Power transmission line hidden danger risk prediction method and system based on multi-source information fusion

Abstract

The invention provides a multi-source information fusion power transmission line hidden danger risk prediction method and system, and the method comprises the steps: judging whether a power transmission line hidden danger target moves to a power transmission line region or not, and determining the size of the power transmission line hidden danger target and the distance between the power transmission line hidden danger target and the power transmission line region; and comprehensively obtaining the final risk level of the power transmission line area. According to the method, multiple algorithms are integrated for collaborative judgment, richer data support can be provided, the accuracy of potential risk prediction of the power transmission line area is improved, resource allocation is optimized before risks occur, and unnecessary economic losses are reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field related to the detection of transmission lines, and particularly relates to a hidden danger risk prediction method and system for transmission lines with multi-source information fusion. Background Technique

[0002] The statements in this part only provide background technical information related to the present invention and do not necessarily constitute prior art.

[0003] Currently, the perception and discovery of hidden danger risks in transmission lines in the market mainly rely on various single technologies, such as image recognition, short video monitoring, three-dimensional ranging, or sound recognition. Although these technologies each have certain advantages, they have not been effectively integrated. In addition, existing algorithms usually improve performance through training, but do not fully consider user behavior, resulting in the inability to understand the subjective intentions of users. With the increase in edge devices, the workload of users has become increasingly heavy.

[0004] In the prior art, the current market system overly relies on the image recognition algorithm of a single manufacturer and lacks the integration technology of the results of multiple algorithms, resulting in poor effects in discovering hidden dangers. The poor linkage between the AI algorithm and user intentions: The current market systems mainly include technologies such as image recognition, short video monitoring, three-dimensional ranging, or sound recognition. Although each has its own advantages, the model is limited to recognition and does not consider from the perspective of users, with a low level of intelligence. The results of different intelligent recognition technologies are stored separately and displayed separately on the web platform, lacking effective combination calculation and display of data.

[0005] In summary, how to improve the accuracy of risk prediction for the transmission line area is a problem that needs to be solved currently. Summary of the Invention

[0006] To overcome the deficiencies of the above prior art, the present invention provides a hidden danger risk prediction method and system for transmission lines with multi-source information fusion, which comprehensively uses multiple algorithms for collaborative determination, can provide richer data support, improve the accuracy of potential risk prediction for the transmission line area, optimize resource allocation before the occurrence of risks, and reduce unnecessary economic losses.

[0007] To achieve the above object, the present invention adopts the following technical solutions:

[0008] In the first aspect, the present invention provides a hidden danger risk prediction method for transmission lines with multi-source information fusion, including:

[0009] Determine whether the hidden danger target of the transmission line moves towards the transmission line area according to the relative position and direction of the center point of the current hidden danger image of the hidden danger target of the transmission line with respect to the center point of the previous hidden danger image;

[0010] If the hidden danger target of the transmission line moves towards the transmission line area, according to the size and type of the hidden danger target of the transmission line, and combined with three-dimensional ranging, the distance between the hidden danger target of the transmission line and the transmission line area is obtained;

[0011] Weights are assigned to the result of moving the hidden danger target of the transmission line towards the transmission line area, the size and type of the hidden danger target of the transmission line, and the distance between the hidden danger target of the transmission line and the transmission line area, to obtain the final risk level of the transmission line area.

[0012] In a second aspect, the present invention provides a hidden danger risk prediction system for transmission lines with multi-source information fusion, including:

[0013] A movement determination module, which is configured to: determine whether the hidden danger target of the transmission line moves towards the transmission line area according to the relative position and direction of the center point of the current hidden danger image of the hidden danger target of the transmission line and the center point of the previous hidden danger image;

[0014] A target size and distance determination module, which is configured to: if the hidden danger target of the transmission line moves towards the transmission line area, according to the size and type of the hidden danger target of the transmission line, and combined with three-dimensional ranging, obtain the distance between the hidden danger target of the transmission line and the transmission line area;

[0015] A risk level determination module, which is configured to: assign different weights to the result of moving the hidden danger target of the transmission line towards the transmission line area, the size and type of the hidden danger target of the transmission line, and the distance between the hidden danger target of the transmission line and the transmission line area, to obtain the final risk level of the transmission line area.

[0016] In a third aspect, the present invention provides an electronic device, including a memory and a processor, and computer instructions stored on the memory and running on the processor. When the computer instructions are run by the processor, the method described in the first aspect is completed.

[0017] In a fourth aspect, the present invention provides a computer-readable storage medium for storing computer instructions. When the computer instructions are executed by a processor, the method described in the first aspect is completed.

[0018] In a fifth aspect, the present invention provides a computer program product, including a computer program. When the computer program is executed by a processor, the method described in the first aspect is implemented.

[0019] The above one or more technical solutions have the following beneficial effects:

[0020] In the present invention, by determining whether the hidden danger target of the transmission line moves towards the transmission line area, as well as the size of the hidden danger target of the transmission line and the distance between the hidden danger target of the transmission line and the transmission line area, the final risk level of the transmission line area is comprehensively obtained. The present invention conducts collaborative determination by integrating multiple algorithms, can provide richer data support, improve the accuracy of predicting potential risks in the transmission line area, optimize resource allocation before the occurrence of risks, and reduce unnecessary economic losses.

[0021] Advantages of additional aspects of the present invention will be given in part in the following description, become apparent in part from the following description, or be understood through the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings forming a part of this specification are used to provide a further understanding of the present invention. The schematic embodiments and descriptions thereof of the present invention are used to explain the present invention and do not constitute an improper limitation to the present invention.

[0023] Figure 1 It is a flowchart of a method for predicting hidden danger risks of a transmission line with multi-source information fusion in the first embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] It should be noted that the following detailed descriptions are all exemplary and are intended to provide further explanations of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs.

[0025] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present invention.

[0026] In the case of no conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other.

[0027] Embodiment 1

[0028] As Figure 1 shown, this embodiment discloses a method for predicting hidden danger risks of a transmission line with multi-source information fusion, including:

[0029] Determine whether the hidden danger target of the transmission line moves towards the transmission line area according to the relative position and direction of the center point of the current hidden danger image of the hidden danger target of the transmission line and the center point of the previous hidden danger image;

[0030] If the hidden danger target of the transmission line moves towards the transmission line area, determine the distance between the hidden danger target of the transmission line and the transmission line area according to the size and type of the hidden danger target of the transmission line and by combining three-dimensional ranging;

[0031] The results of moving the hidden danger target of the transmission line to the transmission line area, the size and type of the hidden danger target of the transmission line, and the distance between the hidden danger target of the transmission line and the transmission line area are given different weights to obtain the final risk level of the transmission line area.

[0032] In this embodiment, according to the relative position and direction of the center point of the current hidden danger image of the hidden danger target of the transmission line and the center point of the previous hidden danger image, it is determined whether the hidden danger target of the transmission line moves towards the transmission line area. Specifically:

[0033] According to the coordinates of the center point of the current hidden danger image of the hidden danger target of the transmission line and the coordinates of the center point of the previous hidden danger image, the moving direction of the hidden danger target of the transmission line is determined;

[0034] Based on the moving direction of the hidden danger target of the transmission line and combined with the direction of the hidden danger target of the transmission line relative to the transmission line area, it is determined whether the hidden danger target of the transmission line moves towards the transmission line area.

[0035] Specifically, considering the center point (Ccurrent) of the hidden danger target box of the transmission line and the center point (Cprevious) of the hidden danger target box of the previous transmission line, by comparing the positions of these two center points, the moving direction and risk level of the hidden danger target of the transmission line can be determined.

[0036] The center point C of the hidden danger target box of the transmission line can be calculated by the following formula:

[0037] C = ((xmin + xmax) / 2, (ymin + ymax) / 2)

[0038] Among them, xmin and xmax are the minimum and maximum coordinates of the hidden danger box in the horizontal direction; ymin and ymax are the minimum and maximum coordinates of the hidden danger box in the vertical direction.

[0039] The coordinates of the center point Ccurrent of the current hidden danger box and the center point Cprevious of the previous hidden danger box are respectively: Ccurrent = (xcurrent, ycurrent), Cprevious = (xprevious, yprevious)

[0040] Calculate the moving direction:

[0041] Direction = (xcurrent - xprevious, ycurrent - yprevious)

[0042] This direction vector indicates the movement of the hidden danger box:

[0043] If xcurrent - xprevious > 0, it means moving to the right in the horizontal direction; if it is less than 0, it means moving to the left.

[0044] If ycurrent - yprevious > 0, it means moving upward in the vertical direction; if it is less than 0, it means moving downward.

[0045] In this embodiment, the size of the hidden danger target of the transmission line is determined according to its size in the image, specifically:

[0046] Sactual = Simage × d / (f × scale)

[0047] Where Sactual is the actual physical size of the hidden danger target of the transmission line; Simage is the pixel size occupied by the hidden danger target of the transmission line in the image, which is a key index for judging whether the target is a "small target", and the display size of the target in the image is obtained by returning the hidden danger coordinate points through the target monitoring algorithm; f is the focal length of the camera, usually in meters (m), and the focal length affects the magnification of the image. The longer the focal length, the larger the target appears in the image; d is the distance between the hidden danger target of the transmission line and the camera, which is calculated by forming a triangle with the three-dimensional point cloud and the installation height. The farther the distance, the fewer pixels the target occupies in the image, so the distance has a great influence on the target size; scale is a scale factor used to convert the actual size into pixel values in the image. For example, 1 meter may be set to 1000 pixels, and this factor converts the calculation result into the unit used in the image coordinate system, so that the target size can be visualized in the image.

[0048] In this embodiment, judging a small target at a short distance:

[0049] If the target distance d < dnear: Check the actual size S of the target actual < Snear.

[0050] Where d is the distance between the hidden danger target of the transmission line and the camera; dnear is the distance threshold for small targets at a short distance, in meters. Snear is the actual size threshold for small targets at a short distance, used to judge whether the target meets the criteria of a small target within a short distance range.

[0051] If it is satisfied, the target is determined to be a small target at a short distance.

[0052] Judging a small target at a medium distance:

[0053] If dnear ≤ d < dfar: Check S actual > Smid.

[0054] Among them, dfar is the distance threshold for long-distance determination, in meters. If the target distance is greater than this value, the target is regarded as a small long-distance target; Smid is the actual size threshold for small medium-distance targets, used to determine whether the target meets the criteria for small targets within the medium-distance range;

[0055] If satisfied, the target is determined to be a small medium-distance target.

[0056] Judging small long-distance targets:

[0057] If d ≥ dfar: Check S actual > Sfar.

[0058] Among them, Sfar is the actual size threshold for small long-distance targets, used to determine whether the size of the target meets the criteria for small targets within the long-distance range.

[0059] If satisfied, the target is determined to be a small long-distance target.

[0060] In this embodiment, it also includes obtaining the sound signal of the transmission line area, identifying the obtained sound signal of the transmission line area to determine whether there is an abnormal sound. When there is an abnormal sound, assign a corresponding weight to the abnormal sound, and combine the result of the transmission line hidden danger target moving towards the transmission line area and the corresponding weight, the size of the transmission line hidden danger target and the corresponding weight, the distance between the transmission line hidden danger target and the transmission line area and the corresponding weight, and finally determine the final risk level of the transmission line hidden danger target.

[0061] This embodiment also includes performing type recognition on the transmission line hidden danger target, inputting the images containing the transmission line hidden danger target into different models for hidden danger recognition respectively. Each model outputs recognition results, including information such as hidden danger type, location, confidence level, etc.; standardize this information into a unified format, such as JSON or XML; merge the recognition results of the three models into a comprehensive result program, and use the dead letter queue + cache invalidation key to form a unified result set;

[0062] If different models have repeated recognition of the same hidden danger, the above duplicate removal process needs to be performed. At the same time, the following two special settings are supported. One is to support setting a threshold (such as confidence level) to select the final result, and the other is to support erasing the overlapping area of the images to form a polygon hidden danger box.

[0063] Since the performance of the models is different, different weights can be assigned to each model, and the results are weighted and combined to obtain the final hidden danger recognition result.

[0064] The core purpose of the hidden danger rejudgment technology is to dynamically adjust the risk score of hidden dangers according to the user's behavior feedback. When the system evaluates hidden dangers, the user's input or behavior can be used as the basis for the system to adjust the risk assessment results. For example:

[0065] The user believes that a detected hidden danger is not real or has little impact;

[0066] After the user intervenes in a hidden danger, they believe that the impact of this hidden danger on the system is low.

[0067] The user's behavior and feedback can affect the rejudgment of hidden dangers in the following aspects:

[0068] User feedback: When the user sees a hidden danger on the interface and marks it as "low risk" or "non-real hidden danger", the system needs to dynamically adjust the risk score of this hidden danger according to these feedbacks.

[0069] User interaction data: Whether the user has taken countermeasures (such as ignoring, marking as risk-free, or having been repaired) to deal with the hidden danger. If the user has been ignoring this hidden danger and has not taken measures, it can be inferred that the risk of this hidden danger is low for the user.

[0070] Historical behavior patterns: Based on the user's historical decision-making patterns, the system can infer the user's attitude towards hidden dangers. For example, a certain user has often ignored a certain type of specific hidden danger in the past.

[0071] Assuming the original risk score is Rorig and the user feedback adjustment factor is αfeedback, the adjusted risk score Radjusted can be expressed as:

[0072] Radjusted = Rorig × (1 - αfeedback)

[0073] Among them, Rorig is the risk score of the hidden danger initially calculated by the system. αfeedback is the adjustment factor based on user feedback, reflecting the actual degree of risk of the hidden danger considered by the user. For example, if the user believes that the risk of this hidden danger is small, αfeedback will be close to 0; if the user believes that the risk is large, then αfeedback is higher.

[0074] Considering whether the user has taken actual actions to deal with the hidden danger (such as ignoring, repairing, etc.), assuming the user behavior intervention factor is αintervention, the adjusted risk score can be expressed as:

[0075] Rfinal = Radjusted × (1 - αintervention)

[0076] Where: αintervention is an adjustment factor reflecting the user's intervention behavior. If the user takes repair or intervention measures, αintervention will be relatively high, indicating that the risk is reduced; if the user does not respond or ignores the hidden danger, αintervention will be relatively low.

[0077] The final risk score can be calculated by integrating the adjustment factors of user feedback and behavioral intervention:

[0078] Rtotal = Rorig × (1 - αfeedback) × (1 - αintervention)

[0079] To further precisely adjust the risk score, it is usually necessary to set the threshold and weight of the risk score. For example, even if the user feedback for some hidden dangers is of low risk, they may not be completely ignored due to their relatively large potential impact on the system. At this time, the system can set a minimum risk score threshold to ensure that the scores of some high-risk hidden dangers are not completely reduced due to user feedback.

[0080] Assume that the final risk score of a certain hidden danger is Rtotal, and the system can set a threshold Rmin to ensure that this hidden danger is not misjudged as low risk:

[0081] Rfinal = max(Rtotal, Rmin)

[0082] In this embodiment, RI: Hidden danger movement risk score (risk severity * confidence level); RS: Voice recognition risk score (risk severity * confidence level); RD: Hidden danger distance risk score (risk severity * confidence level); RT: Hidden danger target size and type (risk severity * confidence level); All risk scores are integrated together to obtain the final comprehensive risk score Rtotal (comprehensive risk score):

[0083] Rtotal = wI * RI + wS * RS + wD * RD + wT * RT

[0084] Define the weights of each score. These weights can be adjusted according to the actual situation and the sum is 1, that is, wI + wS + wD + wT = 1.

[0085] Based on the comprehensive risk score Rtotal, risk judgment is carried out, the risk level is defined, and finally the aggregation result is formed and displayed to the user.

[0086] In this embodiment, an innovative hidden danger rejudgment technology based on user behavior is used. Combining multiple factors such as intrusion into the protection area, determination of moving hidden dangers, determination of small targets at a long distance, hidden danger multi-layer deduplication technology, user's daily click false alarm records, user's daily click alarm records, and user's daily click non-alarm records, the results of each algorithm are rejudged, achieving improved accuracy of hidden danger identification, reduced user work burden, and enhanced system intelligence level.

[0087] This embodiment proposes a collaborative analysis technology for the output results of multiple algorithms, mainly including the following two aspects: First, a multi-class image hidden danger analysis and recognition access technology is established, which supports the summary of the results after the same image is recognized by multiple algorithms. Second, when the image recognition detects the risk of external force damage, the sound recognition also captures abnormal sounds. Combining with the information of three-dimensional ranging, it can effectively judge whether the construction activity is within the risk range. This comprehensive analysis method helps to deeply understand the relationship between construction activities and line risks, thus providing more insightful decision-making support.

[0088] Through the dual fusion of algorithms and results, this embodiment can significantly improve the monitoring accuracy and efficiency of the system, ensure the early discovery and accurate judgment of external force damage during power transmission site construction, and reduce the risks of false alarms and missed alarms.

[0089] This embodiment combines multiple algorithms and their results, which can provide richer data support for the management level, thereby helping decision-makers make more reasonable and scientific safety management decisions.

[0090] Through the fusion technology, this embodiment can better identify and warn of potential risks of power transmission lines, thereby optimizing resource allocation before the risks occur and reducing unnecessary economic losses.

[0091] Embodiment 2

[0092] The purpose of this embodiment is to provide a hidden danger risk prediction system for power transmission lines that fuses multi-source information, including:

[0093] A movement determination module configured to: determine whether a hidden danger target of a power transmission line moves towards the power transmission line area according to the relative position and direction of the center point of the current hidden danger image of the hidden danger target of the power transmission line and the center point of the previous hidden danger image;

[0094] A target size and distance determination module configured to: if the hidden danger target of the power transmission line moves towards the power transmission line area, determine the distance between the hidden danger target of the power transmission line and the power transmission line area according to the size and type of the hidden danger target of the power transmission line and in combination with three-dimensional ranging;

[0095] A risk level determination module, which is configured to: assign different weights to the result of moving the hidden danger target of the transmission line towards the transmission line area, the size and type of the hidden danger target of the transmission line, and the distance between the hidden danger target of the transmission line and the transmission line area, so as to obtain the final risk level of the transmission line area.

[0096] In more embodiments, there is also provided:

[0097] An electronic device includes a memory, a processor, and computer instructions stored on the memory and running on the processor. When the computer instructions are run by the processor, the method described in Embodiment 1 is completed. For the sake of brevity, it will not be elaborated here.

[0098] It should be understood that in this embodiment, the processor may be a central processing unit CPU, and the processor may also be other general-purpose processors, digital signal processors DSP, application-specific integrated circuits ASIC, off-the-shelf programmable gate arrays FPGA, or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0099] The memory may include a read-only memory and a random access memory, and provide instructions and data to the processor. A part of the memory may also include a non-volatile random access memory. For example, the memory may also store information about the device type.

[0100] A computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by the processor, the method described in Embodiment 1 is completed.

[0101] The method in Embodiment 1 can be directly embodied as being executed and completed by a hardware processor, or by a combination of hardware and software modules in the processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory, and the processor reads the information in the memory and combines its hardware to complete the steps of the above method. To avoid repetition, it will not be described in detail here.

[0102] A computer program product includes a computer program. When the computer program is executed by the processor, the method described in Embodiment 1 is implemented and completed.

[0103] The present invention also provides at least one computer program product tangibly stored on a non-transitory computer-readable storage medium. The computer program product includes computer-executable instructions, such as instructions included in program modules, which are executed in a device on a target real or virtual processor to perform the processes / methods described above. Generally, program modules include routines, programs, libraries, objects, classes, components, data structures, etc. that perform specific tasks or implement specific abstract data types. In various embodiments, the functions of program modules can be combined or divided as needed among program modules. The machine-executable instructions for program modules can be executed within local or distributed devices. In a distributed device, program modules can be located in local and remote storage media.

[0104] The computer program code for implementing the method of the present invention can be written in one or more programming languages. This computer program code can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the program code is executed by the computer or other programmable data processing device, the functions / operations specified in the flowchart and / or block diagram are implemented. The program code can be executed entirely on the computer, partially on the computer, as a stand-alone software package, partially on the computer and partially on a remote computer, or entirely on a remote computer or server.

[0105] In the context of the present invention, the computer program code or related data can be carried by any suitable carrier so that a device, apparatus, or processor can perform the various processes and operations described above. Examples of carriers include signals, computer-readable media, etc. Examples of signals can include electrical, optical, radio, acoustic, or other forms of propagated signals, such as carrier waves, infrared signals, etc.

[0106] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in conjunction with this embodiment can be implemented by electronic hardware or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. A professional technician can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of this application.

[0107] Although the specific implementation manners of the present invention have been described above in conjunction with the accompanying drawings, it is not a limitation on the protection scope of the present invention. Those skilled in the art should understand that based on the technical solution of the present invention, various modifications or deformations that can be made by those skilled in the art without creative efforts are still within the protection scope of the present invention.

Claims

1. A hidden danger risk prediction method for transmission lines with multi-source information fusion, characterized in that Including: Determine whether the hidden danger target of the transmission line moves towards the transmission line area according to the relative position and direction between the center point of the current hidden danger image of the hidden danger target of the transmission line and the center point of the previous hidden danger image; If the hidden danger target of the transmission line moves towards the transmission line area, determine the distance between the hidden danger target of the transmission line and the transmission line area according to the size and type of the hidden danger target of the transmission line and in combination with three-dimensional ranging; Assign different weights to the result of the movement of the hidden danger target of the transmission line towards the transmission line area, the size and type of the hidden danger target of the transmission line, and the distance between the hidden danger target of the transmission line and the transmission line area to obtain the final risk level of the transmission line area.

2. The method for predicting hidden danger risks of a transmission line with multi-source information fusion according to claim 1, characterized in that Determine whether the hidden danger target of the transmission line moves towards the transmission line area according to the relative position and direction between the center point of the current hidden danger image of the hidden danger target of the transmission line and the center point of the previous hidden danger image. Specifically: Determine the moving direction of the hidden danger target of the transmission line according to the coordinates of the center point of the current hidden danger image of the hidden danger target of the transmission line and the coordinates of the center point of the previous hidden danger image; Based on the moving direction of the hidden danger target of the transmission line and in combination with the direction of the hidden danger target of the transmission line relative to the transmission line area, determine whether the hidden danger target of the transmission line moves towards the transmission line area.

3. The hidden danger risk prediction method for a transmission line with multi-source information fusion according to claim 1, characterized in that, Determine the target size according to the size of the hidden danger target of the transmission line in the image. Specifically: Sactual = Simage×d / (f×scale) Where, Sactual is the actual physical size of the hidden danger target of the transmission line, Simage is the pixel size occupied by the hidden danger target of the transmission line in the image, f is the focal length of the camera, d is the distance between the hidden danger target of the transmission line and the camera, and scale is the scale factor.

4. A hidden danger risk prediction method for a transmission line with multi-source information fusion according to claim 1, characterized in that It also includes obtaining the sound signal of the transmission line area, identifying the obtained sound signal of the transmission line area to determine whether there is an abnormal sound. When there is an abnormal sound, assign the corresponding weight to the abnormal sound, and in combination with the result of the movement of the hidden danger target of the transmission line towards the transmission line area and the corresponding weight, the size of the hidden danger target of the transmission line and the corresponding weight, the distance between the hidden danger target of the transmission line and the transmission line area and the corresponding weight, finally determine the final risk level of the hidden danger target of the transmission line.

5. A hidden danger risk prediction method for a transmission line with multi-source information fusion according to claim 1, characterized in that, It also includes: Dynamically adjust the final risk level through the adjustment factor reflecting the user intervention behavior. Specifically: Rtotal = Rorig×(1 - αfeedback)×(1 - αintervention) Where, Rorig is the initially calculated hidden danger risk score, αfeedback is the adjustment factor based on user feedback, reflecting the actual degree of the hidden danger risk considered by the user; αintervention is the adjustment factor reflecting the user intervention behavior.

6. The hidden danger risk prediction method for transmission lines with multi-source information fusion according to claim 1, characterized in that, According to the distance between the hidden danger target of the transmission line and the camera, in combination with the set distance thresholds for long-distance determination and short-distance determination, determine whether the hidden danger target of the transmission line is a short-distance target, a medium-distance target or a long-distance target.

7. A hidden danger risk prediction system for transmission lines with multi-source information fusion, characterized in that, Including: A movement determination module, which is configured to: determine whether a hidden danger target of a transmission line moves towards the transmission line area according to the relative position and direction of the center point of the current hidden danger image of the hidden danger target of the transmission line with respect to the center point of the previous hidden danger image; A target size and distance determination module, which is configured to: if the hidden danger target of the transmission line moves towards the transmission line area, determine the distance between the hidden danger target of the transmission line and the transmission line area according to the size and type of the hidden danger target of the transmission line and in combination with three-dimensional ranging; A risk level determination module, which is configured to: assign different weights to the result of the movement of the hidden danger target of the transmission line towards the transmission line area, the size and type of the hidden danger target of the transmission line, and the distance between the hidden danger target of the transmission line and the transmission line area, so as to obtain the final risk level of the transmission line area.

8. An electronic device, characterized in that, Comprising a memory, a processor, and computer instructions stored on the memory and running on the processor, when the computer instructions are run by the processor, the method according to any one of claims 1-6 is completed.

9. A computer-readable storage medium, characterized in that, For storing computer instructions, when the computer instructions are executed by the processor, the method according to any one of claims 1-6 is completed.

10. A computer program product, characterized in that, Comprising a computer program, when the computer program is executed by the processor, the method according to any one of claims 1-6 is implemented.

Images