System

Abstract

A system is provided.SOLUTION: A system including means for collecting actual business data, means for generating a digital twin in a virtual office environment based on the collected data, means for executing the generated digital twin, means for collecting an operation record of the business executed by the digital twin, means for analyzing the business based on the collected operation record, means for causing the digital twin to learn a new business based on an analysis result, and means for proposing an efficiency improvement method based on the business data.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] In the real world, business processes require a lot of time and effort, and there are limitations to how efficiently they can be carried out. It is also difficult to find specific ways to improve business efficiency. Therefore, there is a demand for systems that can accomplish more tasks in the same amount of time. [Means for solving the problem]

[0005] This invention is a system that collects real-world business data and generates a digital twin in a virtual office environment. The digital twin performs real-world tasks and collects records of those tasks. The system analyzes the tasks based on the collected records and provides information to improve efficiency the next time a similar task is performed. The system can also teach the digital twin new work methods based on suggested improvements in efficiency. This allows the system to process more than twice as much work in the same amount of time.

[0006] "Real-world business data" refers to information, operation history, documents, etc. related to business conducted in the real world.

[0007] A "virtual office environment" refers to a simulation environment built on a computer system that mimics a real office.

[0008] "Digital twin" refers to a digital model created in a virtual office environment to mimic real-world operations.

[0009] "Means of performing business operations" refers to the functions and processes that a digital twin performs by imitating real-world operations.

[0010] "Operation records" refer to data that records in detail the operation history and work content when a digital twin performs a task.

[0011] "Means for analyzing work" refers to algorithms or software that analyzes performance records and identifies patterns and opportunities for efficiency improvements.

[0012] "Means of business learning" refers to the means of inputting new business processes and efficient work methods into the digital twin based on past analysis results.

[0013] "Means for proposing methods for improving efficiency" refers to means for presenting specific improvement measures to users for improving the efficiency of their work based on the analysis. [Brief explanation of the drawings]

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

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

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

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

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

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

[0020] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0022] [First embodiment]

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

[0024] 1, a 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 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

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

[0027] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the 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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0031] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

[0032] The storage 32 stores a data generation model 58 and an 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 process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

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

[0035] The present invention is a system for generating a digital twin in a virtual office environment based on real-world business data, thereby improving business efficiency. The processing content of the program of this system is explained below in natural language.

[0036] Program processing overview

[0037] 1. Data collection and digital twin generation

[0038] User: Logging in to the system is a fundamental step in protecting and managing business data.

[0039] Server: Receives the user's authentication information and performs authentication. If authentication is successful, grants the user access rights and prepares to collect business data.

[0040] User: Inputs business data. This refers to data such as operation history, document uploads, and business details.

[0041] Server: Generates a digital twin based on collected business data, including analysis and modeling of business processes.

[0042] 2. Business execution and operation records

[0043] Terminal: The digital twin is placed in a virtual office environment, and users can view it through a user interface.

[0044] Digital twin: Performs actual tasks, such as sorting documents, entering data, and handling initial inquiries, mimicking the routine tasks that users normally perform.

[0045] Server: Collects daily operational records of the digital twin, which are stored as detailed logs for later analysis.

[0046] 3. Business analysis and learning

[0047] Server: Analyzes operations based on the digital twin's operational records. Analyzes past operational records to identify operational patterns and opportunities for efficiency improvements.

[0048] Server: Extracts the likely next occurrence of the same task. Based on this information, the digital twin learns new business processes.

[0049] Server: Input new business knowledge into the digital twin and expand the scope of business. This step will further improve the efficiency of the next business operation.

[0050] 4. Proposals for improving efficiency

[0051] Server: Analyze business data in detail to identify areas that take particularly long. For example, automate data entry, automatically suggest file names, etc.

[0052] Server: Proposes ways to improve efficiency. Presents specific improvement measures and efficiency techniques to the user. This information is then used to train the digital twin.

[0053] Server: By repeating the above steps, the digital twin gradually improves its business processing capabilities.

[0054] Specific examples

[0055] Example 1: Improving efficiency of document management

[0056] 1. Data collection and digital twin generation

[0057] User: Inputs document management data into the system.

[0058] Server: Collects business data such as document classification and storage location input, and generates a digital twin based on that data.

[0059] 2. Business execution and operation records

[0060] Digital twin: Performs document classification and storage location entry tasks.

[0061] Server: Records the digital twin's behavior and collects the logs.

[0062] 3. Business analysis and learning

[0063] Server: Analyzes work patterns based on operation records and teaches the digital twin how to do the next job.

[0064] 4. Proposals for improving efficiency

[0065] Server: Conducts detailed analysis of document management data and proposes specific methods for improving efficiency, such as automatically suggesting file names and setting classification rules.

[0066] Example 2: Improving the efficiency of inquiry response operations

[0067] 1. Data collection and digital twin generation

[0068] User: Inputs data for inquiry handling work.

[0069] Server: Generates a digital twin based on past response history and FAQs.

[0070] 2. Business execution and operation records

[0071] Digital Twin: Respond to initial inquiries based on FAQs.

[0072] Server: Collects the digital twin's response as a log.

[0073] 3. Business analysis and learning

[0074] Server: Analyzes operational records and teaches the digital twin new knowledge for the next inquiry response.

[0075] 4. Proposals for improving efficiency

[0076] Server: Based on the analysis results of inquiry response operations, it proposes, for example, automatic updates to FAQs and revisions to response classifications.

[0077] These examples allow users to use the system efficiently and improve the quality and speed of their work.

[0078] The processing flow will be explained below.

[0079] Data collection and digital twin generation

[0080] Step 1:

[0081] User: Log in to the system, enter login information and wait for authentication.

[0082] Step 2:

[0083] Server: Receives user authentication information and performs authentication. If successful, grants access to the user.

[0084] Step 3:

[0085] User: Inputs business data, such as operation history, document uploads, and business details.

[0086] Step 4:

[0087] Server: Organizes collected business data and stores it in a database. Prepares to generate a digital twin based on this data.

[0088] Step 5:

[0089] Server: Analyzes business processes and creates a digital twin model that mimics those processes. Sets the necessary data in the digital twin and performs a simulation of its operation.

[0090] Business execution and operation records

[0091] Step 1:

[0092] Terminal: The digital twin is placed in a virtual office environment, allowing users to view it through a user interface.

[0093] Step 2:

[0094] Digital Twin: Perform routine tasks in a virtual office environment, such as document sorting, data entry, and initial response to inquiries.

[0095] Step 3:

[0096] Server: Collects and stores a detailed record of the digital twin's daily operations.

[0097] Business Analysis and Learning

[0098] Step 1:

[0099] Server: Analyzes business processes based on collected operational records. Analyzes past operational records to identify patterns and trends.

[0100] Step 2:

[0101] Server: Extracts tasks that are likely to occur again and has the digital twin learn those tasks.

[0102] Step 3:

[0103] Server: Inputs new business knowledge into the digital twin, expanding its scope of operations, and performs learning processes to improve the digital twin's business processing capabilities.

[0104] Efficiency proposals

[0105] Step 1:

[0106] Server: Further analyze the details of your business data to identify areas that are particularly time-consuming.

[0107] Step 2:

[0108] Server: Proposes efficiency improvements and presents specific improvement measures and efficiency methods to users.

[0109] Step 3:

[0110] Server: Trains the digital twin to work in new ways based on efficiency suggestions, for example adding new processes such as auto-completion of input formats and auto-classification of data.

[0111] This allows users to process more than twice as much work in the same amount of time, improving work efficiency.

[0112] Example 1

[0113] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0114] There is a demand for systems that can carry out business efficiently and accurately based on real business data. However, currently, there is a lack of tools to streamline and optimize business processes, and a lot of time and effort is spent on manual data entry and classification. As a result, there is an issue of reduced business efficiency and difficulty in improving productivity.

[0115] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0116] In this invention, the server includes: means for a user to enter authentication information and log in to the system; means for performing user authentication and collecting business data; means for generating a digital twin using an analysis tool based on the collected business data; means for placing the generated digital twin in a virtual office environment and providing a user interface; means for the digital twin to imitate and execute real-world business operations; means for collecting operation records of the digital twin in real time and storing them in a database; means for analyzing the operation record data and identifying business patterns; means for having the digital twin learn new business processes to improve business efficiency in the next business operation; and means for proposing methods for improving business efficiency based on the analysis results, thereby enabling business efficiency improvement and optimization.

[0117] "User authentication" is the process of verifying a user's identity when accessing a system. Authentication information includes a user ID and password.

[0118] "Business data" refers to information related to business processes, and includes, for example, operation history, document information, input data, and the like.

[0119] A "digital twin" is a digital model that recreates real-world business processes and systems in a virtual environment, with the aim of replicating and executing business processes.

[0120] A "virtual office environment" is a workspace that digitally recreates an actual office environment, and is a virtual space in which a digital twin is placed.

[0121] A "user interface" is an interface that allows a user to directly interact with the system, allowing them to operate and monitor the digital twin.

[0122] "Operation records" refer to detailed operation logs and execution histories of the tasks performed by the digital twin. These are collected in real time and stored in a database.

[0123] "Analysis tools" generally refer to software and algorithms that process and analyze collected data, and are used for digital twin generation and business analysis.

[0124] "Business patterns" refer to the characteristic flow of business execution processes and procedures obtained by analyzing business data.

[0125] A "business process" refers to a series of procedures and operations required to carry out a specific task, and new business processes are learned by the digital twin.

[0126] "Efficiency methods" refer to specific techniques and proposals for reducing work time and costs and improving productivity.

[0127] MODE FOR CARRYING OUT THE INVENTION

[0128] The present invention provides a system for generating a digital twin in a virtual office environment based on real-world business data, thereby improving business efficiency. This system is implemented using multiple hardware and software components.

[0129] Data Collection and User Authentication

[0130] 1. User: First logs in to the system, entering their user ID and password as identification information to begin the authentication process.

[0131] 2. Server: Receives user authentication information and compares it with the database. A high-performance server (e.g., Dell PowerEdge R740) is used for this. If authentication is successful, the user is granted access rights and business data can be collected.

[0132] Digital Twin Generation

[0133] 3. User: Inputs business data, specifically, uploads operation history, document information, business details, etc. to the system.

[0134] 4. Server: Generates a digital twin based on the collected data using data analysis tools (e.g., Python's Pandas library) and digital twin generation software (e.g., Ansys Twin Builder). The analyzed data is built as a virtual model and deployed in a virtual office environment.

[0135] Business execution and operation recording

[0136] 5. Terminal: The digital twin is placed in a virtual office environment and a user interface is provided (e.g., Microsoft® Azure® Digital Twins). The user can use this interface to observe and manipulate the behavior of the digital twin in real time.

[0137] 6. Digital Twin: Mimics real-world business processes and performs tasks such as document sorting, data entry, and handling inquiries.

[0138] 7. Server: Collects the digital twin's operational records in real time and stores them in a database. These records are used for analysis.

[0139] Business Analysis and Learning

[0140] 8. Server: Analyze business patterns based on collected operational records. Use analysis tools to identify areas where efficiency can be improved.

[0141] 9. Server: Uses machine learning models (e.g., TENSORFLOW®) to teach the digital twin new processes that will be useful for the next job.

[0142] Efficiency proposals

[0143] 10. Server: Analyzes business data in detail and proposes ways to improve efficiency. For example, it suggests specific improvement measures such as automating data entry and automatically suggesting file names.

[0144] 11. Server: Reflects the proposed efficiency improvements in the digital twin and optimizes the next business process.

[0145] Specific examples

[0146] Example 1: Improving efficiency of document management

[0147] User: Inputs document management data into the system. Specifically, uploads the Excel file "Business Data.xlsx."

[0148] Server: Uses data analysis tools to automate document classification and storage location, generating a digital twin that is then placed in a virtual office environment.

[0149] Example 2: Improving the efficiency of inquiry response operations

[0150] User: Inputs data related to inquiries into the system. Specifically, inputs past response history and FAQ data.

[0151] Server: A digital twin is generated based on the collected data and placed in a virtual office environment. The digital twin responds to initial inquiries and records the results on the server.

[0152] Prompt Sentence Examples

[0153] "Please explain the steps to input business data and generate a digital twin."

[0154] "Please give us a concrete example of how a digital twin can be used to streamline document management operations."

[0155] "Please explain how a digital twin can help improve the efficiency of your inquiry response operations."

[0156] As described above, the present invention effectively collects and analyzes business data and optimizes business processes using digital twins, thereby achieving significant improvements in business efficiency and labor savings.

[0157] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0158] Step 1:

[0159] User: Log in to the system. Enter your user ID and password and click the "Login" button.

[0160] Input: User ID, Password

[0161] Output: Authentication token, access granted

[0162] Specific operation: The user enters the user ID "user123" and password "password123" on the system login screen, for example, and clicks the "Login" button.

[0163] Step 2:

[0164] Server: Receives the user's authentication information and checks it against a database.

[0165] Input: User ID, Password

[0166] Output: Authentication result (success / failure), authentication token

[0167] Specific operation: The server receives the user ID "user123" and password "password123", checks it against the database, and if authentication is successful, generates a token and grants access rights to the user.

[0168] Step 3:

[0169] User: Input business data. For example, upload the "BusinessData.xlsx" file.

[0170] Input: Business data file (e.g., businessdata.xlsx)

[0171] Output: Business data collection

[0172] Specific operation: After logging in, click the "Upload business data" button from the dashboard, select "Business data.xlsx" in the file selection dialog, and upload it.

[0173] Step 4:

[0174] Server: Generates a digital twin based on collected business data.

[0175] Input: Business data file (e.g., businessdata.xlsx)

[0176] Output: Digital twin model

[0177] How it works: The server uses Python's Pandas library to analyze business data and uses Ansys Twin Builder to generate a digital twin model.

[0178] Step 5:

[0179] Terminal: Places the digital twin in a virtual office environment and provides a user interface.

[0180] Input: Digital twin model

[0181] Output: Digital twin on UI

[0182] Specific operation: The server deploys the generated digital twin model to Microsoft Azure Digital Twins and displays it in the user interface.

[0183] Step 6:

[0184] Digital Twin: Imitating and executing real-world operations.

[0185] Input: Business process data

[0186] Output: Work results, operation records

[0187] Specific operations: The digital twin performs document classification, data entry, inquiry response, etc. in a virtual environment, generating business results and action records.

[0188] Step 7:

[0189] Server: Collects digital twin operation records in real time and stores them in a database.

[0190] Input: Digital twin operation record

[0191] Output: Action record database

[0192] Specific operation: The server receives the operation logs recorded by the digital twin and stores them in a database in real time.

[0193] Step 8:

[0194] Server: Analyzes business patterns based on collected operation records.

[0195] Input: Action Record Database

[0196] Output: Business analysis results

[0197] Specific operation: The server analyzes the operation record data using an analysis tool (e.g., Python DataFrame) and identifies business patterns.

[0198] Step 9:

[0199] Server: Trains the digital twin to learn new business processes.

[0200] Input: Business analysis results, new business processes

[0201] Output: Trained digital twin

[0202] Specific operation: Based on the analysis results, the server uses a machine learning model (e.g., TensorFlow) to teach the digital twin new business processes.

[0203] Step 10:

[0204] Server: Conducts detailed analysis of business data and proposes methods for improving efficiency.

[0205] Input: Business data, operation records

[0206] Output: Efficiency proposals

[0207] Specific operation: The server performs detailed data analysis and generates efficiency suggestions, such as "Automating data entry steps can save two hours per day."

[0208] Step 11:

[0209] Server: Reflects the proposed efficiency measures in the digital twin and optimizes the next business process.

[0210] Input: Efficiency proposal

[0211] Output: Optimized business processes

[0212] Specific operation: The server applies the proposed efficiency methods to the digital twin model, allowing the digital twin to learn new business processes and prepare for the next business operation.

[0213] (Application example 1)

[0214] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0215] Traditional production line management in factories requires a great deal of time and effort to improve efficiency and optimization, and efficiency often declines due to the heavy reliance on manual human labor. Furthermore, insufficient analysis and learning based on past operational records can result in waste due to the repetition of the same tasks. Furthermore, there are limited means of immediately applying efficiency suggestions, requiring flexible responses.

[0216] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0217] In this invention, the server includes: means for collecting real-world business data; means for generating a digital twin in a virtual work environment based on the collected data; means for the generated digital twin to execute business operations; means for collecting operation records of the business operations executed by the digital twin; means for analyzing the business operations based on the collected operation records; means for the digital twin to learn new business operations based on the analysis results; means for proposing methods for improving efficiency based on the business data; means for collecting business data of a production line and generating a digital twin; means for the digital twin to imitate production line operations and analyze the operation records to learn the optimal production process; and means for immediately applying the efficiency proposals to the production line. This enables accurate business analysis based on past operation records and specific proposals for improving efficiency, thereby significantly improving the efficiency of the production line.

[0218] "Real-world business data" refers to all data related to work that occurs in real-world environments such as factories and offices. Examples include production line operation data and employee operation records.

[0219] A "virtual work environment" is a digital space that virtually recreates an actual work environment. This eliminates physical constraints, making it easier to perform simulations and optimizations.

[0220] A "digital twin" is a virtual model created based on real-world business data. This model performs the same functions as real systems and business processes, enabling simulation and analysis.

[0221] "Operation records" are historical data of the tasks and actions performed by the digital twin, which are used to evaluate and optimize operations.

[0222] "Means for analyzing work" are methods and techniques for identifying work patterns and opportunities for efficiency improvement based on collected operational records.

[0223] "Means of learning new business" refers to methods and technologies that allow the digital twin to incorporate new business processes and improvement methods, enabling it to operate more efficiently the next time the business is executed.

[0224] "Means for proposing ways to improve efficiency" refers to methods and technologies for analyzing business data, identifying areas for improvement, and making specific proposals for improving efficiency.

[0225] "Production line business data" refers to all data related to the production process, including, for example, the operating status of machines, production volume, and quality inspection results.

[0226] A "production process" is a series of steps to manufacture a product on a production line, including material input, processing, assembly, inspection, and shipping.

[0227] "Means for immediately applying efficiency proposals to the production line" refers to technology that uses digital twins to immediately reflect proposed efficiency methods on the actual production line, enabling rapid improvements.

[0228] The present invention is a digital twin system aimed at improving the efficiency of production lines, and specific embodiments are described below.

[0229] System configuration

[0230] This system, which consists of a server, terminals, and users, has the following main functions:

[0231] 1. Data Collection

[0232] The server collects real-time operational data from the production line through sensors and data input devices, including machine operation data, worker behavior data, and quality inspection results.

[0233] 2. Digital Twin Creation

[0234] The server uses the collected data to create a digital twin in a virtual work environment: a virtual model of the real production line that can accurately mimic its behavior.

[0235] 3. Execution of Business

[0236] The generated digital twin can then be used to virtually execute production line operations via a terminal, recreating the actual production process in a virtual environment.

[0237] 4. Collecting Operational Records

[0238] The server collects records of operations performed by the digital twin, including detailed operational procedures and results.

[0239] 5. Business Analysis

[0240] The server analyzes the collected activity records to identify opportunities for efficiency. This analysis identifies historical patterns and identifies areas for improvement.

[0241] 6. Learning a new job

[0242] Based on the analysis results, the server teaches the digital twin new business processes, allowing it to operate more efficiently the next time the business is executed.

[0243] 7. Efficiency proposals

[0244] The server uses business data to propose ways to improve efficiency, including optimizing production processes, changing processes, and revising work procedures. These proposals are immediately applied to the production line, resulting in rapid improvements.

[0245] Hardware and Software

[0246] This system uses the following hardware and software:

[0247] Hardware: sensors, data input devices, network connection devices, servers

[0248] Software: Software for generating digital twin models, software for data analysis (e.g., Python, Scikit-learn), software for proposing efficiency improvements

[0249] Specific examples

[0250] For example, in a factory's parts assembly line, a server collects operational data from each work station and generates a digital twin based on that data. This digital twin simulates actual assembly work in a virtual environment and analyzes the operational records. Based on the analysis results, new work procedures and process changes are proposed and implemented immediately, significantly improving the efficiency of the assembly line.

[0251] Example prompt sentence:

[0252] Create a virtual environment to optimize your production line and create a digital twin based on operational data. Analyze the collected data, list specific efficiency improvements, and provide steps to implement them.

[0253] As described above, the digital twin system according to the present invention realizes highly accurate efficiency improvements on production lines.

[0254] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0255] Step 1:

[0256] The server collects operational data related to the production line from each work station in the factory through sensors and data input devices. Inputs include machine operation data, worker behavior data, and quality inspection results. This data is sent to the server in real time and saved. The data is organized in JSON format and stored in a database.

[0257] Step 2:

[0258] The server generates a digital twin in a virtual work environment based on the collected business data. The business data collected in step 1 is used as input. Digital twin model generation software is used to create a virtual model of the real production line from that data. This model mimics the real operation in the virtual environment. The output is a digital twin model.

[0259] Step 3:

[0260] The terminal uses the generated digital twin to virtually execute production line operations. The digital twin model is used as input. The production process is reproduced in the virtual environment and operation data is collected. During this process, the digital twin operates in the same way as in reality. The output is an operation log of the digital twin.

[0261] Step 4:

[0262] The server collects and analyzes the operational records of the tasks performed by the digital twin. The operational logs generated in step 3 are used as input. Data analysis software (e.g., Python, Scikit-learn) is used to analyze past operational records and identify patterns and potential for efficiency improvements. The output is the analysis results.

[0263] Step 5:

[0264] The server trains the digital twin to learn new business processes based on the analysis results of the operation records. The analysis results from step 4 are used as input. New business knowledge is input into the digital twin using a machine learning algorithm. The output is a new digital twin model that has completed learning.

[0265] Step 6:

[0266] The server proposes efficiency improvement methods based on business data. The inputs used are the analysis results and the trained digital twin model. Specific improvement measures and efficiency methods are generated using software for proposing efficiency improvements. For example, optimal production processes and revisions to work procedures are proposed. The output is efficiency improvement proposals.

[0267] Step 7:

[0268] The server immediately applies the efficiency improvement proposals to the production line. The efficiency improvement proposals obtained in step 6 are used as input. Specifically, parameters are changed and new work procedures are implemented, and these are reflected in the production line. The output is an efficient new employee production line.

[0269] Through the above steps, the digital twin system of the present invention achieves high-precision efficiency and optimization of production lines.

[0270] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0271] This invention is a system for generating a digital twin in a virtual office environment based on real-world business data, thereby improving business efficiency. Furthermore, by combining it with an emotion engine that recognizes user emotion data, this system achieves more comprehensive business efficiency. The processing content of the program for this system is explained below in natural language.

[0272] Program processing overview

[0273] 1. Data collection and digital twin generation

[0274] User: Log in to the system, enter login information and wait for authentication.

[0275] Server: Receives user credentials and performs authentication. If successful, grants access to the user.

[0276] User: Inputs business data, such as operation history, document uploads, and business details.

[0277] Server: Organizes collected business data and stores it in a database. Prepares to generate a digital twin based on this data.

[0278] Server: Analyzes business processes and creates a digital twin model that mimics those processes. Sets the necessary data in the digital twin and performs a simulation of its operation.

[0279] 2. Business execution and operation records

[0280] Terminal: The digital twin is placed in a virtual office environment, allowing users to view it through a user interface.

[0281] Digital Twin: Perform routine tasks in a virtual office environment, such as document sorting, data entry, and initial response to inquiries.

[0282] Server: Collects and stores a detailed record of the digital twin's daily operations.

[0283] 3. Business analysis and learning

[0284] Server: Analyzes business processes based on collected operational records. Analyzes past operational records to identify patterns and trends.

[0285] Server: Extracts tasks that are likely to occur again and has the digital twin learn those tasks.

[0286] Server: Inputs new business knowledge into the digital twin, expanding its scope of operations, and performs learning processes to improve the digital twin's business processing capabilities.

[0287] 4. Proposals for improving efficiency

[0288] Server: Further analyze the details of your business data to identify areas that are particularly time-consuming.

[0289] Server: Proposes efficiency improvements and presents specific improvement measures and efficiency methods to users.

[0290] Server: Trains the digital twin to work in new ways based on efficiency suggestions, for example adding new processes such as auto-completion of input formats and auto-classification of data.

[0291] 5. Implementing the Emotion Engine

[0292] Server: Collects emotional data such as the user's facial expressions, tone of voice, and text messages through the emotion engine.

[0293] Emotion Engine: Analyzes emotion data and recognizes the user's emotional state, including positive emotions, negative emotions, stress levels, etc.

[0294] Server: Determines the user's current emotional state based on the emotional data provided by the emotion engine.

[0295] 6. Improving business efficiency based on emotional data

[0296] Server: Adjusts work progress and suggestions based on emotional data. For example, if a user is feeling stressed, the server can temporarily have the digital twin take over the work.

[0297] Server: The emotion engine trains the digital twin with the emotional data recognized by the engine, enabling the digital twin to respond according to the user's emotional state.

[0298] Specific examples

[0299] Example 1: Improving efficiency of document management

[0300] 1. Data collection and digital twin generation

[0301] User: Inputs document management data into the system.

[0302] Server: Collects business data such as document classification and storage location input, and generates a digital twin based on that data.

[0303] 2. Business execution and operation records

[0304] Digital twin: Performs document classification and storage location entry tasks.

[0305] Server: Records the digital twin's behavior and collects the logs.

[0306] 3. Business analysis and learning

[0307] Server: Analyzes work patterns based on operation records and teaches the digital twin how to do the next job.

[0308] 4. Proposals for improving efficiency

[0309] Server: Conducts detailed analysis of document management data and proposes specific methods for improving efficiency, such as automatically suggesting file names and setting classification rules.

[0310] 5. Implementing the Emotion Engine

[0311] Emotion Engine: Recognizes and records the emotions users feel while managing documents in real time.

[0312] 6. Improving business efficiency based on emotional data

[0313] Server: Based on the user's emotional data, it identifies areas that cause particular stress and makes suggestions to have those areas of work taken over by the digital twin.

[0314] Example 2: Improving the efficiency of inquiry response operations

[0315] 1. Data collection and digital twin generation

[0316] User: Inputs data for inquiry handling work.

[0317] Server: Generates a digital twin based on past response history and FAQs.

[0318] 2. Business execution and operation records

[0319] Digital Twin: Respond to initial inquiries based on FAQs.

[0320] Server: Collects the digital twin's response as a log.

[0321] 3. Business analysis and learning

[0322] Server: Analyzes operational records and teaches the digital twin new knowledge for the next inquiry response.

[0323] 4. Proposals for improving efficiency

[0324] Server: Based on the analysis results of inquiry response operations, it proposes, for example, automatic updates to FAQs and revisions to response classifications.

[0325] 5. Implementing the Emotion Engine

[0326] Emotion engine: Recognizes user emotions in real time and analyzes work stress and satisfaction.

[0327] 6. Improving business efficiency based on emotional data

[0328] Server: Based on the user's emotional data, the digital twin adjusts its response and learns ways to respond in a way that minimizes stress.

[0329] These specific examples allow users to use the system efficiently, improving the quality and speed of their work, as well as adjusting their workload according to their emotions.

[0330] The processing flow will be explained below.

[0331] Data collection and digital twin generation

[0332] Step 1:

[0333] User: Log in to the system. Enter your login information (user ID and password) and wait for authentication.

[0334] Step 2:

[0335] Server: Receives user authentication information and performs authentication. If authentication is successful, grants access to the user.

[0336] Step 3:

[0337] User: Inputs business data, such as operation history, document uploads, and business details.

[0338] Step 4:

[0339] Server: Organizes the collected business data and stores it in a database. Prepares to start analyzing business processes.

[0340] Step 5:

[0341] Server: Analyzes business processes and creates a digital twin model that mimics those processes. Sets the necessary data in the digital twin and performs a simulation of its operation.

[0342] Business execution and operation records

[0343] Step 1:

[0344] Terminal: The digital twin is placed in a virtual office environment, and users can view it through a user interface.

[0345] Step 2:

[0346] Digital Twin: Perform routine tasks in a virtual office environment, such as document sorting, data entry, and initial response to inquiries.

[0347] Step 3:

[0348] Server: Collects and stores a detailed record of the digital twin's daily operations.

[0349] Business Analysis and Learning

[0350] Step 1:

[0351] Server: Analyzes business processes based on collected operational records. Analyzes past operational records to identify patterns and trends.

[0352] Step 2:

[0353] Server: Extracts tasks that are likely to occur again and has the digital twin learn those tasks.

[0354] Step 3:

[0355] Server: Inputs new business knowledge into the digital twin, expanding its scope of operations, and performs learning processes to improve the digital twin's business processing capabilities.

[0356] Efficiency proposals

[0357] Step 1:

[0358] Server: Further analyze the details of your business data to identify areas that are particularly time-consuming.

[0359] Step 2:

[0360] Server: Proposes efficiency improvements and presents specific improvement measures and efficiency methods to users.

[0361] Step 3:

[0362] Server: Trains the digital twin to work in new ways based on efficiency suggestions, for example adding new processes such as auto-completion of input formats and auto-classification of data.

[0363] Implementing the Emotion Engine

[0364] Step 1:

[0365] Server: Collects emotional data such as the user's facial expressions, tone of voice, and text messages through the emotion engine.

[0366] Step 2:

[0367] Emotion Engine: Analyzes emotion data and recognizes the user's emotional state, identifying positive emotions, negative emotions, stress levels, etc.

[0368] Step 3:

[0369] Server: Determines the user's current emotional state based on the emotional data provided by the emotion engine.

[0370] Improving business efficiency based on emotional data

[0371] Step 1:

[0372] Server: Adjusts work progress and suggestions based on emotional data. For example, if a user is feeling stressed, the server can temporarily have the digital twin take over the work.

[0373] Step 2:

[0374] Server: Provides information to improve work efficiency based on emotional data. For example, suggests ways to relax during stressful work.

[0375] Step 3:

[0376] Server: The emotion engine recognizes the emotional data and trains the digital twin. The digital twin responds according to the user's emotional state, improving work efficiency.

[0377] Specific examples

[0378] Example 1: Improving efficiency of document management

[0379] Step 1:

[0380] User: Inputs document management data into the system.

[0381] Step 2:

[0382] Server: Collects business data such as document classification and storage location input, and generates a digital twin based on that data.

[0383] Step 3:

[0384] Digital twin: Performs document classification and storage location entry tasks.

[0385] Step 4:

[0386] Server: Records the digital twin's behavior and collects the logs.

[0387] Step 5:

[0388] Emotion engine: Analyzes facial expressions and voices while users are performing document management tasks to collect emotional data.

[0389] Step 6:

[0390] Server: Based on the analysis results of document management tasks and user emotion data, it makes suggestions for efficiency improvements, such as automatically suggesting file names and setting classification rules.

[0391] Example 2: Improving the efficiency of inquiry response operations

[0392] Step 1:

[0393] User: Inputs data for inquiry handling work.

[0394] Step 2:

[0395] Server: Generates a digital twin based on past response history and FAQ data.

[0396] Step 3:

[0397] Digital Twin: Respond to initial inquiries based on FAQs.

[0398] Step 4:

[0399] Server: Collects the digital twin's response as a log.

[0400] Step 5:

[0401] Emotion Engine: Recognizes and records the emotions users feel while handling inquiries in real time.

[0402] Step 6:

[0403] Server: Based on the analysis of inquiry response work and emotional data, it makes suggestions for improving efficiency and reducing stress. For example, it automatically updates FAQs and reviews response classifications.

[0404] This improves the quality and speed of work and enables workload adjustment according to the user's emotions.

[0405] Example 2

[0406] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0407] In today's business environment, improving business efficiency is an important issue. Previous systems collected and analyzed business data, but they did not achieve comprehensive efficiency by simulating actual business processes in a virtual environment and incorporating user emotional data. The purpose of this invention is to provide a more advanced business management system that improves business efficiency and reduces the psychological burden on users by utilizing digital twins and an emotion engine.

[0408] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0409] In this invention, the server includes means for collecting real-world business data, means for generating a digital twin in a virtual office environment, means for the generated digital twin to execute the business, means for collecting operation records of the business executed by the digital twin, means for analyzing the business based on the collected operation records, means for having the digital twin learn new business based on the analysis results, means for proposing methods for improving efficiency based on business data, and means for recognizing user emotional data and reflecting it in the business process. This makes it possible to simultaneously execute and streamline business operations and adjust the workload according to the user's emotional state.

[0410] "Real-world business data" refers to various data (e.g., operation history, documents, inquiry details) generated in the daily operations of a company or organization.

[0411] "Virtual office environment" refers to a work environment that is virtually recreated using computer simulation.

[0412] "Digital twin" refers to a digital model that mimics and simulates real-world physical processes or systems in a virtual environment.

[0413] "Means of performing business operations" refers to the digital twin's ability to actually perform routine tasks (e.g., document classification, data entry, and responding to inquiries).

[0414] "Operation records" refer to detailed logs of the operations performed by the digital twin, including the operation history and execution time of the operations.

[0415] "Means for analyzing business operations" refers to the function of analyzing collected operational records and identifying patterns and trends in business processes.

[0416] "Means of business learning" refers to the process of inputting new business knowledge and skills into the digital twin based on the analysis results.

[0417] "Means to propose efficiency improvements" refers to a function that performs detailed analysis of business data and presents specific improvement measures and efficiency methods to the user.

[0418] "Emotional data" refers to data that indicates a user's emotional state, such as facial expressions, tone of voice, or text messages.

[0419] An "emotion engine" refers to a system that analyzes a user's emotional data and recognizes the user's emotional state based on the results.

[0420] This invention is a system for generating a digital twin in a virtual office environment based on real-world business data, thereby improving business efficiency. Furthermore, by combining it with an emotion engine that recognizes user emotion data, it is possible to achieve more comprehensive business efficiency. A specific implementation method of this system will be described below.

[0421] System configuration

[0422] This system consists of a server, a terminal (user interface), a digital twin, and an emotion engine.

[0423] server

[0424] The server has the following main functions:

[0425] 1. Function to collect business data

[0426] 2. Function to generate digital twins based on business data

[0427] 3. Ability to collect and analyze digital twin operation records

[0428] 4. A function that makes suggestions for improving business efficiency

[0429] 5. Function to analyze user emotional data using an emotion engine

[0430] Hardware and Software

[0431] Hardware

[0432] Server: A server with high-performance computing power is required, specifically a cloud server or on-premise server with sufficient CPU, memory and storage.

[0433] Terminals: Includes devices used by users, such as PCs, tablets, and smartphones. These terminals are connected to the Internet and are capable of data communication with servers.

[0434] software

[0435] Data collection: Database management system (e.g., MongoDB, MySQL®)

[0436] Data analysis: Data analysis libraries (Python Pandas, NumPy)

[0437] Digital twin generation: Simulation tools (AnyLogic, MATLAB (registered trademark))

[0438] Machine Learning: Machine learning frameworks (e.g. TensorFlow, scikit-learn)

[0439] Sentiment analysis: Natural language processing libraries (e.g., NLTK, SpaCy), speech analysis tools (Google® Cloud Speech-to-Text), facial recognition libraries (OpenCV)

[0440] What the program does

[0441] User Authentication and Data Collection

[0442] User: Logs in to the system and inputs business data into the system. Specifically, he uploads documents in PDF format or CSV files.

[0443] Server: Stores the business data provided by the user in a database. Pandas and NumPy are used for data analysis.

[0444] Digital Twin Generation

[0445] Server: Based on the data, the business process is analyzed and a digital twin is generated. The generated digital twin is simulated in a virtual office environment and performs business operations.

[0446] Simulation tools: AnyLogic and MATLAB are used to simulate the operation of the digital twin.

[0447] Collection of operational records and business analysis

[0448] Server: Collects and stores in a database the operation records of the tasks performed by the digital twin. These operation records include the operation history and execution time of the tasks.

[0449] Proposals for improving business efficiency

[0450] Server: Uses machine learning algorithms to optimize business processes based on operational records.

[0451] Machine learning: Uses TensorFlow and scikit-learn to analyze business patterns and generate efficiency suggestions.

[0452] Implementing the Emotion Engine

[0453] Server: Analyzes the user's emotional data using the emotion engine. Specifically, it understands the user's emotional state through facial expression recognition, voice analysis, and text analysis.

[0454] Emotion engine: Facial expression data is analyzed using OpenCV, voice data is analyzed using Google Cloud Speech-to-Text, and text messages are analyzed using SpaCy and NLTK.

[0455] Specific examples

[0456] Streamlining document management

[0457] 1. User: Inputs document management data into the system.

[0458] 2. Server: Collects business data such as document classification and storage location information, and generates a digital twin based on that data.

[0459] 3. Digital Twin: Performs document classification and storage location entry tasks.

[0460] 4. Server: Records the digital twin's operations and collects the logs.

[0461] 5. Server: Performs detailed analysis of document management data and proposes specific methods for improving efficiency, such as automatically suggesting file names and setting classification rules.

[0462] 6. Emotion Engine: Recognizes and records the emotions users feel while managing documents in real time.

[0463] Improving efficiency of inquiry response operations

[0464] 1. User: Inputs data for inquiry handling operations.

[0465] 2. Server: Generates a digital twin based on past response history and FAQs.

[0466] 3. Digital Twin: Respond to initial inquiries based on FAQs.

[0467] 4. Server: Collects the digital twin's response as a log.

[0468] 5. Server: Analyzes the operational records and teaches the digital twin new knowledge to respond to the next inquiry.

[0469] 6. Emotion Engine: Recognizes user emotions in real time and analyzes work stress and satisfaction.

[0470] Prompt Sentence Examples

[0471] Below are examples of prompts to encourage the operation of this system.

[0472] Document management optimization prompt example:

[0473] Collect data on document management tasks and provide suggestions for efficient classification and storage locations. Also, monitor the user's stress level while managing each document, and if stress levels are high, have that part of the task be taken over by the digital twin.

[0474] Example prompt for inquiry response optimization:

[0475] Based on the data of customer service operations, optimize FAQs and provide appropriate responses to initial inquiries. Recognize users' emotional data in real time, train your digital twin to respond according to their emotional state, and implement stress-relief measures.

[0476] These concrete examples and prompts allow users to use the system efficiently, improving the quality and speed of their work, as well as adjusting their workload according to their emotions.

[0477] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0478] Step 1:

[0479] User Authentication and Data Collection

[0480] User: Log in to the system by entering your username and password, pressing the login button and waiting for authentication.

[0481] Input: Username, Password

[0482] Output: Authentication token, user access rights

[0483] Server: Checks the user credentials against a database to authenticate them. If authentication is successful, generates an authentication token and grants access to the user.

[0484] Behavior: The user information is matched against a database (e.g. MySQL) for authentication. If authentication is successful, an authentication token is generated and a user session is started.

[0485] Step 2:

[0486] Entering and saving business data

[0487] User: Uploads business data (e.g., documents, operation history, inquiry details) to the system by dragging and dropping PDF or CSV files through the interface.

[0488] Input: Business data (PDF files, CSV files, etc.)

[0489] Output: Message indicating that data has been saved to the business database

[0490] Server: Receives uploaded files, stores them in a database, and extracts and organizes the file contents using OCR and data analysis tools.

[0491] How it works: After receiving the file, it uses OCR software (e.g., Tesseract OCR) to extract the text information, organizes the data using Python's Pandas or NumPy, and stores it in MongoDB or MySQL.

[0492] Step 3:

[0493] Digital Twin Generation

[0494] Server: Analyzes collected business data and generates a digital twin model. Business processes are reproduced in a virtual office environment using simulation tools (e.g., AnyLogic, MATLAB).

[0495] Input: Organized business data

[0496] Output: Digital twin model generation complete message

[0497] Operation: Analyze business data using data analysis libraries (Pandas, NumPy), then create a digital twin model using AnyLogic or MATLAB. Run a simulation to confirm the operation of the digital twin.

[0498] Step 4:

[0499] Business execution and operation recording

[0500] Terminal: Launches a virtual office environment and displays the interface through which the digital twin performs its work.

[0501] Input: Digital twin model

[0502] Output: Business execution visualization interface

[0503] Digital twin: Performs routine tasks such as document sorting, data entry, and handling inquiries.

[0504] How it works: The digital twin uses OCR to classify documents, natural language processing (NLP) to process queries, and records the process of how work is performed in real time.

[0505] Step 5:

[0506] Collection of operational records and business analysis

[0507] Server: Collects the digital twin's operational records in a database. The operational records include the operation history and execution time of the business.

[0508] Input: Digital twin operation record (log data)

[0509] Output: Analysis report

[0510] Actions: Action records are stored in a database (MongoDB, MySQL) and analyzed using machine learning algorithms (e.g. TensorFlow, scikit-learn) to identify patterns and trends in business processes.

[0511] Step 6:

[0512] Proposals for improving business efficiency

[0513] Server: Optimizes business processes based on the analysis results of operational records, proposes specific improvement measures, and presents them to the user in a report.

[0514] Input: Analysis results, output of optimization algorithms

[0515] Output: Efficiency proposal report

[0516] How it works: Optimize business processes using machine learning models and create reports that suggest specific efficiency measures (e.g., RPA implementation, automatic classification).

[0517] Step 7:

[0518] Emotion engine implementation and emotion analysis

[0519] Server: Collects and analyzes user emotion data through the emotion engine and reflects it in business processes.

[0520] Input: User emotion data (facial expression, voice, text)

[0521] Output: A report of the user's emotional state

[0522] How it works: We use OpenCV to analyze facial expression data, Google Cloud Speech-to-Text to analyze audio data, and SpaCy and NLTK to analyze text data to assess the user's emotional state.

[0523] Step 8:

[0524] Integrated business efficiency

[0525] Server: Integrates emotional data and business data to adjust how work proceeds.

[0526] Input: Emotion data, business data

[0527] Output: Workload adjustment plan

[0528] How it works: Dynamically adjusts workload based on the user's stress level and allows the digital twin to take over certain tasks, improving overall operational efficiency.

[0529] Through these steps, this system executes a consistent process from collecting and analyzing business data, generating digital twins, to utilizing emotion data, helping to improve business efficiency.

[0530] (Application example 2)

[0531] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0532] The objective of this invention is to improve the efficiency of food delivery services and manage the stress of delivery workers. Previous systems did not adequately collect and analyze data specific to delivery work, and also lacked work suggestions that took into account the emotional state of delivery workers. As a result, work optimization and stress reduction for delivery workers were not effectively achieved. A new approach to solving this problem is needed.

[0533] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0534] In this invention, the server includes means for collecting real-world business data, means for generating a digital twin in a virtual office environment based on the collected data, means for the generated digital twin to execute business operations, means for collecting operation records of the business operations executed by the digital twin, means for analyzing the business operations based on the collected operation records, means for having the digital twin learn new business operations based on the analysis results, means for proposing methods for improving efficiency based on the business data, means for collecting and analyzing business data specialized for delivery operations, means for collecting and analyzing emotional data of delivery personnel, and means for learning and proposing business methods based on delivery efficiency and the emotional data of delivery personnel. This makes it possible to improve the efficiency of food delivery operations and manage the emotions of delivery personnel.

[0535] "Real business data" refers to all data related to business operations carried out in a real environment.

[0536] A "virtual office environment" is a computer-generated virtual environment that mimics real-world office activities.

[0537] "Digital twin" is a technology that recreates real-world business processes as digital models and uses them to improve business efficiency and optimization.

[0538] "Operation records" are data that record the entire process of work performed by a digital twin.

[0539] "Business analysis" is the process of evaluating business performance based on collected data and operational records and identifying areas for improvement.

[0540] "Methods for improving efficiency" are methodologies for improving business performance, such as reducing work time, cutting costs, and improving the quality of deliverables.

[0541] "Delivery" is the service process of delivering ordered products to a specific location of a customer.

[0542] "Emotional data" is data that indicates the mental state of the delivery person and is obtained through facial expression analysis, voice analysis, text analysis, etc.

[0543] "Business methods" refer to the procedures and techniques required to carry out business.

[0544] An embodiment of the present invention includes a system for collecting real-world business data and generating a digital twin in a virtual office environment based on the collected data. This embodiment will be described in detail below.

[0545] The system program mainly consists of the following hardware and software:

[0546] Hardware: Smartphone (for delivery staff), server (cloud or on-premise)

[0547] Software: Python (programming language), Pandas (data analysis library), JSON (data format)

[0548] The server collects data related to delivery operations and generates a digital twin based on that data. This digital twin simulates the delivery process in a virtual office environment to improve efficiency. The server also has the ability to collect and analyze emotional data from delivery personnel. The results of this analysis are useful for optimizing deliveries and reducing stress for delivery personnel. This data is used to analyze operations and make suggestions for improving delivery methods, especially in the case of delivery delays or customer feedback.

[0549] The device (smartphone) collects real-time data on delivery behavior and emotional state of the delivery person while they are performing their delivery duties. This is achieved by continuously sending data entered by the delivery person on the app, such as the delivery address, delivery time, customer feedback, and the delivery person's emotional state, to a server.

[0550] For example, if delivery time exceeds 30 minutes or negative feedback is received, the system on the server analyzes this data and suggests optimizing delivery routes and readjusting delivery areas, thereby improving delivery efficiency and managing stress for delivery personnel.

[0551] The system also implements algorithms to learn new work methods and improve efficiency. This allows the system to constantly learn and apply the latest work methods. For example, if a delivery person is feeling stressed, the server will use that emotional data to suggest having the digital twin temporarily take over the work.

[0552] An example of a prompt is as follows:

[0553] I would like to know how to generate a digital twin based on operational data from a food delivery service to optimize delivery efficiency, and how to make suggestions using emotional data. Specifically, I would like to hear about a system that collects and analyzes delivery order IDs, delivery addresses, delivery times, customer feedback, and delivery personnel's emotional data to make suggestions to improve delivery efficiency.

[0554] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0555] Step 1:

[0556] A user logs in

[0557] Input: The user enters a user ID and password to log in to the system.

[0558] Processing: The server authenticates the entered user ID and password. The authentication process involves retrieving and verifying user information from a database.

[0559] Output: If authentication is successful, grant access to the user, or if authentication fails, display an error message.

[0560] Step 2:

[0561] Business data collection

[0562] Input: The user enters data related to the delivery job (delivery order ID, delivery address, delivery time, customer feedback, etc.).

[0563] Processing: The terminal collects the input data in real time and sends it to the server, unifying the data format and checking the required fields.

[0564] Output: The server stores the collected data in a database, which is used to generate a digital twin and for subsequent analysis.

[0565] Step 3:

[0566] Digital Twin Generation

[0567] Input: Collected business data

[0568] Processing: The server analyzes the collected business data and generates a digital twin that mimics business processes in a virtual office environment, including defining the business flow and setting up the simulation model.

[0569] Output: The resulting digital twin is a virtual model of the actual work environment that can be viewed by the user and placed in the virtual office environment.

[0570] Step 4:

[0571] Execution of work and collection of operational records

[0572] Input: Business execution results using digital twin

[0573] Processing: The digital twin performs routine tasks in the virtual office environment and records their actions. The terminal monitors the delivery person's actions and history in real time during deliveries and sends the data to the server.

[0574] Output: The collected operation records are stored in a database as detailed logs. This data is used to analyze operations and provide suggestions for improving efficiency.

[0575] Step 5:

[0576] Emotion data collection and analysis

[0577] Input: Delivery person's emotional data (facial expressions, voice, text messages, etc.)

[0578] Processing: The server uses an emotion engine to analyze the delivery person's emotional data and recognize their emotional state (positive, negative, stress level, etc.). This analysis is performed using emotion recognition algorithms and machine learning models.

[0579] Output: As a result of the analysis, the emotional state of the delivery person is stored on the server and used to make suggestions for delivery efficiency and emotion management.

[0580] Step 6:

[0581] Business analysis and efficiency proposals

[0582] Input: Collected business data and emotional data

[0583] Processing: The server analyzes business processes based on the collected data, identifying areas that are particularly time-consuming and that could be improved. It then generates specific recommendations for improving efficiency (e.g., changing delivery routes or readjusting delivery areas). Data analytics techniques and algorithms are used for the analysis.

[0584] Output: The generated suggestions are fed back to the user and further train the digital twin as a new way of working.

[0585] Step 7:

[0586] Learning business methods and implementing proposals

[0587] Input: Efficiency suggestions and new ways of working

[0588] Processing: The server trains the digital twin on the proposed new work methods and applies them the next time the work is performed, resulting in continuous improvement of the system.

[0589] Output: Improved operational methods are reflected in the digital twin, and are expected to have an impact on actual delivery operations.

[0590] This system will enable the efficiency of food delivery operations and the management of delivery personnel's emotions.

[0591] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0592] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0593] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0594] [Second embodiment]

[0595] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0596] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0597] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0598] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0599] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0600] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0601] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0602] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0603] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0604] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0605] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0606] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0607] The present invention is a system for generating a digital twin in a virtual office environment based on real-world business data, thereby improving business efficiency. The processing content of the program of this system is explained below in natural language.

[0608] Program processing overview

[0609] 1. Data collection and digital twin generation

[0610] User: Logging in to the system is a fundamental step in protecting and managing business data.

[0611] Server: Receives the user's authentication information and performs authentication. If authentication is successful, grants the user access rights and prepares to collect business data.

[0612] User: Inputs business data. This refers to data such as operation history, document uploads, and business details.

[0613] Server: Generates a digital twin based on collected business data, including analysis and modeling of business processes.

[0614] 2. Business execution and operation records

[0615] Terminal: The digital twin is placed in a virtual office environment, and users can view it through a user interface.

[0616] Digital twin: Performs actual tasks, such as sorting documents, entering data, and handling initial inquiries, mimicking the routine tasks that users normally perform.

[0617] Server: Collects daily operational records of the digital twin, which are stored as detailed logs for later analysis.

[0618] 3. Business analysis and learning

[0619] Server: Analyzes operations based on the digital twin's operational records. Analyzes past operational records to identify operational patterns and opportunities for efficiency improvements.

[0620] Server: Extracts the likely next occurrence of the same task. Based on this information, the digital twin learns new business processes.

[0621] Server: Input new business knowledge into the digital twin and expand the scope of business. This step will further improve the efficiency of the next business operation.

[0622] 4. Proposals for improving efficiency

[0623] Server: Analyze business data in detail to identify areas that take particularly long. For example, automate data entry, automatically suggest file names, etc.

[0624] Server: Proposes ways to improve efficiency. Presents specific improvement measures and efficiency techniques to the user. This information is then used to train the digital twin.

[0625] Server: By repeating the above steps, the digital twin gradually improves its business processing capabilities.

[0626] Specific examples

[0627] Example 1: Improving efficiency of document management

[0628] 1. Data collection and digital twin generation

[0629] User: Inputs document management data into the system.

[0630] Server: Collects business data such as document classification and storage location input, and generates a digital twin based on that data.

[0631] 2. Business execution and operation records

[0632] Digital twin: Performs document classification and storage location entry tasks.

[0633] Server: Records the digital twin's behavior and collects the logs.

[0634] 3. Business analysis and learning

[0635] Server: Analyzes work patterns based on operation records and teaches the digital twin how to do the next job.

[0636] 4. Proposals for improving efficiency

[0637] Server: Conducts detailed analysis of document management data and proposes specific methods for improving efficiency, such as automatically suggesting file names and setting classification rules.

[0638] Example 2: Improving the efficiency of inquiry response operations

[0639] 1. Data collection and digital twin generation

[0640] User: Inputs data for inquiry handling work.

[0641] Server: Generates a digital twin based on past response history and FAQs.

[0642] 2. Business execution and operation records

[0643] Digital Twin: Respond to initial inquiries based on FAQs.

[0644] Server: Collects the digital twin's response as a log.

[0645] 3. Business analysis and learning

[0646] Server: Analyzes operational records and teaches the digital twin new knowledge for the next inquiry response.

[0647] 4. Proposals for improving efficiency

[0648] Server: Based on the analysis results of inquiry response operations, it proposes, for example, automatic updates to FAQs and revisions to response classifications.

[0649] These examples allow users to use the system efficiently and improve the quality and speed of their work.

[0650] The processing flow will be explained below.

[0651] Data collection and digital twin generation

[0652] Step 1:

[0653] User: Log in to the system, enter login information and wait for authentication.

[0654] Step 2:

[0655] Server: Receives user authentication information and performs authentication. If successful, grants access to the user.

[0656] Step 3:

[0657] User: Inputs business data, such as operation history, document uploads, and business details.

[0658] Step 4:

[0659] Server: Organizes collected business data and stores it in a database. Prepares to generate a digital twin based on this data.

[0660] Step 5:

[0661] Server: Analyzes business processes and creates a digital twin model that mimics those processes. Sets the necessary data in the digital twin and performs a simulation of its operation.

[0662] Business execution and operation records

[0663] Step 1:

[0664] Terminal: The digital twin is placed in a virtual office environment, allowing users to view it through a user interface.

[0665] Step 2:

[0666] Digital Twin: Perform routine tasks in a virtual office environment, such as document sorting, data entry, and initial response to inquiries.

[0667] Step 3:

[0668] Server: Collects and stores a detailed record of the digital twin's daily operations.

[0669] Business Analysis and Learning

[0670] Step 1:

[0671] Server: Analyzes business processes based on collected operational records. Analyzes past operational records to identify patterns and trends.

[0672] Step 2:

[0673] Server: Extracts tasks that are likely to occur again and has the digital twin learn those tasks.

[0674] Step 3:

[0675] Server: Inputs new business knowledge into the digital twin, expanding its scope of operations, and performs learning processes to improve the digital twin's business processing capabilities.

[0676] Efficiency proposals

[0677] Step 1:

[0678] Server: Further analyze the details of your business data to identify areas that are particularly time-consuming.

[0679] Step 2:

[0680] Server: Proposes efficiency improvements and presents specific improvement measures and efficiency methods to users.

[0681] Step 3:

[0682] Server: Trains the digital twin to work in new ways based on efficiency suggestions, for example adding new processes such as auto-completion of input formats and auto-classification of data.

[0683] This allows users to process more than twice as much work in the same amount of time, improving work efficiency.

[0684] Example 1

[0685] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0686] There is a demand for systems that can carry out business efficiently and accurately based on real business data. However, currently, there is a lack of tools to streamline and optimize business processes, and a lot of time and effort is spent on manual data entry and classification. As a result, there is an issue of reduced business efficiency and difficulty in improving productivity.

[0687] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0688] In this invention, the server includes: means for a user to enter authentication information and log in to the system; means for performing user authentication and collecting business data; means for generating a digital twin using an analysis tool based on the collected business data; means for placing the generated digital twin in a virtual office environment and providing a user interface; means for the digital twin to imitate and execute real-world business operations; means for collecting operation records of the digital twin in real time and storing them in a database; means for analyzing the operation record data and identifying business patterns; means for having the digital twin learn new business processes to improve business efficiency in the next business operation; and means for proposing methods for improving business efficiency based on the analysis results, thereby enabling business efficiency improvement and optimization.

[0689] "User authentication" is the process of verifying a user's identity when accessing a system. Authentication information includes a user ID and password.

[0690] "Business data" refers to information related to business processes, and includes, for example, operation history, document information, input data, and the like.

[0691] A "digital twin" is a digital model that recreates real-world business processes and systems in a virtual environment, with the aim of replicating and executing business processes.

[0692] A "virtual office environment" is a workspace that digitally recreates an actual office environment, and is a virtual space in which a digital twin is placed.

[0693] A "user interface" is an interface that allows a user to directly interact with the system, allowing them to operate and monitor the digital twin.

[0694] "Operation records" refer to detailed operation logs and execution histories of the tasks performed by the digital twin. These are collected in real time and stored in a database.

[0695] "Analysis tools" generally refer to software and algorithms that process and analyze collected data, and are used for generating digital twins and business analysis.

[0696] "Business patterns" refer to the characteristic flow of business execution processes and procedures obtained by analyzing business data.

[0697] A "business process" refers to a series of procedures and operations required to carry out a specific task, and new business processes are learned by the digital twin.

[0698] "Efficiency methods" refer to specific techniques and proposals for reducing work time and costs and improving productivity.

[0699] MODE FOR CARRYING OUT THE INVENTION

[0700] The present invention provides a system for generating a digital twin in a virtual office environment based on real-world business data, thereby improving business efficiency. This system is implemented using multiple hardware and software components.

[0701] Data Collection and User Authentication

[0702] 1. User: First logs in to the system, entering their user ID and password as identification information to begin the authentication process.

[0703] 2. Server: Receives user authentication information and compares it with the database. A high-performance server (e.g., Dell PowerEdge R740) is used for this. If authentication is successful, the user is granted access rights and business data can be collected.

[0704] Digital Twin Generation

[0705] 3. User: Inputs business data, specifically, uploads operation history, document information, business details, etc. to the system.

[0706] 4. Server: Generates a digital twin based on the collected data using data analysis tools (e.g., Python's Pandas library) and digital twin generation software (e.g., Ansys Twin Builder). The analyzed data is built as a virtual model and deployed in a virtual office environment.

[0707] Business execution and operation recording

[0708] 5. Terminal: The digital twin is placed in a virtual office environment and a user interface is provided (e.g., Microsoft Azure Digital Twins). Users can use this interface to observe and manipulate the behavior of the digital twin in real time.

[0709] 6. Digital Twin: Mimics real-world business processes and performs tasks such as document sorting, data entry, and handling inquiries.

[0710] 7. Server: Collects the digital twin's operational records in real time and stores them in a database. These records are used for analysis.

[0711] Business Analysis and Learning

[0712] 8. Server: Analyze business patterns based on collected operational records. Use analysis tools to identify areas where efficiency can be improved.

[0713] 9. Server: Uses machine learning models (e.g., TensorFlow) to teach the digital twin new processes that will be useful for the next job.

[0714] Efficiency proposals

[0715] 10. Server: Analyzes business data in detail and proposes ways to improve efficiency. For example, it suggests specific improvement measures such as automating data entry and automatically suggesting file names.

[0716] 11. Server: Reflects the proposed efficiency improvements in the digital twin and optimizes the next business process.

[0717] Specific examples

[0718] Example 1: Improving efficiency of document management

[0719] User: Inputs document management data into the system. Specifically, uploads the Excel file "Business Data.xlsx."

[0720] Server: Uses data analysis tools to automate document classification and storage location, generating a digital twin that is then placed in a virtual office environment.

[0721] Example 2: Improving the efficiency of inquiry response operations

[0722] User: Inputs data related to inquiries into the system. Specifically, inputs past response history and FAQ data.

[0723] Server: A digital twin is generated based on the collected data and placed in a virtual office environment. The digital twin responds to initial inquiries and records the results on the server.

[0724] Prompt Sentence Examples

[0725] "Please explain the steps to input business data and generate a digital twin."

[0726] "Please give us a concrete example of how a digital twin can be used to streamline document management operations."

[0727] "Please explain how a digital twin can help improve the efficiency of your inquiry response operations."

[0728] As described above, the present invention effectively collects and analyzes business data and optimizes business processes using digital twins, thereby achieving significant improvements in business efficiency and labor savings.

[0729] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0730] Step 1:

[0731] User: Log in to the system. Enter your user ID and password and click the "Login" button.

[0732] Input: User ID, Password

[0733] Output: Authentication token, access granted

[0734] Specific operation: The user enters the user ID "user123" and password "password123" on the system login screen, for example, and clicks the "Login" button.

[0735] Step 2:

[0736] Server: Receives the user's authentication information and checks it against a database.

[0737] Input: User ID, Password

[0738] Output: Authentication result (success / failure), authentication token

[0739] Specific operation: The server receives the user ID "user123" and password "password123", checks it against the database, and if authentication is successful, generates a token and grants access rights to the user.

[0740] Step 3:

[0741] User: Input business data. For example, upload the "BusinessData.xlsx" file.

[0742] Input: Business data file (e.g., businessdata.xlsx)

[0743] Output: Business data collection

[0744] Specific operation: After logging in, click the "Upload business data" button from the dashboard, select "Business data.xlsx" in the file selection dialog, and upload it.

[0745] Step 4:

[0746] Server: Generates a digital twin based on collected business data.

[0747] Input: Business data file (e.g., businessdata.xlsx)

[0748] Output: Digital twin model

[0749] How it works: The server uses Python's Pandas library to analyze business data and uses Ansys Twin Builder to generate a digital twin model.

[0750] Step 5:

[0751] Terminal: Places the digital twin in a virtual office environment and provides a user interface.

[0752] Input: Digital twin model

[0753] Output: Digital twin on UI

[0754] Specific operation: The server deploys the generated digital twin model to Microsoft Azure Digital Twins and displays it in the user interface.

[0755] Step 6:

[0756] Digital Twin: Imitating and executing real-world operations.

[0757] Input: Business process data

[0758] Output: Work results, operation records

[0759] Specific operations: The digital twin performs document classification, data entry, inquiry response, etc. in a virtual environment, generating business results and action records.

[0760] Step 7:

[0761] Server: Collects digital twin operation records in real time and stores them in a database.

[0762] Input: Digital twin operation record

[0763] Output: Action record database

[0764] Specific operation: The server receives the operation logs recorded by the digital twin and stores them in a database in real time.

[0765] Step 8:

[0766] Server: Analyzes business patterns based on collected operation records.

[0767] Input: Action Record Database

[0768] Output: Business analysis results

[0769] Specific operation: The server analyzes the operation record data using an analysis tool (e.g., Python DataFrame) and identifies business patterns.

[0770] Step 9:

[0771] Server: Trains the digital twin to learn new business processes.

[0772] Input: Business analysis results, new business processes

[0773] Output: Trained digital twin

[0774] Specific operation: Based on the analysis results, the server uses a machine learning model (e.g., TensorFlow) to teach the digital twin new business processes.

[0775] Step 10:

[0776] Server: Conducts detailed analysis of business data and proposes methods for improving efficiency.

[0777] Input: Business data, operation records

[0778] Output: Efficiency proposals

[0779] Specific operation: The server performs detailed data analysis and generates efficiency suggestions, such as "Automating data entry steps can save two hours per day."

[0780] Step 11:

[0781] Server: Reflects the proposed efficiency measures in the digital twin and optimizes the next business process.

[0782] Input: Efficiency proposal

[0783] Output: Optimized business processes

[0784] Specific operation: The server applies the proposed efficiency methods to the digital twin model, allowing the digital twin to learn new business processes and prepare for the next business operation.

[0785] (Application example 1)

[0786] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0787] Traditional production line management in factories requires a great deal of time and effort to improve efficiency and optimization, and efficiency often declines due to the heavy reliance on manual human labor. Furthermore, insufficient analysis and learning based on past operational records can result in waste due to the repetition of the same tasks. Furthermore, there are limited means of immediately applying efficiency suggestions, requiring flexible responses.

[0788] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0789] In this invention, the server includes: means for collecting real-world business data; means for generating a digital twin in a virtual work environment based on the collected data; means for the generated digital twin to execute business operations; means for collecting operation records of the business operations executed by the digital twin; means for analyzing the business operations based on the collected operation records; means for the digital twin to learn new business operations based on the analysis results; means for proposing methods for improving efficiency based on the business data; means for collecting business data of a production line and generating a digital twin; means for the digital twin to imitate production line operations and analyze the operation records to learn the optimal production process; and means for immediately applying the efficiency proposals to the production line. This enables accurate business analysis based on past operation records and specific proposals for improving efficiency, thereby significantly improving the efficiency of the production line.

[0790] "Real-world business data" refers to all data related to work that occurs in real-world environments such as factories and offices. Examples include production line operation data and employee operation records.

[0791] A "virtual work environment" is a digital space that virtually recreates an actual work environment. This eliminates physical constraints, making it easier to perform simulations and optimizations.

[0792] A "digital twin" is a virtual model created based on real-world business data. This model performs the same functions as real systems and business processes, enabling simulation and analysis.

[0793] "Operation records" are historical data of the tasks and actions performed by the digital twin, which are used to evaluate and optimize operations.

[0794] "Means for analyzing work" are methods and techniques for identifying work patterns and opportunities for efficiency improvement based on collected operational records.

[0795] "Means of learning new business" refers to methods and technologies that allow the digital twin to incorporate new business processes and improvement methods, enabling it to operate more efficiently the next time the business is executed.

[0796] "Means for proposing ways to improve efficiency" refers to methods and technologies for analyzing business data, identifying areas for improvement, and making specific proposals for improving efficiency.

[0797] "Production line business data" refers to all data related to the production process, including, for example, the operating status of machines, production volume, and quality inspection results.

[0798] A "production process" is a series of steps to manufacture a product on a production line, including material input, processing, assembly, inspection, and shipping.

[0799] "Means for immediately applying efficiency proposals to the production line" refers to technology that uses digital twins to immediately reflect proposed efficiency methods on the actual production line, enabling rapid improvements.

[0800] The present invention is a digital twin system aimed at improving the efficiency of production lines, and specific embodiments are described below.

[0801] System configuration

[0802] This system, which consists of a server, terminals, and users, has the following main functions:

[0803] 1. Data Collection

[0804] The server collects real-time operational data from the production line through sensors and data input devices, including machine operation data, worker behavior data, and quality inspection results.

[0805] 2. Digital Twin Creation

[0806] The server uses the collected data to create a digital twin in a virtual work environment: a virtual model of the real production line that can accurately mimic its behavior.

[0807] 3. Execution of Business

[0808] The generated digital twin can then be used to virtually execute production line operations via a terminal, recreating the actual production process in a virtual environment.

[0809] 4. Collecting Operational Records

[0810] The server collects records of operations performed by the digital twin, including detailed operational procedures and results.

[0811] 5. Business Analysis

[0812] The server analyzes the collected activity records to identify opportunities for efficiency. This analysis identifies historical patterns and identifies areas for improvement.

[0813] 6. Learning a new job

[0814] Based on the analysis results, the server teaches the digital twin new business processes, allowing it to operate more efficiently the next time the business is executed.

[0815] 7. Efficiency proposals

[0816] The server uses business data to propose ways to improve efficiency, including optimizing production processes, changing processes, and revising work procedures. These proposals are immediately applied to the production line, resulting in rapid improvements.

[0817] Hardware and Software

[0818] This system uses the following hardware and software:

[0819] Hardware: sensors, data input devices, network connection devices, servers

[0820] Software: Software for generating digital twin models, software for data analysis (e.g., Python, Scikit-learn), software for proposing efficiency improvements

[0821] Specific examples

[0822] For example, in a factory's parts assembly line, a server collects operational data from each work station and generates a digital twin based on that data. This digital twin simulates actual assembly work in a virtual environment and analyzes the operational records. Based on the analysis results, new work procedures and process changes are proposed and implemented immediately, significantly improving the efficiency of the assembly line.

[0823] Example prompt sentence:

[0824] Create a virtual environment to optimize your production line and create a digital twin based on operational data. Analyze the collected data, list specific efficiency improvements, and provide steps to implement them.

[0825] As described above, the digital twin system according to the present invention realizes highly accurate efficiency improvements on production lines.

[0826] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0827] Step 1:

[0828] The server collects operational data related to the production line from each work station in the factory through sensors and data input devices. Inputs include machine operation data, worker behavior data, and quality inspection results. This data is sent to the server in real time and saved. The data is organized in JSON format and stored in a database.

[0829] Step 2:

[0830] The server generates a digital twin in a virtual work environment based on the collected business data. The business data collected in step 1 is used as input. Digital twin model generation software is used to create a virtual model of the real production line from that data. This model mimics the real operation in the virtual environment. The output is a digital twin model.

[0831] Step 3:

[0832] The terminal uses the generated digital twin to virtually execute production line operations. The digital twin model is used as input. The production process is reproduced in the virtual environment and operation data is collected. During this process, the digital twin operates in the same way as in reality. The output is an operation log of the digital twin.

[0833] Step 4:

[0834] The server collects and analyzes the operational records of the tasks performed by the digital twin. The operational logs generated in step 3 are used as input. Data analysis software (e.g., Python, Scikit-learn) is used to analyze past operational records and identify patterns and potential for efficiency improvements. The output is the analysis results.

[0835] Step 5:

[0836] The server trains the digital twin to learn new business processes based on the analysis results of the operation records. The analysis results from step 4 are used as input. New business knowledge is input into the digital twin using a machine learning algorithm. The output is a new digital twin model that has completed learning.

[0837] Step 6:

[0838] The server proposes efficiency improvement methods based on business data. The inputs used are the analysis results and the trained digital twin model. Specific improvement measures and efficiency methods are generated using software for proposing efficiency improvements. For example, optimal production processes and revisions to work procedures are proposed. The output is efficiency improvement proposals.

[0839] Step 7:

[0840] The server immediately applies the efficiency improvement proposals to the production line. The efficiency improvement proposals obtained in step 6 are used as input. Specifically, parameters are changed and new work procedures are implemented, and these are reflected in the production line. The output is an efficient new employee production line.

[0841] Through the above steps, the digital twin system of the present invention achieves high-precision efficiency and optimization of production lines.

[0842] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0843] This invention is a system for generating a digital twin in a virtual office environment based on real-world business data, thereby improving business efficiency. Furthermore, by combining it with an emotion engine that recognizes user emotion data, this system achieves more comprehensive business efficiency. The processing content of the program for this system is explained below in natural language.

[0844] Program processing overview

[0845] 1. Data collection and digital twin generation

[0846] User: Log in to the system, enter login information and wait for authentication.

[0847] Server: Receives user credentials and performs authentication. If successful, grants access to the user.

[0848] User: Inputs business data, such as operation history, document uploads, and business details.

[0849] Server: Organizes collected business data and stores it in a database. Prepares to generate a digital twin based on this data.

[0850] Server: Analyzes business processes and creates a digital twin model that mimics those processes. Sets the necessary data in the digital twin and performs a simulation of its operation.

[0851] 2. Business execution and operation records

[0852] Terminal: The digital twin is placed in a virtual office environment, allowing users to view it through a user interface.

[0853] Digital Twin: Perform routine tasks in a virtual office environment, such as document sorting, data entry, and initial response to inquiries.

[0854] Server: Collects and stores a detailed record of the digital twin's daily operations.

[0855] 3. Business analysis and learning

[0856] Server: Analyzes business processes based on collected operational records. Analyzes past operational records to identify patterns and trends.

[0857] Server: Extracts tasks that are likely to occur again and has the digital twin learn those tasks.

[0858] Server: Inputs new business knowledge into the digital twin, expanding its scope of operations, and performs learning processes to improve the digital twin's business processing capabilities.

[0859] 4. Proposals for improving efficiency

[0860] Server: Further analyze the details of your business data to identify areas that are particularly time-consuming.

[0861] Server: Proposes efficiency improvements and presents specific improvement measures and efficiency methods to users.

[0862] Server: Trains the digital twin to work in new ways based on efficiency suggestions, for example adding new processes such as auto-completion of input formats and auto-classification of data.

[0863] 5. Implementing the Emotion Engine

[0864] Server: Collects emotional data such as the user's facial expressions, tone of voice, and text messages through the emotion engine.

[0865] Emotion Engine: Analyzes emotion data and recognizes the user's emotional state, including positive emotions, negative emotions, stress levels, etc.

[0866] Server: Determines the user's current emotional state based on the emotional data provided by the emotion engine.

[0867] 6. Improving business efficiency based on emotional data

[0868] Server: Adjusts work progress and suggestions based on emotional data. For example, if a user is feeling stressed, the server can temporarily have the digital twin take over the work.

[0869] Server: The emotion engine trains the digital twin with the emotional data recognized by the engine, enabling the digital twin to respond according to the user's emotional state.

[0870] Specific examples

[0871] Example 1: Improving efficiency of document management

[0872] 1. Data collection and digital twin generation

[0873] User: Inputs document management data into the system.

[0874] Server: Collects business data such as document classification and storage location input, and generates a digital twin based on that data.

[0875] 2. Business execution and operation records

[0876] Digital twin: Performs document classification and storage location entry tasks.

[0877] Server: Records the digital twin's behavior and collects the logs.

[0878] 3. Business analysis and learning

[0879] Server: Analyzes work patterns based on operation records and teaches the digital twin how to do the next job.

[0880] 4. Proposals for improving efficiency

[0881] Server: Conducts detailed analysis of document management data and proposes specific methods for improving efficiency, such as automatically suggesting file names and setting classification rules.

[0882] 5. Implementing the Emotion Engine

[0883] Emotion Engine: Recognizes and records the emotions users feel while managing documents in real time.

[0884] 6. Improving business efficiency based on emotional data

[0885] Server: Based on the user's emotional data, it identifies areas that cause particular stress and makes suggestions to have those areas of work taken over by the digital twin.

[0886] Example 2: Improving the efficiency of inquiry response operations

[0887] 1. Data collection and digital twin generation

[0888] User: Inputs data for inquiry handling work.

[0889] Server: Generates a digital twin based on past response history and FAQs.

[0890] 2. Business execution and operation records

[0891] Digital Twin: Respond to initial inquiries based on FAQs.

[0892] Server: Collects the digital twin's response as a log.

[0893] 3. Business analysis and learning

[0894] Server: Analyzes operational records and teaches the digital twin new knowledge for the next inquiry response.

[0895] 4. Proposals for improving efficiency

[0896] Server: Based on the analysis results of inquiry response operations, it proposes, for example, automatic updates to FAQs and revisions to response classifications.

[0897] 5. Implementing the Emotion Engine

[0898] Emotion engine: Recognizes user emotions in real time and analyzes work stress and satisfaction.

[0899] 6. Improving business efficiency based on emotional data

[0900] Server: Based on the user's emotional data, the digital twin adjusts its response and learns ways to respond in a way that minimizes stress.

[0901] These specific examples allow users to use the system efficiently, improving the quality and speed of their work, as well as adjusting their workload according to their emotions.

[0902] The processing flow will be explained below.

[0903] Data collection and digital twin generation

[0904] Step 1:

[0905] User: Log in to the system. Enter your login information (user ID and password) and wait for authentication.

[0906] Step 2:

[0907] Server: Receives user authentication information and performs authentication. If authentication is successful, grants access to the user.

[0908] Step 3:

[0909] User: Inputs business data, such as operation history, document uploads, and business details.

[0910] Step 4:

[0911] Server: Organizes the collected business data and stores it in a database. Prepares to start analyzing business processes.

[0912] Step 5:

[0913] Server: Analyzes business processes and creates a digital twin model that mimics those processes. Sets the necessary data in the digital twin and performs a simulation of its operation.

[0914] Business execution and operation records

[0915] Step 1:

[0916] Terminal: The digital twin is placed in a virtual office environment, and users can view it through a user interface.

[0917] Step 2:

[0918] Digital Twin: Perform routine tasks in a virtual office environment, such as document sorting, data entry, and initial response to inquiries.

[0919] Step 3:

[0920] Server: Collects and stores a detailed record of the digital twin's daily operations.

[0921] Business Analysis and Learning

[0922] Step 1:

[0923] Server: Analyzes business processes based on collected operational records. Analyzes past operational records to identify patterns and trends.

[0924] Step 2:

[0925] Server: Extracts tasks that are likely to occur again and has the digital twin learn those tasks.

[0926] Step 3:

[0927] Server: Inputs new business knowledge into the digital twin, expanding its scope of operations, and performs learning processes to improve the digital twin's business processing capabilities.

[0928] Efficiency proposals

[0929] Step 1:

[0930] Server: Further analyze the details of your business data to identify areas that are particularly time-consuming.

[0931] Step 2:

[0932] Server: Proposes efficiency improvements and presents specific improvement measures and efficiency methods to users.

[0933] Step 3:

[0934] Server: Trains the digital twin to work in new ways based on efficiency suggestions, for example adding new processes such as auto-completion of input formats and auto-classification of data.

[0935] Implementing the Emotion Engine

[0936] Step 1:

[0937] Server: Collects emotional data such as the user's facial expressions, tone of voice, and text messages through the emotion engine.

[0938] Step 2:

[0939] Emotion Engine: Analyzes emotion data and recognizes the user's emotional state, identifying positive emotions, negative emotions, stress levels, etc.

[0940] Step 3:

[0941] Server: Determines the user's current emotional state based on the emotional data provided by the emotion engine.

[0942] Improving business efficiency based on emotional data

[0943] Step 1:

[0944] Server: Adjusts work progress and suggestions based on emotional data. For example, if a user is feeling stressed, the server can temporarily have the digital twin take over the work.

[0945] Step 2:

[0946] Server: Provides information to improve work efficiency based on emotional data. For example, suggests ways to relax during stressful work.

[0947] Step 3:

[0948] Server: The emotion engine recognizes the emotional data and trains the digital twin. The digital twin responds according to the user's emotional state, improving work efficiency.

[0949] Specific examples

[0950] Example 1: Improving efficiency of document management

[0951] Step 1:

[0952] User: Inputs document management data into the system.

[0953] Step 2:

[0954] Server: Collects business data such as document classification and storage location input, and generates a digital twin based on that data.

[0955] Step 3:

[0956] Digital twin: Performs document classification and storage location entry tasks.

[0957] Step 4:

[0958] Server: Records the digital twin's behavior and collects the logs.

[0959] Step 5:

[0960] Emotion engine: Analyzes facial expressions and voices while users are performing document management tasks to collect emotional data.

[0961] Step 6:

[0962] Server: Based on the analysis results of document management tasks and user emotion data, it makes suggestions for efficiency improvements, such as automatically suggesting file names and setting classification rules.

[0963] Example 2: Improving the efficiency of inquiry response operations

[0964] Step 1:

[0965] User: Inputs data for inquiry handling work.

[0966] Step 2:

[0967] Server: Generates a digital twin based on past response history and FAQ data.

[0968] Step 3:

[0969] Digital Twin: Respond to initial inquiries based on FAQs.

[0970] Step 4:

[0971] Server: Collects the digital twin's response as a log.

[0972] Step 5:

[0973] Emotion Engine: Recognizes and records the emotions users feel while handling inquiries in real time.

[0974] Step 6:

[0975] Server: Based on the analysis of inquiry response work and emotional data, it makes suggestions for improving efficiency and reducing stress. For example, it automatically updates FAQs and reviews response classifications.

[0976] This improves the quality and speed of work and enables workload adjustment according to the user's emotions.

[0977] Example 2

[0978] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0979] In today's business environment, improving business efficiency is an important issue. Previous systems collected and analyzed business data, but they did not achieve comprehensive efficiency by simulating actual business processes in a virtual environment and incorporating user emotional data. The purpose of this invention is to provide a more advanced business management system that improves business efficiency and reduces the psychological burden on users by utilizing digital twins and an emotion engine.

[0980] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0981] In this invention, the server includes means for collecting real-world business data, means for generating a digital twin in a virtual office environment, means for the generated digital twin to execute the business, means for collecting operation records of the business executed by the digital twin, means for analyzing the business based on the collected operation records, means for having the digital twin learn new business based on the analysis results, means for proposing methods for improving efficiency based on business data, and means for recognizing user emotional data and reflecting it in the business process. This makes it possible to simultaneously execute and streamline business operations and adjust the workload according to the user's emotional state.

[0982] "Real-world business data" refers to various data (e.g., operation history, documents, inquiry details) generated in the daily operations of a company or organization.

[0983] "Virtual office environment" refers to a work environment that is virtually recreated using computer simulation.

[0984] "Digital twin" refers to a digital model that mimics and simulates real-world physical processes or systems in a virtual environment.

[0985] "Means of performing business operations" refers to the digital twin's ability to actually perform routine tasks (e.g., document classification, data entry, and responding to inquiries).

[0986] "Operation records" refer to detailed logs of the operations performed by the digital twin, including the operation history and execution time of the operations.

[0987] "Means for analyzing business operations" refers to the function of analyzing collected operational records and identifying patterns and trends in business processes.

[0988] "Means of business learning" refers to the process of inputting new business knowledge and skills into the digital twin based on the analysis results.

[0989] "Means to propose efficiency improvements" refers to a function that performs detailed analysis of business data and presents specific improvement measures and efficiency methods to the user.

[0990] "Emotional data" refers to data that indicates a user's emotional state, such as facial expressions, tone of voice, or text messages.

[0991] An "emotion engine" refers to a system that analyzes a user's emotional data and recognizes the user's emotional state based on the results.

[0992] This invention is a system for generating a digital twin in a virtual office environment based on real-world business data, thereby improving business efficiency. Furthermore, by combining it with an emotion engine that recognizes user emotion data, it is possible to achieve more comprehensive business efficiency. A specific implementation method of this system will be described below.

[0993] System configuration

[0994] This system consists of a server, a terminal (user interface), a digital twin, and an emotion engine.

[0995] server

[0996] The server has the following main functions:

[0997] 1. Function to collect business data

[0998] 2. Function to generate digital twins based on business data

[0999] 3. Ability to collect and analyze digital twin operation records

[1000] 4. A function that makes suggestions for improving business efficiency

[1001] 5. Function to analyze user emotional data using an emotion engine

[1002] Hardware and Software

[1003] Hardware

[1004] Server: A server with high-performance computing power is required, specifically a cloud server or on-premise server with sufficient CPU, memory and storage.

[1005] Terminals: Includes devices used by users, such as PCs, tablets, and smartphones. These terminals are connected to the Internet and are capable of data communication with servers.

[1006] software

[1007] Data collection: Database management system (e.g. MongoDB, MySQL)

[1008] Data analysis: Data analysis libraries (Python Pandas, NumPy)

[1009] Digital twin generation: Simulation tools (AnyLogic, MATLAB)

[1010] Machine Learning: Machine learning frameworks (e.g. TensorFlow, scikit-learn)

[1011] Sentiment analysis: Natural language processing libraries (e.g., NLTK, SpaCy), speech analysis tools (Google Cloud Speech-to-Text), facial recognition libraries (OpenCV)

[1012] What the program does

[1013] User Authentication and Data Collection

[1014] User: Logs in to the system and inputs business data into the system. Specifically, he uploads documents in PDF format or CSV files.

[1015] Server: Stores the business data provided by the user in a database. Pandas and NumPy are used for data analysis.

[1016] Digital Twin Generation

[1017] Server: Based on the data, the business process is analyzed and a digital twin is generated. The generated digital twin is simulated in a virtual office environment and performs business operations.

[1018] Simulation tools: AnyLogic and MATLAB are used to simulate the operation of the digital twin.

[1019] Collection of operational records and business analysis

[1020] Server: Collects and stores in a database the operation records of the tasks performed by the digital twin. These operation records include the operation history and execution time of the tasks.

[1021] Proposals for improving business efficiency

[1022] Server: Uses machine learning algorithms to optimize business processes based on operational records.

[1023] Machine learning: Uses TensorFlow and scikit-learn to analyze business patterns and generate efficiency suggestions.

[1024] Implementing the Emotion Engine

[1025] Server: Analyzes the user's emotional data using the emotion engine. Specifically, it understands the user's emotional state through facial expression recognition, voice analysis, and text analysis.

[1026] Emotion engine: Facial expression data is analyzed using OpenCV, voice data is analyzed using Google Cloud Speech-to-Text, and text messages are analyzed using SpaCy and NLTK.

[1027] Specific examples

[1028] Streamlining document management

[1029] 1. User: Inputs document management data into the system.

[1030] 2. Server: Collects business data such as document classification and storage location information, and generates a digital twin based on that data.

[1031] 3. Digital Twin: Performs document classification and storage location entry tasks.

[1032] 4. Server: Records the digital twin's operations and collects the logs.

[1033] 5. Server: Performs detailed analysis of document management data and proposes specific methods for improving efficiency, such as automatically suggesting file names and setting classification rules.

[1034] 6. Emotion Engine: Recognizes and records the emotions users feel while managing documents in real time.

[1035] Improving efficiency of inquiry response operations

[1036] 1. User: Inputs data for inquiry handling operations.

[1037] 2. Server: Generates a digital twin based on past response history and FAQs.

[1038] 3. Digital Twin: Respond to initial inquiries based on FAQs.

[1039] 4. Server: Collects the digital twin's response as a log.

[1040] 5. Server: Analyzes the operational records and teaches the digital twin new knowledge to respond to the next inquiry.

[1041] 6. Emotion Engine: Recognizes user emotions in real time and analyzes work stress and satisfaction.

[1042] Prompt Sentence Examples

[1043] Below are examples of prompts to encourage the operation of this system.

[1044] Document management optimization prompt example:

[1045] Collect data on document management tasks and provide suggestions for efficient classification and storage locations. Also, monitor the user's stress level while managing each document, and if stress levels are high, have that part of the task be taken over by the digital twin.

[1046] Example prompt for inquiry response optimization:

[1047] Based on the data of customer service operations, optimize FAQs and provide appropriate responses to initial inquiries. Recognize users' emotional data in real time, train your digital twin to respond according to their emotional state, and implement stress-relief measures.

[1048] These concrete examples and prompts allow users to use the system efficiently, improving the quality and speed of their work, as well as adjusting their workload according to their emotions.

[1049] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1050] Step 1:

[1051] User Authentication and Data Collection

[1052] User: Log in to the system by entering your username and password, pressing the login button and waiting for authentication.

[1053] Input: Username, Password

[1054] Output: Authentication token, user access rights

[1055] Server: Checks the user credentials against a database to authenticate them. If authentication is successful, generates an authentication token and grants access to the user.

[1056] Behavior: The user information is matched against a database (e.g. MySQL) for authentication. If authentication is successful, an authentication token is generated and a user session is started.

[1057] Step 2:

[1058] Entering and saving business data

[1059] User: Uploads business data (e.g., documents, operation history, inquiry details) to the system by dragging and dropping PDF or CSV files through the interface.

[1060] Input: Business data (PDF files, CSV files, etc.)

[1061] Output: Message indicating that data has been saved to the business database

[1062] Server: Receives uploaded files, stores them in a database, and extracts and organizes the file contents using OCR and data analysis tools.

[1063] How it works: After receiving the file, it uses OCR software (e.g., Tesseract OCR) to extract the text information, organizes the data using Python's Pandas or NumPy, and stores it in MongoDB or MySQL.

[1064] Step 3:

[1065] Digital Twin Generation

[1066] Server: Analyzes collected business data and generates a digital twin model. Business processes are reproduced in a virtual office environment using simulation tools (e.g., AnyLogic, MATLAB).

[1067] Input: Organized business data

[1068] Output: Digital twin model generation complete message

[1069] Operation: Analyze business data using data analysis libraries (Pandas, NumPy), then create a digital twin model using AnyLogic or MATLAB. Run a simulation to confirm the operation of the digital twin.

[1070] Step 4:

[1071] Business execution and operation recording

[1072] Terminal: Launches a virtual office environment and displays the interface through which the digital twin performs its work.

[1073] Input: Digital twin model

[1074] Output: Business execution visualization interface

[1075] Digital twin: Performs routine tasks such as document sorting, data entry, and handling inquiries.

[1076] How it works: The digital twin uses OCR to classify documents, natural language processing (NLP) to process queries, and records the process of how work is performed in real time.

[1077] Step 5:

[1078] Collection of operational records and business analysis

[1079] Server: Collects the digital twin's operational records in a database. The operational records include the operation history and execution time of the business.

[1080] Input: Digital twin operation record (log data)

[1081] Output: Analysis report

[1082] Actions: Action records are stored in a database (MongoDB, MySQL) and analyzed using machine learning algorithms (e.g. TensorFlow, scikit-learn) to identify patterns and trends in business processes.

[1083] Step 6:

[1084] Proposals for improving business efficiency

[1085] Server: Optimizes business processes based on the analysis results of operational records, proposes specific improvement measures, and presents them to the user in a report.

[1086] Input: Analysis results, output of optimization algorithms

[1087] Output: Efficiency proposal report

[1088] How it works: Optimize business processes using machine learning models and create reports that suggest specific efficiency measures (e.g., RPA implementation, automatic classification).

[1089] Step 7:

[1090] Emotion engine implementation and emotion analysis

[1091] Server: Collects and analyzes user emotion data through the emotion engine and reflects it in business processes.

[1092] Input: User emotion data (facial expression, voice, text)

[1093] Output: A report of the user's emotional state

[1094] How it works: We use OpenCV to analyze facial expression data, Google Cloud Speech-to-Text to analyze audio data, and SpaCy and NLTK to analyze text data to assess the user's emotional state.

[1095] Step 8:

[1096] Integrated business efficiency

[1097] Server: Integrates emotional data and business data to adjust how work proceeds.

[1098] Input: Emotion data, business data

[1099] Output: Workload adjustment plan

[1100] How it works: Dynamically adjusts workload based on the user's stress level and allows the digital twin to take over certain tasks, improving overall operational efficiency.

[1101] Through these steps, this system executes a consistent process from collecting and analyzing business data, generating digital twins, to utilizing emotion data, helping to improve business efficiency.

[1102] (Application example 2)

[1103] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1104] The objective of this invention is to improve the efficiency of food delivery services and manage the stress of delivery workers. Previous systems did not adequately collect and analyze data specific to delivery work, and also lacked work suggestions that took into account the emotional state of delivery workers. As a result, work optimization and stress reduction for delivery workers were not effectively achieved. A new approach to solving this problem is needed.

[1105] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1106] In this invention, the server includes means for collecting real-world business data, means for generating a digital twin in a virtual office environment based on the collected data, means for the generated digital twin to execute business operations, means for collecting operation records of the business operations executed by the digital twin, means for analyzing the business operations based on the collected operation records, means for having the digital twin learn new business operations based on the analysis results, means for proposing methods for improving efficiency based on the business data, means for collecting and analyzing business data specialized for delivery operations, means for collecting and analyzing emotional data of delivery personnel, and means for learning and proposing business methods based on delivery efficiency and the emotional data of delivery personnel. This makes it possible to improve the efficiency of food delivery operations and manage the emotions of delivery personnel.

[1107] "Real business data" refers to all data related to business operations carried out in a real environment.

[1108] A "virtual office environment" is a computer-generated virtual environment that mimics real-world office activities.

[1109] "Digital twin" is a technology that recreates real-world business processes as digital models and uses them to improve business efficiency and optimization.

[1110] "Operation records" are data that record the entire process of work performed by a digital twin.

[1111] "Business analysis" is the process of evaluating business performance based on collected data and operational records and identifying areas for improvement.

[1112] "Methods for improving efficiency" are methodologies for improving business performance, such as reducing work time, cutting costs, and improving the quality of deliverables.

[1113] "Delivery" is the service process of delivering ordered products to a specific location of a customer.

[1114] "Emotional data" is data that indicates the mental state of the delivery person and is obtained through facial expression analysis, voice analysis, text analysis, etc.

[1115] "Business methods" refer to the procedures and techniques required to carry out business.

[1116] An embodiment of the present invention includes a system for collecting real-world business data and generating a digital twin in a virtual office environment based on the collected data. This embodiment will be described in detail below.

[1117] The system program mainly consists of the following hardware and software:

[1118] Hardware: Smartphone (for delivery staff), server (cloud or on-premise)

[1119] Software: Python (programming language), Pandas (data analysis library), JSON (data format)

[1120] The server collects data related to delivery operations and generates a digital twin based on that data. This digital twin simulates the delivery process in a virtual office environment to improve efficiency. The server also has the ability to collect and analyze emotional data from delivery personnel. The results of this analysis are useful for optimizing deliveries and reducing stress for delivery personnel. This data is used to analyze operations and make suggestions for improving delivery methods, especially in the case of delivery delays or customer feedback.

[1121] The device (smartphone) collects real-time data on delivery behavior and emotional state of the delivery person while they are performing their delivery duties. This is achieved by continuously sending data entered by the delivery person on the app, such as the delivery address, delivery time, customer feedback, and the delivery person's emotional state, to a server.

[1122] For example, if delivery time exceeds 30 minutes or negative feedback is received, the system on the server analyzes this data and suggests optimizing delivery routes and readjusting delivery areas, thereby improving delivery efficiency and managing stress for delivery personnel.

[1123] The system also implements algorithms to learn new work methods and improve efficiency. This allows the system to constantly learn and apply the latest work methods. For example, if a delivery person is feeling stressed, the server will use that emotional data to suggest having the digital twin temporarily take over the work.

[1124] An example of a prompt is as follows:

[1125] I would like to know how to generate a digital twin based on operational data from a food delivery service to optimize delivery efficiency, and how to make suggestions using emotional data. Specifically, I would like to hear about a system that collects and analyzes delivery order IDs, delivery addresses, delivery times, customer feedback, and delivery personnel's emotional data to make suggestions to improve delivery efficiency.

[1126] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1127] Step 1:

[1128] A user logs in

[1129] Input: The user enters a user ID and password to log in to the system.

[1130] Processing: The server authenticates the entered user ID and password. The authentication process involves retrieving and verifying user information from a database.

[1131] Output: If authentication is successful, grant access to the user, or if authentication fails, display an error message.

[1132] Step 2:

[1133] Business data collection

[1134] Input: The user enters data related to the delivery job (delivery order ID, delivery address, delivery time, customer feedback, etc.).

[1135] Processing: The terminal collects the input data in real time and sends it to the server, unifying the data format and checking the required fields.

[1136] Output: The server stores the collected data in a database, which is used to generate a digital twin and for subsequent analysis.

[1137] Step 3:

[1138] Digital Twin Generation

[1139] Input: Collected business data

[1140] Processing: The server analyzes the collected business data and generates a digital twin that mimics business processes in a virtual office environment, including defining the business flow and setting up the simulation model.

[1141] Output: The resulting digital twin is a virtual model of the actual work environment that can be viewed by the user and placed in the virtual office environment.

[1142] Step 4:

[1143] Execution of work and collection of operational records

[1144] Input: Business execution results using digital twin

[1145] Processing: The digital twin performs routine tasks in the virtual office environment and records their actions. The terminal monitors the delivery person's actions and history in real time during deliveries and sends the data to the server.

[1146] Output: The collected operation records are stored in a database as detailed logs. This data is used to analyze operations and provide suggestions for improving efficiency.

[1147] Step 5:

[1148] Emotion data collection and analysis

[1149] Input: Delivery person's emotional data (facial expressions, voice, text messages, etc.)

[1150] Processing: The server uses an emotion engine to analyze the delivery person's emotional data and recognize their emotional state (positive, negative, stress level, etc.). This analysis is performed using emotion recognition algorithms and machine learning models.

[1151] Output: As a result of the analysis, the emotional state of the delivery person is stored on the server and used to make suggestions for delivery efficiency and emotion management.

[1152] Step 6:

[1153] Business analysis and efficiency proposals

[1154] Input: Collected business data and emotional data

[1155] Processing: The server analyzes business processes based on the collected data, identifying areas that are particularly time-consuming and that could be improved. It then generates specific recommendations for improving efficiency (e.g., changing delivery routes or readjusting delivery areas). Data analytics techniques and algorithms are used for the analysis.

[1156] Output: The generated suggestions are fed back to the user and further train the digital twin as a new way of working.

[1157] Step 7:

[1158] Learning business methods and implementing proposals

[1159] Input: Efficiency suggestions and new ways of working

[1160] Processing: The server trains the digital twin on the proposed new work methods and applies them the next time the work is performed, resulting in continuous improvement of the system.

[1161] Output: Improved operational methods are reflected in the digital twin, and are expected to have an impact on actual delivery operations.

[1162] This system will enable the efficiency of food delivery operations and the management of delivery personnel's emotions.

[1163] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1164] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1165] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1166] [Third embodiment]

[1167] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1168] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1169] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1170] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1171] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1172] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1173] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1174] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1175] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1176] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1177] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1178] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[1179] The present invention is a system for generating a digital twin in a virtual office environment based on real-world business data, thereby improving business efficiency. The processing content of the program of this system is explained below in natural language.

[1180] Program processing overview

[1181] 1. Data collection and digital twin generation

[1182] User: Logging in to the system is a fundamental step in protecting and managing business data.

[1183] Server: Receives the user's authentication information and performs authentication. If authentication is successful, grants the user access rights and prepares to collect business data.

[1184] User: Inputs business data. This refers to data such as operation history, document uploads, and business details.

[1185] Server: Generates a digital twin based on collected business data, including analysis and modeling of business processes.

[1186] 2. Business execution and operation records

[1187] Terminal: The digital twin is placed in a virtual office environment, and users can view it through a user interface.

[1188] Digital twin: Performs actual tasks, such as sorting documents, entering data, and handling initial inquiries, mimicking the routine tasks that users normally perform.

[1189] Server: Collects daily operational records of the digital twin, which are stored as detailed logs for later analysis.

[1190] 3. Business analysis and learning

[1191] Server: Analyzes operations based on the digital twin's operational records. Analyzes past operational records to identify operational patterns and opportunities for efficiency improvements.

[1192] Server: Extracts the likely next occurrence of the same task. Based on this information, the digital twin learns new business processes.

[1193] Server: Input new business knowledge into the digital twin and expand the scope of business. This step will further improve the efficiency of the next business operation.

[1194] 4. Proposals for improving efficiency

[1195] Server: Analyze business data in detail to identify areas that take particularly long. For example, automate data entry, automatically suggest file names, etc.

[1196] Server: Proposes ways to improve efficiency. Presents specific improvement measures and efficiency techniques to the user. This information is then used to train the digital twin.

[1197] Server: By repeating the above steps, the digital twin gradually improves its business processing capabilities.

[1198] Specific examples

[1199] Example 1: Improving efficiency of document management

[1200] 1. Data collection and digital twin generation

[1201] User: Inputs document management data into the system.

[1202] Server: Collects business data such as document classification and storage location input, and generates a digital twin based on that data.

[1203] 2. Business execution and operation records

[1204] Digital twin: Performs document classification and storage location entry tasks.

[1205] Server: Records the digital twin's behavior and collects the logs.

[1206] 3. Business analysis and learning

[1207] Server: Analyzes work patterns based on operation records and teaches the digital twin how to do the next job.

[1208] 4. Proposals for improving efficiency

[1209] Server: Conducts detailed analysis of document management data and proposes specific methods for improving efficiency, such as automatically suggesting file names and setting classification rules.

[1210] Example 2: Improving the efficiency of inquiry response operations

[1211] 1. Data collection and digital twin generation

[1212] User: Inputs data for inquiry handling work.

[1213] Server: Generates a digital twin based on past response history and FAQs.

[1214] 2. Business execution and operation records

[1215] Digital Twin: Respond to initial inquiries based on FAQs.

[1216] Server: Collects the digital twin's response as a log.

[1217] 3. Business analysis and learning

[1218] Server: Analyzes operational records and teaches the digital twin new knowledge for the next inquiry response.

[1219] 4. Proposals for improving efficiency

[1220] Server: Based on the analysis results of inquiry response operations, it proposes, for example, automatic updates to FAQs and revisions to response classifications.

[1221] These examples allow users to use the system efficiently and improve the quality and speed of their work.

[1222] The processing flow will be explained below.

[1223] Data collection and digital twin generation

[1224] Step 1:

[1225] User: Log in to the system, enter login information and wait for authentication.

[1226] Step 2:

[1227] Server: Receives user authentication information and performs authentication. If successful, grants access to the user.

[1228] Step 3:

[1229] User: Inputs business data, such as operation history, document uploads, and business details.

[1230] Step 4:

[1231] Server: Organizes collected business data and stores it in a database. Prepares to generate a digital twin based on this data.

[1232] Step 5:

[1233] Server: Analyzes business processes and creates a digital twin model that mimics those processes. Sets the necessary data in the digital twin and performs a simulation of its operation.

[1234] Business execution and operation records

[1235] Step 1:

[1236] Terminal: The digital twin is placed in a virtual office environment, allowing users to view it through a user interface.

[1237] Step 2:

[1238] Digital Twin: Perform routine tasks in a virtual office environment, such as document sorting, data entry, and initial response to inquiries.

[1239] Step 3:

[1240] Server: Collects and stores a detailed record of the digital twin's daily operations.

[1241] Business Analysis and Learning

[1242] Step 1:

[1243] Server: Analyzes business processes based on collected operational records. Analyzes past operational records to identify patterns and trends.

[1244] Step 2:

[1245] Server: Extracts tasks that are likely to occur again and has the digital twin learn those tasks.

[1246] Step 3:

[1247] Server: Inputs new business knowledge into the digital twin, expanding its scope of operations, and performs learning processes to improve the digital twin's business processing capabilities.

[1248] Efficiency proposals

[1249] Step 1:

[1250] Server: Further analyze the details of your business data to identify areas that are particularly time-consuming.

[1251] Step 2:

[1252] Server: Proposes efficiency improvements and presents specific improvement measures and efficiency methods to users.

[1253] Step 3:

[1254] Server: Trains the digital twin to work in new ways based on efficiency suggestions, for example adding new processes such as auto-completion of input formats and auto-classification of data.

[1255] This allows users to process more than twice as much work in the same amount of time, improving work efficiency.

[1256] Example 1

[1257] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1258] There is a demand for systems that can carry out business efficiently and accurately based on real business data. However, currently, there is a lack of tools to streamline and optimize business processes, and a lot of time and effort is spent on manual data entry and classification. As a result, there is an issue of reduced business efficiency and difficulty in improving productivity.

[1259] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1260] In this invention, the server includes: means for a user to enter authentication information and log in to the system; means for performing user authentication and collecting business data; means for generating a digital twin using an analysis tool based on the collected business data; means for placing the generated digital twin in a virtual office environment and providing a user interface; means for the digital twin to imitate and execute real-world business operations; means for collecting operation records of the digital twin in real time and storing them in a database; means for analyzing the operation record data and identifying business patterns; means for having the digital twin learn new business processes to improve business efficiency in the next business operation; and means for proposing methods for improving business efficiency based on the analysis results, thereby enabling business efficiency improvement and optimization.

[1261] "User authentication" is the process of verifying a user's identity when accessing a system. Authentication information includes a user ID and password.

[1262] "Business data" refers to information related to business processes, and includes, for example, operation history, document information, input data, and the like.

[1263] A "digital twin" is a digital model that recreates real-world business processes and systems in a virtual environment, with the aim of replicating and executing business processes.

[1264] A "virtual office environment" is a workspace that digitally recreates an actual office environment, and is a virtual space in which a digital twin is placed.

[1265] A "user interface" is an interface that allows a user to directly interact with the system, allowing them to operate and monitor the digital twin.

[1266] "Operation records" refer to detailed operation logs and execution histories of the tasks performed by the digital twin. These are collected in real time and stored in a database.

[1267] "Analysis tools" generally refer to software and algorithms that process and analyze collected data, and are used to generate digital twins and analyze business processes.

[1268] "Business patterns" refer to the characteristic flow of business execution processes and procedures obtained by analyzing business data.

[1269] A "business process" refers to a series of procedures and operations required to carry out a specific task, and new business processes are learned by the digital twin.

[1270] "Efficiency methods" refer to specific techniques and proposals for reducing work time and costs and improving productivity.

[1271] MODE FOR CARRYING OUT THE INVENTION

[1272] The present invention provides a system for generating a digital twin in a virtual office environment based on real-world business data, thereby improving business efficiency. This system is implemented using multiple hardware and software components.

[1273] Data Collection and User Authentication

[1274] 1. User: First logs in to the system, entering their user ID and password as identification information to begin the authentication process.

[1275] 2. Server: Receives user authentication information and compares it with the database. A high-performance server (e.g., Dell PowerEdge R740) is used for this. If authentication is successful, the user is granted access rights and business data can be collected.

[1276] Digital Twin Generation

[1277] 3. User: Inputs business data, specifically, uploads operation history, document information, business details, etc. to the system.

[1278] 4. Server: Generates a digital twin based on the collected data using data analysis tools (e.g., Python's Pandas library) and digital twin generation software (e.g., Ansys Twin Builder). The analyzed data is built as a virtual model and deployed in a virtual office environment.

[1279] Business execution and operation recording

[1280] 5. Terminal: The digital twin is placed in a virtual office environment and a user interface is provided (e.g., Microsoft Azure Digital Twins). Users can use this interface to observe and manipulate the behavior of the digital twin in real time.

[1281] 6. Digital Twin: Mimics real-world business processes and performs tasks such as document sorting, data entry, and handling inquiries.

[1282] 7. Server: Collects the digital twin's operational records in real time and stores them in a database. These records are used for analysis.

[1283] Business Analysis and Learning

[1284] 8. Server: Analyze business patterns based on collected operational records. Use analysis tools to identify areas where efficiency can be improved.

[1285] 9. Server: Uses machine learning models (e.g., TensorFlow) to teach the digital twin new processes that will be useful for the next job.

[1286] Efficiency proposals

[1287] 10. Server: Analyzes business data in detail and proposes ways to improve efficiency. For example, it suggests specific improvement measures such as automating data entry and automatically suggesting file names.

[1288] 11. Server: Reflects the proposed efficiency improvements in the digital twin and optimizes the next business process.

[1289] Specific examples

[1290] Example 1: Improving efficiency of document management

[1291] User: Inputs document management data into the system. Specifically, uploads the Excel file "Business Data.xlsx."

[1292] Server: Uses data analysis tools to automate document classification and storage location, generating a digital twin that is then placed in a virtual office environment.

[1293] Example 2: Improving the efficiency of inquiry response operations

[1294] User: Inputs data related to inquiries into the system. Specifically, inputs past response history and FAQ data.

[1295] Server: A digital twin is generated based on the collected data and placed in a virtual office environment. The digital twin responds to initial inquiries and records the results on the server.

[1296] Prompt Sentence Examples

[1297] "Please explain the steps to input business data and generate a digital twin."

[1298] "Please give us a concrete example of how a digital twin can be used to streamline document management operations."

[1299] "Please explain how a digital twin can help improve the efficiency of your inquiry response operations."

[1300] As described above, the present invention effectively collects and analyzes business data and optimizes business processes using digital twins, thereby achieving significant improvements in business efficiency and labor savings.

[1301] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1302] Step 1:

[1303] User: Log in to the system. Enter your user ID and password and click the "Login" button.

[1304] Input: User ID, Password

[1305] Output: Authentication token, access granted

[1306] Specific operation: The user enters the user ID "user123" and password "password123" on the system login screen, for example, and clicks the "Login" button.

[1307] Step 2:

[1308] Server: Receives the user's authentication information and checks it against a database.

[1309] Input: User ID, Password

[1310] Output: Authentication result (success / failure), authentication token

[1311] Specific operation: The server receives the user ID "user123" and password "password123", checks it against the database, and if authentication is successful, generates a token and grants access rights to the user.

[1312] Step 3:

[1313] User: Input business data. For example, upload the "BusinessData.xlsx" file.

[1314] Input: Business data file (e.g., businessdata.xlsx)

[1315] Output: Business data collection

[1316] Specific operation: After logging in, click the "Upload business data" button from the dashboard, select "Business data.xlsx" in the file selection dialog, and upload it.

[1317] Step 4:

[1318] Server: Generates a digital twin based on collected business data.

[1319] Input: Business data file (e.g., businessdata.xlsx)

[1320] Output: Digital twin model

[1321] How it works: The server uses Python's Pandas library to analyze business data and uses Ansys Twin Builder to generate a digital twin model.

[1322] Step 5:

[1323] Terminal: Places the digital twin in a virtual office environment and provides a user interface.

[1324] Input: Digital twin model

[1325] Output: Digital twin on UI

[1326] Specific operation: The server deploys the generated digital twin model to Microsoft Azure Digital Twins and displays it in the user interface.

[1327] Step 6:

[1328] Digital Twin: Imitating and executing real-world operations.

[1329] Input: Business process data

[1330] Output: Work results, operation records

[1331] Specific operations: The digital twin performs document classification, data entry, inquiry response, etc. in a virtual environment, generating business results and action records.

[1332] Step 7:

[1333] Server: Collects digital twin operation records in real time and stores them in a database.

[1334] Input: Digital twin operation record

[1335] Output: Action record database

[1336] Specific operation: The server receives the operation logs recorded by the digital twin and stores them in a database in real time.

[1337] Step 8:

[1338] Server: Analyzes business patterns based on collected operation records.

[1339] Input: Action Record Database

[1340] Output: Business analysis results

[1341] Specific operation: The server analyzes the operation record data using an analysis tool (e.g., Python DataFrame) and identifies business patterns.

[1342] Step 9:

[1343] Server: Trains the digital twin to learn new business processes.

[1344] Input: Business analysis results, new business processes

[1345] Output: Trained digital twin

[1346] Specific operation: Based on the analysis results, the server uses a machine learning model (e.g., TensorFlow) to teach the digital twin new business processes.

[1347] Step 10:

[1348] Server: Conducts detailed analysis of business data and proposes methods for improving efficiency.

[1349] Input: Business data, operation records

[1350] Output: Efficiency proposals

[1351] Specific operation: The server performs detailed data analysis and generates efficiency suggestions, such as "Automating data entry steps can save two hours per day."

[1352] Step 11:

[1353] Server: Reflects the proposed efficiency measures in the digital twin and optimizes the next business process.

[1354] Input: Efficiency proposal

[1355] Output: Optimized business processes

[1356] Specific operation: The server applies the proposed efficiency methods to the digital twin model, allowing the digital twin to learn new business processes and prepare for the next business operation.

[1357] (Application example 1)

[1358] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1359] Traditional production line management in factories requires a great deal of time and effort to improve efficiency and optimization, and efficiency often declines due to the heavy reliance on manual human labor. Furthermore, insufficient analysis and learning based on past operational records can result in waste due to the repetition of the same tasks. Furthermore, there are limited means of immediately applying efficiency suggestions, requiring flexible responses.

[1360] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1361] In this invention, the server includes: means for collecting real-world business data; means for generating a digital twin in a virtual work environment based on the collected data; means for the generated digital twin to execute business operations; means for collecting operation records of the business operations executed by the digital twin; means for analyzing the business operations based on the collected operation records; means for the digital twin to learn new business operations based on the analysis results; means for proposing methods for improving efficiency based on the business data; means for collecting business data of a production line and generating a digital twin; means for the digital twin to imitate production line operations and analyze the operation records to learn the optimal production process; and means for immediately applying the efficiency proposals to the production line. This enables accurate business analysis based on past operation records and specific proposals for improving efficiency, thereby significantly improving the efficiency of the production line.

[1362] "Real-world business data" refers to all data related to work that occurs in real-world environments such as factories and offices. Examples include production line operation data and employee operation records.

[1363] A "virtual work environment" is a digital space that virtually recreates an actual work environment. This eliminates physical constraints, making it easier to perform simulations and optimizations.

[1364] A "digital twin" is a virtual model created based on real-world business data. This model performs the same functions as real systems and business processes, enabling simulation and analysis.

[1365] "Operation records" are historical data of the tasks and actions performed by the digital twin, which are used to evaluate and optimize operations.

[1366] "Means for analyzing work" are methods and techniques for identifying work patterns and opportunities for efficiency improvement based on collected operational records.

[1367] "Means of learning new business" refers to methods and technologies that allow the digital twin to incorporate new business processes and improvement methods, enabling it to operate more efficiently the next time the business is executed.

[1368] "Means for proposing ways to improve efficiency" refers to methods and technologies for analyzing business data, identifying areas for improvement, and making specific proposals for improving efficiency.

[1369] "Production line business data" refers to all data related to the production process, including, for example, the operating status of machines, production volume, and quality inspection results.

[1370] A "production process" is a series of steps to manufacture a product on a production line, including material input, processing, assembly, inspection, and shipping.

[1371] "Means for immediately applying efficiency proposals to the production line" refers to technology that uses digital twins to immediately reflect proposed efficiency methods on the actual production line, enabling rapid improvements.

[1372] The present invention is a digital twin system aimed at improving the efficiency of production lines, and specific embodiments are described below.

[1373] System configuration

[1374] This system, which consists of a server, terminals, and users, has the following main functions:

[1375] 1. Data Collection

[1376] The server collects real-time operational data from the production line through sensors and data input devices, including machine operation data, worker behavior data, and quality inspection results.

[1377] 2. Digital Twin Creation

[1378] The server uses the collected data to create a digital twin in a virtual work environment: a virtual model of the real production line that can accurately mimic its behavior.

[1379] 3. Execution of Business

[1380] The generated digital twin can then be used to virtually execute production line operations via a terminal, recreating the actual production process in a virtual environment.

[1381] 4. Collecting Operational Records

[1382] The server collects records of operations performed by the digital twin, including detailed operational procedures and results.

[1383] 5. Business Analysis

[1384] The server analyzes the collected activity records to identify opportunities for efficiency. This analysis identifies historical patterns and identifies areas for improvement.

[1385] 6. Learning a new job

[1386] Based on the analysis results, the server teaches the digital twin new business processes, allowing it to operate more efficiently the next time the business is executed.

[1387] 7. Efficiency proposals

[1388] The server uses business data to propose ways to improve efficiency, including optimizing production processes, changing processes, and revising work procedures. These proposals are immediately applied to the production line, resulting in rapid improvements.

[1389] Hardware and Software

[1390] This system uses the following hardware and software:

[1391] Hardware: sensors, data input devices, network connection devices, servers

[1392] Software: Software for generating digital twin models, software for data analysis (e.g., Python, Scikit-learn), software for proposing efficiency improvements

[1393] Specific examples

[1394] For example, in a factory's parts assembly line, a server collects operational data from each work station and generates a digital twin based on that data. This digital twin simulates actual assembly work in a virtual environment and analyzes the operational records. Based on the analysis results, new work procedures and process changes are proposed and implemented immediately, significantly improving the efficiency of the assembly line.

[1395] Example prompt sentence:

[1396] Create a virtual environment to optimize your production line and create a digital twin based on operational data. Analyze the collected data, list specific efficiency improvements, and provide steps to implement them.

[1397] As described above, the digital twin system according to the present invention realizes highly accurate efficiency improvements on production lines.

[1398] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1399] Step 1:

[1400] The server collects operational data related to the production line from each work station in the factory through sensors and data input devices. Inputs include machine operation data, worker behavior data, and quality inspection results. This data is sent to the server in real time and saved. The data is organized in JSON format and stored in a database.

[1401] Step 2:

[1402] The server generates a digital twin in a virtual work environment based on the collected business data. The business data collected in step 1 is used as input. Digital twin model generation software is used to create a virtual model of the real production line from that data. This model mimics the real operation in the virtual environment. The output is a digital twin model.

[1403] Step 3:

[1404] The terminal uses the generated digital twin to virtually execute production line operations. The digital twin model is used as input. The production process is reproduced in the virtual environment and operation data is collected. During this process, the digital twin operates in the same way as in reality. The output is an operation log of the digital twin.

[1405] Step 4:

[1406] The server collects and analyzes the operational records of the tasks performed by the digital twin. The operational logs generated in step 3 are used as input. Data analysis software (e.g., Python, Scikit-learn) is used to analyze past operational records and identify patterns and potential for efficiency improvements. The output is the analysis results.

[1407] Step 5:

[1408] The server trains the digital twin to learn new business processes based on the analysis results of the operation records. The analysis results from step 4 are used as input. New business knowledge is input into the digital twin using a machine learning algorithm. The output is a new digital twin model that has completed learning.

[1409] Step 6:

[1410] The server proposes efficiency improvement methods based on business data. The inputs used are the analysis results and the trained digital twin model. Specific improvement measures and efficiency methods are generated using software for proposing efficiency improvements. For example, optimal production processes and revisions to work procedures are proposed. The output is efficiency improvement proposals.

[1411] Step 7:

[1412] The server immediately applies the efficiency improvement proposals to the production line. The efficiency improvement proposals obtained in step 6 are used as input. Specifically, parameters are changed and new work procedures are implemented, and these are reflected in the production line. The output is an efficient new employee production line.

[1413] Through the above steps, the digital twin system of the present invention achieves high-precision efficiency and optimization of production lines.

[1414] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1415] This invention is a system for generating a digital twin in a virtual office environment based on real-world business data, thereby improving business efficiency. Furthermore, by combining it with an emotion engine that recognizes user emotion data, this system achieves more comprehensive business efficiency. The processing content of the program for this system is explained below in natural language.

[1416] Program processing overview

[1417] 1. Data collection and digital twin generation

[1418] User: Log in to the system, enter login information and wait for authentication.

[1419] Server: Receives user credentials and performs authentication. If successful, grants access to the user.

[1420] User: Inputs business data, such as operation history, document uploads, and business details.

[1421] Server: Organizes collected business data and stores it in a database. Prepares to generate a digital twin based on this data.

[1422] Server: Analyzes business processes and creates a digital twin model that mimics those processes. Sets the necessary data in the digital twin and performs a simulation of its operation.

[1423] 2. Business execution and operation records

[1424] Terminal: The digital twin is placed in a virtual office environment, allowing users to view it through a user interface.

[1425] Digital Twin: Perform routine tasks in a virtual office environment, such as document sorting, data entry, and initial response to inquiries.

[1426] Server: Collects and stores a detailed record of the digital twin's daily operations.

[1427] 3. Business analysis and learning

[1428] Server: Analyzes business processes based on collected operational records. Analyzes past operational records to identify patterns and trends.

[1429] Server: Extracts tasks that are likely to occur again and has the digital twin learn those tasks.

[1430] Server: Inputs new business knowledge into the digital twin, expanding its scope of operations, and performs learning processes to improve the digital twin's business processing capabilities.

[1431] 4. Proposals for improving efficiency

[1432] Server: Further analyze the details of your business data to identify areas that are particularly time-consuming.

[1433] Server: Proposes efficiency improvements and presents specific improvement measures and efficiency methods to users.

[1434] Server: Trains the digital twin to work in new ways based on efficiency suggestions, for example adding new processes such as auto-completion of input formats and auto-classification of data.

[1435] 5. Implementing the Emotion Engine

[1436] Server: Collects emotional data such as the user's facial expressions, tone of voice, and text messages through the emotion engine.

[1437] Emotion Engine: Analyzes emotion data and recognizes the user's emotional state, including positive emotions, negative emotions, stress levels, etc.

[1438] Server: Determines the user's current emotional state based on the emotional data provided by the emotion engine.

[1439] 6. Improving business efficiency based on emotional data

[1440] Server: Adjusts work progress and suggestions based on emotional data. For example, if a user is feeling stressed, the server can temporarily have the digital twin take over the work.

[1441] Server: The emotion engine trains the digital twin with the emotional data recognized by the engine, enabling the digital twin to respond according to the user's emotional state.

[1442] Specific examples

[1443] Example 1: Improving efficiency of document management

[1444] 1. Data collection and digital twin generation

[1445] User: Inputs document management data into the system.

[1446] Server: Collects business data such as document classification and storage location input, and generates a digital twin based on that data.

[1447] 2. Business execution and operation records

[1448] Digital twin: Performs document classification and storage location entry tasks.

[1449] Server: Records the digital twin's behavior and collects the logs.

[1450] 3. Business analysis and learning

[1451] Server: Analyzes work patterns based on operation records and teaches the digital twin how to do the next job.

[1452] 4. Proposals for improving efficiency

[1453] Server: Conducts detailed analysis of document management data and proposes specific methods for improving efficiency, such as automatically suggesting file names and setting classification rules.

[1454] 5. Implementing the Emotion Engine

[1455] Emotion Engine: Recognizes and records the emotions users feel while managing documents in real time.

[1456] 6. Improving business efficiency based on emotional data

[1457] Server: Based on the user's emotional data, it identifies areas that cause particular stress and makes suggestions to have those areas of work taken over by the digital twin.

[1458] Example 2: Improving the efficiency of inquiry response operations

[1459] 1. Data collection and digital twin generation

[1460] User: Inputs data for inquiry handling work.

[1461] Server: Generates a digital twin based on past response history and FAQs.

[1462] 2. Business execution and operation records

[1463] Digital Twin: Respond to initial inquiries based on FAQs.

[1464] Server: Collects the digital twin's response as a log.

[1465] 3. Business analysis and learning

[1466] Server: Analyzes operational records and teaches the digital twin new knowledge for the next inquiry response.

[1467] 4. Proposals for improving efficiency

[1468] Server: Based on the analysis results of inquiry response operations, it proposes, for example, automatic updates to FAQs and revisions to response classifications.

[1469] 5. Implementing the Emotion Engine

[1470] Emotion engine: Recognizes user emotions in real time and analyzes work stress and satisfaction.

[1471] 6. Improving business efficiency based on emotional data

[1472] Server: Based on the user's emotional data, the digital twin adjusts its response and learns ways to respond in a way that minimizes stress.

[1473] These specific examples allow users to use the system efficiently, improving the quality and speed of their work, as well as adjusting their workload according to their emotions.

[1474] The processing flow will be explained below.

[1475] Data collection and digital twin generation

[1476] Step 1:

[1477] User: Log in to the system. Enter your login information (user ID and password) and wait for authentication.

[1478] Step 2:

[1479] Server: Receives user authentication information and performs authentication. If authentication is successful, grants access to the user.

[1480] Step 3:

[1481] User: Inputs business data, such as operation history, document uploads, and business details.

[1482] Step 4:

[1483] Server: Organizes the collected business data and stores it in a database. Prepares to start analyzing business processes.

[1484] Step 5:

[1485] Server: Analyzes business processes and creates a digital twin model that mimics those processes. Sets the necessary data in the digital twin and performs a simulation of its operation.

[1486] Business execution and operation records

[1487] Step 1:

[1488] Terminal: The digital twin is placed in a virtual office environment, and users can view it through a user interface.

[1489] Step 2:

[1490] Digital Twin: Perform routine tasks in a virtual office environment, such as document sorting, data entry, and initial response to inquiries.

[1491] Step 3:

[1492] Server: Collects and stores a detailed record of the digital twin's daily operations.

[1493] Business Analysis and Learning

[1494] Step 1:

[1495] Server: Analyzes business processes based on collected operational records. Analyzes past operational records to identify patterns and trends.

[1496] Step 2:

[1497] Server: Extracts tasks that are likely to occur again and has the digital twin learn those tasks.

[1498] Step 3:

[1499] Server: Inputs new business knowledge into the digital twin, expanding its scope of operations, and performs learning processes to improve the digital twin's business processing capabilities.

[1500] Efficiency proposals

[1501] Step 1:

[1502] Server: Further analyze the details of your business data to identify areas that are particularly time-consuming.

[1503] Step 2:

[1504] Server: Proposes efficiency improvements and presents specific improvement measures and efficiency methods to users.

[1505] Step 3:

[1506] Server: Trains the digital twin to work in new ways based on efficiency suggestions, for example adding new processes such as auto-completion of input formats and auto-classification of data.

[1507] Implementing the Emotion Engine

[1508] Step 1:

[1509] Server: Collects emotional data such as the user's facial expressions, tone of voice, and text messages through the emotion engine.

[1510] Step 2:

[1511] Emotion Engine: Analyzes emotion data and recognizes the user's emotional state, identifying positive emotions, negative emotions, stress levels, etc.

[1512] Step 3:

[1513] Server: Determines the user's current emotional state based on the emotional data provided by the emotion engine.

[1514] Improving business efficiency based on emotional data

[1515] Step 1:

[1516] Server: Adjusts work progress and suggestions based on emotional data. For example, if a user is feeling stressed, the server can temporarily have the digital twin take over the work.

[1517] Step 2:

[1518] Server: Provides information to improve work efficiency based on emotional data. For example, suggests ways to relax during stressful work.

[1519] Step 3:

[1520] Server: The emotion engine recognizes the emotional data and trains the digital twin. The digital twin responds according to the user's emotional state, improving work efficiency.

[1521] Specific examples

[1522] Example 1: Improving efficiency of document management

[1523] Step 1:

[1524] User: Inputs document management data into the system.

[1525] Step 2:

[1526] Server: Collects business data such as document classification and storage location input, and generates a digital twin based on that data.

[1527] Step 3:

[1528] Digital twin: Performs document classification and storage location entry tasks.

[1529] Step 4:

[1530] Server: Records the digital twin's behavior and collects the logs.

[1531] Step 5:

[1532] Emotion engine: Analyzes facial expressions and voices while users are performing document management tasks to collect emotional data.

[1533] Step 6:

[1534] Server: Based on the analysis results of document management tasks and user emotion data, it makes suggestions for efficiency improvements, such as automatically suggesting file names and setting classification rules.

[1535] Example 2: Improving the efficiency of inquiry response operations

[1536] Step 1:

[1537] User: Inputs data for inquiry handling work.

[1538] Step 2:

[1539] Server: Generates a digital twin based on past response history and FAQ data.

[1540] Step 3:

[1541] Digital Twin: Respond to initial inquiries based on FAQs.

[1542] Step 4:

[1543] Server: Collects the digital twin's response as a log.

[1544] Step 5:

[1545] Emotion Engine: Recognizes and records the emotions users feel while handling inquiries in real time.

[1546] Step 6:

[1547] Server: Based on the analysis of inquiry response work and emotional data, it makes suggestions for improving efficiency and reducing stress. For example, it automatically updates FAQs and reviews response classifications.

[1548] This improves the quality and speed of work and enables workload adjustment according to the user's emotions.

[1549] Example 2

[1550] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1551] In today's business environment, improving business efficiency is an important issue. Previous systems collected and analyzed business data, but they did not achieve comprehensive efficiency by simulating actual business processes in a virtual environment and incorporating user emotional data. The purpose of this invention is to provide a more advanced business management system that improves business efficiency and reduces the psychological burden on users by utilizing digital twins and an emotion engine.

[1552] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1553] In this invention, the server includes means for collecting real-world business data, means for generating a digital twin in a virtual office environment, means for the generated digital twin to execute the business, means for collecting operation records of the business executed by the digital twin, means for analyzing the business based on the collected operation records, means for having the digital twin learn new business based on the analysis results, means for proposing methods for improving efficiency based on business data, and means for recognizing user emotional data and reflecting it in the business process. This makes it possible to simultaneously execute and streamline business operations and adjust the workload according to the user's emotional state.

[1554] "Real-world business data" refers to various data (e.g., operation history, documents, inquiry details) generated in the daily operations of a company or organization.

[1555] "Virtual office environment" refers to a work environment that is virtually recreated using computer simulation.

[1556] "Digital twin" refers to a digital model that mimics and simulates real-world physical processes or systems in a virtual environment.

[1557] "Means of performing business operations" refers to the digital twin's ability to actually perform routine tasks (e.g., document classification, data entry, and responding to inquiries).

[1558] "Operation records" refer to detailed logs of the operations performed by the digital twin, including the operation history and execution time of the operations.

[1559] "Means for analyzing business operations" refers to the function of analyzing collected operational records and identifying patterns and trends in business processes.

[1560] "Means of business learning" refers to the process of inputting new business knowledge and skills into the digital twin based on the analysis results.

[1561] "Means to propose efficiency improvements" refers to a function that performs detailed analysis of business data and presents specific improvement measures and efficiency methods to the user.

[1562] "Emotional data" refers to data that indicates a user's emotional state, such as facial expressions, tone of voice, or text messages.

[1563] An "emotion engine" refers to a system that analyzes a user's emotional data and recognizes the user's emotional state based on the results.

[1564] This invention is a system for generating a digital twin in a virtual office environment based on real-world business data, thereby improving business efficiency. Furthermore, by combining it with an emotion engine that recognizes user emotion data, it is possible to achieve more comprehensive business efficiency. A specific implementation method of this system will be described below.

[1565] System configuration

[1566] This system consists of a server, a terminal (user interface), a digital twin, and an emotion engine.

[1567] server

[1568] The server has the following main functions:

[1569] 1. Function to collect business data

[1570] 2. Function to generate digital twins based on business data

[1571] 3. Ability to collect and analyze digital twin operation records

[1572] 4. A function that makes suggestions for improving business efficiency

[1573] 5. Function to analyze user emotional data using an emotion engine

[1574] Hardware and Software

[1575] Hardware

[1576] Server: A server with high-performance computing power is required, specifically a cloud server or on-premise server with sufficient CPU, memory and storage.

[1577] Terminals: Includes devices used by users, such as PCs, tablets, and smartphones. These terminals are connected to the Internet and are capable of data communication with servers.

[1578] software

[1579] Data collection: Database management system (e.g. MongoDB, MySQL)

[1580] Data analysis: Data analysis libraries (Python Pandas, NumPy)

[1581] Digital twin generation: Simulation tools (AnyLogic, MATLAB)

[1582] Machine Learning: Machine learning frameworks (e.g. TensorFlow, scikit-learn)

[1583] Sentiment analysis: Natural language processing libraries (e.g., NLTK, SpaCy), speech analysis tools (Google Cloud Speech-to-Text), facial recognition libraries (OpenCV)

[1584] What the program does

[1585] User Authentication and Data Collection

[1586] User: Logs in to the system and inputs business data into the system. Specifically, he uploads documents in PDF format or CSV files.

[1587] Server: Stores the business data provided by the user in a database. Pandas and NumPy are used for data analysis.

[1588] Digital Twin Generation

[1589] Server: Based on the data, the business process is analyzed and a digital twin is generated. The generated digital twin is simulated in a virtual office environment and performs business operations.

[1590] Simulation tools: AnyLogic and MATLAB are used to simulate the operation of the digital twin.

[1591] Collection of operational records and business analysis

[1592] Server: Collects and stores in a database the operation records of the tasks performed by the digital twin. These operation records include the operation history and execution time of the tasks.

[1593] Proposals for improving business efficiency

[1594] Server: Uses machine learning algorithms to optimize business processes based on operational records.

[1595] Machine learning: Uses TensorFlow and scikit-learn to analyze business patterns and generate efficiency suggestions.

[1596] Implementing the Emotion Engine

[1597] Server: Analyzes the user's emotional data using the emotion engine. Specifically, it understands the user's emotional state through facial expression recognition, voice analysis, and text analysis.

[1598] Emotion engine: Facial expression data is analyzed using OpenCV, voice data is analyzed using Google Cloud Speech-to-Text, and text messages are analyzed using SpaCy and NLTK.

[1599] Specific examples

[1600] Streamlining document management

[1601] 1. User: Inputs document management data into the system.

[1602] 2. Server: Collects business data such as document classification and storage location information, and generates a digital twin based on that data.

[1603] 3. Digital Twin: Performs document classification and storage location entry tasks.

[1604] 4. Server: Records the digital twin's operations and collects the logs.

[1605] 5. Server: Performs detailed analysis of document management data and proposes specific methods for improving efficiency, such as automatically suggesting file names and setting classification rules.

[1606] 6. Emotion Engine: Recognizes and records the emotions users feel while managing documents in real time.

[1607] Improving efficiency of inquiry response operations

[1608] 1. User: Inputs data for inquiry handling operations.

[1609] 2. Server: Generates a digital twin based on past response history and FAQs.

[1610] 3. Digital Twin: Respond to initial inquiries based on FAQs.

[1611] 4. Server: Collects the digital twin's response as a log.

[1612] 5. Server: Analyzes the operational records and teaches the digital twin new knowledge to respond to the next inquiry.

[1613] 6. Emotion Engine: Recognizes user emotions in real time and analyzes work stress and satisfaction.

[1614] Prompt Sentence Examples

[1615] Below are examples of prompts to encourage the operation of this system.

[1616] Document management optimization prompt example:

[1617] Collect data on document management tasks and provide suggestions for efficient classification and storage locations. Also, monitor the user's stress level while managing each document, and if stress levels are high, have that part of the task be taken over by the digital twin.

[1618] Example prompt for inquiry response optimization:

[1619] Based on the data of customer service operations, optimize FAQs and provide appropriate responses to initial inquiries. Recognize users' emotional data in real time, train your digital twin to respond according to their emotional state, and implement stress-relief measures.

[1620] These concrete examples and prompts allow users to use the system efficiently, improving the quality and speed of their work, as well as adjusting their workload according to their emotions.

[1621] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1622] Step 1:

[1623] User Authentication and Data Collection

[1624] User: Log in to the system by entering your username and password, pressing the login button and waiting for authentication.

[1625] Input: Username, Password

[1626] Output: Authentication token, user access rights

[1627] Server: Checks the user credentials against a database to authenticate them. If authentication is successful, generates an authentication token and grants access to the user.

[1628] Behavior: The user information is matched against a database (e.g. MySQL) for authentication. If authentication is successful, an authentication token is generated and a user session is started.

[1629] Step 2:

[1630] Entering and saving business data

[1631] User: Uploads business data (e.g., documents, operation history, inquiry details) to the system by dragging and dropping PDF or CSV files through the interface.

[1632] Input: Business data (PDF files, CSV files, etc.)

[1633] Output: Message indicating that data has been saved to the business database

[1634] Server: Receives uploaded files, stores them in a database, and extracts and organizes the file contents using OCR and data analysis tools.

[1635] How it works: After receiving the file, it uses OCR software (e.g., Tesseract OCR) to extract the text information, organizes the data using Python's Pandas or NumPy, and stores it in MongoDB or MySQL.

[1636] Step 3:

[1637] Digital Twin Generation

[1638] Server: Analyzes collected business data and generates a digital twin model. Business processes are reproduced in a virtual office environment using simulation tools (e.g., AnyLogic, MATLAB).

[1639] Input: Organized business data

[1640] Output: Digital twin model generation complete message

[1641] Operation: Analyze business data using data analysis libraries (Pandas, NumPy), then create a digital twin model using AnyLogic or MATLAB. Run a simulation to confirm the operation of the digital twin.

[1642] Step 4:

[1643] Business execution and operation recording

[1644] Terminal: Launches a virtual office environment and displays the interface through which the digital twin performs its work.

[1645] Input: Digital twin model

[1646] Output: Business execution visualization interface

[1647] Digital twin: Performs routine tasks such as document sorting, data entry, and handling inquiries.

[1648] How it works: The digital twin uses OCR to classify documents, natural language processing (NLP) to process queries, and records the process of how work is performed in real time.

[1649] Step 5:

[1650] Collection of operational records and business analysis

[1651] Server: Collects the digital twin's operational records in a database. The operational records include the operation history and execution time of the business.

[1652] Input: Digital twin operation record (log data)

[1653] Output: Analysis report

[1654] Action: Action records are stored in a database (MongoDB, MySQL) and analyzed using machine learning algorithms (e.g. TensorFlow, scikit-learn) to identify patterns and trends in business processes.

[1655] Step 6:

[1656] Proposals for improving business efficiency

[1657] Server: Optimizes business processes based on the analysis results of operational records, proposes specific improvement measures, and presents them to the user in a report.

[1658] Input: Analysis results, output of optimization algorithms

[1659] Output: Efficiency proposal report

[1660] How it works: Optimize business processes using machine learning models and create reports that suggest specific efficiency measures (e.g., RPA implementation, automatic classification).

[1661] Step 7:

[1662] Emotion engine implementation and emotion analysis

[1663] Server: Collects and analyzes user emotion data through the emotion engine and reflects it in business processes.

[1664] Input: User emotion data (facial expression, voice, text)

[1665] Output: A report of the user's emotional state

[1666] How it works: We use OpenCV to analyze facial expression data, Google Cloud Speech-to-Text to analyze audio data, and SpaCy and NLTK to analyze text data to assess the user's emotional state.

[1667] Step 8:

[1668] Integrated business efficiency

[1669] Server: Integrates emotional data and business data to adjust how work proceeds.

[1670] Input: Emotion data, business data

[1671] Output: Workload adjustment plan

[1672] How it works: Dynamically adjusts workload based on the user's stress level and allows the digital twin to take over certain tasks, improving overall operational efficiency.

[1673] Through these steps, this system executes a consistent process from collecting and analyzing business data, generating digital twins, to utilizing emotion data, helping to improve business efficiency.

[1674] (Application example 2)

[1675] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1676] The objective of this invention is to improve the efficiency of food delivery services and manage the stress of delivery workers. Previous systems did not adequately collect and analyze data specific to delivery work, and also lacked work suggestions that took into account the emotional state of delivery workers. As a result, work optimization and stress reduction for delivery workers were not effectively achieved. A new approach to solving this problem is needed.

[1677] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1678] In this invention, the server includes means for collecting real-world business data, means for generating a digital twin in a virtual office environment based on the collected data, means for the generated digital twin to execute business operations, means for collecting operation records of the business operations executed by the digital twin, means for analyzing the business operations based on the collected operation records, means for having the digital twin learn new business operations based on the analysis results, means for proposing methods for improving efficiency based on the business data, means for collecting and analyzing business data specialized for delivery operations, means for collecting and analyzing emotional data of delivery personnel, and means for learning and proposing business methods based on delivery efficiency and the emotional data of delivery personnel. This makes it possible to improve the efficiency of food delivery operations and manage the emotions of delivery personnel.

[1679] "Real business data" refers to all data related to business operations carried out in a real environment.

[1680] A "virtual office environment" is a computer-generated virtual environment that mimics real-world office activities.

[1681] "Digital twin" is a technology that recreates real-world business processes as digital models and uses them to improve business efficiency and optimization.

[1682] "Operation records" are data that record the entire process of work performed by a digital twin.

[1683] "Business analysis" is the process of evaluating business performance based on collected data and operational records and identifying areas for improvement.

[1684] "Methods for improving efficiency" are methodologies for improving business performance, such as reducing work time, cutting costs, and improving the quality of deliverables.

[1685] "Delivery" is the service process of delivering ordered products to a specific location of a customer.

[1686] "Emotional data" is data that indicates the mental state of the delivery person and is obtained through facial expression analysis, voice analysis, text analysis, etc.

[1687] "Business methods" refer to the procedures and techniques required to carry out business.

[1688] An embodiment of the present invention includes a system for collecting real-world business data and generating a digital twin in a virtual office environment based on the collected data. This embodiment will be described in detail below.

[1689] The system program mainly consists of the following hardware and software:

[1690] Hardware: Smartphone (for delivery staff), server (cloud or on-premise)

[1691] Software: Python (programming language), Pandas (data analysis library), JSON (data format)

[1692] The server collects data related to delivery operations and generates a digital twin based on that data. This digital twin simulates the delivery process in a virtual office environment to improve efficiency. The server also has the ability to collect and analyze emotional data from delivery personnel. The results of this analysis are useful for optimizing deliveries and reducing stress for delivery personnel. This data is used to analyze operations and make suggestions for improving delivery methods, especially in the case of delivery delays or customer feedback.

[1693] The device (smartphone) collects real-time data on delivery behavior and emotional state of the delivery person while they are performing their delivery duties. This is achieved by continuously sending data entered by the delivery person on the app, such as the delivery address, delivery time, customer feedback, and the delivery person's emotional state, to a server.

[1694] For example, if delivery time exceeds 30 minutes or negative feedback is received, the system on the server analyzes this data and suggests optimizing delivery routes and readjusting delivery areas, thereby improving delivery efficiency and managing stress for delivery personnel.

[1695] The system also implements algorithms to learn new work methods and improve efficiency. This allows the system to constantly learn and apply the latest work methods. For example, if a delivery person is feeling stressed, the server will use that emotional data to suggest having the digital twin temporarily take over the work.

[1696] An example of a prompt is as follows:

[1697] I would like to know how to generate a digital twin based on operational data from a food delivery service to optimize delivery efficiency, and how to make suggestions using emotional data. Specifically, I would like to hear about a system that collects and analyzes delivery order IDs, delivery addresses, delivery times, customer feedback, and delivery personnel's emotional data to make suggestions to improve delivery efficiency.

[1698] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1699] Step 1:

[1700] A user logs in

[1701] Input: The user enters a user ID and password to log in to the system.

[1702] Processing: The server authenticates the entered user ID and password. The authentication process involves retrieving and verifying user information from a database.

[1703] Output: If authentication is successful, grant access to the user, or if authentication fails, display an error message.

[1704] Step 2:

[1705] Business data collection

[1706] Input: The user enters data related to the delivery job (delivery order ID, delivery address, delivery time, customer feedback, etc.).

[1707] Processing: The terminal collects the input data in real time and sends it to the server, unifying the data format and checking the required fields.

[1708] Output: The server stores the collected data in a database, which is used to generate a digital twin and for subsequent analysis.

[1709] Step 3:

[1710] Digital Twin Generation

[1711] Input: Collected business data

[1712] Processing: The server analyzes the collected business data and generates a digital twin that mimics business processes in a virtual office environment, including defining the business flow and setting up the simulation model.

[1713] Output: The resulting digital twin is a virtual model of the actual work environment that can be viewed by the user and placed in the virtual office environment.

[1714] Step 4:

[1715] Execution of work and collection of operational records

[1716] Input: Business execution results using digital twin

[1717] Processing: The digital twin performs routine tasks in the virtual office environment and records their actions. The terminal monitors the delivery person's actions and history in real time during deliveries and sends the data to the server.

[1718] Output: The collected operation records are stored in a database as detailed logs. This data is used to analyze operations and provide suggestions for improving efficiency.

[1719] Step 5:

[1720] Emotion data collection and analysis

[1721] Input: Delivery person's emotional data (facial expressions, voice, text messages, etc.)

[1722] Processing: The server uses an emotion engine to analyze the delivery person's emotional data and recognize their emotional state (positive, negative, stress level, etc.). This analysis is performed using emotion recognition algorithms and machine learning models.

[1723] Output: As a result of the analysis, the emotional state of the delivery person is stored on the server and used to make suggestions for delivery efficiency and emotion management.

[1724] Step 6:

[1725] Business analysis and efficiency proposals

[1726] Input: Collected business data and emotional data

[1727] Processing: The server analyzes business processes based on the collected data, identifying areas that are particularly time-consuming and that could be improved. It then generates specific recommendations for improving efficiency (e.g., changing delivery routes or readjusting delivery areas). Data analytics techniques and algorithms are used for the analysis.

[1728] Output: The generated suggestions are fed back to the user and further train the digital twin as a new way of working.

[1729] Step 7:

[1730] Learning business methods and implementing proposals

[1731] Input: Efficiency suggestions and new ways of working

[1732] Processing: The server trains the digital twin on the proposed new work methods and applies them the next time the work is performed, resulting in continuous improvement of the system.

[1733] Output: Improved operational methods are reflected in the digital twin, and are expected to have an impact on actual delivery operations.

[1734] This system will enable the efficiency of food delivery operations and the management of delivery personnel's emotions.

[1735] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1736] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1737] 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 the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1738] [Fourth embodiment]

[1739] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1740] 7, a 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.

[1741] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1742] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1743] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1744] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1745] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1746] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1747] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1748] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1749] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1750] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1751] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1752] The present invention is a system for generating a digital twin in a virtual office environment based on real-world business data, thereby improving business efficiency. The processing content of the program of this system is explained below in natural language.

[1753] Program processing overview

[1754] 1. Data collection and digital twin generation

[1755] User: Logging in to the system is a fundamental step in protecting and managing business data.

[1756] Server: Receives the user's authentication information and performs authentication. If authentication is successful, grants the user access rights and prepares to collect business data.

[1757] User: Inputs business data. This refers to data such as operation history, document uploads, and business details.

[1758] Server: Generates a digital twin based on collected business data, including analysis and modeling of business processes.

[1759] 2. Business execution and operation records

[1760] Terminal: The digital twin is placed in a virtual office environment, and users can view it through a user interface.

[1761] Digital twin: Performs actual tasks, such as sorting documents, entering data, and handling initial inquiries, mimicking the routine tasks that users normally perform.

[1762] Server: Collects daily operational records of the digital twin, which are stored as detailed logs for later analysis.

[1763] 3. Business analysis and learning

[1764] Server: Analyzes operations based on the digital twin's operational records. Analyzes past operational records to identify operational patterns and opportunities for efficiency improvements.

[1765] Server: Extracts the likely next occurrence of the same task. Based on this information, the digital twin learns new business processes.

[1766] Server: Input new business knowledge into the digital twin and expand the scope of business. This step will further improve the efficiency of the next business operation.

[1767] 4. Proposals for improving efficiency

[1768] Server: Analyze business data in detail to identify areas that take particularly long. For example, automate data entry, automatically suggest file names, etc.

[1769] Server: Proposes ways to improve efficiency. Presents specific improvement measures and efficiency techniques to the user. This information is then used to train the digital twin.

[1770] Server: By repeating the above steps, the digital twin gradually improves its business processing capabilities.

[1771] Specific examples

[1772] Example 1: Improving efficiency of document management

[1773] 1. Data collection and digital twin generation

[1774] User: Inputs document management data into the system.

[1775] Server: Collects business data such as document classification and storage location input, and generates a digital twin based on that data.

[1776] 2. Business execution and operation records

[1777] Digital twin: Performs document classification and storage location entry tasks.

[1778] Server: Records the digital twin's behavior and collects the logs.

[1779] 3. Business analysis and learning

[1780] Server: Analyzes work patterns based on operation records and teaches the digital twin how to do the next job.

[1781] 4. Proposals for improving efficiency

[1782] Server: Conducts detailed analysis of document management data and proposes specific methods for improving efficiency, such as automatically suggesting file names and setting classification rules.

[1783] Example 2: Improving the efficiency of inquiry response operations

[1784] 1. Data collection and digital twin generation

[1785] User: Inputs data for inquiry handling work.

[1786] Server: Generates a digital twin based on past response history and FAQs.

[1787] 2. Business execution and operation records

[1788] Digital Twin: Respond to initial inquiries based on FAQs.

[1789] Server: Collects the digital twin's response as a log.

[1790] 3. Business analysis and learning

[1791] Server: Analyzes operational records and teaches the digital twin new knowledge for the next inquiry response.

[1792] 4. Proposals for improving efficiency

[1793] Server: Based on the analysis results of inquiry response operations, it proposes, for example, automatic updates to FAQs and revisions to response classifications.

[1794] These examples allow users to use the system efficiently and improve the quality and speed of their work.

[1795] The processing flow will be explained below.

[1796] Data collection and digital twin generation

[1797] Step 1:

[1798] User: Log in to the system, enter login information and wait for authentication.

[1799] Step 2:

[1800] Server: Receives user authentication information and performs authentication. If successful, grants access to the user.

[1801] Step 3:

[1802] User: Inputs business data, such as operation history, document uploads, and business details.

[1803] Step 4:

[1804] Server: Organizes collected business data and stores it in a database. Prepares to generate a digital twin based on this data.

[1805] Step 5:

[1806] Server: Analyzes business processes and creates a digital twin model that mimics those processes. Sets the necessary data in the digital twin and performs a simulation of its operation.

[1807] Business execution and operation records

[1808] Step 1:

[1809] Terminal: The digital twin is placed in a virtual office environment, allowing users to view it through a user interface.

[1810] Step 2:

[1811] Digital Twin: Perform routine tasks in a virtual office environment, such as document sorting, data entry, and initial response to inquiries.

[1812] Step 3:

[1813] Server: Collects and stores a detailed record of the digital twin's daily operations.

[1814] Business Analysis and Learning

[1815] Step 1:

[1816] Server: Analyzes business processes based on collected operational records. Analyzes past operational records to identify patterns and trends.

[1817] Step 2:

[1818] Server: Extracts tasks that are likely to occur again and has the digital twin learn those tasks.

[1819] Step 3:

[1820] Server: Inputs new business knowledge into the digital twin, expanding its scope of operations, and performs learning processes to improve the digital twin's business processing capabilities.

[1821] Efficiency proposals

[1822] Step 1:

[1823] Server: Further analyze the details of your business data to identify areas that are particularly time-consuming.

[1824] Step 2:

[1825] Server: Proposes efficiency improvements and presents specific improvement measures and efficiency methods to users.

[1826] Step 3:

[1827] Server: Trains the digital twin to work in new ways based on efficiency suggestions, for example adding new processes such as auto-completion of input formats and auto-classification of data.

[1828] This allows users to process more than twice as much work in the same amount of time, improving work efficiency.

[1829] Example 1

[1830] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1831] There is a demand for systems that can carry out business efficiently and accurately based on real business data. However, currently, there is a lack of tools to streamline and optimize business processes, and a lot of time and effort is spent on manual data entry and classification. As a result, there is an issue of reduced business efficiency and difficulty in improving productivity.

[1832] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1833] In this invention, the server includes: means for a user to enter authentication information and log in to the system; means for performing user authentication and collecting business data; means for generating a digital twin using an analysis tool based on the collected business data; means for placing the generated digital twin in a virtual office environment and providing a user interface; means for the digital twin to imitate and execute real-world business operations; means for collecting operation records of the digital twin in real time and storing them in a database; means for analyzing the operation record data and identifying business patterns; means for having the digital twin learn new business processes to improve business efficiency in the next business operation; and means for proposing methods for improving business efficiency based on the analysis results, thereby enabling business efficiency improvement and optimization.

[1834] "User authentication" is the process of verifying a user's identity when accessing a system. Authentication information includes a user ID and password.

[1835] "Business data" refers to information related to business processes, and includes, for example, operation history, document information, input data, and the like.

[1836] A "digital twin" is a digital model that recreates real-world business processes and systems in a virtual environment, with the aim of replicating and executing business processes.

[1837] A "virtual office environment" is a workspace that digitally recreates an actual office environment, and is a virtual space in which a digital twin is placed.

[1838] A "user interface" is an interface that allows a user to directly interact with the system, allowing them to operate and monitor the digital twin.

[1839] "Operation records" refer to detailed operation logs and execution histories of the tasks performed by the digital twin. These are collected in real time and stored in a database.

[1840] "Analysis tools" generally refer to software and algorithms that process and analyze collected data, and are used to generate digital twins and analyze business processes.

[1841] "Business patterns" refer to the characteristic flow of business execution processes and procedures obtained by analyzing business data.

[1842] A "business process" refers to a series of procedures and operations required to carry out a specific task, and new business processes are learned by the digital twin.

[1843] "Efficiency methods" refer to specific techniques and proposals for reducing work time and costs and improving productivity.

[1844] MODE FOR CARRYING OUT THE INVENTION

[1845] The present invention provides a system for generating a digital twin in a virtual office environment based on real-world business data, thereby improving business efficiency. This system is implemented using multiple hardware and software components.

[1846] Data Collection and User Authentication

[1847] 1. User: First logs in to the system, entering their user ID and password as identification information to begin the authentication process.

[1848] 2. Server: Receives user authentication information and compares it with the database. A high-performance server (e.g., Dell PowerEdge R740) is used for this. If authentication is successful, the user is granted access rights and business data can be collected.

[1849] Digital Twin Generation

[1850] 3. User: Inputs business data, specifically, uploads operation history, document information, business details, etc. to the system.

[1851] 4. Server: Generates a digital twin based on the collected data using data analysis tools (e.g., Python's Pandas library) and digital twin generation software (e.g., Ansys Twin Builder). The analyzed data is built as a virtual model and deployed in a virtual office environment.

[1852] Business execution and operation recording

[1853] 5. Terminal: The digital twin is placed in a virtual office environment and a user interface is provided (e.g., Microsoft Azure Digital Twins). Users can use this interface to observe and manipulate the behavior of the digital twin in real time.

[1854] 6. Digital Twin: Mimics real-world business processes and performs tasks such as document sorting, data entry, and handling inquiries.

[1855] 7. Server: Collects the digital twin's operational records in real time and stores them in a database. These records are used for analysis.

[1856] Business Analysis and Learning

[1857] 8. Server: Analyze business patterns based on collected operational records. Use analysis tools to identify areas where efficiency can be improved.

[1858] 9. Server: Uses machine learning models (e.g., TensorFlow) to teach the digital twin new processes that will be useful for the next job.

[1859] Efficiency proposals

[1860] 10. Server: Analyzes business data in detail and proposes ways to improve efficiency. For example, it suggests specific improvement measures such as automating data entry and automatically suggesting file names.

[1861] 11. Server: Reflects the proposed efficiency improvements in the digital twin and optimizes the next business process.

[1862] Specific examples

[1863] Example 1: Improving efficiency of document management

[1864] User: Inputs document management data into the system. Specifically, uploads the Excel file "Business Data.xlsx."

[1865] Server: Uses data analysis tools to automate document classification and storage location, generating a digital twin that is then placed in a virtual office environment.

[1866] Example 2: Improving the efficiency of inquiry response operations

[1867] User: Inputs data related to inquiries into the system. Specifically, inputs past response history and FAQ data.

[1868] Server: A digital twin is generated based on the collected data and placed in a virtual office environment. The digital twin responds to initial inquiries and records the results on the server.

[1869] Prompt Sentence Examples

[1870] "Please explain the steps to input business data and generate a digital twin."

[1871] "Please give us a concrete example of how a digital twin can be used to streamline document management operations."

[1872] "Please explain how a digital twin can help improve the efficiency of your inquiry response operations."

[1873] As described above, the present invention effectively collects and analyzes business data and optimizes business processes using digital twins, thereby achieving significant improvements in business efficiency and labor savings.

[1874] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1875] Step 1:

[1876] User: Log in to the system. Enter your user ID and password and click the "Login" button.

[1877] Input: User ID, Password

[1878] Output: Authentication token, access granted

[1879] Specific operation: The user enters the user ID "user123" and password "password123" on the system login screen, for example, and clicks the "Login" button.

[1880] Step 2:

[1881] Server: Receives the user's authentication information and checks it against a database.

[1882] Input: User ID, Password

[1883] Output: Authentication result (success / failure), authentication token

[1884] Specific operation: The server receives the user ID "user123" and password "password123", checks it against the database, and if authentication is successful, generates a token and grants access rights to the user.

[1885] Step 3:

[1886] User: Input business data. For example, upload the "BusinessData.xlsx" file.

[1887] Input: Business data file (e.g., businessdata.xlsx)

[1888] Output: Business data collection

[1889] Specific operation: After logging in, click the "Upload business data" button from the dashboard, select "Business data.xlsx" in the file selection dialog, and upload it.

[1890] Step 4:

[1891] Server: Generates a digital twin based on collected business data.

[1892] Input: Business data file (e.g., businessdata.xlsx)

[1893] Output: Digital twin model

[1894] How it works: The server uses Python's Pandas library to analyze business data and uses Ansys Twin Builder to generate a digital twin model.

[1895] Step 5:

[1896] Terminal: Places the digital twin in a virtual office environment and provides a user interface.

[1897] Input: Digital twin model

[1898] Output: Digital twin on UI

[1899] Specific operation: The server deploys the generated digital twin model to Microsoft Azure Digital Twins and displays it in the user interface.

[1900] Step 6:

[1901] Digital Twin: Imitating and executing real-world operations.

[1902] Input: Business process data

[1903] Output: Work results, operation records

[1904] Specific operations: The digital twin performs document classification, data entry, inquiry response, etc. in a virtual environment, generating business results and action records.

[1905] Step 7:

[1906] Server: Collects digital twin operation records in real time and stores them in a database.

[1907] Input: Digital twin operation record

[1908] Output: Action record database

[1909] Specific operation: The server receives the operation logs recorded by the digital twin and stores them in a database in real time.

[1910] Step 8:

[1911] Server: Analyzes business patterns based on collected operation records.

[1912] Input: Action Record Database

[1913] Output: Business analysis results

[1914] Specific operation: The server analyzes the operation record data using an analysis tool (e.g., Python DataFrame) and identifies business patterns.

[1915] Step 9:

[1916] Server: Trains the digital twin to learn new business processes.

[1917] Input: Business analysis results, new business processes

[1918] Output: Trained digital twin

[1919] Specific operation: Based on the analysis results, the server uses a machine learning model (e.g., TensorFlow) to teach the digital twin new business processes.

[1920] Step 10:

[1921] Server: Conducts detailed analysis of business data and proposes methods for improving efficiency.

[1922] Input: Business data, operation records

[1923] Output: Efficiency proposals

[1924] Specific operation: The server performs detailed data analysis and generates efficiency suggestions, such as "Automating data entry steps can save two hours per day."

[1925] Step 11:

[1926] Server: Reflects the proposed efficiency measures in the digital twin and optimizes the next business process.

[1927] Input: Efficiency proposal

[1928] Output: Optimized business processes

[1929] Specific operation: The server applies the proposed efficiency methods to the digital twin model, allowing the digital twin to learn new business processes and prepare for the next business operation.

[1930] (Application example 1)

[1931] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1932] Traditional production line management in factories requires a great deal of time and effort to improve efficiency and optimization, and efficiency often declines due to the heavy reliance on manual human labor. Furthermore, insufficient analysis and learning based on past operational records can result in waste due to the repetition of the same tasks. Furthermore, there are limited means of immediately applying efficiency suggestions, requiring flexible responses.

[1933] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1934] In this invention, the server includes: means for collecting real-world business data; means for generating a digital twin in a virtual work environment based on the collected data; means for the generated digital twin to execute business operations; means for collecting operation records of the business operations executed by the digital twin; means for analyzing the business operations based on the collected operation records; means for the digital twin to learn new business operations based on the analysis results; means for proposing methods for improving efficiency based on the business data; means for collecting business data of a production line and generating a digital twin; means for the digital twin to imitate production line operations and analyze the operation records to learn the optimal production process; and means for immediately applying the efficiency proposals to the production line. This enables accurate business analysis based on past operation records and specific proposals for improving efficiency, thereby significantly improving the efficiency of the production line.

[1935] "Real-world business data" refers to all data related to work that occurs in real-world environments such as factories and offices. Examples include production line operation data and employee operation records.

[1936] A "virtual work environment" is a digital space that virtually recreates an actual work environment. This eliminates physical constraints, making it easier to perform simulations and optimizations.

[1937] A "digital twin" is a virtual model created based on real-world business data. This model performs the same functions as real systems and business processes, enabling simulation and analysis.

[1938] "Operation records" are historical data of the tasks and actions performed by the digital twin, which are used to evaluate and optimize operations.

[1939] "Means for analyzing work" are methods and techniques for identifying work patterns and opportunities for efficiency improvement based on collected operational records.

[1940] "Means of learning new business" refers to methods and technologies that allow the digital twin to incorporate new business processes and improvement methods, enabling it to operate more efficiently the next time the business is executed.

[1941] "Means for proposing ways to improve efficiency" refers to methods and technologies for analyzing business data, identifying areas for improvement, and making specific proposals for improving efficiency.

[1942] "Production line business data" refers to all data related to the production process, including, for example, the operating status of machines, production volume, and quality inspection results.

[1943] A "production process" is a series of steps to manufacture a product on a production line, including material input, processing, assembly, inspection, and shipping.

[1944] "Means for immediately applying efficiency proposals to the production line" refers to technology that uses digital twins to immediately reflect proposed efficiency methods on the actual production line, enabling rapid improvements.

[1945] The present invention is a digital twin system aimed at improving the efficiency of production lines, and specific embodiments are described below.

[1946] System configuration

[1947] This system, which consists of a server, terminals, and users, has the following main functions:

[1948] 1. Data Collection

[1949] The server collects real-time operational data from the production line through sensors and data input devices, including machine operation data, worker behavior data, and quality inspection results.

[1950] 2. Digital Twin Creation

[1951] The server uses the collected data to create a digital twin in a virtual work environment: a virtual model of the real production line that can accurately mimic its behavior.

[1952] 3. Execution of Business

[1953] The generated digital twin can then be used to virtually execute production line operations via a terminal, recreating the actual production process in a virtual environment.

[1954] 4. Collecting Operational Records

[1955] The server collects records of operations performed by the digital twin, including detailed operational procedures and results.

[1956] 5. Business Analysis

[1957] The server analyzes the collected activity records to identify opportunities for efficiency. This analysis identifies historical patterns and identifies areas for improvement.

[1958] 6. Learning a new job

[1959] Based on the analysis results, the server teaches the digital twin new business processes, allowing it to operate more efficiently the next time the business is executed.

[1960] 7. Efficiency proposals

[1961] The server uses business data to propose ways to improve efficiency, including optimizing production processes, changing processes, and revising work procedures. These proposals are immediately applied to the production line, resulting in rapid improvements.

[1962] Hardware and Software

[1963] This system uses the following hardware and software:

[1964] Hardware: sensors, data input devices, network connection devices, servers

[1965] Software: Software for generating digital twin models, software for data analysis (e.g., Python, Scikit-learn), software for proposing efficiency improvements

[1966] Specific examples

[1967] For example, in a factory's parts assembly line, a server collects operational data from each work station and generates a digital twin based on that data. This digital twin simulates actual assembly work in a virtual environment and analyzes the operational records. Based on the analysis results, new work procedures and process changes are proposed and implemented immediately, significantly improving the efficiency of the assembly line.

[1968] Example prompt sentence:

[1969] Create a virtual environment to optimize your production line and create a digital twin based on operational data. Analyze the collected data, list specific efficiency improvements, and provide steps to implement them.

[1970] As described above, the digital twin system according to the present invention realizes highly accurate efficiency improvements on production lines.

[1971] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1972] Step 1:

[1973] The server collects operational data related to the production line from each work station in the factory through sensors and data input devices. Inputs include machine operation data, worker behavior data, and quality inspection results. This data is sent to the server in real time and saved. The data is organized in JSON format and stored in a database.

[1974] Step 2:

[1975] The server generates a digital twin in a virtual work environment based on the collected business data. The business data collected in step 1 is used as input. Digital twin model generation software is used to create a virtual model of the real production line from that data. This model mimics the real operation in the virtual environment. The output is a digital twin model.

[1976] Step 3:

[1977] The terminal uses the generated digital twin to virtually execute production line operations. The digital twin model is used as input. The production process is reproduced in the virtual environment and operation data is collected. During this process, the digital twin operates in the same way as in reality. The output is an operation log of the digital twin.

[1978] Step 4:

[1979] The server collects and analyzes the operational records of the tasks performed by the digital twin. The operational logs generated in step 3 are used as input. Data analysis software (e.g., Python, Scikit-learn) is used to analyze past operational records and identify patterns and potential for efficiency improvements. The output is the analysis results.

[1980] Step 5:

[1981] The server trains the digital twin to learn new business processes based on the analysis results of the operation records. The analysis results from step 4 are used as input. New business knowledge is input into the digital twin using a machine learning algorithm. The output is a new digital twin model that has completed learning.

[1982] Step 6:

[1983] The server proposes efficiency improvement methods based on business data. The inputs used are the analysis results and the trained digital twin model. Specific improvement measures and efficiency methods are generated using software for proposing efficiency improvements. For example, optimal production processes and revisions to work procedures are proposed. The output is efficiency improvement proposals.

[1984] Step 7:

[1985] The server immediately applies the efficiency improvement proposals to the production line. The efficiency improvement proposals obtained in step 6 are used as input. Specifically, parameters are changed and new work procedures are implemented, and these are reflected in the production line. The output is an efficient new employee production line.

[1986] Through the above steps, the digital twin system of the present invention achieves high-precision efficiency and optimization of production lines.

[1987] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1988] This invention is a system for generating a digital twin in a virtual office environment based on real-world business data, thereby improving business efficiency. Furthermore, by combining it with an emotion engine that recognizes user emotion data, this system achieves more comprehensive business efficiency. The processing content of the program for this system is explained below in natural language.

[1989] Program processing overview

[1990] 1. Data collection and digital twin generation

[1991] User: Log in to the system, enter login information and wait for authentication.

[1992] Server: Receives user credentials and performs authentication. If successful, grants access to the user.

[1993] User: Inputs business data, such as operation history, document uploads, and business details.

[1994] Server: Organizes collected business data and stores it in a database. Prepares to generate a digital twin based on this data.

[1995] Server: Analyzes business processes and creates a digital twin model that mimics those processes. Sets the necessary data in the digital twin and performs a simulation of its operation.

[1996] 2. Business execution and operation records

[1997] Terminal: The digital twin is placed in a virtual office environment, allowing users to view it through a user interface.

[1998] Digital Twin: Perform routine tasks in a virtual office environment, such as document sorting, data entry, and initial response to inquiries.

[1999] Server: Collects and stores a detailed record of the digital twin's daily operations.

[2000] 3. Business analysis and learning

[2001] Server: Analyzes business processes based on collected operational records. Analyzes past operational records to identify patterns and trends.

[2002] Server: Extracts tasks that are likely to occur again and has the digital twin learn those tasks.

[2003] Server: Inputs new business knowledge into the digital twin, expanding its scope of operations, and performs learning processes to improve the digital twin's business processing capabilities.

[2004] 4. Proposals for improving efficiency

[2005] Server: Further analyze the details of your business data to identify areas that are particularly time-consuming.

[2006] Server: Proposes efficiency improvements and presents specific improvement measures and efficiency methods to users.

[2007] Server: Trains the digital twin to work in new ways based on efficiency suggestions, for example adding new processes such as auto-completion of input formats and auto-classification of data.

[2008] 5. Implementing the Emotion Engine

[2009] Server: Collects emotional data such as the user's facial expressions, tone of voice, and text messages through the emotion engine.

[2010] Emotion Engine: Analyzes emotion data and recognizes the user's emotional state, including positive emotions, negative emotions, stress levels, etc.

[2011] Server: Determines the user's current emotional state based on the emotional data provided by the emotion engine.

[2012] 6. Improving business efficiency based on emotional data

[2013] Server: Adjusts work progress and suggestions based on emotional data. For example, if a user is feeling stressed, the server can temporarily have the digital twin take over the work.

[2014] Server: The emotion engine trains the digital twin with the emotional data recognized by the engine, enabling the digital twin to respond according to the user's emotional state.

[2015] Specific examples

[2016] Example 1: Improving efficiency of document management

[2017] 1. Data collection and digital twin generation

[2018] User: Inputs document management data into the system.

[2019] Server: Collects business data such as document classification and storage location input, and generates a digital twin based on that data.

[2020] 2. Business execution and operation records

[2021] Digital twin: Performs document classification and storage location entry tasks.

[2022] Server: Records the digital twin's behavior and collects the logs.

[2023] 3. Business analysis and learning

[2024] Server: Analyzes work patterns based on operation records and teaches the digital twin how to do the next job.

[2025] 4. Proposals for improving efficiency

[2026] Server: Conducts detailed analysis of document management data and proposes specific methods for improving efficiency, such as automatically suggesting file names and setting classification rules.

[2027] 5. Implementing the Emotion Engine

[2028] Emotion Engine: Recognizes and records the emotions users feel while managing documents in real time.

[2029] 6. Improving business efficiency based on emotional data

[2030] Server: Based on the user's emotional data, it identifies areas that cause particular stress and makes suggestions to have those areas of work taken over by the digital twin.

[2031] Example 2: Improving the efficiency of inquiry response operations

[2032] 1. Data collection and digital twin generation

[2033] User: Inputs data for inquiry handling work.

[2034] Server: Generates a digital twin based on past response history and FAQs.

[2035] 2. Business execution and operation records

[2036] Digital Twin: Respond to initial inquiries based on FAQs.

[2037] Server: Collects the digital twin's response as a log.

[2038] 3. Business analysis and learning

[2039] Server: Analyzes operational records and teaches the digital twin new knowledge for the next inquiry response.

[2040] 4. Proposals for improving efficiency

[2041] Server: Based on the analysis results of inquiry response operations, it proposes, for example, automatic updates to FAQs and revisions to response classifications.

[2042] 5. Implementing the Emotion Engine

[2043] Emotion engine: Recognizes user emotions in real time and analyzes work stress and satisfaction.

[2044] 6. Improving business efficiency based on emotional data

[2045] Server: Based on the user's emotional data, the digital twin adjusts its response and learns ways to respond in a way that minimizes stress.

[2046] These specific examples allow users to use the system efficiently, improving the quality and speed of their work, as well as adjusting their workload according to their emotions.

[2047] The processing flow will be explained below.

[2048] Data collection and digital twin generation

[2049] Step 1:

[2050] User: Log in to the system. Enter your login information (user ID and password) and wait for authentication.

[2051] Step 2:

[2052] Server: Receives user authentication information and performs authentication. If authentication is successful, grants access to the user.

[2053] Step 3:

[2054] User: Inputs business data, such as operation history, document uploads, and business details.

[2055] Step 4:

[2056] Server: Organizes the collected business data and stores it in a database. Prepares to start analyzing business processes.

[2057] Step 5:

[2058] Server: Analyzes business processes and creates a digital twin model that mimics those processes. Sets the necessary data in the digital twin and performs a simulation of its operation.

[2059] Business execution and operation records

[2060] Step 1:

[2061] Terminal: The digital twin is placed in a virtual office environment, and users can view it through a user interface.

[2062] Step 2:

[2063] Digital Twin: Perform routine tasks in a virtual office environment, such as document sorting, data entry, and initial response to inquiries.

[2064] Step 3:

[2065] Server: Collects and stores a detailed record of the digital twin's daily operations.

[2066] Business Analysis and Learning

[2067] Step 1:

[2068] Server: Analyzes business processes based on collected operational records. Analyzes past operational records to identify patterns and trends.

[2069] Step 2:

[2070] Server: Extracts tasks that are likely to occur again and has the digital twin learn those tasks.

[2071] Step 3:

[2072] Server: Inputs new business knowledge into the digital twin, expanding its scope of operations, and performs learning processes to improve the digital twin's business processing capabilities.

[2073] Efficiency proposals

[2074] Step 1:

[2075] Server: Further analyze the details of your business data to identify areas that are particularly time-consuming.

[2076] Step 2:

[2077] Server: Proposes efficiency improvements and presents specific improvement measures and efficiency methods to users.

[2078] Step 3:

[2079] Server: Trains the digital twin to work in new ways based on efficiency suggestions, for example adding new processes such as auto-completion of input formats and auto-classification of data.

[2080] Implementing the Emotion Engine

[2081] Step 1:

[2082] Server: Collects emotional data such as the user's facial expressions, tone of voice, and text messages through the emotion engine.

[2083] Step 2:

[2084] Emotion Engine: Analyzes emotion data and recognizes the user's emotional state, identifying positive emotions, negative emotions, stress levels, etc.

[2085] Step 3:

[2086] Server: Determines the user's current emotional state based on the emotional data provided by the emotion engine.

[2087] Improving business efficiency based on emotional data

[2088] Step 1:

[2089] Server: Adjusts work progress and suggestions based on emotional data. For example, if a user is feeling stressed, the server can temporarily have the digital twin take over the work.

[2090] Step 2:

[2091] Server: Provides information to improve work efficiency based on emotional data. For example, suggests ways to relax during stressful work.

[2092] Step 3:

[2093] Server: The emotion engine recognizes the emotional data and trains the digital twin. The digital twin responds according to the user's emotional state, improving work efficiency.

[2094] Specific examples

[2095] Example 1: Improving efficiency of document management

[2096] Step 1:

[2097] User: Inputs document management data into the system.

[2098] Step 2:

[2099] Server: Collects business data such as document classification and storage location input, and generates a digital twin based on that data.

[2100] Step 3:

[2101] Digital twin: Performs document classification and storage location entry tasks.

[2102] Step 4:

[2103] Server: Records the digital twin's behavior and collects the logs.

[2104] Step 5:

[2105] Emotion engine: Analyzes facial expressions and voices while users are performing document management tasks to collect emotional data.

[2106] Step 6:

[2107] Server: Based on the analysis results of document management tasks and user emotion data, it makes suggestions for efficiency improvements, such as automatically suggesting file names and setting classification rules.

[2108] Example 2: Improving the efficiency of inquiry response operations

[2109] Step 1:

[2110] User: Inputs data for inquiry handling work.

[2111] Step 2:

[2112] Server: Generates a digital twin based on past response history and FAQ data.

[2113] Step 3:

[2114] Digital Twin: Respond to initial inquiries based on FAQs.

[2115] Step 4:

[2116] Server: Collects the digital twin's response as a log.

[2117] Step 5:

[2118] Emotion Engine: Recognizes and records the emotions users feel while handling inquiries in real time.

[2119] Step 6:

[2120] Server: Based on the analysis of inquiry response work and emotional data, it makes suggestions for improving efficiency and reducing stress. For example, it automatically updates FAQs and reviews response classifications.

[2121] This improves the quality and speed of work and enables workload adjustment according to the user's emotions.

[2122] Example 2

[2123] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2124] In today's business environment, improving business efficiency is an important issue. Previous systems collected and analyzed business data, but they did not achieve comprehensive efficiency by simulating actual business processes in a virtual environment and incorporating user emotional data. The purpose of this invention is to provide a more advanced business management system that improves business efficiency and reduces the psychological burden on users by utilizing digital twins and an emotion engine.

[2125] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[2126] In this invention, the server includes means for collecting real-world business data, means for generating a digital twin in a virtual office environment, means for the generated digital twin to execute the business, means for collecting operation records of the business executed by the digital twin, means for analyzing the business based on the collected operation records, means for having the digital twin learn new business based on the analysis results, means for proposing methods for improving efficiency based on business data, and means for recognizing user emotional data and reflecting it in the business process. This makes it possible to simultaneously execute and streamline business operations and adjust the workload according to the user's emotional state.

[2127] "Real-world business data" refers to various data (e.g., operation history, documents, inquiry details) generated in the daily operations of a company or organization.

[2128] "Virtual office environment" refers to a work environment that is virtually recreated using computer simulation.

[2129] "Digital twin" refers to a digital model that mimics and simulates real-world physical processes or systems in a virtual environment.

[2130] "Means of performing business operations" refers to the digital twin's ability to actually perform routine tasks (e.g., document classification, data entry, and responding to inquiries).

[2131] "Operation records" refer to detailed logs of the operations performed by the digital twin, including the operation history and execution time of the operations.

[2132] "Means for analyzing business operations" refers to the function of analyzing collected operational records and identifying patterns and trends in business processes.

[2133] "Means of business learning" refers to the process of inputting new business knowledge and skills into the digital twin based on the analysis results.

[2134] "Means to propose efficiency improvements" refers to a function that performs detailed analysis of business data and presents specific improvement measures and efficiency methods to the user.

[2135] "Emotional data" refers to data that indicates a user's emotional state, such as facial expressions, tone of voice, or text messages.

[2136] An "emotion engine" refers to a system that analyzes a user's emotional data and recognizes the user's emotional state based on the results.

[2137] This invention is a system for generating a digital twin in a virtual office environment based on real-world business data, thereby improving business efficiency. Furthermore, by combining it with an emotion engine that recognizes user emotion data, it is possible to achieve more comprehensive business efficiency. A specific implementation method of this system will be described below.

[2138] System configuration

[2139] This system consists of a server, a terminal (user interface), a digital twin, and an emotion engine.

[2140] server

[2141] The server has the following main functions:

[2142] 1. Function to collect business data

[2143] 2. Function to generate digital twins based on business data

[2144] 3. Ability to collect and analyze digital twin operation records

[2145] 4. A function that makes suggestions for improving business efficiency

[2146] 5. Function to analyze user emotional data using an emotion engine

[2147] Hardware and Software

[2148] Hardware

[2149] Server: A server with high-performance computing power is required, specifically a cloud server or on-premise server with sufficient CPU, memory and storage.

[2150] Terminals: Includes devices used by users, such as PCs, tablets, and smartphones. These terminals are connected to the Internet and are capable of data communication with servers.

[2151] software

[2152] Data collection: Database management system (e.g. MongoDB, MySQL)

[2153] Data analysis: Data analysis libraries (Python Pandas, NumPy)

[2154] Digital twin generation: Simulation tools (AnyLogic, MATLAB)

[2155] Machine Learning: Machine learning frameworks (e.g. TensorFlow, scikit-learn)

[2156] Sentiment analysis: Natural language processing libraries (e.g., NLTK, SpaCy), speech analysis tools (Google Cloud Speech-to-Text), facial recognition libraries (OpenCV)

[2157] What the program does

[2158] User Authentication and Data Collection

[2159] User: Logs in to the system and inputs business data into the system. Specifically, he uploads documents in PDF format or CSV files.

[2160] Server: Stores the business data provided by the user in a database. Pandas and NumPy are used for data analysis.

[2161] Digital Twin Generation

[2162] Server: Based on the data, the business process is analyzed and a digital twin is generated. The generated digital twin is simulated in a virtual office environment and performs business operations.

[2163] Simulation tools: AnyLogic and MATLAB are used to simulate the operation of the digital twin.

[2164] Collection of operational records and business analysis

[2165] Server: Collects and stores in a database the operation records of the tasks performed by the digital twin. These operation records include the operation history and execution time of the tasks.

[2166] Proposals for improving business efficiency

[2167] Server: Uses machine learning algorithms to optimize business processes based on operational records.

[2168] Machine learning: Uses TensorFlow and scikit-learn to analyze business patterns and generate efficiency suggestions.

[2169] Implementing the Emotion Engine

[2170] Server: Analyzes the user's emotional data using the emotion engine. Specifically, it understands the user's emotional state through facial expression recognition, voice analysis, and text analysis.

[2171] Emotion engine: Facial expression data is analyzed using OpenCV, voice data is analyzed using Google Cloud Speech-to-Text, and text messages are analyzed using SpaCy and NLTK.

[2172] Specific examples

[2173] Streamlining document management

[2174] 1. User: Inputs document management data into the system.

[2175] 2. Server: Collects business data such as document classification and storage location information, and generates a digital twin based on that data.

[2176] 3. Digital Twin: Performs document classification and storage location entry tasks.

[2177] 4. Server: Records the digital twin's operations and collects the logs.

[2178] 5. Server: Performs detailed analysis of document management data and proposes specific methods for improving efficiency, such as automatically suggesting file names and setting classification rules.

[2179] 6. Emotion Engine: Recognizes and records the emotions users feel while managing documents in real time.

[2180] Improving efficiency of inquiry response operations

[2181] 1. User: Inputs data for inquiry handling operations.

[2182] 2. Server: Generates a digital twin based on past response history and FAQs.

[2183] 3. Digital Twin: Respond to initial inquiries based on FAQs.

[2184] 4. Server: Collects the digital twin's response as a log.

[2185] 5. Server: Analyzes the operational records and teaches the digital twin new knowledge to respond to the next inquiry.

[2186] 6. Emotion Engine: Recognizes user emotions in real time and analyzes work stress and satisfaction.

[2187] Prompt Sentence Examples

[2188] Below are examples of prompts to encourage the operation of this system.

[2189] Document management optimization prompt example:

[2190] Collect data on document management tasks and provide suggestions for efficient classification and storage locations. Also, monitor the user's stress level while managing each document, and if stress levels are high, have that part of the task be taken over by the digital twin.

[2191] Example prompt for inquiry response optimization:

[2192] Based on the data of customer service operations, optimize FAQs and provide appropriate responses to initial inquiries. Recognize users' emotional data in real time, train your digital twin to respond according to their emotional state, and implement stress-relief measures.

[2193] These concrete examples and prompts allow users to use the system efficiently, improving the quality and speed of their work, as well as adjusting their workload according to their emotions.

[2194] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2195] Step 1:

[2196] User Authentication and Data Collection

[2197] User: Log in to the system by entering your username and password, pressing the login button and waiting for authentication.

[2198] Input: Username, Password

[2199] Output: Authentication token, user access rights

[2200] Server: Checks the user credentials against a database to authenticate them. If authentication is successful, generates an authentication token and grants access to the user.

[2201] Behavior: The user information is matched against a database (e.g. MySQL) for authentication. If authentication is successful, an authentication token is generated and a user session is started.

[2202] Step 2:

[2203] Entering and saving business data

[2204] User: Uploads business data (e.g., documents, operation history, inquiry details) to the system by dragging and dropping PDF or CSV files through the interface.

[2205] Input: Business data (PDF files, CSV files, etc.)

[2206] Output: Message indicating that data has been saved to the business database

[2207] Server: Receives uploaded files, stores them in a database, and extracts and organizes the file contents using OCR and data analysis tools.

[2208] How it works: After receiving the file, it uses OCR software (e.g., Tesseract OCR) to extract the text information, organizes the data using Python's Pandas or NumPy, and stores it in MongoDB or MySQL.

[2209] Step 3:

[2210] Digital Twin Generation

[2211] Server: Analyzes collected business data and generates a digital twin model. Business processes are reproduced in a virtual office environment using simulation tools (e.g., AnyLogic, MATLAB).

[2212] Input: Organized business data

[2213] Output: Digital twin model generation complete message

[2214] Operation: Analyze business data using data analysis libraries (Pandas, NumPy), then create a digital twin model using AnyLogic or MATLAB. Run a simulation to confirm the operation of the digital twin.

[2215] Step 4:

[2216] Business execution and operation recording

[2217] Terminal: Launches a virtual office environment and displays the interface through which the digital twin performs its work.

[2218] Input: Digital twin model

[2219] Output: Business execution visualization interface

[2220] Digital twin: Performs routine tasks such as document sorting, data entry, and handling inquiries.

[2221] How it works: The digital twin uses OCR to classify documents, natural language processing (NLP) to process queries, and records the process of how work is performed in real time.

[2222] Step 5:

[2223] Collection of operational records and business analysis

[2224] Server: Collects the digital twin's operational records in a database. The operational records include the operation history and execution time of the business.

[2225] Input: Digital twin operation record (log data)

[2226] Output: Analysis report

[2227] Action: Action records are stored in a database (MongoDB, MySQL) and analyzed using machine learning algorithms (e.g. TensorFlow, scikit-learn) to identify patterns and trends in business processes.

[2228] Step 6:

[2229] Proposals for improving business efficiency

[2230] Server: Optimizes business processes based on the analysis results of operational records, proposes specific improvement measures, and presents them to the user in a report.

[2231] Input: Analysis results, output of optimization algorithms

[2232] Output: Efficiency proposal report

[2233] How it works: Optimize business processes using machine learning models and create reports that suggest specific efficiency measures (e.g., RPA implementation, automatic classification).

[2234] Step 7:

[2235] Emotion engine implementation and emotion analysis

[2236] Server: Collects and analyzes user emotion data through the emotion engine and reflects it in business processes.

[2237] Input: User emotion data (facial expression, voice, text)

[2238] Output: A report of the user's emotional state

[2239] How it works: We use OpenCV to analyze facial expression data, Google Cloud Speech-to-Text to analyze audio data, and SpaCy and NLTK to analyze text data to assess the user's emotional state.

[2240] Step 8:

[2241] Integrated business efficiency

[2242] Server: Integrates emotional data and business data to adjust how work proceeds.

[2243] Input: Emotion data, business data

[2244] Output: Workload adjustment plan

[2245] How it works: Dynamically adjusts workload based on the user's stress level and allows the digital twin to take over certain tasks, improving overall operational efficiency.

[2246] Through these steps, this system executes a consistent process from collecting and analyzing business data, generating digital twins, to utilizing emotion data, helping to improve business efficiency.

[2247] (Application example 2)

[2248] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2249] The objective of this invention is to improve the efficiency of food delivery services and manage the stress of delivery workers. Previous systems did not adequately collect and analyze data specific to delivery work, and also lacked work suggestions that took into account the emotional state of delivery workers. As a result, work optimization and stress reduction for delivery workers were not effectively achieved. A new approach to solving this problem is needed.

[2250] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[2251] In this invention, the server includes means for collecting real-world business data, means for generating a digital twin in a virtual office environment based on the collected data, means for the generated digital twin to execute business operations, means for collecting operation records of the business operations executed by the digital twin, means for analyzing the business operations based on the collected operation records, means for having the digital twin learn new business operations based on the analysis results, means for proposing methods for improving efficiency based on the business data, means for collecting and analyzing business data specialized for delivery operations, means for collecting and analyzing emotional data of delivery personnel, and means for learning and proposing business methods based on delivery efficiency and the emotional data of delivery personnel. This makes it possible to improve the efficiency of food delivery operations and manage the emotions of delivery personnel.

[2252] "Real business data" refers to all data related to business operations carried out in a real environment.

[2253] A "virtual office environment" is a computer-generated virtual environment that mimics real-world office activities.

[2254] "Digital twin" is a technology that recreates real-world business processes as digital models and uses them to improve business efficiency and optimization.

[2255] "Operation records" are data that record the entire process of work performed by a digital twin.

[2256] "Business analysis" is the process of evaluating business performance based on collected data and operational records and identifying areas for improvement.

[2257] "Methods for improving efficiency" are methodologies for improving business performance, such as reducing work time, cutting costs, and improving the quality of deliverables.

[2258] "Delivery" is the service process of delivering ordered products to a specific location of a customer.

[2259] "Emotional data" is data that indicates the mental state of the delivery person and is obtained through facial expression analysis, voice analysis, text analysis, etc.

[2260] "Business methods" refer to the procedures and techniques required to carry out business.

[2261] An embodiment of the present invention includes a system for collecting real-world business data and generating a digital twin in a virtual office environment based on the collected data. This embodiment will be described in detail below.

[2262] The system program mainly consists of the following hardware and software:

[2263] Hardware: Smartphone (for delivery staff), server (cloud or on-premise)

[2264] Software: Python (programming language), Pandas (data analysis library), JSON (data format)

[2265] The server collects data related to delivery operations and generates a digital twin based on that data. This digital twin simulates the delivery process in a virtual office environment to improve efficiency. The server also has the ability to collect and analyze emotional data from delivery personnel. The results of this analysis are useful for optimizing deliveries and reducing stress for delivery personnel. This data is used to analyze operations and make suggestions for improving delivery methods, especially in the case of delivery delays or customer feedback.

[2266] The device (smartphone) collects real-time data on delivery behavior and emotional state of the delivery person while they are performing their delivery duties. This is achieved by continuously sending data entered by the delivery person on the app, such as the delivery address, delivery time, customer feedback, and the delivery person's emotional state, to a server.

[2267] For example, if delivery time exceeds 30 minutes or negative feedback is received, the system on the server analyzes this data and suggests optimizing delivery routes and readjusting delivery areas, thereby improving delivery efficiency and managing stress for delivery personnel.

[2268] The system also implements algorithms to learn new work methods and improve efficiency. This allows the system to constantly learn and apply the latest work methods. For example, if a delivery person is feeling stressed, the server will use that emotional data to suggest having the digital twin temporarily take over the work.

[2269] An example of a prompt is as follows:

[2270] I would like to know how to generate a digital twin based on operational data from a food delivery service to optimize delivery efficiency, and how to make suggestions using emotional data. Specifically, I would like to hear about a system that collects and analyzes delivery order IDs, delivery addresses, delivery times, customer feedback, and delivery personnel's emotional data to make suggestions to improve delivery efficiency.

[2271] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2272] Step 1:

[2273] A user logs in

[2274] Input: The user enters a user ID and password to log in to the system.

[2275] Processing: The server authenticates the entered user ID and password. The authentication process involves retrieving and verifying user information from a database.

[2276] Output: If authentication is successful, grant access to the user, or if authentication fails, display an error message.

[2277] Step 2:

[2278] Business data collection

[2279] Input: The user enters data related to the delivery job (delivery order ID, delivery address, delivery time, customer feedback, etc.).

[2280] Processing: The terminal collects the input data in real time and sends it to the server, unifying the data format and checking the required fields.

[2281] Output: The server stores the collected data in a database, which is used to generate a digital twin and for subsequent analysis.

[2282] Step 3:

[2283] Digital Twin Generation

[2284] Input: Collected business data

[2285] Processing: The server analyzes the collected business data and generates a digital twin that mimics business processes in a virtual office environment, including defining the business flow and setting up the simulation model.

[2286] Output: The resulting digital twin is a virtual model of the actual work environment that can be viewed by the user and placed in the virtual office environment.

[2287] Step 4:

[2288] Execution of work and collection of operational records

[2289] Input: Business execution results using digital twin

[2290] Processing: The digital twin performs routine tasks in the virtual office environment and records their actions. The terminal monitors the delivery person's actions and history in real time during deliveries and sends the data to the server.

[2291] Output: The collected operation records are stored in a database as detailed logs. This data is used to analyze operations and provide suggestions for improving efficiency.

[2292] Step 5:

[2293] Emotion data collection and analysis

[2294] Input: Delivery person's emotional data (facial expressions, voice, text messages, etc.)

[2295] Processing: The server uses an emotion engine to analyze the delivery person's emotional data and recognize their emotional state (positive, negative, stress level, etc.). This analysis is performed using emotion recognition algorithms and machine learning models.

[2296] Output: As a result of the analysis, the emotional state of the delivery person is stored on the server and used to make suggestions for delivery efficiency and emotion management.

[2297] Step 6:

[2298] Business analysis and efficiency proposals

[2299] Input: Collected business data and emotional data

[2300] Processing: The server analyzes business processes based on the collected data, identifying areas that are particularly time-consuming and that could b...

Claims

1. A means of collecting real-world business data; A means to generate a digital twin in a virtual office environment based on the collected data; The means by which the generated digital twin will carry out its business; A means for collecting operational records of the business performed by the digital twin; A means for analyzing operations based on collected operation records; A means to teach the digital twin new tasks based on the analysis results, and A means to propose ways to improve efficiency based on business data, A system including:

2. The system of claim 1, which analyzes the records of operations performed by the digital twin and provides information to improve efficiency the next time the same task is performed.

3. The system of claim 1 , wherein the digital twin learns new work methods based on efficiency suggestions.

Images