Data processing method and device based on edge calculation, equipment and storage medium

Abstract

The invention discloses a data processing method and device based on edge computing, equipment and a storage medium, and belongs to the technical field of big data. According to the method, firstly, features are extracted from initial data collected by a sensor through feature extraction, and the data type is identified through data classification; then, according to the data type, distributing the data to a corresponding edge server for preprocessing, and generating an edge processing result; then, in an exception handling decision library of the edge server, a target decision conforming to the processing result is searched, and the decision is executed to generate a final data processing result. And finally, uploading an edge processing result and a final data processing result to a cloud server for storage. The invention further relates to the technical field of block chains, and the initial data is stored on a block chain network. The data transmission pressure can be reduced, the data processing efficiency can be improved, and the response speed and the intelligent level of the system can be enhanced.

Description

Technical Field

[0001] The present application belongs to the field of big data technology, and specifically relates to a data processing method, device, equipment and storage medium based on edge computing. Background Art

[0002] In recent years, with the rise and popularization of technologies such as the Internet of Things and cloud computing, many traditional industries (such as agriculture, animal husbandry, aquaculture, etc.) have gradually begun to build intelligent management systems based on these two technologies. For example, in the agricultural field, many major agricultural provinces and bases have put into use automated breeding monitoring systems based on the Internet of Things and cloud computing, which collect and process environmental information such as light, temperature, humidity, pH value, etc. collected by various sensors in fruit tree greenhouses, collect dynamic video information of greenhouses through high-definition cameras, and then the cloud processing decision server makes comprehensive judgments based on the specific parameters of each information to make early warnings and automatic control decisions.

[0003] However, since various sensors, cameras and other data collection devices on this platform are often far away from the cloud processing and decision-making service center, they need to be transmitted remotely through the Internet. In addition, the amount of data collected, such as video information, is huge, which consumes a lot of network bandwidth and may cause large network delays or even service interruptions. It is impossible to make real-time and effective warnings, controls and decisions for some emergency incidents. Summary of the invention

[0004] The purpose of the embodiments of the present application is to propose a data processing method, device, computer equipment and storage medium based on edge computing to solve the technical problems that the existing intelligent management system consumes a large amount of network bandwidth during remote transmission, which may cause large network delays or even service interruptions, and cannot make real-time and effective warnings, controls and decisions for some emergency incidents.

[0005] In order to solve the above technical problems, the embodiment of the present application provides a data processing method based on edge computing, which adopts the following technical solution:

[0006] A data processing method based on edge computing, the data processing method is applied to an intelligent management system, the intelligent management system includes a sensor, an edge server and a cloud server, and the data processing method includes:

[0007] Acquire initial data collected by the sensor, and extract features of the initial data to obtain initial data features, wherein the initial data is multimodal data;

[0008] Determine the data type of the initial data according to the initial data feature, wherein the data type includes text type, voice type, image type and video type;

[0009] According to the data type of the initial data, the initial data is sent to the adapted edge server for data preprocessing to generate edge processing results;

[0010] In the data exception processing decision library of the edge server, identifying the target processing decision that matches the edge processing result;

[0011] Execute target processing decisions and generate data processing results;

[0012] The edge processing results and data processing results are sent to the cloud server for data storage.

[0013] Furthermore, the steps of obtaining the initial data collected by the sensor and extracting the features of the initial data to obtain the features of the initial data specifically include:

[0014] Obtain the initial data collected by the sensor and generate an initial data file;

[0015] Identify the file name of the initial data file and obtain the file extension of the initial data file;

[0016] or identifying the content of the initial data file to determine the file header type of the initial data file;

[0017] The file extension of the initial data file or the file header type of the initial data file is used as the initial data feature.

[0018] Furthermore, before the step of sending the initial data to an adapted edge server for data preprocessing and generating an edge processing result according to the data type of the initial data, the method further includes:

[0019] Obtain a pre-set detection data packet and send the detection data packet from the sensor to the edge server;

[0020] Record the timestamps when the probe data packet is sent and received, and calculate the timestamp difference;

[0021] Calculate the network bandwidth based on the timestamp difference and the size of the detection data packet;

[0022] The initial data is divided into blocks according to the network bandwidth to obtain a number of initial data blocks.

[0023] Furthermore, after the step of calculating the network bandwidth according to the timestamp difference and the size of the detection data packet, the method further includes:

[0024] Determine the type of edge server, wherein the type of edge server includes text server, voice server, image server and video server;

[0025] Within a preset first time period, regularly sampling the network bandwidth to obtain a network bandwidth sampling value;

[0026] According to the type of edge server, the network bandwidth sampling values ​​are weighted averaged to obtain the average network bandwidth.

[0027] Furthermore, the step of dividing the initial data into blocks according to the network bandwidth to obtain a plurality of initial data blocks specifically includes:

[0028] Based on the network bandwidth sampling value and the average network bandwidth, a preset linear regression model is used to predict the bandwidth change trend within a preset second time period;

[0029] The initial data is divided into blocks based on the bandwidth variation trend to obtain a number of initial data blocks.

[0030] Furthermore, the intelligent management system includes a plurality of sensors, each of which corresponds to an edge server. In the data anomaly processing decision library of the edge server, the steps of identifying the target processing decision matching the edge processing result specifically include:

[0031] In each edge server, the edge processing result is compared with the preset processing result in the exception processing decision library;

[0032] According to the comparison of processing results, the initial processing decision of each sensor adaptation is determined;

[0033] The initial processing decisions adapted by each sensor are integrated to obtain the target processing decision.

[0034] Furthermore, after the step of identifying the target processing decision matching the edge processing result in the data exception processing decision library of the edge server, the method further includes:

[0035] When no adapted initial processing decision is identified in the exception processing decision library, the initial data is divided into blocks to obtain a number of initial data blocks;

[0036] Send the initial data block to the cloud server;

[0037] Obtain the user feedback processing decision sent from the cloud server, and use the user feedback processing decision as the target processing decision.

[0038] In order to solve the above technical problems, the embodiment of the present application also provides a data processing device based on edge computing, which adopts the following technical solution:

[0039] A data processing device based on edge computing, the data processing device is used to run an intelligent management system, the intelligent management system includes a sensor, an edge server and a cloud server, and the data processing device includes:

[0040] A feature extraction module is used to obtain the initial data collected by the sensor and extract the features of the initial data to obtain the initial data features, wherein the initial data is multimodal data;

[0041] A data classification module, used to determine the data type of the initial data according to the initial data features, wherein the data type includes text type, voice type, image type and video type;

[0042] The edge processing module is used to send the initial data to the adapted edge server for data preprocessing according to the data type of the initial data, and generate edge processing results;

[0043] A decision recognition module, used to identify a target processing decision matching an edge processing result in a data exception processing decision library of an edge server;

[0044] The decision execution module is used to execute the target processing decision and generate data processing results;

[0045] The data storage module is used to send edge processing results and data processing results to the cloud server for data storage.

[0046] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0047] A computer device comprises a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the data processing method based on edge computing as described in any one of the above items are implemented.

[0048] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0049] A computer-readable storage medium having computer-readable instructions stored thereon, wherein the computer-readable instructions, when executed by a processor, implement the steps of the data processing method based on edge computing as described in any one of the above.

[0050] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0051] The present application discloses a data processing method, device, equipment and storage medium based on edge computing, which belongs to the field of big data technology. The present application realizes localized preprocessing and real-time decision-making of data in the intelligent management system by introducing edge computing, thereby effectively alleviating the dependence of remote transmission on network bandwidth. Specifically, the data processing device classifies multimodal data and performs adaptive preprocessing on the edge server, and then quickly makes processing decisions and executions based on the exception processing decision library. The present application reduces the amount of data transmission and dependence on the cloud through edge data processing, thereby significantly reducing network latency and bandwidth consumption, avoiding service unavailability problems caused by network congestion or interruption, and can provide real-time early warning, control and decision-making for emergencies, improving the system's emergency response capabilities and service reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0053] Figure 1 An exemplary system architecture diagram is shown in which the present application can be applied;

[0054] Figure 2 A flow chart of an embodiment of a data processing method based on edge computing according to the present application is shown;

[0055] Figure 3 A schematic structural diagram of an embodiment of a data processing device based on edge computing according to the present application is shown;

[0056] Figure 4 A schematic structural diagram of an embodiment of a computer device according to the present application is shown. DETAILED DESCRIPTION

[0057] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0058] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0059] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0060] like Figure 1 As shown, the system architecture 100 may include a terminal device 101, a network 102 and a server 103. The terminal device 101 may be a laptop 1011, a tablet computer 1012 or a mobile phone 1013. The network 102 is used to provide a medium for a communication link between the terminal device 101 and the server 103. The network 102 may include various connection types, such as wired, wireless communication links or optical fiber cables.

[0061] The user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0062] The terminal device 101 can be any electronic device with a display screen and supporting web browsing. In addition to a laptop computer 1011, a tablet computer 1012 or a mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV), a laptop computer, a desktop computer, etc.

[0063] The server 103 may be a server that provides various services, such as a background server that provides support for a web page displayed on the terminal device 101 .

[0064] It should be noted that the data processing method based on edge computing provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the data processing device based on edge computing is generally arranged in the server / terminal device.

[0065] It should be understood that Figure 1 The numbers of terminal devices, networks and servers in the embodiment are merely illustrative. The above system may have any number of terminal devices, networks and servers according to implementation requirements.

[0066] Continue to refer Figure 2 , shows a flow chart of an embodiment of a method for data processing based on edge computing according to the present application. The data processing method based on edge computing is applied to an intelligent management system, the intelligent management system includes sensors, edge servers and cloud servers, and the data processing method includes:

[0067] S201, acquiring initial data collected by a sensor, and extracting features of the initial data to obtain initial data features, wherein the initial data is multimodal data.

[0068] Specifically, sensors in the intelligent management system collect multiple forms of initial data, such as multimodal data such as text, voice, image and video. These data may come from different sensor devices, reflecting the diverse information during the operation of the system. Through the feature extraction module, the system analyzes the initial data and extracts its features for classification and processing. The feature extraction process usually includes a variety of preprocessing operations, such as data cleaning, noise filtering, data standardization and feature vectorization. Data feature extraction helps to reveal the key information of the data for accurate classification, and the data form after feature extraction is easy to classify and transmit, which can improve the system's adaptability and real-time response capabilities to complex scenarios.

[0069] S202, determining a data type of the initial data according to the initial data characteristics, wherein the data type includes a text type, a voice type, an image type, and a video type.

[0070] Specifically, after completing the data feature extraction, the system will determine the specific type of the initial data based on these feature information. The data classification module determines which type of data the data belongs to by analyzing the data features, such as text, voice, image or video. This step ensures that the system can select appropriate processing methods according to different data types, and allocate appropriate edge servers for data preprocessing to improve processing efficiency. The classification process usually relies on machine learning or pattern recognition algorithms to assign multimodal data to corresponding categories by identifying features. After classification, the system can select the corresponding edge server for subsequent preprocessing operations based on the data type to ensure that the data is optimized for transmission path and processing method, further improving the utilization efficiency of system resources.

[0071] S203: Send the initial data to an adapted edge server for data preprocessing according to the data type of the initial data, and generate an edge processing result.

[0072] Specifically, based on the data classification results, the system sends the initial data to the most suitable data processing unit, that is, a specific type of edge server, to achieve efficient preprocessing of the data. Different edge servers have specialized data processing functions and algorithms. For example, text processing servers can perform natural language processing, voice servers can perform voice recognition, and image servers can perform image enhancement or target detection. The core of this step is to use the "localization" characteristics of edge computing to reduce bandwidth consumption and speed up response time, and to reduce unnecessary transmission delays by processing data on edge servers. In addition, edge preprocessing can filter out redundant data, making the data uploaded to the cloud more streamlined and efficient, thereby reducing network load and improving data processing efficiency.

[0073] S204: Identify a target processing decision that matches the edge processing result in the data exception processing decision library of the edge server.

[0074] Specifically, after the edge server completes data preprocessing, the system compares the preprocessing results with the exception handling decision library inside the edge server to identify the target processing decision that best suits the current situation. The decision library contains emergency response plans for various abnormal situations and can respond quickly. By analyzing the edge processing results, the system can quickly identify potential abnormal situations and select corresponding warning, control or processing decisions. This matching process is usually based on pattern matching algorithms, rule engines or deep learning models to achieve accurate and real-time decision-making. By performing decision identification at the edge, the system can make some real-time processing before the data enters the cloud server, effectively improving the response speed to emergencies.

[0075] S205, executing target processing decision and generating data processing results.

[0076] Specifically, once the target processing decision is identified, the system will immediately execute the corresponding decision instructions on the edge server to generate the final data processing results. The decision execution module is responsible for executing actions on preset strategies, such as issuing alarms after detecting anomalies, starting specific control processes, or further analyzing data. The process of executing decisions may involve linkage operations, such as adjusting system parameters through edge devices, sending alarm information, or sharing processing results with other modules. This step ensures that the edge computing system can perform partial processing before the data flows to the cloud, greatly shortening the response time to emergencies and improving the overall efficiency and flexibility of the system.

[0077] S206, sending the edge processing results and the data processing results to the cloud server for data storage.

[0078] Specifically, the edge processing results generated in the edge processing stage and the final data processing results will be uploaded to the cloud server for long-term storage. The data storage module in this step will organize, compress and upload the processing results to ensure the integrity and security of the data. Storing data in the cloud facilitates large-scale centralized analysis of historical data for future pattern mining and decision optimization. In addition, by storing the processing results and edge processing results together, the system can achieve collaborative computing between the edge and the cloud, which not only improves the real-time processing capabilities of data, but also provides complete data support for more in-depth analysis, thereby enhancing the intelligence level and data utilization efficiency of the entire intelligent management system.

[0079] In the above embodiments, the present application realizes localized preprocessing and real-time decision-making of data in the intelligent management system by introducing edge computing, thereby effectively alleviating the dependence of remote transmission on network bandwidth. Specifically, the data processing device classifies the multimodal data and performs adaptive preprocessing on the edge server, and then quickly makes processing decisions and executions based on the exception processing decision library. The present application reduces the amount of data transmission and dependence on the cloud through edge data processing, thereby significantly reducing network latency and bandwidth consumption, avoiding service unavailability problems caused by network congestion or interruptions, and can provide real-time early warning, control and decision-making for emergencies, improving the system's emergency response capabilities and service reliability.

[0080] Furthermore, the steps of obtaining the initial data collected by the sensor and extracting the features of the initial data to obtain the features of the initial data specifically include:

[0081] Obtain the initial data collected by the sensor and generate an initial data file;

[0082] Identify the file name of the initial data file and obtain the file extension of the initial data file;

[0083] or identifying the content of the initial data file to determine the file header type of the initial data file;

[0084] The file extension of the initial data file or the file header type of the initial data file is used as the initial data feature.

[0085] In this embodiment, the system first obtains raw data from the sensor and generates initial data files, which contain multimodal data such as text, voice, image or video. To ensure that the data can be processed correctly, the system will then identify the file name of the initial data file and determine the file type by the file extension. For example, text files usually have a ".txt" extension, and image files may be ".jpg" or ".png". If it cannot be identified directly by the extension, the system will further analyze the content of the file and infer the format of the data by checking the file header type, such as determining whether it is an image or video type by looking at the first few bytes of the file. This recognition process helps the system understand the data format more accurately, which facilitates subsequent processing and classification. Finally, through the file extension or file header type, the system can extract the characteristics of the initial data.

[0086] Through the above steps, the system can quickly and accurately identify and classify different types of initial data, improve the automation and efficiency of data processing, and reduce the possibility of human intervention and errors.

[0087] Furthermore, before the step of sending the initial data to an adapted edge server for data preprocessing and generating an edge processing result according to the data type of the initial data, the method further includes:

[0088] Obtain a pre-set detection data packet and send the detection data packet from the sensor to the edge server;

[0089] Record the timestamps when the probe data packet is sent and received, and calculate the timestamp difference;

[0090] Calculate the network bandwidth based on the timestamp difference and the size of the detection data packet;

[0091] The initial data is divided into blocks according to the network bandwidth to obtain a number of initial data blocks.

[0092] In this embodiment, in order to ensure that the initial data can be efficiently transmitted to the edge server for preprocessing, the system first evaluates the current network status through a preset detection data packet. Specifically, the system first obtains the detection data packet and sends it from the sensor to the edge server, and records the timestamps of the detection data packet sending and receiving in the process. Subsequently, the system calculates the difference between the timestamps to measure the transmission delay of the data packet in the network. Combined with the size of the detection data packet, the bandwidth of the current network is calculated. This step helps the system understand the transmission speed and network load, thereby providing a basis for subsequent data transmission. After obtaining the bandwidth data, the system blocks the initial data according to the network bandwidth, splitting it into several small blocks of data that adapt to the network bandwidth, thereby avoiding transmission delays or packet loss caused by insufficient bandwidth. After the data is blocked, each data block can be transmitted to the edge server more quickly to ensure the timeliness and continuity of data processing.

[0093] Through the above steps, the system can dynamically adapt to the current network bandwidth situation and ensure that the initial data can be efficiently transmitted to the edge server, thereby improving the speed and stability of data preprocessing and reducing the impact of network delays.

[0094] Furthermore, after the step of calculating the network bandwidth according to the timestamp difference and the size of the detection data packet, the method further includes:

[0095] Determine the type of edge server, wherein the type of edge server includes text server, voice server, image server and video server;

[0096] Within a preset first time period, regularly sampling the network bandwidth to obtain a network bandwidth sampling value;

[0097] According to the type of edge server, the network bandwidth sampling values ​​are weighted averaged to obtain the average network bandwidth.

[0098] In this embodiment, after the system preliminarily measures the network bandwidth, in order to further ensure the transmission effect, it is also necessary to determine the adapted edge server type and obtain a more accurate network bandwidth evaluation through weighted calculation. First, the system identifies the edge server type required for data processing, including text, voice, image or video servers. Each server type is designed for different data types and has different processing requirements and priorities. Then, within a preset first time period, the system regularly samples the network bandwidth, records the instantaneous changes in the bandwidth, and generates a series of bandwidth sampling values. Since the bandwidth requirements of different server types are different, in order to optimize resource allocation, the system performs weighted processing on the bandwidth sampling values ​​according to the type of edge server. Through weighted averaging, the system can more reasonably estimate the suitable transmission speed of each data type under the current network environment. For example, video servers have higher bandwidth requirements, and can be given greater weights to obtain more accurate average network bandwidth values, thereby ensuring the continuity and quality of video data. Finally, the average network bandwidth calculated by weighted calculation can guide the data transmission strategy, making the system more efficient and stable in the process of diversified data transmission.

[0099] Through the above steps, the system can dynamically adapt to the network bandwidth environment according to the data type, ensuring that different types of data can be transmitted in the best way, thereby improving data processing efficiency and system stability.

[0100] Furthermore, the step of dividing the initial data into blocks according to the network bandwidth to obtain a plurality of initial data blocks specifically includes:

[0101] Based on the network bandwidth sampling value and the average network bandwidth, a preset linear regression model is used to predict the bandwidth change trend within a preset second time period;

[0102] The initial data is divided into blocks based on the bandwidth variation trend to obtain a number of initial data blocks.

[0103] In this embodiment, the system can perform more intelligent block processing on the initial data according to the current network bandwidth status to adapt to the subsequent bandwidth changes. Specifically, the system first predicts the bandwidth change trend in the next second time period based on the real-time network bandwidth sampling value and the previously calculated average network bandwidth using a preset linear regression model. The linear regression model can predict the growth or decline trend of bandwidth in the future by analyzing the change characteristics of the bandwidth sampling value. This prediction result helps the system dynamically adjust the data block strategy to ensure that the data block is small and can be transmitted smoothly when the bandwidth is reduced, and the data block can be enlarged when the bandwidth is large to improve the transmission efficiency. The size of the data block after block will be dynamically adjusted with the bandwidth trend, so as to maintain the continuity and stability of data transmission when the network environment changes. Especially for data types with high bandwidth requirements, such as video or image files, the system can optimize the block size by predicting bandwidth fluctuations to ensure efficient transmission of large-capacity data.

[0104] Through the above steps, the system can intelligently adjust the data segmentation strategy, effectively adapt to the bandwidth change trend, ensure the stability and efficiency of data transmission, and reduce the impact of network jitter on transmission quality.

[0105] Furthermore, the intelligent management system includes a plurality of sensors, each of which corresponds to an edge server. In the data anomaly processing decision library of the edge server, the steps of identifying the target processing decision matching the edge processing result specifically include:

[0106] In each edge server, the edge processing result is compared with the preset processing result in the exception processing decision library;

[0107] According to the comparison of processing results, the initial processing decision of each sensor adaptation is determined;

[0108] The initial processing decisions adapted by each sensor are integrated to obtain the target processing decision.

[0109] In this embodiment, the system gradually identifies the abnormal situation of sensor data on each edge server and matches the corresponding processing decision. Specifically, each edge server compares the edge processing results it receives with the abnormal processing decision library it stores, which contains preset processing results for different abnormal situations and is used to quickly respond to various abnormal events. For example, the edge server of the temperature sensor may contain preset processing decisions for too high or too low temperature, while the image sensor contains processing decisions for image blur or color abnormality. After the comparison is completed, the system assigns a preliminary adaptation processing decision to each sensor based on the matching of the processing results. This preliminary decision can quickly respond to emergencies locally and ensure real-time performance. After that, the system will integrate the initial processing decisions of each sensor to obtain a comprehensive target processing decision, further improving the overall response effect. For example, in a multi-sensor scenario, the initial decision results of the temperature sensor and the smoke sensor are fed back to the system together so that the system can generate a more accurate fire warning decision. Finally, through the target processing decision, the system can realize the linkage processing between multiple sensors.

[0110] Through the above steps, the system can combine the abnormal data characteristics of multiple sensors to achieve flexible comprehensive decision-making, improve the system's real-time response capability and the accuracy of abnormal event processing, and effectively meet the needs of intelligent management.

[0111] Furthermore, after the step of identifying the target processing decision matching the edge processing result in the data exception processing decision library of the edge server, the method further includes:

[0112] When no adapted initial processing decision is identified in the exception processing decision library, the initial data is divided into blocks to obtain a number of initial data blocks;

[0113] Send the initial data block to the cloud server;

[0114] Obtain the user feedback processing decision sent from the cloud server, and use the user feedback processing decision as the target processing decision.

[0115] In this embodiment, when the local edge server cannot find an adapted processing decision, the processing decision of the complex situation is completed with the help of the processing capacity of the cloud server. When the exception processing decision library of the edge server fails to identify the initial processing decision that matches the current data, the system blocks the original initial data and generates several initial data blocks suitable for network bandwidth and transmission efficiency. These data blocks are then transmitted to the cloud server to use the resources and algorithm library of the cloud to handle more complex or unprecedented abnormal situations. After receiving the block data, the cloud server performs further analysis and calculation, and generates a feedback processing decision based on historical data and advanced algorithms. The feedback processing decision is then sent back to the edge server and executed as the target processing decision in the current scenario. This processing method based on cloud feedback effectively improves the adaptability of the system when facing new or complex abnormal situations, allowing edge devices to achieve more accurate responses with the help of cloud computing resources, while also providing scalability for the system.

[0116] Through the above steps, the system can dynamically use cloud capabilities when edge decision-making is limited, flexibly respond to unknown abnormal situations, ensure the integrity and adaptability of data processing, and achieve efficient and intelligent management of edge-cloud collaboration.

[0117] In the above embodiments, the present application discloses a data processing method based on edge computing, which belongs to the field of big data technology. The present application realizes localized preprocessing and real-time decision-making of data in the intelligent management system by introducing edge computing, thereby effectively alleviating the dependence of remote transmission on network bandwidth. Specifically, the data processing device classifies the multimodal data and performs adaptive preprocessing on the edge server, and then quickly makes processing decisions and executions based on the exception processing decision library. The present application reduces the amount of data transmission and dependence on the cloud through the data processing method at the edge, thereby significantly reducing network latency and bandwidth consumption, avoiding service unavailability problems caused by network congestion or interruption, and can provide real-time early warning, control and decision-making for emergencies, and improve the system's emergency response capabilities and service reliability.

[0118] In this embodiment, the data processing method based on edge computing runs on the electronic device (for example Figure 1 The server shown in the figure) can receive instructions or obtain data through a wired connection or a wireless connection. It should be noted that the above wireless connection method may include but is not limited to 3G / 4G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or to be developed in the future.

[0119] It should be emphasized that in order to further ensure the privacy and security of the above-mentioned initial data information, the above-mentioned initial data information can also be stored in a node of a blockchain.

[0120] The blockchain referred to in this application is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0121] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0122] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0123] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0124] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0125] Further references Figure 3 , as a response to the above Figure 2 The present application provides an embodiment of a data processing device based on edge computing. Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0126] like Figure 3 As shown, the data processing device 300 based on edge computing described in this embodiment is used to run an intelligent management system, which includes sensors, edge servers and cloud servers. The data processing device includes:

[0127] The feature extraction module 301 is used to obtain the initial data collected by the sensor and extract the features of the initial data to obtain the initial data features, wherein the initial data is multimodal data;

[0128] A data classification module 302 is used to determine the data type of the initial data according to the initial data features, wherein the data type includes text type, voice type, image type and video type;

[0129] The edge processing module 303 is used to send the initial data to the adapted edge server for data preprocessing according to the data type of the initial data, and generate an edge processing result;

[0130] A decision identification module 304 is used to identify a target processing decision matching an edge processing result in a data exception processing decision library of an edge server;

[0131] The decision execution module 305 is used to execute the target processing decision and generate data processing results;

[0132] The data storage module 306 is used to send the edge processing results and the data processing results to the cloud server for data storage.

[0133] Furthermore, the feature extraction module 301 is specifically used for:

[0134] Acquire initial data collected by the sensor and generate an initial data file; identify the file name of the initial data file and obtain the file extension of the initial data file; or identify the content of the initial data file and determine the file header type of the initial data file; use the file extension of the initial data file or the file header type of the initial data file as an initial data feature.

[0135] Furthermore, the data processing device 300 based on edge computing further includes a data segmentation module, which is specifically used for:

[0136] Obtain a preset detection data packet and send the detection data packet from the sensor to the edge server; record the timestamps when the detection data packet is sent and received, and calculate the timestamp difference; calculate the network bandwidth based on the timestamp difference and the size of the detection data packet; divide the initial data into blocks according to the network bandwidth to obtain several initial data blocks.

[0137] Furthermore, the data segmentation module is further used to:

[0138] Determine the type of edge server, wherein the type of edge server includes text server, voice server, image server and video server; regularly sample the network bandwidth within a preset first time period to obtain a network bandwidth sampling value; and perform weighted averaging on the network bandwidth sampling values ​​according to the type of edge server to obtain an average network bandwidth.

[0139] Furthermore, the data segmentation module is further used to:

[0140] Based on the network bandwidth sampling value and the average network bandwidth, a preset linear regression model is used to predict the bandwidth change trend within a preset second time period; and the initial data is divided into data blocks based on the bandwidth change trend to obtain a plurality of initial data blocks.

[0141] Furthermore, the intelligent management system includes a plurality of sensors, each of which corresponds to an edge server, and the decision recognition module 304 is specifically used for:

[0142] In each edge server, the edge processing result is compared with the preset processing result in the exception processing decision library; based on the comparison of the processing results, the initial processing decision adapted by each sensor is determined; the initial processing decisions adapted by each sensor are integrated to obtain the target processing decision.

[0143] Furthermore, the data processing device 300 based on edge computing further includes a user feedback module, which is specifically used for:

[0144] When no adapted initial processing decision is identified in the exception processing decision library, the initial data is segmented into blocks to obtain a number of initial data blocks; the initial data blocks are sent to the cloud server; the user feedback processing decision sent from the cloud server is obtained, and the user feedback processing decision is used as the target processing decision.

[0145] In the above embodiments, the present application discloses a data processing device based on edge computing, which belongs to the field of big data technology. The present application realizes localized preprocessing and real-time decision-making of data in the intelligent management system by introducing edge computing, thereby effectively alleviating the dependence of remote transmission on network bandwidth. Specifically, the data processing device classifies multimodal data and performs adaptive preprocessing on the edge server, and then quickly makes processing decisions and executions based on the exception processing decision library. The present application reduces the amount of data transmission and dependence on the cloud through edge data processing, thereby significantly reducing network latency and bandwidth consumption, avoiding service unavailability problems caused by network congestion or interruption, and can provide real-time early warning, control and decision-making for emergencies, improving the system's emergency response capabilities and service reliability.

[0146] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0147] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected and communicated through a system bus. It should be noted that the figure only shows a computer device 4 with a memory 41, a processor 42, and a network interface 43, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0148] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0149] The memory 41 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as a hard disk or memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. equipped on the computer device 4. Of course, the memory 41 can also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions of a data processing method based on edge computing, etc. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or are to be output.

[0150] The processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip in some embodiments. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to run computer-readable instructions stored in the memory 41 or process data, such as computer-readable instructions for running the data processing method based on edge computing.

[0151] The network interface 43 may include a wireless network interface or a wired network interface. The network interface 43 is generally used to establish a communication connection between the computer device 4 and other electronic devices.

[0152] In the above embodiment, the present application discloses a computer device, which belongs to the field of big data technology. The present application realizes localized preprocessing and real-time decision-making of data in the intelligent management system by introducing edge computing, thereby effectively alleviating the dependence of remote transmission on network bandwidth. Specifically, the data processing device classifies the multimodal data and performs adaptive preprocessing on the edge server, and then quickly makes processing decisions and executions based on the exception processing decision library. The present application reduces the amount of data transmission and dependence on the cloud through the data processing method at the edge, thereby significantly reducing network latency and bandwidth consumption, avoiding service unavailability problems caused by network congestion or interruption, and can provide real-time early warning, control and decision-making for emergencies, improving the system's emergency response capabilities and service reliability.

[0153] The present application also provides another embodiment, namely, providing a computer-readable storage medium, which stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the edge computing-based data processing method as described above.

[0154] In the above embodiments, the present application discloses a computer-readable storage medium, which belongs to the field of big data technology. The present application realizes localized preprocessing and real-time decision-making of data in the intelligent management system by introducing edge computing, thereby effectively alleviating the dependence of remote transmission on network bandwidth. Specifically, the data processing device classifies the multimodal data and performs adaptive preprocessing on the edge server, and then quickly makes processing decisions and executions based on the exception processing decision library. The present application reduces the amount of data transmission and dependence on the cloud through edge data processing, thereby significantly reducing network latency and bandwidth consumption, avoiding service unavailability problems caused by network congestion or interruption, and can provide real-time early warning, control and decision-making for emergencies, improving the system's emergency response capabilities and service reliability.

[0155] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0156] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application 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. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0157] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A data processing method based on edge computing, characterized in that: The data processing method is applied to an intelligent management system, which includes a sensor, an edge server and a cloud server. The data processing method includes: Acquire initial data collected by the sensor, and extract features of the initial data to obtain initial data features, wherein the initial data is multimodal data; Determine the data type of the initial data according to the initial data feature, wherein the data type includes text type, voice type, image type and video type; According to the data type of the initial data, the initial data is sent to an adapted edge server for data preprocessing to generate an edge processing result; In the data exception processing decision library of the edge server, identifying a target processing decision that matches the edge processing result; Execute the target processing decision and generate data processing results; The edge processing result and the data processing result are sent to the cloud server for data storage.

2. The edge computing data processing method according to claim 1, characterized in that: The step of acquiring the initial data collected by the sensor and extracting the features of the initial data to obtain the features of the initial data specifically includes: Acquire the initial data collected by the sensor and generate an initial data file; Identify the file name of the initial data file and obtain the file extension of the initial data file; or identifying the content of the initial data file to determine the file header type of the initial data file; The file extension of the initial data file or the file header type of the initial data file is used as the initial data feature.

3. The edge computing data processing method according to claim 1, characterized in that: Before the step of sending the initial data to an adapted edge server for data preprocessing and generating an edge processing result according to the data type of the initial data, the step further includes: Obtaining a preset detection data packet, and sending the detection data packet from the sensor to the edge server; Recording the timestamps when the detection data packet is sent and received, and calculating the timestamp difference; Calculating the network bandwidth according to the timestamp difference and the size of the detection data packet; The initial data is divided into data blocks according to the network bandwidth to obtain a plurality of initial data blocks.

4. The edge computing data processing method according to claim 3, characterized in that: After the step of calculating the network bandwidth according to the timestamp difference and the size of the detection data packet, the method further includes: Determining the type of the edge server, wherein the type of the edge server includes a text server, a voice server, an image server, and a video server; Within a preset first time period, regularly sampling the network bandwidth to obtain a network bandwidth sampling value; According to the type of the edge server, the network bandwidth sampling values ​​are weighted averaged to obtain an average network bandwidth.

5. The edge computing data processing method according to claim 4, characterized in that: The step of dividing the initial data into blocks according to the network bandwidth to obtain a plurality of initial data blocks specifically includes: Based on the network bandwidth sampling value and the average network bandwidth, a preset linear regression model is used to predict a bandwidth change trend within a preset second time period; The initial data is divided into data blocks based on the bandwidth variation trend to obtain a plurality of initial data blocks.

6. The edge computing data processing method according to claim 1, characterized in that: The intelligent management system includes a plurality of sensors, each of which corresponds to an edge server. The step of identifying a target processing decision matching the edge processing result in a data exception processing decision library of the edge server specifically includes: In each of the edge servers, the edge processing result is compared with a preset processing result in the exception processing decision library; Determining the initial processing decision for each sensor adaptation according to the comparison of the processing results; The initial processing decisions adapted by each of the sensors are integrated to obtain the target processing decision.

7. The edge computing data processing method according to claim 6, characterized in that: After the step of identifying the target processing decision matching the edge processing result in the data exception processing decision library of the edge server, the method further includes: When no adapted initial processing decision is identified in the exception processing decision library, the initial data is divided into data blocks to obtain a plurality of initial data blocks; Sending the initial data block to the cloud server; The user feedback processing decision sent from the cloud server is obtained, and the user feedback processing decision is used as the target processing decision.

8. A data processing device based on edge computing, characterized in that: The data processing device is used to run an intelligent management system, which includes a sensor, an edge server and a cloud server. The data processing device includes: A feature extraction module, used to obtain the initial data collected by the sensor and extract features of the initial data to obtain initial data features, wherein the initial data is multimodal data; A data classification module, used to determine the data type of the initial data according to the initial data features, wherein the data type includes text type, voice type, image type and video type; An edge processing module, used for sending the initial data to an adapted edge server for data preprocessing according to the data type of the initial data, and generating an edge processing result; A decision identification module, used to identify a target processing decision matching the edge processing result in a data exception processing decision library of the edge server; A decision execution module, used to execute the target processing decision and generate data processing results; The data storage module is used to send the edge processing result and the data processing result to the cloud server for data storage.

9. A computer device, characterized in that: It includes a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the edge computing-based data processing method as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the edge computing-based data processing method according to any one of claims 1 to 7.

Images