Intelligent terminal data processing method and system based on edge computing

Abstract

The invention discloses an intelligent terminal data processing method and system based on edge computing. The method comprises the following steps: acquiring equipment monitoring data sent by monitoring equipment arranged in a photovoltaic production area; determining a processing performance parameter corresponding to the equipment monitoring data based on a prediction algorithm; determining an abnormal possibility parameter of the equipment monitoring data based on a data analysis algorithm; according to the processing performance parameters and the abnormal possibility parameters, judging whether to send the equipment monitoring data to a local intelligent terminal for edge calculation processing; and the intelligent terminal is used for processing the equipment monitoring data and then sending a processing result to the cloud terminal. Therefore, the efficiency and the real-time performance of data processing can be improved, non-critical data are prevented from occupying cloud resources, the cloud computing burden is reduced, and the intelligent scheduling capability and the data processing flexibility of the whole system are enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular, to a method and system for processing intelligent terminal data based on edge computing. Background Art

[0002] In the existing photovoltaic production monitoring technology, device monitoring data is usually directly uploaded to the cloud for unified processing and analysis to monitor and manage the operating status of the device. Although this method can centrally process a large amount of data, there are problems such as high data transmission pressure, slow response speed, and low utilization efficiency of cloud resources. Especially in the case of limited processing performance or network fluctuations, abnormal data may not be processed in time, affecting fault identification and system operation and maintenance efficiency. Some solutions attempt to introduce an edge computing architecture, but lack an intelligent judgment mechanism for data processing priorities and cannot dynamically select processing paths according to the importance or abnormal characteristics of the data itself, resulting in the edge computing ability not being fully utilized and affecting the real-time and intelligent level of the overall system. It can be seen that there are defects in the existing technology and urgent solutions are needed. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a method and system for processing intelligent terminal data based on edge computing, which can improve the efficiency and real-time performance of data processing, avoid non-critical data occupying cloud resources, reduce the cloud computing burden, and enhance the intelligent scheduling ability and data processing flexibility of the overall system.

[0004] To solve the above technical problem, in the first aspect of the present invention, an intelligent terminal data processing method based on edge computing is disclosed, and the method includes: Obtain device monitoring data sent by monitoring devices arranged in the photovoltaic production area; Based on a prediction algorithm, determine the processing performance parameters corresponding to the device monitoring data; Based on a data analysis algorithm, determine the abnormal possibility parameters of the device monitoring data; According to the processing performance parameters and the abnormal possibility parameters, determine whether to send the device monitoring data to a local intelligent terminal for edge computing processing; the intelligent terminal is used to send the processing result to a cloud terminal after processing the device monitoring data.

[0005] As an optional implementation manner, in the first aspect of the present invention, the device monitoring data includes at least one of device temperature, device humidity, device image, device sound, device vibration, device working data, and device communication data.

[0006] As an optional implementation manner, in the first aspect of the present invention, the determining the processing performance parameters corresponding to the device monitoring data based on a prediction algorithm includes: Input the device monitoring data into the trained neural network for predicting processing tasks to obtain an output set of processing tasks; the neural network for predicting processing tasks is trained by a training data set including a plurality of training monitoring data and corresponding processing task annotations; According to the set of processing tasks and the corresponding relationship between the preset processing tasks and performance parameters, determine the processing performance parameters corresponding to the device monitoring data.

[0007] As an optional implementation manner, in the first aspect of the present invention, the determining the processing performance parameters corresponding to the device monitoring data according to the set of processing tasks and the corresponding relationship between the preset processing tasks and performance parameters includes: For each predicted processing task in the set of processing tasks, determine a set of performance parameters corresponding to each predicted processing task according to the corresponding relationship between the preset processing tasks and performance parameters; the set of performance parameters includes multiple required performance parameters of multiple parameter types; Calculate the intersection of all parameter types corresponding to the sets of performance parameters corresponding to all the predicted processing tasks to obtain a set of parameter types corresponding to the device monitoring data; For each parameter type in the set of parameter types, calculate the average value of the parameter values of this parameter type in all the sets of performance parameters to obtain the performance parameter value corresponding to this parameter type; Determine the performance parameter values corresponding to all the parameter types in the set of parameter types as the processing performance parameters corresponding to the device monitoring data.

[0008] As an optional implementation manner, in the first aspect of the present invention, the parameter type is a processor clock frequency parameter, a cache capacity parameter, a core number parameter, a thread number parameter, a power consumption parameter, a memory bandwidth parameter, a hard disk storage capacity parameter, a floating-point operation frequency parameter, or an integer operation frequency parameter.

[0009] As an optional implementation manner, in the first aspect of the present invention, the determining the anomaly possibility parameter of the device monitoring data based on the data analysis algorithm includes: For each monitoring data in the device monitoring data, determine the data type and the monitored object device corresponding to this monitoring data; Determine a plurality of historical normal data corresponding to the data type and the monitored object device in the historical database; Calculate the average value of all the historical normal data to obtain a reference data value; Calculate the difference between this monitoring data and the reference data value; Calculate the weighted sum average of the differences corresponding to all the monitored data to obtain the abnormal possibility parameter of the device monitored data.

[0010] As an optional implementation manner, in the first aspect of the present invention, when calculating the weighted sum average of the differences corresponding to all the monitored data, the weighted calculation weights corresponding to each difference include a first weight and a second weight; the first weight is proportional to the data volume of the corresponding historical normal data; the second weight is proportional to the historical abnormal frequency corresponding to the monitored object device.

[0011] As an optional implementation manner, in the first aspect of the present invention, the determining whether to send the device monitored data to a local intelligent terminal for edge computing processing according to the processing performance parameter and the abnormal possibility parameter includes: Determine whether the processing performance parameter is less than a first parameter threshold to obtain a first determination result; Determine whether the abnormal possibility parameter is less than a second parameter threshold to obtain a second determination result; When both the first determination result and the second determination result are yes, send the device monitored data to a local intelligent terminal for edge computing processing.

[0012] A second aspect of the embodiments of the present invention discloses an intelligent terminal data processing system based on edge computing, and the system includes: An acquisition module, configured to acquire device monitored data sent by a monitoring device arranged in a photovoltaic production area; A prediction module, configured to determine a processing performance parameter corresponding to the device monitored data based on a prediction algorithm; An analysis module, configured to determine an abnormal possibility parameter of the device monitored data based on a data analysis algorithm; A judgment module, configured to judge whether to send the device monitored data to a local intelligent terminal for edge computing processing according to the processing performance parameter and the abnormal possibility parameter; the intelligent terminal is configured to send a processing result to a cloud terminal after processing the device monitored data.

[0013] As an optional implementation manner, in the second aspect of the present invention, the device monitored data includes at least one of device temperature, device humidity, device image, device sound, device vibration, device working data, and device communication data.

[0014] As an optional implementation manner, in the second aspect of the present invention, the specific manner in which the prediction module determines the processing performance parameter corresponding to the device monitored data based on a prediction algorithm includes: Input the device monitoring data into the trained neural network for predicting processing tasks to obtain the output set of processing tasks; the neural network for predicting processing tasks is trained by a training data set including a plurality of training monitoring data and corresponding processing task annotations; Determine the processing performance parameters corresponding to the device monitoring data according to the set of processing tasks and the corresponding relationship between the preset processing tasks and performance parameters.

[0015] As an optional implementation manner, in the second aspect of the present invention, the specific manner in which the prediction module determines the processing performance parameters corresponding to the device monitoring data according to the set of processing tasks and the corresponding relationship between the preset processing tasks and performance parameters includes: For each predicted processing task in the set of processing tasks, determine the set of performance parameters corresponding to each predicted processing task according to the corresponding relationship between the preset processing tasks and performance parameters; the set of performance parameters includes multiple required performance parameters of multiple parameter types; Calculate the intersection of all parameter types corresponding to the sets of performance parameters corresponding to all the predicted processing tasks to obtain the set of parameter types corresponding to the device monitoring data; For each parameter type in the set of parameter types, calculate the average value of the parameter values of this parameter type in all the sets of performance parameters to obtain the performance parameter value corresponding to this parameter type; Determine the performance parameter values corresponding to all the parameter types in the set of parameter types as the processing performance parameters corresponding to the device monitoring data.

[0016] As an optional implementation manner, in the second aspect of the present invention, the parameter type is a processor clock frequency parameter, a cache capacity parameter, a core number parameter, a thread number parameter, a power consumption parameter, a memory bandwidth parameter, a hard disk storage capacity parameter, a floating-point operation frequency parameter, or an integer operation frequency parameter.

[0017] As an optional implementation manner, in the second aspect of the present invention, the specific manner in which the analysis module determines the abnormal possibility parameter of the device monitoring data based on the data analysis algorithm includes: For each monitoring data in the device monitoring data, determine the data type and the monitored object device corresponding to this monitoring data; Determine a plurality of historical normal data corresponding to the data type and the monitored object device in the historical database; Calculate the average value of all the historical normal data to obtain a reference data value; Calculate the difference between this monitoring data and the reference data value; Calculate the weighted sum average of the differences corresponding to all the monitored data to obtain the abnormal possibility parameter of the device monitored data.

[0018] As an optional implementation manner, in the second aspect of the present invention, when calculating the weighted sum average of the differences corresponding to all the monitored data, the weighted calculation weights corresponding to each difference include a first weight and a second weight; the first weight is proportional to the data volume of the corresponding historical normal data; the second weight is proportional to the historical abnormal frequency of the corresponding monitored object device.

[0019] As an optional implementation manner, in the second aspect of the present invention, the specific manner in which the judgment module judges whether to send the device monitored data to a local intelligent terminal for edge computing processing according to the processing performance parameter and the abnormal possibility parameter includes: Judge whether the processing performance parameter is less than a first parameter threshold to obtain a first judgment result; Judge whether the abnormal possibility parameter is less than a second parameter threshold to obtain a second judgment result; When both the first judgment result and the second judgment result are yes, send the device monitored data to a local intelligent terminal for edge computing processing.

[0020] The third aspect of the present invention discloses another intelligent terminal data processing system based on edge computing, and the system includes: A memory storing executable program codes; A processor coupled to the memory; The processor calls the executable program codes stored in the memory and executes some or all of the steps in the intelligent terminal data processing method based on edge computing disclosed in the first aspect of the present invention.

[0021] The fourth aspect of the present invention discloses a computer storage medium, and the computer storage medium stores computer instructions, which are used to execute some or all of the steps in the intelligent terminal data processing method based on edge computing disclosed in the first aspect of the present invention when called.

[0022] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: The present invention processes the processing performance analysis and abnormal possibility evaluation of the device monitored data in the photovoltaic production area, and combines two types of parameters to judge whether to send the device monitored data to a local intelligent terminal for edge computing processing, so as to improve the efficiency and real-time performance of data processing, avoid non-critical data occupying cloud resources, reduce the cloud computing burden, and enhance the intelligent scheduling ability and data processing flexibility of the overall system. Description of the Drawings

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0024] Figure 1 It is a schematic flowchart of a method for processing intelligent terminal data based on edge computing disclosed in an embodiment of the present invention.

[0025] Figure 2 It is a schematic structural diagram of a system for processing intelligent terminal data based on edge computing disclosed in an embodiment of the present invention.

[0026] Figure 3 It is a schematic structural diagram of another system for processing intelligent terminal data based on edge computing disclosed in an embodiment of the present invention. Detailed implementation manners

[0027] In order to enable those skilled in the art to better understand the solutions of the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0028] The terms "first", "second", etc. in the specification and claims of the present invention and the above accompanying drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, device, product or equipment that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products or equipment.

[0029] Referring to "embodiment" herein means that a specific feature, structure or characteristic described in connection with the embodiment can be included in at least one embodiment of the present invention. The phrase appears in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0030] The present invention discloses a method and system for processing intelligent terminal data based on edge computing. By analyzing the processing performance and evaluating the abnormal possibility of the device monitoring data in the photovoltaic production area, and combining two types of parameters to determine whether to send the device monitoring data to the local intelligent terminal for edge computing processing, it can improve the efficiency and real-time performance of data processing, avoid non-critical data occupying cloud resources, reduce the cloud computing burden, and enhance the intelligent scheduling ability and data processing flexibility of the overall system. The following will be described in detail respectively.

[0031] Embodiment 1 Please refer to Figure 1 , Figure 1 which is a schematic flowchart of a method for processing intelligent terminal data based on edge computing disclosed in an embodiment of the present invention. Among them, Figure 1 the described method for processing intelligent terminal data based on edge computing can be applied to a data processing system / data processing device / data processing server (wherein, the server includes a local processing server or a cloud processing server). As Figure 1 shown, the method for processing intelligent terminal data based on edge computing may include the following operations: 101. Obtain the device monitoring data sent by the monitoring devices set in the photovoltaic production area.

[0032] 102. Based on the prediction algorithm, determine the processing performance parameters corresponding to the device monitoring data. 103. Based on the data analysis algorithm, determine the abnormal possibility parameters of the device monitoring data. 104. According to the processing performance parameters and the abnormal possibility parameters, determine whether to send the device monitoring data to the local intelligent terminal for edge computing processing.

[0033] Optionally, the intelligent terminal is used to send the processing result to the cloud terminal after processing the device monitoring data.

[0034] It can be seen that through the above-mentioned invention embodiments, by analyzing the processing performance and evaluating the abnormal possibility of the device monitoring data in the photovoltaic production area, and combining two types of parameters to determine whether to send the device monitoring data to the local intelligent terminal for edge computing processing, it can improve the efficiency and real-time performance of data processing, avoid non-critical data occupying cloud resources, reduce the cloud computing burden, and enhance the intelligent scheduling ability and data processing flexibility of the overall system.

[0035] As an optional embodiment, among the above steps, the device monitoring data includes at least one of device temperature, device humidity, device image, device sound, device vibration, device working data, and device communication data.

[0036] It can be seen that through the above optional embodiments, the content of the device monitoring data is defined to comprehensively characterize the operation-related characteristics of the monitored device, so as to facilitate the subsequent determination of the accurate calculation path, assist in improving the efficiency and real-time performance of data processing, avoid non-critical data occupying cloud resources, reduce the cloud computing burden, and enhance the intelligent scheduling ability and data processing flexibility of the overall system.

[0037] As an optional embodiment, in the above steps, based on the prediction algorithm, the processing performance parameters corresponding to the device monitoring data are determined, including: Input the device monitoring data into the trained processing task prediction neural network to obtain the output set of processing tasks; optionally, the processing task prediction neural network is trained through a training data set including multiple training monitoring data and corresponding processing task annotations; According to the set of processing tasks and the corresponding relationship between the preset processing tasks and performance parameters, determine the processing performance parameters corresponding to the device monitoring data.

[0038] It can be seen that through the above optional embodiments, by inputting the device monitoring data into the trained processing task prediction neural network, an output set of processing tasks required for the data is obtained, and combined with the corresponding relationship between the preset tasks and performance parameters, the processing performance parameters corresponding to the device monitoring data are determined, so that the processing complexity and resource occupancy of the data can be intelligently evaluated based on the specific processing requirements, and the accuracy of subsequent computing resource scheduling and the system operation efficiency can be improved.

[0039] As an optional embodiment, in the above steps, according to the set of processing tasks and the corresponding relationship between the preset processing tasks and performance parameters, the processing performance parameters corresponding to the device monitoring data are determined, including: For each predicted processing task in the set of processing tasks, according to the corresponding relationship between the preset processing tasks and performance parameters, determine the set of performance parameters corresponding to each predicted processing task; optionally, the set of performance parameters includes multiple required performance parameters of multiple parameter types; Calculate the intersection of all parameter types corresponding to the sets of performance parameters of all predicted processing tasks to obtain the set of parameter types corresponding to the device monitoring data; For each parameter type in the set of parameter types, calculate the average value of the parameter values of this parameter type in all sets of performance parameters to obtain the performance parameter value corresponding to this parameter type; Determine the performance parameter values corresponding to all parameter types in the set of parameter types as the processing performance parameters corresponding to the device monitoring data.

[0040] It can be seen that through the above optional embodiments, by performing parameter type merging and aggregation processing on multiple performance parameter sets corresponding to the prediction processing tasks, first extracting the common parameter types in the performance parameter sets corresponding to all prediction processing tasks, and then calculating the average value of the parameter values of each parameter type respectively, the processing performance parameters that comprehensively and accurately reflect the processing requirements of device monitoring data are finally determined, so as to realize the refined modeling of data processing complexity and the quantitative evaluation of resource consumption, and improve the rationality and stability of edge computing resource scheduling and task distribution.

[0041] As an optional embodiment, in the above steps, the parameter types are processor clock frequency parameter, cache capacity parameter, core number parameter, thread number parameter, power consumption parameter, memory bandwidth parameter, hard disk storage capacity parameter, floating-point operation frequency parameter or integer operation frequency parameter.

[0042] It can be seen that through the above optional embodiments, the types of processing performance parameters are defined to determine the processing performance parameters that comprehensively and accurately reflect the processing requirements of device monitoring data, assist in improving the efficiency and real-time performance of data processing, avoid non-critical data occupying cloud resources, reduce the cloud computing burden, and enhance the intelligent scheduling ability and data processing flexibility of the overall system.

[0043] As an optional embodiment, in the above steps, based on the data analysis algorithm, the abnormal possibility parameter of the device monitoring data is determined, including: For each piece of monitoring data in the device monitoring data, determine the data type and the monitored object device corresponding to the monitoring data; Determine multiple historical normal data corresponding to the data type and the monitored object device in the historical database; Calculate the average value of all historical normal data to obtain the reference data value; Calculate the difference between the monitoring data and the reference data value; Calculate the weighted sum average of the differences corresponding to all monitoring data to obtain the abnormal possibility parameter of the device monitoring data.

[0044] It can be seen that through the above optional embodiments, by accurately screening historical normal data based on the data type and the monitored object device, and using the difference weighted sum average method to quantitatively evaluate the overall deviation degree of the current monitoring data, the abnormal possibility parameter reflecting the abnormal degree of the current device state can be effectively generated, assist in improving the efficiency and real-time performance of data processing, avoid non-critical data occupying cloud resources, reduce the cloud computing burden, and enhance the intelligent scheduling ability and data processing flexibility of the overall system.

[0045] As an optional embodiment, in the above steps, when calculating the weighted sum average of the differences corresponding to all the monitoring data, the weighted calculation weights corresponding to each difference include a first weight and a second weight; the first weight is proportional to the data volume of the corresponding historical normal data; the second weight is proportional to the historical abnormal frequency of the corresponding monitored object device.

[0046] It can be seen that through the above optional embodiment, by introducing a first weight proportional to the historical normal data volume and a second weight proportional to the historical abnormal frequency of the monitored object device in the weighted sum average calculation of the differences, it is possible to fully consider the credibility of historical data and the device abnormal risk level when evaluating the abnormal possibility of the current monitoring data, thereby improving the accuracy and discrimination of the abnormal possibility parameter, assisting in improving the efficiency and real-time performance of data processing, avoiding non-critical data from occupying cloud resources, reducing the cloud computing burden, and enhancing the intelligent scheduling ability and data processing flexibility of the overall system.

[0047] As an optional embodiment, in the above steps, according to the processing performance parameter and the abnormal possibility parameter, determining whether to send the device monitoring data to the local intelligent terminal for edge computing processing includes: Determining whether the processing performance parameter is less than the first parameter threshold to obtain a first determination result; Determining whether the abnormal possibility parameter is less than the second parameter threshold to obtain a second determination result; When both the first determination result and the second determination result are yes, sending the device monitoring data to the local intelligent terminal for edge computing processing.

[0048] It can be seen that through the above optional embodiment, by respectively determining whether the processing performance parameter and the abnormal possibility parameter corresponding to the device monitoring data are lower than their respective preset thresholds, and triggering the edge computing processing operation when both conditions are met, it is possible to hand over the data to the local intelligent terminal for processing only when the device is in good operating condition and there is no abnormal risk, thereby improving the security and reliability of edge computing, and at the same time avoiding waste of computing resources or processing deviation in high-risk or complex computing scenarios, and finally realizing the precision of edge computing task scheduling and ensuring the stability of the operation of the photovoltaic monitoring system.

[0049] Embodiment 2 Please refer to Figure 2 , Figure 2 which is a schematic structural diagram of an edge-computing-based intelligent terminal data processing system disclosed in an embodiment of the present invention. Among them, Figure 2 The described edge-computing-based intelligent terminal data processing system can be applied to a data processing system / data processing device / data processing server (wherein, the server includes a local processing server or a cloud processing server). As Figure 2As shown in the figure, the intelligent terminal data processing system based on edge computing may include: An acquisition module 201, configured to acquire device monitoring data sent by monitoring devices arranged in a photovoltaic production area.

[0050] A prediction module 202, configured to determine processing performance parameters corresponding to the device monitoring data based on a prediction algorithm. An analysis module 203, configured to determine an abnormal possibility parameter of the device monitoring data based on a data analysis algorithm. A judgment module 204, configured to judge whether to send the device monitoring data to a local intelligent terminal for edge computing processing according to the processing performance parameters and the abnormal possibility parameters.

[0051] Optionally, the intelligent terminal is configured to send a processing result to a cloud terminal after processing the device monitoring data.

[0052] It can be seen that through the above-mentioned invention embodiments, by performing processing performance analysis and abnormal possibility evaluation on the device monitoring data in the photovoltaic production area, and combining the two types of parameters to judge whether to send the device monitoring data to a local intelligent terminal for edge computing processing, the efficiency and real-time performance of data processing can be improved, non-critical data occupying cloud resources can be avoided, the cloud computing burden can be reduced, and the intelligent scheduling ability and data processing flexibility of the overall system can be enhanced.

[0053] As an optional embodiment, the device monitoring data includes at least one of device temperature, device humidity, device image, device sound, device vibration, device working data, and device communication data.

[0054] It can be seen that through the above-mentioned optional embodiment, the content of the device monitoring data is defined to comprehensively represent the operation-related characteristics of the monitored object device, so as to facilitate the subsequent determination of an accurate calculation path, assist in improving the efficiency and real-time performance of data processing, avoid non-critical data occupying cloud resources, reduce the cloud computing burden, and enhance the intelligent scheduling ability and data processing flexibility of the overall system.

[0055] As an optional embodiment, the specific manner in which the prediction module determines the processing performance parameters corresponding to the device monitoring data based on a prediction algorithm includes: Inputting the device monitoring data into a trained processing task prediction neural network to obtain an output processing task set; optionally, the processing task prediction neural network is trained through a training data set including a plurality of training monitoring data and corresponding processing task annotations; Determining the processing performance parameters corresponding to the device monitoring data according to the processing task set and a preset correspondence between processing tasks and performance parameters.

[0056] It can be seen that through the above optional embodiments, by inputting device monitoring data into a trained processing task prediction neural network, outputting a set of processing tasks required for the data, and combining the corresponding relationship between the preset tasks and performance parameters, the processing performance parameters corresponding to the device monitoring data are determined. Therefore, it is possible to intelligently evaluate the processing complexity and resource occupancy based on the specific processing requirements of the data, improving the accuracy of subsequent computing resource scheduling and the system operation efficiency.

[0057] As an optional embodiment, the specific manner in which the prediction module determines the processing performance parameters corresponding to the device monitoring data according to the set of processing tasks and the corresponding relationship between the preset processing tasks and performance parameters includes: For each predicted processing task in the set of processing tasks, according to the corresponding relationship between the preset processing tasks and performance parameters, determine the set of performance parameters corresponding to each predicted processing task; optionally, the set of performance parameters includes multiple required performance parameters of multiple parameter types; Calculate the intersection of all parameter types corresponding to the sets of performance parameters corresponding to all predicted processing tasks to obtain the set of parameter types corresponding to the device monitoring data; For each parameter type in the set of parameter types, calculate the average value of the parameter values of this parameter type in all sets of performance parameters to obtain the performance parameter value corresponding to this parameter type; Determine the performance parameter values corresponding to all parameter types in the set of parameter types as the processing performance parameters corresponding to the device monitoring data.

[0058] It can be seen that through the above optional embodiments, through parameter type merging and aggregation processing of multiple sets of performance parameters corresponding to the predicted processing tasks, first extract the common parameter types in the sets of performance parameters corresponding to all predicted processing tasks, and then calculate the average value of the parameter values of each parameter type respectively, and finally determine the processing performance parameters that comprehensively and accurately reflect the processing requirements of the device monitoring data. Therefore, it is possible to achieve refined modeling of the data processing complexity and quantitative evaluation of the resource consumption, improving the rationality and stability of the edge computing resource scheduling and task distribution.

[0059] As an optional embodiment, the parameter type is a processor clock frequency parameter, a cache capacity parameter, a core number parameter, a thread number parameter, a power consumption parameter, a memory bandwidth parameter, a hard disk storage capacity parameter, a floating-point operation frequency parameter, or an integer operation frequency parameter.

[0060] It can be seen that through the above optional embodiments, the types of processing performance parameters are defined to determine the processing performance parameters that comprehensively and accurately reflect the processing requirements of device monitoring data, assisting in improving the efficiency and real-time performance of data processing, avoiding non-critical data from occupying cloud resources, reducing the cloud computing burden, and enhancing the intelligent scheduling ability and data processing flexibility of the overall system.

[0061] As an optional embodiment, the specific manner in which the analysis module determines the abnormality possibility parameter of the device monitoring data based on the data analysis algorithm includes: For each piece of monitoring data in the device monitoring data, determine the data type and the monitored object device corresponding to the monitoring data; Determine multiple historical normal data corresponding to the data type and the monitored object device in the historical database; Calculate the average value of all historical normal data to obtain a reference data value; Calculate the difference between the monitoring data and the reference data value; Calculate the weighted sum average of the differences corresponding to all monitoring data to obtain the abnormality possibility parameter of the device monitoring data.

[0062] It can be seen that through the above optional embodiments, by accurately screening historical normal data based on the data type and the monitored object device, and using the difference weighted sum average method to quantitatively evaluate the overall deviation degree of the current monitoring data, it is possible to effectively generate an abnormality possibility parameter reflecting the current device state abnormality degree, assisting in improving the efficiency and real-time performance of data processing, avoiding non-critical data from occupying cloud resources, reducing the cloud computing burden, and enhancing the intelligent scheduling ability and data processing flexibility of the overall system.

[0063] As an optional embodiment, when calculating the weighted sum average of the differences corresponding to all monitoring data, the weighted calculation weights corresponding to each difference include a first weight and a second weight; the first weight is proportional to the data volume of the corresponding historical normal data; the second weight is proportional to the historical abnormality frequency of the corresponding monitored object device.

[0064] It can be seen that through the above optional embodiments, by introducing a first weight proportional to the number of historical normal data and a second weight proportional to the historical abnormality frequency of the monitored object device in the difference weighted sum average calculation, it is possible to fully consider the credibility of historical data and the device abnormality risk level when evaluating the abnormality possibility of the current monitoring data, thereby improving the accuracy and discrimination of the abnormality possibility parameter, assisting in improving the efficiency and real-time performance of data processing, avoiding non-critical data from occupying cloud resources, reducing the cloud computing burden, and enhancing the intelligent scheduling ability and data processing flexibility of the overall system.

[0065] As an optional embodiment, the specific manner in which the determination module determines whether to send device monitoring data to a local intelligent terminal for edge computing processing based on processing performance parameters and exception possibility parameters includes: Determine whether the processing performance parameter is less than the first parameter threshold to obtain a first determination result; Determine whether the exception possibility parameter is less than the second parameter threshold to obtain a second determination result; When both the first determination result and the second determination result are yes, send the device monitoring data to a local intelligent terminal for edge computing processing.

[0066] It can be seen that through the above optional embodiment, by respectively determining whether the processing performance parameter and the exception possibility parameter corresponding to the device monitoring data are lower than their respective preset thresholds, and triggering the edge computing processing operation when both conditions are met, the data is only handed over to the local intelligent terminal for processing when the device is in good operating condition and there is no abnormal risk, thereby improving the security and reliability of edge computing, and at the same time avoiding waste of computing resources or processing deviation in high-risk or complex computing scenarios, and finally realizing the precision of edge computing task scheduling and the stability guarantee of the operation of the photovoltaic monitoring system.

[0067] Embodiment III Please refer to Figure 3 , Figure 3 which is another intelligent terminal data processing system based on edge computing disclosed in the embodiments of the present invention. Figure 3 The described intelligent terminal data processing system based on edge computing is applied to a data processing system / data processing device / data processing server (wherein, the server includes a local processing server or a cloud processing server). As Figure 3 shown, the intelligent terminal data processing system based on edge computing may include: A memory 301 storing executable program code; A processor 302 coupled to the memory 301; Wherein, the processor 302 calls the executable program code stored in the memory 301 to execute the steps of the intelligent terminal data processing method based on edge computing described in Embodiment I.

[0068] Embodiment IV The embodiments of the present invention disclose a computer-readable storage medium, which stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the intelligent terminal data processing method based on edge computing described in Embodiment I.

[0069] Embodiment V An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute the steps of the intelligent terminal data processing method based on edge computing described in the first embodiment.

[0070] The above describes specific embodiments of this specification, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the figures do not necessarily have to be in the specific order or sequential order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0071] The systems, devices, modules, or units illustrated in the above embodiments may be specifically implemented by a computer chip or entity, or by a product with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or any combination of these devices.

[0072] For convenience of description, when describing the above device, it is divided into various units according to functions and described separately. Of course, when implementing this specification, the functions of each unit may be implemented in the same or multiple software and / or hardware.

[0073] Those skilled in the art should understand that the embodiments of this specification may be provided as a method, a system, or a computer program product. Therefore, the embodiments of this specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the embodiments of this specification may take 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.

[0074] This specification is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate for implementation in the processFigure 1 means for the functions specified in one or more processes and / or boxes Figure 1 or boxes.

[0075] 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, so that the instructions stored in the computer-readable memory produce a manufactured article including an instruction means that implements the functions specified in one process Figure 1 or more processes and / or boxes Figure 1 or boxes.

[0076] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide means for implementing the functions specified in one process Figure 1 or more processes and / or boxes Figure 1 or boxes.

[0077] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and a memory.

[0078] The memory may include non-permanent memory in the computer-readable medium, in the form of 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 a computer-readable medium.

[0079] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology for information storage. 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 disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media, such as modulated data signals and carrier waves.

[0080] 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, commodity 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, commodity 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, commodity or device comprising said element.

[0081] This specification can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification can also be practiced in a distributed computing environment where tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0082] Each embodiment in this specification is described in a progressive manner. For parts that are the same or similar among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for system embodiments, since they are basically similar to method embodiments, the description is relatively simple. For related parts, reference can be made to the description of the method embodiments.

[0083] Finally, it should be noted that: What is disclosed in the method and system for processing intelligent terminal data based on edge computing disclosed in the embodiments of the present invention is only the preferred embodiments of the present invention, and is only used to illustrate the technical solutions of the present invention, rather than to limit it; Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; And these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent terminal data processing method based on edge computing, characterized in that, The method includes: Obtaining device monitoring data sent by monitoring devices set in the photovoltaic production area; Determining the processing performance parameters corresponding to the device monitoring data based on a prediction algorithm; Determining the anomaly possibility parameters of the device monitoring data based on a data analysis algorithm; Judging whether to send the device monitoring data to a local intelligent terminal for edge computing processing according to the processing performance parameters and the anomaly possibility parameters; the intelligent terminal is used to send the processing result to a cloud terminal after processing the device monitoring data.

2. The method for processing intelligent terminal data based on edge computing according to claim 1, wherein The device monitoring data includes at least one of device temperature, device humidity, device image, device sound, device vibration, device working data, and device communication data.

3. The method for processing intelligent terminal data based on edge computing according to claim 1, wherein The determining the processing performance parameters corresponding to the device monitoring data based on a prediction algorithm includes: Inputting the device monitoring data into a trained processing task prediction neural network to obtain an output set of processing tasks; the processing task prediction neural network is trained by a training data set including a plurality of training monitoring data and corresponding processing task annotations; Determining the processing performance parameters corresponding to the device monitoring data according to the set of processing tasks and the corresponding relationship between the preset processing tasks and performance parameters.

4. The method for processing intelligent terminal data based on edge computing according to claim 3, characterized in that The determining the processing performance parameters corresponding to the device monitoring data according to the set of processing tasks and the corresponding relationship between the preset processing tasks and performance parameters includes: For each predicted processing task in the set of processing tasks, determining a set of performance parameters corresponding to each predicted processing task according to the corresponding relationship between the preset processing tasks and performance parameters; the set of performance parameters includes multiple required performance parameters of multiple parameter types; Calculating the intersection of all parameter types corresponding to the sets of performance parameters corresponding to all the predicted processing tasks to obtain a set of parameter types corresponding to the device monitoring data; For each parameter type in the set of parameter types, calculating the average value of the parameter values of this parameter type in all the sets of performance parameters to obtain the performance parameter value corresponding to this parameter type; Determining the performance parameter values corresponding to all the parameter types in the set of parameter types as the processing performance parameters corresponding to the device monitoring data.

5. The method for processing intelligent terminal data based on edge computing according to claim 4, wherein The parameter type is a processor clock frequency parameter, cache capacity parameter, core number parameter, thread number parameter, power consumption parameter, memory bandwidth parameter, hard disk storage capacity parameter, floating-point operation frequency parameter, or integer operation frequency parameter.

6. The method for processing intelligent terminal data based on edge computing according to claim 1, characterized in that, The determining the anomaly possibility parameters of the device monitoring data based on a data analysis algorithm includes: For each piece of monitoring data in the device monitoring data, determining the data type and the monitored object device corresponding to this piece of monitoring data; Determining a plurality of historical normal data corresponding to the data type and the monitored object device in the historical database; Calculating the average value of all the historical normal data to obtain a reference data value; Calculating the difference between this piece of monitoring data and the reference data value; Calculating the weighted sum average of the differences corresponding to all the monitoring data to obtain the anomaly possibility parameters of the device monitoring data.

7. The method for processing intelligent terminal data based on edge computing according to claim 6, wherein When calculating the weighted sum average of the differences corresponding to all the monitored data, the weighted calculation weights corresponding to each difference include a first weight and a second weight; the first weight is proportional to the data volume of the corresponding historical normal data; the second weight is proportional to the historical abnormal frequency of the corresponding monitored object device.

8. The method for processing intelligent terminal data based on edge computing according to claim 1, wherein The determining whether to send the device monitoring data to a local intelligent terminal for edge computing processing according to the processing performance parameter and the abnormal possibility parameter includes: Determining whether the processing performance parameter is less than a first parameter threshold to obtain a first determination result; Determining whether the abnormal possibility parameter is less than a second parameter threshold to obtain a second determination result; When both the first determination result and the second determination result are yes, sending the device monitoring data to a local intelligent terminal for edge computing processing.

9. An intelligent terminal data processing system based on edge computing, characterized in that, The system includes: An acquisition module, configured to acquire device monitoring data sent by a monitoring device arranged in a photovoltaic production area; A prediction module, configured to determine a processing performance parameter corresponding to the device monitoring data based on a prediction algorithm; An analysis module, configured to determine an abnormal possibility parameter of the device monitoring data based on a data analysis algorithm; A judgment module, configured to judge whether to send the device monitoring data to a local intelligent terminal for edge computing processing according to the processing performance parameter and the abnormal possibility parameter; the intelligent terminal is configured to send a processing result to a cloud terminal after processing the device monitoring data.

10. An intelligent terminal data processing system based on edge computing, characterized in that, The system includes: A memory storing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory and executes the edge-computing-based intelligent terminal data processing method according to any one of claims 1-8.

Images