Monitoring equipment detection method and device, equipment and medium

Abstract

The invention discloses a monitoring equipment detection method and device, equipment and a medium. The method comprises the following steps: acquiring at least one monitoring device and device operation information corresponding to each monitoring device; for each monitoring device, generating three-dimensional data corresponding to the monitoring device according to the parameter value of the parameter item in the device operation information of the monitoring device, the change data of the parameter value and the fault level to which the parameter value belongs, and mapping the three-dimensional data into a device image; acquiring a real-time shot image of the monitoring equipment; fusing the equipment image of the monitoring equipment and the real-time shot image, and determining a target image corresponding to the monitoring equipment; and calculating the similarity between the target image and the standard normal image of each piece of monitoring equipment, and carrying out anomaly detection on each piece of monitoring equipment. According to the embodiment of the invention, the detection efficiency of the monitoring equipment can be improved.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method, apparatus, equipment and medium for detecting monitoring equipment. Background Technology

[0002] With the rapid development of technology, the number of monitoring devices is increasing and they have permeated all aspects of people's lives to monitor the target environment. If the monitoring devices malfunction, it will be difficult to monitor changes in the target environment in a timely manner, making it difficult to ensure the safety of life and property.

[0003] Currently, the reliability of monitoring equipment is ensured by periodically inspecting it manually.

[0004] However, the number and types of monitoring equipment are numerous, and manual detection is too inefficient. Summary of the Invention

[0005] This invention provides a method, apparatus, equipment, and medium for detecting monitoring equipment, in order to improve the accuracy of monitoring equipment detection.

[0006] In a first aspect, embodiments of the present invention provide a method for detecting monitoring equipment, the method comprising:

[0007] Obtain at least one monitoring device and its corresponding device operation information;

[0008] For each monitoring device, based on the parameter values, parameter value changes, and fault levels of the parameter values ​​in the device's operation information, three-dimensional data corresponding to the monitoring device is generated and mapped into a device image.

[0009] Acquire real-time images captured by monitoring equipment;

[0010] By fusing the device images and real-time captured images from the monitoring equipment, the target image corresponding to the monitoring equipment can be determined.

[0011] Calculate the similarity between the target image and the standard normal image of each monitoring device, and perform anomaly detection on each monitoring device.

[0012] Secondly, embodiments of the present invention also provide a monitoring equipment detection device, the device comprising:

[0013] The information acquisition module is used to acquire at least one monitoring device and the corresponding device operation information of each monitoring device.

[0014] The equipment image generation module is used to generate three-dimensional data corresponding to each monitoring device based on the parameter values, parameter value changes, and fault levels of the parameter values ​​in the equipment operation information of the monitoring device, and map them into equipment images.

[0015] The image acquisition module is used to acquire real-time images captured by the monitoring equipment;

[0016] The image fusion module is used to fuse the equipment images and real-time captured images of the monitoring equipment to determine the target image corresponding to the monitoring equipment;

[0017] The anomaly detection module is used to calculate the similarity between the target image and the standard normal image of each monitoring device, and to perform anomaly detection on each monitoring device.

[0018] Thirdly, embodiments of the present invention also provide a monitoring device detection device, which includes:

[0019] At least one processor; and

[0020] A memory that is communicatively connected to at least one processor; wherein,

[0021] The memory stores a computer program that can be executed by at least one processor, such that the at least one processor is able to perform the monitoring device detection method of any embodiment of the present invention.

[0022] According to another aspect of the present invention, a computer-readable storage medium is provided, which stores computer instructions for causing a processor to execute and implement the monitoring device detection method of any embodiment of the present invention.

[0023] The technical solution of this invention generates three-dimensional data corresponding to each monitoring device through the device operation information of each monitoring device, and maps it to a device image. It can preserve the spatial relationship between attribute features, and fuse the device image of the monitoring device with the real-time captured image to determine the target image corresponding to the monitoring device. It calculates the similarity between the target image of each monitoring device and the standard normal image to perform anomaly detection on each monitoring device. It can detect monitoring devices through multi-dimensional data, thereby improving the accuracy of monitoring device detection.

[0024] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 This is a flowchart of a monitoring equipment detection method provided in Embodiment 1 of the present invention;

[0027] Figure 2 This is a flowchart of a monitoring equipment detection method provided according to Embodiment 2 of the present invention;

[0028] Figure 3 This is a structural diagram of a monitoring equipment detection device provided according to an embodiment of the present invention;

[0029] Figure 4 This is a schematic diagram of the structure of a monitoring and detection device provided in an embodiment of the present invention. Detailed Implementation

[0030] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0031] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0032] The acquisition, storage, and application of equipment operation information and other related information in the technical solutions of this invention comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0033] Example 1

[0034] Figure 1 This is a flowchart illustrating a monitoring device detection method according to Embodiment 1 of the present invention. This embodiment of the invention is applicable to monitoring device detection, and the method can be executed by a monitoring device detection device, which can be implemented in hardware and / or software.

[0035] See Figure 1 The monitoring equipment detection method shown includes:

[0036] S101. Obtain at least one monitoring device and the corresponding device operation information for each monitoring device.

[0037] The monitoring equipment can be devices that collect, transmit, store, and analyze video information of a target area in real time. Equipment operation information can be key data reflecting the real-time or historical operating status, performance parameters, or health condition of the monitoring equipment.

[0038] Specifically, there is a one-to-one correspondence between monitoring devices and monitoring identifiers. By acquiring at least one monitoring identifier, the monitoring device corresponding to each identifier can be determined. At least one parameter item is acquired. The parameter values ​​corresponding to each parameter item of each monitoring device can be monitored to determine the device's operational information. The data type and number of parameter values ​​corresponding to different parameter items can vary. For example, when the parameter item is the device's on / off status, the parameter value corresponding to the parameter item is only either on (1) or off (0); when the parameter item is the number of faults within a year, the number of parameter values ​​can be 12, and the content of the parameter value can be the month identifier and its corresponding number of faults.

[0039] S102. For each monitoring device, based on the parameter values, parameter value changes, and fault levels of the parameter values ​​in the device operation information, generate the corresponding three-dimensional data of the monitoring device and map it into a device image.

[0040] The fault level can be the severity level of the fault corresponding to the parameter value. The equipment image can be an image containing equipment operation information of the monitoring equipment.

[0041] Specifically, in digital images, channels are the basic units that constitute image color or information, used to independently store a certain type of image feature. The pixel color or information of a digital image is also determined by the combination of values ​​from different channels. An RGB image (3 channels) contains three channels: red (R), green (G), and blue (B). Each channel independently stores the brightness information of its corresponding color, and the combination of values ​​from the three channels forms the color of a pixel. An image is a collection of pixels; by determining the values ​​of all pixels in each channel, a complete image can be generated. For each monitoring device, the parameter values, parameter value changes, and fault levels associated with the parameters in the device's operating information are stored in different channels. The pixel values ​​of each pixel corresponding to each channel are determined, generating data for the three channels corresponding to the monitoring device, determining the three-dimensional data of the monitoring device, and finally, determining the device image based on the data from the three channels.

[0042] S103. Acquire real-time images captured by the monitoring equipment.

[0043] Among them, real-time captured images can be images captured by the monitoring equipment at the current time.

[0044] Specifically, a shooting request can be sent to each of the aforementioned monitoring devices. After receiving the shooting request, each monitoring device will capture images of the target area it is monitoring, thereby obtaining a real-time captured image corresponding to each monitoring device. The real-time captured image can be a multi-channel image or a single-channel image.

[0045] S104. Combine the equipment images and real-time captured images of the monitoring equipment to determine the target image corresponding to the monitoring equipment.

[0046] The target image can be an image generated by fusing the device image of the monitoring equipment with the real-time captured image.

[0047] Specifically, the length and width of the device image are the same as those of the real-time captured image. For each pixel in the device image, the pixel value of that pixel is added to the corresponding pixel value in the real-time captured image to determine the pixel value corresponding to the pixel in the target image, thereby determining the target image.

[0048] S105. Calculate the similarity between the target image and the standard normal image of each monitoring device, and perform anomaly detection on each monitoring device.

[0049] Among them, a standard normal image can be an image that stores the equipment operation information of the monitoring equipment under normal operating conditions.

[0050] Specifically, for each monitoring device, the similarity between the target image and the standard normal image is calculated. If the similarity between the target image and the standard normal image is within a preset similarity data range, it indicates that the device's operating information is in a normal state, and the monitoring device is not abnormal. If the similarity between the target image and the standard normal image is not within the preset similarity data range, it indicates that the device's operating information contains abnormal operating information, and the monitoring device is abnormal. Abnormal devices can be filtered out from the monitoring devices and alarms can be issued for device maintenance. Alarm methods include, but are not limited to, information alarms, email alarms, pop-up alarms, voice alarms, or telephone alarms. This embodiment of the invention does not impose any limitations on these methods.

[0051] The technical solution of this invention generates three-dimensional data corresponding to each monitoring device through the device operation information of each monitoring device, and maps it to a device image. It can preserve the spatial relationship between attribute features, and fuse the device image of the monitoring device with the real-time captured image to determine the target image corresponding to the monitoring device. It calculates the similarity between the target image of each monitoring device and the standard normal image to perform anomaly detection on each monitoring device. It can detect monitoring devices through multi-dimensional data, thereby improving the accuracy of monitoring device detection.

[0052] Example 2

[0053] Figure 2 This is a flowchart illustrating a monitoring device detection method according to Embodiment 2 of the present invention. Based on the above embodiments, this embodiment optimizes and improves the monitoring device detection operation.

[0054] Furthermore, the process of "generating 3D data corresponding to the monitoring equipment based on the equipment operation information and mapping it to an equipment image" is refined into "generating an attribute matrix based on the parameter values ​​of the parameter items in the equipment operation information; generating curve data based on the change data of the parameter values ​​of the parameter items in the equipment operation information; generating fault identification data based on the fault level to which the parameter values ​​of the parameter items in the equipment operation information belong; normalizing the attribute matrix, curve data, and fault identification data to the same numerical range space; and stitching the normalized attribute matrix, curve data, and fault identification data on the channel to obtain the equipment image," thereby improving the operation of monitoring equipment detection.

[0055] It should be noted that for parts not described in detail in the embodiments of the present invention, please refer to the descriptions in other embodiments.

[0056] See Figure 2 The monitoring equipment detection method shown includes:

[0057] S201. Obtain at least one monitoring device and the corresponding device operation information for each monitoring device.

[0058] S202. For each monitoring device, generate an attribute matrix based on the parameter values ​​of the parameter items in the device operation information of the monitoring device.

[0059] The attribute matrix can be a matrix composed of parameter values ​​corresponding to the parameter items of the monitoring device.

[0060] Specifically, for each monitoring device, there is at least one corresponding parameter item. The parameter values ​​for each parameter item are then obtained. For each parameter item, the region in the device image where the parameter value can be stored is located. Based on the length and width of this region, the number of rows and columns of the matrix is ​​determined. Each parameter value of the parameter item is mapped to a position in the matrix, thus generating an attribute matrix for the parameter value of the parameter item. The attribute matrix includes at least one element, which corresponds to both a position coordinate and an element value. The position coordinate of the element indicates that the element value is stored at the corresponding pixel in the device image, and the element value has the same magnitude as the parameter value stored at that position coordinate.

[0061] S203. Generate curve data based on the changes in parameter values ​​of parameter items in the equipment operation information of the monitoring equipment.

[0062] Curve data can be a collection of data storing the changes in parameter values ​​of parameter items.

[0063] Specifically, the equipment operation information contains at least one parameter item. For each parameter item, there are at least one parameter value, and each parameter value is data obtained from monitoring the parameter item at different time points. The parameter value corresponding to different time points may be different. The coordinate system position area corresponding to the parameter item is obtained by querying the parameter item. A Cartesian coordinate system is established at the coordinate system position area of ​​the equipment image under the specified channel. The horizontal coordinate of the position in the Cartesian coordinate system of the equipment image at each time point is determined. The parameter value at each time point is determined as the vertical coordinate of the position corresponding to the horizontal coordinate. Based on the horizontal coordinate, vertical coordinate, and coordinate system position area, curve data is determined.

[0064] S204. Generate fault identification data based on the fault level of the parameter value in the equipment operation information of the monitoring equipment.

[0065] Among them, fault identification data can be data of patterns that identify faults.

[0066] Specifically, different parameter values ​​correspond to different operating states of the monitoring equipment. For example, different parameter values ​​within different data ranges correspond to different fault degrees; different parameter values ​​with different string identifiers also correspond to different fault degrees. Different parameter items correspond to different fault identification patterns; for example, the fault identification pattern can be a circle, a triangle, etc. Different parameter values ​​belonging to different fault levels correspond to different sizes of fault identification patterns; for example, different parameter values ​​belonging to different fault levels correspond to different radii of the circles. Fault identification data is generated based on the fault levels of the parameter values ​​in the monitoring equipment's operating information.

[0067] S205. Normalize the attribute matrix, curve data, and fault identification data to the same numerical range space.

[0068] Specifically, the image consists of three channels: Red, Green, and Blue. Each channel has a value ranging from 0 to 255, with higher values ​​indicating brighter color components. Attribute matrices, curve data, and fault identification data are all stored in different channels, with each channel corresponding to at least one pixel. Each element in the attribute matrix, curve data, and fault identification data corresponds to two pieces of information: the element's position coordinates and a parameter value. The parameter values ​​are normalized to the range of 0-255.

[0069] S206. The normalized attribute matrix, curve data, and fault identification data are stitched together on the channel to obtain the equipment image.

[0070] Specifically, the attribute matrix, curve data, and fault identification data are stored on the images corresponding to different channels. The normalized attribute matrix, curve data, and fault identification data are stitched together on the channels to determine the pixel values ​​of each pixel in the image on different channels, that is, to determine the three-dimensional pixel values ​​of each pixel in the image, thus obtaining the device image.

[0071] S207. Acquire real-time images captured by the monitoring equipment.

[0072] S208. Combine the device image and real-time captured image of the monitoring equipment to determine the target image corresponding to the monitoring equipment.

[0073] S209. Calculate the similarity between the target image and the standard normal image of each monitoring device, and perform anomaly detection on each monitoring device.

[0074] This invention generates an attribute matrix based on the parameter values ​​of parameters in the equipment operation information of the monitoring equipment; generates curve data based on the change data of parameter values ​​in the equipment operation information of the monitoring equipment; generates fault identification data based on the fault level to which the parameter values ​​of the parameters in the equipment operation information of the monitoring equipment belong; normalizes the attribute matrix, curve data, and fault identification data to the same numerical range space; and stitches the normalized attribute matrix, curve data, and fault identification data on a channel to obtain an equipment image. This allows the multidimensional data of the monitoring equipment to be stored in the equipment image, preserving the spatial relationship between various attributes and improving the accuracy of equipment anomaly detection.

[0075] Optionally, an attribute matrix is ​​generated based on the parameter values ​​of the parameter items in the device operation information of the monitoring device, including: for each parameter item of the monitoring device, determining at least one parameter value and attribute location area corresponding to the parameter item; determining at least one element position based on the attribute location area; matching each parameter value corresponding to the parameter item with each element position to determine the matrix position corresponding to each parameter value; and determining the attribute matrix based on each parameter value and the matrix position corresponding to each parameter value.

[0076] Among them, the attribute location region can be the descriptive information of the region location of the parameter value corresponding to the parameter item that can be stored in the image.

[0077] Specifically, different parameter items can correspond to different storable channels, and different parameter items can have different storable areas on the same channel. For each parameter item of the monitoring device, determine at least one parameter value and attribute location area corresponding to the parameter item; determine at least one element position based on the attribute location area; the length and width of the attribute location area correspond to the length and width of the matrix. Assign each parameter value to each element position to determine the matrix position corresponding to each parameter value; determine the attribute matrix based on each parameter value and its corresponding matrix position. For each element in the attribute matrix, store the parameter value corresponding to the element at the image position corresponding to the element, thus determining the image under the corresponding channel of the attribute matrix.

[0078] By targeting each parameter item of the monitoring equipment, at least one parameter value and attribute location area corresponding to the parameter item are determined; at least one element position is determined based on the attribute location area; the parameter values ​​corresponding to each parameter item are matched with the element positions to determine the matrix position corresponding to each parameter value; and the attribute matrix is ​​determined based on each parameter value and the matrix position corresponding to each parameter value, so as to structure the parameter values ​​of the parameter items and realize operations such as dimensionality reduction and feature extraction of parameter value features.

[0079] Optionally, curve data is generated based on the parameter value changes of parameter items in the equipment operation information of the monitoring equipment. This includes: for each parameter item of the monitoring equipment, obtaining the curve area corresponding to the parameter item and at least one parameter value corresponding to the parameter item, where the parameter value includes the sampling time and the sampled value corresponding to the sampling time; determining the abscissa position of the curve corresponding to each parameter value based on the curve area corresponding to the parameter item and the sampling time corresponding to each parameter value; determining the ordinate position of the curve corresponding to each parameter value based on the curve area corresponding to the parameter item and the sampled value corresponding to each parameter value; and determining the curve data based on the abscissa position and ordinate position of the curve corresponding to each parameter value.

[0080] Specifically, for each parameter item of the monitoring equipment, the corresponding curve area and at least one parameter value are obtained. The parameter value includes the sampling time and the sampled value corresponding to the sampling time. A Cartesian coordinate system is established within the curve area corresponding to the parameter item. The horizontal coordinate position of the curve corresponding to each parameter value is determined based on the sampling time. The vertical coordinate position of the curve corresponding to each parameter value is determined based on the sampled value. The vertical coordinate points of each curve are connected using the same preset pixel value identifier to determine the curve data. The curve and coordinate system can be displayed in the image curve area of ​​the corresponding channel using the preset pixel value identifier, while the pixel values ​​of all other pixels in the curve area are 0.

[0081] By targeting each parameter item of the monitoring equipment, the corresponding curve region and at least one parameter value are obtained. The parameter value includes the sampling time and the sampled value corresponding to the sampling time. Based on the curve region corresponding to the parameter item and the sampling time corresponding to each parameter value, the horizontal coordinate position of the curve corresponding to each parameter value is determined. Based on the curve region corresponding to the parameter item and the sampled value corresponding to each parameter value, the vertical coordinate position of the curve corresponding to each parameter value is determined. Based on the horizontal and vertical coordinate positions of the curves corresponding to each parameter value, the curve data is determined, transforming discrete points into continuous trend information, and the potential patterns between parameter values ​​can be identified.

[0082] Optionally, fault identification data is generated based on the fault level of the parameter value of the parameter item in the equipment operation information of the monitoring equipment, including: performing fault detection on the parameter value of the parameter item in the equipment operation information of the monitoring equipment according to preset rules to obtain the fault type and the corresponding fault level; determining the corresponding fault pattern identifier according to the fault type and fault level; and generating the fault pattern identifier at the corresponding position of the parameter item in the equipment operation information of the monitoring equipment.

[0083] Specifically, fault detection is performed on the parameter values ​​of the parameter items in the equipment operation information of the monitoring equipment according to preset rules. For example, the preset rules may be to identify the type of fault string contained in the parameter value or to determine the data range to which the parameter value belongs, so as to obtain the fault type and the corresponding fault level; the fault pattern type is determined according to the fault type, the size of the fault pattern is determined according to the fault level, and a fault pattern identifier is generated at the corresponding position of the parameter item in the equipment operation information of the monitoring equipment according to the type and size of the fault pattern.

[0084] By performing fault detection on the parameter values ​​of the equipment operation information of the monitoring equipment according to preset rules, the fault type and corresponding fault level are obtained; the corresponding fault pattern identifier is determined according to the fault type and fault level; and the fault pattern identifier is generated at the corresponding position of the parameter item in the equipment operation information of the monitoring equipment, which can reduce the difficulty of anomaly identification and improve the efficiency of anomaly identification.

[0085] Optionally, the device image and real-time captured image of the monitoring device are fused to determine the target image corresponding to the monitoring device, including: obtaining a preset pixel threshold; performing binarization processing on the real-time captured image according to the preset pixel threshold to determine a binary image; and adding the pixel value of each pixel in the binary image to the pixel value of its corresponding pixel in the device image to determine the target image corresponding to the monitoring device.

[0086] The preset pixel threshold can be the pixel value of a preset pixel.

[0087] Specifically, the preset pixel threshold can be a threshold for one channel, two channels, or three channels; this embodiment of the invention does not impose any limitation on this. The pixel value of each pixel in the real-time captured image is compared with the preset pixel threshold. If the pixel value of a pixel in the real-time captured image is greater than the preset pixel threshold, then the pixel value of the pixel in the real-time captured image is determined as the first pixel value; for example, the first pixel value can be 0. If the pixel value of a pixel in the real-time captured image is less than or equal to the preset pixel threshold, then the pixel value of the pixel in the real-time captured image is determined as the second pixel value; for example, the first pixel value can be 255. The real-time captured image is binarized according to the preset pixel threshold to determine a binary image. The pixel value of each pixel in the binary image is added to the pixel value of its corresponding pixel in the device image to determine the target image corresponding to the monitoring device.

[0088] By acquiring a preset pixel threshold, binarizing the real-time captured image according to the preset pixel threshold to determine a binary image, and adding the pixel value of each pixel in the binary image to the pixel value of its corresponding pixel in the device image to determine the target image corresponding to the monitoring device, anomaly detection of the monitoring device can be performed through real-time captured images and device operation information, thereby improving the accuracy of anomaly detection of the monitoring device.

[0089] Optionally, after generating 3D data corresponding to the monitoring device based on the parameter values, parameter value changes, and fault levels of the parameter values ​​in the device operation information of the monitoring device, and mapping it to a device image, the process further includes: acquiring incremental data of the target device's operation information; determining the target channel based on the incremental data; updating the data on the target channel based on the incremental data and its corresponding weights; updating the device image based on the updated data on the target channel; fusing the updated device image of the target device with the real-time captured image to determine the target image corresponding to the target device; and calculating the similarity between the target image of the target device and a standard normal image to perform anomaly detection on the target device.

[0090] Incremental data can be newly detected parameter values ​​for the parameters of the monitoring equipment. The target channel can be the channel for which data updates are to be performed.

[0091] Specifically, the process involves: acquiring incremental data of the target device's operational information; determining the required storage channel and target channel based on the incremental data; obtaining the weights corresponding to the incremental data, which can be achieved by querying a mapping table between incremental data and weights; updating the parameter values ​​of the corresponding parameters on the target channel based on the incremental data and their corresponding weights, by multiplying the weights of the incremental data by the corresponding parameter values; updating the device image based on the updated data on the target channel; fusing the updated device image and the real-time captured image according to the rule of adding the pixel values ​​of the same pixels to determine the target image for the target device; and calculating the similarity between the target image and the standard normal image to perform anomaly detection on the target device.

[0092] The system acquires incremental data on the operation of the target device; determines the target channel based on the incremental data; updates the data on the target channel according to the incremental data and its corresponding weights; updates the device image based on the updated data on the target channel; fuses the updated device image with real-time captured images to determine the target image corresponding to the target device; calculates the similarity between the target image and a standard normal image to perform anomaly detection on the target device. The system can update the device image based on the monitored data of the real-time acquired parameters, improving the accuracy of device fault detection.

[0093] Example 3

[0094] Figure 3 This is a schematic diagram of a monitoring equipment detection device provided in Embodiment 3 of the present invention. This embodiment of the present invention is applicable to monitoring equipment detection, and the device can execute a monitoring equipment detection method. The device can be implemented in hardware and / or software.

[0095] See Figure 3 The monitoring equipment detection device shown includes: an information acquisition module 301, an equipment image generation module 302, a captured image acquisition module 303, an image fusion module 304, and an anomaly detection module 305, wherein...

[0096] Information acquisition module 301 is used to acquire at least one monitoring device and the corresponding device operation information of each monitoring device;

[0097] The device image generation module 302 is used to generate three-dimensional data corresponding to each monitoring device based on the parameter values, parameter value change data and fault level of the parameter values ​​in the device operation information of the monitoring device, and map them into a device image.

[0098] The image acquisition module 303 is used to acquire real-time images captured by the monitoring equipment.

[0099] The image fusion module 304 is used to fuse the device image and the real-time captured image of the monitoring device to determine the target image corresponding to the monitoring device.

[0100] The anomaly detection module 305 is used to calculate the similarity between the target image and the standard normal image of each monitoring device, and to perform anomaly detection on each monitoring device.

[0101] The technical solution of this invention generates three-dimensional data corresponding to each monitoring device through the device operation information of each monitoring device, and maps it to a device image. It can preserve the spatial relationship between attribute features, and fuse the device image of the monitoring device with the real-time captured image to determine the target image corresponding to the monitoring device. It calculates the similarity between the target image of each monitoring device and the standard normal image to perform anomaly detection on each monitoring device. It can detect monitoring devices through multi-dimensional data, thereby improving the accuracy of monitoring device detection.

[0102] Optionally, the device image generation module 302 includes:

[0103] The matrix generation unit is used to generate an attribute matrix based on the parameter values ​​of parameter items in the equipment operation information of the monitoring equipment.

[0104] The curve data generation unit is used to generate curve data based on the changes in parameter values ​​of parameter items in the equipment operation information of the monitoring equipment.

[0105] The identifier generation unit is used to generate fault identifier data based on the fault level of the parameter value in the equipment operation information of the monitoring equipment.

[0106] The data normalization unit is used to normalize attribute matrices, curve data, and fault identification data to the same numerical range space.

[0107] The data stitching unit is used to stitch the normalized attribute matrix, curve data, and fault identification data on the channel to obtain the equipment image.

[0108] Optional, matrix generating unit, specifically used for:

[0109] For each parameter item of the monitoring equipment, determine at least one parameter value and attribute location area corresponding to the parameter item;

[0110] Determine the position of at least one element based on the attribute position area;

[0111] By associating each parameter value with the position of each element, the matrix position corresponding to each parameter value is determined.

[0112] The attribute matrix is ​​determined based on the values ​​of each parameter and the corresponding matrix positions.

[0113] Optional, curve data generation unit, specifically used for:

[0114] For each parameter item of the monitoring device, obtain the curve area corresponding to the parameter item and at least one parameter value corresponding to the parameter item. The parameter value includes the sampling time and the sampling value corresponding to the sampling time.

[0115] Based on the curve region corresponding to the parameter item and the sampling time corresponding to each parameter value, determine the horizontal coordinate position of the curve corresponding to each parameter value;

[0116] Based on the curve region corresponding to the parameter item and the sampled value corresponding to each parameter value, determine the ordinate position of the curve corresponding to each parameter value;

[0117] The curve data is determined based on the x-coordinate and y-coordinate positions of the curves corresponding to each parameter value.

[0118] Optional, the identifier generation unit is specifically used for:

[0119] Based on preset rules, fault detection is performed on the parameter values ​​of the parameter items in the equipment operation information of the monitoring equipment to obtain the fault type and the corresponding fault level;

[0120] Determine the corresponding fault pattern identifier based on the fault type and fault level;

[0121] A fault pattern identifier is generated at the corresponding position of the parameter item in the equipment operation information of the monitoring equipment.

[0122] Optionally, the image fusion module 304 is specifically used for:

[0123] Get the preset pixel threshold;

[0124] The real-time captured image is binarized according to a preset pixel threshold to determine the binary image;

[0125] The target image corresponding to the monitoring device is determined by adding the pixel value of each pixel in the binary image to the pixel value of the corresponding pixel in the device image.

[0126] Optionally, the device image generation module 302 is also specifically used for:

[0127] Based on the parameter values, parameter value changes, and fault levels of the parameters in the equipment operation information of the monitoring equipment, the corresponding three-dimensional data of the monitoring equipment is generated and mapped into an equipment image. Then, incremental data of the target equipment's operation information is obtained.

[0128] Determine the target channel based on incremental data;

[0129] The data on the target channel is updated based on the incremental data and its corresponding weights.

[0130] Update the device image based on the updated data from the target channel;

[0131] The updated device image of the target device and the real-time captured image are fused together to determine the target image corresponding to the target device;

[0132] Calculate the similarity between the target image of the target device and the standard normal image to perform anomaly detection on the target device.

[0133] Example 4

[0134] Figure 4 A schematic diagram of the structure of a monitoring device detection device 400 that can be used to implement an embodiment of the present invention is shown.

[0135] like Figure 4 As shown, the monitoring device detection device 400 includes at least one processor 401 and a memory, such as a read-only memory (ROM) 402 or a random access memory (RAM) 403, communicatively connected to the at least one processor 401. The memory stores computer programs executable by the at least one processor. The processor 401 can perform various appropriate actions and processes based on the computer program stored in the ROM 402 or loaded into the RAM 403 from the storage unit 408. The RAM 403 can also store various programs and data required for the operation of the monitoring device detection device 400. The processor 401, ROM 402, and RAM 403 are interconnected via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0136] Multiple components in the monitoring equipment detection device 400 are connected to the I / O interface 405, including: an input unit 406, such as a keyboard or mouse; an output unit 407, such as various types of displays or speakers; a storage unit 408, such as a hard disk or optical disk; and a communication unit 409, such as a network interface card (NIC), modem, or wireless transceiver. The communication unit 409 allows the monitoring equipment detection device 400 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0137] Processor 401 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 401 performs the various methods and processes described above, such as monitoring device detection methods.

[0138] In some embodiments, the monitoring device detection method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on the monitoring device detection device 400 via ROM 402 and / or communication unit 409. When the computer program is loaded into RAM 403 and executed by processor 401, one or more steps of the monitoring device detection method described above may be performed. Alternatively, in other embodiments, processor 401 may be configured to perform the monitoring device detection method by any other suitable means (e.g., by means of firmware).

[0139] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0140] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0141] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0142] To provide user interaction, the systems and techniques described herein can be implemented on a monitoring device detection apparatus, which includes: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the monitoring device detection apparatus. Other types of devices can also be used to provide user interaction; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0143] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0144] A computing system can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system. It addresses the shortcomings of traditional physical hosts and VPS (Virtual Private Server) services, such as high management difficulty and weak business scalability.

[0145] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0146] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for detecting monitoring equipment, characterized in that, The method includes: Obtain at least one monitoring device and the corresponding device operation information for each monitoring device; For each of the monitoring devices, based on the parameter values, parameter value changes, and fault levels of the parameter values ​​in the device operation information, three-dimensional data corresponding to the monitoring device is generated and mapped into a device image. Acquire real-time images captured by the monitoring device; The device image and real-time captured image of the monitoring device are fused together to determine the target image corresponding to the monitoring device; Calculate the similarity between the target image and the standard normal image of each monitoring device, and perform anomaly detection on each monitoring device.

2. The method according to claim 1, characterized in that, The step of generating 3D data corresponding to the monitoring device based on the device operation information of the monitoring device and mapping it into a device image includes: Generate an attribute matrix based on the parameter values ​​of the parameter items in the device operation information of the monitoring device; Curve data is generated based on the changes in parameter values ​​of parameter items in the equipment operation information of the monitoring equipment; Fault identification data is generated based on the fault level of the parameter values ​​in the equipment operation information of the monitoring equipment. The attribute matrix, the curve data, and the fault identification data are normalized to the same numerical range space; The normalized attribute matrix, the curve data, and the fault identification data are stitched together on the channel to obtain the device image.

3. The method according to claim 2, characterized in that, The step of generating an attribute matrix based on the parameter values ​​of parameter items in the device operation information of the monitoring device includes: For each parameter item of the monitoring device, at least one parameter value and attribute location area corresponding to the parameter item are determined based on the parameter item; Based on the attribute location region, determine at least one element position; By associating each parameter value corresponding to the parameter item with each element position, the matrix position corresponding to each parameter value is determined. The attribute matrix is ​​determined based on each parameter value and the matrix position corresponding to each parameter value.

4. The method according to claim 2, characterized in that, The step of generating curve data based on the parameter value changes in the device operation information of the monitoring device includes: For each parameter item of the monitoring device, obtain the curve region corresponding to the parameter item and at least one parameter value corresponding to the parameter item, wherein the parameter value includes the sampling time and the sampling value corresponding to the sampling time; Based on the curve region corresponding to the parameter item and the sampling time corresponding to each parameter value, determine the horizontal coordinate position of the curve corresponding to each parameter value; Based on the curve region corresponding to the parameter item and the sampled value corresponding to each parameter value, determine the curve ordinate position corresponding to each parameter value; The curve data is determined based on the horizontal and vertical coordinate positions of the curves corresponding to each parameter value.

5. The method according to claim 2, characterized in that, The step of generating fault identification data based on the fault level of the parameter values ​​in the equipment operation information of the monitoring equipment includes: According to preset rules, the parameter values ​​of the parameter items in the equipment operation information of the monitoring equipment are used to detect faults, and the fault type and corresponding fault level are obtained. Determine the corresponding fault pattern identifier based on the fault type and fault level; The fault pattern identifier is generated at the corresponding position of the parameter item in the device operation information of the monitoring device.

6. The method according to claim 1, characterized in that, The step of fusing the device image and real-time captured image of the monitoring device to determine the target image corresponding to the monitoring device includes: Get the preset pixel threshold; The real-time captured image is binarized according to the preset pixel threshold to determine a binary image; The target image corresponding to the monitoring device is determined by adding the pixel value of each pixel in the binary image to the pixel value of the corresponding pixel in the device image.

7. The method according to claim 2, characterized in that, After generating 3D data corresponding to the monitoring device and mapping it into a device image based on the parameter values, parameter value changes, and fault levels of the parameter values ​​in the device operation information of the monitoring device, the process further includes: Acquire incremental data of the target device's operational information; Determine the target channel based on incremental data; The data on the target channel is updated based on the incremental data and the weights corresponding to the incremental data; Update the device image based on the updated data from the target channel; The updated device image of the target device and the real-time captured image are fused together to determine the target image corresponding to the target device; Calculate the similarity between the target image of the target device and a standard normal image, and perform anomaly detection on the target device.

8. A detection device for monitoring equipment, characterized in that, The device includes: The information acquisition module is used to acquire at least one monitoring device and the device operation information corresponding to each monitoring device; The device image generation module is used to generate three-dimensional data corresponding to each monitoring device based on the parameter values, parameter value change data, and fault level of the parameter values ​​in the device operation information of the monitoring device, and map them into a device image. An image acquisition module is used to acquire real-time images captured by the monitoring device; An image fusion module is used to fuse the device image and real-time captured image of the monitoring device to determine the target image corresponding to the monitoring device. An anomaly detection module is used to calculate the similarity between the target image and the standard normal image of each monitoring device, and to perform anomaly detection on each monitoring device.

9. A monitoring equipment detection device, characterized in that, The monitoring equipment detection equipment includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the monitoring device detection method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the monitoring device detection method according to any one of claims 1-7.

Images