A RMS evaluation method and performance evaluation system for intelligent equipment

By introducing a performance evaluation system in smart devices, using edge computing and dynamic adaptive communication modules for RMS evaluation, the delay and stability problems caused by cloud computing center dependence are solved, and faster and more accurate data processing and network stability are achieved. sex.

CN118210693BActive Publication Date: 2024-11-01CHINA ELECTRONICS CORP 6TH RES INST
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410481776.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-04-22
Publication Date
2024-11-01
Estimated Expiration
2044-04-22

AI Technical Summary

Technical Problem

The RMS evaluation of smart devices relies on cloud computing centers, resulting in delayed data transmission, untimely processing and risk of central node failure, and the existing communication methods are unstable in harsh or unstable network environments.

Method used

Using a performance evaluation system, including multiple edge computing modules, dynamic adaptive communication modules and data fusion modules, RMS evaluation is performed through quantum communication components, quantum computing components and classic computing components, data is collected in real time, local evaluation is performed and communication network is optimized. Transmission, combined with importance weighting processing, realizes comprehensive evaluation of smart devices.

Benefits of technology

It reduces data transmission delay, enhances the immediacy and accuracy of data processing, ensures the stability of the transmission network, and improves the robustness and adaptability of the system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118210693B_ABST
    Figure CN118210693B_ABST
Patent Text Reader

Abstract

The present application provides a RMS evaluation method and performance evaluation system for intelligent devices, including: an edge computing module, which performs RMS evaluation on local equipment data, obtains local evaluation results reflecting the RMS performance of key components, and sends the local evaluation results and local equipment data to the corresponding dynamic adaptive communication module; a dynamic adaptive communication module, which optimizes the communication network between the edge computing module and the data fusion module, and sends the local evaluation results to the data fusion module through the optimized communication network; a data fusion module, which performs importance weighting processing on each local evaluation result according to the importance of different key components to the intelligent device, and obtains a comprehensive evaluation result reflecting the RMS performance of the intelligent device under a preset test environment. The present application introduces a performance evaluation system to perform RMS evaluation on intelligent devices, reduce data transmission delays, enhance the immediacy and accuracy of data processing, and ensure the stability of the transmission network.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of RMS evaluation of smart devices, and in particular to a RMS evaluation method and performance evaluation system for smart devices. Background Art

[0002] Currently, the RMS (Root Mean Square) evaluation corresponding to smart devices mostly relies on cloud computing centers for data processing and analysis, which leads to risks such as data transmission delays, untimely processing and central node failures. In addition, although existing communication methods such as DDS provide a good data sharing platform, their performance is not robust when facing harsh or unstable network environments. Summary of the invention

[0003] In view of this, the purpose of this application is to at least provide an RMS evaluation method and performance evaluation system for smart devices. This application introduces a performance evaluation system to perform RMS evaluation on smart devices, thereby reducing data transmission delays, enhancing the immediacy and accuracy of data processing, and ensuring the stability of the transmission network.

[0004] This application mainly includes the following aspects:

[0005] In a first aspect, an embodiment of the present application provides an RMS evaluation method for an intelligent device, which is applied to a performance evaluation system. The performance evaluation system includes multiple edge computing modules, multiple dynamic adaptive communication modules and a data fusion module. The multiple edge computing modules correspond to the multiple dynamic adaptive communication modules one by one. Different edge computing modules are connected to different key components of the intelligent device. The intelligent device is placed in a preset test environment. The method includes: the edge computing module collects the local equipment data generated by the corresponding key components and / or data interaction with other edge computing modules in real time, performs RMS evaluation on the local equipment data, obtains a local evaluation result reflecting the RMS performance of the key components, and sends the local evaluation result and the local equipment data to the corresponding dynamic adaptive communication module. The dynamic adaptive communication module extracts communication status data from the local equipment data, optimizes the communication network between the edge computing module and the data fusion module through a pre-trained Qos adjustment model and communication status data, and sends the local evaluation result to the data fusion module through the optimized communication network. The data fusion module performs importance weighting processing on each local evaluation result according to the importance of different key components to the intelligent device, so as to obtain a comprehensive evaluation result reflecting the RMS performance of the intelligent device under the preset test environment.

[0006] In one possible implementation, each edge computing module includes a quantum communication component, a quantum computing component, a classical computing component and an edge computing platform, and the performance indicators output by different edge computing modules are different. The first quantum communication component uses quantum key distribution technology to exchange quantum keys and local equipment data from the corresponding data interface and / or other edge computing modules, and sends the collected local equipment data to the quantum computing component and the classical computing component respectively; the quantum computing component performs quantum calculations on the local equipment data, determines multiple quality assessment features and sends them to the edge computing platform; the classical computing component performs classical calculations on the local equipment data, determines multiple quality assessment features and sends them to the edge computing platform; the edge computing platform uses a pre-trained RMS performance prediction model corresponding to the key components to perform RMS evaluation on multiple quality assessment features, obtains multiple performance indicators reflecting the RMS performance of the key components, weights the multiple performance indicators by an importance weighting method, obtains a local evaluation result corresponding to the key components under a preset test environment, and sends the local evaluation result and the local equipment data to the edge computing management component and the dynamic adaptive communication module.

[0007] In one possible implementation, the edge computing platform is also used to: integrate local evaluation results of key components in multiple different test environments; perform importance-weighted processing on the local evaluation results corresponding to the key components in each test environment according to the impact weights of different test environments on the key components, and obtain target local evaluation results that reflect the key components. The target local evaluation results reflect the overall stability of the key components when the test environment changes.

[0008] In one possible implementation, the edge computing module also includes an edge computing management component, which: updates local evaluation results corresponding to key components; determines whether the local evaluation results reach a warning threshold; and triggers an alarm for the key components if it is determined that the local evaluation results reach the warning threshold.

[0009] In one possible implementation, the dynamic adaptive communication module includes a second quantum communication component, a data collection and processing component, a QoS parameter prediction component and an adaptive QoS manager. The second quantum communication integration component uses quantum key distribution technology to exchange quantum keys, local equipment data and local evaluation results from the corresponding edge computing module, and sends the local equipment data and local evaluation results to the data collection and processing component; the data collection and processing component extracts communication status data from the local equipment data, analyzes the communication status data, and inputs the communication status data into the QoS parameter prediction component; the QoS parameter prediction component inputs the communication status data and the local evaluation results into a built-in QoS adjustment model to determine the optimal QoS parameter combination for the best communication performance, and sends the optimal QoS parameter combination to the adaptive QoS manager; the adaptive QoS manager optimizes the communication network between the edge computing module and the data fusion module according to the optimal QoS parameter combination, and sends the local evaluation results to the data fusion module through the optimized communication network.

[0010] In one possible implementation, the dynamic adaptive communication module also includes a heterogeneous network access layer, which is arranged at the front end of the second quantum communication integrated component in the corresponding edge computing module. The heterogeneous network access layer enables key components and / or other edge computing modules of different network types to access the corresponding edge computing modules through a preset universal adapter. The preset universal adapter describes the mapping relationship between the transmission protocol and the unified protocol under different network types.

[0011] In one possible implementation, the data fusion module is also used to: integrate the comprehensive evaluation results of the smart device in multiple different test environments; perform importance-weighted processing on the comprehensive evaluation results in each test environment according to the weight of the smart device and the weights corresponding to different test environments, so as to obtain a target comprehensive evaluation result reflecting the smart device.

[0012] In one possible implementation, the performance evaluation system also includes an advanced monitoring and management center, wherein the advanced monitoring and management center monitors the load conditions of each edge computing module, and performs dynamic task scheduling and resource allocation based on the load conditions; monitors the operating status of the edge computing module in real time, and initiates an abnormality recovery mechanism corresponding to the abnormal state if an abnormality is detected in the edge computing module; monitors the performance indicators of the edge computing module in real time, and executes corresponding performance optimization strategies based on the performance status of the key components indicated by the performance indicators.

[0013] In one possible implementation, the performance evaluation system also includes a user interface module, which is respectively connected to multiple edge computing modules and a data fusion module, and is used to: visualize local evaluation results corresponding to different key components of the smart device, target local evaluation results, and comprehensive evaluation results of the smart device under a preset test environment, as well as target comprehensive evaluation results.

[0014] In a second aspect, an embodiment of the present application further provides a performance evaluation system, which includes multiple edge computing modules, an edge performance integration module, multiple dynamic adaptive communication modules and a data fusion module. The multiple edge computing modules correspond one-to-one to the multiple dynamic adaptive communication modules. Different edge computing modules are connected to different key components of the smart device. The smart device is placed in a preset test environment, wherein the edge computing module collects the local equipment data generated by the corresponding key components and / or data interaction with other edge computing modules in real time, performs RMS evaluation on the local equipment data, obtains a local evaluation result reflecting the RMS performance of the key components, and sends the local evaluation result and the local equipment data to the corresponding dynamic adaptive communication module; the dynamic adaptive communication module extracts communication status data from the local equipment data, optimizes the communication network between the edge computing module and the data fusion module through the pre-trained Qos adjustment model and communication status data, and sends the local evaluation result to the data fusion module through the optimized communication network; the data fusion module performs importance weighting processing on each local evaluation result according to the importance of different key components to the smart device, and obtains a comprehensive evaluation result reflecting the RMS performance of the smart device under the preset test environment.

[0015] The embodiment of the present application provides an RMS evaluation method and performance evaluation system for smart devices, including: an edge computing module, which performs RMS evaluation on local equipment data, obtains local evaluation results reflecting the RMS performance of key components, and sends the local evaluation results and local equipment data to the corresponding dynamic adaptive communication module; a dynamic adaptive communication module, which optimizes the communication network between the edge computing module and the data fusion module, and sends the local evaluation results to the data fusion module through the optimized communication network; a data fusion module, which performs importance weighting processing on each local evaluation result according to the importance of different key components to the smart device, and obtains a comprehensive evaluation result reflecting the RMS performance of the smart device under a preset test environment. The present application introduces a performance evaluation system to perform RMS evaluation on smart devices, thereby reducing data transmission delays, enhancing the immediacy and accuracy of data processing, and ensuring the stability of the transmission network.

[0016] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 A performance evaluation system provided by an embodiment of the present application is shown;

[0019] Figure 2 An interactive schematic diagram of an intelligent device RMS evaluation method provided by an embodiment of the present application is shown;

[0020] Figure 3 An architecture diagram of an edge computing module provided in an embodiment of the present application is shown;

[0021] Figure 4 A schematic diagram of a dynamic adaptive communication module provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0022] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the drawings in the present application only serve the purpose of explanation and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn in real proportion. The flowchart used in this application shows the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowchart can be implemented out of sequence, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art, under the guidance of the content of the present application, can add one or more other operations to the flowchart, or remove one or more operations from the flowchart.

[0023] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0024] Currently, most smart device RMS assessments rely on cloud computing centers for data processing and analysis, which leads to risks such as data transmission delays, untimely processing, and central node failures. In addition, although existing communication methods such as DDS provide a good data sharing platform, their performance is not robust when facing harsh or unstable network environments.

[0025] Based on this, the embodiment of the present application provides a smart device performance prediction method and a performance evaluation system. By introducing a performance evaluation system to perform RMS evaluation on smart devices, data transmission delay is reduced, the immediacy and accuracy of data processing are enhanced, and the stability of the transmission network is ensured. The details are as follows:

[0026] See also Figure 1 , Figure 1 A performance evaluation system provided by an embodiment of the present application is shown. Figure 2 , Figure 2 FIG. 1 is an interactive schematic diagram of a smart device RMS evaluation method provided by an embodiment of the present application. Figure 1 and Figure 2 As shown, the performance evaluation system includes multiple edge computing modules 1, multiple dynamic adaptive communication modules 2, a data fusion module 3, an advanced monitoring and management center 4 and a user interface module 5, wherein the multiple edge computing modules 1 correspond one-to-one to the multiple dynamic adaptive communication modules 2, different edge computing modules are connected to different key components 61 of the smart device 6, and the smart device 6 is placed in a preset test environment.

[0027] In a preferred embodiment, the method comprises:

[0028] For edge computing module 1, execute:

[0029] S100. Real-time collection of corresponding key components and / or local equipment data generated by data interaction with other edge computing modules.

[0030] S110, performing RMS evaluation on local equipment data to obtain local evaluation results reflecting the RMS performance of key components.

[0031] S120, sending the local evaluation results and local equipment data to the corresponding dynamic adaptive communication module.

[0032] For dynamic adaptive communication module 2, execute:

[0033] S200: extracting communication status data from local equipment data.

[0034] S210. Optimize the communication network between the edge computing module and the data fusion module through the pre-trained QoS adjustment model and communication status data.

[0035] S220, sending the local evaluation results to the data fusion module through the optimized communication network.

[0036] For data fusion module 3, execute:

[0037] S300. According to the importance of different key components to the smart device, each local evaluation result is weighted to obtain a comprehensive evaluation result reflecting the RMS performance of the smart device under a preset test environment.

[0038] For Advanced Monitoring and Management Center 4, execute:

[0039] S400: Monitor the load of each edge computing module and perform dynamic task scheduling and resource allocation based on the load.

[0040] Specifically, by monitoring the load of each edge computing module, it is possible to avoid performance degradation of some edge computing modules due to excessive load, while improving the efficiency and reliability of the overall system.

[0041] S410: Monitor the operating status of the edge computing module in real time. If an abnormality is detected in the edge computing module, initiate an abnormality recovery mechanism corresponding to the abnormal status.

[0042] Abnormalities in the edge computing module include node offline and erroneous calculations. This real-time monitoring and rapid fault recovery can improve the stability and reliability of the system and prevent faults from affecting the RMS evaluation and optimization process of smart devices.

[0043] S420. Monitor the performance indicators of the edge computing module in real time, and execute corresponding performance optimization strategies according to the performance status of the key components indicated by the performance indicators.

[0044] By monitoring the performance indicators of edge computing modules, such as processing speed and resource utilization, conducting performance analysis and optimization, and determining the corresponding performance status of key components, performance bottlenecks and hotspots can be discovered in a timely manner, and then corresponding optimization strategies can be adopted to improve the computing efficiency and responsiveness of the nodes, thereby improving the real-time performance and efficiency of the evaluation system.

[0045] The user interface module 5 is connected to multiple edge computing modules and data fusion modules respectively to execute:

[0046] S500, visually displaying the local evaluation results corresponding to different key components of the smart device, the target local evaluation results, the comprehensive evaluation results of the smart device under a preset test environment, and the target comprehensive evaluation results.

[0047] Specifically, in step S100 to step S120, the smart device includes multiple key components, such as motors, sensors, and controllers. The smart device performance prediction method and performance evaluation system provided by the present application establish multiple edge computing modules, and each edge computing module is connected to a corresponding key component of the smart device. Specifically, the edge computing module accesses the key component through a preset data interaction module, and the preset data interaction module corresponds to the edge computing module one by one, and collects corresponding local equipment data from the key component. The lightweight DDS client built into the preset data interaction module and the DDS server built into the edge computing module communicate in real time. The preset data interaction module is a submodule under the edge computing module, which is responsible for collecting real-time data of key components. The edge computing module and the preset data interaction module communicate in real time and share data in real time.

[0048] The edge computing module completes the RMS performance evaluation of the key components corresponding to the edge computing module under the preset test environment by processing and analyzing the local equipment data generated by the key components.

[0049] Preferably, taking the key equipment of the intelligent device including the motor, the sensor and the controller as an example, the multiple edge computing modules include edge computing modules A, B and C, the edge computing module A is connected to the motor, the edge computing module B is connected to the sensor, and the edge computing module C is connected to the controller. Then, for the edge computing module A: the local equipment data collected is the motor operation data, and the motor operation data is analyzed and processed to complete the performance evaluation of the motor, and the local evaluation result corresponding to the motor is obtained; for the edge computing module B: the local equipment data collected is the sensor operation data, and the sensor operation data is analyzed and processed to complete the performance evaluation of the sensor, and the local evaluation result corresponding to the sensor is obtained; for the edge computing module C: the local equipment data collected is the controller operation data, and the controller operation data is analyzed and processed to complete the performance evaluation of the controller, and the local evaluation result corresponding to the controller is obtained.

[0050] In the prior art, when performing RMS performance evaluation on smart devices, it is necessary to aggregate the entire device data to a central processor or cloud computing center for unified processing, resulting in risks such as data transmission delays, untimely data processing, and central node failures. The present application utilizes multiple edge computing modules to perform RMS performance evaluation on key components of smart devices separately, thereby reducing dependence on the central processor, reducing transmission delays, and enhancing the immediacy and accuracy of data processing.

[0051] In a preferred embodiment, see Figure 3 , Figure 3 The following is an architecture diagram of an edge computing module provided by an embodiment of the present application. Figure 3As shown, the edge computing module 1 includes a quantum communication component 11, a quantum computing component 12, a classical computing component 13, an edge computing platform 14 and an edge computing management component 15, and the performance indicators output by different edge computing modules are different.

[0052] Preferably, for the first quantum communication component 11, execute:

[0053] S1001. Use quantum key distribution technology to exchange quantum keys and local equipment data from corresponding data interfaces and / or other edge computing modules.

[0054] S1002. Send the collected local equipment data to the quantum computing component and the classical computing component respectively.

[0055] Specifically, in steps S1001 to S1002, the first quantum communication component 11 internally integrates quantum communication technology, is responsible for secure communication with corresponding key components and / or other edge computing modules, and uses quantum key distribution (QKD) technology to perform secure key exchange, thereby realizing the data encryption / decryption process. The first quantum communication component 11 also uses a repeater to extend the quantum communication distance.

[0056] For the quantum computing component 12, execute:

[0057] S1003. Perform quantum computing on local equipment data, determine multiple quality assessment features and send them to the edge computing platform.

[0058] Among them, the quantum computing component 12 is used to perform quantum computing tasks that the classical computing component 13 cannot perform. The quantum computing component 12 integrates quantum bits and quantum algorithms. Quantum bits are the basic units for quantum computing, and quantum algorithms are algorithms used to solve quantum computing tasks.

[0059] For Classic Computing Component 13, execute:

[0060] S1004. Perform classical calculations on local equipment data, determine multiple quality assessment features and send them to the edge computing platform.

[0061] Specifically, the classic computing component 13 integrates computing components such as CPU and memory, and is responsible for executing classic computing tasks.

[0062] Time series analysis and statistical methods can be further integrated within the classical computing component 13 and the quantum computing component 12 to obtain multiple quality assessment features.

[0063] For edge computing platform 14, execute:

[0064] S1005. Perform RMS evaluation on multiple quality evaluation features using a pre-trained RMS performance prediction model corresponding to the key components to obtain multiple performance indicators reflecting the RMS performance of the key components.

[0065] S1006. Perform weighted processing on multiple performance indicators through importance weighting method to obtain local evaluation results corresponding to key components under a preset test environment.

[0066] S1007. Send the local evaluation results and local equipment data to the edge computing management component and the dynamic adaptive communication module.

[0067] Specifically, in the present application, the edge computing platform 14 is also used to manage the resources corresponding to the quantum computing component 12 and the classical computing component 13. The training method of the RMS performance prediction model includes but is not limited to a deep learning network, a reinforcement learning algorithm, and a swarm intelligence algorithm. After extracting multiple quality assessment features, they are input into the RMS performance prediction model to obtain multiple performance indicators, such as failure rate, maintenance time, availability, etc. Taking into account the importance differences of different performance indicators, the weight factors corresponding to each performance indicator can be determined based on a pre-set weight distribution strategy corresponding to the key components. Under this weight distribution strategy, the local evaluation results of the key components under the preset test environment are further determined. After determining the local evaluation results, the edge computing platform 14 can send the local evaluation results and local equipment data to the edge management component 15, and then use the first quantum communication component 11 to send the local evaluation results and local equipment data to the corresponding dynamic adaptive communication module 2.

[0068] In another preferred embodiment, the edge computing platform is also used for:

[0069] Integrate the local evaluation results of key components in multiple different test environments, and perform importance-weighted processing on the local evaluation results corresponding to the key components in each test environment according to the weight of the impact of different test environments on the key components. Then, obtain the target local evaluation results that reflect the overall stability of the key components when the test environment changes.

[0070] In this application, the edge computing platform will also record the local evaluation results for key components obtained under different test environments, and then further weightedly calculate the target local evaluation results of the key components through the pre-set different test environments with different impact weights on the key components. The target local evaluation results are relative to the local evaluation results and can better reflect the stability of the key components under changes in the test environment.

[0071] For the edge computing management component 15, execute:

[0072] S1008. Update the local evaluation results corresponding to the key components.

[0073] S1009: Determine whether the local assessment result reaches the warning threshold.

[0074] S1010: If it is determined that the local evaluation result reaches the warning threshold, an alarm for a key component is triggered.

[0075] In steps S1008 to S1010, by real-time monitoring of local equipment data and calculated performance indicators, local evaluation results are updated in a timely manner, and corresponding early warning mechanisms are set. Once the local evaluation results reach the early warning threshold, the system can automatically trigger alarms, maintenance or optimization measures.

[0076] The edge computing module architecture in this application has the following benefits:

[0077] (1) Secure communication: The first quantum communication component combined with quantum communication technology is used to achieve secure and high-speed communication between the edge computing module and key components and / or other edge computing modules. Quantum communication technology can prevent eavesdropping and attacks, ensuring the secure transmission of data.

[0078] (2) Improving computing power and computing efficiency: Implementing hybrid computing, that is, integrating the quantum computing component 12 and the classical computing component 13, can simultaneously execute quantum computing tasks and classical computing tasks. This integration method simultaneously utilizes the advantages of quantum computing and classical computing, improves computing efficiency, and improves the computing power of the entire edge computing module.

[0079] (3) Edge computing: Multiple edge computing modules are distributed and deployed near different key components to provide low-latency, high-bandwidth RMS evaluation computing services for smart devices, which can reduce data transmission delays and improve application performance.

[0080] In a preferred embodiment, see Figure 4 , Figure 4 FIG. 1 shows an architecture diagram of a dynamic adaptive communication module provided by an embodiment of the present application. Figure 4 As shown, the dynamic adaptive communication module includes a heterogeneous network access layer (HNAL) (not shown in the figure), a second quantum communication component 22, a data collection and processing component 23, a QoS parameter prediction component 24 and an adaptive QoS manager 25. The heterogeneous network access layer is arranged at the front end of the second quantum communication integrated component in the corresponding edge computing module.

[0081] Heterogeneous network access layer, performs:

[0082] By presetting a universal adapter, key components and / or other edge computing modules of different network types can be connected to the corresponding edge computing modules.

[0083] In this application, the preset universal adapter describes the mapping relationship between the transmission protocol and the unified protocol under different network types. The heterogeneous network access layer is responsible for managing the access and collaborative work of different types of communication networks. The heterogeneous network access layer designs an access point discovery and registration mechanism to allow fast access of different types of network devices. The universal adapter can convert communication protocols from different network devices into a unified format. Network types include but are not limited to classical networks and quantum networks.

[0084] The second quantum communication integrated component 22 executes:

[0085] S2002. Use quantum key distribution technology to exchange quantum keys, local equipment data and local evaluation results from the corresponding edge computing module, and send the local equipment data and local evaluation results to the data collection and processing component.

[0086] Specifically, the second quantum communication integrated component 22 is similar to the first quantum communication integrated component, and also implements quantum key distribution and quantum state transmission, provides a quantum encryption interface for different network types connected, ensures the security of information transmission, implements quantum encoding and decoding protocols, and communication protocols with quantum hardware interfaces.

[0087] The data collection and processing component 23 executes:

[0088] S2003. Extract communication status data from local equipment data.

[0089] S2004: Analyze the communication status data and input the communication status data into the QoS parameter prediction component.

[0090] Preferably, the communication status data includes network performance data and key component status information, wherein the network performance data includes but is not limited to at least one of the following items: bandwidth utilization, latency, and packet loss rate, and the key component status information includes but is not limited to at least one of the following items: battery life, mobility mode, and resource consumption.

[0091] The QoS parameter prediction component 24 performs:

[0092] S2005. Input the communication status data and the local evaluation results into the built-in QoS adjustment model to determine the best QoS parameter combination for the best communication performance.

[0093] S2006. Send the best QoS parameter combination to the adaptive QoS manager.

[0094] In this application, a machine learning method is used to build and train a QoS adjustment model. The QoS adjustment model determines the optimal QoS parameter combination that optimizes communication performance based on the input communication status data and local evaluation results. The QoS parameter prediction component 24 obtains the optimal QoS parameter combination through the pre-created QoS adjustment model, thereby improving the real-time, reliability and adaptability of the system.

[0095] Specifically, the QoS parameters of the present application refer to the network parameters corresponding to the communication network or data channel between the edge computing module and the data fusion module. The QoS parameters include but are not limited to at least one of the following items: data transmission priority, data transmission rate, data packet loss rate, transmission time delay, transmission reliability, bandwidth, number of retransmissions, compression ratio and data sending frequency.

[0096] The adaptive QoS manager 25 executes:

[0097] S2008. Optimize the communication network between the edge computing module and the data fusion module according to the optimal QoS parameter combination.

[0098] S2009. Send the local evaluation results to the data fusion module through the optimized communication network.

[0099] In this application, the main task of the dynamic adaptive communication module 2 is to optimize data transmission by adjusting QoS parameters and to ensure the transmission security of local evaluation results in an unstable network environment.

[0100] In the process of determining the best QoS parameter combination, the QoS adjustment model of this application follows the following rules for determining each best QoS parameter:

[0101] Data transmission priority: Adjust the data transmission priority based on the importance and timeliness of the local assessment results. Specifically, a higher priority can be set for critical data and real-time data to ensure that they are transmitted first.

[0102] Data transmission rate: Dynamically adjust the data transmission rate according to the network status and data volume. When the network load is low or the data volume is small, increase the transmission rate to speed up data transmission.

[0103] Packet loss rate: Set an appropriate packet loss rate tolerance based on network stability and data importance. When network conditions are poor, you can increase the tolerance appropriately to ensure the reliability of data transmission.

[0104] Transmission time delay: Control the transmission time delay according to the real-time requirements of the data. For data that needs to be processed immediately, a lower delay can be set to reduce the time interval for data transmission.

[0105] Transmission reliability: Adjust the transmission reliability requirements based on the importance of the data and the network conditions. When the network environment is poor or the data is of high importance, increase transmission redundancy to improve data reliability.

[0106] Bandwidth allocation: Dynamically adjust the transmission rate according to the current network bandwidth and data importance. For high-priority critical data, increase the transmission rate and allocate more bandwidth resources to ensure timely transmission. For low-priority data, appropriately reduce the transmission rate and reduce bandwidth resource allocation to avoid occupying too much bandwidth and affecting the transmission of other important data.

[0107] Error control: Adjust the packet retransmission strategy according to the stability and reliability requirements of the network environment. When the network conditions are poor, increase the number of retransmissions to improve the reliability of data transmission. When the network conditions are good, reduce the number of retransmissions to reduce transmission delays.

[0108] Data compression and segmentation: Dynamically adjust the data compression ratio and segmentation size according to the data type and transmission distance. For a large amount of duplicate data or data with a high possibility of lossless compression, increase the compression ratio to reduce the amount of data transmission. For data with a long transmission distance, appropriately segment the data to reduce transmission delay.

[0109] Data flow control: Dynamically adjust the data transmission frequency and buffer size according to network congestion and data transmission rate. When the network congestion is serious, reduce the data transmission frequency to reduce data loss and transmission delay. When the network congestion is light, increase the data transmission frequency to improve data transmission efficiency.

[0110] In step S300, the task of the data fusion module 3 is to collect the processing results of each edge node processing module, and comprehensively calculate the comprehensive evaluation results of the smart device under the preset test environment according to the different weights and local evaluation results of the key components. For example, different key components can be assigned different weights in advance according to their importance to the overall performance of the smart device through weighted summation, and then the local evaluation results of each key component are multiplied by the corresponding weight for weighted summation to obtain a comprehensive evaluation index reflecting the performance of the entire smart device.

[0111] Comprehensive evaluation indicators can help users fully understand the overall RMS performance of smart devices and provide a reference for the optimization and decision-making of smart devices.

[0112] In a preferred embodiment, the data fusion module is further used for:

[0113] Integrate the comprehensive evaluation results of smart devices in multiple different test environments, and perform importance-weighted processing on the comprehensive evaluation results in each test environment according to the weight of the smart device and the weights corresponding to different test environments, so as to obtain the target comprehensive evaluation results reflecting the smart device.

[0114] In other words, the data fusion module can not only obtain the RMS performance of the smart device in a test environment, but also integrate the comprehensive evaluation results of the same device in different test environments, add the corresponding test environment weight and the corresponding weight of the smart device itself, and then perform importance weighting. For example, the comprehensive evaluation results corresponding to the smart device are multiplied by the corresponding test environment weight for weighted summation, and the obtained data is then multiplied by the corresponding weight of the smart device itself to obtain the target comprehensive evaluation result. The target comprehensive evaluation result reflects the overall comprehensive evaluation performance of the smart device in different environments.

[0115] In summary, the dynamic adaptive communication module of the present application is beneficial in that:

[0116] (1) Traditional communication methods such as DDS usually use fixed QoS parameters and cannot adapt to changes in different network environments. The dynamic adaptive communication module uses machine learning algorithms to intelligently adjust QoS parameters based on historical data and real-time feedback, enabling the system to make intelligent adjustments based on actual conditions and provide flexible, stable and efficient communication services.

[0117] (2) Adjust the communication strategy according to the network status. You can choose the appropriate data transmission method and compression algorithm based on indicators such as bandwidth and delay to maximize the data transmission rate and quality and improve the data transmission effect.

[0118] (3) According to the QoS adjustment model, it is possible to determine which data has a higher priority based on the data type and importance, and give priority to the transmission of key information during the transmission process, ensuring the timely and reliable delivery of key information, supporting the real-time nature and decision support of smart devices.

[0119] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the system and device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. In the several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0120] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0121] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0122] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.

[0123] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for evaluating RMS of a smart device, characterized in that: Applied to a performance evaluation system, the performance evaluation system includes multiple edge computing modules, multiple dynamic adaptive communication modules and a data fusion module, the multiple edge computing modules correspond to the multiple dynamic adaptive communication modules one by one, different edge computing modules are connected to different key components of an intelligent device, and the intelligent device is placed in a preset test environment, wherein the method includes: The edge computing module collects the corresponding key components and / or local equipment data generated by data interaction with other edge computing modules in real time, performs RMS evaluation on the local equipment data, obtains a local evaluation result reflecting the RMS performance of the key components, and sends the local evaluation result and the local equipment data to the corresponding dynamic adaptive communication module; The dynamic adaptive communication module extracts communication status data from the local equipment data, optimizes the communication network between the edge computing module and the data fusion module through the pre-trained QoS adjustment model and the communication status data, and sends the local evaluation result to the data fusion module through the optimized communication network; The data fusion module performs importance weighting processing on each local evaluation result according to the importance of different key components to the smart device, and obtains a comprehensive evaluation result reflecting the RMS performance of the smart device under a preset test environment; Each edge computing module includes quantum communication components, quantum computing components, classical computing components and edge computing platforms. The performance indicators output by different edge computing modules are different. The first quantum communication component uses quantum key distribution technology to exchange quantum keys and the local equipment data from the corresponding data interface and / or other edge computing modules, and sends the collected local equipment data to the quantum computing component and the classical computing component respectively; a quantum computing component that performs quantum computing on the local equipment data, determines a plurality of quality assessment features, and sends the features to the edge computing platform; a classical computing component, performing classical computing on the local equipment data, determining a plurality of quality assessment features and sending the features to the edge computing platform; The edge computing platform uses a pre-trained RMS performance prediction model corresponding to the key components to perform RMS evaluation on the multiple quality assessment features to obtain multiple performance indicators reflecting the RMS performance of the key components, and weights the multiple performance indicators through an importance weighting method to obtain a local evaluation result corresponding to the key components under the preset test environment, and sends the local evaluation result and the local equipment data to the edge computing management component and the dynamic adaptive communication module.

2. The method according to claim 1, characterized in that The edge computing platform is also used to: Integrate local evaluation results of the key components under multiple different test environments; According to the influence weight of different test environments on the key components, the local evaluation results corresponding to the key components under each test environment are weighted by importance to obtain the target local evaluation results reflecting the key components. The target local evaluation results reflect the overall stability of the key components when the test environment changes.

3. The method according to claim 1, characterized in that The edge computing module also includes an edge computing management component, The edge computing management component: Updating the local evaluation results corresponding to the key components; Determining whether the local assessment result reaches a warning threshold; If it is determined that the local evaluation result reaches the warning threshold, an alarm is triggered for the key component.

4. The method according to claim 1, characterized in that The dynamic adaptive communication module includes a second quantum communication component, a data collection and processing component, a QoS parameter prediction component and an adaptive QoS manager. A second quantum communication integrated component uses quantum key distribution technology to exchange quantum keys, the local equipment data and the local evaluation results from the corresponding edge computing module, and sends the local equipment data and the local evaluation results to the data collection and processing component; A data collection and processing component extracts communication status data from the local equipment data, analyzes the communication status data, and inputs the communication status data into a QoS parameter prediction component; A QoS parameter prediction component, inputting the communication state data and the local evaluation result into a built-in QoS adjustment model, determining an optimal QoS parameter combination for optimal communication performance, and sending the optimal QoS parameter combination to the adaptive QoS manager; The adaptive QoS manager optimizes the communication network between the edge computing module and the data fusion module according to the optimal QoS parameter combination, and sends the local evaluation result to the data fusion module through the optimized communication network.

5. The method according to claim 1, characterized in that The dynamic adaptive communication module also includes a heterogeneous network access layer, which is arranged at the front end of the second quantum communication integrated component in the corresponding edge computing module. The heterogeneous network access layer enables key components and / or other edge computing modules of different network types to access corresponding edge computing modules through a preset universal adapter. The preset universal adapter describes the mapping relationship between the transmission protocol and the unified protocol under different network types.

6. The method according to claim 1, characterized in that The data fusion module is also used for: Integrate comprehensive evaluation results of the smart device in multiple different test environments; According to the weight of the smart device and the weights corresponding to different test environments, the comprehensive evaluation results under each test environment are weighted by importance to obtain a target comprehensive evaluation result reflecting the smart device.

7. The method according to claim 1, characterized in that The performance evaluation system also includes an advanced monitoring and management center, The advanced monitoring and management center monitors the load of each edge computing module and performs dynamic task scheduling and resource allocation according to the load. Monitor the running status of the edge computing module in real time. If an abnormality is detected in the edge computing module, start the abnormal recovery mechanism corresponding to the abnormal status. Monitor the performance indicators of the edge computing module in real time, and execute corresponding performance optimization strategies according to the performance status of the key components indicated by the performance indicators.

8. The method according to claim 1, characterized in that: The performance evaluation system further includes a user interface module, which is connected to the plurality of edge computing modules and the data fusion module respectively, and is used to: The local evaluation results corresponding to different key components of the smart device, the target local evaluation results, the comprehensive evaluation results of the smart device under the preset test environment, and the target comprehensive evaluation results are visualized.

9. A performance evaluation system, characterized in that: The performance evaluation system includes multiple edge computing modules, edge performance integration modules, multiple dynamic adaptive communication modules and data fusion modules. The multiple edge computing modules correspond to the multiple dynamic adaptive communication modules one by one. Different edge computing modules are connected to different key components of the smart device. The smart device is placed in a preset test environment, wherein: The edge computing module collects the corresponding key components and / or local equipment data generated by data interaction with other edge computing modules in real time, performs RMS evaluation on the local equipment data, obtains a local evaluation result reflecting the RMS performance of the key components, and sends the local evaluation result and the local equipment data to the corresponding dynamic adaptive communication module; The dynamic adaptive communication module extracts communication status data from the local equipment data, optimizes the communication network between the edge computing module and the data fusion module through the pre-trained QoS adjustment model and the communication status data, and sends the local evaluation result to the data fusion module through the optimized communication network; The data fusion module performs importance weighting processing on each local evaluation result according to the importance of different key components to the smart device, and obtains a comprehensive evaluation result reflecting the RMS performance of the smart device under a preset test environment; Each edge computing module includes quantum communication components, quantum computing components, classical computing components and edge computing platforms. The performance indicators output by different edge computing modules are different. The first quantum communication component uses quantum key distribution technology to exchange quantum keys and the local equipment data from the corresponding data interface and / or other edge computing modules, and sends the collected local equipment data to the quantum computing component and the classical computing component respectively; a quantum computing component that performs quantum computing on the local equipment data, determines a plurality of quality assessment features, and sends the features to the edge computing platform; a classical computing component, performing classical computing on the local equipment data, determining a plurality of quality assessment features and sending the features to the edge computing platform; The edge computing platform uses a pre-trained RMS performance prediction model corresponding to the key components to perform RMS evaluation on the multiple quality assessment features to obtain multiple performance indicators reflecting the RMS performance of the key components, and weights the multiple performance indicators through an importance weighting method to obtain a local evaluation result corresponding to the key components under the preset test environment, and sends the local evaluation result and the local equipment data to the edge computing management component and the dynamic adaptive communication module.