Execution apparatus for digital twin service and Execution apparatus for digital twin service

Abstract

The digital twin service providing device of the present invention may include at least one sub-component that provides a digital twin service; a data storage unit that stores first information necessary for providing a digital twin service; and a reliability calculation unit that calculates the reliability of the digital twin service.

Description

Technology Field

[0001] The present invention relates to a digital twin service providing device and a digital twin service providing method. Background Technology

[0002] A digital twin is a technology that collects data from the real world in real time, reflects the collected data in a virtual world, and replicates the real-world data identically in the virtual world. The aforementioned data can be stored and analyzed on a cloud-based platform to generate various information.

[0003] The application of digital twins offers several advantages, including improved operational efficiency and cost reduction, enhanced product quality and competitiveness, and support for decision-making processes through simulation. Despite these benefits, decision-making errors resulting from inaccurate simulation results can be fatal to corporate operations. Unreliable data risks generating corrupted models and creating inaccurate digital twins. These issues must be addressed to ensure accurate and reliable decision-making.

[0004] As a solution to the above problem, there is a technology that combines blockchain and digital twin. For example, Publication No. 1020200081395 proposes a computer implementation system and method for combining blockchain technology and digital twin. By utilizing the above prior art, data of the digital twin is stored in the blockchain. Through this, the immutability of past information stored in the blockchain can be verified. Prior art literature

[0005] Publication No. 1020200081395 Computer-implemented system and method for combining blockchain technology and digital twin The problem to be solved

[0006] The present invention provides a technology capable of analyzing the difference between the real world and a digital twin.

[0007] The present invention provides a technology that provides a degree of reliability for a digital twin.

[0008] The present invention provides a technology for quantitatively analyzing the reliability of a digital twin.

[0009] The present invention provides a technology that provides reliability of a digital twin in response to errors in the digital twin—wherein the errors include detection errors in the real world, communication errors between the real world and the digital twin, and generation errors of the digital twin.

[0010] The present invention provides a technology capable of providing the reliability of a digital twin in real time. means of solving the problem

[0011] The digital twin service providing device of the present invention may include at least one sub-component that provides a digital twin service; a data storage unit that stores first information necessary for providing a digital twin service; and a reliability calculation unit that calculates the reliability of the digital twin service.

[0012] The above sub-components may include: a monitoring-related sub-component configured to continuously detect, collect, and analyze first data occurring in the real world; a mirroring-related sub-component that performs the process of synchronizing a scene of the real world with a digital twin environment; and a modeling and simulation-related sub-component that constructs a physical model of the digital twin and performs predictions using it.

[0013] The first information stored in the data storage unit includes the first data, the second data calculated by the sub-component, reliability, and metadata, and can be configured to provide the first information upon request by the reliability calculation unit.

[0014] The above reliability calculation unit can quantitatively calculate the reliability of the digital twin service using the third data and provide a reliability value.

[0015] The above third data may include regional reliability, which is the reliability of individual modules providing digital twin services.

[0016] The above third data may include hyperparameters of individual modules, which are weights of individual modules providing digital twin services.

[0017] The above third data may include hyperparameters of the blockchain, which are weights corresponding to citing the blockchain to provide a digital twin service.

[0018] The above third data includes the time (t) when the request for calculation of the reliability value occurred and the time (τ) when the quantitative reliability was calculated. x Hyperparameters of time difference, which are weights for the difference of ), may be included.

[0019] The above reliability value is calculated using the following formula, and

[0020]

[0021] Here, S is the set of all modules to be considered for calculating quantitative reliability, x is an individual module included in set S, and LC x (Local confidence) is the quantitative confidence of module x, and ω x is a hyperparameter of an individual module as a weight for module x, γ is a hyperparameter of the blockchain as a weight for the blockchain-based trust guarantee module, t is a timestamp at which a request for calculating the quantitative trust value occurred, and τ x is the timestamp at the time when the quantitative confidence of module x was calculated, and Δ t is the time (t) when the request for calculation of the quantitative reliability value occurred and the time (τ) when the quantitative reliability was calculated. xAs a weight for the difference of ), it can be a hyperparameter of the time difference.

[0022] A method for providing a digital twin service according to another embodiment may include, as a mirroring process, a process of synchronizing a 3D scene of an external real-world environment intended for the digital twin with a scene on the digital twin; as a monitoring process, a process of monitoring an external real-world environment intended for the digital twin and any object within the external real-world environment; and as a modeling and simulation (M&S) process, a first step of constructing a physical model of the digital twin using data collected in the mirroring and monitoring and the external real-world environment, and a second step of receiving a prediction result of the model.

[0023] The above method for providing a digital twin service may include a process of changing the state of the external real environment as a management process.

[0024] The above method for providing a digital twin service may include, as a confidence guarantee process, a process of providing the reliability of the digital twin at any given time as a quantitative confidence value.

[0025] The above reliability value can be calculated by using together the first local reliability of the first individual module and the second local reliability of the second individual module, which are used to provide the digital twin service.

[0026] In calculating the above reliability value, the hyperparameters of individual modules, which are the weights of individual modules providing digital twin services; the hyperparameters of the blockchain, which are the weights corresponding to citing the blockchain to provide digital twin services; the time at which the request for calculation of the above reliability value occurred; and the time at which the above local reliability was calculated (τ xHyperparameters of time difference, which are weights for the difference of ), may be included. Effects of the invention

[0027] According to the present invention, the reliability of a digital twin can be quantitatively provided. Various advantages thereof may be presented in more detail in the detailed description.

[0028] According to the present invention, the reliability of the digital twin can be verified at the current time. Brief explanation of the drawing

[0029] FIG. 1 is a diagram illustrating the configuration of a digital twin service providing device according to an embodiment. FIG. 2 is a diagram illustrating the configuration of a digital twin service provider according to another embodiment. FIG. 3 is a drawing showing in detail a specific embodiment of a digital twin service provider. Figure 4 is a graph of the types of time parameters used in calculating reliability values ​​and the corresponding time coefficients. Figure 5 is a flowchart specifically showing the method for calculating the reliability value. Figure 6 is a table showing the calculation results of exemplary reliability values. Specific details for implementing the invention

[0030] Specific embodiments of the present disclosure are described in detail below with reference to the drawings. However, the spirit of the present disclosure is not limited to the embodiments described below. Those skilled in the art who understand the spirit of the present disclosure may easily propose other embodiments included within the scope of the same spirit by adding, changing, deleting, or adding components, and such are also included within the scope of the spirit of the present disclosure. In describing the drawings, identical or similar components are assigned identical or similar reference numbers regardless of the drawing symbols, and redundant descriptions thereof may be omitted. The suffixes "module" and "part" for components used in the following description are assigned or used interchangeably solely for the ease of drafting the specification and do not have distinct meanings or roles in themselves. In describing the embodiments disclosed in this specification, if it is determined that a detailed description of related prior art may obscure the essence of the embodiments disclosed in this specification, such detailed description is omitted. The attached drawings are intended only to facilitate understanding of the embodiments disclosed in this specification, and the technical concept disclosed in this specification is not limited by the attached drawings; it should be understood that all modifications, equivalents, and substitutions included within the concept and technical scope of this disclosure are included. Terms including ordinal numbers, such as first, second, etc., may be used to describe various components, but said components are not limited by said terms. Such terms are used solely for the purpose of distinguishing one component from another. When a component is described as being "connected" or "joined" to another component, it should be understood that it may be directly connected or joined to that other component, or that there may be other components in between.On the other hand, when it is stated that one component is "directly connected" or "directly coupled" to another component, it should be understood that there are no other components in between. A singular expression may include a plural expression unless the context clearly indicates otherwise. In this application, terms such as "comprising" or "having" are intended to specify the existence of the features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof. The operations, roles, functions, and actions of modules for carrying out the present invention may be performed by at least one processor. The at least one processor may be separated from one another in time and / or space. The processor may exemplify a computer.

[0031] FIG. 1 illustrates the configuration of a digital twin service providing device according to an embodiment.

[0032] Refer to FIG. 1. The digital twin service providing device of the embodiment may include at least one sub-component (1) configured to provide a digital twin service, a data storage unit (2) for storing data, and a reliability calculation unit (3) for calculating the reliability of the provided digital twin service. The sub-component (1) may include at least two.

[0033] The real world may be the external environment that serves as the purpose of the digital twin. The real world may be the physical environment in which data is generated. Data collected from the real world may be provided to a component that processes input among the sub-components constituting the digital twin service provider. Accordingly, changes in the state of the real world may be reflected in the digital twin. The device collecting data from the real world may include various devices such as sensors, IoT devices, and cameras.

[0034] A digital twin may include forming a virtual system or model based on data collected from the real world, and operating said system and said model. A digital twin may mirror and monitor the state of the real world, and perform predictions or analyses based on the mirrored and monitored information.

[0035] The above sub-component may refer to detailed components constituting the digital twin. The above sub-component may include a configuration that receives data collected from the real world and calculates reliability and reliability values. The reliability may be defined as an absolute or relative degree of reliability. The reliability value may be defined as a value representing reliability as a quantitative numerical value. The reliability value is explained as follows: For example, there may be a temperature measurement error of 10% in a real-world temperature sensor. Accordingly, if the temperature in the real world is 10 degrees, the temperature measured by the temperature sensor may be measured as 9-11. In this case, the reliability value of the temperature specified by the temperature sensor may be 90%. The reliability value may be defined as including engineering errors. The definition of reliability may apply to all configurations, modules, parts, and processors included in the implementation of the digital twin. The above sub-component may perform various processes exemplifying input processing, mirroring, monitoring, modeling, and simulation. The above sub-component may independently evaluate the reliability of the data. The evaluated reliability can be stored along with metadata. In this case, it may be transferred to and stored in a separate data storage unit. The metadata may be data for data. Examples of the metadata may include timestamps, data structures, and container identification information.

[0036] The above sub-component may include the following individual components.

[0037] The above sub-component may include a mirroring-related sub-component. The mirroring-related sub-component may perform a process of synchronizing a 3D scene of the real world with a digital twin environment. In this case, the scene data of the real world may be generated by a human operator or an intelligent device. The generation process may be performed periodically. It may include dynamic modification of object information within the scene of the digital twin based on data collected during the monitoring process. For example, the mirroring-related sub-component may be a sub-component related to the process of synchronizing scenes of the real world and the digital world.

[0038] The above sub-component may include a monitoring-related sub-component. The monitoring-related sub-component may perform processes such as continuously detecting, collecting, and analyzing data generated in the real world or within objects therefrom. In this case, the data to be targeted can be converted into digital signals in the real world and observed in real-time or near-real-time. For example, the monitoring-related sub-component may be a sub-component related to a series of processes in which changes in the real world are reflected in virtual objects within the digital twin.

[0039] The above sub-components may include sub-components related to modeling and simulation. The sub-components related to modeling and simulation may construct a physical model of the digital twin and perform predictions using it. The modeling may refer to constructing a model to predict structural changes in the real world within the digital twin. The simulation may refer to the model providing predicted results according to a given purpose. For example, the sub-components related to modeling and simulation may be sub-components related to performing modeling and simulation.

[0040] The above data storage unit can store data, reliability, metadata, etc., calculated by the above sub-component. The above data storage unit can provide data required by the reliability calculation unit. The above data storage unit can efficiently manage the data of the entire device.

[0041] The reliability calculation unit can calculate the reliability of the device, system, or method of the invention. The reliability calculation unit can calculate the overall reliability of the digital twin based on stored data and metadata. This process can ensure the reliability of the system and contribute to accurate judgment. The calculated reliability value can be provided to the user. It can be utilized as an important indicator for evaluating the reliability of the digital twin system. For example, the user can determine the reliability level of the digital twin using the reliability value. For example, if the current reliability value of the digital twin is less than 50% as a threshold, it can be determined that the current digital twin cannot be trusted.

[0042] The user may be an end user utilizing the results of the digital twin system. Based on the reliability value provided by the reliability calculation unit, the user can perform system operation, decision-making, and management of real-world situations.

[0043] FIG. 2 illustrates the configuration of a digital twin service providing device according to an embodiment.

[0044] Refer to FIG. 2. The digital twin service provider of FIG. 2 may further include a blockchain storage unit (4) in addition to the digital twin service provider of FIG. 1. For parts not specifically described, the description of FIG. 1 may be applied as is.

[0045] The blockchain storage unit can store data within the digital twin that requires integrity and immutability to be guaranteed in a blockchain network. It can perform the role of returning a hash value that guarantees the integrity of the stored data. Through the blockchain storage unit, advantages can be obtained such as guaranteeing the originality of the data and improving the accuracy of quantitative reliability by considering whether the data is stored in the blockchain when calculating reliability. In particular, the blockchain storage unit of the embodiment is characterized in that it acts as an element in the calculation of quantitative reliability, not just in the comparison of hash values.

[0046] Hereinafter, a digital twin service providing device and method including the blockchain storage unit and the provision of blockchain services through the above-mentioned blockchain storage unit will be described. Embodiments without the blockchain storage unit are also possible.

[0047] FIG. 3 illustrates a specific embodiment of a digital twin service provider.

[0048] Refer to FIG. 3. The real world can be defined as the external environment for the purpose of the digital twin. The user can be defined as a digital twin client module. The digital twin client module may be a computer program or a set of computer programs that a user of the service can interact with for mirroring, monitoring, modeling and simulation, management, and reliability verification. The user may be a person using the digital twin service.

[0049] The edge cloud cluster development and operation module (100) may be a digital twin service provider. Specifically, the edge cloud cluster development and operation module (100) may be a module in which an operator operates the digital twin service provider. More specifically, the edge cloud cluster development and operation module (100) may be a set of computer programs that develops and operates a set of computer programs constituting the digital twin service provider for the purpose of high flexibility and high availability.

[0050] The data storage unit (2) may include a digital twin data integrated storage unit (16). The reliability calculation unit (3) may include a quantitative reliability calculation module (19). The blockchain storage unit (4) may include a blockchain network (41), a blockchain-based reliability guarantee module (15), and a reference-based off-chain storage (42). The sub-storage unit (1) may include a plurality of modules to provide digital twin services.

[0051] The specific configuration of the embodiment is described in detail.

[0052] The continuous data detection and collection module (11) may be a device and a set of devices that continuously detect and collect external environments that are the purpose of the digital twin, the state of any object within said environment, and information that can be converted into a digital signal. For example, it may include IoT sensors / devices such as temperature and humidity sensors and UWB.

[0053] The scene data generation module (12) may be a device capable of intelligent processing or a set of devices capable of generating data corresponding to a scene of the external environment that is the purpose of the digital twin. For example, it may include a three-dimensional information providing device and a three-dimensional scene generation module. By the generation module, data corresponding to changes in the scene of the external environment can be generated at any period or intermittently.

[0054] The data integration and relay module (13) may include a processor, a computer program, and / or a set of programs that perform the function of integrating and relaying data composed of different arbitrary periods and types. For example, it may include Kafka + Kafka Connect + Kafka Stream.

[0055] The data processing and analysis module (14) may include a processor, a computer program, or a set of programs that perform the function of processing, analyzing, and processing data received from the data integration and relay module. For example, it may include Spark + Scikit-learn + customized functions.

[0056] A blockchain-based reliability guarantee module (15) may include a processor, a computer program, and / or a set of programs capable of guaranteeing reliability for any data by utilizing reference-based off-chain storage for lightweighting of the blockchain and the blockchain network.

[0057] Reference-based off-chain storage (42) may include a storage device, a processor, a computer program, a plurality of storage devices, and / or a set of programs that store original data and return a unique reference value for the efficient operation of a blockchain network, thereby enabling access to the original data. For example, it may include an IPFS (CID) that returns a CID as a reference value.

[0058] A blockchain network (41) is a distributed ledger storage system composed of any consensus algorithm, and may include a network system composed of a processor, a plurality of computing devices, and / or computer programs to ensure the integrity and immutability of data and to intelligently process any shared procedural contract.

[0059] A digital twin data integrated storage storage (16) may include a processor, a storage device, a computer program, a plurality of storage devices, and / or a set of programs that perform the function of integrating and storing data related to the digital twin so as to facilitate management and access.

[0060] The digital twin operation module (18) may include a processor, a computer program, and / or a set of computer programs that perform overall operation functions including mirroring, monitoring, modeling and simulation, and management processes of the digital twin, and provide information on the digital twin environment and reliability assurance therefor in accordance with the client's request.

[0061] The digital twin modeling and simulation module (17) may include a processor, a computer program, and / or a set of computer programs that create a model capable of making predictions through data of the digital twin and other external environments, and simulate results for any point in time or situation through such a model.

[0062] The quantitative reliability calculation module (19) may include a processor, a computer program, and / or a set of computer programs that provide a quantitative reliability for a digital twin at any point in time by considering the reliability of related sub-modules and whether they are stored on a blockchain, etc., to ensure the reliability of the digital twin.

[0063] The digital twin purpose environment control module (20) may include a processor, a machine, a computer program, a plurality of machines, and / or a set of computer programs that perform the function of controlling a machine and device capable of changing the state of the purpose external environment according to a request from a digital twin client (user) or intelligent processing of the digital twin.

[0064] A method for providing a digital twin service provided by the device of Fig. 3 is described.

[0065] The method for providing digital twin services may include a mirroring process, a monitoring process, a modeling and simulation process, a management process, and a reliability assurance process. The flow of each process is specified in the upper right corner of Fig. 3 for the mirroring process, monitoring process, modeling and simulation process, management process, and reliability assurance process.

[0066] The above mirroring process may mean synchronizing a 3D scene of the external real-world environment intended for the digital twin with a scene on the digital twin. The mirroring process may include static modification, which generates digital twin scene data for the scene of the external real-world environment at random intervals through a human operator or a machine device and computer program capable of intelligent processing, and dynamic modification, which modifies arbitrary object information within the scene according to data detected and collected during the monitoring process.

[0067] The above monitoring process may occur as a continuous flow in the "external real-world environment" or "any object within the external real-world environment" that the digital twin aims to achieve. Monitoring may refer to observing signals that can be converted into digital form. The monitoring process may be performed by machines and devices that continuously detect and collect said signals. The monitoring process may refer to observing changes in the target external environment in real-time and near-real-time at short intervals through said device or multiple devices.

[0068] The above monitoring process may refer to visualization in an arbitrary manner within the edge cloud cluster development and operation module. It primarily refers to continuously observing the state of an "arbitrary object" that is the source of data detected and collected by the device within a digital twin environment, and the corresponding "virtual twin object."

[0069] The Modeling & Simulation (M&S) process may include modeling and simulation. "Modeling" may refer to constructing a physical model of the digital twin based on data provided by a client or a digital twin operation module regarding the external real-world environment and the data collected from the aforementioned mirroring and monitoring. "Simulation" may refer to the act of receiving the prediction results of a model constructed for an arbitrary purpose.

[0070] The management process may be performed by controllable machines and devices capable of changing the state of the external real-world environment for the purpose of the digital twin. The devices may include processors and / or computer programs. The management process may refer to the act of changing the state of the external real-world environment by controlling appropriate machines and devices through intelligent judgment by a client, who is a user of the digital twin, or a digital twin operation module.

[0071] The digital twin process can be performed through the four steps mentioned above. However, a problem arises in that the reliability of the resulting digital twin is not guaranteed. For example, it is possible to verify whether the digital twin completely matches the real world. As an extreme example, the digital twin could be implemented completely differently from the real world.

[0072] The confidence assurance process can provide quantitative confidence regarding the state of the digital twin to ensure the confidence of the digital twin. The confidence assurance process can utilize blockchain-based confidence assurance techniques. The confidence assurance process can provide confidence regarding the state of the digital twin at any given point in time. Through this, the confidence of the digital twin can be guaranteed for any given point in time. For example, by performing the above confidence assurance process, quantitative information regarding confidence that it matches the real world by 95% (quantitatively) can be provided.

[0073] The specific flow of the digital twin service provision method according to the embodiment is explained. The process is explained using the original numbers indicated in FIG. 3. At least one of the following steps may not be performed.

[0074] 1. Data regarding the external environment that serves as the purpose of the digital twin or the environment is generated and collected. Monitoring may include the continuous detection and collection of the state of any object and information convertible into a digital signal. Mirroring may generate scene data regarding components such as the target external environment and any object within the external environment.

[0075] 2. The detected and collected original data and their sets can be transmitted to a reliability data integration and collection module with metadata predefined by the digital twin operator. Multiple sub-modules for detecting and collecting original data for reliability calculation can be configured, and intelligent processing can be performed according to the sub-modules.

[0076] The above metadata may include a number of examples as follows.

[0077] (1) Timestamp: The time at which metadata and data were transmitted. For example, it may include "timestamp": "2024-11-07T12:34:56Z".

[0078] (2) Data structure: A description of the structure of the response data, for example, may include "data_schema":"JSON".

[0079] (3) Container identification information: Information that can identify a container. For example, it may include "container_id": "container_1234".

[0080] (4) Container type: A distinction regarding the role of the container (type of sub-component). For example, it may include "container_type": "mirroring" (or a more specific type may be specified). The container type will vary depending on the policy and can be distinguished through container identification information.

[0081] (5) Related resource status: Status information such as CPU, Memory, etc. For example, it may include "cpu_usage":"55.3%", "memory_usage":"2.4GB". Through the resource status above, it is possible to compare with the previous state, and this information can be used to calculate Local confidence (LC, local confidence of each module and sub-component).

[0082] (6) Local Confidence: This may be a confidence calculated internally by each individual processing unit (similar to the container above). Depending on the policy, local confidence may or may not be calculated. Local confidence may be calculated later by the confidence calculation unit. However, it may include storing information for calculating quantitative confidence regarding the state of the digital twin together as metadata, and finally calculating it quantitatively by the confidence calculation unit. For example, the confidence regarding the "state" of the "local_confidence": "89.1" container may be given as an example.

[0083] (7) Output Confidence (Opt.): If the sub-component of this component produces an output value, it may optionally include confidence in the output value (such as in the case of an artificial intelligence model). For example, it may include "validation_loss":"0.02", "mAP@50":"0.995".

[0084] (8) Optional data: Optional data may vary depending on the type of container, etc. For example, "tags": ["sensor","temperature","video", "etc."] : Tags can be added according to policy. "processing_time_ms":150 : Time taken for processing (distinguished from timestamp). "sensor_config" or "sensor_spec": {"sampling_rate": "10Hz", "threshold": "75"}. "sensor_status": {"running", "stop", or a description of the status}. "log": Examples include log information for debugging, etc.

[0085] (9) Other required metadata. For example, "version":"1.0.0": version information for digital twin control. "error_code":"E_NONE": error code. "checksum":"281ef2...": may include checksum data for verifying data integrity.

[0086] (10) Actual data payload. For example, it may include eg "data_payload": {...actual data...}.

[0087] 3. To ensure the smooth operation of the digital twin while simultaneously processing blockchain-based trust, each data item and its associated metadata, such as low trust levels, can be relayed to an appropriate module. This relaying process can improve operational efficiency in cases such as real-time processing by separating "trust guarantee and trust calculation" from "digital twin operation." In this case, since trust is calculated considering whether the data is stored on the blockchain, it may be appropriate for real-time data to have a relatively low trust level.

[0088] 4. Data requiring blockchain-based reliability guarantee can be appropriately batched and processed according to the type of data and operational policy, and related metadata can be added and stored together in reference-based off-chain storage.

[0089] 5. After storing the data from step 4 above, reference data for the data can be returned. For example, it may include the IPFS CID (Content ID).

[0090] 6. The reference data returned in Step 5 for the data of Step 4 above can be stored in a blockchain network. This step can be performed on-chain.

[0091] 7. After the transaction of step 6 above is stored in the blockchain network, the transaction hash (TxHash) can be returned.

[0092] 8. The data from step 4 above, the reference data returned from step 5 above, the transaction hash returned from step 7 above, and metadata according to the operation policy can be stored together in integrated storage.

[0093] 9. Data with guaranteed reliability stored in integrated storage can be moved to the data analysis and processing module along with its metadata to perform analysis and processing.

[0094] 10. As a result of analyzing and processing the data from Step 9 above, the resulting "reliability" and "metadata" based on the operation policy can be moved to the digital twin operation module for smooth operation. Along with this, they can be moved to the corresponding module to ensure blockchain-based reliability.

[0095] 11. For the data of Step 10 above, blockchain-based reliability guarantee processing corresponding to Steps 4-7 above can be performed and stored in integrated storage as in Step 8 above.

[0096] 12. Data can be transmitted and processed to calculate the reliability of monitoring and mirroring for any point in time from the digital twin operation module. At this time, depending on the operation policy, requests may be made using metadata such as data references or transaction hashes instead of the original data.

[0097] 13. Calculated reliability and the data and metadata associated therewith can be stored in integrated storage for future use. This process may be optionally included depending on operational policies.

[0098] 14. By confirming that data storage including reliability is complete in the integrated storage and receiving the stored data one more time, the reliability of the reliability calculated by the data integrity verification can be strengthened. This process may be optionally included according to the operational policy. If this process is included, if the integrity of the transmitted data is not guaranteed, retries may be performed a number of times specified in the operational policy.

[0099] 15. The calculated reliability can provide quantitative reliability for the Monitoring and Mirroring processes at any given point in time.

[0100] 16. Requests for modeling and simulation of arbitrary data may occur based on user requests or intelligent processing of the digital twin. Alternatively, modeling and simulation may be performed based on data collected, processed, and stored over an arbitrary time interval.

[0101] 17. For modeling, data required for modeling and corresponding reliability guarantee data can be requested from the integrated storage. For simulation, the model to be used for simulation and corresponding reliability guarantee data can be requested from the integrated storage.

[0102] 18. The data requested in step 17 above can be returned to the modeling and simulation module.

[0103] 19. In addition to the "modeling and simulation results" and the corresponding "usage data" and "reliability metadata," you can request a calculation from the reliability calculation module by including the "reliability value" calculated in the M&S module.

[0104] 20. In step 19 above, the calculated reliability can be returned to the modeling and simulation module.

[0105] 21. The calculated reliability can quantitatively provide the reliability of the results of the M&S process using a digital twin.

[0106] Consequently, quantitative reliability can be delivered to the client module. Users can utilize this quantitative reliability information to aid in decision-making. For example, if reliability is high, users can trust the information in the digital twin and make a decision. Conversely, if reliability is low, users may only refer to the digital twin's information and make a decision after investigating further.

[0107] The following describes in detail the reliability and the method for calculating the reliability value.

[0108] Figure 4 is a graph of the types of time parameters used in calculating reliability values ​​and the corresponding time coefficients. Figure 5 is a flowchart specifically showing the method for calculating reliability values. Figure 6 is a table showing exemplary results of reliability value calculations.

[0109] Refer to FIGS. 4 to 6. Reliability may refer to the overall reliability of the digital twin. Reliability may be calculated by reflecting the reliability of at least one individual module. Reliability may be calculated by reflecting the reliability of all individual modules. The reliability of the individual modules has been explained using a temperature sensor as an example.

[0110] The above reliability can be performed using mathematical formula 1.

[0111]

[0112] Each element of the above mathematical formula 1 is explained.

[0113] S can be the set of all modules that must be considered to calculate quantitative reliability.

[0114] x can represent individual modules included in set S. For example, it can include all elements included in the implementation of a digital twin.

[0115] LC x (Local confidence, Regional reliability ) is the quantitative reliability of module x and may be a value at a given time. The above LC x It can be greater than or equal to 0 and less than or equal to 1.

[0116] ω x is as a weight for modulo x individual modules HyperparametersIt may be. The hyperparameters of the individual modules may be greater than or equal to 0 and less than or equal to 1. The hyperparameters of the individual modules may represent the degree to which the individual modules affect the reliability (reliability of the digital twin). For example, if the influence of an individual module on the digital twin is significant, the hyperparameters of the individual modules may increase.

[0117] γ is the weight of the blockchain-based trust guarantee module, corresponding to the use of the blockchain. blockchain's Hyperparameters It may be. The hyperparameters of the blockchain may be greater than or equal to 0 and less than or equal to 1. When data, etc. is stored in the blockchain, the blockchain hyperparameters may be set to 1. When data, etc. is not stored in the blockchain, the blockchain hyperparameters may be set to a value greater than or equal to 0 and less than 1.

[0118] t may be the timestamp at which the request to calculate the quantitative confidence value occurred. In other words, it may be the timestamp at the target point in time.

[0119] τ x may be a timestamp at the time when the quantitative confidence of module x was calculated.

[0120] Δ t is the time (t) when the request for calculation of the quantitative reliability value occurred and the time (τ) when the quantitative reliability was calculated. x As a weight for the difference of ), time difference Hyperparameters It can be. The hyperparameter of the above time difference can be given by Equation 2.

[0121]

[0122] In the above mathematical equation 2, the parameter z is the time (t) when the request for calculation of the quantitative reliability value occurs and the time (τ) when the quantitative reliability is calculated. xIt may be a predetermined function that takes the difference of ) as an argument. In the embodiment, the parameter z is the time (t) when the request to calculate the quantitative reliability value occurred and the time (τ) when the quantitative reliability was calculated. x It can be defined as the value obtained by subtracting the difference of ) and multiplying it by a predetermined coefficient (α). Figure 4 presents the result of Equation 2 as the coefficient is varied. The result of Equation 2 can present the result of the hyperparameter of the time difference.

[0123] The reliability can be calculated by the operation of the above mathematical formula 1 and the above mathematical formula 2.

[0124] FIG. 5 explains the process of calculating the reliability value according to the providing method presented in FIG. 3.

[0125] For example, each individual module can calculate its own local reliability. For instance, in the case of a temperature sensor, this can be determined in advance based on the sensor's measurement error. As another example, local reliability can be determined through statistical analysis of historical data or through an analysis of the true value versus the current value. Various other methods may also be used.

[0126] Subsequently, outside the individual module, LC x (Local confidence), ω x (hyperparameters of individual modules), and τ x (LC x The calculated timestamp) can be transmitted externally. The digital twin data integrated storage storage (16) can store data necessary for calculating the reliability value. The quantitative reliability calculation module (19) can determine the reliability of the digital twin using the stored data and the mathematical formulas 1 and 2. The reliability can be transmitted externally.

[0127] It can be seen that the reliability value obtained exemplarily in FIG. 6 is 65.31%. It can be seen that the hyperparameter of the individual module of the blockchain-based reliability guarantee module (15) is the largest. This may mean that the reliability of the digital twin is improved by the blockchain. The scene data generation module (12) [describes] the time (t) when the request for calculation of the quantitative reliability value occurs and the time (τ) when the quantitative reliability is calculated x It can be seen that the difference is the largest. This results in the hyperparameter of the above time difference becoming smaller. Accordingly, it can be seen that the reliability of the digital twin decreases as the time difference increases. Industrial applicability

[0128] According to the present invention, the quantitative reliability of a digital twin can be determined by considering the degree of contribution of each module of the digital twin, the reliability of each module, the tracking of module problems, and the reflection of operational policies. The quantitative reliability can be referenced for decision-making utilizing the digital twin. For example, when operating a smart factory, the results of the digital twin's execution can be reflected to determine whether to implement the smart factory in the real world. As a result, if the reliability of the digital twin is high, the likelihood of success for the smart factory in the real world can be increased. Explanation of the symbols

[0129] 1: Subcomponent 2: Data storage unit 3: Reliability Calculation Unit 4: Blockchain Storage

Claims

Claim 1 A digital twin service providing device comprising: at least one sub-component providing a digital twin service; a data storage unit storing first information necessary for providing the digital twin service; and a reliability calculation unit calculating the reliability of the digital twin service, wherein the sub-component includes: a monitoring-related sub-component configured to continuously detect, collect, and analyze first data occurring in the real world; a mirroring-related sub-component performing a process of synchronizing a scene of the real world with a digital twin environment; and a modeling and simulation-related sub-component constructing a physical model of the digital twin and performing a prediction using the physical model, wherein the first information stored in the data storage unit includes the first data, second data calculated by the sub-component, reliability, and metadata, and is configured to provide the first information upon request by the reliability calculation unit, and wherein the reliability calculation unit quantitatively calculates the reliability of the digital twin service using third data and provides a reliability value. Claim 2 A digital twin service providing device according to claim 1, wherein the third data includes regional reliability, which is the reliability of an individual module providing a digital twin service. Claim 3 A digital twin service providing device according to claim 1, wherein the third data includes hyperparameters of individual modules, which are weights of individual modules providing digital twin services. Claim 4 A digital twin service providing device according to claim 1, wherein the third data includes a hyperparameter of a blockchain, which is a weight corresponding to citing a blockchain to provide a digital twin service. Claim 5 In claim 1, the third data includes the time (t) when the request for calculation of the reliability value occurred and the time (τ) when the quantitative reliability was calculated. x A digital twin service provider that includes a hyperparameter of time difference, which is a weight for the difference of ). Claim 6 In claim 1, the reliability value is calculated using the following formula, and Here, S is the set of all modules to be considered for calculating quantitative reliability, x is an individual module included in set S, and LC x (Local confidence) is the quantitative confidence of module x, and ω x is a hyperparameter of an individual module as a weight for module x, γ is a hyperparameter of the blockchain as a weight for the blockchain-based trust guarantee module, t is a timestamp at which a request to calculate the quantitative trust value occurred, and τ x is the timestamp at the time when the quantitative confidence of module x was calculated, and Δ t is the time (t) when the request for calculation of the quantitative reliability value occurred and the time (τ) when the quantitative reliability was calculated. x A digital twin service provider, which is a hyperparameter of the time difference as a weight for the difference of ). Claim 7 A method for providing a digital twin service, comprising: a mirroring process, a process of synchronizing a 3D scene of an external real environment intended for the digital twin with a scene on the digital twin; a monitoring process, a process of monitoring the external real environment and any object within the external real environment; a modeling and simulation (M&S) process, a process of performing a first step of constructing a physical model of the digital twin using data collected in the mirroring and monitoring and the external real environment, and a second step of receiving a prediction result of the model; a management process, a process of changing the state of the external real environment; and a confidence guarantee process, a process of providing the confidence of the digital twin at any given point in time as a quantitative confidence value, wherein the confidence value is calculated by using together a first regional confidence of a first individual module and a second regional confidence of a second individual module, which are used to provide the digital twin service. Claim 8 In claim 7, the calculation of the reliability value comprises: hyperparameters of individual modules that are weights of individual modules providing digital twin services; hyperparameters of blockchain that are weights corresponding to citing the blockchain to provide digital twin services; and the time at which a request for calculation of the reliability value occurred and the time at which the local reliability was calculated (τ x A digital twin service provider comprising at least one of the hyperparameters of the time difference, which is a weight for the difference of ). Claim 9 In claim 7, the reliability value is calculated by the following formula, and Here, S is the set of all modules to be considered for calculating quantitative reliability, x is an individual module included in set S, and LC x (Local confidence) is the quantitative confidence of module x, and ω x is a hyperparameter of an individual module as a weight for module x, γ is a hyperparameter of the blockchain as a weight for the blockchain-based trust guarantee module, t is a timestamp at which a request to calculate the quantitative trust value occurred, and τ x is the timestamp at the time when the quantitative confidence of module x was calculated, and Δ t is the time (t) when the request for calculation of the quantitative reliability value occurred and the time (τ) when the quantitative reliability was calculated. x A method for providing a digital twin service, which is a hyperparameter of the time difference as a weight for the difference of ).

Images