Device reverse integration method and system based on digital twin optimization

Abstract

The invention discloses an equipment reverse integration method and system based on digital twin optimization, and relates to the technical field of Internet of Things. According to the main technical scheme, the method comprises the following steps: when to-be-added equipment exists in power-on equipment through scanning, determining an equipment twinborn body according to equipment information of the to-be-added equipment, and replaying an access process of the equipment twinborn body based on a digital twinborn model to obtain a replaying access result corresponding to the to-be-added equipment; generating a target access strategy corresponding to the to-be-newly added device by using a risk assessment algorithm according to risk indexes in the network performance indexes, the system resource influence indexes and the inter-device compatibility indexes and the risk degrees of the risk indexes; and according to the target access strategy, registering the to-be-added device to a server of the Internet of Things platform to access the to-be-added device. The main purpose is to reduce the risk that newly-added equipment accesses the Internet of Things platform and improve the stability and reliability of the reverse integration equipment of the Internet of Things platform.

Description

Technical Field

[0001] The present application relates to the technical field of Internet of Things, and in particular to a device reverse integration method and system based on digital twin optimization. Background Art

[0002] With the rapid development of the Internet of Things (IoT) and edge computing technology, the demand for IoT device access in industries such as industry, transportation, and smart cities has grown exponentially. The efficiency and stability of device access have become the core challenges of the IoT platform. If a device is to be used in the IoT, it must first be registered and connected to the IoT platform before intelligent management and automated control can be achieved.

[0003] At present, the access of new devices is usually done by direct access, that is, once the new device is detected to be powered on and connected to the Internet, it is attempted to be connected to the IoT platform. However, this method does not fully evaluate the adverse effects that the access of new devices may have on the IoT platform, which can easily lead to instability or even failure when the IoT platform reversely integrates the device. After the instability or failure occurs, a lot of manual troubleshooting and debugging work is required, which increases the operation and maintenance costs. Summary of the invention

[0004] In view of the above problems, the present application provides a device reverse integration method and system based on digital twin optimization, the main purpose of which is to reduce the risk of new devices accessing the Internet of Things platform and improve the stability and reliability of reverse integrated devices on the Internet of Things platform.

[0005] In order to solve the above technical problems, this application proposes the following solutions:

[0006] In a first aspect, the present application provides a device reverse integration method based on digital twin optimization, the method comprising:

[0007] When there is a device to be added among the scanned powered-on devices, the device twin is determined according to the device information of the device to be added, and the access process of the device twin is replayed based on the digital twin model to obtain the replayed access result corresponding to the device to be added, wherein the digital twin model is a virtual operation platform of the Internet of Things platform, and the replayed access result includes network performance indicators, system resource impact indicators, and compatibility indicators between devices;

[0008] Using a risk assessment algorithm, according to the risk indicators in the network performance indicator, the system resource impact indicator, and the inter-device compatibility indicator and the risk degree of the risk indicator, a target access strategy corresponding to the device to be added is generated;

[0009] According to the target access strategy, the device to be added is registered to the server of the Internet of Things platform to access the device to be added.

[0010] In a second aspect, the present application provides a device reverse integration system optimized based on digital twin. The system includes:

[0011] A replay processing unit, configured to, when there is a device to be newly added among the scanned and powered-on devices, determine a device twin according to the device information of the device to be newly added, and replay the access process of the device twin based on a digital twin model to obtain a replay access result corresponding to the device to be newly added. Wherein, the digital twin model is a virtual operation platform of an IoT platform, and the replay access result includes network performance indicators, system resource impact indicators, and device compatibility indicators;

[0012] A policy generation unit, configured to use a risk assessment algorithm to generate a target access policy corresponding to the device to be newly added according to the risk indicators among the network performance indicators, the system resource impact indicators, and the device compatibility indicators and the risk levels of the risk indicators;

[0013] A registration access unit, configured to register the device to be newly added to the server of the IoT platform according to the target access policy to access the device to be newly added.

[0014] To achieve the above object, according to a third aspect of the present application, there is provided a storage medium, which includes a stored program. When the program runs, it controls the device where the storage medium is located to execute the device reverse integration method based on digital twin optimization in the first aspect above.

[0015] To achieve the above object, according to a fourth aspect of the present application, there is provided a processor, which is used to run a program. When the program runs, it executes the device reverse integration method based on digital twin optimization in the first aspect above.

[0016] By means of the above-mentioned technical scheme, the present application provides a device reverse integration method and system based on digital twin optimization. When there is a device to be added among the scanned and powered-on devices, the device twin is determined according to the device information of the device to be added, and the access process of the device twin is reproduced based on the digital twin model to obtain the replayed access result corresponding to the device to be added. The digital twin model is a virtual operation platform of the Internet of Things platform. The replayed access result includes network performance indicators, system resource impact indicators and compatibility indicators between devices. A risk assessment algorithm is used to generate a target access strategy corresponding to the device to be added based on the risk indicators in the network performance indicators, system resource impact indicators and compatibility indicators between devices and the risk degree of the risk indicators. According to the target access strategy, the device to be added is registered to the server of the Internet of Things platform to access the device to be added. The technical solution provided by this application creates a digital twin of the device to be added, and uses the virtual operation platform (digital twin model) of the Internet of Things platform to replay its access process, predicts and evaluates the impact of new devices on network performance, system resources, and compatibility between devices in advance, and determines the risk indicators and the risk level of the risk indicators. Based on the risk indicators and risk level, the optimal target access strategy is generated using the risk assessment algorithm, thereby effectively reducing the risk of new devices accessing the Internet of Things platform and improving the stability and reliability of the reverse integration equipment of the Internet of Things platform. In addition, this method reduces the manual intervention required for problems caused by network congestion, device incompatibility, or resource contention, and reduces operation and maintenance costs.

[0017] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present application. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0019] Figure 1 A flow chart of a device reverse integration method based on digital twin optimization provided in an embodiment of the present application is shown;

[0020] Figure 2 A flow chart of another device reverse integration method based on digital twin optimization provided in an embodiment of the present application is shown;

[0021] Figure 3The block diagram of a device reverse integration system optimized based on digital twin provided by an embodiment of the present application is shown;

[0022] Figure 4 The block diagram of another device reverse integration system optimized based on digital twin provided by an embodiment of the present application is shown. Detailed implementation manners

[0023] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be fully conveyed to those skilled in the art.

[0024] Currently, for the access of newly added devices, a direct access method is usually adopted, that is, once it is detected that a newly added device is powered on and connected to the network, an attempt is made to connect it to the IoT platform. However, this method does not fully evaluate the possible adverse effects on the IoT platform when newly added devices are accessed, which easily leads to unstable or even faulty situations when the IoT platform reverse integrates devices. Moreover, after unstable or faulty situations occur, a large amount of manual troubleshooting and debugging work is required, increasing the operation and maintenance costs.

[0025] Therefore, an embodiment of the present application provides a device reverse integration method optimized based on digital twin. Through this method, the risk of newly added devices accessing the IoT platform can be reduced, and the stability and reliability of the IoT platform reverse integrating devices can be improved. The specific implementation steps are as follows Figure 1 shown, including:

[0026] 101. When there is a device to be newly added among the scanned powered-on devices, determine the device twin according to the device information of the device to be newly added, and replay the access process of the device twin based on the digital twin model to obtain the replayed access result corresponding to the device to be newly added.

[0027] Among them, the digital twin model is the virtual operation platform of the IoT platform, and the replayed access result includes network performance indicators, system resource impact indicators, and device compatibility indicators.

[0028] In this step, the IoT platform will scan the devices within the connection range regularly or in real time, send detection signals through specific network protocols (such as RS-232, RS-422, RS-485, ZigBee, Bluetooth, XingShan, Ethernet, etc.), and detect whether there are new devices powered on and in a connectable state. The scanning frequency can be set according to the actual needs of the IoT platform or edge nodes. For example, in industrial IoT scenarios with high real-time requirements, it may be set to scan once per second, while in some home IoT scenarios with lower real-time requirements, it may be set to scan once every few minutes.

[0029] When a new device is detected as powered on, the IoT platform will determine whether the device is a device to be newly added based on device information (such as MAC address, serial number, etc.). If the device information does not exist in the list of already connected devices of the IoT platform, then it will be identified as a device to be newly added.

[0030] The IoT platform communicates with the device to be newly added to obtain its detailed device information. This information includes but is not limited to the type of the device (such as sensors, actuators, controllers, etc.), model, hardware configuration (such as CPU model, memory size, storage capacity, etc.), supported communication protocols, working mode, data transmission frequency, etc. The way to obtain device information can be through the automatic reporting of the device to be newly added, or the IoT platform actively sending query commands to the device to be newly added to obtain it.

[0031] After obtaining the device information of the device to be newly added, the device twin of the device to be newly added can be determined according to the device information to connect it to the digital twin model constructed based on the IoT platform. This digital twin model is the virtual operation platform of the IoT platform, and through this virtual operation platform, the access process of the device twin can be reproduced. Before the device twin is accessed, the digital twin model can be initialized according to the real-time status data of the IoT platform (such as the current network load, system resource usage, running status of the already connected devices, etc.) to ensure that the digital twin model can accurately reflect the current state of the IoT platform. During the reproduction process, the digital twin model will dynamically calculate and reproduce the impact of device access on network performance, system resources, and device compatibility according to the characteristics and behavior patterns of the device twin, as well as the real-time status of the IoT platform, and obtain network performance indicators, system resource impact indicators, and device compatibility indicators. Among them, network performance indicators include but are not limited to bandwidth occupancy, average latency, and packet loss rate, system resource impact indicators include but are not limited to CPU usage, memory occupancy, and storage usage, and device compatibility indicators include but are not limited to communication protocol matching degree and signal interference degree.

[0032] According to the above detailed implementation, the digital twin model is used as the virtual operation platform of the IoT platform to replay the access process of the twin of the device to be added. Before the actual access, network performance indicators (such as bandwidth occupancy, average delay, packet loss rate), system resource impact indicators (such as CPU utilization, memory occupancy, storage usage) and inter-device compatibility indicators (such as communication protocol matching, signal interference degree) can be obtained. This enables the IoT platform to predict the risks that may be brought about by the access of the new device in advance, such as network congestion, insufficient system resources or communication conflicts between devices, and avoids instability and failure caused by problems found after actual access. Since the risk can be assessed in advance, the probability of instability or failure during actual access is reduced, thereby greatly reducing a large amount of manual troubleshooting and debugging work afterwards, and significantly reducing the operation and maintenance costs. In addition, by replaying the system resource impact indicators obtained during the access process, the IoT platform can reasonably allocate system resources in advance according to the needs of the new device to be added, avoiding resource waste or insufficient resources. For example, for some devices with high CPU resource requirements, their occupancy of the system CPU can be evaluated in the replay stage, and the resource allocation strategy can be adjusted in advance to ensure the efficient operation of the system.

[0033] 102. Utilize a risk assessment algorithm to generate a target access strategy corresponding to the device to be added based on the risk indicators in the network performance indicators, the system resource impact indicators, and the compatibility indicators between devices, as well as the risk levels of the risk indicators.

[0034] In this step, the risk threshold of each indicator can be determined in advance by statistically analyzing the historical network performance indicators, historical system resource impact indicators, and historical inter-device compatibility indicators of each type of connected device in the IoT platform during a preset period. For example, the mean and standard deviation of each indicator can be calculated, and the sum of the mean and the standard deviation of the preset multiple is used as the risk threshold corresponding to each indicator, and the preset multiple can be determined based on the failure frequency of each type of connected device after each connection to the IoT platform during the preset period.

[0035] The network performance indicators, system resource impact indicators, and inter-device compatibility indicators in the replay access results are compared with the risk thresholds determined above, and indicators exceeding the risk thresholds are found as risk indicators, and the risk level corresponding to the risk indicators is determined according to the degree of exceeding the thresholds. For example, the risk level can be divided into three levels: low, medium, and high.

[0036] Pre-collect the historical network performance indicators, historical system resource impact indicators, historical device compatibility indicators, and the actually adopted access strategies each time various connected devices are connected in the Internet of Things platform, and construct historical device access data. Among them, the actually adopted access strategies are all secure access strategies that have been continuously optimized. Perform preprocessing operations such as cleaning and normalization on the historical device access data to remove noise and outliers in the data, and normalize the indicator data in different ranges to the same scale so that the risk assessment model can better process the data. According to the characteristics of the problem and the type of data, select a suitable machine learning algorithm as the risk assessment algorithm, and construct the risk assessment model accordingly, such as decision tree, random forest, neural network, etc. Use the preprocessed historical device access data set to train the selected machine learning algorithm, so that the machine learning algorithm learns the mapping relationship between risk indicators, risk levels, and access strategies, so that after inputting the obtained risk indicators and risk levels into the risk assessment model through this mapping relationship, the best expected access strategy can be output. The expected access strategy can be directly used as the target access strategy. It is also possible to combine the occurrence probability of the access strategy being actually adopted in the historical device access data, so that the above risk assessment model additionally outputs a strategy confidence level at the same time. When the strategy confidence level exceeds a certain set threshold, the expected access strategy is considered trustworthy, and at this time, the expected access strategy is used as the target access strategy. Otherwise, the expected access strategy is untrustworthy, and at this time, manual review can be triggered so that relevant personnel can adjust and optimize the expected access strategy to obtain the target access strategy.

[0037] According to the above detailed implementation method, the risk assessment algorithm can screen out the most suitable expected access strategy from the access strategy library based on the risk indicators and risk levels in the replay access results and the mapping relationship learned from the historical device access data. The historical device access data includes various indicators and the actually adopted access strategies each time various connected devices are connected, enabling the generated strategy to fully consider the characteristics of different devices and access scenarios, and improving the accuracy and adaptability of the strategy. As the number of devices in the Internet of Things platform continues to increase and the network environment changes, the risk indicators and risk levels will also change dynamically. The risk assessment algorithm can adjust the target access strategy in real time according to the latest replay access results to ensure that the strategy always adapts to the current state of the Internet of Things platform. For example, when the network load suddenly increases, the risk assessment algorithm can timely adjust the access strategy to give priority to ensuring the access and operation of key devices. The reliability of the expected access strategy is judged by calculating the strategy confidence level. When the strategy confidence level reaches the preset trust threshold, the expected access strategy is used as the target access strategy. When the strategy confidence level does not reach the trust threshold, a manual review instruction is triggered, and the target access strategy is generated based on the results modified by humans. This method combines the intelligence of machine learning and the empirical judgment of humans, increasing the reliability of the target access strategy.

[0038] 103. Register the device to be added to the server of the IoT platform according to the target access policy to access the device to be added.

[0039] In this step, the IoT platform parses the generated target access policy to clarify the operations and configuration information included in the policy, such as the network configuration parameters (IP address, subnet mask, gateway, etc.), communication protocol settings, and system resource allocation scheme of the device to be added. According to the requirements of the target access policy, the IoT platform configures the device by sending the corresponding configuration information to the device to be added through communication with the device to be added. For example, if the target access policy requires the device to communicate using a specific communication protocol, the IoT platform will send the configuration parameters of the protocol to the device to be added for the device to be added to make the corresponding settings. After the device to be added is configured, the IoT platform registers the device information (such as the MAC address and serial number of the device) and configuration information in the server of the IoT platform. The server assigns a unique identifier to the device and stores the device information in the database for subsequent management and monitoring of the device to be added. After registration, the device to be added accesses the IoT platform according to the configured parameters and policies and starts data interaction and communication with the IoT platform. The IoT platform monitors the running status and data transmission of the device to be added in real time to ensure the normal access and stable operation of the device to be added. If an abnormal situation occurs during the access process, the IoT platform will handle it according to the preset emergency plan, such as reconfiguring the device and adjusting the access policy.

[0040] According to the above detailed implementation methods, using the optimized and precisely formulated target access policy to access the device to be added can maximize the avoidance of unstable factors during the access process and ensure that the device can be successfully accessed to the IoT platform and operate stably. For example, reasonably configuring the network parameters and communication protocols of the device according to the policy avoids communication failures caused by parameter mismatches. The target access policy is generated based on the replay access results and risk assessment algorithms, which can quickly determine the optimal access method and configuration parameters, reduce the trial-and-error time during the access process, and improve the efficiency of device access. For example, the original direct access method may require multiple attempts to find the appropriate configuration, while with the target access policy, the probability of successful access at one time is greatly increased.

[0041] Based on the above Figure 1It can be seen from the implementation method that the device reverse integration method based on digital twin optimization provided by this application creates a digital twin of the device to be added, and uses the virtual operation platform (digital twin model) of the Internet of Things platform to replay its access process, predicts and evaluates the impact of new devices on network performance, system resources and compatibility between devices in advance, and determines the risk indicators and the risk level of the risk indicators from them. Based on the risk indicators and risk level, the optimal target access strategy is generated using the risk assessment algorithm, thereby effectively reducing the risk of new devices accessing the Internet of Things platform and improving the stability and reliability of the reverse integration equipment of the Internet of Things platform. In addition, this method reduces the manual intervention required for problems caused by network congestion, device incompatibility or resource contention, and reduces operation and maintenance costs.

[0042] Further, the preferred embodiment of the present application is in the above Figure 1 Based on this, a detailed description of the process of reverse integration of equipment based on digital twin optimization is given. The specific steps are as follows Figure 2 As shown, including:

[0043] 201. Obtain the basic characteristics, behavior patterns and default parameters of various devices connected to the IoT platform.

[0044] In this step, comprehensive data collection can be performed on the devices connected to the IoT platform. Basic features include but are not limited to the brand, model, hardware specifications (such as CPU type, memory size, etc.), communication protocol, operating system version and other information of the device. The behavior mode refers to the behavior of the device during normal operation, including but not limited to data transmission frequency, response delay, working time period, etc. The default parameters cover the various parameter values ​​in the factory settings of the device, including but not limited to the preset operating temperature range, bandwidth requirements under the standard configuration, etc. This information can be obtained through the documents provided by the device manufacturer, API interface or directly from the device itself. For some old devices or devices that do not provide self-reporting function, the default parameters are supplemented by manually filling out the form.

[0045] 202. Create a device template according to basic features, behavior patterns and default parameters, and build a device template library based on the device template.

[0046] In this step, the connected devices of the IoT platform are classified by function, and a common template framework is designed for different types of devices, including the basic characteristics, typical behavior patterns, and commonly used default parameters of the type of device. In addition to common attributes, custom attributes specific to certain device types are allowed to be added to meet special needs. For example, for industrial control equipment, additional attributes may be required to describe its security level or protection capability.

[0047] Use the data collected in step 201 to fill in the corresponding fields in each device template. As more devices of the same type are connected to the IoT platform, regularly review and update the templates to reflect the latest changes or discovered problems. For example, if the performance of a certain model of a certain brand of device has improved after a firmware update, the relevant parameters in the device template of this device should be adjusted in a timely manner. Store all device templates in a database or file system that is easy to manage and retrieve according to a certain logic, that is, establish a searchable and clearly classified device template library to facilitate quickly locating and applying the appropriate template to the newly added device. For example, classification can be carried out according to the brand, function type or other meaningful criteria.

[0048] 203. Match the target device template corresponding to the newly added device in the device template library according to the device information, and generate the device twin corresponding to the newly added device based on the target device template and the device information.

[0049] Each device template in reference step 202 includes fields such as the basic features, typical behavior patterns, and common default parameters of this type of device. Therefore, the information corresponding to the above fields can be determined from the device information, that is, the target features, target behavior patterns, and target parameters of the newly added device. By comparing the similarity of the target features, target behavior patterns, and target parameters with the basic features, behavior patterns, and default parameters included in each device template, the target device template can be determined in the device template library.

[0050] It should be noted that the specific execution process of matching the target device template corresponding to the newly added device in the device template library according to the device information and generating the device twin corresponding to the newly added device based on the target device template and the device information is as follows: determine the target features, target behavior patterns, and target parameters in the device information, and obtain the weight coefficients corresponding to the target features, target behavior patterns, and target parameters respectively; calculate the matching degree with each device template in the device template library according to the target features, target behavior patterns, target parameters, and weight coefficients; use the device template with the highest matching degree as the target device template; generate the device twin corresponding to the newly added device based on the target features, target behavior patterns, target parameters, and target device template.

[0051] In this step, the target features include but are not limited to the brand, model, hardware specifications (such as CPU type, memory size, etc.) of the newly added device. The target behavior patterns include but are not limited to the data transmission frequency, response delay, working time period, etc. of the newly added device. The target parameters include but are not limited to the preset working temperature range of the newly added device, the bandwidth requirement under standard configuration, etc. Feature similarity S feature A string matching algorithm or a classification algorithm can be used to measure the similarity of text information such as brand and model. Behavior pattern similarity Sbehavior The similarity can be calculated by comparing the differences in numerical data such as data transfer frequency and working hours, and the standardized difference method or cosine similarity can be used. The parameter similarity S parameter The differences between numerical values can be directly compared, or the percentage of relative error can be used to evaluate the similarity.

[0052] According to domain knowledge or historical data analysis, corresponding weight coefficients are assigned to each target feature, target behavior pattern, and target parameter. These weight coefficients are used to reflect their importance in the matching process. The weight coefficients of the target feature, target behavior pattern, and target parameter are w feature , W behavior and W parameter . Replace S feature , S behavior , S parameter , w feature , W behavior and W parameter with S f , S b , S p , w f , w b and w p respectively. For each device template T i in the device template library, calculate its matching degree M(T i ) with the device to be newly added. Assuming m represents the target feature, n represents the target behavior pattern, and k represents the target parameter, the specific expression is:

[0053]

[0054] where S fj is the similarity score of the j-th feature, w fj is its weight, and the value range of j is (1, m), represents traversing all feature items and calculating the sum of the products of the similarity score and the weight. S bg is the similarity score of the g-th feature, w bg is its weight, and the value range of g is (1, n) represents traversing all behavior pattern items and calculating the sum of the products of the similarity score and the weight. S pl is the similarity score of the l-th feature, w pl is its weight, and the value range of l is (1, k) It means traversing all parameter items and calculating the sum of the products of similarity scores and weights. For the denominator part, the weights of features, behavior patterns, and parameters are summed respectively as a normalization factor to ensure the rationality of the matching degree calculation. Multiplying the similarity score by the corresponding weight coefficient is to reflect the "contribution weight" of each part to the final matching degree. Through weighted summation, the actual value of each target feature, target behavior pattern, and target parameter in the matching process can be more reasonably reflected, avoiding the deviation of the result from the true requirements due to "equal treatment" of all. i represents each device template in the device template library, and its value range is the entire set of the device template library.

[0055] According to the calculated matching degrees M(T i ) of all device templates, select the device template with the highest matching degree as the target device template T best . best Replace the basic features, behavior patterns, and default parameters in the selected target device template T

[0056] with the target features, target behavior patterns, and target parameters of the device to be newly added to generate a device twin. This device twin not only contains all the key characteristics of the physical device but also can accurately reproduce its expected performance in the digital twin model.

[0057] In this step, obtain the real-time status data of the IoT platform, including but not limited to bandwidth usage, average latency, packet loss rate, etc. Monitor the key resource metrics such as CPU usage, memory occupancy, and storage usage of the monitoring server and network nodes. It also includes physical environmental factors such as temperature and humidity, as well as any external conditions that may affect the device performance. Based on the collected real-time status data, adjust the basic settings of the digital twin model to ensure that it is as close as possible to the real operating environment. For example, if the bandwidth usage in the actual network is high, a corresponding high-load scenario should also be set in the digital twin model. In addition to real-time data, historical data over a period of time can also be loaded to help predict possible future trends or problems, which is helpful for a more comprehensive assessment of the potential impact after the new device is connected.

[0058] Define the key metrics to be monitored during the replay process, such as bandwidth occupancy, average latency, packet loss rate, CPU usage, memory occupancy, storage usage, communication protocol matching degree, and signal interference degree, etc. "virtually" connect the device twin to the digital twin model. It should be emphasized that this process involves all steps of the replay device going online, starting from the initial connection to the network until all necessary registration and configuration processes are completed. In the replay environment, let the device twin interact with other existing device twins, and replay operations such as data exchange and command execution in the real scenario.

[0059] 205. During the access process, real-time monitor and record the network performance metrics, system resource impact metrics, and device compatibility metrics between devices, and summarize them as the replay access result.

[0060] Among them, the network performance metrics include bandwidth occupancy, average latency, and packet loss rate; the system resource impact metrics include CPU usage, memory occupancy, and storage usage; the device compatibility metrics between devices include communication protocol matching degree and signal interference degree.

[0061] In this step, the measurement methods for the above-mentioned metrics are shown in Table 1:

[0062] Table 1

[0063]

[0064]

[0065] Summarize the metrics in the network performance metrics, system resource impact metrics, and device compatibility metrics between devices obtained based on the measurement methods in Table 1 as the replay access result of the device twin.

[0066] 206. Judge whether each metric in the network performance metrics, system resource impact metrics, and device compatibility metrics between devices is less than its respective preset compliance threshold.

[0067] In this step, extract each metric from the replay access result, including bandwidth occupancy, average latency, packet loss rate in the network performance metrics, CPU usage, memory occupancy, storage usage in the system resource impact metrics, and communication protocol matching degree and signal interference degree in the device compatibility metrics between devices.

[0068] Preset the compliance thresholds for each metric according to enterprise standards or industry specifications, etc. Evaluate each metric separately to check whether it is lower than the corresponding compliance threshold. If all metrics are lower than their respective compliance thresholds, it is considered that the device to be newly added can be safely accessed, and at this time, step 208 is executed. If any one or more metrics exceed the compliance threshold, then step 207 is executed at this time, that is, prepare to execute the access operation according to a specific strategy.

[0069] According to the above detailed embodiments, before optimizing the access policy for the device to be newly added through the risk assessment algorithm, the compliance threshold can be used to determine whether the device to be newly added can be safely connected to the IoT platform. If so, there is no need to generate an additional access policy, which greatly improves the access efficiency of the device to be newly added and reduces the computational burden.

[0070] 207. Using the risk assessment algorithm, generate the target access policy corresponding to the device to be newly added according to the risk indicators and the risk levels of the risk indicators in the network performance indicators, system resource impact indicators, and device compatibility indicators.

[0071] This step is combined with the description of step 102 in the above method, and the same content will not be repeated here. It should be noted that the specific execution process of generating the target access policy corresponding to the device to be newly added according to the risk indicators and the risk levels of the risk indicators in the network performance indicators, system resource impact indicators, and device compatibility indicators by using the risk assessment algorithm is as follows: Compare each indicator in the network performance indicators, system resource impact indicators, and device compatibility indicators with their respective preset risk thresholds to obtain the risk indicators and the risk levels of the risk indicators; input the risk indicators and the risk levels into the trained risk assessment model to obtain the expected access policy and the policy confidence corresponding to the expected access policy; if the policy confidence reaches the preset trust threshold, then use the expected access policy as the target access policy; if the policy confidence reaches the trust threshold, then trigger the manual review instruction for the expected access policy, and generate the target access policy based on the modification event of the expected access policy.

[0072] Among them, the risk assessment model filters out the expected access policy corresponding to the risk indicators and the risk levels in the access policy library according to the mapping relationship learned from the historical device access data. The historical device access data includes the historical network performance indicators, historical system resource impact indicators, historical device compatibility indicators, and the actual access policies when each type of connected device is accessed. The policy confidence is used to represent the occurrence probability corresponding to the actual access policy.

[0073] In this step, the risk thresholds corresponding to each indicator in the network performance indicators, system resource impact indicators, and device compatibility indicators are determined in advance. Each indicator is evaluated separately, that is, to check whether it exceeds the corresponding risk threshold. If it exceeds, it is defined as a risk indicator, and its risk level is determined according to the difference between the actual value of the risk indicator and the risk threshold. For example, different difference intervals are set, and each difference interval corresponds to a different risk level, such as low, medium, and high levels.

[0074] Input all the identified risk indicators and their risk levels into a pre-trained risk assessment model. This risk assessment model is trained based on historical device access data, which includes historical network performance indicators, historical system resource impact indicators, historical device compatibility indicators, and the actual access strategies adopted each time and their effectiveness feedback for various types of connected devices. The goal of this risk assessment model is to learn a mapping relationship from the historical device access data. This mapping relationship refers to the relationship between the historical network performance indicators, historical system resource impact indicators, historical device compatibility indicators, and the actual access strategies adopted each time. The access strategy library contains the actual access strategies adopted each time for various types of connected devices. It can predict the best access strategy and its confidence level when given a new set of risk indicators and risk levels. This risk assessment model can be trained using supervised learning methods such as random forest, support vector machine, or neural network, etc. Input all the identified risk indicators and their risk levels into the pre-trained risk assessment model. This risk assessment model can predict the best access strategy corresponding to the current risk indicators and risk levels, that is, the expected access strategy, according to the learned mapping relationship, and give a strategy confidence score. Since the strategy confidence is used to characterize the occurrence probability corresponding to the actual access strategy, the higher the occurrence probability, the more times the expected access strategy is used, and the higher the corresponding strategy confidence score will be.

[0075] Exemplarily, assume that the expected access strategy output by the risk assessment model is A, and its corresponding strategy confidence is C A . Then the strategy confidence C A has the following specific expression:

[0076]

[0077] where RiskIndicators is the set of all indicators identified as risks. W I is the weight coefficient of each risk indicator, reflecting the importance of this risk indicator in the overall risk assessment. R I is the risk level corresponding to the risk indicator. C A ranges from 0 to 1. The closer it is to 1, the higher the confidence of the risk assessment model in the expected access strategy. The value range of I is each risk indicator in the set RiskIndicators, that is, I traverses all the indicators identified as risks in the RiskIndicators set.

[0078] After determining the strategy confidence, obtain the preset trust threshold Threshold trust, the trust threshold can be customized according to requirements or determined by monitoring the actual effects of each access of various connected devices (such as whether the access is successful, whether there are any faults or performance issues, etc.). If C A ≥Threshold trust , the expected access policy output by the risk assessment model is directly adopted as the target access policy. If C A <Threshold trust , an artificial review instruction is triggered, that is, relevant personnel review the expected access policy, modify the expected access policy according to the actual situation, and generate the final target access policy based on the modification events of relevant personnel.

[0079] For the above description of the risk threshold, the specific implementation process for determining the risk threshold is as follows: Obtain the historical network performance indicators, historical system resource impact indicators, and historical device - to - device compatibility indicators of various connected devices each time they are accessed within a preset period on the IoT platform; calculate the mean and standard deviation of each indicator among the historical network performance indicators, historical system resource impact indicators, and historical device - to - device compatibility indicators respectively; add the mean of each indicator to the standard deviation multiplied by a preset multiple to obtain the risk threshold corresponding to each indicator.

[0080] Among them, the preset multiple is determined according to the failure frequency of various devices each time they are accessed within a preset period on the IoT platform.

[0081] In this step, each indicator in the network performance indicator, system resource impact indicator, and device - to - device compatibility indicator is determined in advance. For each indicator, the failure situation (if any) after each access also needs to be recorded. For each indicator I, calculate its mean μ I and standard deviation σ I . The specific expressions are as follows:

[0082]

[0083] Among them, N is the total number of accesses of all connected devices within a preset period. I i is the specific value of this indicator at the i - th access. i is an index variable used to traverse each access record of all connected devices, and the value range of i is (1, N).

[0084] The preset multiple k I is determined according to the failure frequency of various connected devices each time they are accessed within a preset period on the IoT platform. We can define a function F(I) based on the failure frequency to quantify the impact of the failure frequency on the preset multiple. Assume f iIndicates whether there is a fault during the i-th access (1 indicates there is a fault, 0 indicates there is no fault), then the total fault frequency F can be expressed as:

[0085]

[0086] To convert the fault frequency into a preset multiple k I , a non-linear function g(F) can be defined as:

[0087] k I = g(F) = a + b·e c·F ;

[0088] Where a, b, c are adjustable parameters that can be adjusted according to actual needs. For example, a = 1, b = 2, c = 5 can be selected to ensure that when the fault frequency is low, the preset multiple is close to 1, and as the fault frequency increases, the preset multiple increases rapidly.

[0089] Using the calculated mean μ I , standard deviation σ I and preset multiple k I , the risk threshold T tisk (I) of each index can be obtained:

[0090] T tisk (I) = μ I + k I ·σ I .

[0091] Through this formula, it can be ensured that the risk threshold not only considers the mean and fluctuation range of historical data, but also combines the influence of the fault frequency, so as to better reflect the risk level in actual operation.

[0092] 208. According to the target access policy, register the device to be added to the server of the IoT platform to access the device to be added.

[0093] This step is combined with the description of step 103 in the above method, and the same content will not be repeated here.

[0094] Furthermore, as an implementation of the method embodiment shown above Figure 1-2 , the embodiment of the present application provides a device reverse integration system optimized based on digital twin, which is used to reduce the risk of adding new devices to the IoT platform and improve the stability and reliability of the IoT platform for reverse integrating devices. The embodiment of this system corresponds to the foregoing method embodiment. For the convenience of reading, the details of the foregoing method embodiment will not be repeated one by one in this embodiment, but it should be clear that the system in this embodiment can correspondingly implement all the content in the foregoing method embodiment. Specifically as Figure 3 shown, this system includes:

[0095] A replay processing unit 31, configured to, when there is a device to be newly added in the scanned power-on device, determine a device twin according to the device information of the device to be newly added, and replay the access process of the device twin based on a digital twin model to obtain a replay access result corresponding to the device to be newly added, where the digital twin model is a virtual operation platform of the IoT platform, and the replay access result includes network performance indicators, system resource impact indicators, and device compatibility indicators;

[0096] A policy generation unit 32, configured to use a risk assessment algorithm to generate a target access policy corresponding to the device to be newly added according to risk indicators in the network performance indicators, the system resource impact indicators, and the device compatibility indicators and the risk levels of the risk indicators;

[0097] A registration access unit 33, configured to register the device to be newly added to the server of the IoT platform according to the target access policy to access the device to be newly added.

[0098] Further, as Figure 4 shown, the system further includes:

[0099] An acquisition unit 34, configured to acquire basic features, behavior patterns, and default parameters of various devices already connected to the IoT platform before the replay processing unit 31;

[0100] A construction unit 35, configured to create a device template according to the basic features, the behavior patterns, and the default parameters, and construct a device template library based on the device template;

[0101] The replay processing unit 31 includes:

[0102] A matching generation module 311, configured to match a target device template corresponding to the device to be newly added in the device template library according to the device information, and generate the device twin corresponding to the device to be newly added based on the target device template and the device information;

[0103] A replay access module 312, configured to initialize the digital twin model according to real-time status data of the IoT platform, and access the device twin into the digital twin model, so that the digital twin model replays the access process of the device twin;

[0104] A recording and summarizing module 313, configured to monitor and record the network performance indicators, the system resource impact indicators, and the device compatibility indicators in real time during the access process, and summarize them into the replay access result.

[0105] Further, as Figure 4As shown, the matching generation module 311 is specifically configured to:

[0106] Determine the target features, target behavior patterns, and target parameters in the device information, and obtain the weight coefficients corresponding to the target features, the target behavior patterns, and the target parameters respectively;

[0107] Calculate the matching degrees with each device template in the device template library respectively according to the target features, the target behavior patterns, the target parameters, and the weight coefficients;

[0108] Take the device template with the highest matching degree as the target device template;

[0109] Generate the device digital twin corresponding to the device to be newly added based on the target features, the target behavior patterns, the target parameters, and the target device template.

[0110] Furthermore, as Figure 4 shown, the policy generation unit 32 includes:

[0111] A risk comparison module 321, configured to compare each index in the network performance index, the system resource impact index, and the device - to - device compatibility index with its respective preset risk threshold to obtain the risk index and the risk level of the risk index;

[0112] A policy determination module 322, configured to input the risk index and the risk level into a trained risk assessment model to obtain the expected access policy and the policy confidence level corresponding to the expected access policy, where the risk assessment model filters out the expected access policy corresponding to the risk index and the risk level from the access policy library according to the mapping relationship learned from historical device access data, and the historical device access data includes the historical network performance index, historical system resource impact index, historical device - to - device compatibility index, and the actual access policy adopted each time for various connected devices, and the policy confidence level is used to represent the occurrence probability corresponding to the actual access policy;

[0113] A first processing module 323, configured to, if the policy confidence level reaches a preset trust threshold, take the expected access policy as the target access policy;

[0114] A second processing module 324, configured to, if the policy confidence level reaches the trust threshold, trigger an artificial review instruction for the expected access policy, and generate the target access policy based on the modification event of the expected access policy.

[0115] Furthermore, as Figure 4 shown, the system further includes:

[0116] An index acquisition module 325, configured to acquire historical network performance indexes, historical system resource impact indexes, and historical device - to - device compatibility indexes each time various types of connected devices are connected to the IoT platform within a preset period before the risk comparison module 321;

[0117] An index calculation module 326, configured to calculate the mean and standard deviation of each index among the historical network performance indexes, the historical system resource impact indexes, and the historical device - to - device compatibility indexes respectively;

[0118] A threshold determination module 327, configured to add the mean of each index to the standard deviation multiplied by a preset multiple to obtain the risk threshold corresponding to each index, where the preset multiple is determined according to the failure frequency of various types of devices each time they are connected to the IoT platform within a preset period.

[0119] Further, as Figure 4 shown, the system further includes:

[0120] A compliance judgment unit 36, configured to judge whether each index among the network performance index, the system resource impact index, and the device - to - device compatibility index is less than its respective preset compliance threshold before the policy generation unit 32;

[0121] The policy generation unit 32 is specifically configured to,

[0122] if not, then use a risk assessment algorithm to generate a target access policy for the to - be - added device according to the risk indexes and the risk levels of the risk indexes among the network performance index, the system resource impact index, and the device - to - device compatibility index;

[0123] The registration and accounting unit 33 is further configured to, if so, directly register the to - be - added device to the server of the IoT platform to access the to - be - added device.

[0124] Further, as Figure 4 shown, the system further includes:

[0125] The network performance index includes bandwidth occupancy, average latency, and packet loss rate;

[0126] The system resource impact index includes CPU usage rate, memory occupancy, and storage usage;

[0127] The device - to - device compatibility index includes communication protocol matching degree and signal interference degree.

[0128] Further, an embodiment of the present application also provides a storage medium for storing a computer program, wherein when the computer program runs, it controls the device where the storage medium is located to execute the above-mentioned Figure 1-2 device reverse integration method optimized based on digital twin described in

[0129] Further, an embodiment of the present application also provides a processor for running a program, wherein when the program runs, it executes the above-mentioned Figure 1-2 device reverse integration method optimized based on digital twin described in

[0130] In the above embodiments, the descriptions of the respective embodiments have their own focuses. For parts not detailed in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0131] It can be understood that the relevant features in the above methods and systems can be referred to each other. In addition, the "first", "second", etc. in the above embodiments are used to distinguish the respective embodiments, and do not represent the advantages or disadvantages of the respective embodiments.

[0132] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0133] The algorithms and displays provided herein are not inherently related to any specific computer, virtual system, or other device. Various general-purpose systems can also be used in conjunction with the teachings herein. The structure required to construct such a system is obvious from the above description. In addition, the present application is not directed to any specific programming language. It should be understood that the content of the present application described herein can be implemented using various programming languages, and the description of the specific language above is to disclose the best implementation mode of the present application.

[0134] In addition, the memory may include non-permanent memory in a computer-readable medium, random access memory (RAM), and / or non-volatile memory such as read-only memory (ROM) or flash RAM, and the memory includes at least one storage chip.

[0135] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0136] This application is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, as well as the combination of flows and / or blocks in the flowchart and / or block diagram. These computer program instructions can be provided to the processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing device to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing device generate a system for implementing the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 one or more of the blocks and implementing the functions specified therein.

[0137] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including an instruction system that implements the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 one or more of the blocks and implementing the functions specified therein.

[0138] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operational steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 one or more of the blocks and implementing the functions specified therein.

[0139] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0140] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM), and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM). The memory is an example of computer-readable media.

[0141] A computer-readable medium includes both permanent and non-permanent, removable and non-removable media and can implement information storage by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transitory medium that can be used to store information accessible by a computing device. As defined herein, a computer-readable medium does not include transitory computer-readable media, such as modulated data signals and carrier waves.

[0142] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the element.

[0143] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, system, or computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer-usable program code.

[0144] The above are only embodiments of the present application and are not used to limit the present application. For those skilled in the art, the present application can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. A device reverse integration method based on digital twin optimization, characterized in that: The method comprises: When there is a device to be added among the scanned powered-on devices, the device twin is determined according to the device information of the device to be added, and the access process of the device twin is replayed based on the digital twin model to obtain the replayed access result corresponding to the device to be added, wherein the digital twin model is a virtual operation platform of the Internet of Things platform, and the replayed access result includes network performance indicators, system resource impact indicators, and compatibility indicators between devices; Using a risk assessment algorithm, according to the risk indicators in the network performance indicator, the system resource impact indicator, and the inter-device compatibility indicator and the risk degree of the risk indicator, a target access strategy corresponding to the device to be added is generated; According to the target access strategy, the device to be added is registered to the server of the Internet of Things platform to access the device to be added.

2. The method according to claim 1, characterized in that Before determining a twin according to the device information of the device to be added, and replaying the access process of the device twin based on the digital twin model to obtain a replay access result corresponding to the device to be added, the method further includes: Obtain the basic characteristics, behavior patterns and default parameters of various devices connected to the IoT platform; Creating a device template according to the basic features, the behavior mode and the default parameters, and building a device template library based on the device template; The determining of the device twin according to the device information of the device to be added, and replaying the access process of the device twin based on the digital twin model to obtain the replay access result corresponding to the device to be added, includes: Matching a target device template corresponding to the device to be added in the device template library according to the device information, and generating the device twin corresponding to the device to be added based on the target device template and the device information; Initializing the digital twin model according to the real-time status data of the IoT platform, and connecting the device twin to the digital twin model, so that the digital twin model replays the connection process of the device twin; During the access process, the network performance index, the system resource impact index and the inter-device compatibility index are monitored and recorded in real time, and summarized as the replay access result.

3. The method according to claim 2, characterized in that According to the device information, a target device template corresponding to the device to be added is matched in the device template library, and the device twin corresponding to the device to be added is generated based on the target device template and the device information, including: Determine the target feature, target behavior pattern and target parameter in the device information, and obtain the weight coefficient corresponding to each of the target feature, the target behavior pattern and the target parameter; Calculating the matching degree with each device template in the device template library respectively according to the target feature, the target behavior pattern, the target parameter and the weight coefficient; Using the device template with the highest matching degree as the target device template; Based on the target features, the target behavior patterns, the target parameters and the target device template, the device twin corresponding to the device to be added is generated.

4. The method according to claim 1, characterized in that Using a risk assessment algorithm, according to the risk indicators in the network performance indicator, the system resource impact indicator, and the inter-device compatibility indicator and the risk degree of the risk indicator, a target access strategy corresponding to the device to be added is generated, including: Comparing each of the network performance index, the system resource impact index, and the inter-device compatibility index with respective preset risk thresholds to obtain the risk index and the risk degree of the risk index; The risk indicator and the risk degree are input into a trained risk assessment model to obtain the expected access strategy and the policy confidence corresponding to the expected access strategy, wherein the risk assessment model selects the expected access strategy corresponding to the risk indicator and the risk degree in the access policy library according to the mapping relationship learned from the historical device access data, the historical device access data includes the historical network performance indicators, historical system resource impact indicators, historical inter-device compatibility indicators and the actually adopted access strategies of various types of accessed devices at each access, and the policy confidence is used to characterize the occurrence probability corresponding to the actually adopted access strategy; If the policy confidence reaches a preset trust threshold, the expected access policy is used as the target access policy; If the policy confidence reaches the trust threshold, a manual review instruction of the expected access policy is triggered, and the target access policy is generated based on the modification event of the expected access policy.

5. The method according to claim 4, characterized in that Before comparing the network performance indicator, the system resource impact indicator, and the inter-device compatibility indicator with respective preset risk thresholds to obtain the risk indicator and the risk degree of the risk indicator, the method further includes: Obtain historical network performance indicators, historical system resource impact indicators, and historical inter-device compatibility indicators of each type of connected device at each access of the IoT platform within a preset period; Respectively calculating the mean and standard deviation of each of the historical network performance index, the historical system resource impact index, and the historical inter-device compatibility index; The mean of each indicator is added to the standard deviation of the preset multiple to obtain the risk threshold corresponding to each indicator, wherein the preset multiple is determined based on the failure frequency of each type of equipment after each connection to the IoT platform within a preset period.

6. The method according to any one of claims 1 to 5, characterized in that Before generating a target access policy corresponding to the device to be added by using a risk assessment algorithm according to the risk indicators in the network performance indicator, the system resource impact indicator, and the inter-device compatibility indicator and the risk degree of the risk indicator, the method further includes: Determining whether each of the network performance indicator, the system resource impact indicator, and the inter-device compatibility indicator is less than a respective preset compliance threshold; If not, using a risk assessment algorithm, according to the risk indicators in the network performance indicator, the system resource impact indicator, and the inter-device compatibility indicator and the risk degree of the risk indicator, a target access strategy corresponding to the device to be added is generated; If yes, the device to be added is directly registered to the server of the IoT platform to access the device to be added.

7. The method according to any one of claims 1 to 5, characterized in that The network performance indicators include bandwidth occupancy, average delay and packet loss rate; The system resource impact indicators include CPU usage, memory usage, and storage usage; The inter-device compatibility index includes communication protocol matching and signal interference level.

8. A device reverse integration system based on digital twin optimization, characterized in that: The system comprises: A replay processing unit, for determining a device twin according to device information of the device to be added when there is a device to be added among the scanned powered-on devices, and replaying the access process of the device twin based on the digital twin model to obtain a replay access result corresponding to the device to be added, wherein the digital twin model is a virtual operation platform of the IoT platform, and the replay access result includes network performance indicators, system resource impact indicators, and compatibility indicators between devices; A policy generating unit, configured to generate a target access policy corresponding to the device to be added by using a risk assessment algorithm according to the risk indicators in the network performance indicator, the system resource impact indicator, and the inter-device compatibility indicator and the risk degree of the risk indicator; A registration access unit is used to register the device to be added to the server of the Internet of Things platform according to the target access strategy to access the device to be added.

9. A storage medium, characterized in that: The storage medium includes a stored program, wherein, when the program is running, the device where the storage medium is located is controlled to execute the device reverse integration method based on digital twin optimization as described in any one of claims 1 to 7.

10. A processor, characterized in that: The processor is used to run a program, wherein the program, when running, executes the device reverse integration method based on digital twin optimization as described in any one of claims 1 to claim 7.

Images