CN117726145B

CN117726145B - Cable inspection processing method and device, electronic equipment and computer readable medium

Info

Publication number: CN117726145B
Application number: CN202410171872.8A
Authority: CN
Inventors: 张竞; 何泽斌; 许宇翔; 宋廷汉; 孔诗琦; 贲成; 黄轲
Original assignee: Guangzhou Power Supply Bureau of Guangdong Power Grid Co Ltd
Current assignee: Guangzhou Power Supply Bureau of Guangdong Power Grid Co Ltd
Priority date: 2024-02-07
Filing date: 2024-02-07
Publication date: 2024-05-10
Anticipated expiration: 2044-02-07
Also published as: CN117726145A

Abstract

The embodiment of the disclosure discloses a cable inspection processing method, a device, electronic equipment and a computer readable medium. One embodiment of the method comprises the following steps: acquiring a three-dimensional digital twin model; in response to receiving the inspection information, determining at least one piece of information to be inspected corresponding to the target cable area according to a digital twin area model corresponding to the target cable area; for each piece of information to be patrolled and examined, executing a work order processing step: generating a patrol work order; matching corresponding patrol personnel information according to the content of the work order; adding the patrol personnel information to the patrol work order to generate a complete patrol work order; executing the complete inspection work order to monitor the corresponding inspection personnel in real time for cable inspection. The embodiment can utilize a three-dimensional digital twin model to accurately and efficiently realize the inspection processing of the cable.

Description

Cable inspection processing method and device, electronic equipment and computer readable medium

Technical Field

Embodiments of the present disclosure relate to the field of computer technology, and in particular, to a cable inspection processing method, a device, an electronic apparatus, and a computer readable medium.

Background

At present, the cable is widely applied to daily life of people. Various damage problems often occur to the cable during use. For the inspection processing of the cable, the following modes are generally adopted: and manually indicating relevant inspection workers to go to the site to perform comprehensive real-time inspection treatment on the cable.

However, the inventors found that when the above-mentioned method is used to perform the inspection process of the cable, there is often the following technical problem:

the comprehensive implementation of the inspection treatment of the cable is carried out on site, the workload is large, and the problem of low inspection efficiency exists.

Continuing, in the technical scheme of adopting to solve the technical problem of low inspection efficiency, how to accurately generate corresponding multi-azimuth image difference detection information according to the multi-azimuth cable diagram and the multi-azimuth historical cable diagram. For the generation of multi-aspect image difference detection information, conventional solutions are generally: the conventional multi-layer series connected convolutional neural network is directly used to generate multi-azimuth image difference detection information for the multi-azimuth cable graphs and the multi-azimuth historical cable graphs. However, the above solution has the following technical problem two:

The characteristics extracted by the conventional convolutional neural network are not accurate enough, the dimension of the considered characteristic information is not comprehensive enough, the output prediction accuracy is not enough, and the generated information to be patrolled and examined is not accurate enough.

The above information disclosed in this background section is only for enhancement of understanding of the background of the inventive concept and, therefore, may contain information that does not form the prior art that is already known to those of ordinary skill in the art in this country.

Disclosure of Invention

The disclosure is in part intended to introduce concepts in a simplified form that are further described below in the detailed description. The disclosure is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.

Some embodiments of the present disclosure propose a cable inspection processing method, apparatus, electronic device, and computer readable medium to solve one or more of the technical problems mentioned in the background section above.

In a first aspect, some embodiments of the present disclosure provide a cable inspection processing method, including: acquiring a three-dimensional digital twin model, wherein the three-dimensional digital twin model is a digital twin model established for a cable region; in response to receiving inspection information for a target cable area in the cable area, determining at least one piece of information to be inspected corresponding to the target cable area according to a digital twin area model corresponding to the target cable area; for each piece of information to be inspected in the at least one piece of information to be inspected, executing the following work order processing steps: generating a patrol work order corresponding to the information to be patrol; matching corresponding patrol personnel information according to the work order content corresponding to the patrol work order; adding the patrol personnel information into the patrol work order to generate a complete patrol work order; executing the complete inspection work order to monitor the corresponding inspection personnel in real time for cable inspection processing.

In a second aspect, some embodiments of the present disclosure provide a cable inspection processing device, comprising: an acquisition unit configured to acquire a three-dimensional digital twin model, wherein the three-dimensional digital twin model is a digital twin model established for a cable region; a determining unit configured to determine, in response to receiving patrol information for a target cable area in the cable areas, at least one piece of information to be patrol corresponding to the target cable area according to a digital twin area model corresponding to the target cable area; the execution unit is configured to execute the following work order processing steps for each piece of information to be patrolled and examined in the at least one piece of information to be patrolled and examined: generating a patrol work order corresponding to the information to be patrol; matching corresponding patrol personnel information according to the work order content corresponding to the patrol work order; adding the patrol personnel information into the patrol work order to generate a complete patrol work order; executing the complete inspection work order to monitor the corresponding inspection personnel in real time for cable inspection processing.

In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device having one or more programs stored thereon, which when executed by one or more processors, cause the one or more processors to implement the method as described in any of the implementations of the first aspect.

In a fourth aspect, some embodiments of the present disclosure provide a computer readable medium having a computer program stored thereon, wherein the program when executed by a processor implements a method as described in any of the implementations of the first aspect.

The above embodiments of the present disclosure have the following advantageous effects: the cable inspection processing method can utilize the three-dimensional digital twin model to accurately and efficiently realize the cable inspection processing. In particular, the reason for the insufficient precision and efficiency of the inspection process of the associated sub-cables is: the comprehensive implementation of the inspection treatment of the cable is carried out on site, the workload is large, and the problem of low inspection efficiency exists. Based on this, the cable inspection processing method of some embodiments of the present disclosure first acquires a three-dimensional digital twin model. Wherein the three-dimensional digital twin model is a digital twin model established for the cable region. The cable detail in the cable area can be accurately monitored through the three-dimensional digital twin model, so that the cable needing to be inspected can be detected in real time, and the working operation of the cable area is guaranteed. Then, in response to receiving the inspection information for the target cable region in the cable region, determining at least one piece of information to be inspected corresponding to the target cable region can be accurately realized according to the digital twin region model corresponding to the target cable region. Then, for each piece of the at least one piece of information to be inspected, the following work order processing steps are executed: first, generating a patrol worksheet corresponding to the information to be patrol, so as to be used for subsequently dispatching corresponding patrol personnel to execute corresponding patrol tasks. And step two, matching corresponding patrol personnel information according to the worksheet content corresponding to the patrol worksheets so as to screen out proper patrol personnel aiming at the information to be patrol. And thirdly, adding the patrol personnel information into the patrol work order to generate a complete patrol work order so as to facilitate the subsequent realization of cable patrol processing. And fourthly, executing the complete inspection work order to monitor the corresponding inspection personnel in real time to carry out cable inspection processing. In sum, the matching of at least one piece of information to be inspected and the corresponding inspection personnel of each piece of information to be inspected is determined through the three-dimensional digital twin model, so that the efficient inspection processing of the cable can be realized in a targeted manner.

Drawings

The above and other features, advantages, and aspects of embodiments of the present disclosure will become more apparent by reference to the following detailed description when taken in conjunction with the accompanying drawings. The same or similar reference numbers will be used throughout the drawings to refer to the same or like elements. It should be understood that the figures are schematic and that elements and components are not necessarily drawn to scale.

FIG. 1 is a flow chart of some embodiments of a cable inspection processing method according to the present disclosure;

FIG. 2 is a schematic structural view of some embodiments of a cable inspection processing device according to the present disclosure;

fig. 3 is a schematic structural diagram of an electronic device suitable for use in implementing some embodiments of the present disclosure.

Detailed Description

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete. It should be understood that the drawings and embodiments of the present disclosure are for illustration purposes only and are not intended to limit the scope of the present disclosure.

It should be noted that, for convenience of description, only the portions related to the present invention are shown in the drawings. Embodiments of the present disclosure and features of embodiments may be combined with each other without conflict.

It should be noted that the terms "first," "second," and the like in this disclosure are merely used to distinguish between different devices, modules, or units and are not used to define an order or interdependence of functions performed by the devices, modules, or units.

It should be noted that references to "one", "a plurality" and "a plurality" in this disclosure are intended to be illustrative rather than limiting, and those of ordinary skill in the art will appreciate that "one or more" is intended to be understood as "one or more" unless the context clearly indicates otherwise.

The names of messages or information interacted between the various devices in the embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.

Referring to fig. 1, a flow 100 of some embodiments of a cable inspection processing method according to the present disclosure is shown. The cable inspection processing method comprises the following steps:

And step 101, acquiring a three-dimensional digital twin model.

In some embodiments, the executing body of the cable inspection processing method may acquire the three-dimensional digital twin model through a wired connection manner or a wireless connection manner. Wherein the three-dimensional digital twin model is a digital twin model established for the cable region. The three-dimensional digital twin model may be a digital twin model in three-dimensional form. The cable area may be an area where various types of cables are arranged in advance. For example, the cable area may be a target power plant.

Step 102, in response to receiving the inspection information for the target cable area in the cable area, determining at least one piece of information to be inspected corresponding to the target cable area according to the digital twin area model corresponding to the target cable area.

In some embodiments, in response to receiving the routing inspection information for the target cable region in the cable region, the executing body may determine at least one piece of information to be routing inspected corresponding to the target cable region according to a digital twin region model corresponding to the target cable region. The target cable area may be an area selected by the relevant cable manager and among the cable areas. The routing information may be a routing request for the target cable area. The digital twin region model corresponding to the target cable region may be a sub-model of the three-dimensional digital twin model described above for the target cable region. The information to be inspected may be related information to be inspected for the cable. In practice, the information to be patrol may include, but is not limited to, at least one of: the information of the patrol places, the information of the patrol modes and the information of the patrol time. The information to be patrol may be patrol information of some places in the target cable area.

In some optional implementations of some embodiments, the determining at least one piece of information to be inspected corresponding to the target cable area may include the following steps:

First, important order information of cable detection nodes for the target cable area is acquired. Wherein the cable detection node importance sequence information characterizes importance degrees of each cable key node in the target cable area. The degree of importance corresponding to each cable node may be predetermined for the target cable area. When the importance level is greater than the target value, the cable node may be determined as a cable key node. For example, each cable critical node includes: the first cable critical node, the second cable critical node, and the third cable critical node. The first cable critical node may correspond to an importance level of 80%. The second cable key node may correspond to a degree of importance of 70%. The third cable key node may correspond to a degree of importance of 82%. The corresponding cable detection node importance sequence information may be { third cable key node, first cable key node, second cable key node }.

And secondly, dividing cable key nodes in the cable key node set corresponding to the target cable region according to the important sequence information of the cable detection nodes in a preset proportion to generate a cable key node group set. The higher the importance degree of the cable key nodes is, the fewer the number of the nodes corresponding to the cable key node group is. For example, the cable critical node group set includes: a first cable critical node group, a second cable critical node group, and a third cable critical node group. The first cable critical node group includes respective cable critical nodes having a greater degree of importance than the second cable critical node group includes respective cable critical nodes. The second cable key group includes respective cable key nodes having a greater degree of importance than respective cable key nodes of the third cable key group. The first cable key group includes 4 cable key nodes. The second set of cable key nodes includes 8 cable key nodes. The third cable key node group includes 12 cable key nodes. The predetermined ratio may be "1:2:3".

And thirdly, sequentially carrying out node detection on each cable key node in the cable key node group according to the importance degree of the cable key node to obtain target number of information to be inspected as the at least one information to be inspected.

Optionally, the sequentially performing node detection on each cable key node in the cable key node group to obtain the target number of information to be patrolled and examined may include the following steps:

The first step, for the cable key nodes to be executed in the cable key node group set, the following first generation steps are executed:

And determining the position information of the key node of the cable to be executed in the three-dimensional digital twin model to obtain the node position information. The three-dimensional digital twin model may be a model built in a target coordinate system. The location information may be coordinates of the cable key node to be executed for the three-dimensional digital twin model on the above-mentioned target coordinate system.

And a second sub-step of acquiring at least one adjacent cable key node in the three-dimensional digital twin model corresponding to the cable key node to be executed. The adjacent cable key node may be a cable key node having a positional proximity relation with the cable key node to be executed.

And a third sub-step of acquiring three-dimensional space information for the at least one adjacent cable key node. The three-dimensional space information corresponding space is a control established by taking each node in the at least one adjacent cable key node as a vertex.

And a fourth sub-step of performing space equal proportion multiple reduction on the three-dimensional space information to generate reduced space information. In practice, the equal ratio multiple may be a preset multiple. For example, the scaling factor may be 2:1.

And a fifth substep, establishing detection space information taking the node position information as a center point and the three-dimensional space corresponding to the reduced space information as a detection space range.

And a sixth sub-step of generating cable external abnormality detection information for the detection space information corresponding space by using a cable external abnormality detection model. The cable external abnormality detection model may be a neural network model that generates cable external abnormality detection information. The cable exterior abnormality detection information may be information for abnormality detection with respect to the cable exterior. For example, the cable external abnormality detection information may be cable damage detection information.

And a seventh substep of generating the cable internal abnormality detection information of each cable in the detection space information corresponding space to obtain a cable internal abnormality detection information set. The cable internal abnormality detection information may be information for detecting an abnormality in the cable. For example, the cable internal abnormality detection information may be cable short circuit detection information.

As an example, the execution body described above may determine a cable detection area corresponding to each cable. Then, the cable internal abnormality detection information of the cable is detected by shorting or line-changing connection.

And an eighth substep, generating the information to be inspected according to the cable external abnormality detection information and the cable internal abnormality detection information set.

As an example, the above-described execution subject may directly determine the cable external abnormality detection information and the above-described cable internal abnormality detection information set as the information to be patrol.

In some optional implementations of some embodiments, the generating the information to be inspected according to the cable external anomaly detection information and the cable internal anomaly detection information set may include the following steps:

And the first step is to screen out the cable position information corresponding to the external abnormality of the characterization cable from the external abnormality detection information of the cable to obtain at least one piece of cable position information.

A second step of, for each of the at least one piece of cable position information, performing the following third generation step:

A first sub-step of generating a multi-azimuth cable map for the cable position information. The multi-azimuth cable graphs can be a plurality of cable graphs which are acquired aiming at the multi-azimuth shooting view angle and take the direction in which the cable position information is located as the shooting direction.

And a second sub-step of acquiring a multi-azimuth historical cable map for the cable position information. Wherein the history cable graph in the multi-azimuth history cable graph is not an abnormal cable graph. The history cable map is a history-captured image when the cable is operating normally.

And a third sub-step of correspondingly inputting the multi-azimuth cable drawing and the multi-azimuth historical cable drawing into an image difference detection information generation model to generate multi-azimuth image difference detection information. The image difference detection information generation model may be a neural network model that generates the image difference detection information. The image difference detection information may characterize an image difference between the input plurality of images.

And a fourth sub-step of checking whether the cable corresponding to the cable position information is abnormal according to the multi-azimuth image difference detection information to obtain first check information.

As an example, in response to determining that the multi-aspect image difference detection information characterizes no differences between the multi-aspect images, first verification information characterizing that the cable position information corresponds to no anomalies in the cable is generated.

Thirdly, carrying out information verification on each piece of cable internal abnormality detection information in the cable internal abnormality detection information set to generate second verification information, and obtaining a second verification information set.

As an example, the execution subject may assign another anomaly checker to artificially perform information checking on each of the cable internal anomaly detection information in the cable internal anomaly detection information set to generate second check information, resulting in a second check information set.

Fourth, generating the information to be inspected according to the obtained first check information set and the second check information set.

As an example, in response to determining that the first set of check information and the check information in the second set of check information are both check-free, the cable external anomaly detection information and the cable internal anomaly detection information set are determined as the information to be inspected.

In some optional implementations of some embodiments, the cable external anomaly detection model includes: the spatial gradient feature extraction model is used for generating a model with image content position information, and is based on an external abnormality detection model of an attention mechanism and an external normal detection model of the attention mechanism. The spatial gradient feature extraction model may be a neural network model that generates control gradient feature extraction information. The co-image content location information generation model may be a neural network model that determines location information of co-image content locations in the input plurality of images. The external anomaly detection model based on the attention mechanism may be a neural network model for external anomaly detection based on the attention mechanism. The external normal detection model based on the attention mechanism may be a neural network model for external normal detection based on the attention mechanism. The spatial gradient feature extraction model may be a convolutional neural network + pooling pyramid. The co-image content location information generation model may include: image feature extraction model + image feature comparison model + image segmentation model. In practice, the image feature extraction model may be a multi-layer series connected convolutional neural network. The image feature comparison model may be an attention mechanism model. The external abnormality detection model based on the attention mechanism and the internal abnormality detection model based on the attention mechanism share the same image feature extraction model. And the external anomaly detection model based on the attention mechanism further comprises: a multi-headed attentiveness-mechanism model for determining an external abnormality detection attentiveness determination. The internal anomaly detection model based on the attention mechanism further includes: a multi-headed attentiveness-mechanism model for determining internal anomaly detection attentiveness determination.

Alternatively, the generating the cable external abnormality detection information for the space corresponding to the detection space information using the cable external abnormality detection model may include the steps of:

The first step is to control a plurality of image acquisition devices disposed in the detection space information corresponding space to acquire image sequences corresponding to the detection space information corresponding space in a clockwise direction and a multi-angle and multi-azimuth manner. In practice, the image acquisition device may be an imaging device. The multi-angle multi-azimuth can be a plurality of angles and a plurality of azimuth which are preset. The image sequence may be an image sequence acquired with the detection space information as a shooting direction.

And a second step of inputting every adjacent at least two images in the image sequence into the spatial gradient feature extraction model to generate gradient feature information so as to obtain a gradient feature information sequence.

And thirdly, extracting image characteristic information corresponding to each image in the image sequence to obtain the image characteristic information sequence.

Fourth, executing the following second generation step for every two adjacent image feature information in the image feature information sequence:

and a first sub-step, performing characteristic information stitching on the two image characteristic information to generate stitched characteristic information.

And a second sub-step of inputting the splice feature information into a same-image-content-position-information generation model to generate a same-image-content-position-information group for the two image feature information.

And a third sub-step of combining the same-image-content position information set, the two image feature information and the gradient feature information sequence in a predetermined order to generate combined information. Wherein the predetermined order may be a predetermined order.

And a fourth sub-step of inputting the above-described combined information to an external abnormality detection model based on an attention mechanism to generate external abnormality detection information.

And a fifth sub-step of inputting the above combined information to an external normal detection model based on an attention mechanism to generate external normal detection information.

And a sixth sub-step of determining the external abnormality detection information as the cable external abnormality detection sub-information in response to determining that the addition value of the external abnormality detection information corresponding to the abnormality probability value and the external normal detection information corresponding to the normal probability value is larger than a first value and the subtraction value between the abnormality probability value and the normal probability value is larger than a second value. The first value and the second value may be predetermined values.

And fifthly, information summarizing all the cable external abnormality detection sub-information in the obtained cable external abnormality detection sub-information sequence to generate the cable external abnormality detection information.

Aiming at the second technical problem: the characteristics extracted by the conventional convolutional neural network are not accurate enough, the dimension of the considered characteristic information is not comprehensive enough, the output prediction accuracy is not enough, and the generated information to be patrolled and examined is not accurate enough. In combination with the technical advantages/market state of knowledge possessed by teams, we decided to employ the following solutions:

Optionally, the multi-azimuth cable map and the multi-azimuth historical cable map are correspondingly input into an image difference detection information generation model to generate multi-azimuth image difference detection information, which comprises the following steps:

first, for each azimuth cable map of the azimuth cable maps, the following first processing steps are performed:

A first sub-step of inputting the azimuth cable map into a cable segmentation model included in the image difference detection information generation model to generate a cable image set and a cable image position information set. Wherein the cable segmentation model may be a U-net model. The cable image position information may be position information of the cable image in the azimuth cable map described above. In practice, the cable image position information may be position information in the form of a plurality of coordinates. The cable images in the cable image set have a one-to-one correspondence with the cable image position information in the cable image position information set.

And a second sub-step of inputting the target historical cable map into a cable segmentation model included in the image difference detection information generation model to generate a historical cable image set and a historical cable image position information set. The target history cable graph may be a history cable graph having the same azimuth as the azimuth corresponding to the azimuth cable graph. There is a one-to-one correspondence between the historical cable images in the historical cable image set and the historical cable image position information in the historical cable image position information set.

And a third sub-step of determining whether or not there is a difference in position information between the cable image position information set and the history cable image position information set.

And a fourth sub-step of generating cable image feature information corresponding to each cable image in the cable image set by using an image feature extraction model included in the image difference detection information generation model to obtain a cable image feature information set, and generating historical cable image feature information corresponding to each historical cable image in the historical cable image set to obtain a historical cable image feature information set. The image feature extraction model may be a multi-layer series connected convolutional neural network model, among others.

And a fifth substep, in response to determining that there is no difference in the position information, performing feature information splicing on each piece of cable image feature information in the cable image feature information set according to a priority order of the cable image position information from left to right and from top to bottom to obtain first splicing information, and performing feature information splicing on each piece of history cable image feature information in the history cable image feature information set according to a priority order of the history cable image position information from left to right and from top to bottom to obtain second splicing information.

A sixth substep of information encoding each of the cable image positional information in the set of cable image positional information to generate a set of positional encoded information, and information encoding each of the historical cable image positional information in the set of historical cable image positional information to generate a set of historical positional encoded information.

And a seventh substep, respectively performing coding information splicing on the position coding information set and the historical position coding information set according to the characteristic information splicing mode of the cable image characteristic information set and the characteristic information splicing mode of the historical cable image characteristic information set so as to generate first position splicing information and second position splicing information.

And an eighth substep of inputting the first splicing information into the first convolutional neural network to generate a first output result, and inputting the second splicing information into the second convolutional neural network to generate a second output result.

And a ninth substep of inputting the first position splicing information into a third convolutional neural network to generate a third output result, and inputting the second position splicing information into a fourth convolutional neural network to generate a fourth output result.

A tenth substep of inputting the third output result and the first output result to a fifth convolutional neural network to generate a fifth output result, and inputting the fourth output result and the second output result to a sixth convolutional neural network to generate a sixth output result.

And an eleventh sub-step of performing predetermined sequential splicing on the fifth output result and the first output result to generate a third spliced result, and performing predetermined sequential splicing on the sixth output result and the second output result to generate a fourth spliced result.

And a twelfth substep, inputting the third splicing result and the fourth splicing result into an image feature similarity weight generation model based on a multi-head attention mechanism to generate an image similarity weight matrix. The image similarity weight matrix is the same as the matrix dimension corresponding to the first splicing information. Each element in the image similarity weight matrix characterizes the degree of similarity of the corresponding two sub-images. The image feature similarity weight generation model may be a model that generates image feature similarity weights. In practice, the image feature similarity weight generation model may be a multi-headed attention mechanism model in a transducer model.

And a thirteenth substep of splicing the fifth output result and the third output result in a predetermined order to generate a fifth spliced result, and splicing the sixth output result and the fourth output result in a predetermined order to generate a sixth spliced result.

And a fourteenth substep, inputting the fifth splicing result and the sixth splicing result into an image position feature similarity weight generation model based on a multi-head attention mechanism to generate an image position similarity weight matrix. And the image position similarity weight matrix is the same as the matrix dimension corresponding to the first position splicing information. Each element in the image position similarity weight matrix characterizes the degree of similarity of the corresponding two sub-image positions. The image location feature similarity weight generation model may be a model that generates image location feature similarity weights. In practice, the image location feature similarity weight generation model may be a multi-headed attention mechanism model in a transducer model.

And a fifteenth sub-step of generating information representing the degree of difference between the azimuth cable graph and the target historical azimuth cable graph according to the image position similarity weight matrix and the image similarity weight matrix.

As an example, in response to determining that each element included in the image location similarity weight matrix and each element included in the image similarity weight matrix is greater than a target value, difference information is generated that characterizes no difference between the azimuth cable map and the target historical azimuth cable map.

As yet another example, in response to determining that each element included in the image location similarity weight matrix and each element included in the image similarity weight matrix has an element that is less than or equal to a target value, information is generated that characterizes a difference between the azimuth cable map and the target historical azimuth cable map.

And secondly, summarizing each difference information in the obtained difference information set to generate summarized information serving as multi-azimuth image difference detection information.

The above optional content, as an invention point of the present disclosure, solves the technical problem mentioned in the background art, namely, the second "the feature extracted by the conventional convolutional neural network is not accurate enough, the dimension of the considered feature information is not comprehensive enough, the output prediction accuracy is not enough, and the generated information to be patrolled and examined is not accurate enough. Based on this, the present disclosure can comprehensively extract image content feature information and image space feature information between two images at positions corresponding to a multi-azimuth image and a multi-azimuth history image through each submodel included in the image difference detection information generation model, and can accurately generate multi-azimuth image difference detection information for a multi-azimuth cable image and the multi-azimuth history cable image through a constraint relationship between the image content feature information and the image space feature information and a feature similarity degree corresponding to the image content feature information and a feature similarity degree corresponding to the image space feature information, so as to ensure that more accurate inspection information is generated later.

Step 103, for each piece of information to be inspected in the at least one piece of information to be inspected, executing the following work order processing steps:

Step 1031, generating the inspection work order corresponding to the information to be inspected.

In some embodiments, the executing body may generate a patrol worksheet corresponding to the information to be patrol. The inspection work order can be a task work order corresponding to the inspection task.

As an example, first, a patrol job ticket template is acquired. And then, inputting the information to be inspected to an inspection work order template to generate an inspection work order.

Step 1032, matching corresponding patrol personnel information according to the worksheet content corresponding to the patrol worksheet.

In some embodiments, the executing body may match corresponding patrol personnel information according to the content of the work order corresponding to the patrol work order. The patrol personnel information may be personnel information for performing patrol operation for a patrol task.

As an example, first, the execution subject may determine the patrol type corresponding to the work order content. And then, matching corresponding patrol personnel information according to the patrol type.

Step 1033, adding the inspection personnel information to the inspection work order to generate a complete inspection work order.

In some embodiments, the executing entity may add the inspection personnel information to the inspection work order to generate a complete inspection work order.

Step 1034, executing the complete inspection work order to monitor the corresponding inspection personnel in real time for cable inspection.

In some embodiments, the executing body may execute the complete inspection work order to monitor the corresponding inspection personnel in real time for performing the cable inspection process.

In some alternative implementations of some embodiments, after step 1034, the steps further include:

the first step, receiving the work order execution result aiming at the inspection work order. The work order execution result can be an execution result uploaded by a related technician after the inspection work order is executed.

And secondly, utilizing a virtual reality ideal execution result corresponding to the three-dimensional digital twin model and aiming at the target cable area. The virtual reality ideal execution result may be a work order execution result that reflects the target cable area based on the form of virtual reality technology.

As an example, first, the above-described execution subject may generate a virtual reality model for a cable region from a three-dimensional digital twin model. And then, extracting a virtual reality ideal execution result corresponding to the target cable region from the virtual reality model.

And thirdly, acquiring the current virtual reality execution result of the target cable area in real time. The virtual reality current execution result may be a work order current actual execution result of the target cable area based on a form of virtual reality technology.

As an example, first, the execution body may acquire a three-dimensional digital twin model after the inspection work order is processed. Then, a virtual reality model of the three-dimensional digital twin model processed by the inspection work order is generated and used as a target virtual reality model. And finally, extracting the current virtual reality execution result corresponding to the target cable region from the target virtual reality model.

And step four, determining difference information between the ideal execution result of the virtual reality and the current execution result of the virtual reality.

As an example, the execution subject may receive difference information between the virtual reality ideal execution result and the virtual reality current execution result uploaded by the relevant virtual reality viewer.

And fifthly, executing result verification of the work order execution result according to the difference information.

As an example, in response to determining that the difference information is similar to the execution content corresponding to the work order execution result, information characterizing the result verification passing for the work order execution result is generated.

In some optional implementations of some embodiments, the executing the complete inspection work order to monitor the corresponding inspection personnel in real time to perform the cable inspection process may include the following steps:

And the first step is to send the complete inspection work order and inspection operation information to the cable inspection processing terminal corresponding to the inspection personnel. The cable inspection processing terminal is connected with the target three-dimensional digital twin model using platform. The target three-dimensional digital twin model using platform is a platform for carrying out model control on the three-dimensional digital twin model. The cable inspection processing terminal can be a task processing terminal related to a cable inspection task. Model manipulation may include: model enlargement, model clipping, model reduction, and model movement.

And secondly, responding to the detection that the patrol personnel reach the information to be patrol corresponding to the complete patrol work order, and determining the node position information of the key node of the cable corresponding to the information to be patrol as target node position information.

And thirdly, taking the target node position information as a display center of the cable inspection processing terminal, and sending the real-time three-dimensional digital twin sub-model corresponding to the target node position information to the cable inspection processing terminal so as to enable the inspection personnel to perform various model operations on the real-time three-dimensional digital twin sub-model. Wherein the various model operations include: model rotation operation, model part enlargement operation, model part reduction operation.

And fourthly, in response to detecting that the patrol personnel do not perform node operation on the cable key nodes within the target time length, updating the real-time three-dimensional digital twin sub-model in real time, and taking the updated real-time three-dimensional digital twin sub-model as the updated real-time three-dimensional digital twin sub-model. Wherein the target time period may be a predetermined time period. For example, the target time period may be 2 minutes.

And fifthly, determining the updated real-time three-dimensional digital twin sub-model as a real-time three-dimensional digital twin sub-model so that the patrol personnel can continue to carry out cable patrol processing.

With further reference to fig. 2, as an implementation of the method shown in the above figures, the present disclosure provides embodiments of a cable inspection processing device, which correspond to those method embodiments shown in fig. 1, and which are particularly applicable to various electronic devices.

As shown in fig. 2, a cable inspection processing device 200 includes: an acquisition unit 201, a determination unit 202, and an execution unit 203. Wherein the obtaining unit 201 is configured to obtain a three-dimensional digital twin model, wherein the three-dimensional digital twin model is a digital twin model established for a cable region; a determining unit 202 configured to determine, in response to receiving patrol information for a target cable area of the cable areas, at least one to-be-patrol information corresponding to the target cable area according to a digital twin area model corresponding to the target cable area; an execution unit 203 configured to execute, for each piece of the at least one piece of information to be patrol, the following work order processing steps: generating a patrol work order corresponding to the information to be patrol; matching corresponding patrol personnel information according to the work order content corresponding to the patrol work order; adding the patrol personnel information into the patrol work order to generate a complete patrol work order; executing the complete inspection work order to monitor the corresponding inspection personnel in real time for cable inspection processing.

It will be appreciated that the elements described in the cable inspection processing device 200 correspond to the various steps in the method described with reference to fig. 1. Thus, the operations, features and advantages described above for the method are equally applicable to the cable inspection processing device 200 and the units contained therein, and are not described herein.

Referring now to fig. 3, a schematic diagram of an electronic device (e.g., electronic device) 300 suitable for use in implementing some embodiments of the present disclosure is shown. The electronic device shown in fig. 3 is merely an example and should not impose any limitations on the functionality and scope of use of embodiments of the present disclosure.

As shown in fig. 3, the electronic device 300 may include a processing means (e.g., a central processing unit, a graphics processor, etc.) 301 that may perform various suitable actions and processes in accordance with a program stored in a Read Only Memory (ROM) 302 or a program loaded from a storage means 308 into a Random Access Memory (RAM) 303. In the RAM303, various programs and data required for the operation of the electronic apparatus 300 are also stored. The processing device 301, the ROM302, and the RAM303 are connected to each other via a bus 304. An input/output (I/O) interface 305 is also connected to bus 304.

In general, the following devices may be connected to the I/O interface 305: input devices 306 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; an output device 307 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 308 including, for example, magnetic tape, hard disk, etc.; and communication means 309. The communication means 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. While fig. 3 shows an electronic device 300 having various means, it is to be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may be implemented or provided instead. Each block shown in fig. 3 may represent one device or a plurality of devices as needed.

In particular, according to some embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flow chart. In such embodiments, the computer program may be downloaded and installed from a network via communications device 309, or from storage device 308, or from ROM 302. The above-described functions defined in the methods of some embodiments of the present disclosure are performed when the computer program is executed by the processing means 301.

It should be noted that, in some embodiments of the present disclosure, the computer readable medium may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In some embodiments of the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In some embodiments of the present disclosure, however, the computer-readable signal medium may comprise a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.

In some embodiments, the clients, servers may communicate using any currently known or future developed network protocol, such as HTTP (HyperText Transfer Protocol ), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the internet (e.g., the internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed networks.

The computer readable medium may be contained in the electronic device; or may exist alone without being incorporated into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: acquiring a three-dimensional digital twin model, wherein the three-dimensional digital twin model is a digital twin model established for a cable region; in response to receiving inspection information for a target cable area in the cable area, determining at least one piece of information to be inspected corresponding to the target cable area according to a digital twin area model corresponding to the target cable area; for each piece of information to be inspected in the at least one piece of information to be inspected, executing the following work order processing steps: generating a patrol work order corresponding to the information to be patrol; matching corresponding patrol personnel information according to the work order content corresponding to the patrol work order; adding the patrol personnel information into the patrol work order to generate a complete patrol work order; executing the complete inspection work order to monitor the corresponding inspection personnel in real time for cable inspection processing.

Computer program code for carrying out operations for some embodiments of the present disclosure may be written in one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in some embodiments of the present disclosure may be implemented by means of software, or may be implemented by means of hardware. The described units may also be provided in a processor, for example, described as: a processor includes an acquisition unit, a determination unit, and an execution unit. The names of these units do not constitute a limitation on the unit itself in some cases, and the acquisition unit may also be described as "a unit that acquires a three-dimensional digital twin model", for example.

The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: a Field Programmable Gate Array (FPGA), an Application Specific Integrated Circuit (ASIC), an Application Specific Standard Product (ASSP), a system on a chip (SOC), a Complex Programmable Logic Device (CPLD), and the like.

The foregoing description is only of the preferred embodiments of the present disclosure and description of the principles of the technology being employed. It will be appreciated by those skilled in the art that the scope of the invention in the embodiments of the present disclosure is not limited to the specific combination of the above technical features, but encompasses other technical features formed by any combination of the above technical features or their equivalents without departing from the spirit of the invention. Such as the above-described features, are mutually substituted with (but not limited to) the features having similar functions disclosed in the embodiments of the present disclosure.

Claims

1. A cable inspection processing method comprises the following steps:

acquiring a three-dimensional digital twin model, wherein the three-dimensional digital twin model is a digital twin model established for a cable region;

Responsive to receiving inspection information for a target cable zone of the cable zones, determining at least one piece of information to be inspected corresponding to the target cable zone according to a digital twin zone model corresponding to the target cable zone,

The determining at least one piece of information to be patrolled and examined corresponding to the target cable area comprises the following steps:

Acquiring important sequence information of cable detection nodes aiming at the target cable area, wherein the important sequence information of the cable detection nodes represents the importance degree of each cable key node in the target cable area;

According to the important sequence information of the cable detection nodes, cable key nodes in the cable key node set corresponding to the target cable area are divided in a preset proportion to generate a cable key node group set, wherein the higher the importance degree of the cable key nodes is, the fewer the number of nodes corresponding to the cable key node group is;

According to the importance degree of the cable key nodes, sequentially carrying out node detection on each cable key node in the cable key node group to obtain target number of information to be patrolled and examined as the at least one information to be patrolled and examined,

The step of sequentially detecting the nodes of each cable key node in the cable key node group to obtain target number of information to be patrolled and examined comprises the following steps:

for the cable key nodes to be executed in the cable key node group set, executing the following first generation steps:

Determining the position information of the key node of the cable to be executed in the three-dimensional digital twin model to obtain node position information;

acquiring at least one adjacent cable key node in the three-dimensional digital twin model corresponding to the cable key node to be executed;

Acquiring three-dimensional space information aiming at the at least one adjacent cable key node, wherein the corresponding space of the three-dimensional space information is a control established by taking each node in the at least one adjacent cable key node as a vertex;

performing space equal proportion multiple reduction on the three-dimensional space information to generate reduced space information;

establishing detection space information taking the node position information as a center point, wherein the reduced space information corresponds to a three-dimensional space as a detection space range;

Generating cable external abnormality detection information for a space corresponding to the detection space information by using a cable external abnormality detection model;

Generating cable internal abnormality detection information of each cable in the detection space information corresponding space to obtain a cable internal abnormality detection information set;

Generating the information to be patrolled and examined according to the external abnormality detection information of the cable and the internal abnormality detection information set of the cable,

Wherein the generating the information to be inspected according to the cable external abnormality detection information and the cable internal abnormality detection information set includes:

Screening out cable position information corresponding to the external abnormality of the characterization cable from the external abnormality detection information of the cable to obtain at least one piece of cable position information;

for each of the at least one cable position information, performing the following third generating step:

generating a multi-azimuth cable map for the cable location information;

Acquiring a multi-azimuth historical cable graph aiming at the cable position information, wherein the historical cable graph in the multi-azimuth historical cable graph is not an abnormal cable graph;

Correspondingly inputting the multi-azimuth cable drawing and the multi-azimuth historical cable drawing into an image difference detection information generation model to generate multi-azimuth image difference detection information;

Checking whether the cable corresponding to the cable position information is abnormal according to the multi-azimuth image difference detection information to obtain first check information;

Performing information verification on each cable internal abnormality detection information in the cable internal abnormality detection information set to generate second verification information, and obtaining a second verification information set;

generating the information to be inspected according to the obtained first check information set and the second check information set,

Correspondingly inputting the multi-azimuth cable drawing and the multi-azimuth historical cable drawing into an image difference detection information generation model to generate multi-azimuth image difference detection information, wherein the multi-azimuth image difference detection information generation model comprises:

for each of the multi-azimuth cable graphs, performing the following first processing step:

inputting the azimuth cable map to a cable segmentation model included in the image difference detection information generation model to generate a cable image set and a cable image position information set;

Inputting a target historical cable graph to a cable segmentation model included in the image difference detection information generation model to generate a historical cable image set and a historical cable image position information set;

determining whether there is a difference in location information between the cable image location information set and the historical cable image location information set;

Generating cable image feature information corresponding to each cable image in the cable image set by using an image feature extraction model included in the image difference detection information generation model to obtain a cable image feature information set, and generating historical cable image feature information corresponding to each historical cable image in the historical cable image set to obtain a historical cable image feature information set;

in response to determining that no position information difference exists, performing feature information splicing on each piece of cable image feature information in the cable image feature information set according to the priority order of the cable image position information from left to right and from top to bottom to obtain first splicing information, and performing feature information splicing on each piece of history cable image feature information in the history cable image feature information set according to the priority order of the history cable image position information from left to right and from top to bottom to obtain second splicing information;

Information encoding each cable image location information in the set of cable image location information to generate a set of location encoded information, and information encoding each historical cable image location information in the set of historical cable image location information to generate a set of historical location encoded information;

According to the characteristic information splicing mode of the cable image characteristic information set and the characteristic information splicing mode of the historical cable image characteristic information set, respectively splicing the position coding information set and the historical position coding information set to generate first position splicing information and second position splicing information;

inputting the first splicing information into a first convolutional neural network to generate a first output result, and inputting the second splicing information into a second convolutional neural network to generate a second output result;

Inputting the first position splicing information into a third convolutional neural network to generate a third output result, and inputting the second position splicing information into a fourth convolutional neural network to generate a fourth output result;

inputting the third output result and the first output result to a fifth convolutional neural network to generate a fifth output result, and inputting the fourth output result and the second output result to a sixth convolutional neural network to generate a sixth output result;

splicing the fifth output result and the first output result in a preset sequence to generate a third splicing result, and splicing the sixth output result and the second output result in a preset sequence to generate a fourth splicing result;

inputting the third splicing result and the fourth splicing result into an image feature similarity weight generation model based on a multi-head attention mechanism to generate an image similarity weight matrix;

Splicing the fifth output result and the third output result in a preset sequence to generate a fifth splicing result, and splicing the sixth output result and the fourth output result in a preset sequence to generate a sixth splicing result;

inputting the fifth splicing result and the sixth splicing result into an image position feature similarity weight generation model based on a multi-head attention mechanism to generate an image position similarity weight matrix;

generating information representing the degree of difference between the azimuth cable graph and the target historical azimuth cable graph according to the image position similarity weight matrix and the image similarity weight matrix;

summarizing each difference information in the obtained difference information set to generate summarized information as multi-azimuth image difference detection information;

for each piece of information to be patrolled and examined in the at least one piece of information to be patrolled and examined, executing the following work order processing steps:

Generating a patrol work order corresponding to the information to be patrol;

matching corresponding patrol personnel information according to the work order content corresponding to the patrol work order;

adding the patrol personnel information to the patrol work order to generate a complete patrol work order;

And executing the complete inspection work order to monitor and control corresponding inspection personnel in real time to carry out cable inspection processing.

2. The method of claim 1, wherein after said executing the complete inspection worksheet to monitor in real-time a cable inspection process by a corresponding inspector, the method further comprises:

Receiving a work order execution result aiming at the inspection work order;

utilizing a virtual reality ideal execution result corresponding to the three-dimensional digital twin model and aiming at the target cable region;

Acquiring a virtual reality current execution result of the target cable area in real time;

Determining difference information between the ideal virtual reality execution result and the current virtual reality execution result;

and executing the result verification of the work order execution result according to the difference information.

3. The method of claim 2, wherein the cable external anomaly detection model comprises: the system comprises a spatial gradient feature extraction model, an image content position information generation model, an attention mechanism-based external abnormality detection model and an attention mechanism-based external normal detection model, wherein the spatial gradient feature extraction model is a neural network model for generating gradient feature extraction information, the image content position information generation model is a neural network model for determining position information of the image content position in a plurality of input images, and the image content position information generation model comprises: an image feature extraction model, an image feature comparison model and an image segmentation model; and

The generating, by using the cable external abnormality detection model, cable external abnormality detection information for a space corresponding to the detection space information includes:

Controlling a plurality of image acquisition devices deployed in the detection space information corresponding space to acquire image sequences aiming at the detection space information corresponding space in a clockwise direction and multi-angle and multi-azimuth mode;

inputting every adjacent at least two images in the image sequence into the spatial gradient feature extraction model to generate gradient feature information, and obtaining a gradient feature information sequence;

Extracting image characteristic information corresponding to each image in the image sequence to obtain an image characteristic information sequence;

And executing the following second generation step on every two adjacent image characteristic information in the image characteristic information sequence:

Performing characteristic information stitching on the two image characteristic information to generate stitched characteristic information;

Inputting the spliced characteristic information into a same-image content position information generation model to generate a same-image content position information group for the two image characteristic information;

Combining the same-image content position information group, the two image characteristic information and the gradient characteristic information sequence in a preset order to generate combined information;

inputting the combined information to an external abnormality detection model based on an attention mechanism to generate external abnormality detection information;

Inputting the combined information to an external normal detection model based on an attention mechanism to generate external normal detection information;

In response to determining that the external anomaly detection information corresponds to an anomaly probability value and the external normal detection information corresponds to a normal probability value, a summation value is greater than a first value, and a subtraction value between the anomaly probability value and the normal probability value is greater than a second value, determining the external anomaly detection information as cable external anomaly detection sub-information;

and carrying out information aggregation on each piece of cable external abnormality detection sub information in the obtained cable external abnormality detection sub information sequence so as to generate the cable external abnormality detection information.

4. The method of claim 3, wherein the executing the complete inspection worksheet to monitor the corresponding inspector for cable inspection in real-time comprises:

Transmitting the complete inspection work order and inspection operation information to a cable inspection processing terminal corresponding to the inspection personnel, wherein the cable inspection processing terminal is connected with a target three-dimensional digital twin model using platform, and the target three-dimensional digital twin model using platform is a platform for performing model control on the three-dimensional digital twin model;

responding to detection that the patrol personnel reach the information to be patrol corresponding to the complete patrol worksheet, and determining node position information of key nodes of the cable corresponding to the information to be patrol as target node position information;

The target node position information is taken as a display center of the cable inspection processing terminal, and the real-time three-dimensional digital twin sub-model corresponding to the target node position information is sent to the cable inspection processing terminal so that the inspection personnel can perform various model operations on the real-time three-dimensional digital twin sub-model, wherein the various model operations comprise: model rotation operation, model part enlargement operation, model part reduction operation;

In response to detecting that the patrol personnel do not perform node operation on the cable key nodes within the target time length, updating the real-time three-dimensional digital twin sub-model in real time to serve as an updated real-time three-dimensional digital twin sub-model;

And determining the updated real-time three-dimensional digital twin sub-model as a real-time three-dimensional digital twin sub-model so as to enable the patrol personnel to continue cable patrol processing.

5. A cable inspection processing device, comprising:

An acquisition unit configured to acquire a three-dimensional digital twin model, wherein the three-dimensional digital twin model is a digital twin model established for a cable region;

A determining unit configured to determine, in response to receiving patrol information for a target cable area in the cable areas, at least one piece of information to be patrol corresponding to the target cable area according to a digital twin area model corresponding to the target cable area, wherein the determining the at least one piece of information to be patrol corresponding to the target cable area includes: acquiring important sequence information of cable detection nodes aiming at the target cable area, wherein the important sequence information of the cable detection nodes represents the importance degree of each cable key node in the target cable area; according to the important sequence information of the cable detection nodes, cable key nodes in the cable key node set corresponding to the target cable area are divided in a preset proportion to generate a cable key node group set, wherein the higher the importance degree of the cable key nodes is, the fewer the number of nodes corresponding to the cable key node group is; according to the importance degree of the cable key nodes, sequentially performing node detection on each cable key node in the cable key node group to obtain target number of information to be inspected, as the at least one information to be inspected, wherein the sequentially performing node detection on each cable key node in the cable key node group to obtain target number of information to be inspected includes: for the cable key nodes to be executed in the cable key node group set, executing the following first generation steps: determining the position information of the key node of the cable to be executed in the three-dimensional digital twin model to obtain node position information; acquiring at least one adjacent cable key node in the three-dimensional digital twin model corresponding to the cable key node to be executed; acquiring three-dimensional space information aiming at the at least one adjacent cable key node, wherein the corresponding space of the three-dimensional space information is a control established by taking each node in the at least one adjacent cable key node as a vertex; performing space equal proportion multiple reduction on the three-dimensional space information to generate reduced space information; establishing detection space information taking the node position information as a center point, wherein the reduced space information corresponds to a three-dimensional space as a detection space range; generating cable external abnormality detection information for a space corresponding to the detection space information by using a cable external abnormality detection model; generating cable internal abnormality detection information of each cable in the detection space information corresponding space to obtain a cable internal abnormality detection information set; generating the information to be inspected according to the cable external abnormality detection information and the cable internal abnormality detection information set, wherein the generating the information to be inspected according to the cable external abnormality detection information and the cable internal abnormality detection information set includes: screening out cable position information corresponding to the external abnormality of the characterization cable from the external abnormality detection information of the cable to obtain at least one piece of cable position information; for each of the at least one cable position information, performing the following third generating step: generating a multi-azimuth cable map for the cable location information; acquiring a multi-azimuth historical cable graph aiming at the cable position information, wherein the historical cable graph in the multi-azimuth historical cable graph is not an abnormal cable graph; correspondingly inputting the multi-azimuth cable drawing and the multi-azimuth historical cable drawing into an image difference detection information generation model to generate multi-azimuth image difference detection information; checking whether the cable corresponding to the cable position information is abnormal according to the multi-azimuth image difference detection information to obtain first check information; performing information verification on each cable internal abnormality detection information in the cable internal abnormality detection information set to generate second verification information, and obtaining a second verification information set; generating the information to be inspected according to the obtained first check information set and the second check information set, wherein the multi-azimuth cable map and the multi-azimuth historical cable map are correspondingly input into an image difference detection information generation model to generate multi-azimuth image difference detection information, and the method comprises the following steps of: for each of the multi-azimuth cable graphs, performing the following first processing step: inputting the azimuth cable map to a cable segmentation model included in the image difference detection information generation model to generate a cable image set and a cable image position information set; inputting a target historical cable graph to a cable segmentation model included in the image difference detection information generation model to generate a historical cable image set and a historical cable image position information set; determining whether there is a difference in location information between the cable image location information set and the historical cable image location information set; generating cable image feature information corresponding to each cable image in the cable image set by using an image feature extraction model included in the image difference detection information generation model to obtain a cable image feature information set, and generating historical cable image feature information corresponding to each historical cable image in the historical cable image set to obtain a historical cable image feature information set; in response to determining that no position information difference exists, performing feature information splicing on each piece of cable image feature information in the cable image feature information set according to the priority order of the cable image position information from left to right and from top to bottom to obtain first splicing information, and performing feature information splicing on each piece of history cable image feature information in the history cable image feature information set according to the priority order of the history cable image position information from left to right and from top to bottom to obtain second splicing information; information encoding each cable image location information in the set of cable image location information to generate a set of location encoded information, and information encoding each historical cable image location information in the set of historical cable image location information to generate a set of historical location encoded information; according to the characteristic information splicing mode of the cable image characteristic information set and the characteristic information splicing mode of the historical cable image characteristic information set, respectively splicing the position coding information set and the historical position coding information set to generate first position splicing information and second position splicing information; inputting the first splicing information into a first convolutional neural network to generate a first output result, and inputting the second splicing information into a second convolutional neural network to generate a second output result; inputting the first position splicing information into a third convolutional neural network to generate a third output result, and inputting the second position splicing information into a fourth convolutional neural network to generate a fourth output result; inputting the third output result and the first output result to a fifth convolutional neural network to generate a fifth output result, and inputting the fourth output result and the second output result to a sixth convolutional neural network to generate a sixth output result; splicing the fifth output result and the first output result in a preset sequence to generate a third splicing result, and splicing the sixth output result and the second output result in a preset sequence to generate a fourth splicing result; inputting the third splicing result and the fourth splicing result into an image feature similarity weight generation model based on a multi-head attention mechanism to generate an image similarity weight matrix; splicing the fifth output result and the third output result in a preset sequence to generate a fifth splicing result, and splicing the sixth output result and the fourth output result in a preset sequence to generate a sixth splicing result; inputting the fifth splicing result and the sixth splicing result into an image position feature similarity weight generation model based on a multi-head attention mechanism to generate an image position similarity weight matrix; generating information representing the degree of difference between the azimuth cable graph and the target historical azimuth cable graph according to the image position similarity weight matrix and the image similarity weight matrix; summarizing each difference information in the obtained difference information set to generate summarized information as multi-azimuth image difference detection information;

The execution unit is configured to execute the following work order processing steps for each piece of information to be patrolled and examined in the at least one piece of information to be patrolled and examined: generating a patrol work order corresponding to the information to be patrol; matching corresponding patrol personnel information according to the work order content corresponding to the patrol work order; adding the patrol personnel information to the patrol work order to generate a complete patrol work order; and executing the complete inspection work order to monitor and control corresponding inspection personnel in real time to carry out cable inspection processing.

6. An electronic device, comprising:

One or more processors;

a storage device having one or more programs stored thereon,

When executed by the one or more processors, causes the one or more processors to implement the method of any of claims 1-4.

7. A computer readable medium having stored thereon a computer program, wherein the program when executed by a processor implements the method of any of claims 1-4.