Power grid operation area construction monitoring method, system, equipment and medium
By adopting a two-dimensional adjustment mechanism of location weight coefficient and personnel hazard coefficient in power operation construction, combined with ResNet-LSTM model and risk area behavior type weight table, the early warning level can be accurately adjusted, which solves the problem of insufficient monitoring accuracy in existing technologies and improves the safety of construction in power grid operation areas.
Patent Information
- Application Number
- CN202511771224.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-28
- Publication Date
- 2026-02-03
AI Technical Summary
In existing power operation construction monitoring, it is difficult to dynamically adjust the monitoring and early warning level according to the personnel attributes of the construction workers and the type of construction location, resulting in reduced monitoring accuracy.
By combining a location weight coefficient with a personnel risk coefficient in a two-dimensional adjustment mechanism, and integrating the coefficients of operational qualifications, training records and historical hazardous behaviors for individualized design, the early warning level can be accurately anchored. The ResNet-LSTM model is used to identify operational behaviors and to perform differentiated weighting in combination with a risk area behavior type weight table, and to carry out dynamic iteration throughout the entire cycle.
This approach achieves a high degree of alignment between early warning levels and actual risks, reducing the probability of false alarms and missed alarms, and improving the accuracy and security of monitoring.
Smart Images
Figure CN121459290A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of power construction monitoring, in particular to a power grid operation area construction monitoring method, system, device and medium. BACKGROUND
[0002] As the core infrastructure of national energy transmission, the operation area construction safety of the power grid is directly related to the stability of energy supply, the safety of operating personnel and the order of social production and life. With the advancement of China's power grid construction towards "ultra-high voltage, cross-regional and intelligent", the operation scene is becoming increasingly complex, covering 110kV and above high-voltage live substation, wild mountain power transmission tower, urban underground cable well, remote area distribution area and other multiple scenes, and the operation process involves high-risk links such as high-altitude climbing, live operation and use of heavy equipment.
[0003] However, in reality, due to the different construction qualifications and construction levels of different construction operating personnel, the risk coefficients of each construction operating personnel are different; but in the existing power operation construction monitoring, it is difficult to dynamically adjust the monitoring and warning level according to the personnel attribute and construction position area type of the construction operating personnel, which is prone to false positives or false negatives, resulting in reduced monitoring accuracy.
[0004] Therefore, the present application aims to provide a power grid operation area construction monitoring method, system, device and medium to solve the above-mentioned related problems. SUMMARY
[0005] The technical problem to be solved by the present application is that in the existing power operation construction monitoring, it is difficult to dynamically adjust the monitoring and warning level according to the personnel attribute and construction position area type of the construction operating personnel, and the purpose is to provide a power grid operation area construction monitoring method, system, device and medium, which realizes accurate anchoring of the warning level through the dual-dimension adjustment mechanism of the position weight coefficient combined with the personnel risk coefficient; relies on the risk area behavior type weight table to obtain differentiated weighting for the same behavior in different risk areas; at the same time, combined with the individualized design of the coefficients of operation qualification, training record and historical dangerous behavior, completely discards the fixed warning mode, makes the warning level highly consistent with the actual risk, reduces the probability of false positives and false negatives; at the same time, through the personnel risk coefficient closed-loop updating mechanism, the warning level is dynamically iterated throughout the cycle.
[0006] The present application is realized by the following technical solutions:
[0007] A power grid operation area construction monitoring method, the method comprising:
[0008] acquire multi-dimensional monitoring data of workers in a power grid work area and work area position information; the multi-dimensional monitoring data includes work behavior images and a worker danger coefficient; the worker danger coefficient is calculated based on worker information and historical dangerous behavior information of the workers;
[0009] input the work behavior images into a construction behavior risk monitoring model to identify a current work behavior risk, and obtain a work behavior type and an initial behavior risk level;
[0010] based on a pre-constructed risk area behavior type weight table, acquire a position weight coefficient by using the work area position information and the behavior type, and preliminarily adjust the initial behavior risk level by using the position weight coefficient to obtain an adjusted behavior risk level;
[0011] adjust the adjusted behavior risk level by using the worker danger coefficient to obtain a final behavior risk level and output a corresponding early warning signal, and update the worker danger coefficient of the corresponding worker by using the behavior risk level.
[0012] Further, the multi-dimensional monitoring data of the workers in the power grid work area is acquired, and specifically:
[0013] acquire work behavior images of the workers by using an image acquisition device, and perform portrait recognition on the workers in the work behavior images by using a portrait recognition model to obtain worker identity information of the workers;
[0014] acquire the worker danger coefficient of the workers from a worker danger coefficient database by using the worker identity information of the workers.
[0015] Further, the worker information includes historical safety training records, work experience, and construction qualification certificate levels of the workers; and the historical dangerous behavior information includes different historical behavior risk levels and corresponding historical behavior risk level times.
[0016] Further, the worker danger coefficient is calculated based on the worker information and the historical dangerous behavior information of the workers, and specifically:
[0017] according to a pre-constructed information score mapping table, set a basic information score for each worker by using the worker information of the worker;
[0018] according to the multiple historical behavior risk levels and corresponding historical behavior risk level times of each worker, obtain a risk level score of each worker based on a pre-constructed risk score mapping table;
[0019] According to the basic information score and the risk level score, a personnel risk coefficient of each worker is obtained.
[0020] Further, the construction behavior risk monitoring model adopts a pre-trained ResNet-LSTM model, and the ResNet-LSTM model comprises a ResNet module and an LSTM module; the ResNet module comprises an input layer, a convolution layer, a plurality of linear residual layers, an average pooling layer and a full connection layer connected in sequence, each linear residual layer comprises a plurality of residual blocks connected in sequence, and each residual block comprises a first 3*3 convolution unit, a first batch normalization unit, a ReLU activation unit, a second 3*3 convolution unit, a second batch normalization unit and a CBAM unit connected in sequence.
[0021] Further, the personnel risk coefficient of the corresponding worker is updated by using the behavior risk level, and specifically:
[0022] According to the current behavior risk level, the historical behavior risk level and the historical behavior risk level times of the corresponding worker are updated; and the pre-constructed risk score mapping table is used to obtain the updated risk level score of the worker;
[0023] According to the basic information score and the updated risk level score of the worker, the personnel risk coefficient is obtained and sent to the personnel risk coefficient database for data updating.
[0024] The application also provides a power grid operation area construction monitoring system, which is used in the power grid operation area construction monitoring method.
[0025] The monitoring data acquisition module is used for acquiring multi-dimensional monitoring data of workers in the power grid operation area and operation area position information; wherein the multi-dimensional monitoring data comprises operation behavior images and personnel risk coefficients; the personnel risk coefficient is calculated based on worker information and historical dangerous behavior information of the workers;
[0026] The initial risk level identification module is used for inputting the operation behavior images into the construction behavior risk monitoring model to identify the current operation behavior risk, and obtain the behavior type of the construction operation behavior and the initial behavior risk level;
[0027] The risk level adjustment module is used for querying the position weight coefficient by using the operation area position information and the behavior type based on the pre-constructed risk area behavior type weight table; and the initial behavior risk level is preliminarily adjusted by using the position weight coefficient to obtain the adjusted behavior risk level;
[0028] The risk early warning signal output module is configured to adjust the adjusted behavior risk level by using the personnel risk coefficient of the worker to obtain a final behavior risk level and output a corresponding early warning signal, and update the personnel risk coefficient of the corresponding worker by using the behavior risk level.
[0029] The application further provides a computer device comprising a system memory and a processor, wherein the system memory stores a computer program, and the processor implements the steps of the method according to any one of the preceding embodiments when executing the computer program.
[0030] The application further provides a computer readable storage medium, which stores a computer program, and the computer program implements the steps of the method according to any one of the preceding embodiments when executed by a processor.
[0031] The application further provides a computer program product comprising instructions, which, when executed by a computer device cluster, cause the computer device cluster to perform the method according to any one of the preceding embodiments.
[0032] Compared with the prior art, the application has the following advantages and beneficial effects:
[0033] In the application, the dual-dimension adjustment mechanism of the position weight coefficient combined with the personnel risk coefficient is used to realize accurate anchoring of the early warning level; the risk area behavior type weight table is used to obtain differentiated weighting of the same behavior in different risk areas; meanwhile, the coefficients of the individualized design of the combination of the operation qualification, the training record and the historical dangerous behavior are used to completely abandon the fixed early warning mode, so that the early warning level is highly consistent with the actual risk, and the occurrence probability of false positives and false negatives is reduced; meanwhile, the personnel risk coefficient closed-loop updating mechanism is used to realize the whole-cycle dynamic iteration of the early warning level. BRIEF DESCRIPTION OF DRAWINGS
[0034] In order to more clearly illustrate the technical solutions of the example embodiments of the application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only show some of the embodiments of the application, and therefore should not be considered as a limitation to the scope. For those skilled in the art, other related drawings can also be obtained without creative labor. In the drawings:
[0035] Figure 1 The figure is a method flow diagram of the power grid operation area construction monitoring method in the embodiment;
[0036] Figure 2 The figure is a model structure diagram of the ResNet-LSTM model in the embodiment;
[0037] Figure 3 The figure is a structure diagram of the residual block in the embodiment;
[0038] Figure 4 a structural schematic diagram of a CBAM unit in the embodiment;
[0039] Figure 5 a module connection schematic diagram of a power grid operation area construction monitoring system in the embodiment;
[0040] Figure 6 a structural schematic diagram of a computer device in the embodiment. DETAILED DESCRIPTION
[0041] Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, which include various details of the embodiments of the present disclosure to assist in understanding, and should be considered as merely exemplary. Thus, those of ordinary skill in the art will recognize various changes and modifications of the embodiments described herein, without departing from the scope of the present disclosure. Also, descriptions of well-known functions and structures are omitted in the following description for clarity and conciseness.
[0042] In the present disclosure, the terms "first", "second", and the like are used to describe various elements only and do not intend to limit the positional relationship, the time sequence relationship, or the importance relationship of the elements, and such terms are only used to distinguish one element from another element. In some examples, the first element and the second element can refer to the same instance of the element, and in some cases, based on the context of the description, they can also refer to different instances.
[0043] The terms used in the description of various examples in the present disclosure are only for the purpose of describing specific examples and are not intended to be limiting. Unless the number of elements is specifically limited, the element can be one or more than one, if the number of elements is not specifically limited. In addition, the term "and / or" used in the present disclosure encompasses any one of the listed items and all possible combinations thereof.
[0044] Embodiment 1
[0045] Referring to Figure 1 , Figure 1 A method flow schematic diagram of a power grid operation area construction monitoring method is shown, wherein the method comprises:
[0046] S1: obtaining multi-dimensional monitoring data of operation personnel in the power grid operation area and operation area position information; wherein the multi-dimensional monitoring data comprises operation behavior images and personnel risk coefficients; the personnel risk coefficients are calculated based on operation personnel information and historical dangerous behavior information of the operation personnel;
[0047] Specifically, in the embodiment, the multi-dimensional monitoring data of the operating personnel in the power grid operating area and the operating area position information are acquired, specifically: first, the operating behavior image of the operating personnel is acquired by using the image acquisition device, and the operating personnel in the operating behavior image is recognized by using the portrait recognition model to obtain the personnel identity information of the operating personnel;
[0048] It should be noted that in the embodiment, the portrait recognition model adopts conventional technical means in the art, which will not be described in detail here; at the same time, the personnel identity information includes the name, age and gender of the operating personnel; in other embodiments, other identity information can also be included, which will not be described in detail here.
[0049] Then, the personnel risk coefficient of the operating personnel is obtained from the personnel risk coefficient database by using the personnel identity information of the operating personnel;
[0050] It should be noted that in the embodiment, the personnel risk coefficient database is obtained in advance, and the personnel risk coefficient database stores the personnel risk coefficient corresponding to each operating personnel, and the corresponding personnel risk coefficient can be queried in the database by the personnel identity information of the operating personnel; at the same time, in the embodiment, an operating personnel information database is also provided, which stores the operating personnel information of each operating personnel, and the corresponding operating personnel information can be queried from the database by the personnel identity information of the operating personnel; the operating personnel information database is connected with the State Grid management system, and the operating personnel information of the State Grid management system is used to update the database in real time.
[0051] Finally, the operating area position information is obtained according to the installation position of the image acquisition device or through the monitoring position information bound in advance by the image acquisition device; this technical content is a conventional technical means in the art, which will not be described in detail here.
[0052] At the same time, in the embodiment, the personnel risk coefficient is calculated based on the operating personnel information and the historical dangerous behavior information of the operating personnel, specifically: according to the pre-constructed information score mapping table, the operating personnel information of each operating personnel is used to set a basic information score for each operating personnel;
[0053] It should be noted that in the embodiment, the operating personnel information includes the historical safety training record, working years and construction qualification certificate level of the operating personnel; in other embodiments, other information settings can also be used, which will not be limited here;
[0054] The pre-constructed information score mapping table is shown in Table 1 below; the historical safety training record refers to the number of safety training of the operating personnel in the past three years, and the final basic information score is the sum of the corresponding training score, years score and qualification score;
[0055] Table 1 Information Score Mapping Table
[0056] Historical safety training record Training score Work experience Experience score Construction qualification level Qualification score [0,1] 5 [0,1] 5 Level 1 5 [2,4] 4 [2,4] 4 Level 2 4 [4,6] 3 [5,7] 3 Level 3 3 [7,10] 2 [8,10] 2 Level 4 2 [10,+∞] 1 [11,+∞] 1 Level 5 1
[0057] Based on each worker's multiple historical behavioral risk levels and the corresponding number of times each historical behavioral risk level was recorded, a risk level score for each worker was obtained using a pre-built risk score mapping table. The worker's personnel hazard coefficient was then calculated based on the basic information score and the risk level score. The personnel hazard coefficient is calculated as follows: Personnel Hazard Coefficient = Basic Information Score + Risk Level Score
[0058] It should be noted that, in this embodiment, the historical dangerous behavior information includes different historical behavior risk levels and the number of times each historical behavior risk level is reached; in other embodiments, other information settings may also be used, and no further restrictions are imposed here.
[0059] The risk score mapping table constructed in advance is shown in Table 2 below; the risk level score is obtained by adding up all the scores of the worker's behaviors based on the risk level of the worker's historical behaviors and the corresponding number of times they have been triggered in the past five years.
[0060] Table 2 Risk Score Mapping Table
[0061] Historical behavior risk level Times Behavior score Historical behavior risk level Times Behavior score Level 1 [0,1] 1 Level 3 [5, +∞] 5 Level 1 [2,4] 2 Level 4 [0,1] 4 Level 1 [5, +∞] 3 Level 4 [2,4] 5 Level 2 [0,1] 2 Level 5 [5, +∞] 6 Level 2 [2,4] 3 Level 5 [0,1] 6 Level 3 [5, +∞] 4 Level 5 [2,4] 7 Level 3 [0,1] 3 Figure 2 [5, +∞] 8 Figure 2 [2,4] 4
[0062] S2: Input the image of the work behavior into the construction behavior risk monitoring model to identify the current work behavior risk and obtain the behavior type and initial behavior risk level of the construction work behavior;
[0063] Specifically, in this embodiment, the construction behavior risk monitoring model adopts a pre-trained ResNet-LSTM model, see [link to relevant documentation]. Figure 3 , Figure 3 The diagram illustrates the model structure of the ResNet-LSTM model, which includes a ResNet module and an LSTM module. The ResNet module comprises a sequentially connected input layer, convolutional layer, multiple linear residual layers, an average pooling layer, and a fully connected layer. Each linear residual layer includes multiple sequentially connected residual blocks. (See [link to documentation]). Figure 4 , Figure 4 A schematic diagram of the residual block structure is shown, wherein each residual block includes a first 3×3 convolutional unit, a first batch normalization unit, a ReLU activation unit, a second 3×3 convolutional unit, a second batch normalization unit, and a CBAM unit connected in sequence; the LSTM module includes multiple LSTM units; see [link to documentation]. Operation not standardized , No safety helmet A schematic diagram of the CBAM unit is shown;
[0064] The image of the work operation is input into a convolutional layer through an input layer, and image features are extracted through a 7×7 convolutional layer. The extracted image features are then sequentially input into multiple linear residual layers to extract deeper image features. After pooling and mapping processing by average pooling layers and fully connected layers, the image features are output to the LSTM module. The LSTM module classifies and identifies the image features to obtain the behavior type of the final construction operation. Finally, by extracting and constructing a behavior type level reference table, an initial behavior risk level is assigned to the behavior type of the construction operation.
[0065] It should be noted that in this embodiment, the number of linear residual layers is 4, and the number of residual blocks in each linear residual layer is 2; in other embodiments, other numbers can also be set; at the same time, the behavior types include non-standard operation, not wearing a safety helmet, not carrying a safety belt, entering a high-risk area in violation of regulations, and using tools improperly; and the above behavior types are divided into five initial behavior risk levels; the specific classification method depends on the actual situation and is not restricted in detail here.
[0066] S3: Based on the pre-built risk area behavior type weight table, the location weight coefficient is obtained by querying the work area location information and behavior type; and the initial behavior risk level is initially adjusted using the location weight coefficient to obtain the adjusted behavior risk level; where, risk level = location weight coefficient × initial behavior risk level;
[0067] It should be noted that in this embodiment, the work area location information includes extremely high-risk areas, high-risk areas, medium-risk areas, and low-risk areas. The constructed risk area behavior type weight table is shown in Table 3 below:
[0068] Table 3. Weighting Table of Behavioral Types in Risk Areas
[0069] No safety belt Illegal entry into high-risk area Non-standard use of tools Extremely high-risk area High-risk area Medium-risk area 1.4 1.5 1.6 1.8 1.4 Low-risk area 1.3 1.4 1.4 1.3 Behavior risk level 1.1 1.2 1.1 1.1 Personnel risk coefficient x adjusted behavior risk level 0.9 0.9 0.8 0.8
[0070] S4: Adjust the adjusted behavioral risk level using the personnel hazard coefficient of the workers to obtain the final behavioral risk level and output the corresponding early warning signal. At the same time, update the personnel hazard coefficient of the corresponding workers using the behavioral risk level.
[0071] Specifically, in this embodiment, the adjusted behavioral risk level is adjusted using the personnel hazard coefficient of the operator to obtain the final behavioral risk level and output the corresponding early warning signal. Specifically, the behavioral risk level = personnel hazard coefficient × adjusted behavioral risk level. The behavioral risk level is finally divided into five levels according to the result calculated by the above formula. The specific classification is shown in Table 4 below. The corresponding early warning strategy signal is output according to the behavioral risk level.
[0072] Table 4 Behavioral Risk Level Classification Table
[0073] Early warning strategy Level 1 No early warning Level 2 [0,20] Green early warning Level 3 (20,50] Blue early warning Level 4 (50,80] Yellow early warning Level 5 (80,120] Red early warning Figure 5 (120, +∞] Figure 6
[0074] It should be noted that, in this embodiment, after a green warning signal is triggered, an alarm signal is sent to the operator's terminal to remind the operator to follow the prescribed work procedures; after a blue warning signal is triggered, in addition to the green warning signal, an on-site audible and visual alarm is also triggered to further remind the operator; after a yellow warning signal is triggered, in addition to the blue warning signal, an alarm signal is sent to the safety officer's terminal to remind the safety officer to go to the designated location for verification; after a red warning signal is triggered, in addition to the green warning signal, work is immediately stopped, personnel are evacuated, and potential risks are investigated.
[0075] Meanwhile, in this embodiment, the personnel risk coefficient of the corresponding operator is updated using the behavioral risk level. Specifically, the historical behavioral risk level and the number of times the historical behavioral risk level is updated for the corresponding operator based on the current behavioral risk level; then, the updated risk level score of the operator is obtained using a pre-built risk score mapping table; and finally, the personnel risk coefficient is obtained based on the operator's basic information score and the updated risk level score, and sent to the personnel risk coefficient database for data update.
[0076] Specifically, in this embodiment, a dual-dimensional adjustment mechanism combining location weight coefficients and personnel risk coefficients is used to accurately anchor the warning level; relying on the risk area behavior type weight table, the same behavior receives differentiated weights in different risk areas; at the same time, by combining the individualized design of coefficients based on integrated work qualifications, training records and historical dangerous behaviors, the fixed warning mode is completely abandoned, making the warning level highly consistent with the actual risk and reducing the probability of false alarms and missed alarms; and at the same time, a closed-loop update mechanism for personnel risk coefficients is used to achieve dynamic iteration of the warning level throughout the entire cycle.
[0077] Example 2
[0078] See The present invention also provides a power grid operation area construction monitoring system, which is used in any of the above-described power grid operation area construction monitoring methods, the system comprising:
[0079] The monitoring data acquisition module 100 is used to acquire multi-dimensional monitoring data of workers in the power grid operation area and the location information of the operation area; wherein, the multi-dimensional monitoring data includes images of work behavior and personnel risk coefficients; the personnel risk coefficients are calculated based on worker information and historical risk behavior information of workers;
[0080] The initial risk level identification module 200 is used to input the operation behavior image into the construction behavior risk monitoring model, identify the current operation behavior risk, and obtain the behavior type and initial behavior risk level of the construction operation behavior;
[0081] The risk level adjustment module 300 is used to obtain the location weight coefficient based on the pre-built risk area behavior type weight table, using the work area location information and behavior type query; and to use the location weight coefficient to perform preliminary adjustment on the initial behavior risk level to obtain the adjusted behavior risk level.
[0082] The risk warning signal output module 400 is used to adjust the adjusted behavioral risk level by using the personnel risk coefficient of the operator to obtain the final behavioral risk level and output the corresponding warning signal. At the same time, it uses the behavioral risk level to update the personnel risk coefficient of the corresponding operator.
[0083] It should be noted that the modules in the system of Embodiment 2 correspond to the steps in the method of Embodiment 1. The steps in the method of Embodiment 1 have been described in detail in Embodiment 1, and the module content in the system will not be described in detail in this Embodiment 2.
[0084] Example 3
[0085] See This embodiment also provides a computer device, including a system memory 1005 and a processor 1001. The system memory 1005 stores a computer program, and the processor 1001 executes the computer program to implement the steps of any of the methods described above.
[0086] It should be noted that the processor 1001 is used to execute the steps in the above method embodiments according to the instructions in the program code. Alternatively, when the processor 1001 executes the computer program, it implements the functions of each module / unit in the above system / device embodiments.
[0087] Specifically, in this embodiment, the computer program can be divided into one or more modules / units. One or more modules / units are stored in the system memory 1005 and executed by the processor 1001 to complete this application. One or more modules / units can be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program in the terminal device.
[0088] The terminal device can be a desktop computer, laptop, handheld computer, or cloud server, etc. The terminal device may include, but is not limited to, a processor 1001 and a system memory 1005. Those skilled in the art will understand that this does not constitute a limitation on the terminal device, which may include more or fewer components than shown, or a combination of certain components, or different components. For example, the terminal device may also include an input / output device 1003, a network access device 1002, a bus 1006, etc.
[0089] The processor 1001 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.
[0090] System memory 1005 can be an internal storage unit of the terminal device, such as a hard drive or RAM. System memory 1005 can also be a storage device 1004 of the terminal device, such as an external hard drive, SmartMedia Card (SMC), Secure Digital (SD) card, or FlashCard. Furthermore, system memory 1005 can include both internal storage units and storage device 1004. System memory 1005 is used to store computer programs and other programs and data required by the terminal device. System memory 1005 can also be used to temporarily store data that has been output or will be output.
[0091] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.
[0092] Example 4
[0093] This embodiment provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the methods described above.
[0094] The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), registers, hard disks, optical fibers, compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof, or any other form of computer-readable storage medium in the art.
[0095] An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and storage medium can reside within an application-specific integrated circuit (ASIC). In embodiments of the invention, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device.
[0096] Example 5
[0097] This embodiment also provides a computer program product containing instructions that, when executed by a cluster of computer devices, cause the cluster of computer devices to perform the method described in Embodiment 1.
[0098] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.
Claims
1. A method for monitoring construction in a power grid operation area, characterized in that the method... include: Acquire multi-dimensional monitoring data of workers within the power grid operation area, as well as the location information of the operation area; wherein, the multi-dimensional monitoring data includes images of work behavior and personnel risk coefficients; the personnel risk coefficients are calculated based on worker information and historical hazardous behavior information of workers; The images of the work activities are input into the construction behavior risk monitoring model to identify the risks of the current work activities and obtain the behavior type and initial risk level of the construction work activities. Based on a pre-built risk area behavior type weight table, the location weight coefficient is obtained by querying the work area location information and behavior type; and the initial behavior risk level is preliminarily adjusted using the location weight coefficient to obtain the adjusted behavior risk level. The adjusted behavioral risk level is adjusted using the personnel hazard coefficient of the workers to obtain the final behavioral risk level and output the corresponding early warning signal. At the same time, the personnel hazard coefficient of the corresponding workers is updated using the behavioral risk level.
2. The method for monitoring construction in a power grid operation area according to claim 1, characterized in that, Obtain multi-dimensional monitoring data of personnel working within the power grid operation area, specifically: The image acquisition device is used to acquire images of the workers' work behavior, and at the same time, the facial recognition model is used to perform facial recognition on the workers in the work behavior images to obtain the workers' identity information. Using the worker's identity information, the worker's risk factor is retrieved from the personnel risk factor database.
3. The method for monitoring construction in a power grid operation area according to claim 1, characterized in that, The operator information includes the operator's historical safety training records, years of service, and construction qualification certificate level; the historical hazardous behavior information includes different historical behavior risk levels and the number of times each historical behavior risk level is recorded.
4. The method for monitoring construction in a power grid operation area according to claim 3, characterized in that, The personnel risk factor is calculated based on the information of the workers and their historical hazardous behavior information, specifically: Based on the pre-built information score mapping table, a basic information score is set for each operator using their operator information; Based on each worker's multiple historical behavioral risk levels and the corresponding number of times each historical behavioral risk level was recorded, a risk level score for each worker was obtained using a pre-built risk score mapping table. The personnel hazard coefficient for each worker is determined based on the basic information score and risk level score.
5. The method for monitoring construction in a power grid operation area according to claim 1, characterized in that, The construction behavior risk monitoring model adopts a pre-trained ResNet-LSTM model, which includes a ResNet module and an LSTM module. The ResNet module includes an input layer, a convolutional layer, multiple linear residual layers, an average pooling layer, and a fully connected layer connected in sequence. Each linear residual layer includes multiple residual blocks connected in sequence. Each residual block includes a first 3×3 convolutional unit, a first batch normalization unit, a ReLU activation unit, a second 3×3 convolutional unit, a second batch normalization unit, and a CBAM unit connected in sequence.
6. The method for monitoring construction in a power grid operation area according to claim 1, characterized in that, The personnel hazard coefficient of the corresponding workers is updated based on the behavioral risk level, specifically as follows: Based on the current behavioral risk level, the historical behavioral risk level and the number of times the corresponding behavioral risk level is updated for the corresponding worker; then, using the pre-built risk score mapping table, the updated risk level score for the worker is obtained. Based on the worker's basic information score and updated risk level score, the worker's risk coefficient is obtained and sent to the worker risk coefficient database for data update.
7. A construction monitoring system for power grid operation areas, characterized in that, This system is used in a construction monitoring method for a power grid operation area as described in any one of claims 1-6, the system comprising: The monitoring data acquisition module is used to acquire multi-dimensional monitoring data of workers within the power grid operation area and the location information of the operation area; wherein, the multi-dimensional monitoring data includes images of work behavior and personnel risk coefficients; the personnel risk coefficients are calculated based on worker information and historical hazardous behavior information of workers; The initial risk level identification module is used to input the operation behavior image into the construction behavior risk monitoring model, identify the current operation behavior risk, and obtain the behavior type and initial behavior risk level of the construction operation behavior; The risk level adjustment module is used to obtain the location weight coefficient based on the pre-built risk area behavior type weight table, using the work area location information and behavior type query; and to use the location weight coefficient to perform preliminary adjustment on the initial behavior risk level to obtain the adjusted behavior risk level. The risk warning signal output module is used to adjust the adjusted behavioral risk level based on the personnel risk coefficient of the workers to obtain the final behavioral risk level and output the corresponding warning signal. At the same time, it uses the behavioral risk level to update the personnel risk coefficient of the corresponding workers.
8. A computer device comprising a system memory and a processor, wherein the system memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method described in any one of claims 1 to 6.
10. A computer program product containing instructions, characterized in that, When the instructions are executed by a cluster of computer devices, the cluster of computer devices causes the cluster of computer devices to perform the method as described in any one of claims 1 to 6.