4:

[0470] The server uses a predictive model to forecast future workload. This forecast evaluates the load at specific time intervals and identifies peak times for business operations.

[0471] Step 5:

[0472] The server generates an optimal work schedule based on the prediction results. The schedule is designed to equalize the workload and ensure efficient use of resources.

[0473] Step 6:

[0474] The server plans resource allocation based on predictions and determines the number of personnel and materials needed. This ensures that no resources are in excess or insufficient.

[0475] Step 7:

[0476] The terminal notifies the user of the generated work schedule and resource allocation plan. The notification includes specific work plans and the underlying forecast information.

[0477] Step 8:

[0478] The server monitors the actual progress of the work in real time. It acquires necessary data from sensors and management systems as the work progresses.

[0479] Step 9:

[0480] If the server detects a discrepancy between predictions and actual results, it will send an alert to the user via their terminal. This alert is intended to prompt a quick response.

[0481] Step 10:

[0482] Review the schedules and resource allocations received by the user and make adjustments as needed. By incorporating the user's suggested revisions, the work plan can be flexibly adjusted.

[0483] (Example 1)

[0484] 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."

[0485] Amidst increasing operational complexity and market fluctuations, efficient operational management and resource allocation are becoming difficult, necessitating the provision of comprehensive systems to address these challenges. Specifically, there is a need for means to enable rapid response through the collection, forecasting, scheduling, and real-time feedback of operational data.

[0486] 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.

[0487] In this invention, the server includes means for automatically acquiring business-related information and preparing data, means for constructing a predictive structure for business processing based on the pre-processed information and turning it into knowledge, and means for predicting future workload using the predictive structure. This enables efficient and effective business planning, optimal resource allocation, and real-time adjustment of business progress.

[0488] "Business-related information" refers to data related to the operations of a company or organization, including information such as the number of transactions processed and resource usage.

[0489] "Data preparation" is the process of imputing missing values ​​and correcting outliers in collected data, and it also includes normalization and format conversion.

[0490] A "predictive structure" is a model built to learn rules and patterns derived from past data, and is used to predict future workloads.

[0491] A "work plan" is a schedule generated based on predicted workload, with the aim of avoiding peak workloads and distributing the load evenly.

[0492] "Resource allocation" refers to the process of appropriately allocating necessary personnel and equipment based on a work plan, and is essential for achieving efficient work execution.

[0493] "Real-time feedback" refers to a system that monitors the progress of work in real time, issues immediate alerts as needed, and prompts adjustments.

[0494] The business efficiency system of this invention is designed to automatically collect business-related information and optimize business plans based on that information. The following is a description of a specific embodiment.

[0495] This system uses a server as the core of its data processing. The server automatically retrieves business-related information from the company's database using APIs and ETL (Extract, Transform, Load) processes. This process utilizes data processing libraries such as Python's pandas and NumPy. The collected data undergoes preprocessing, including the imputation of missing values ​​and the correction of outliers.

[0496] Based on preprocessed data, the server uses machine learning libraries such as scikit-learn and TensorFlow to construct a prediction structure. This allows the server to accurately predict future workloads and generate effective work plans. The work plan formulation utilizes flexible algorithms that can be applied to production management and personnel scheduling.

[0497] Along with the generated work plan, the server optimizes resource allocation and determines the placement of necessary personnel and equipment. This information is provided to the user via a terminal, and the user can view details through a dashboard or alert email. The user can also provide feedback on the presented plan and make modifications as needed.

[0498] During the work process, the server tracks progress in real time and, if it detects a discrepancy between the planned and actual progress, it quickly sends an alert to the user via their terminal. This feedback allows the user to immediately adjust their work plan.

[0499] As a concrete example, in the manufacturing industry, this system has been used to forecast demand and develop production plans, enabling efficient resource allocation. An example of a prompt message would be, "Please propose a method for optimizing demand forecasting and resource allocation in the manufacturing industry." This allows companies to improve operational efficiency and maintain their competitiveness.

[0500] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0501] Step 1:

[0502] The server connects to the company's database and automatically retrieves business-related information using APIs and ETL processes. The data collected includes historical transaction counts, resource usage, and sales data. Input is raw data retrieved from various databases, and output is a raw dataset for data preprocessing. This process is scheduled to run periodically.

[0503] Step 2:

[0504] The server performs preprocessing on the collected raw dataset. This preprocessing uses the Python pandas library to impute missing values ​​and correct outliers. Data normalization and formatting are also performed, organizing the data into a user-friendly format. Specifically, numerical data is scaled and categorical data is encoded. The input is the raw dataset obtained in step 1, and the output is the prepared dataset.

[0505] Step 3:

[0506] Based on a pre-configured dataset, a prediction structure is built using machine learning libraries such as scikit-learn and TensorFlow. This prediction structure is a model designed to predict future workload by learning past trends. The specific operation involves using the output dataset from step 2 as training data and applying algorithms to train the model. The input is a pre-processed dataset, and the output is the trained prediction model.

[0507] Step 4:

[0508] The server uses a predictive model to generate an optimal work plan to address future workloads. This plan aims to evenly distribute peak loads. Specifically, resource allocation is optimized through simulations using a generative AI model. The inputs are the predictive model and real-time status data, and the outputs are the work schedule and resource allocation plan.

[0509] Step 5:

[0510] The terminal receives output information from the server and notifies the user. Notification methods include visualization on a dashboard and sending alert emails. The user can review the provided information and provide feedback. Specifically, this involves accessing a user interface for reviewing, modifying, and approving plans. Inputs are work schedules and resource allocation plans, while output is user feedback.

[0511] Step 6:

[0512] The server tracks the progress of tasks in real time and issues alerts if predictions and actual results deviate. This allows users to quickly adjust their work plans. Specific operations include data collection from IoT devices and sensors, comparative analysis, and alert notifications. Input is real-time data, and output is updated work plans or alert notifications.

[0513] (Application Example 1)

[0514] 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."

[0515] To improve operational efficiency in logistics centers, it is necessary to collect diverse data and formulate appropriate work schedules and resource allocations. However, conventional systems perform these tasks individually, resulting in time-consuming data integration and analysis, making rapid decision-making difficult. To solve this problem, it is necessary to monitor the progress of operations in real time and make adjustments as needed.

[0516] 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.

[0517] In this invention, the server includes a device that automatically collects and preprocesses business information, a device that develops and trains a predictive model for business processing using the preprocessed information, and a device that monitors business progress in real time and proposes adjustments as needed. This enables the rapid and accurate formulation of business plans and the optimal allocation of resources.

[0518] "Operational information" refers to all data related to the operation of the logistics center, including work progress, resource usage, and past work history.

[0519] "Preprocessing" is the process of converting collected raw data into an analyzable format, including imputing missing values ​​and correcting outliers.

[0520] A "predictive model" refers to a mathematical or statistical model used to predict future workloads based on past business data.

[0521] A "work plan" is a detailed schedule and resource allocation plan for efficiently carrying out future business activities at a logistics center.

[0522] "Resources" refers to the personnel, equipment, and other necessary elements required to carry out the operations of a logistics center.

[0523] "Monitoring" refers to the process of tracking the progress of operations in real time and immediately detecting any anomalies.

[0524] "Adjustment" refers to actions taken to maximize operational efficiency by making necessary changes to work plans and resource allocations.

[0525] "Device" refers to the hardware and software components necessary to perform each of the above functions.

[0526] The system implementing this invention aims to improve the operational efficiency of a logistics center, with a server, terminals, and users playing key roles. The server automatically collects operational information and preprocesses the data using Python and related libraries. Specifically, it uses Pandas to impute missing values ​​and correct outliers. The preprocessed data is fed into a predictive model using TensorFlow to predict future workload.

[0527] The server generates an optimal work plan based on the predicted workload. This plan is created using optimization algorithms such as linear programming. The generated work plan is then pushed to the device via an application built with React Native and communicated to the user.

[0528] Users can review the plan presented through their terminal and make adjustments as needed. During actual work, the server uses AWS to monitor operations in real time and issues warnings if the predicted results deviate from actual results. This allows users to respond quickly and fine-tune their operations.

[0529] As a concrete example, to prevent congestion at logistics centers during the year-end period when consumption increases, it becomes possible to arrange additional personnel in advance. An example of a prompt message to the generated AI model is, "Based on past operational data of the logistics center, predict the workload for the next three months and propose the optimal staffing arrangement."

[0530] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0531] Step 1:

[0532] The server automatically collects business information from various data sources using APIs. It receives data from various databases and sensors as input, and outputs an integrated dataset. This integrated data forms the basis for subsequent analysis.

[0533] Step 2:

[0534] The server performs preprocessing on the collected dataset. Specifically, it uses the Pandas library to impute missing values ​​with the mean and correct outliers. It accepts an integrated raw dataset as input and outputs a clean, analyzable dataset.

[0535] Step 3:

[0536] The server uses a generative AI model based on TensorFlow to make predictions, utilizing pre-processed data to train the predictive model. A clean dataset is fed into the model as input, and the output predicts future workload. This allows for the prediction of business needs and peak times.

[0537] Step 4:

[0538] The server uses linear programming to generate an optimal workload plan based on the predicted workload. It receives the prediction results as input and creates a detailed schedule and resource allocation plan as output. This plan enables the optimal allocation of resources.

[0539] Step 5:

[0540] The device notifies the user of the work plan generated through an application built with React Native. It receives the work plan from the server as input and communicates the information to the user via push notifications as output. The user then uses this information to respond to the work situation.

[0541] Step 6:

[0542] Users review the plan presented via their terminal and make adjustments as needed. They review the work plan generated as input and make necessary changes or approvals as output. This allows for plan adjustments that are adapted to the actual situation on site.

[0543] Step 7:

[0544] The server uses AWS to monitor business progress in real time and issues warnings when discrepancies between actual results and forecasts are detected. It receives real-time data as input and notifies the user of warning alerts when discrepancies are detected as output. This allows users to take quick action.

[0545] 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.

[0546] This invention is a business efficiency system that takes into account the emotional state of the user. It not only collects and analyzes business data, but also provides a function to recognize the user's emotions in real time and adjust the business plan based on those emotions.

[0547] The server first connects to the company's business database and collects historical business processing data and resource usage. This data is then preprocessed to generate a standardized dataset. The data created here forms the basis for predictive models of business processes.

[0548] Next, the server uses machine learning algorithms to build a predictive model of business processes, thereby predicting future workloads. Based on these predictions, an optimal work schedule is generated, and resource allocation is planned to avoid peak workloads.

[0549] The emotion engine, a key feature of this invention, recognizes the user's emotional state in real time, and this emotional data is analyzed by a server. Based on the user's emotional data, the server evaluates the stress level and motivation level, and adjusts the workload and resource allocation as needed to reduce the user's workload and ensure appropriate resource allocation.

[0550] The generated work schedule and resource allocation are notified to the user via their terminal. The user can review this information and provide situation-appropriate feedback. The results of the emotion engine are also notified, allowing the user to understand their own emotional state.

[0551] Furthermore, by having the server monitor the progress of tasks in real time, if there is a discrepancy between predictions and actual results, a prompt alert is sent to the user via the terminal. Once the user approves, the server implements the proposed adjustments and immediately updates the task schedule and resource allocation.

[0552] As a concrete example, one customer support center implemented a system utilizing this emotion engine, which enabled them to regularly monitor the stress levels of their staff. When the emotion engine data indicated high stress levels, the server automatically took measures to reduce the workload, resulting in improved work efficiency while maintaining staff motivation. This allowed the company to simultaneously maintain service quality and improve employee satisfaction.

[0553] The following describes the processing flow.

[0554] Step 1:

[0555] The server connects to the business management system and automatically collects historical business processing data. This data includes the number of items processed, processing time, and resources used.

[0556] Step 2:

[0557] The server preprocesses the acquired data. This includes imputing missing values, detecting and correcting outliers, and normalizing the data.

[0558] Step 3:

[0559] The server uses pre-processed data to build predictive models for business processes using machine learning algorithms. Specifically, it performs trend analysis and learns seasonal patterns.

[0560] Step 4:

[0561] The server uses a predictive model to forecast future business processing loads. These forecasts include identifying daily or weekly load peaks.

[0562] Step 5:

[0563] The server generates an optimal work schedule based on the prediction results, planning for the equal use of resources during each work period.

[0564] Step 6:

[0565] The server plans resource allocation and optimally assigns the necessary personnel and equipment, thereby avoiding resource surpluses or shortages.

[0566] Step 7:

[0567] The terminal notifies the user of the generated work schedule and resource allocation. The notification includes a detailed schedule and forecast background.

[0568] Step 8:

[0569] The device detects the user's emotional state in real time via an emotion engine. The data is used to measure stress levels and motivation levels.

[0570] Step 9:

[0571] The server analyzes emotional data and readjusts workload if user stress levels are high. If necessary, it proposes a reallocation of personnel.

[0572] Step 10:

[0573] The server monitors the progress of operations in real time, and if there is a discrepancy between predictions and actual results, it sends an alert to the user via the terminal.

[0574] Step 11:

[0575] The user reviews the alert and approves any necessary adjustments to the work schedule or resource allocation. Based on the user's approval, the server automatically executes the adjustments.

[0576] (Example 2)

[0577] 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."

[0578] In today's work environment, predicting workload and allocating resources appropriately are difficult, hindering efficient operations. Furthermore, the lack of consideration for employees' emotional states leads to stress and decreased motivation, resulting in reduced work efficiency. Under these circumstances, there is a need to achieve both high work efficiency and employee satisfaction.

[0579] 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.

[0580] In this invention, the server includes means for automatically collecting and standardizing business data, means for building and training a predictive model of business processing based on the pre-processed data, and means for estimating future workload using the predictive model. This enables efficient business management and flexible business adjustments that take into account the emotional state of users.

[0581] "Business data" refers to information about the execution status of business processes and resource usage, and is used for business planning, analysis, and forecasting.

[0582] "Standardization" refers to the process of converting collected data into a unified format or standard, and is a technique used to maintain consistency in data analysis and model building.

[0583] A "predictive model" is a model that combines mathematical or computational methods to estimate future workload based on past data.

[0584] A "work plan" refers to an optimized schedule of tasks that takes into account the resources and time required to execute those tasks.

[0585] "Resource allocation" is the process of most effectively allocating available resources (such as personnel and equipment) to tasks with the aim of efficiently carrying out those tasks.

[0586] "Users" refers to individuals or organizations that operate the system, receive various information related to their work, and provide feedback.

[0587] "Emotional information" refers to data that indicates the user's psychological and physiological state, such as their stress level and motivation.

[0588] "Real-time monitoring" refers to the continuous tracking of business processes and user status in real time, providing information in real time.

[0589] A "warning" is a notification issued by the system when it detects an abnormal condition or a discrepancy between predictions and actual results, and is intended to prompt a quick response.

[0590] "Correction" refers to the act of improving and adjusting business plans and resource allocation when there is a discrepancy between predictions and the current situation.

[0591] This invention is a system that collects, analyzes, and predicts business data in order to improve operational efficiency. Each process is carried out through the collaboration of a server, terminals, and users.

[0592] First, the server connects to the company's database to collect data on business processes and resource usage. This operation utilizes techniques that access the database using SQL queries. The data is then aggregated on the server and cleansed and standardized using Python or other data processing languages. This data preparation creates the dataset that forms the basis of the predictive model.

[0593] Next, the server uses a machine learning platform (e.g., scikit-learn or TensorFlow) to build a predictive model for business processes. This model allows for the estimation of future workload and the planning of optimal resource allocation.

[0594] Furthermore, a crucial aspect of this system is the real-time recognition of the user's emotional state. Wearable devices and applications used by the user collect data such as heart rate, sweating, and facial expressions, and send it to a server. The server analyzes this data and quantifies the user's stress level and motivation.

[0595] The terminal is a device that provides users with notifications and alerts from the server. On the terminal, users can check their work schedule and proposed adjustments, and input feedback on the spot. Notifications are provided as text messages and pop-up alerts.

[0596] As a concrete example, one customer support center adjusts workloads based on the emotional state of its staff. For instance, if emotional analysis determines that a particular staff member is experiencing high stress levels, the server automatically takes measures to reduce their workload. This allows for flexible resource allocation through schedule adjustments, enabling both improved operational efficiency and increased employee satisfaction.

[0597] An example of a prompt is: "Consider the user's emotional state and suggest ways to adjust next week's work schedule and optimize resource allocation." The system will then generate an optimized solution and propose it to the user.

[0598] As described above, the present invention provides a mechanism for improving work efficiency and appropriately managing the emotional state of users, and is expected to be used in a variety of work environments.

[0599] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0600] Step 1:

[0601] The server connects to the business database. It retrieves historical business processing data and resource usage information from the database as input. The server then collects the data and performs cleansing and standardization processes. It converts the raw data received from the database into a consistent format and outputs it as a dataset ready for the predictive model. Specifically, this involves extracting necessary information using SQL queries.

[0602] Step 2:

[0603] The server uses machine learning libraries to build a predictive model of business processes based on a dataset. The server uses a prepared dataset as input. It applies machine learning algorithms (e.g., regression analysis, time series forecasting) to output a model that estimates future workload. This model establishes the foundation for developing business plans. A concrete example of this is the execution of a script using Python.

[0604] Step 3:

[0605] The server creates a work plan and resource allocation based on the output from a predictive model. Predicted workload data is used as input. The server generates a work schedule to reduce inefficient workload peaks and optimize resource allocation. This schedule is output in a way that supports the smooth execution of operations. Specifically, this involves the application of a scheduling algorithm.

[0606] Step 4:

[0607] Users record their emotional state using provided wearable devices and apps, and send this data to a server via their devices. Emotional data is input as heart rate and skin electrical responses. The server analyzes this data, evaluates stress levels, quantifies motivation, and outputs the results. Specific actions include data transmission and app operation.

[0608] Step 5:

[0609] The terminal notifies the user of the work schedule and sentiment analysis results received from the server. The input consists of analysis results and work plans from the server. The terminal provides this information to the user, allowing them to check the situation immediately. The notified information is output as a basis for user confirmation and feedback. Specific actions include displaying alerts and sending messages.

[0610] Step 6:

[0611] The server monitors the progress of tasks in real time and proposes adjustments via terminals as needed. It processes data on the progress of tasks as input. The server analyzes the difference between predictions and actual results from this input and outputs necessary alerts and adjustment proposals to the user. Specifically, it integrates with the monitoring system and performs data analysis.

[0612] Step 7:

[0613] The user approves or modifies the proposed adjustments via their terminal and provides feedback, which is then sent to the server. Receiving user instructions as input, the server modifies the work plan and resource allocation. This creates an optimal work environment that reflects the user's needs and outputs it as an actionable plan. Specifically, this involves filling out a feedback form.

[0614] (Application Example 2)

[0615] 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."

[0616] In modern households, an individual's emotional state significantly impacts the efficiency of daily life. However, a system that effectively manages this and optimizes household tasks and daily schedules still lacks a solution. Therefore, there is a need for flexible scheduling adjustments that take into account the well-being of all family members.

[0617] 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.

[0618] In this invention, the server includes means for automatically collecting and preprocessing business data, means for building and training a predictive model for business processing based on the preprocessed data, and means for adjusting household tasks and daily schedules based on an individual's emotional state. This enables flexible schedule adjustments that reflect the emotional state of family members.

[0619] "Business data" refers to a collection of information related to business activities, and is a general term for data including past business processing data and resource usage status.

[0620] "Preprocessing" refers to the process of performing necessary modifications on collected raw data, including tasks such as data standardization and noise reduction.

[0621] A "predictive model" is a mathematical model built using machine learning algorithms to derive new insights from data, and it estimates future trends in business processes.

[0622] A "work schedule" is a plan created based on the predicted workload, and it defines the time allocation necessary to optimally carry out work activities.

[0623] "Resource allocation" refers to the appropriate distribution of resources such as people, materials, money, and information in order to carry out tasks efficiently.

[0624] "Monitoring" refers to activities that involve monitoring the progress of work in real time and understanding the status of that progress.

[0625] "Adjustment" refers to proposing and implementing changes to planned schedules and resource allocations as necessary.

[0626] "Emotional state" refers to an individual's psychological state and is used to evaluate indicators such as stress levels and feelings of well-being.

[0627] "Household tasks" refer to everyday tasks performed at home, including activities related to daily life such as cleaning, cooking, and shopping.

[0628] To realize this invention, a system involving three main parties—a server, a terminal, and a user—is necessary. The server collects various data from within the home, preprocesses it, and then builds a predictive model using a machine learning algorithm. Specifically, the server integrates various business and emotional data from within the home and predicts future task loads based on this data.

[0629] The server uses emotion recognition APIs (such as EmotionAPI) to analyze the user's emotional state and processes the emotional data in real time. Based on this analysis, it adjusts the allocation of household task schedules. It also uses machine learning platforms such as TensorFlow to predict the behavioral patterns of the entire family and create an optimal daily schedule.

[0630] The device delivers various notifications to the user and provides suggested task schedules and emotional state feedback on the electronic screen. Based on this feedback, the user can understand their emotional state and request adjustments from the system as needed.

[0631] When performing various tasks within the home, users receive suggestions based on emotional data provided by the server, which helps them manage their family's daily life smoothly. For example, if a user is tired in the morning, the server might suggest, "You seem particularly tired today. How about preparing a hot coffee and a slightly larger, more nutritious breakfast?"

[0632] An example of a prompt message might be: "Based on the user's emotional data, suggest an optimal morning routine for when their stress level is high."

[0633] In this way, the present invention makes it possible to optimize the lives of individuals and families as a whole through the recognition of emotions within the home.

[0634] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0635] Step 1:

[0636] The server collects business and emotional data from various sensors and devices within the home. Inputs include emotional data acquired from cameras and microphones, and environmental data from temperature and humidity sensors. At this stage, the data is collected in raw format and stored in a database.

[0637] Step 2:

[0638] The server preprocesses the collected raw data, particularly by removing noise and standardizing it. The input is raw data, and the output is a clean, consistent dataset. This process includes imputing missing values ​​and removing outliers.

[0639] Step 3:

[0640] The server builds and trains a predictive model based on preprocessed data. Specifically, it uses a machine learning algorithm based on TensorFlow. The input is the preprocessed data, and the output is the predictive model. The model learns family emotional tendencies and patterns of daily tasks to predict future situations.

[0641] Step 4:

[0642] The server uses a built predictive model to forecast future household task loads. Inputs are the predictive model and current sentiment data; output is the future task load forecast. This provides information useful for improving the efficiency of daily life.

[0643] Step 5:

[0644] The server adjusts the household task schedule considering the user's emotional state and notifies the user of the suggestions via the terminal. Inputs are future task load predictions and emotional data, while output is the suggested schedule. In this step, the suggestions are generated by a generative AI model, and prompt statements are also referenced.

[0645] Step 6:

[0646] Users review the proposals from their devices and approve or modify the system's schedule by providing feedback. Here, the input is the proposed schedule, and the output is the user's feedback. Specifically, this involves confirmation and response on a smartphone or tablet.

[0647] Step 7:

[0648] The server receives user feedback and updates task schedules and resource allocations as needed. These updates are reflected in the system in real time, resulting in an optimized home task schedule as output.

[0649] 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.

[0650] 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.

[0651] 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.

[0652] [Fourth Embodiment]

[0653] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0654] 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.

[0655] 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).

[0656] 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.

[0657] 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.

[0658] 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).

[0659] 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.

[0660] 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.

[0661] 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.

[0662] 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.

[0663] 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.

[0664] 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.

[0665] 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".

[0666] The business efficiency system of this invention is based on a software program that enables the automatic collection, analysis, prediction, scheduling, and resource allocation of business data.

[0667] The server first accesses the company's business database to collect data on past business process counts and resource usage. APIs and ETL (Extract, Transform, Load) processes are used for this data collection.

[0668] Subsequently, the server preprocesses the acquired data, filling in missing values ​​and correcting outliers. Data normalization and format conversion are also performed at this stage. Based on this prepared data, the server builds a predictive model using machine learning algorithms. This model learns from past trends and predicts future workloads with high accuracy.

[0669] Based on the predicted workload, the server automatically generates a work schedule. This schedule is designed to avoid peak workloads, distribute the load evenly, and allocate resources effectively. In addition, resource allocation is performed simultaneously, specifically determining the number of personnel and equipment required.

[0670] The user will be notified of the created schedule and resource allocation details via their device. The user can review these proposals and make modifications as needed.

[0671] Furthermore, during actual work, the server monitors the progress in real time. This monitoring triggers alerts to the user via their terminal if there is a discrepancy between predictions and actual results. This allows users to quickly fine-tune their work schedules.

[0672] As a concrete example, one manufacturing company used this system to create production plans, preventing production disruptions during peak seasons. The server performed demand forecasts, and terminals presented optimal production plans to administrators, resulting in efficient personnel allocation and a reduction in excess inventory. In this way, the company's overall operational efficiency improved, enabling it to maintain its competitiveness.

[0673] The following describes the processing flow.

[0674] Step 1:

[0675] The server connects to the company's business database and automatically extracts data on past business transaction counts, hourly load, and resource usage. Database queries and APIs are used for this extraction.

[0676] Step 2:

[0677] The server performs preprocessing on the acquired data. Preprocessing includes imputing missing values, removing outliers, normalizing the data, and standardizing date and time formats.

[0678] Step 3:

[0679] Based on the data stored on the server, machine learning algorithms are applied to build predictive models for business processes. Algorithm selection utilizes technologies aligned with past trends (e.g., ARIMA, LSTM, etc.).

[0680] Step 4:

[0681] The server uses a predictive model to forecast future workload. This forecast evaluates the load at specific time intervals and identifies peak times for business operations.

[0682] Step 5:

[0683] The server generates an optimal work schedule based on the prediction results. The schedule is designed to equalize the workload and ensure efficient use of resources.

[0684] Step 6:

[0685] The server plans resource allocation based on predictions and determines the number of personnel and materials needed. This ensures that no resources are in excess or insufficient.

[0686] Step 7:

[0687] The terminal notifies the user of the generated work schedule and resource allocation plan. The notification includes specific work plans and the underlying forecast information.

[0688] Step 8:

[0689] The server monitors the actual progress of the work in real time. It acquires necessary data from sensors and management systems as the work progresses.

[0690] Step 9:

[0691] If the server detects a discrepancy between predictions and actual results, it will send an alert to the user via their terminal. This alert is intended to prompt a quick response.

[0692] Step 10:

[0693] Review the schedules and resource allocations received by the user and make adjustments as needed. By incorporating the user's suggested revisions, the work plan can be flexibly adjusted.

[0694] (Example 1)

[0695] 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".

[0696] Amidst increasing operational complexity and market fluctuations, efficient operational management and resource allocation are becoming difficult, necessitating the provision of comprehensive systems to address these challenges. Specifically, there is a need for means to enable rapid response through the collection, forecasting, scheduling, and real-time feedback of operational data.

[0697] 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.

[0698] In this invention, the server includes means for automatically acquiring business-related information and preparing data, means for constructing a predictive structure for business processing based on the pre-processed information and turning it into knowledge, and means for predicting future workload using the predictive structure. This enables efficient and effective business planning, optimal resource allocation, and real-time adjustment of business progress.

[0699] "Business-related information" refers to data related to the operations of a company or organization, including information such as the number of transactions processed and resource usage.

[0700] "Data preparation" is the process of imputing missing values ​​and correcting outliers in collected data, and it also includes normalization and format conversion.

[0701] A "predictive structure" is a model built to learn rules and patterns derived from past data, and is used to predict future workloads.

[0702] A "work plan" is a schedule generated based on predicted workload, with the aim of avoiding peak workloads and distributing the load evenly.

[0703] "Resource allocation" refers to the process of appropriately allocating necessary personnel and equipment based on a work plan, and is essential for achieving efficient work execution.

[0704] "Real-time feedback" refers to a system that monitors the progress of work in real time, issues immediate alerts as needed, and prompts adjustments.

[0705] The business efficiency system of this invention is designed to automatically collect business-related information and optimize business plans based on that information. The following is a description of a specific embodiment.

[0706] This system uses a server as the core of its data processing. The server automatically retrieves business-related information from the company's database using APIs and ETL (Extract, Transform, Load) processes. This process utilizes data processing libraries such as Python's pandas and NumPy. The collected data undergoes preprocessing, including the imputation of missing values ​​and the correction of outliers.

[0707] Based on preprocessed data, the server uses machine learning libraries such as scikit-learn and TensorFlow to construct a prediction structure. This allows the server to accurately predict future workloads and generate effective work plans. The work plan formulation utilizes flexible algorithms that can be applied to production management and personnel scheduling.

[0708] Along with the generated work plan, the server optimizes resource allocation and determines the placement of necessary personnel and equipment. This information is provided to the user via a terminal, and the user can view details through a dashboard or alert email. The user can also provide feedback on the presented plan and make modifications as needed.

[0709] During the work process, the server tracks progress in real time and, if it detects a discrepancy between the planned and actual progress, it quickly sends an alert to the user via their terminal. This feedback allows the user to immediately adjust their work plan.

[0710] As a concrete example, in the manufacturing industry, this system has been used to forecast demand and develop production plans, enabling efficient resource allocation. An example of a prompt message would be, "Please propose a method for optimizing demand forecasting and resource allocation in the manufacturing industry." This allows companies to improve operational efficiency and maintain their competitiveness.

[0711] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0712] Step 1:

[0713] The server connects to the company's database and automatically retrieves business-related information using APIs and ETL processes. The data collected includes historical transaction counts, resource usage, and sales data. Input is raw data retrieved from various databases, and output is a raw dataset for data preprocessing. This process is scheduled to run periodically.

[0714] Step 2:

[0715] The server performs preprocessing on the collected raw dataset. This preprocessing uses the Python pandas library to impute missing values ​​and correct outliers. Data normalization and formatting are also performed, organizing the data into a user-friendly format. Specifically, numerical data is scaled and categorical data is encoded. The input is the raw dataset obtained in step 1, and the output is the prepared dataset.

[0716] Step 3:

[0717] Based on a pre-configured dataset, a prediction structure is built using machine learning libraries such as scikit-learn and TensorFlow. This prediction structure is a model designed to predict future workload by learning past trends. The specific operation involves using the output dataset from step 2 as training data and applying algorithms to train the model. The input is a pre-processed dataset, and the output is the trained prediction model.

[0718] Step 4:

[0719] The server uses a predictive model to generate an optimal work plan to address future workloads. This plan aims to evenly distribute peak loads. Specifically, resource allocation is optimized through simulations using a generative AI model. The inputs are the predictive model and real-time status data, and the outputs are the work schedule and resource allocation plan.

[0720] Step 5:

[0721] The terminal receives output information from the server and notifies the user. Notification methods include visualization on a dashboard and sending alert emails. The user can review the provided information and provide feedback. Specifically, this involves accessing a user interface for reviewing, modifying, and approving plans. Inputs are work schedules and resource allocation plans, while output is user feedback.

[0722] Step 6:

[0723] The server tracks the progress of tasks in real time and issues alerts if predictions and actual results deviate. This allows users to quickly adjust their work plans. Specific operations include data collection from IoT devices and sensors, comparative analysis, and alert notifications. Input is real-time data, and output is updated work plans or alert notifications.

[0724] (Application Example 1)

[0725] 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".

[0726] To improve operational efficiency in logistics centers, it is necessary to collect diverse data and formulate appropriate work schedules and resource allocations. However, conventional systems perform these tasks individually, resulting in time-consuming data integration and analysis, making rapid decision-making difficult. To solve this problem, it is necessary to monitor the progress of operations in real time and make adjustments as needed.

[0727] 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.

[0728] In this invention, the server includes a device that automatically collects and preprocesses business information, a device that develops and trains a predictive model for business processing using the preprocessed information, and a device that monitors business progress in real time and proposes adjustments as needed. This enables the rapid and accurate formulation of business plans and the optimal allocation of resources.

[0729] "Operational information" refers to all data related to the operation of the logistics center, including work progress, resource usage, and past work history.

[0730] "Preprocessing" is the process of converting collected raw data into an analyzable format, including imputing missing values ​​and correcting outliers.

[0731] A "predictive model" refers to a mathematical or statistical model used to predict future workloads based on past business data.

[0732] A "work plan" is a detailed schedule and resource allocation plan for efficiently carrying out future business activities at a logistics center.

[0733] "Resources" refers to the personnel, equipment, and other necessary elements required to carry out the operations of a logistics center.

[0734] "Monitoring" refers to the process of tracking the progress of operations in real time and immediately detecting any anomalies.

[0735] "Adjustment" refers to actions taken to maximize operational efficiency by making necessary changes to work plans and resource allocations.

[0736] "Device" refers to the hardware and software components necessary to perform each of the above functions.

[0737] The system implementing this invention aims to improve the operational efficiency of a logistics center, with a server, terminals, and users playing key roles. The server automatically collects operational information and preprocesses the data using Python and related libraries. Specifically, it uses Pandas to impute missing values ​​and correct outliers. The preprocessed data is fed into a predictive model using TensorFlow to predict future workload.

[0738] The server generates an optimal work plan based on the predicted workload. This plan is created using optimization algorithms such as linear programming. The generated work plan is then pushed to the device via an application built with React Native and communicated to the user.

[0739] Users can review the plan presented through their terminal and make adjustments as needed. During actual work, the server uses AWS to monitor operations in real time and issues warnings if the predicted results deviate from actual results. This allows users to respond quickly and fine-tune their operations.

[0740] As a concrete example, to prevent congestion at logistics centers during the year-end period when consumption increases, it becomes possible to arrange additional personnel in advance. An example of a prompt message to the generated AI model is, "Based on past operational data of the logistics center, predict the workload for the next three months and propose the optimal staffing arrangement."

[0741] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0742] Step 1:

[0743] The server automatically collects business information from various data sources using APIs. It receives data from various databases and sensors as input, and outputs an integrated dataset. This integrated data forms the basis for subsequent analysis.

[0744] Step 2:

[0745] The server performs preprocessing on the collected dataset. Specifically, it uses the Pandas library to impute missing values ​​with the mean and correct outliers. It accepts an integrated raw dataset as input and outputs a clean, analyzable dataset.

[0746] Step 3:

[0747] The server uses a generative AI model based on TensorFlow to make predictions, utilizing pre-processed data to train the predictive model. A clean dataset is fed into the model as input, and the output predicts future workload. This allows for the prediction of business needs and peak times.

[0748] Step 4:

[0749] The server uses linear programming to generate an optimal workload plan based on the predicted workload. It receives the prediction results as input and creates a detailed schedule and resource allocation plan as output. This plan enables the optimal allocation of resources.

[0750] Step 5:

[0751] The device notifies the user of the work plan generated through an application built with React Native. It receives the work plan from the server as input and communicates the information to the user via push notifications as output. The user then uses this information to respond to the work situation.

[0752] Step 6:

[0753] Users review the plan presented via their terminal and make adjustments as needed. They review the work plan generated as input and make necessary changes or approvals as output. This allows for plan adjustments that are adapted to the actual situation on site.

[0754] Step 7:

[0755] The server uses AWS to monitor business progress in real time and issues warnings when discrepancies between actual results and forecasts are detected. It receives real-time data as input and notifies the user of warning alerts when discrepancies are detected as output. This allows users to take quick action.

[0756] 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.

[0757] This invention is a business efficiency system that takes into account the emotional state of the user. It not only collects and analyzes business data, but also provides a function to recognize the user's emotions in real time and adjust the business plan based on those emotions.

[0758] The server first connects to the company's business database and collects historical business processing data and resource usage. This data is then preprocessed to generate a standardized dataset. The data created here forms the basis for predictive models of business processes.

[0759] Next, the server uses machine learning algorithms to build a predictive model of business processes, thereby predicting future workloads. Based on these predictions, an optimal work schedule is generated, and resource allocation is planned to avoid peak workloads.

[0760] The emotion engine, a key feature of this invention, recognizes the user's emotional state in real time, and this emotional data is analyzed by a server. Based on the user's emotional data, the server evaluates the stress level and motivation level, and adjusts the workload and resource allocation as needed to reduce the user's workload and ensure appropriate resource allocation.

[0761] The generated work schedule and resource allocation are notified to the user via their terminal. The user can review this information and provide situation-appropriate feedback. The results of the emotion engine are also notified, allowing the user to understand their own emotional state.

[0762] Furthermore, by having the server monitor the progress of tasks in real time, if there is a discrepancy between predictions and actual results, a prompt alert is sent to the user via the terminal. Once the user approves, the server implements the proposed adjustments and immediately updates the task schedule and resource allocation.

[0763] As a concrete example, one customer support center implemented a system utilizing this emotion engine, which enabled them to regularly monitor the stress levels of their staff. When the emotion engine data indicated high stress levels, the server automatically took measures to reduce the workload, resulting in improved work efficiency while maintaining staff motivation. This allowed the company to simultaneously maintain service quality and improve employee satisfaction.

[0764] The following describes the processing flow.

[0765] Step 1:

[0766] The server connects to the business management system and automatically collects historical business processing data. This data includes the number of items processed, processing time, and resources used.

[0767] Step 2:

[0768] The server preprocesses the acquired data. This includes imputing missing values, detecting and correcting outliers, and normalizing the data.

[0769] Step 3:

[0770] The server uses pre-processed data to build predictive models for business processes using machine learning algorithms. Specifically, it performs trend analysis and learns seasonal patterns.

[0771] Step 4:

[0772] The server uses a predictive model to forecast future business processing loads. These forecasts include identifying daily or weekly load peaks.

[0773] Step 5:

[0774] The server generates an optimal work schedule based on the prediction results, planning for the equal use of resources during each work period.

[0775] Step 6:

[0776] The server plans resource allocation and optimally assigns the necessary personnel and equipment, thereby avoiding resource surpluses or shortages.

[0777] Step 7:

[0778] The terminal notifies the user of the generated work schedule and resource allocation. The notification includes a detailed schedule and forecast background.

[0779] Step 8:

[0780] The device detects the user's emotional state in real time via an emotion engine. The data is used to measure stress levels and motivation levels.

[0781] Step 9:

[0782] The server analyzes emotional data and readjusts workload if user stress levels are high. If necessary, it proposes a reallocation of personnel.

[0783] Step 10:

[0784] The server monitors the progress of operations in real time, and if there is a discrepancy between predictions and actual results, it sends an alert to the user via the terminal.

[0785] Step 11:

[0786] The user reviews the alert and approves any necessary adjustments to the work schedule or resource allocation. Based on the user's approval, the server automatically executes the adjustments.

[0787] (Example 2)

[0788] 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".

[0789] In today's work environment, predicting workload and allocating resources appropriately are difficult, hindering efficient operations. Furthermore, the lack of consideration for employees' emotional states leads to stress and decreased motivation, resulting in reduced work efficiency. Under these circumstances, there is a need to achieve both high work efficiency and employee satisfaction.

[0790] 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.

[0791] In this invention, the server includes means for automatically collecting and standardizing business data, means for building and training a predictive model of business processing based on the pre-processed data, and means for estimating future workload using the predictive model. This enables efficient business management and flexible business adjustments that take into account the emotional state of users.

[0792] "Business data" refers to information about the execution status of business processes and resource usage, and is used for business planning, analysis, and forecasting.

[0793] "Standardization" refers to the process of converting collected data into a unified format or standard, and is a technique used to maintain consistency in data analysis and model building.

[0794] A "predictive model" is a model that combines mathematical or computational methods to estimate future workload based on past data.

[0795] A "work plan" refers to an optimized schedule of tasks that takes into account the resources and time required to execute those tasks.

[0796] "Resource allocation" is the process of most effectively allocating available resources (such as personnel and equipment) to tasks with the aim of efficiently carrying out those tasks.

[0797] "Users" refers to individuals or organizations that operate the system, receive various information related to their work, and provide feedback.

[0798] "Emotional information" refers to data that indicates the user's psychological and physiological state, such as their stress level and motivation.

[0799] "Real-time monitoring" refers to the continuous tracking of business processes and user status in real time, providing information in real time.

[0800] A "warning" is a notification issued by the system when it detects an abnormal condition or a discrepancy between predictions and actual results, and is intended to prompt a quick response.

[0801] "Correction" refers to the act of improving and adjusting business plans and resource allocation when there is a discrepancy between predictions and the current situation.

[0802] This invention is a system that collects, analyzes, and predicts business data in order to improve operational efficiency. Each process is carried out through the collaboration of a server, terminals, and users.

[0803] First, the server connects to the company's database to collect data on business processes and resource usage. This operation utilizes techniques that access the database using SQL queries. The data is then aggregated on the server and cleansed and standardized using Python or other data processing languages. This data preparation creates the dataset that forms the basis of the predictive model.

[0804] Next, the server uses a machine learning platform (e.g., scikit-learn or TensorFlow) to build a predictive model for business processes. This model allows for the estimation of future workload and the planning of optimal resource allocation.

[0805] Furthermore, a crucial aspect of this system is the real-time recognition of the user's emotional state. Wearable devices and applications used by the user collect data such as heart rate, sweating, and facial expressions, and send it to a server. The server analyzes this data and quantifies the user's stress level and motivation.

[0806] The terminal is a device that provides users with notifications and alerts from the server. On the terminal, users can check their work schedule and proposed adjustments, and input feedback on the spot. Notifications are provided as text messages and pop-up alerts.

[0807] As a concrete example, one customer support center adjusts workloads based on the emotional state of its staff. For instance, if emotional analysis determines that a particular staff member is experiencing high stress levels, the server automatically takes measures to reduce their workload. This allows for flexible resource allocation through schedule adjustments, enabling both improved operational efficiency and increased employee satisfaction.

[0808] An example of a prompt is: "Consider the user's emotional state and suggest ways to adjust next week's work schedule and optimize resource allocation." The system will then generate an optimized solution and propose it to the user.

[0809] As described above, the present invention provides a mechanism for improving work efficiency and appropriately managing the emotional state of users, and is expected to be used in a variety of work environments.

[0810] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0811] Step 1:

[0812] The server connects to the business database. It retrieves historical business processing data and resource usage information from the database as input. The server then collects the data and performs cleansing and standardization processes. It converts the raw data received from the database into a consistent format and outputs it as a dataset ready for the predictive model. Specifically, this involves extracting necessary information using SQL queries.

[0813] Step 2:

[0814] The server uses machine learning libraries to build a predictive model of business processes based on a dataset. The server uses a prepared dataset as input. It applies machine learning algorithms (e.g., regression analysis, time series forecasting) to output a model that estimates future workload. This model establishes the foundation for developing business plans. A concrete example of this is the execution of a script using Python.

[0815] Step 3:

[0816] The server creates a work plan and resource allocation based on the output from a predictive model. Predicted workload data is used as input. The server generates a work schedule to reduce inefficient workload peaks and optimize resource allocation. This schedule is output in a way that supports the smooth execution of operations. Specifically, this involves the application of a scheduling algorithm.

[0817] Step 4:

[0818] Users record their emotional state using provided wearable devices and apps, and send this data to a server via their devices. Emotional data is input as heart rate and skin electrical responses. The server analyzes this data, evaluates stress levels, quantifies motivation, and outputs the results. Specific actions include data transmission and app operation.

[0819] Step 5:

[0820] The terminal notifies the user of the work schedule and sentiment analysis results received from the server. The input consists of analysis results and work plans from the server. The terminal provides this information to the user, allowing them to check the situation immediately. The notified information is output as a basis for user confirmation and feedback. Specific actions include displaying alerts and sending messages.

[0821] Step 6:

[0822] The server monitors the progress of tasks in real time and proposes adjustments via terminals as needed. It processes data on the progress of tasks as input. The server analyzes the difference between predictions and actual results from this input and outputs necessary alerts and adjustment proposals to the user. Specifically, it integrates with the monitoring system and performs data analysis.

[0823] Step 7:

[0824] The user approves or modifies the proposed adjustments via their terminal and provides feedback, which is then sent to the server. Receiving user instructions as input, the server modifies the work plan and resource allocation. This creates an optimal work environment that reflects the user's needs and outputs it as an actionable plan. Specifically, this involves filling out a feedback form.

[0825] (Application Example 2)

[0826] 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".

[0827] In modern households, an individual's emotional state significantly impacts the efficiency of daily life. However, a system that effectively manages this and optimizes household tasks and daily schedules still lacks a solution. Therefore, there is a need for flexible scheduling adjustments that take into account the well-being of all family members.

[0828] 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.

[0829] In this invention, the server includes means for automatically collecting and preprocessing business data, means for building and training a predictive model for business processing based on the preprocessed data, and means for adjusting household tasks and daily schedules based on an individual's emotional state. This enables flexible schedule adjustments that reflect the emotional state of family members.

[0830] "Business data" refers to a collection of information related to business activities, and is a general term for data including past business processing data and resource usage status.

[0831] "Preprocessing" refers to the process of performing necessary modifications on collected raw data, including tasks such as data standardization and noise reduction.

[0832] A "predictive model" is a mathematical model built using machine learning algorithms to derive new insights from data, and it estimates future trends in business processes.

[0833] A "work schedule" is a plan created based on the predicted workload, and it defines the time allocation necessary to optimally carry out work activities.

[0834] "Resource allocation" refers to the appropriate distribution of resources such as people, materials, money, and information in order to carry out tasks efficiently.

[0835] "Monitoring" refers to activities that involve monitoring the progress of work in real time and understanding the status of that progress.

[0836] "Adjustment" refers to proposing and implementing changes to planned schedules and resource allocations as necessary.

[0837] "Emotional state" refers to an individual's psychological state and is used to evaluate indicators such as stress levels and feelings of well-being.

[0838] "Household tasks" refer to everyday tasks performed at home, including activities related to daily life such as cleaning, cooking, and shopping.

[0839] To realize this invention, a system involving three main parties—a server, a terminal, and a user—is necessary. The server collects various data from within the home, preprocesses it, and then builds a predictive model using a machine learning algorithm. Specifically, the server integrates various business and emotional data from within the home and predicts future task loads based on this data.

[0840] The server uses emotion recognition APIs (such as EmotionAPI) to analyze the user's emotional state and processes the emotional data in real time. Based on this analysis, it adjusts the allocation of household task schedules. It also uses machine learning platforms such as TensorFlow to predict the behavioral patterns of the entire family and create an optimal daily schedule.

[0841] The device delivers various notifications to the user and provides suggested task schedules and emotional state feedback on the electronic screen. Based on this feedback, the user can understand their emotional state and request adjustments from the system as needed.

[0842] When performing various tasks within the home, users receive suggestions based on emotional data provided by the server, which helps them manage their family's daily life smoothly. For example, if a user is tired in the morning, the server might suggest, "You seem particularly tired today. How about preparing a hot coffee and a slightly larger, more nutritious breakfast?"

[0843] An example of a prompt message might be: "Based on the user's emotional data, suggest an optimal morning routine for when their stress level is high."

[0844] In this way, the present invention makes it possible to optimize the lives of individuals and families as a whole through the recognition of emotions within the home.

[0845] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0846] Step 1:

[0847] The server collects business and emotional data from various sensors and devices within the home. Inputs include emotional data acquired from cameras and microphones, and environmental data from temperature and humidity sensors. At this stage, the data is collected in raw format and stored in a database.

[0848] Step 2:

[0849] The server preprocesses the collected raw data, particularly by removing noise and standardizing it. The input is raw data, and the output is a clean, consistent dataset. This process includes imputing missing values ​​and removing outliers.

[0850] Step 3:

[0851] The server builds and trains a predictive model based on preprocessed data. Specifically, it uses a machine learning algorithm based on TensorFlow. The input is the preprocessed data, and the output is the predictive model. The model learns family emotional tendencies and patterns of daily tasks to predict future situations.

[0852] Step 4:

[0853] The server uses a built predictive model to forecast future household task loads. Inputs are the predictive model and current sentiment data; output is the future task load forecast. This provides information useful for improving the efficiency of daily life.

[0854] Step 5:

[0855] The server adjusts the household task schedule considering the user's emotional state and notifies the user of the suggestions via the terminal. Inputs are future task load predictions and emotional data, while output is the suggested schedule. In this step, the suggestions are generated by a generative AI model, and prompt statements are also referenced.

[0856] Step 6:

[0857] Users review the proposals from their devices and approve or modify the system's schedule by providing feedback. Here, the input is the proposed schedule, and the output is the user's feedback. Specifically, this involves confirmation and response on a smartphone or tablet.

[0858] Step 7:

[0859] The server receives user feedback and updates task schedules and resource allocations as needed. These updates are reflected in the system in real time, resulting in an optimized home task schedule as output.

[0860] 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.

[0861] 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.

[0862] 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.

[0863] 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.

[0864] 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.

[0865] 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.

[0866] 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.

[0867] 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.

[0868] 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."

[0869] 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.

[0870] 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.

[0871] 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.

[0872] 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.

[0873] 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.

[0874] 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.

[0875] 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.

[0876] 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.

[0877] 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.

[0878] 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.

[0879] 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.

[0880] 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.

[0881] The following is further disclosed regarding the embodiments described above.

[0882] (Claim 1)

[0883] A means for automatically collecting and pre-processing business data,

[0884] A method for building and training a predictive model for business processes based on pre-processed data,

[0885] A method for predicting future business processing load using a predictive model,

[0886] A means for generating a work schedule based on prediction results,

[0887] A means of optimally allocating resources based on the work schedule,

[0888] A means of notifying the user of the generated schedule and resource allocation,

[0889] A means to monitor the progress of work in real time and propose adjustments as needed,

[0890] A system that includes this.

[0891] (Claim 2)

[0892] The system according to claim 1, comprising means for detecting discrepancies between predictions and actual results based on the results of monitoring business progress and issuing alerts.

[0893] (Claim 3)

[0894] The system according to claim 1, comprising means for automatically re-executing user-approved adjustments and modifying work schedules and resource allocations.

[0895] "Example 1"

[0896] (Claim 1)

[0897] A means of automatically acquiring business-related information and organizing the data,

[0898] A means of constructing a predictive structure for business processes based on pre-processed information and turning it into knowledge,

[0899] A means of predicting future workload using a predictive structure,

[0900] A means for generating a business plan based on prediction results,

[0901] A means of optimally allocating resources based on the business plan,

[0902] A means of notifying users of the generated plan and resource allocation,

[0903] A means to track the progress of work in real time and propose adjustments as needed,

[0904] A system that includes this.

[0905] (Claim 2)

[0906] The system according to claim 1, comprising means for recognizing the discrepancy between predictions and actual results based on the results of tracking business progress and sending a warning.

[0907] (Claim 3)

[0908] The system according to claim 1, comprising means for automatically re-executing adjustments approved by the user and modifying the work plan and resource allocation.

[0909] "Application Example 1"

[0910] (Claim 1)

[0911] A device that automatically collects and preprocesses business information,

[0912] A device that develops and trains a predictive model for business processes using pre-processed information,

[0913] A device that uses a predictive model to predict future workload,

[0914] A device that generates a business plan based on prediction results,

[0915] A device that optimally allocates resources based on a business plan,

[0916] A device that notifies the user of the generated plan and resource allocation,

[0917] A device that monitors the progress of work in real time and proposes adjustments as needed,

[0918] A data analysis device using an application to support the operational efficiency of logistics centers,

[0919] A system that includes this.

[0920] (Claim 2)

[0921] The system according to claim 1, comprising a device that detects discrepancies between predictions and actual results based on the results of monitoring business progress and issues a warning.

[0922] (Claim 3)

[0923] The system according to claim 1, comprising a device that automatically re-executes adjustments approved by the user and modifies the work plan and resource allocation.

[0924] "Example 2 of combining an emotion engine"

[0925] (Claim 1)

[0926] A means of automatically collecting and standardizing business data,

[0927] A method for building and training a predictive model for business processes based on pre-processed data,

[0928] A method for estimating future workload using predictive models,

[0929] A means of creating a business plan based on the prediction results,

[0930] Means for optimally allocating resources based on a business plan,

[0931] A means of notifying the user of the generated plan and resource allocation,

[0932] A means of recognizing and analyzing user emotional information in real time,

[0933] A means to adjust the workload according to emotional state,

[0934] A means to monitor the progress of work in real time and propose corrections as needed,

[0935] A system that includes this.

[0936] (Claim 2)

[0937] The system according to claim 1, comprising means for detecting discrepancies between predictions and actual results based on the results of monitoring business progress and issuing warnings.

[0938] (Claim 3)

[0939] The system according to claim 1, comprising means for automatically re-executing user-approved modifications and changing the work plan and resource allocation.

[0940] "Application example 2 when combining with an emotional engine"

[0941] (Claim 1)

[0942] A means for automatically collecting and pre-processing business data,

[0943] A method for building and training a predictive model for business processes based on pre-processed data,

[0944] A method for predicting future business processing load using a predictive model,

[0945] A means for generating a work schedule based on prediction results,

[0946] A means of optimally allocating resources based on the work schedule,

[0947] A means of notifying users of the generated schedule and resource allocation,

[0948] A means to monitor the progress of work in real time and propose adjustments as needed,

[0949] A means of adjusting household tasks and daily schedules based on an individual's emotional state,

[0950] A system that includes this.

[0951] (Claim 2)

[0952] The system according to claim 1, comprising means for detecting discrepancies between predictions and actual results based on the results of monitoring business progress and issuing warnings.

[0953] (Claim 3)

[0954] The system according to claim 1, comprising means for automatically re-executing adjustments approved by the user and modifying the work schedule and resource allocation. [Explanation of symbols]

[0955] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for automatically collecting and pre-processing business data, A method for building and training a predictive model for business processes based on pre-processed data, A method for predicting future business processing load using a predictive model, A means for generating a work schedule based on prediction results, A means of optimally allocating resources based on the work schedule, A means of notifying the user of the generated schedule and resource allocation, A means to monitor the progress of work in real time and propose adjustments as needed, A system that includes this.

2. The system according to claim 1, comprising means for detecting discrepancies between predictions and actual results based on the results of monitoring business progress and issuing alerts.

3. The system according to claim 1, comprising means for automatically re-executing user-approved adjustments and modifying work schedules and resource allocations.

Images