How to create a worker digital profile and related applications

Abstract

To provide a method and system for performing operation optimization through virtual simulation.SOLUTION: A method disclosed herein comprises: causing a processor to generate operator digital profiles associated with a plurality of operators, perform virtual simulation using the operator digital profiles as input to a first model, and generate performance prediction as output from the first model; and performing operation optimization based on the performance prediction.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] The present disclosure generally relates to methods and systems for performing work optimization through virtual simulation.

Background Art

[0002] In manufacturing and production processes involving a certain level of worker activity, quantitative information regarding performance, efficiency, throughput, and work quality is difficult to obtain and predict. However, information such as detailed worker capabilities for a particular task, learning curves for new tasks, task times for each operation, and work quality is important information used when designing, monitoring, analyzing, and improving manufacturing processes. When designing a new production line or modifying an existing one, the performance and throughput of each operation play an important role in ensuring the proper flow of the manufacturing process. The throughput and performance of machines and / or automated processes can be obtained relatively easily. However, on the other hand, the performance and throughput of manual work are relatively difficult to obtain.

Summary of the Invention

Problems to be Solved by the Invention

[0003] In related technologies, methods for generating performance and throughput through estimation have been disclosed. However, the information obtained through estimated performance may rather be inaccurate, and its application tends to lead to incorrect results.

[0004] In related technologies, methods for generating performance and throughput through physical measurement in an inspection environment have been disclosed. However, the preparation of an inspection environment is not only time-consuming but also costly.

Means for Solving the Problems

[0005] Aspects of this disclosure involve an innovative method for performing work optimization through virtual simulation. This method may include: generating worker digital profiles associated with multiple workers using a processor; running a virtual simulation using the worker digital profiles as input to a first model using a processor; generating performance predictions as output from the first model using a processor; and performing work optimization based on the performance predictions.

[0006] Aspects of this disclosure involve an innovative non-temporary computer-readable medium for storing instructions for performing work optimization through virtual simulation. Instructions may include generating worker digital profiles associated with multiple workers, running virtual simulations using the worker digital profiles as input to a first model, generating performance predictions as output from the first model, and performing work optimization based on the performance predictions.

[0007] Aspects of this disclosure involve an innovative server system for performing work optimization through virtual simulation. The system may include, by a processor, generating worker digital profiles associated with multiple workers; by a processor, performing virtual simulation using the worker digital profiles as input to a first model; by a processor, generating performance predictions as output from the first model; and performing work optimization based on the performance predictions.

[0008] Aspects of the present disclosure involve an innovative system for performing work optimization through virtual simulation. The system may include means for generating worker digital profiles associated with multiple workers; means for performing virtual simulations using the worker digital profiles as input to a first model; means for generating performance predictions as output from the first model; and means for performing work optimization based on the performance predictions.

[0009] The following describes a general-purpose architecture that implements various features of this disclosure, with reference to the drawings. The drawings and related descriptions are provided to illustrate exemplary embodiments of this disclosure and are not intended to limit the scope of this disclosure. Throughout the drawings, reference numbers are also used again to indicate the correspondence between the referenced elements. [Brief explanation of the drawing]

[0010] [Figure 1] This figure shows an exemplary process flow 100 for generating a worker digital profile according to one exemplary embodiment. [Figure 2] This figure shows an exemplary process flow 200 for worker digital profile application according to one exemplary embodiment. [Figure 3] This figure shows an exemplary system configuration 300 according to one exemplary embodiment. [Figure 4] This figure shows a conventional line balancing process 400. [Figure 5] This figure shows an exemplary line balancing process 500 according to one exemplary embodiment. [Figure 6] Figure 600 shows an exemplary embodiment for performing automated detailed task information gathering. [Figure 7] Figure 700 shows an exemplary embodiment for performing a production line design. [Figure 8]This figure shows an exemplary computing environment having exemplary computing devices suitable for use in several exemplary embodiments. [Modes for carrying out the invention]

[0011] The following detailed description provides details of the figures and exemplary embodiments of the present application. Reference numbers and descriptions of elements that overlap between figures are omitted for clarity. The terms used throughout the description are provided as examples and are not intended to limit the scope. For example, the use of the term “automatic” may include fully automatic or semi-automatic embodiments, depending on a desired embodiment for those skilled in the art practicing the embodiments of the present application, including user or administrator control over certain aspects of the implementation. Selection may be performed by a user via a user interface or other input means, or via a desired algorithm. Exemplary embodiments such as those described herein may be available individually or in combination, and the functions of such exemplary embodiments may be implemented.

[0012] An exemplary embodiment provides a novel method for measuring and modeling worker capabilities across various classifications and for performing task / job simulations (virtual simulations) based on the measurements. Once worker characteristics are measured / modeled, a digital profile or digital twin of that worker is subsequently generated. This digital profile can be used to simulate the worker's / individual performance for new tasks (e.g., tasks the individual has never performed before). This digital profile can be used to map the worker's skill level and can provide information to help assign work and / or training.

[0013] Figure 1 shows an exemplary process flow 100 for generating a worker digital profile according to an exemplary embodiment. The preparation and characterization of the worker digital profile are performed by process flow 100. Several standard tests need to be performed to characterize the worker / individual's capabilities. In step S102, quantitative measurements of the worker / individual's capabilities are obtained through a set of standard tests. These standard tests may involve classifications such as, but are not limited to, muscle strength, speed, balance, consistency, accuracy, agility, reaction time, and sensation. To perform the standard tests, multiple sensors such as fixed or wearable cameras, wearable sensors, and health monitoring devices are applied to obtain information / results (quantitative measurements) such as pressure, force, angle, speed, time, completion status, quality inspection, temperature, and geometric shape.

[0014] In step S104, these measurements are provided as input to an artificial intelligence (AI) / machine learning (ML) model to characterize and parameterize worker capabilities across various classifications. The AI / ML model may include, but is not limited to, convolutional neural networks (CNNs), recurrent neural networks (RNNs), deep RNNs (DRNNs), Q-learning networks (QNs), deep Q-learning networks (DQNs), linear regression, logistic regression, decision trees, and K-proximity methods. RNNs may include long short-term memory (LSTMs).

[0015] Next, the process proceeds to step S106, where the worker / individual worker digital profile is generated as the output of the AI / ML model. This worker digital profile may include quantitative measurements of worker competence in various classifications. In some exemplary embodiments, each classification may further include subcategories. For example, the classification "muscle strength" may have subcategories for different muscle groups and subcategories for performance on different types of muscle-related tasks such as lifting, horizontal propagation, and arm / torso angles. In alternative exemplary embodiments, a rule-dependent model may be used instead of the AI / ML model to characterize and parameterize worker competence and generate the worker digital profile. In step S108, the generated worker digital profile is stored in data storage, which may be local memory or centralized storage in the cloud.

[0016] Figure 2 shows an exemplary process flow 200 for worker digital profile application according to an exemplary embodiment. This process begins in step S202, where information associated with a new work / task is received. Such information may include a work / task description and quantitative work / task parameters. In step S204, an artificial intelligence (AI) / machine learning (ML) model receives and analyzes the information associated with the new work / task and a worker digital profile, such as the one derived in Figure 1. The AI / ML model is trained using past worker digital profiles and may include, but is not limited to, convolutional neural networks (CNNs), recurrent neural networks (RNNs), deep RNNs (DRNNs), Q-learning networks (QNs), deep Q-learning networks (DQNs), linear regression, logistic regression, decision trees, K-proximity methods, etc. RNNs may include long short-term memory (LSTMs). The AI / ML model analyzes the information associated with the new work / task (e.g., work content) and simulates worker performance using the information provided from the worker digital profile (through virtual simulation).

[0017] In step S206, performance predictions are generated as output from the AI / ML model. These performance predictions may include, but are not limited to, information such as the worker / individual's ability to perform the task (e.g., whether they can or cannot), estimated training time for the task, estimated task completion time, estimated performance metrics (e.g., speed, quality, etc.), estimated fatigue level, and work progress. These prediction results may be stored in data storage.

[0018] In step S208, the generated performance predictions are used to perform various optimization and operational tasks. Such tasks may include, but are not limited to, work cycle time estimation in manufacturing, simulation of production line performance for line balancing / reconfiguration, performance simulation for production line design, worker skill mapping, training performance, and video game design and customization. In alternative exemplary embodiments, rule-dependent models may be used instead of AI / ML models when performing performance predictions.

[0019] Figure 3 shows an exemplary system configuration 300 according to one exemplary embodiment. As shown in Figure 3, the system configuration 300 may include components such as a standard inspection module 302, a sensing module 304, a data acquisition module 306, a data storage module 308, a worker characterization module 310, a worker digital profile module 312, a simulation module 314, and a work prediction module 316. The standard inspection module 302, sensing module 304, data acquisition module 306, data storage module 308, and worker characterization module 310 together form the worker digital profile generation process described in Figure 1. The simulation module 314 and the work prediction module 316 together form the worker digital profile application process described in Figure 2.

[0020] The standard inspection module 302 stores a set of standard inspections for various classifications performed by an operator / individual. The standard inspection module 302 can be physically or wirelessly connected to several sensors in order to quantify the operator capabilities of the operator / individual in several classifications. The sensing module 304 receives sensor data (raw data) generated from the sensors.

[0021] The data collection module 306 receives sensor data (raw data) from the sensing module 304 and performs data preprocessing on the received sensor data. Data preprocessing may include cleaning, transforming, and integrating the sensor data to prepare the sensor data for subsequent processing steps. The preprocessed data is then stored in the data storage module 308 and retrieved for processing.

[0022] The operator characterization module 310 analyzes the preprocessed data to generate an operator digital profile, which is then stored in the operator digital profile module 312. In some exemplary embodiments, the data storage module 308 and the operator digital profile module 312 are part of a data storage (not shown) to the system configuration 300. In some exemplary embodiments, at least one of the data storage module 308 or the operator digital profile module 312 exists on cloud storage.

[0023] The operator digital profile application process is initiated through the reception of new work / task information in the simulation module 314. The simulation module 314 then performs a work prediction by analyzing the received new work / task information and the operator digital profile as obtained from the operator digital profile module 312. The generated work prediction is then output to the work prediction module 316, retrieved and further processed in various applications / uses.

[0024] In some exemplary embodiments, an optional verification module 318 may be included as part of the system configuration 300. The verification module 318 may perform enhancement of the worker digital profile and may include two submodules, namely a verification data acquisition module 320 and a verification data analysis module 322. Data on the physical performance of the worker / individual work / task can be collected using the verification data acquisition module 320 and used by the verification data analysis module 322 when performing data analysis. The verification data analysis module 322 compares the actual physical ability of the worker to the work / task performed by the worker with the predicted output from the work prediction module 316 in order to optimize / improve the relevant worker digital profile stored in the worker digital profile module 312. Quantitative measurements of worker ability may be updated based on this comparison and used to further improve the accuracy of the results generated by the simulation module 314 and the work prediction module 316 in subsequent simulations.

[0025] First Embodiment - Line Balancing

[0026] Throughput variations are common across production lines in the automotive manufacturing process. When such variations are detected, manufacturers then perform line balancing across different stations on the production line to address the variations and improve throughput. Line balancing involves identifying slow / problematic stations and reorganizing work between different stations.

[0027] Figure 4 illustrates a conventional line balancing process 400. Detailed task information 402 for various processes is typically measured manually at each workstation and manually analyzed to identify problems in the production / manufacturing line. Such detailed task information 402 typically includes the time taken for each task, target / standard work description, and performance quality. Based on this analysis, a new line configuration / line recommendation 404 is proposed by an experienced engineer and implemented on-site. A reconfiguration trail 406 for documenting configuration changes is generated whenever the line configuration is updated. Manual measurements are then performed to obtain updated detailed task information 402 in order to evaluate the modified line configuration. This balancing process may be repeated multiple times to further improve production / manufacturing outcomes. The process itself can be time-consuming and costly due to the labor involved and production downtime from configuration embodiments.

[0028] Figure 5 shows an exemplary line balancing process 500 according to one exemplary embodiment. Compared to conventional line balancing processes, the line balancing process 500 achieves higher efficiency, cost reduction, and minimizes disruptions to the production / manufacturing process. First, detailed task information 502 is generated by performing automated data collection and analysis, which is described in more detail below in relation to Figure 6. The line configuration module 504 contains the details of the production / manufacturing line configuration. The ontology database module 506 contains 4M ontology data (worker data 508, machine data 510, material data 512, and method data 514). Together, the detailed task information 502, the line configuration information from the line configuration module 504, and the 4M ontology data from the ontology database module 506 are combined and input into the line configurator module 516.

[0029] The line configurator module 516 analyzes the current performance and generates a proposed configuration based on ontology data along with physical constraints. The generated configuration is then sent as input to the work simulation module 518. The work simulation module 518 executes the simulation function of the simulation module 314 in Figure 3, acquiring the configuration generated by the line configurator module 516 and digitized worker capability data from the worker digital profile module 312 (worker digital profiles 524 of the relevant operators on the production line) when running the simulation. The simulated performance of the configuration is then output to the line optimizer 520, which compares the performance results and eliminates candidates based on the results (e.g., performance below a performance threshold). The remaining candidates are then sent back to the line configurator module 516 along with updated constraints and results for additional configuration updates. The process of configuration generation, simulation, and optimization may be repeated until one or a predetermined number of candidate configurations are generated as line recommendations 522. If a single candidate configuration is generated, that configuration is implemented. Once a predetermined number of candidates have been generated, the user selects the configuration to implement.

[0030] Based on the above, the line balancing process 500 does not require actual trial and error by workers / operators. In addition, the use of worker digital profiles enables the generation of more accurate and reliable predictions and recommendations than conventional methods. For example, a task that requires operator A to complete in 10 seconds may require operator B to complete in 15 seconds. Worker digital profiles can identify such differences in operator capabilities and enable the generation of predictions that take such differences into account.

[0031] Figure 6 shows an exemplary Figure 600 for performing automated detailed task information collection according to an exemplary embodiment. During the production process, location data may be acquired from a camera and a light-sensing ranging (LiDAR) sensor 602, while other production data (e.g., work errors) may be acquired using other sensor / sensing devices (i.e., wearable sensing devices) such as a sensor glove 604. The camera and LiDAR sensor 602 generate images / videos from the camera and LiDAR data from the LiDAR sensor. Data analysis (AI / ML, image recognition, feature extraction, etc.) is then performed on the data to generate operator and / or object location data 606 (e.g., identifier, timestamp, object orientation (x,y,z), etc.). The location data 606 is then analyzed (e.g., application of AI / ML, feature extraction) to identify work locations 608 (e.g., tool rack, task site, installation location, primary work area, etc.). Key work data 610 is then derived by analyzing the work locations 608.

[0032] The sensor globe 604 generates other production data, which is then processed (e.g., pattern recognition, sampling, data post-processing, etc.) to generate motion data 612 (e.g., force, pressure, sound, etc.). The motion data 612 is then analyzed (e.g., application of AI / ML, data post-processing, etc.) to generate detailed work data 614 (e.g., pickup equipment / tools, drilling, installation tools, etc.). Detailed personal work data 616 is then derived by analyzing the detailed work data 614.

[0033] Next, the main work data 610 and detailed individual work data 616 are analyzed and combined to generate detailed task information 502. The collected detailed task information can be used to perform work variability analysis, line balancing, work quality verification, work verification, production line design / redesign, training, and the like.

[0034] Second Embodiment - Production Line Design and Virtual Commissioning

[0035] Figure 7 shows an exemplary Figure 700 for performing a production line design according to an exemplary embodiment. A new production line design (new design 702) is proposed and provided to a production simulation module 704 that performs a function similar to the simulation module 314 in Figure 3. In addition to the new design 702, the production simulation module 704 also receives a worker digital profile 706 generated by the worker digital profile module 312 when performing the production simulation. The production simulation module 704 then generates a performance forecast 708, which is then used to decide whether to implement the new design 702 or to generate additional recommendations using the design optimization module 710. If recommendations are generated by the design optimization module 710, those recommendations are then applied as an updated new design 702, and additional simulations are performed based on the updated design.

[0036] Third Embodiment - Game Design

[0037] Worker digital profiles can also be used in the design / creation of virtual characters in games or any metaverse-based software. Players can participate in a set or subset of the checks performed by the standard check module 302 in Figure 3 when generating their digital profiles. Worker digital profiles can then be used to enhance the in-game reality representation of the player and their abilities.

[0038] Fourth Embodiment - Skill Mapping and Training

[0039] Generating worker digital profiles naturally provides a benchmark for operators' skills and abilities. Additional insights can be generated to recommend training materials and track training progress.

[0040] The exemplary embodiments described above may offer various benefits and advantages. For example, they represent an unconventional approach to improving product line configurations through the generation of worker digital profiles when performing virtual simulations based on worker digital profiles to map the precise skill levels of workers and optimize line configurations. Measurements derived from various sensors and inspections are provided as input to an AI / ML model when generating worker digital profiles that uniquely characterize and parameterize the capabilities of employees / workers, something that was not possible with related technologies. Implementing worker digital profiling in training and simulations helps quantify worker / employee performance, reduce costs, and minimize obstacles to actual production / manufacturing processes.

[0041] Figure 8 shows an exemplary computing environment having exemplary computing devices suitable for use in several exemplary embodiments. The computing device 805 in the computing environment 800 may include one or more processing units, cores, or processors 810, memory 815 (e.g., RAM, ROM, and / or similar), internal storage 820 (e.g., magnetic, optical, solid-state storage, and / or organic), and / or I / O interfaces 825, any of which may be coupled on a communication mechanism or bus 830 for communicating information, or incorporated into the computing device 805. The I / O interface 825 may be further configured, depending on the desired embodiment, to receive images from a camera or to provide images to a projector or display.

[0042] The computing device 805 may be communicatively coupled to an input / user interface 835 and an output device / interface 840. Either or both of the input / user interface 835 and the output device / interface 840 may be wired or wireless interfaces and may be detachable. The input / user interface 835 may include any physical or virtual device, component, sensor, or interface available to provide input (e.g., buttons, touchscreen interfaces, keyboards, pointing / cursor controls, microphones, cameras, Brailles, motion sensors, accelerometers, optical readers, and / or similar). The output device / interface 840 may include displays, televisions, monitors, printers, speakers, Brailles, or similar. In some exemplary embodiments, the input / user interface 835 and the output device / interface 840 may be integrated with the computing device 805 or be physically coupled to it. In other exemplary embodiments, other computing devices may function as, or provide, the input / user interface 835 and the output device / interface 840 for the computing device 805.

[0043] Examples of computing devices 805 may include, but are not limited to, highly mobile devices (e.g., smartphones, devices mounted in vehicles and other machines, devices held by people or animals, and the like), mobile devices (e.g., tablets, notebooks, laptops, personal computers, portable televisions, radios, and the like), and devices not designed for mobility (e.g., desktop computers, other computers, information kiosks, televisions with one or more processors incorporated and / or televisions, radios with one or more processors combined).

[0044] Computing device 805 may be communicably coupled to external storage 845 and network 850 (for example, via I / O interface 825) for communication with any number of network-connected components, devices, and systems, including one or more computing devices of the same or different configurations. Computing device 805 or any connected computing device may function, provide services, or be referred to as a server, client, thin server, general-purpose machine, dedicated machine, or other.

[0045] The I / O interface 825 may include, but is not limited to, wired and / or wireless interfaces using any communication or I / O protocol or convention (e.g., Ethernet, 802.11x, Universal System Bus, WiMAX, modem, cellular network protocol, and similar) for information communication to and from at least all connected components, devices, and networks in the computing environment 800. The network 850 may be any network or combination of networks (e.g., the Internet, local area network, wide area network, telephone network, cellular network, satellite network, and similar).

[0046] Computing device 805 is capable of using and / or using computer-usable or computer-readable media, including temporary and non-temporary media. Temporary media include transmission media (e.g., metal cables, optical fibers), signals, carrier waves, and the like. Non-temporary media include magnetic media (e.g., disks and tapes), optical media (e.g., CD-ROMs, digital video discs, Blu-ray® discs), solid-state media (e.g., RAM, ROMs, flash memory, solid-state storage), and other non-volatile storage or memory.

[0047] Computing device 805 may be used to implement techniques, methods, applications, processes, or computer executable instructions in several exemplary computing environments. Computer executable instructions can be retrieved from temporary media, stored in non-temporary media, and retrieved from there. Executable instructions may originate from one or more of any programming languages, scripting languages, and machine languages ​​(e.g., C, C++, C#, Java, Visual Basic, Python, Perl, JavaScript, etc.).

[0048] The processor 810 can run under any operating system (OS) (not shown) in a native or virtual environment. One or more applications may be deployed, including a logical unit 860, an application programming interface (API) unit 865, an input unit 870, an output unit 875, and an inter-unit communication mechanism 895 for different units to communicate with each other, with the OS, and with other applications (not shown). The units and elements described above may differ in design, function, configuration, or implementation, and are not limited to the above description. The processor 810 may take the form of a hardware processor such as a central processing unit (CPU), or it may be a combination of hardware and software units.

[0049] In some exemplary embodiments, when information or execution instructions are received by the API unit 865, they may be transmitted to one or more other units (e.g., a logic unit 860, an input unit 870, and an output unit 875). In some examples, the logic unit 860 may be configured to control the flow of information between units and to direct the services provided by the API unit 865, the input unit 870, and the output unit 875 in some exemplary embodiments described above. For example, the flow of one or more processes or embodiments may be controlled by the logic unit 860 alone or in conjunction with the API unit 865. The input unit 870 may be configured to take input to the calculations described in the exemplary embodiments, and the output unit 875 may be configured to provide outputs based on the calculations described in the exemplary embodiments.

[0050] The processor 810 may be configured to generate worker digital profiles associated with multiple workers, as shown in Figures 1 to 3. The processor 810 may also be configured to run a virtual simulation using the worker digital profiles as input to a first model, as shown in Figures 1 to 3. The processor 810 may also be configured to generate performance predictions as output from the first model, as shown in Figures 1 to 3. The processor 810 may also be configured to perform work optimization based on the performance predictions, as shown in Figures 1 to 3.

[0051] The processor 810 may also be further configured to perform data validation on worker digital profiles based on performance predictions, as shown in Figure 3. The processor 810 may also be further configured to update worker digital profiles based on the results of data validation, as shown in Figure 3. The processor 810 may also be further configured to generate line configurations, as shown in Figure 7. The processor 810 may also be configured to receive task information, production line configuration information, and ontology information, as shown in Figure 5.

[0052] Some parts of the detailed description are presented by algorithms and symbolic representations of the work performed within the computer. The descriptions and symbolic representations of these algorithms are means used by those skilled in the field of data processing to convey the essence of their innovations to others skilled in the art. An algorithm is a set of defined steps leading to a desired final state or result. In exemplary embodiments, the steps performed require the physical manipulation of tangible quantities to achieve a tangible result.

[0053] Unless otherwise noted, as will be apparent from the description, any description throughout this specification using words such as “process,” “calculate,” “calculate,” “determine,” “display,” or similar means may include actions and processes of a computer system or other information processing device that manipulate data represented as physical (electronic) quantities in the registers and memory of a computer system to convert it into other data similarly represented as physical quantities in the memory or registers or other information storage devices, transmission devices or display devices of a computer system.

[0054] Exemplary embodiments may further relate to apparatus for performing work herein. This apparatus may be specifically constructed for a desired purpose, or may include one or more general-purpose computers that are selectively activated or reconfigured by one or more computer programs. Such computer programs may be stored on computer-readable media such as computer-readable storage media or computer-readable signal media. Computer-readable storage media may include, but are not limited to, tangible media such as optical disks, magnetic disks, read-only memory, random-access memory, solid-state devices and drives, or any other type of tangible or non-temporary media suitable for storing electronic information. Computer-readable signal media may include media such as carrier waves. The algorithms and representations presented herein are not inherently related to any particular computer or other apparatus. Computer programs may include pure software implementations containing instructions for performing work in a desired embodiment.

[0055] Various general-purpose systems may be used with the programs and modules illustrated herein, or it may be convenient as a result to construct more specialized devices to perform steps of the desired method. Furthermore, the exemplary embodiments are not described with reference to any particular programming language. It will be understood that various programming languages ​​may be used to carry out the teachings of the exemplary embodiments described herein. Instructions of a programming language may be executed by one or more processing devices, such as a central processing unit (CPU), processor, or controller.

[0056] As is known in the art to which this invention belongs, the operations described above can be performed by hardware, software, or any combination of software and hardware. Various aspects of the exemplary embodiments may be performed using circuits and logic devices (hardware), while other aspects may be performed using instructions stored on a machine-readable medium (software), which, when performed by a processor, causes the processor to perform the method for performing the implementation of the present application. Furthermore, some exemplary embodiments of the present application may be performed by hardware alone, while other exemplary embodiments may be performed by software alone. Furthermore, the various functions described can be performed by a single unit or distributed across a number of components in any number of ways. When performed by software, the method may be performed by a processor, such as a general-purpose computer, based on instructions stored on a computer-readable medium. If necessary, the instructions may be stored on the medium in compressed and / or encrypted form.

[0057] Furthermore, other embodiments of the present application will be apparent to those skilled in the art from the considerations herein and the practice of the teachings herein. Various aspects and / or components of the exemplary embodiments described may be used individually or in any combination. This specification and the exemplary embodiments are intended to be considered as examples only, and the true scope and spirit of the present application are set forth by the following claims. [Explanation of Symbols]

[0058] 302 Standard Inspection Module 304 Sensing Module 306 Data Acquisition Module 308 Data Storage Module 310 Worker Characterization Module 312 Worker Digital Profile Module 314 Simulation Modules 316 Work Prediction Module 320 Verification Data Collection Module 322 Validation Data Analysis Module 506 Ontology Database Module 516 Line Configurator Module 518 Work Simulation Module 520 Line Optimizer 805 Computing Devices 810 processor 815 memory 820 internal storage 825 I / O Interfaces 835 Input / User Interface 840 Output Devices / Interfaces 845 External Storage 850 Network 860 Logical Units 865 API Unit 870 Input Unit 875 Output Unit

Claims

1. A method for performing work optimization through virtual simulation, The processor uses multiple sensors to obtain quantitative measurements of the work performance of multiple workers through standard muscle strength tests, The processor inputs the acquired quantitative measurements of the multiple workers to a second model, which is a machine learning model that takes quantitative measurements of multiple workers as input and outputs worker digital profiles, thereby generating worker digital profiles that are profiles associated with the multiple workers and include quantitative measurements of worker abilities in multiple classifications, including the classification of muscle strength. The processor performs a virtual simulation using the generated worker digital profile by inputting the generated worker digital profile into a first model, which is a machine learning model that takes a worker digital profile as input and outputs a performance prediction. The processor generates a performance prediction as output from the first model, which includes the results of the virtual simulation performed using the generated worker digital profile, and which includes estimated training time for training for the work, estimated task completion time, estimated speed, estimated quality, estimated fatigue level, and work progress. A method comprising: performing worker skill mapping based on the performance prediction using the processor.

2. The processor further includes performing data validation on the worker digital profile based on the performance prediction, The method according to claim 1, wherein the processor is configured to perform data validation by comparing the performance prediction with actual performance data of actual work performed by the plurality of workers.

3. The method according to claim 2, further comprising updating the worker digital profile based on the results of the data verification by the processor.

4. The method according to claim 1, wherein the first model is learned using past worker digital profiles.

5. The method according to claim 1, further comprising using the worker digital profile to design a virtual character for augmented reality representation.

6. A system for performing work optimization through virtual simulation, Multiple sensors, A processor that communicates with the aforementioned multiple sensors Equipped with, The aforementioned processor, Using the aforementioned multiple sensors, quantitative measurements of the work performance of multiple workers are obtained through standard tests related to muscle strength. The second model is a machine learning model that takes quantitative measurements of multiple workers as input and outputs worker digital profiles. By inputting the acquired quantitative measurements of the multiple workers into the second model, a worker digital profile is generated, which is a profile associated with the multiple workers and includes quantitative measurements of worker abilities in multiple classifications, including the classification of muscle strength. The first model is a machine learning model that takes worker digital profiles as input and outputs performance predictions. By inputting the generated worker digital profiles into this model, a virtual simulation is performed using the generated worker digital profiles. The output from the first model is the result of the virtual simulation performed using the generated worker digital profile, which generates a performance prediction including the estimated training time for training for the work, estimated task completion time, estimated speed, estimated quality, estimated fatigue level, and work progress. A system configured to perform worker skill mapping based on the aforementioned performance prediction.

7. The aforementioned processor, Based on the performance prediction, the system is further configured to perform data validation on the worker's digital profile. The system according to claim 6, wherein the processor is configured to perform data validation by comparing the performance prediction with actual performance data of actual work performed by the plurality of workers.

8. The aforementioned processor, The system according to claim 7, further configured to update the worker's digital profile based on the results of the data verification.

9. The system according to claim 6, wherein the first model is learned using past worker digital profiles.

10. The aforementioned processor, The system according to claim 6, further configured to use the worker digital profile to design a virtual character for augmented reality representation.

Images