Intelligent monitoring method for electric power field operation risk and related device

Abstract

The invention provides an intelligent monitoring method for electric power field operation risks and a related device. The method comprises the steps that multiple pieces of first image data are acquired; performing identification analysis on the plurality of pieces of first image data to obtain a plurality of risk levels; generating a plurality of pieces of alarm information according to the plurality of risk levels; compressing the plurality of first image data according to the plurality of risk levels to obtain a plurality of second image data; analyzing the importance degrees of the plurality of pieces of second image data to obtain a plurality of importance degrees; distributing priorities for the second image data according to the risk level and the importance degree to obtain a plurality of priorities; sorting the second image data according to the priority to obtain a target transmission queue; transmitting, decompressing and analyzing the second image data according to the target transmission queue to obtain a target risk assessment result; and the alarm information and the target risk assessment result are fed back to the terminal equipment, so that the risk event of the power operation site can be timely responded.

Description

Technical Field

[0001] The present application relates to the field of intelligent monitoring technology, and in particular to an intelligent monitoring method and related devices for risks of power field operations. Background Art

[0002] In the field of power operations, on-site safety monitoring is crucial to preventing accidents and ensuring personnel safety. Traditional video surveillance systems are often limited by network bandwidth when transmitting large amounts of data in real time, resulting in delayed transmission of monitoring data and failure to detect and respond to potential safety risks in a timely manner. This problem is particularly prominent in remote areas or environments with poor network conditions.

[0003] At present, a ball control system can be deployed at the work site to collect and store video of the site, and then sample and recognize the image information of the video to analyze the area and transmit it to the edge computing module of the monitoring host and the network cloud monitoring platform. However, when faced with different network environments and a large amount of alarm information, problems such as inefficient data transmission and delayed alarm response may occur.

[0004] Therefore, how to improve the timeliness and accuracy of safety monitoring in response to the risks of power site operations has become an urgent problem to be solved. Summary of the invention

[0005] The embodiments of the present application provide an intelligent monitoring method and related devices for the risks of power operation sites. The method can compress the image data of the power operation site and assign priorities according to the risk level and importance, thereby ensuring that high-risk and important image data are transmitted first, thereby improving the transmission efficiency, and timely receiving and processing alarm information and risk assessment results to speed up the response speed and improve the timeliness and accuracy of safety monitoring.

[0006] In a first aspect, an embodiment of the present application provides an intelligent monitoring method for risks of power field operations, which is applied to an intelligent monitoring system, wherein the intelligent monitoring system is connected to a cloud and a terminal device for communication, and the method includes:

[0007] Acquire a plurality of first image data of a target power operation site;

[0008] Identify and analyze each of the plurality of first image data according to a preset risk level standard to obtain a plurality of risk levels;

[0009] Generate multiple warning messages according to the multiple risk levels; each risk level corresponds to one warning message;

[0010] compressing the plurality of first image data according to the plurality of risk levels to obtain a plurality of second image data;

[0011] Analyzing the importance of each second image data among the plurality of second image data to obtain a plurality of importance levels;

[0012] Assigning priorities to the plurality of second image data according to the plurality of risk levels and the plurality of importance levels to obtain a plurality of priorities; each second image data corresponds to a priority;

[0013] sorting the plurality of second image data according to the plurality of priorities to obtain a target transmission queue;

[0014] transmitting the plurality of second image data to the cloud according to the target transmission queue;

[0015] Receiving the plurality of second image data through the cloud, and decompressing and analyzing the plurality of second image data to obtain a target risk assessment result;

[0016] The multiple alarm information and the target risk assessment results are fed back to the terminal device to facilitate timely response to risk events at the target power operation site.

[0017] In a second aspect, an embodiment of the present application provides an intelligent monitoring device for risks of power field operations, which is applied to an intelligent monitoring system, wherein the intelligent monitoring system is connected to the cloud and a terminal device for communication, and the device includes an acquisition module, an identification module, a generation module, a compression module, an analysis module, an allocation module, a sorting module, a transmission module, and a feedback module, wherein:

[0018] The acquisition module is used to acquire a plurality of first image data of a target power operation site;

[0019] The identification module is used to identify and analyze each of the plurality of first image data according to a preset risk level standard to obtain a plurality of risk levels;

[0020] The generating module is used to generate a plurality of warning information according to the plurality of risk levels; each risk level corresponds to one warning information;

[0021] The compression module is used to compress the plurality of first image data according to the plurality of risk levels to obtain a plurality of second image data;

[0022] The analysis module is used to analyze the importance of each second image data among the plurality of second image data to obtain a plurality of importance levels;

[0023] The allocation module is used to allocate priorities to the plurality of second image data according to the plurality of risk levels and the plurality of importance levels to obtain a plurality of priorities; each second image data corresponds to a priority;

[0024] The sorting module is used to sort the plurality of second image data according to the plurality of priorities to obtain a target transmission queue;

[0025] The transmission module is used to transmit the plurality of second image data to the cloud according to the target transmission queue;

[0026] The analysis module is further used to receive the plurality of second image data through the cloud, and decompress and analyze the plurality of second image data to obtain a target risk assessment result;

[0027] The feedback module is used to feed back the multiple alarm information and the target risk assessment results to the terminal device, so as to facilitate timely response to risk events at the target power operation site.

[0028] In a third aspect, an embodiment of the present application provides an electronic device, comprising a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the program includes instructions for executing the steps of any method in the first aspect of the embodiment of the present application.

[0029] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps described in any method of the first aspect of the embodiment of the present application.

[0030] In a fifth aspect, an embodiment of the present application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps described in any method of the first aspect of the embodiment of the present application. The computer program product may be a software installation package.

[0031] By implementing the embodiments of the present application, the image data of the power operation site can be compressed and assigned priorities according to the risk level and importance, thereby ensuring that high-risk and important image data is transmitted first, thereby improving transmission efficiency, and timely receiving and processing alarm information and risk assessment results to speed up response speed and improve the timeliness and accuracy of safety monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. 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.

[0033] Figure 1 It is a system architecture diagram of an intelligent monitoring system provided by an embodiment of the present application;

[0034] Figure 2 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application;

[0035] Figure 3 It is a flow chart of an intelligent monitoring method for power field operation risks provided by an embodiment of the present application;

[0036] Figure 4 It is a block diagram of the functional modules of an intelligent monitoring device for power field operation risks provided in an embodiment of the present application. DETAILED DESCRIPTION

[0037] 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 drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0038] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0039] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article indicates that the associated objects before and after are in an "or" relationship. The "plurality" appearing in the embodiments of the present application refers to two or more.

[0040] In the embodiments of the present application, "at least one item" or similar expressions refer to any combination of these items, including any combination of single items or plural items, and refer to one or more, and multiple refers to two or more. For example, at least one item of a, b, or c can represent the following seven situations: a, b, c, a and b, a and c, b and c, a, b, and c. Among them, each of a, b, and c can be an element or a set containing one or more elements.

[0041] The "connection" that appears in the embodiments of the present application refers to various connection methods such as direct connection or indirect connection to achieve communication between devices, and the embodiments of the present application do not impose any limitations on this.

[0042] 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.

[0043] The following is an explanation of the relevant terms involved in this application, as follows:

[0044] Yolo-V7 (You Only Look Once-version 7) model: refers to an object detection model that optimizes model re-parameterization, dynamic label allocation, auxiliary head training, etc., improves the detection accuracy and speed of the model, and is widely used in computer vision tasks.

[0045] Long Short-Term Memory (LSTM) model: refers to a special type of recurrent neural network that is used to process and predict long-distance dependencies in time series data, and has a better processing effect on long sequence data.

[0046] JPEG2000 algorithm: refers to an image compression standard that uses a compression method based on wavelet transform. Compared with traditional image compression algorithms, it provides higher compression efficiency and image quality, and supports both lossless and lossy compression.

[0047] In the field of power operations, on-site safety monitoring is crucial to preventing accidents and ensuring personnel safety. Traditional video surveillance systems are often limited by network bandwidth when transmitting large amounts of data in real time, resulting in delayed transmission of monitoring data and failure to detect and respond to potential safety risks in a timely manner. This problem is particularly prominent in remote areas or environments with poor network conditions.

[0048] At present, a ball control system can be deployed at the operation site to collect and store videos of the site, and then sample and recognize the image information of the video to analyze the area and transmit it to the edge computing module of the monitoring host and the network cloud monitoring platform. However, when faced with different network environments and a large amount of alarm information, problems such as low data transmission efficiency and delayed alarm response may occur. Therefore, how to improve the timeliness and accuracy of safety monitoring in response to the risks of power site operations has become an urgent problem to be solved.

[0049] To solve the above problems, the embodiments of the present application provide an intelligent monitoring method and related devices for the risks of power site operations, which are applied to an intelligent monitoring system, wherein the intelligent monitoring system is connected to the cloud and terminal devices for communication; multiple first image data of the target power operation site are obtained; each of the multiple first image data is identified and analyzed according to a preset risk level standard to obtain multiple risk levels; multiple alarm messages are generated according to the multiple risk levels; each risk level corresponds to an alarm message; the multiple first image data are compressed according to the multiple risk levels to obtain multiple second image data; the importance of each of the multiple second image data is analyzed; The plurality of second image data are analyzed to obtain multiple importance levels; priorities are assigned to the plurality of second image data according to the plurality of risk levels and the plurality of importance levels to obtain multiple priorities; each second image data corresponds to a priority; the plurality of second image data are sorted according to the plurality of priorities to obtain a target transmission queue; the plurality of second image data are transmitted to the cloud according to the target transmission queue; the plurality of second image data are received through the cloud, and the plurality of second image data are decompressed and analyzed to obtain a target risk assessment result; the plurality of alarm information and the target risk assessment result are fed back to the terminal device to facilitate timely response to the risk event of the target power operation site. The image data of the power operation site can be compressed, and priorities can be assigned according to the risk level and importance to ensure that high-risk and important image data are transmitted first, thereby improving the transmission efficiency, and timely receiving and processing of alarm information and risk assessment results to speed up the response speed, improve the timeliness and accuracy of safety monitoring.

[0050] Combine the following Figure 1 A system architecture for executing an intelligent monitoring method for power field operation risks in an embodiment of the present application is described. Figure 1 This is a system architecture diagram of an intelligent monitoring system provided in an embodiment of the present application. The intelligent monitoring system includes multiple control balls and a control center, and is communicated with the cloud and terminal devices through the control center.

[0051] In one possible embodiment, according to the needs of the power operation site, the control center reasonably selects the number and installation angle of the control ball to ensure that each key area can be covered. Among them, the key areas include but are not limited to high-voltage equipment areas, personnel operation areas, and potential danger areas, which are not specifically limited here. Then, a specific viewing angle and angle can be set for each control ball to maximize the field of view. At the same time, each control ball is equipped with a high-resolution camera that can capture clear image data to ensure that the details of the captured image are clear and convenient for subsequent analysis and evaluation. Therefore, the image data of the power operation site can be collected in real time through the control ball, including static scenes and dynamic scenes, to ensure that the information of the key areas is fully recorded. The control center performs a preliminary evaluation of the image data based on the preset risk assessment criteria to obtain the risk assessment results. The image data is compressed according to the risk assessment results, that is, the data in the high-risk area needs to retain more details, and its compression degree is lower, while the data in the low-risk area has a higher compression degree, thereby optimizing the storage and transmission efficiency. The compressed image data is transmitted to the cloud by the control center, and further decompressed and analyzed to obtain the risk assessment results and real-time alarm information. The risk assessment results and real-time alarm information are fed back to the user's terminal device so that operators or managers can take prompt action to ensure the safety of the power operation site.

[0052] It can be seen that through the above system architecture, efficient and comprehensive safety monitoring of the power operation site can be achieved, and potential risks can be responded to in a timely manner, providing strong protection for the safety of power operations.

[0053] Combine the following Figure 2 The electronic device in the embodiment of the present application is described. Figure 2 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application is shown in FIG. Figure 2 As shown, the electronic device includes one or more processors, a memory, a communication interface and one or more programs, and the processor is communicatively connected with the memory and the communication interface via an internal communication bus.

[0054] Among them, the processor is mainly used for:

[0055] Acquire a plurality of first image data of a target power operation site;

[0056] Identify and analyze each of the plurality of first image data according to a preset risk level standard to obtain a plurality of risk levels;

[0057] Generate multiple warning messages according to multiple risk levels; each risk level corresponds to one warning message;

[0058] compressing the plurality of first image data according to the plurality of risk levels to obtain a plurality of second image data;

[0059] Analyzing the importance of each second image data among the plurality of second image data to obtain a plurality of importance levels;

[0060] Assigning priorities to the plurality of second image data according to the plurality of risk levels and the plurality of importance levels to obtain a plurality of priorities; each second image data corresponds to a priority;

[0061] sorting the plurality of second image data according to a plurality of priorities to obtain a target transmission queue;

[0062] transmitting the plurality of second image data to the cloud according to the target transmission queue;

[0063] Receiving a plurality of second image data through the cloud, and decompressing and analyzing the plurality of second image data to obtain a target risk assessment result;

[0064] Feedback of multiple alarm information and target risk assessment results to terminal devices facilitates timely response to risk events at the target power operation site.

[0065] The one or more programs are stored in the above-mentioned memory and are configured to be executed by the above-mentioned processor, and the one or more programs include instructions for executing any step in the above-mentioned method embodiment.

[0066] Among them, the processor can be, for example, a central processing unit (CPU), a general processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It can implement or execute various exemplary logic blocks, units and circuits described in conjunction with the disclosure of this application. The processor can also be a combination that implements a computing function, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like. The communication unit can be a communication interface, a transceiver, a transceiver circuit, etc., and the storage unit can be a memory.

[0067] The memory may be a volatile memory or a nonvolatile memory, or may include both volatile and nonvolatile memories. Among them, the nonvolatile memory may be a read-only memory (ROM), a programmable ROM (PROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM bus random access memory (DR RAM).

[0068] It is understandable that the electronic device may include more or fewer structural elements than those in the above structural block diagram, for example, including a power module, physical buttons, Wi-Fi module, speaker, Bluetooth module, sensor, display module, etc., which are not limited here. It is understandable that the electronic device may be equipped with Figure 1 The system architecture described.

[0069] After understanding the software and hardware architecture of this application, Figure 3 An intelligent monitoring method for power field operation risks in an embodiment of the present application is described. Figure 3 A flow chart of an intelligent monitoring method for power field operation risks provided in an embodiment of the present application is applied to an intelligent monitoring system, wherein the intelligent monitoring system is connected to the cloud and a terminal device for communication, and specifically includes the following steps:

[0070] Step S301: Acquire a plurality of first image data of a target power operation site.

[0071] Specifically, the intelligent monitoring system also includes multiple control balls, which are deployed at different locations of the target power operation site to form a multi-view, high-density monitoring network, and ensure that the camera of the control ball can cover the target power operation site in all directions and without blind spots. Each control ball has a high-definition camera function and can collect image data of the target power operation site. Among them, when multiple control balls collect images of the target power operation site, multiple first image data can be obtained, and each image data corresponds to a control ball.

[0072] Step S302: identifying and analyzing each of the plurality of first image data according to a preset risk level standard to obtain a plurality of risk levels.

[0073] Among them, a preset risk factor library and an assessment weight group are obtained; the risk factor library includes multiple risk factors; the assessment weight group includes multiple assessment weights; each risk factor corresponds to an assessment weight; the risk factor set corresponding to the reference image data is determined according to the risk factor library to obtain a reference risk factor set; the reference image data is any first image data among the multiple first image data; according to the mapping relationship between the preset risk factors and the risk initial values, the risk initial value corresponding to each reference risk factor in the reference risk factor set is determined to obtain a reference risk initial value group; the reference risk initial value group is weighted and summed according to the assessment weight group to obtain a reference risk assessment value; the risk level corresponding to the reference risk assessment value is determined according to the risk level standard to obtain the risk level of the reference image data.

[0074] Specifically, the preset risk factor library includes multiple risk factors, including but not limited to personnel misoperation, personnel safety, and environmental abnormalities, which are not specifically limited here. Among them, personnel misoperation includes unauthorized operation of equipment, violation of safety operating procedures, incorrect use of tools or equipment, etc.; personnel safety includes not wearing a safety helmet, not wearing work clothes, not wearing a safety rope, etc.; environmental abnormalities include fire, smoke, oil leakage, etc. The evaluation weight group includes multiple evaluation weights, and each risk factor corresponds to an evaluation weight. For example, the evaluation weight corresponding to personnel misoperation is 0.3, the evaluation weight corresponding to personnel safety is 0.3, and the evaluation weight corresponding to environmental abnormalities is 0.4, which are not specifically limited here. Any first image data among the multiple first image data is determined as reference image data, and then the risk factor set corresponding to the reference image data is determined according to the risk factor library to obtain a reference risk factor set. According to the mapping relationship between the preset risk factors and the risk initial value, the risk initial value corresponding to each reference risk factor in the reference risk factor set is determined to obtain a reference risk initial value group. The reference risk initial value group is weighted summed according to the evaluation weight group to obtain a reference risk evaluation value. The risk level corresponding to the reference risk assessment value is determined according to the risk level standard to obtain the risk level of the reference image data. The preset risk level standards include low risk, medium risk, and high risk. The environment of the power field operation can also be quantitatively evaluated according to methods such as fuzzy comprehensive evaluation and combined with the risk level standard, which is not specifically limited here.

[0075] The detection target corresponding to the reference image data includes at least one of the following: personnel, equipment, and environment. The risk factor set corresponding to the reference image data is determined according to the risk factor library to obtain the reference risk factor set. Specifically, the steps include:

[0076] When the reference image data is a static scene, and the detection target corresponding to the reference image data includes at least one of the following: personnel, equipment, and environment, the reference image data is detected according to a preset first model to determine the first risk factor corresponding to the detection target and the risk factor library; and the reference risk factor set is determined according to the first risk factor;

[0077] or,

[0078] When the reference image data is a dynamic scene, and the detection targets corresponding to the reference image data include not only personnel but also equipment and / or environment, the steps of detecting the reference image data according to a preset first model to determine the first risk factor corresponding to the detection target and the risk factor library are performed; analyzing the personnel in the adjacent image data of the specified time period corresponding to the reference image data according to a preset second model to obtain an action sequence, and identifying the action sequence to obtain the second risk factor corresponding to the action sequence and the risk factor library; and determining the reference risk factor set based on the first risk factor and the second risk factor.

[0079] It should be noted that the preset first model can be a Yolo-V7 model, and the preset second model can be an LSTM model, which is not specifically limited here. Among them, the Yolo-V7 model is used to identify people, equipment and environment in the image, and provide preliminary identification of static risk factors. The LSTM model is used to analyze the actions and behaviors of people in the time series, which can capture the dynamic behavior patterns of people and facilitate the identification of behavioral risks such as unauthorized operation of equipment or incorrect use of tools, thereby making up for the shortcomings of static detection alone.

[0080] In a possible embodiment, the reference image data is a static scene, that is, the scene in the reference image data is fixed and does not change dynamically. The Yolo-V7 model can be used to detect the personnel, equipment, and environment in the reference image data to determine whether the personnel, equipment, and environment match the first risk factor in the risk factor library, for example, a person not wearing a helmet, the environment is on fire, etc., and the matching first risk factors are integrated into a reference risk factor set.

[0081] In one possible embodiment, the reference image data is a dynamic scene, that is, the scene in the reference image data changes over time, then the Yolo-V7 model can be used to detect the personnel, equipment, and environment in the reference image data to obtain the first risk factor, and the LSTM model can be used to further detect the personnel in the reference image data. Among them, the personnel in the adjacent image data of the specified time period corresponding to the reference image data can be analyzed to obtain an action sequence. Then, the action sequence is identified to obtain a second risk factor corresponding to the action sequence and the risk factor library, for example, unauthorized operation of equipment by personnel, incorrect use of tools or equipment by personnel, etc., and the first risk factor and the second risk factor are integrated into a reference risk factor set.

[0082] It can be seen that through real-time analysis and detection of risk factors in static and dynamic scenarios, a more comprehensive and accurate identification of risk factors in power operation sites can be achieved, enhancing the overall safety and reliability of the system.

[0083] Step S303: Generate multiple warning messages according to the multiple risk levels; each risk level corresponds to one warning message.

[0084] Specifically, the warning information includes but is not limited to risk level, risk description, occurrence time, specific location, preliminary suggestions, response time, and responsible department, which are not specifically limited here.

[0085] Step S304: compress the multiple first image data according to the multiple risk levels to obtain multiple second image data.

[0086] Among them, according to the mapping relationship between the preset risk level and the compression parameter, the reference compression parameter corresponding to the reference risk level is determined; the reference compression parameter includes a reference quantization step and a reference quantization value; wherein, the higher the risk level, the smaller the quantization step and the lower the quantization value; according to the reference quantization step and the reference quantization value, the reference image data is compressed to obtain reference second image data; the reference second image data is the second image data corresponding to the reference first image data among the multiple second image data.

[0087] It should be noted that when the risk level is higher, it means that the requirements for image data details are higher, which requires a smaller quantization step and a lower quantization value to ensure higher image quality. Among them, the quantization step is the quantization accuracy during the data compression process. The smaller the step, the higher the quantization accuracy. The quantization value is the calibration value used when quantizing image data. The lower the value, the less data loss during the quantization process and the higher the image fidelity.

[0088] In a possible embodiment, the image data is efficiently compressed according to a preset image compression algorithm, and while maintaining the image quality, the transmission amount of the image data can be significantly reduced to reduce bandwidth occupancy and improve data transmission efficiency. The image compression algorithm can be a JPEG2000 algorithm, which is not specifically limited here. In the compression process of the image data, encoding can be performed through steps such as preprocessing, discrete wavelet transform, quantization, entropy coding, and code stream organization. Among them, in the preprocessing step, various preprocessing operations can be performed on the original image data, such as color space conversion, denoising, etc., to improve the compression efficiency; in the discrete wavelet transform step, the image data is decomposed into wavelet coefficients of different resolution levels, and the wavelet coefficients contain different detail information of the image data; in the quantization step, the wavelet coefficients generated by the discrete wavelet transform are quantized to reduce the amount of data and realize the compression of the image data; in the entropy coding step, the quantized wavelet coefficients are entropy coded to further reduce the amount of data; in the code stream organization step, the encoded data is organized into a code stream for easy storage or transmission, and the code stream organization step also includes code stream segmentation, packet header information addition and other operations to improve transmission efficiency and error recovery capability.

[0089] It should be noted that in the quantization step, the quantization step size or quantization table can be dynamically adjusted according to the risk level to control the degree of reduction in the accuracy of the image data. Among them, a smaller step size is used in high-risk areas to retain more details; a larger step size is used in low-risk areas to improve the compression ratio. In the quantization process, the corresponding quantization step size is applied according to the risk level of the area. A quantization table suitable for different areas is generated according to the importance of the image data, and a lower quantization value is used for important areas to retain higher image quality; a higher quantization value is used for unimportant areas to increase the compression effect. In the quantization process, the quantization values ​​in the quantization table are updated to ensure appropriate quantization of different areas. Among them, the parameters of the quantization step can also be adjusted according to the preset adjustment rules to ensure that the amount of data is reduced as much as possible while maintaining key information.

[0090] It can be seen that by analyzing the risk level of image data, the compression strategy of image data can be adjusted efficiently and dynamically to balance image quality and compression ratio, thereby improving data transmission efficiency without affecting image effects.

[0091] Step S305 , analyzing the importance of each second image data among the plurality of second image data to obtain a plurality of importance levels.

[0092] Specifically, the following steps can be performed for each second image data: the features of the second image data can be extracted by a preset computer vision technology to obtain edge information, texture information, and color histogram of the second image data, wherein the computer vision technology includes but is not limited to edge detection, texture analysis, and color histogram, which are not specifically limited here. The edge information, texture information, and color histogram are comprehensively scored according to a preset scoring standard to obtain a target score, and the target importance corresponding to the target score is determined according to the mapping relationship between the preset score and importance.

[0093] Step S306: assigning priorities to the plurality of second image data according to the plurality of risk levels and the plurality of importance levels to obtain a plurality of priorities.

[0094] Each second image data corresponds to a priority, the priority includes an integer part and a decimal part, and the priorities are assigned to the plurality of second image data according to the plurality of risk levels and the plurality of importance levels to obtain a plurality of priorities, and the specific steps include:

[0095] Allocate the integer part of the priority to the multiple second image data according to the multiple risk levels to obtain the integer part of the multiple priorities; the higher the risk level, the greater the value of the integer part of the priority; allocate the decimal part of the priority to the multiple second image data according to the multiple importance levels to obtain the decimal part of the multiple priorities; the higher the importance level, the greater the value of the decimal part of the priority; integrate the integer part of the multiple priorities and the decimal part of the multiple priorities to obtain the multiple priorities.

[0096] Specifically, the integer part of the priority is assigned to each second image data according to the risk level. For example, if the risk level of image data A is high, the integer part of its priority can be 6.0, and if the risk level of image data B is low, the integer part of its priority can be 2.0. No specific limitation is made here, and the higher the risk level, the larger the integer part of the priority. The decimal part of the priority is assigned to each second image data according to the importance. For example, if the importance of image data A is low, the decimal part of its priority can be 0.2, and if the importance of image data B is high, the integer part of its priority can be 0.6. No specific limitation is made here, and the higher the importance, the larger the decimal part of the priority. The integer part and decimal part of the priority are integrated to obtain the final priority of each second image data. For example, the final priority of image data A is 6.2, and the final priority of image data B is 2.6. No specific limitation is made here.

[0097] It can be seen that assigning priorities according to risk level and importance can ensure that higher-risk and important data are processed first, thereby improving overall processing efficiency and focusing more resources on more critical data to avoid waste of resources.

[0098] Step S307 , sorting the plurality of second image data according to the plurality of priorities to obtain a target transmission queue.

[0099] Specifically, the plurality of second image data are sorted according to their corresponding priorities, with the image data with a higher priority being placed in front, and then the target transmission queue is determined according to the sorted second image data to ensure that the image data with a higher priority is transmitted first.

[0100] In a possible embodiment, the current network status is obtained; the current network status includes any one of the following: a first-level congestion status, a second-level congestion status, and a smooth status; if the current network status is the first-level congestion status, the multiple second image data are transmitted to the cloud at a preset first transmission rate; if the current network status is the second-level congestion status, the transmission of low-priority second image data among the multiple second image data is suspended according to a preset time interval, and / or the resolution of high-priority second image data among the multiple second image data is reduced according to a preset ratio; if the current network status is the smooth status, the multiple second image data are transmitted to the cloud at a preset second transmission rate; the first transmission rate is less than the second transmission rate.

[0101] Specifically, the network status can be obtained during the transmission process. When the network status is a first-level congestion state, all the second image data are transmitted to the cloud at a preset first transmission rate. The first transmission rate is relatively low and can adapt to the first-level congestion of the network. When the network status is a second-level congestion state, the transmission of the low-priority second image data can be suspended according to a preset time interval, or the resolution or frame rate of the high-priority second image data can be reduced according to a preset ratio to reduce the amount of transmitted data and adapt to the second-level congestion of the network. When the network status is a smooth state, all the second image data are transmitted to the cloud at a preset second transmission rate, wherein the second transmission rate is relatively high and suitable for a smooth network.

[0102] It can be seen that by adjusting the transmission rate and the resolution of the image data, it is possible to better adapt to the network status and avoid transmission delays caused by congestion. When the network is congested, suspending the transmission of low-priority data or reducing the resolution of high-priority data facilitates the rational use of network bandwidth and reduces the risk of data loss.

[0103] In one possible embodiment, the effectiveness of the transmission strategy can be evaluated by tracking and analyzing key indicators in the transmission process, and the performance of the system in different network environments can be optimized. Among them, the key indicators include but are not limited to success rate, delay time, bandwidth usage, and packet loss rate, which are not specifically limited here. Machine learning algorithms can also be used to analyze historical data and real-time feedback to optimize transmission strategies, and by predicting network change trends and automatically adjusting transmission parameters, risk identification and importance assessment models can be gradually optimized, thereby improving the accuracy and efficiency of the overall system.

[0104] It can be seen that through real-time feedback and adaptive optimization, more efficient transmission and more accurate risk identification can be achieved.

[0105] Step S308: transmitting the plurality of second image data to the cloud according to the target transmission queue.

[0106] Specifically, according to the target transmission queue, the second image data is transmitted to the cloud in queue order, ensuring that important or urgent image data is uploaded first, thereby optimizing resource allocation and efficiency during the transmission process.

[0107] Step S309: receiving the plurality of second image data through the cloud, and decompressing and analyzing the plurality of second image data to obtain a target risk assessment result.

[0108] Among them, the multiple second image data are decompressed to obtain multiple third image data; the risk level corresponding to each of the multiple third image data is determined to obtain multiple target risk levels; the multiple target risk levels are analyzed to obtain multiple countermeasure suggestions; each target risk level corresponds to a countermeasure suggestion; and the target risk assessment result is determined based on the multiple target risk levels and the multiple countermeasure suggestions.

[0109] Specifically, the second image data is decompressed, that is, the compressed image is restored to its original state for further analysis. Then, the risk level of each image data can be evaluated again to obtain its corresponding target risk level. Each target risk level is analyzed to identify the countermeasures required for different levels. For example, image data A shows that device A shows signs of overheating, corresponding to a high risk level, and its corresponding countermeasures are "it is recommended to check the equipment immediately, take cooling measures, and arrange emergency repairs." Image data B shows that device B is obviously worn, corresponding to a medium risk level, and its corresponding countermeasures are "it is recommended to arrange regular inspections and plan to replace worn parts within the next maintenance cycle." The target risk assessment result is determined based on the target risk level and the countermeasures. For example, the target risk assessment result of image data A is "high risk level" and "it is recommended to check the equipment immediately, take cooling measures, and arrange emergency repairs."

[0110] It can be seen that by systematically combining risk levels and response measures, the efficiency and accuracy of risk management can be improved.

[0111] Step S310, feeding back the multiple alarm information and the target risk assessment result to the terminal device, so as to facilitate timely response to risk events at the target power operation site.

[0112] Specifically, through various channels, such as sound, pop-up windows, and text messages, real-time alarm information is transmitted to the user's terminal devices, such as mobile phones, tablets, and computers, to ensure that users can receive alarm information in the shortest time and understand its severity and specific content, so as to respond to risk events at the target power operation site in a timely manner. At the same time, the latest risk assessment report is automatically generated and fed back to the terminal device regularly or when major changes occur. The risk assessment report includes but is not limited to the analysis results of each alarm, the overall risk assessment, and response suggestions. Historical data can be archived to facilitate users to query historical alarm records, risk assessment results, and detailed information on treatment measures, among which, they can be filtered and queried by time range, alarm type, device ID, etc. Through the analysis of historical data, potential safety trends and problems can be identified, so that preventive measures can be taken in advance, such as optimizing equipment maintenance plans and adjusting monitoring strategies.

[0113] It can be seen that through effective analysis and processing of data, on-site risks can be managed efficiently, emergencies can be responded to quickly, and long-term trends can be analyzed, thereby improving the overall safety management level.

[0114] The above mainly introduces the scheme of the embodiment of the present application from the perspective of the execution process on the method side. It is understandable that, in order to realize the above functions, the electronic device includes a hardware structure and / or software module corresponding to the execution of each function. It should be easily appreciated by those skilled in the art that, in combination with the units and algorithm steps of each example described in the embodiments provided herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present application.

[0115] The embodiment of the present application can divide the electronic device into functional units according to the above method example. For example, each functional unit can be divided according to each function, or two or more functions can be integrated into one processing unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. It should be noted that the division of units in the embodiment of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0116] In the case of dividing each functional module into corresponding functional modules, Figure 4 A functional module composition block diagram of an intelligent monitoring device for power field operation risks provided in an embodiment of the present application is applied to an intelligent monitoring system, wherein the intelligent monitoring system is connected to the cloud and a terminal device for communication, and the intelligent monitoring device 400 for power field operation risks includes an acquisition module 410, an identification module 420, a generation module 430, a compression module 440, an analysis module 450, an allocation module 460, a sorting module 470, a transmission module 480, and a feedback module 490, wherein:

[0117] The acquisition module 410 is used to acquire a plurality of first image data of a target power operation site;

[0118] The identification module 420 is used to identify and analyze each of the plurality of first image data according to a preset risk level standard to obtain a plurality of risk levels;

[0119] The generating module 430 is used to generate a plurality of warning messages according to the plurality of risk levels; each risk level corresponds to one warning message;

[0120] The compression module 440 is used to compress the plurality of first image data according to the plurality of risk levels to obtain a plurality of second image data;

[0121] The analysis module 450 is used to analyze the importance of each second image data in the plurality of second image data to obtain a plurality of importance levels;

[0122] The allocation module 460 is used to allocate priorities to the plurality of second image data according to the plurality of risk levels and the plurality of importance levels, so as to obtain a plurality of priorities; each second image data corresponds to a priority;

[0123] The sorting module 470 is used to sort the plurality of second image data according to the plurality of priorities to obtain a target transmission queue;

[0124] The transmission module 480 is used to transmit the plurality of second image data to the cloud according to the target transmission queue;

[0125] The analysis module 450 is further configured to receive the plurality of second image data through the cloud, and decompress and analyze the plurality of second image data to obtain a target risk assessment result;

[0126] The feedback module 490 is used to feed back the multiple alarm information and the target risk assessment results to the terminal device to facilitate timely response to risk events at the target power operation site.

[0127] Optionally, in the aspect of identifying and analyzing each of the plurality of first image data according to a preset risk level standard to obtain a plurality of risk levels, the identification module 420 is specifically used to:

[0128] Obtaining a preset risk factor library and an assessment weight group; the risk factor library includes multiple risk factors; the assessment weight group includes multiple assessment weights; each risk factor corresponds to an assessment weight;

[0129] Determine a risk factor set corresponding to the reference image data according to the risk factor library to obtain a reference risk factor set; the reference image data is any one of the multiple first image data;

[0130] Determine the initial risk value corresponding to each reference risk factor in the reference risk factor set according to the mapping relationship between the preset risk factors and the initial risk values, and obtain a reference risk initial value group;

[0131] Performing weighted summation on the reference risk initial value group according to the assessment weight group to obtain a reference risk assessment value;

[0132] The risk level corresponding to the reference risk assessment value is determined according to the risk level standard to obtain the risk level of the reference image data.

[0133] Optionally, the detection target corresponding to the reference image data includes at least one of the following: personnel, equipment, and environment. In determining the risk factor set corresponding to the reference image data according to the risk factor library to obtain the reference risk factor set, the identification module 420 is further specifically used to:

[0134] When the reference image data is a static scene, and when the detection target corresponding to the reference image data includes at least one of the following: personnel, equipment, and environment, the reference image data is detected according to a preset first model to determine the first risk factor corresponding to the detection target and the risk factor library;

[0135] determining the reference risk factor set according to the first risk factor;

[0136] or,

[0137] When the reference image data is a dynamic scene, and when the detection target corresponding to the reference image data includes not only personnel but also equipment and / or environment, the step of detecting the reference image data according to a preset first model to determine the detection target and the first risk factor corresponding to the risk factor library is performed;

[0138] Analyze the persons in the adjacent image data of the specified time period corresponding to the reference image data according to the preset second model to obtain an action sequence, and identify the action sequence to obtain a second risk factor corresponding to the action sequence and the risk factor library;

[0139] The reference risk factor set is determined according to the first risk factor and the second risk factor.

[0140] Optionally, in the aspect of compressing the plurality of first image data according to the plurality of risk levels to obtain the plurality of second image data, the compression module 440 is specifically configured to:

[0141] Determine the reference compression parameter corresponding to the reference risk level according to the mapping relationship between the preset risk level and the compression parameter; the reference compression parameter includes a reference quantization step and a reference quantization value; wherein the higher the risk level, the smaller the quantization step and the lower the quantization value;

[0142] The reference image data is compressed according to a reference quantization step and a reference quantization value to obtain reference second image data; the reference second image data is second image data corresponding to the reference first image data among the plurality of second image data.

[0143] Optionally, the priority includes an integer part and a decimal part. In the aspect of assigning priorities to the plurality of second image data according to the plurality of risk levels and the plurality of importance levels to obtain the plurality of priorities, the assigning module 460 is specifically used to:

[0144] Allocating integer parts of priorities to the plurality of second image data according to the plurality of risk levels to obtain integer parts of the plurality of priorities; the higher the risk level, the greater the value of the integer part of the priority;

[0145] assigning decimal parts of priorities to the plurality of second image data according to the plurality of importance levels to obtain decimal parts of the plurality of priorities; the smaller the importance level, the greater the value of the decimal part of the priority level;

[0146] The multiple priorities are obtained by integrating the integer parts of the multiple priorities and the decimal parts of the multiple priorities.

[0147] Optionally, the transmission module 480 is further specifically configured to:

[0148] Obtaining the current network status; the current network status includes any one of the following: first-level congestion status, second-level congestion status, and smooth status;

[0149] If the current network state is the first-level congestion state, transmitting the plurality of second image data to the cloud at a preset first transmission rate;

[0150] If the current network state is the second-level congestion state, suspending the transmission of the second image data with a low priority among the plurality of second image data according to a preset time interval, and / or reducing the resolution of the second image data with a high priority among the plurality of second image data according to a preset ratio;

[0151] If the current network state is the unblocked state, the plurality of second image data are transmitted to the cloud at a preset second transmission rate; and the first transmission rate is lower than the second transmission rate.

[0152] Optionally, in the aspect of receiving the plurality of second image data through the cloud, decompressing and analyzing the plurality of second image data, and obtaining the target risk assessment result, the analysis module 450 is further specifically used for:

[0153] Decompressing the plurality of second image data to obtain a plurality of third image data;

[0154] Determine a risk level corresponding to each of the plurality of third image data to obtain a plurality of target risk levels;

[0155] Analyze the multiple target risk levels to obtain multiple response measures suggestions; each target risk level corresponds to a response measure suggestion;

[0156] The target risk assessment result is determined according to the multiple target risk levels and the multiple countermeasure suggestions.

[0157] It can be seen that the comprehensive use of risk assessment, data compression, priority allocation and cloud analysis has improved the response speed and processing capabilities of the overall system, making the monitoring and management of power operation sites more efficient.

[0158] It should be noted that the specific implementation of each operation can adopt the corresponding description of the method embodiment shown above. The intelligent monitoring device 400 for the risks of power field operations can be used to execute the above method embodiment of the present application, which will not be repeated here.

[0159] An embodiment of the present application also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps of any method recorded in the above method embodiments, and the above computer includes an electronic device.

[0160] The present application also provides 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 some or all of the steps of any method described in the method embodiment. The computer program product may be a software installation package, and the computer includes an electronic device.

[0161] It should be noted that, for the above-mentioned various embodiments, for the sake of simple description, they are all expressed as a series of action combinations. Those skilled in the art should be aware that the present application is not limited by the described order of actions, because some steps in the embodiments of the present application can be performed in other orders or simultaneously. In addition, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions, steps, modules or units involved are not necessarily required by the embodiments of the present application.

[0162] In the above embodiments, the embodiments of the present application have different focuses on the description of each embodiment. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0163] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

[0164] The steps of the method or algorithm described in the embodiments of the present application can be implemented in hardware or by executing software instructions by a processor. The software instructions can be composed of corresponding software modules, and the software modules can be stored in RAM, flash memory, ROM, EPROM, electrically erasable programmable read-only memory (electrically EPROM, EEPROM), registers, hard disks, mobile hard disks, read-only compact disks (CD-ROMs) or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an ASIC. In addition, the ASIC can be located in a terminal device or a management device. Of course, the processor and the storage medium can also be present in a terminal device or a management device as discrete components.

[0165] Those skilled in the art should be aware that in one or more of the above examples, the functions described in the embodiments of the present application can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiments of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, computer, server, or data center to another website site, computer, server, or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrations. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital video disc (DVD)), or a semiconductor medium (eg, a solid state disk (SSD)).

[0166] The modules / units included in the devices and products described in the above embodiments may be software modules / units or hardware modules / units, or may be partially software modules / units and partially hardware modules / units. For example, for the devices and products applied to or integrated in the chip, the modules / units included therein may all be implemented in the form of hardware such as circuits, or at least some of the modules / units may be implemented in the form of software programs, which run on the processor integrated inside the chip, and the remaining (if any) modules / units may be implemented in the form of hardware such as circuits; for the devices and products applied to or integrated in the chip module, the modules / units included therein may all be implemented in the form of hardware such as circuits, and different modules / units may be located in the same component (such as a chip, circuit module, etc.) or in different components of the chip module, or at least some of the modules / units may be implemented in the form of software programs. The software programs run on the processor integrated inside the chip, and the remaining (if any) modules / units may be implemented in the form of hardware such as circuits. It is implemented in the form of a software program, which runs on a processor integrated inside the chip module, and the remaining (if any) modules / units can be implemented in hardware such as circuits; for various devices and products applied to or integrated in the terminal equipment, the various modules / units contained therein can be implemented in hardware such as circuits, and different modules / units can be located in the same component (for example, chip, circuit module, etc.) or in different components in the terminal equipment, or, at least some modules / units can be implemented in the form of a software program, which runs on a processor integrated inside the terminal equipment, and the remaining (if any) modules / units can be implemented in hardware such as circuits.

[0167] The specific implementation methods described above further illustrate the purpose, technical solutions and beneficial effects of the embodiments of the present application. It should be understood that the above description is only the specific implementation method of the embodiments of the present application and is not intended to limit the protection scope of the embodiments of the present application. Any modifications, equivalent substitutions, improvements, etc. made on the basis of the technical solutions of the embodiments of the present application should be included in the protection scope of the embodiments of the present application.

Claims

1. An intelligent monitoring method for power field operation risks, characterized in that: Applied to an intelligent monitoring system, the intelligent monitoring system is connected to the cloud and a terminal device for communication, and the method includes: Acquire a plurality of first image data of a target power operation site; Identify and analyze each of the plurality of first image data according to a preset risk level standard to obtain a plurality of risk levels; Generate multiple warning messages according to the multiple risk levels; each risk level corresponds to one warning message; compressing the plurality of first image data according to the plurality of risk levels to obtain a plurality of second image data; Analyzing the importance of each second image data among the plurality of second image data to obtain a plurality of importance levels; Assigning priorities to the plurality of second image data according to the plurality of risk levels and the plurality of importance levels to obtain a plurality of priorities; each second image data corresponds to a priority; sorting the plurality of second image data according to the plurality of priorities to obtain a target transmission queue; transmitting the plurality of second image data to the cloud according to the target transmission queue; Receiving the plurality of second image data through the cloud, and decompressing and analyzing the plurality of second image data to obtain a target risk assessment result; The multiple alarm information and the target risk assessment results are fed back to the terminal device to facilitate timely response to risk events at the target power operation site.

2. The method according to claim 1, characterized in that The step of identifying and analyzing each of the plurality of first image data according to a preset risk level standard to obtain a plurality of risk levels includes: Obtaining a preset risk factor library and an assessment weight group; the risk factor library includes multiple risk factors; the assessment weight group includes multiple assessment weights; each risk factor corresponds to an assessment weight; Determine a risk factor set corresponding to the reference image data according to the risk factor library to obtain a reference risk factor set; the reference image data is any one of the multiple first image data; Determine the initial risk value corresponding to each reference risk factor in the reference risk factor set according to the mapping relationship between the preset risk factors and the initial risk values, and obtain a reference risk initial value group; Performing weighted summation on the reference risk initial value group according to the assessment weight group to obtain a reference risk assessment value; The risk level corresponding to the reference risk assessment value is determined according to the risk level standard to obtain the risk level of the reference image data.

3. The method according to claim 2, characterized in that The detection target corresponding to the reference image data includes at least one of the following: personnel, equipment, and environment. The risk factor set corresponding to the reference image data is determined according to the risk factor library to obtain the reference risk factor set, including: When the reference image data is a static scene, and when the detection target corresponding to the reference image data includes at least one of the following: personnel, equipment, and environment, the reference image data is detected according to a preset first model to determine the first risk factor corresponding to the detection target and the risk factor library; determining the reference risk factor set according to the first risk factor; or, When the reference image data is a dynamic scene, and when the detection target corresponding to the reference image data includes not only personnel but also equipment and / or environment, the step of detecting the reference image data according to a preset first model to determine the detection target and the first risk factor corresponding to the risk factor library is performed; Analyze the persons in the adjacent image data of the specified time period corresponding to the reference image data according to the preset second model to obtain an action sequence, and identify the action sequence to obtain a second risk factor corresponding to the action sequence and the risk factor library; The reference risk factor set is determined according to the first risk factor and the second risk factor.

4. The method according to claim 2 or 3, characterized in that The compressing the plurality of first image data according to the plurality of risk levels to obtain the plurality of second image data comprises: Determine the reference compression parameter corresponding to the reference risk level according to the mapping relationship between the preset risk level and the compression parameter; the reference compression parameter includes a reference quantization step and a reference quantization value; wherein the higher the risk level, the smaller the quantization step and the lower the quantization value; The reference image data is compressed according to a reference quantization step and a reference quantization value to obtain reference second image data; the reference second image data is second image data corresponding to the reference first image data among the plurality of second image data.

5. The method according to claim 1, characterized in that The priority includes an integer part and a decimal part, and the priorities are assigned to the plurality of second image data according to the plurality of risk levels and the plurality of importance levels to obtain a plurality of priorities, including: Allocating integer parts of priorities to the plurality of second image data according to the plurality of risk levels to obtain integer parts of the plurality of priorities; the higher the risk level, the greater the value of the integer part of the priority; assigning decimal parts of priorities to the plurality of second image data according to the plurality of importance levels to obtain decimal parts of the plurality of priorities; the higher the importance level, the greater the value of the decimal part of the priority level; The multiple priorities are obtained by integrating the integer parts of the multiple priorities and the decimal parts of the multiple priorities.

6. The method according to claim 1, characterized in that The method further comprises: Obtaining the current network status; the current network status includes any one of the following: first-level congestion status, second-level congestion status, and smooth status; If the current network state is the first-level congestion state, transmitting the plurality of second image data to the cloud at a preset first transmission rate; If the current network state is the second-level congestion state, suspending the transmission of the second image data with a low priority among the plurality of second image data according to a preset time interval, and / or reducing the resolution of the second image data with a high priority among the plurality of second image data according to a preset ratio; If the current network state is the unblocked state, the plurality of second image data are transmitted to the cloud at a preset second transmission rate; and the first transmission rate is lower than the second transmission rate.

7. The method according to claim 1, characterized in that The receiving the plurality of second image data through the cloud, and decompressing and analyzing the plurality of second image data to obtain a target risk assessment result includes: Decompressing the plurality of second image data to obtain a plurality of third image data; Determine a risk level corresponding to each of the plurality of third image data to obtain a plurality of target risk levels; Analyze the multiple target risk levels to obtain multiple response measures suggestions; each target risk level corresponds to a response measure suggestion; The target risk assessment result is determined according to the multiple target risk levels and the multiple countermeasure suggestions.

8. An intelligent monitoring device for risks in power field operations, characterized in that: Applied to an intelligent monitoring system, the intelligent monitoring system is connected to the cloud and the terminal device in communication, the device includes an acquisition module, an identification module, a generation module, a compression module, an analysis module, an allocation module, a sorting module, a transmission module and a feedback module, wherein: The acquisition module is used to acquire a plurality of first image data of a target power operation site; The identification module is used to identify and analyze each of the plurality of first image data according to a preset risk level standard to obtain a plurality of risk levels; The generating module is used to generate a plurality of warning information according to the plurality of risk levels; each risk level corresponds to one warning information; The compression module is used to compress the plurality of first image data according to the plurality of risk levels to obtain a plurality of second image data; The analysis module is used to analyze the importance of each second image data among the plurality of second image data to obtain a plurality of importance levels; The allocation module is used to allocate priorities to the plurality of second image data according to the plurality of risk levels and the plurality of importance levels to obtain a plurality of priorities; each second image data corresponds to a priority; The sorting module is used to sort the plurality of second image data according to the plurality of priorities to obtain a target transmission queue; The transmission module is used to transmit the plurality of second image data to the cloud according to the target transmission queue; The analysis module is further used to receive the plurality of second image data through the cloud, and decompress and analyze the plurality of second image data to obtain a target risk assessment result; The feedback module is used to feed back the multiple alarm information and the target risk assessment results to the terminal device, so as to facilitate timely response to risk events at the target power operation site.

9. An electronic device, characterized in that: include: A processor, a memory, a communication interface, and one or more programs; The one or more programs are stored in the memory and configured to be executed by the processor, the programs comprising instructions for executing the steps in the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor is caused to perform the method according to any one of claims 1 to 7.

Images