Resource processing method and apparatus, computer device, and storage medium

Abstract

The application relates to a resource processing method and device and a computer device. The method comprises the following steps: acquiring a target device area image, identifying the target device area image, obtaining initial tree information, device line information and device node information corresponding to the target device area, acquiring a tree position influence parameter, performing device line anomaly detection based on the tree position influence parameter, the initial tree information and the device line information, obtaining a device line anomaly degree, performing device node anomaly detection based on the device line anomaly degree and the device node information, obtaining a device node anomaly degree, determining a region anomaly degree corresponding to the target device area image based on the device node anomaly degree, and updating the initial tree information when the region anomaly degree exceeds a preset anomaly threshold to obtain target tree information. The method can improve anomaly detection accuracy and improve the accuracy of tree resource management.

Description

Technical Field

[0001] This application relates to the field of data analysis technology, and in particular to a resource processing method, apparatus, computer equipment, storage medium, and computer program product. Background Technology

[0002] With the development of modern society, resource conflicts can occur, such as power transmission equipment failures or building damage caused by fallen trees during storms. Therefore, it is necessary to conduct advance detection of abnormal situations such as power transmission equipment failures or building damage, and manage vegetation resources based on the detection results to prevent such anomalies from occurring. Vegetation resources include, for example, tree resources.

[0003] Currently, abnormal situations such as power transmission equipment failures or building damage are typically detected according to pre-set detection rules. However, relying on pre-set rules for detecting abnormalities can easily reduce the accuracy of anomaly detection, thereby reducing the accuracy of vegetation resource management and resulting in the waste of vegetation resources. Summary of the Invention

[0004] Therefore, it is necessary to provide a resource processing method, apparatus, computer equipment, computer-readable storage medium, and computer program product that can improve the accuracy of anomaly detection in response to the above-mentioned technical problems.

[0005] Firstly, this application provides a resource processing method. The method includes:

[0006] Acquire images of the target device area, identify the target device area images, and obtain the initial tree information, device line information, and device node information corresponding to the target device area;

[0007] Obtain tree location impact parameters, and perform equipment line anomaly detection based on tree location impact parameters, initial tree information, and equipment line information to obtain the degree of equipment line anomaly.

[0008] Based on the degree of equipment line anomaly and equipment node information, equipment node anomaly detection is performed to obtain the degree of equipment node anomaly.

[0009] The anomaly level of the target device area image is determined based on the anomaly level of the device node. When the anomaly level of the area exceeds the preset anomaly threshold, the initial tree information is updated to obtain the target tree information.

[0010] Secondly, this application also provides a resource processing apparatus. The apparatus includes:

[0011] The identification module is used to acquire images of the target device area, identify the target device area images, and obtain the initial tree information, device line information, and device node information corresponding to the target device area.

[0012] The line detection module is used to obtain tree location impact parameters, and based on the tree location impact parameters, initial tree information and equipment line information, it performs equipment line anomaly detection to obtain the degree of equipment line anomaly.

[0013] The node detection module is used to detect device node anomalies based on the degree of device line anomalies and device node information, and to obtain the degree of device node anomalies.

[0014] The anomaly detection module is used to determine the degree of anomaly in the target device area image based on the degree of anomaly of the device node. When the degree of anomaly in the area exceeds the preset anomaly threshold, the initial tree information is updated to obtain the target tree information.

[0015] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:

[0016] Acquire images of the target device area, identify the target device area images, and obtain the initial tree information, device line information, and device node information corresponding to the target device area;

[0017] Obtain tree location impact parameters, and perform equipment line anomaly detection based on tree location impact parameters, initial tree information, and equipment line information to obtain the degree of equipment line anomaly.

[0018] Based on the degree of equipment line anomaly and equipment node information, equipment node anomaly detection is performed to obtain the degree of equipment node anomaly.

[0019] The anomaly level of the target device area image is determined based on the anomaly level of the device node. When the anomaly level of the area exceeds the preset anomaly threshold, the initial tree information is updated to obtain the target tree information.

[0020] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:

[0021] Acquire images of the target device area, identify the target device area images, and obtain the initial tree information, device line information, and device node information corresponding to the target device area;

[0022] Obtain tree location impact parameters, and perform equipment line anomaly detection based on tree location impact parameters, initial tree information, and equipment line information to obtain the degree of equipment line anomaly.

[0023] Based on the degree of equipment line anomaly and equipment node information, equipment node anomaly detection is performed to obtain the degree of equipment node anomaly.

[0024] The anomaly level of the target device area image is determined based on the anomaly level of the device node. When the anomaly level of the area exceeds the preset anomaly threshold, the initial tree information is updated to obtain the target tree information.

[0025] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, performs the following steps:

[0026] Acquire images of the target device area, identify the target device area images, and obtain the initial tree information, device line information, and device node information corresponding to the target device area;

[0027] Obtain tree location impact parameters, and perform equipment line anomaly detection based on tree location impact parameters, initial tree information, and equipment line information to obtain the degree of equipment line anomaly.

[0028] Based on the degree of equipment line anomaly and equipment node information, equipment node anomaly detection is performed to obtain the degree of equipment node anomaly.

[0029] The anomaly level of the target device area image is determined based on the anomaly level of the device node. When the anomaly level of the area exceeds the preset anomaly threshold, the initial tree information is updated to obtain the target tree information.

[0030] The aforementioned resource processing method, apparatus, computer equipment, storage medium, and computer program product obtain initial tree information, equipment line information, and equipment node information corresponding to the target equipment area by identifying the target equipment area. Based on tree location influence parameters, initial tree information, and equipment line information, they perform equipment line anomaly detection to determine the degree of equipment line anomaly. Then, based on the degree of equipment line anomaly and equipment node information, they perform equipment node anomaly detection to determine the impact of the degree of equipment line anomaly on the equipment nodes, thus obtaining the degree of equipment node anomaly. By using tree location influence parameters, initial tree information, and equipment line information to detect the degree of equipment node anomaly, the accuracy of the degree of equipment node anomaly is improved. Determining the degree of regional anomaly corresponding to the target equipment area image based on the degree of equipment node anomaly improves the accuracy of the degree of regional anomaly. Furthermore, when the degree of regional anomaly exceeds a preset anomaly threshold, it is determined that the target equipment area corresponding to the target equipment area image has an anomaly, enabling timely updates of the initial tree information to obtain the target tree information. This improves the accuracy of tree resource management and saves tree resources. Attached Figure Description

[0031] Figure 1This is an application environment diagram of a resource processing method in one embodiment;

[0032] Figure 2 This is a flowchart illustrating a resource processing method in one embodiment;

[0033] Figure 3 This is a schematic diagram of the device circuit anomaly detection process in one embodiment;

[0034] Figure 4 This is a schematic diagram illustrating the abnormal angle range of a target tree in one embodiment;

[0035] Figure 5 This is a schematic diagram illustrating the abnormal height range of a target tree in one embodiment;

[0036] Figure 6 This is a schematic diagram of a device network in one embodiment;

[0037] Figure 7 This is a structural block diagram of a resource processing device in one embodiment;

[0038] Figure 8 This is an internal structural diagram of a computer device in one embodiment;

[0039] Figure 9 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0040] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0041] The resource processing method provided in this application embodiment can be applied to, for example, Figure 1In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104 or placed on a cloud or other network server. Server 104 can acquire an image of the target device area through terminal 102, identify the target device area image, and obtain the initial tree information, device line information, and device node information corresponding to the target device area. Server 104 acquires tree location influence parameters, performs device line anomaly detection based on the tree location influence parameters, initial tree information, and device line information, and obtains the degree of device line anomaly. Server 104 performs device node anomaly detection based on the degree of device line anomaly and device node information, and obtains the degree of device node anomaly. Server 104 determines the degree of regional anomaly corresponding to the target device area image based on the degree of device node anomaly. When the degree of regional anomaly exceeds a preset anomaly threshold, the initial tree information is updated to obtain the target tree information, which the server can then return to terminal 102. The terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, and smart in-vehicle systems. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted devices. The server 104 can be implemented using a standalone server or a server cluster consisting of multiple servers.

[0042] In one embodiment, such as Figure 2 As shown, a resource processing method is provided. This embodiment illustrates the method applied to a server. It is understood that this method can also be applied to a terminal, and further to a system including both a terminal and a server, and is implemented through interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0043] Step 202: Obtain the target device area image, identify the target device area image, and obtain the initial tree information, device line information, and device node information corresponding to the target device area.

[0044] The target device area image refers to the graphic acquired based on the target device area, which can be a 3D image. The target device area refers to the area where the device is located and anomaly detection is to be performed, including the device area and the tree area. The device can be power transmission equipment, communication equipment, etc. The device area can be a device network area, which consists of various device nodes and device lines. Initial tree information refers to the basic attribute information related to trees in the target device area, including tree density, number of trees, tree location, and tree height. Device line information refers to information characterizing the device lines, which can be physical information related to the device lines. Device node information refers to information characterizing the device nodes.

[0045] Specifically, a 3D image acquisition device is deployed in the target device area. This device acquires images of the target device area and sends them to the server. The server identifies the device and tree areas within the target device area image, obtaining their corresponding 3D information. Based on this 3D information, the server determines initial tree information, device routing information, and device node information.

[0046] Step 204: Obtain tree location impact parameters, and perform equipment line anomaly detection based on tree location impact parameters, initial tree information, and equipment line information to obtain the degree of equipment line anomaly.

[0047] Among them, the tree location influence parameter refers to the parameter that represents the force that causes changes in the tree's location. The equipment line anomaly degree refers to the degree to which the equipment line's function is likely to malfunction.

[0048] Specifically, the parameter influencing tree location can be wind parameters. The server divides the wind detection areas for each device line based on historical wind parameters; this division can be done horizontally or vertically. Wind sensors are deployed in each detection area, and these sensors monitor wind parameters in real time. The wind sensors calculate the average wind parameters over a preset time period as the tree location influence parameter, and this parameter is then sent to the server.

[0049] The server obtains the tree impact parameters, equipment line information, and tree information corresponding to each equipment line from the initial tree information. This represents the basic attribute information related to trees within the preset range of the equipment line. Then, based on the tree impact parameters and tree information, it calculates the probability of tree position changes. Finally, based on the probability of tree position changes and equipment line information, it calculates the degree of impact of tree position changes on the equipment line, thus obtaining the abnormality level of each equipment line.

[0050] Step 206: Based on the degree of equipment line anomaly and equipment node information, perform equipment node anomaly detection to obtain the degree of equipment node anomaly.

[0051] Among them, the degree of device node anomaly refers to the degree to which the function of a device node may malfunction.

[0052] Specifically, the server determines the device nodes corresponding to each device line based on the device line information and device node information. The server obtains the anomaly level of each device line. Based on the anomaly level of the device line, the server calculates the anomaly level of the corresponding device node, thus obtaining the anomaly level of each device node.

[0053] Step 208: Determine the degree of regional anomaly corresponding to the target device area image based on the degree of anomaly of the device node. When the degree of regional anomaly exceeds the preset anomaly threshold, update the initial tree information to obtain the target tree information.

[0054] Among these, the regional anomaly level refers to the probability of an overall functional malfunction of the device network in the target device area. The preset anomaly threshold is a pre-set threshold for the regional anomaly level, used to determine whether an anomaly has occurred in the target device area. Target tree information refers to the physical information related to trees after the initial tree information has been updated.

[0055] Specifically, the server obtains the anomaly level and weight information of each device node, and performs a weighted calculation on the anomaly level of each device node based on the weight information of each device node to obtain the region anomaly level corresponding to the target device image region.

[0056] Then, when the server detects that the degree of anomaly in a region exceeds the preset anomaly threshold, it determines the possibility that there are trees in the target device region that may cause the device to malfunction. Based on the degree of anomaly in the region, the server calculates tree information update parameters, which may be the number of trees to be cleared. The server updates the tree density parameters in the initial tree information based on the tree information update parameters to obtain the target tree information.

[0057] The aforementioned resource processing method identifies the target device region to obtain initial tree information, equipment line information, and equipment node information corresponding to that region. Based on tree location influence parameters, initial tree information, and equipment line information, it performs equipment line anomaly detection to determine the degree of anomaly. Then, based on the degree of anomaly and the equipment node information, it performs equipment node anomaly detection to determine the impact of the equipment line anomaly on the equipment nodes, thus obtaining the degree of equipment node anomaly. By using tree location influence parameters, initial tree information, and equipment line information to detect the degree of equipment node anomaly, the accuracy of the degree of equipment node anomaly is improved. Determining the degree of regional anomaly corresponding to the target device region image based on the degree of equipment node anomaly improves the accuracy of regional anomaly determination. Furthermore, when the regional anomaly degree exceeds a preset anomaly threshold, it is determined that the target device region corresponding to the target device region image has an anomaly, allowing for timely updates of the initial tree information to obtain the target tree information. This improves the accuracy of tree resource management and conserves tree resources.

[0058] In one embodiment, such as Figure 3 The diagram illustrates a process for detecting equipment line anomalies. Step 204 involves obtaining tree location influence parameters, and based on these parameters, initial tree information, and equipment line information, performing equipment line anomaly detection to determine the degree of anomaly, including:

[0059] Step 302: Calculate the probability of tree location anomalies using tree location influence parameters;

[0060] Step 304: Use tree location influence parameters, initial tree information and equipment line information to detect tree angle anomalies and obtain the probability of tree angle anomalies;

[0061] Step 306: Use the tree attribute information, equipment line information and tree angle anomaly probability from the initial tree information to perform tree attribute anomaly detection and obtain the tree attribute anomaly probability.

[0062] Step 308: Calculate the degree of equipment line anomaly by multiplying the probability of abnormal tree location and the probability of abnormal tree attribute in the line equipment information.

[0063] Among these, "Tree Location Anomaly Probability" refers to the possibility of a tree's location changing. "Tree Angle Anomaly Probability" refers to the possibility of a tree's angle falling within the abnormal angle range. "Tree Angle" refers to the angle at which a tree's location changes. "Abnormal Tree Angle Range" refers to the range of angles within which a tree can reach the equipment wiring after its location changes. "Tree Attribute Anomaly Probability" refers to the possibility of a tree's height attribute falling within the abnormal height range. "Abnormal Tree Height Range" refers to the range of tree heights within the target angle range within which a tree can reach the equipment wiring after its location changes. "Equipment Width" refers to the length of the equipment wiring between equipment nodes.

[0064] Specifically, the server obtains the tree location impact parameters corresponding to each device line, device line information, and tree information corresponding to each device line from the initial tree information. The tree location impact parameters can be the average wind speed and wind direction within a preset time period.

[0065] The server calculates the probability of tree location anomalies based on the average wind speed in the tree impact parameters, representing the likelihood of a tree falling at different wind speeds. Then, the server calculates the tree angle based on the wind direction in the tree location impact parameters, representing the angle at which the tree will fall. The server uses tree information and equipment line information to calculate the target tree angle range and the probability of the tree angle falling within that range, thus obtaining the probability of tree angle anomalies.

[0066] The server uses initial tree information and device line information to calculate the target tree height range, and calculates the tree attribute anomaly probability based on the probability of tree angle anomalies and the tree height in the tree attribute information. This represents the probability that the tree angle is within the target angle range and the tree height is within the target tree height range when the tree position changes.

[0067] The server obtains the device line length, the probability of tree location anomalies, and the probability of tree attribute anomalies corresponding to each device line, multiplies them, and calculates the degree of device line anomaly.

[0068] The server can use tree impact parameters and initial tree information to calculate the probability of tree location anomalies according to formula (1), which represents the probability of a tree falling due to wind speed. Formula (1) is shown below:

[0069]

[0070] Among them, K V This represents the probability of a tree falling down relative to the average wind speed V. w The correspondence between them; K N γ represents the probability of tree collapse per unit area; γ represents the preset tree collapse rate, which is obtained based on historical tree collapse rate statistics; ρ represents the tree planting density in the initial tree information; P(hT ) represents the distribution function of tree height following a normal distribution; h T Indicates tree height; K V (V w )*K N This indicates the probability of an abnormal tree location, or it can be expressed as a height reaching h. T The probability of trees falling down.

[0071] In this embodiment, by using various parameters to calculate the probability of abnormal tree location, abnormal tree angle, and abnormal tree attributes, the various probabilities of tree collapse causing equipment line failure are determined. Therefore, by calculating the product of equipment line length, the probability of abnormal tree location, and the probability of abnormal tree attributes, a more accurate degree of equipment line anomaly is obtained. Furthermore, the equipment line anomaly detection process is optimized, thereby improving the efficiency of equipment line anomaly detection.

[0072] In one embodiment, step 304 involves using tree location influence parameters, initial tree information, and equipment line information to detect tree angle anomalies and determine the probability of tree angle anomalies, including:

[0073] The abnormal angle range of the target tree is calculated using the target tree height and target tree distance from the initial tree information and the line height from the equipment line information.

[0074] The probability of tree angle anomalies is calculated by using the range of abnormal angles of the target tree and the parameters affecting the tree position.

[0075] Here, "target tree height" refers to the height of the target tree, and "target tree" refers to the tree to be inspected. "Target tree distance" refers to the horizontal distance between the target tree and the equipment wiring. "Target tree abnormal angle range" refers to the range of angles within which the target tree can contact the equipment wiring after its position changes.

[0076] Specifically, the server obtains the wind direction from the tree location influence parameters and the angle between the wind direction and the normal vector of the equipment line, which is taken as the line angle. The server can pre-calculate the correspondence between tree angle and wind direction using the wind direction and line angle, and calculate the probability that the tree angle corresponding to the target tree is the same as the wind direction based on this correspondence. The server can use formula (2) to perform the calculation. Formula (2) is shown below:

[0077]

[0078] Among them, P θ (θ) represents the probability that the angle of the target tree is the same as the wind direction; θ represents the wind direction; Δθ represents the line angle.

[0079] The server identifies the target tree within the tree area corresponding to the device line. The target tree can be the tallest tree within a preset range of the device line, or a tree whose height exceeds a preset height threshold. Then, the server retrieves the tree information corresponding to the device line from the initial tree information, and determines the target tree height and distance from the target tree within this information. Finally, the server obtains the line height from the device line information.

[0080] The server can use the target tree height, target tree distance, and line height to calculate the range of abnormal tree angles and obtain the range of abnormal tree angles.

[0081] The abnormal angle range of the target tree can be used It means that X L h represents the distance to the target tree. L Indicates the height of the line. For example... Figure 4 As shown, this diagram illustrates the abnormal angle range of a target tree: angle α in the diagram represents... Angle β represents

[0082] The server uses the range of abnormal angles of the target tree and the probability that the tree angle and wind direction are the same to calculate the probability of abnormal tree angle, which represents the probability that the target tree will fall in the direction of the equipment line. The calculation of the probability of abnormal tree angle is shown in formula (3):

[0083]

[0084] In this embodiment, by calculating the range of abnormal angles of the target tree and the probability of abnormal tree angles, the probability of tree collapse causing faults to equipment lines is determined, so that the probability of abnormal tree attributes can be directly used to calculate the probability of abnormal tree attributes in the future, thereby improving the calculation efficiency of the probability of abnormal tree attributes.

[0085] In one embodiment, step 306 involves using tree attribute information, equipment line information, and the probability of tree angle anomalies from the initial tree information to perform tree attribute anomaly detection, obtaining the probability of tree attribute anomalies, including:

[0086] The range of abnormal tree attributes is calculated using the target tree height and target tree distance from the initial tree information, and the line height from the equipment line information, to obtain the range of abnormal tree attributes.

[0087] The probability of tree attribute anomalies is calculated by using the range of abnormal attributes of the target tree, the probability of abnormal tree angles, and tree attribute information.

[0088] Among them, the abnormal attribute range of the target tree refers to the abnormal height range of the tree corresponding to the target tree, that is, the height range of the target tree that can reach the equipment line after the position of the target tree changes within the target angle range.

[0089] Specifically, the server can use the target tree height, target tree distance, and line height to calculate the range of abnormal tree attributes, thus obtaining the range of abnormal attributes for the target tree. The range of abnormal tree attributes can be the range of abnormal tree heights corresponding to the target tree, which can be used... It means that h Tmax Indicates the maximum tree height. For example... Figure 5 The diagram illustrates the range of abnormal tree heights for a target tree: the dashed line d in the diagram represents the range of abnormal tree heights.

[0090] The server obtains the tree information corresponding to the device line from the initial tree information, and obtains the tree attribute information corresponding to the target tree from the tree information corresponding to the device line. This can be a distribution function corresponding to the height of the target tree, representing the probability of the existence of the height of the target tree.

[0091] The server uses the range of abnormal attributes of the target tree, the probability of abnormal tree angles, and tree attribute information to calculate the probability of abnormal tree attributes, thus representing the probability that the target tree's collapse will cause equipment line failure. The calculation of the probability of abnormal tree attributes is shown in formula (4):

[0092]

[0093] In one specific embodiment, the degree of equipment line abnormality at a certain location of the equipment line can be calculated in advance using tree height, average wind speed, horizontal distance between trees and equipment lines, and the correspondence between tree angle and wind direction. The calculation formula is shown in formula (5):

[0094]

[0095] Where y represents a specific location on a certain equipment line; h L (y) represents the height of the line corresponding to position y on the equipment line; y max This represents the line length, and y∈[0,y]. max The calculation expression for the degree of equipment line abnormality of the entire equipment line is shown in formula (6):

[0096]

[0097] Among them, R i Indicates the degree of abnormality of the equipment line corresponding to the i-th equipment line; y" max Indicates y max The line length after normalization.

[0098] Due to λ TF (y) is only related to the line height at position y, and the other parameters remain unchanged. For the sake of simplifying the calculation, the line height of the entire equipment line is assumed to be fixed. The calculation expression for the abnormality of the entire equipment line is shown in formula (7):

[0099]

[0100] Among them, h Tmax This indicates the maximum tree height.

[0101] The server obtains the line length corresponding to each line device, and normalizes it based on the probability of abnormal tree location and the probability of abnormal tree attribute for each line device to obtain the processed line length. Then, the server multiplies the processed line length, the probability of abnormal tree location, and the probability of abnormal tree attribute to calculate the abnormality level of each line device.

[0102] In this embodiment, by calculating the range of abnormal attributes of the target tree and the probability of abnormal tree attributes of the target tree based on the tree attribute information, the impact of the collapse of trees of different heights on the functional abnormality of the equipment line can be accumulated one by one according to the proportion of trees of different heights. The proportion of trees of different heights that cause equipment line failure when trees fall in the direction of the equipment line within a unit area is determined, thereby improving the accuracy of equipment line abnormality detection.

[0103] In one embodiment, the device node information includes the identifiers of each device node; step 206, based on the degree of device line anomaly and the device node information, performs device node anomaly detection to obtain the degree of device node anomaly, including:

[0104] Determine the current device node identifier and the associated device node identifier of the current device node from each device node identifier;

[0105] The current line identifier is determined from the equipment line information based on the current device node identifier and the associated device node identifier;

[0106] Obtain the anomaly level of the associated device node corresponding to the associated device node identifier and the anomaly level of the current line corresponding to the current line identifier;

[0107] Calculate the anomaly level of the device node corresponding to the current device node identifier based on the anomaly level of the associated device node and the anomaly level of the current line;

[0108] Iterate through each device node identifier to obtain the anomaly level of the device node corresponding to each device node identifier.

[0109] Here, "current device node" refers to the device node currently undergoing anomaly detection. "Associated device node" refers to the device node connected to the current device node via a device line.

[0110] Specifically, the server determines the current device node identifier and the associated device node identifier from each device node identifier. The associated device node can be an upstream device node of the current device node. Then, based on the current device node identifier and the associated device node identifier, the server determines the current line identifier from the device line information. Finally, the server obtains the anomaly level of the associated device node corresponding to the associated device node identifier and the anomaly level of the current line corresponding to the current line identifier.

[0111] The server calculates the anomaly level of the current device node identifier based on the anomaly levels of associated device nodes and the anomaly level of the current line. Then, the server iterates through each device node identifier and its associated device nodes to calculate the anomaly level of each device node.

[0112] In one specific embodiment, such as Figure 6 The diagram illustrates a device network, where numbers represent device nodes. Device nodes and device lines form the device network, which can be a tree-like structure. The root node in the device network can be a power supply node, used to transmit power to all device nodes. The failure probability P of the device node corresponding to the root node is then determined. s =0, the failure probability P of other device node n n The failure probability P of its adjacent upstream device node prd can be used as a reference. prd The probability of line failure R between device lines i and two device nodes. i The calculation is performed using the formula shown in formula (8):

[0113] P n =1-(1-P) prd )*(1-R i ) Formula (8)

[0114] For example, device node 3 is the current device node, and the upstream device node 1 of device node 3 is the device node 1 corresponding to the root node. The failure probability P of the device node 1 corresponding to the root node is... s =0, the probability of line failure between device node 1 and device node 3 is R1, then the probability of failure of the current device node is P3 = 1 - (1 - P s )*(1-Ri )=1-(1-0)*(1-R i ) = R i This is used to calculate the node failure probability for each device node in the device network.

[0115] In this embodiment, the accuracy of the regional anomaly level is improved by calculating the regional anomaly level based on the weight information of the device nodes. This allows the area where trees are prioritized for clearing to be determined based on the anomaly level of each device node when the regional anomaly level exceeds a preset anomaly threshold, thereby improving the accuracy of the area to be cleared and saving tree resources.

[0116] In one embodiment, step 208, determining the degree of region anomaly corresponding to the target device region image based on the degree of device node anomaly, includes:

[0117] Obtain the weight information corresponding to the anomaly level of the device nodes, and perform weighted calculation on the anomaly level of the device nodes based on the weight information to obtain the anomaly level of the region corresponding to the target device region image.

[0118] Among them, weight information refers to parameters that characterize the different levels of importance of device nodes.

[0119] Specifically, the server obtains the weight information and anomaly level of each device node. Based on the weight information of each device node, the anomaly level of each device node is weighted and calculated to obtain the anomaly level of the target device region image. The weighted calculation formula is shown in formula (9):

[0120]

[0121] Here, risk represents the degree of anomaly in the region. λ n This indicates the weight information corresponding to the device node.

[0122] Then the server determines whether the degree of anomaly in the area exceeds the preset anomaly threshold. When the degree of anomaly in the area exceeds the preset anomaly threshold, the degree of anomaly in the area is sent to the management terminal. The server receives the tree information update parameters returned by the management terminal. The tree information update parameters can be the number of trees to be cleared. The server updates the tree density in the initial tree information according to the tree information update parameters to obtain the target tree information.

[0123] In one specific embodiment, the server can obtain tree clearing condition parameters, representing the conditions required for clearing trees, such as the clearing cost of a single tree and the tree clearing time. The server can pre-establish a tree clearing objective function using formula (9) and the tree clearing condition parameters, representing the objective function that minimizes the overall equipment failure probability risk and tree felling cost of the target equipment area. The number of trees to be cleared when the overall equipment failure probability risk and tree felling cost are minimized can be calculated using the objective function, as shown in formula (10):

[0124] min(risk+mΔρ) formula (10)

[0125] Where m represents the tree clearing condition parameter; Δρ represents the number of trees to be cleared.

[0126] Specifically, formula (10) can be derived from formulas (7) to (9), where κ in formula (7) N The expression can be obtained from formula (1). The probability of tree collapse is related to the tree density ρ. Therefore, the tree density relationship can be preset as ρ = ρ0 + Δρ, where ρ0 represents the target tree density in the target equipment area after tree clearing. By presetting the specific value of ρ0, and then replacing the parameter of ρ in formula (1) with ρ0 + Δρ, we get the parameter-replaced formula (7). After deriving formulas (7) to (9), we get the objective function with Δρ as the variable, i.e., formula (10). Then, we can use the solver Gurobi to solve it. During the solution process, by adjusting the value of ρ0, we get the optimal calculation expression for Δρ. Then, the server stores the optimal calculation expression for Δρ.

[0127] In one specific embodiment, the resource processing method of this application can be used to process tree resources in an area where power equipment is located. The server acquires an image of the power equipment area sent by the terminal, identifies the image, and obtains initial tree information, power line information, tree influence parameters, and power equipment node information corresponding to the power equipment area. The initial tree information includes a pre-set ρ0. Then, the server uses the aforementioned parameters to calculate the tree information update parameter Δρ according to the optimal calculation expression for Δρ. The server then updates the tree density ρ in the initial tree information based on the tree information update parameter Δρ to obtain the target tree information. Finally, the server can select the power line area where trees should be cleared based on the line fault probability corresponding to the power line.

[0128] For example, by setting different unit tree felling costs, different optimal solutions with respect to Δρ can be obtained. The higher the felling cost, the fewer areas where trees can be removed. When the server detects that the unit tree felling cost exceeds a preset cost threshold, it selects to remove trees near a power line—that is, trees near the power line with the highest probability of failure.

[0129] As logging costs decrease, more and more areas become available for clearing, reducing the overall risk of power outages for electrical equipment. When the server detects that the cost of logging per unit of tree does not exceed a preset cost threshold, the server can choose an upstream line to process tree resources because the failure probability of upstream nodes affects the failure probability of downstream nodes.

[0130] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0131] Based on the same inventive concept, this application also provides a resource processing apparatus for implementing the resource processing method described above. The solution provided by this apparatus is similar to the implementation scheme described in the above method; therefore, the specific limitations in one or more resource processing apparatus embodiments provided below can be found in the limitations of the resource processing method described above, and will not be repeated here.

[0132] In one embodiment, such as Figure 7 As shown, a resource processing device 700 is provided, including: an identification module 702, a line detection module 704, a node detection module 706, and an anomaly judgment module 708, wherein:

[0133] The identification module 702 is used to acquire an image of the target device area, identify the image of the target device area, and obtain the initial tree information, device line information, and device node information corresponding to the target device area.

[0134] The line detection module 704 is used to obtain tree location influence parameters, and to perform equipment line anomaly detection based on tree location influence parameters, initial tree information and equipment line information to obtain the degree of equipment line anomaly.

[0135] The node detection module 706 is used to detect device node anomalies based on the degree of device line anomalies and device node information, and to obtain the degree of device node anomalies.

[0136] The anomaly detection module 708 is used to determine the degree of anomaly of the target device area image based on the degree of anomaly of the device node. When the degree of anomaly of the area exceeds the preset anomaly threshold, the initial tree information is updated to obtain the target tree information.

[0137] In one embodiment, the line detection module 704 includes:

[0138] The line anomaly calculation unit is used to calculate the probability of tree location anomalies using tree location influence parameters; to detect tree angle anomalies using tree location influence parameters, initial tree information, and equipment line information, and to obtain the probability of tree angle anomalies; to detect tree attribute anomalies using tree attribute information, equipment line information, and the probability of tree angle anomalies in the initial tree information, and to obtain the probability of tree attribute anomalies; and to calculate the degree of equipment line anomalies by multiplying the equipment line length, the probability of tree location anomalies, and the probability of tree attribute anomalies in the line equipment information.

[0139] In one embodiment, the line detection module 704 includes:

[0140] The angle anomaly calculation unit is used to calculate the range of abnormal tree angles using the target tree height and distance from the initial tree information and the line height from the equipment line information, to obtain the range of abnormal tree angles; and to calculate the probability of abnormal tree angles using the range of abnormal tree angles and tree position influence parameters, to obtain the probability of abnormal tree angles.

[0141] In one embodiment, the line detection module 704 includes:

[0142] The attribute anomaly calculation unit is used to calculate the range of abnormal tree attributes using the target tree height and distance from the initial tree information and the line height from the equipment line information, to obtain the range of abnormal tree attributes; and to calculate the probability of abnormal tree attributes using the range of abnormal tree attributes, the probability of abnormal tree angles, and the tree attribute information, to obtain the probability of abnormal tree attributes.

[0143] In one embodiment, the node detection module 706 includes:

[0144] The node anomaly calculation unit is used to determine the current device node identifier and the associated device node identifiers of the current device node from each device node identifier; determine the current line identifier from the device line information based on the current device node identifier and the associated device node identifiers; obtain the anomaly degree of the associated device node corresponding to the associated device node identifier and the anomaly degree of the current line corresponding to the current line identifier; calculate the anomaly degree of the device node corresponding to the current device node identifier based on the anomaly degree of the associated device node identifier and the anomaly degree of the current line; and traverse each device node identifier to obtain the anomaly degree of the device node corresponding to each device node identifier.

[0145] In one embodiment, the anomaly detection module 708 includes:

[0146] The regional anomaly calculation unit is used to obtain the weight information corresponding to the anomaly degree of the device node, and to perform weighted calculation on the anomaly degree of the device node based on the weight information to obtain the regional anomaly degree corresponding to the target device region image.

[0147] Each module in the aforementioned resource processing device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0148] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 8 As shown, this computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores images of the target device area. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements a resource processing method.

[0149] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 9As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a resource processing method. The display unit of the computer device is used to form a visually visible image. It can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0150] Those skilled in the art will understand that Figure 8-9 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0151] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0152] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0153] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0154] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data shall comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0155] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0156] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0157] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A resource processing method, characterized by, The method comprises: obtaining a target device area image, identifying the target device area image, obtaining initial tree information, device line information and device node information corresponding to the target device area image; obtaining a tree position influence parameter, performing device line anomaly detection based on the tree position influence parameter, the initial tree information and the device line information, and obtaining a device line anomaly degree; performing device node anomaly detection based on the device line anomaly degree and the device node information, and obtaining a device node anomaly degree; based on the device node anomaly degree, determining a region anomaly degree corresponding to the target device area image, when the region anomaly degree exceeds a preset anomaly threshold, updating the initial tree information to obtain target tree information; wherein, based on the tree position influence parameter, the initial tree information and the device line information, performing device line anomaly detection to obtain a device line anomaly degree, comprising: using the tree position influence parameter to calculate a tree position anomaly possibility; using the tree position influence parameter, the initial tree information and the device line information to perform tree angle anomaly detection to obtain a tree angle anomaly possibility; using tree attribute information in the initial tree information, the device line information and the tree angle anomaly possibility to perform tree attribute anomaly detection to obtain a tree attribute anomaly possibility; multiplying the tree position anomaly possibility and the tree attribute anomaly possibility to obtain a device line anomaly degree of a certain position of the device line; normalizing the device line length in the device line information, and determining the device line anomaly degree according to the normalized device line length and the device line anomaly degree at all positions of the device line.

2. The method of claim 1, wherein, The tree position influence parameter comprises a wind force parameter, and obtaining the tree position influence parameter comprises: dividing each device line into a wind force detection area according to historical wind force parameters; deploying a wind force sensor in each wind force detection area; real-time detecting a wind force parameter through the wind force sensor, and obtaining a tree position influence parameter by calculating an average value of the wind force parameter in a preset time period.

3. The method of claim 1, wherein, The tree angle anomaly detection using the tree position influence parameter, the initial tree information and the device line information to obtain a tree angle anomaly possibility comprises: using a target tree height in the initial tree information, a target tree distance in the initial tree information and a line height in the device line information to calculate a target tree abnormal angle range to obtain a target tree abnormal angle range; using the target tree abnormal angle range and the tree position influence parameter to calculate a tree angle anomaly possibility of the target tree.

4. The method of claim 1, wherein, The tree attribute anomaly detection using the tree attribute information in the initial tree information, the device line information and the tree angle anomaly possibility to obtain a tree attribute anomaly possibility comprises: perform tree abnormal attribute range calculation using the target tree height in the initial tree information, the target tree distance in the initial tree information, and the line height in the device line information to obtain a target tree abnormal attribute range; perform tree attribute abnormality likelihood calculation using the target tree abnormal attribute range, the tree angle abnormality likelihood, and the tree attribute information to obtain a tree attribute abnormality likelihood of the target tree.

5. The method of claim 1, wherein, The device node information includes respective device node identifiers. The device node abnormality detection based on the device line abnormality degree and the device node information obtains a device node abnormality degree, including: determining a current device node identifier among the respective device node identifiers, and associated device node identifiers associated with the current device node; determining a current line identifier from the device line information based on the current device node identifier and the associated device node identifiers; obtaining an associated device node abnormality degree corresponding to the associated device node identifiers and a current line abnormality degree corresponding to the current line identifier; calculating a device node abnormality degree corresponding to the current device node identifier based on the associated device node abnormality degree and the current line abnormality degree; iterating through the respective device node identifiers to obtain a device node abnormality degree corresponding to each of the respective device node identifiers.

6. The method of claim 1, wherein, The determination of the region abnormality degree corresponding to the target device region image based on the device node abnormality degree includes: obtaining weight information corresponding to the device node abnormality degree, and performing weighted calculation on the device node abnormality degree based on the weight information to obtain the region abnormality degree corresponding to the target device region image.

7. A resource processing device, characterized by The apparatus includes: an identification module configured to obtain a target device region image, identify the target device region image, and obtain initial tree information, device line information, and device node information corresponding to the target device region; a line detection module configured to obtain a tree position influence parameter, perform device line abnormality detection based on the tree position influence parameter, the initial tree information, and the device line information, and obtain a device line abnormality degree; a node detection module configured to perform device node abnormality detection based on the device line abnormality degree and the device node information, and obtain a device node abnormality degree; an abnormality judgment module configured to determine a region abnormality degree corresponding to the target device region image based on the device node abnormality degree, and update the initial tree information to obtain target tree information when the region abnormality degree exceeds a preset abnormality threshold. The line detection module is further configured to: calculate a tree position abnormality likelihood using the tree position influence parameter; perform tree angle abnormality detection using the tree position influence parameter, the initial tree information, and the device line information to obtain a tree angle abnormality likelihood; perform tree attribute abnormality detection using tree attribute information in the initial tree information, the device line information, and the tree angle abnormality likelihood to obtain a tree attribute abnormality likelihood; The tree position abnormality possibility and the tree attribute abnormality possibility are multiplied to obtain a device line abnormality degree of a certain position of the device line; The device line length in the device line information is normalized, and the device line abnormality degree is determined according to the normalized device line length and the device line abnormality degrees of all positions of the device line.

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that, The processor, when executing the computer program, implements the steps of the method in any one of claims 1 to 6.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program, when executed by the processor, implements the steps of the method in any one of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that, The computer program, when executed by the processor, implements the steps of the method in any one of claims 1 to 6.

Images