Communication engineering construction site anomaly detection method and system based on visual identification

Abstract

The invention relates to the technical field of visual identification, and discloses a communication engineering construction site anomaly detection method and system based on visual identification, and the system comprises a video monitoring system and a monitoring scheduling system. The monitoring scheduling system comprises a monitoring scheduling information acquisition unit for acquiring associated information of a monitoring scheduling task and a monitoring scheduling unit for generating a monitoring scheduling plan, and the monitoring scheduling unit comprises a monitoring task identification module and a scheduling plan generation module. Wherein the task identification module is used for identifying a monitoring task of a next scheduling period from associated information for monitoring a scheduling task; according to the invention, intelligent distribution of dynamic monitoring tasks can be carried out according to real-time changes of a construction site and various environmental data, so that key links are ensured to be monitored preferentially.

Description

Technical Field

[0001] The present invention relates to the field of visual recognition technology, and more specifically, to a method and system for detecting anomalies at a communication engineering construction site based on visual recognition. Background Art

[0002] On-site monitoring and management of communication projects is a necessary means to ensure construction safety, quality and timely completion of projects. Traditional monitoring methods usually rely on manual inspections and fixed camera systems, which have the following shortcomings:

[0003] Lack of real-time performance: Fixed monitoring equipment cannot fully cover dynamic and rapidly changing construction areas, resulting in delayed monitoring information.

[0004] Waste of resources: Manual inspection requires a lot of manpower and time, is inefficient and unsustainable.

[0005] Lack of intelligence: Traditional monitoring systems usually rely on preset plans and lack the ability to make adjustments based on real-time on-site conditions. Summary of the invention

[0006] The present invention provides a method and system for detecting anomalies at a construction site of a communication engineering project based on visual recognition, which solves the technical problem in related technologies that monitoring relies on preset schemes and cannot be flexibly adjusted.

[0007] The present invention provides a communication engineering construction site anomaly detection system based on visual recognition, including a video monitoring system, the video monitoring system including an image acquisition unit arranged at a monitoring point, an image storage device for storing images acquired by the image acquisition unit, and further including:

[0008] A monitoring and scheduling system, comprising a monitoring and scheduling information acquisition unit for acquiring associated information of monitoring and scheduling tasks and a monitoring and scheduling unit for generating a monitoring and scheduling plan, wherein the monitoring and scheduling unit comprises a monitoring task identification module and a scheduling plan generation module, wherein the task identification module is used to identify the monitoring tasks of the next scheduling cycle from the associated information of the monitoring and scheduling tasks, and the scheduling plan generation module is used to analyze and obtain the monitoring and scheduling plan of the next scheduling cycle from the associated information of the monitoring and scheduling tasks and the monitoring tasks of the next scheduling cycle; the monitoring and scheduling plan includes the location of the monitoring points of the next scheduling cycle and / or the monitoring tasks that need to be implemented at each monitoring point.

[0009] Furthermore, the associated information of the monitoring scheduling task includes the task plan of the communication project, the information of the monitoring tasks implemented in the historical scheduling cycle, the information of the monitoring points in the historical scheduling cycle, and the information of the subtasks of the communication project performed in the historical scheduling cycle.

[0010] Furthermore, the task plan of the communication project is an orderly arrangement of all subtasks of the communication project, and is the information on the order in which all subtasks are to be implemented.

[0011] Furthermore, the associated information of the monitoring and scheduling tasks is structured before being input into the monitoring and scheduling unit to obtain ordered information in two structural dimensions. The basic structural elements included in the first structural dimension are objects, including: monitoring points, communication links, monitoring tasks, subtasks, and construction areas; the basic structural elements included in the second structural dimension are timing units.

[0012] Furthermore, the method for processing and obtaining the orderliness information includes:

[0013] Objects for extracting orderliness information;

[0014] Monitoring point object: represents a monitoring point;

[0015] Communication link object: represents the communication link between monitoring points or the communication link between a monitoring point and an image storage device;

[0016] Monitoring task object: represents a monitoring task;

[0017] Subtask object: represents a subtask of a communication project;

[0018] Construction area object: represents a construction area;

[0019] Extract specific features associated with the object, and divide the extracted specific features into multiple parts according to the scheduling period, and map one part to a timing unit. The order of the timing units is consistent with the time order of the scheduling period of the specific features.

[0020] Establishing a mapping between the extracted objects and their associated specific features;

[0021] For any two objects, if there is a correlation between the associated specific features related to the monitoring and scheduling task or there is a correlation between the objects related to the monitoring and scheduling task, an object relationship is established between the two objects.

[0022] Furthermore, the correlations related to the monitoring and scheduling tasks include:

[0023] The monitoring points are adjacent in space;

[0024] The monitoring point is connected with the communication link;

[0025] The image acquisition unit at the monitoring point performs the monitoring task;

[0026] Monitor the association between tasks and subtasks;

[0027] The monitoring point is located in the construction area;

[0028] Association of subtasks with construction areas.

[0029] Furthermore, a deep learning model is used as a monitoring and scheduling unit, and the deep learning model includes a first graph network layer, a first timing layer, a first output layer, a second graph network layer, a second timing layer, a feature fusion layer and a second output layer, wherein the first graph network layer inputs the associated information of the monitoring and scheduling task, outputs the first hidden feature to the first timing layer, the first timing layer outputs the second hidden feature to the first output layer and the feature fusion layer, the second graph network layer inputs the associated information of the monitoring and scheduling task, outputs the third hidden feature to the second timing layer, the second timing layer outputs the fourth hidden feature to the feature fusion layer, the feature fusion layer outputs the fused feature to the second output layer, the first output layer outputs the result of the monitoring task of the next scheduling cycle, and the second output layer outputs the result of the monitoring scheduling plan of the next scheduling cycle.

[0030] Further, the first graph network layer, the first temporal layer, and the first output layer constitute a task identification module;

[0031] The second graph network layer, the second timing layer, the feature fusion layer and the second output layer constitute a scheduling plan generation module.

[0032] The present invention provides a method for detecting anomalies at a construction site of a communication engineering project based on visual recognition, comprising the following steps:

[0033] Get the associated information of monitoring and scheduling tasks;

[0034] Identify the monitoring task of the next scheduling cycle from the associated information of the monitoring scheduling task;

[0035] Analyze and obtain the monitoring scheduling plan for the next scheduling period from the associated information of the monitoring scheduling task and the monitoring tasks of the next scheduling period;

[0036] The monitoring scheduling plan includes the location of the monitoring points in the next scheduling cycle and / or the monitoring tasks to be implemented at each monitoring point;

[0037] Execute monitoring scheduling plan and arrange image acquisition units;

[0038] Read the image data collected by the image acquisition unit and identify the image data to perform monitoring tasks.

[0039] The present invention provides a computer-readable storage medium for storing computer-readable instructions, which, when read by a computer, can run the aforementioned visual recognition-based communication engineering construction site anomaly detection system.

[0040] The beneficial effects of the present invention are as follows: the present invention can intelligently allocate dynamic monitoring tasks according to real-time changes at the construction site and various environmental data to ensure that key links are monitored first;

[0041] In a changing environment and multiple possible locations, choose the best monitoring point deployment location to better perform future monitoring tasks and improve monitoring effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a module schematic diagram of a communication engineering construction site anomaly detection system based on visual recognition of the present invention;

[0043] Figure 2 is an example of a mission plan for communications engineering;

[0044] Figure 3 is an example of a monitoring task implemented in a historical scheduling cycle;

[0045] Figure 4 is an example of a monitoring point in a historical scheduling cycle;

[0046] Figure 5 is an example of the division of monitoring areas;

[0047] Figure 6 is an example of a matrix output by the second output layer;

[0048] Figure 7 is an example of another matrix output by the second output layer. DETAILED DESCRIPTION

[0049] The subject matter described herein will now be discussed with reference to example implementations. It should be understood that the discussion of these implementations is only to enable those skilled in the art to better understand and implement the subject matter described herein, and the functions and arrangements of the elements discussed may be changed without departing from the scope of protection of the present specification. Various examples may omit, replace, or add various processes or components as needed. In addition, the features described in some examples may also be combined in other examples.

[0050] First of all, it should be noted that performing monitoring tasks based on image information to identify image content is a general technology, which includes a video monitoring system 101 for collecting images and an algorithm for identifying image content. The algorithm for identifying image content includes mature algorithms or models such as the YOLO (You Only Look Once) algorithm.

[0051] The application of video surveillance system 101 in communication engineering construction includes many aspects such as progress, quality, safety, cost, and coordination;

[0052] Security applications include:

[0053] Analysis of hazard sources at the construction site:

[0054] There are many sources of danger at the construction site of communication construction projects, such as high-altitude operations, electrical operations, mechanical equipment operations, etc. Analyzing these sources of danger can help workers better understand the safety risks at the construction site and take corresponding preventive measures.

[0055] Safety of working at heights:

[0056] High-altitude work is a common work content in communication construction projects, and it is also one of the important sources of danger at the construction site. When performing high-altitude work, workers must strictly abide by relevant safety operating procedures, wear safety belts, safety helmets and other protective equipment to ensure their own safety.

[0057] Electrical work safety:

[0058] Electrical work involves electrical equipment and power lines, which poses a risk of electric shock. When performing electrical work, workers must ensure that the equipment is powered off and wear protective equipment such as insulating gloves to avoid electric shock accidents.

[0059] Mechanical equipment operation safety:

[0060] Commonly used mechanical equipment in communication construction projects include cranes, hanging baskets, etc. These equipment are prone to cause accidental injuries if they are not operated properly. When operating mechanical equipment, workers must receive professional training and be familiar with the operating procedures to ensure the safe and stable operation of the equipment.

[0061] The video surveillance system 101 can capture the dynamics of the construction site in real time, and provide detailed information about the construction progress to project managers and related managers, helping them to better track and control the project.

[0062] The real-time images recorded by the video surveillance system 101 can be used to track the progress against the construction plan. Managers can play back the surveillance video to confirm whether the construction is carried out according to the planned schedule or what deviations exist. In order to improve efficiency, intelligent video analysis technology can be used to analyze the video content through algorithms, automatically identify the differences between the construction progress and the plan, and give corresponding reports.

[0063] The column header for an example of a set of construction progress identification is as follows:

[0064] |Serial number|Construction area|Task description|Start time|End time|Efficiency evaluation|.

[0065] Project quality is the core issue of construction management. Using video surveillance technology, quality problems can be discovered in time during the construction process to ensure that the construction quality meets the standards.

[0066] Analysis of key points of quality control:

[0067] Video surveillance can be used to monitor key quality control points during the construction process. For example, during key processes such as steel bar tying and concrete pouring, high-definition cameras can be installed for real-time monitoring. Once quality deviations are found, construction personnel can be notified immediately to make corrections.

[0068] Tracing and handling of quality issues:

[0069] When quality problems occur, video surveillance data can be used as historical data for problem tracing. By analyzing the links where the problems occurred, the causes can be found, and corresponding corrective measures can be taken to prevent future construction. Using video technology to trace back the construction process can provide strong evidence for quality analysis and management.

[0070] Video surveillance can not only improve the visual management of construction quality and progress, but can also be directly applied to control project costs.

[0071] Construction of cost monitoring indicator system:

[0072] Cost control requires the construction of an indicator system that covers all key cost factors. For example, monitoring the usage of materials, the operating time of equipment, etc. By combining video monitoring with sensor data, real-time monitoring of these key indicators can be achieved.

[0073] Resource allocation and scheduling optimization:

[0074] Video surveillance can provide information about the use of resources under actual construction conditions, including manpower, equipment and materials. This can provide a basis for resource allocation and scheduling, reduce resource waste and optimize costs.

[0075] At least one embodiment of the present invention discloses a communication engineering construction site anomaly detection system based on visual recognition, such as Figure 1 As shown, including:

[0076] The video monitoring system 101 includes an image acquisition unit disposed at a monitoring point, an image storage for storing images acquired by the image acquisition unit, and a monitoring dynamic control unit for calculating and reasoning to obtain the optimal location of the monitoring point (the actual physical arrangement of the image acquisition unit still needs to be completed manually or by automated mechanical equipment);

[0077] The monitoring and scheduling system 102 includes a monitoring and scheduling information acquisition unit 1021 for acquiring associated information of monitoring and scheduling tasks and a monitoring and scheduling unit 1022 for generating a monitoring and scheduling plan, wherein the monitoring and scheduling unit includes a monitoring task identification module 10221 and a scheduling plan generation module 10222, wherein the task identification module 10221 is used to identify the monitoring task of the next scheduling cycle from the associated information of the monitoring and scheduling tasks, and the scheduling plan generation module 10222 is used to analyze the associated information of the monitoring and scheduling tasks and the monitoring tasks of the next scheduling cycle to obtain the monitoring scheduling plan of the next scheduling cycle; the monitoring and scheduling plan includes at least the location of the monitoring point of the next scheduling cycle, and may also include the monitoring tasks that need to be implemented at each monitoring point.

[0078] In one embodiment of the present invention, the associated information of the monitoring scheduling task includes the task plan of the communication project, the information of the monitoring tasks implemented in the historical scheduling cycle, the information of the monitoring points in the historical scheduling cycle, and the information of the subtasks of the communication project performed in the historical scheduling cycle;

[0079] The task plan of a communication project can be an ordered arrangement of all subtasks of the communication project, which is the information of the order in which all subtasks are implemented. It can also be sorted in the form of task clusters. A task cluster contains multiple subtasks. Task clusters are sorted, and subtasks within the same task cluster are also sorted.

[0080] The monitoring task information includes the type of monitoring task, the description text of the monitoring task and the monitoring result record of the monitoring task.

[0081] In one embodiment of the present invention, the monitoring tasks include types of progress, quality, safety, cost, and collaboration;

[0082] It also includes construction site hazard analysis, height operation safety, electrical operation safety, mechanical equipment operation safety, and resource usage types.

[0083] Some of these types are hierarchical. For example, safety-type monitoring tasks include construction site hazard analysis, height operation safety, electrical operation safety, and mechanical equipment operation safety monitoring tasks. However, it is understandable that a monitoring task may not have only one type.

[0084] In one embodiment of the present invention, the associated information of the monitoring and scheduling tasks is structured before being input into the monitoring and scheduling unit to obtain ordered information of two structural dimensions. The basic structural elements included in the first structural dimension are objects, including: monitoring points, communication links, monitoring tasks, subtasks, and construction areas (referring to the division of the area that can be affected by the construction of the communication project, which can be the division based on sub-projects or the result of grid division); the basic structural elements included in the second structural dimension are time sequence units;

[0085] Methods for processing and obtaining ordered information include:

[0086] Objects for extracting orderliness information;

[0087] Monitoring point object: represents a monitoring point;

[0088] Communication link object: represents the communication link between monitoring points or the communication link between a monitoring point and an image storage device;

[0089] Monitoring task object: represents a monitoring task;

[0090] Subtask object: represents a subtask of a communication project;

[0091] Construction area object: represents a construction area;

[0092] Extract specific features associated with the object, and divide the extracted specific features into multiple parts according to the scheduling period, and map one part to a timing unit. The order of the timing units is consistent with the time order of the scheduling period of the specific features.

[0093] Establishing a mapping between the extracted objects and their associated specific features;

[0094] Specific features associated with monitoring points: location of monitoring points;

[0095] Specific characteristics associated with communication link objects:

[0096] The starting point and end point of a communication link: Indicates the connection source and destination of the link.

[0097] Link bandwidth and latency: performance metrics that describe a communication link.

[0098] Link status: reflects the availability and health of the link in real time.

[0099] Monitors specific characteristics associated with task objects:

[0100] Monitoring Task Type: Indicates whether it is a progress, safety, quality, cost or coordination type of monitoring task.

[0101] Priority of monitoring tasks: Priority determines the execution order of tasks or the monitoring frequency.

[0102] Monitoring results: result data or evaluation information obtained after task execution.

[0103] Task Description: Briefly describe the purpose and operational requirements of the monitoring task.

[0104] Specific features of subtask object associations:

[0105] Subtask start and end times: Identify the planned time frame for each subtask.

[0106] Subtask dependencies: Describes the dependencies between this subtask and other tasks.

[0107] Resource requirements of subtasks: personnel, equipment, materials, etc. required to perform the subtasks.

[0108] Subtask completion status: Track the completion progress of subtasks in real time.

[0109] Specific features associated with construction area objects:

[0110] Geographic location of the construction area: Specific construction area coordinates or location description.

[0111] Construction environmental conditions: climate, geology and other environmental factors in the construction area.

[0112] Safety level of the construction area: Safety risk assessment of the area.

[0113] Construction impact scope: the surrounding environment and areas that may be affected by the construction in this area.

[0114] For any two objects, if there is a correlation between the associated specific features related to the monitoring and scheduling task or there is a correlation between the objects related to the monitoring and scheduling task, an object relationship is established between the two objects;

[0115] In some embodiments of the present invention, the associations related to the monitoring scheduling task include:

[0116] The monitoring points are adjacent in space;

[0117] The monitoring point is connected with the communication link;

[0118] The image acquisition unit at the monitoring point performs the monitoring task;

[0119] Monitor the association between tasks and subtasks;

[0120] The monitoring point is located in the construction area;

[0121] Association of subtasks with construction areas.

[0122] In one embodiment of the present invention, the length of a scheduling cycle is 3-20 days, and the next monitoring scheduling plan is executed at the end of each scheduling cycle.

[0123] This scheduling cycle is generally proportional to the scale of the communication project construction, because the overall engineering environment changes more slowly in larger-scale construction, and the frequency of monitoring and scheduling can be lower.

[0124] In one embodiment of the present invention, a deep learning model is used as a monitoring and scheduling unit, and the deep learning model includes a first graph network layer, a first timing layer, a first output layer, a second graph network layer, a second timing layer, a feature fusion layer and a second output layer, wherein the first graph network layer inputs the associated information of the monitoring and scheduling task, outputs the first hidden feature to the first timing layer, the first timing layer outputs the second hidden feature to the first output layer and the feature fusion layer, the second graph network layer inputs the associated information of the monitoring and scheduling task, outputs the third hidden feature to the second timing layer, the second timing layer outputs the fourth hidden feature to the feature fusion layer, the feature fusion layer outputs the fused feature to the second output layer, the first output layer outputs the result of the monitoring task of the next scheduling period, and the second output layer outputs the result of the monitoring scheduling plan of the next scheduling period.

[0125] The first graph network layer, the first temporal layer, and the first output layer constitute the task identification module;

[0126] The second graph network layer, the second timing layer, the feature fusion layer, and the second output layer constitute a scheduling plan generation module 10222;

[0127] In the aforementioned embodiments of the present invention, although a monitoring scheduling plan is provided, it does not exclude or hinder manual adjustment of the monitoring scheduling plan.

[0128] In one embodiment of the present invention, the first graph network layer and the second graph network layer both adopt a multi-layer structure, and the calculation formula of the first layer is as follows:

[0129]

[0130] represents the object recognition feature of the vth object in the lth layer, represents the object recognition feature of the u-th object in the l-1th layer, and Respectively represent the set of objects that have object relationships with object v and object u, represents the cardinality of a set, represents the plane recognition weight matrix of the first data structure recognition layer, , E represents the total number of layers, when l=1 , Represents the feature associated with the u-th object, when l=E is equal to the first or third hidden feature of object v (the first graph network layer outputs the first hidden feature, and the second graph network layer outputs the third hidden feature, but the trainable parameters of the first graph network layer and the second graph network layer are different), is the sigmoid function.

[0131] Both the first temporal layer and the second temporal layer adopt a temporal neural network, such as RNN, LSTM or GRU.

[0132] An expression of the first and second timing layers is as follows:

[0133]

[0134]

[0135]

[0136]

[0137] and : The activation vector of the reset gate and update gate at step t;

[0138] : Candidate state generated in step t;

[0139] : The second or fourth hidden feature of the tth step (the first temporal layer outputs the second hidden feature, and the second temporal layer outputs the fourth hidden feature);

[0140] : 1st, 2nd, 3rd, 4th, 5th, 6th transformation matrices (trainable parameters);

[0141] : 1st, 2nd, 3rd deviations (trainable parameters);

[0142] r∈G, G represents the set of all objects, t∈{1, 2, 3, …, n}, t=1 ;

[0143] , It represents the first hidden feature of the object v output when the t-th time sequence unit is input into the first graph network layer or the third hidden feature of the object v output when it is input into the second graph network layer. Represents the collection of all objects;

[0144] : Sigmoid activation function;

[0145] : tanh activation function;

[0146] The expression of the feature fusion layer is as follows:

[0147]

[0148] in represents the fusion feature, represents the concatenation function, and They represent the second and fourth hidden features of the nth step respectively, and n is the total number of sequential units.

[0149] In one embodiment of the present invention, the first output layer outputs a matrix, in which a component of a row vector of the matrix represents the probability of a monitoring task in a task library being selected, and the monitoring task with the highest probability in a row vector is selected as the monitoring task for the next scheduling cycle.

[0150] The task library refers to a library that stores monitoring tasks that may exist in the current communication project.

[0151] In one embodiment of the present invention, the construction area of ​​the entire communication project is discretized into multiple grids, each grid can be arranged with a monitoring point, and the location of the monitoring point can be represented by the ID of the grid;

[0152] The second output layer outputs a matrix. The cth component of the i-th row vector of the matrix represents the probability of the i-th monitoring point selecting the c-th position. The position with the largest probability value is selected as the position of the i-th monitoring point in the next scheduling cycle.

[0153] Furthermore, the second output layer is divided into two layers. The first layer outputs a matrix. The cth component of the i-th row vector of the matrix represents the probability of the i-th monitoring point selecting the c-th position. The position with the largest probability value is selected as the position of the i-th monitoring point in the next scheduling cycle.

[0154] The second layer outputs a matrix. The cth component of the i-th row vector of the matrix represents the probability of the i-th monitoring point selecting the c-th monitoring task. The monitoring task with the largest probability value is selected as the monitoring task of the i-th monitoring point in the next scheduling cycle.

[0155] Data preparation:

[0156] When building such a deep learning model, you need to prepare the following types of data:

[0157] Geographic data: including grid information of the construction area to facilitate the location of monitoring points.

[0158] Task data: Information base of monitoring tasks, including task type, priority, etc.

[0159] Historical monitoring data: includes monitoring tasks, their effects and feedback within past scheduling cycles.

[0160] The task plan of communication engineering is as follows Figure 2 As shown;

[0161] Examples of monitoring tasks implemented in historical scheduling cycles are Figure 3 As shown;

[0162] An example of the information of monitoring points in the historical scheduling cycle is as follows: Figure 4 As shown;

[0163] Examples of monitoring area division include Figure 5 shown.

[0164] Data preprocessing:

[0165] Data preprocessing is critical to ensuring the accuracy and efficiency of deep learning models, including:

[0166] Data cleaning: remove duplicate and erroneous data and fill in missing values.

[0167] Normalization: Scaling numerical data to a common scale, such as [0, 1], to enhance the convergence of deep learning models.

[0168] Feature selection: Select features that have a greater impact on the prediction results based on the relevance and importance of the data.

[0169] Data Splitting: Divide the dataset into training, validation, and test sets.

[0170] Deep learning model training:

[0171] The deep learning model first trains the task recognition module through supervised learning;

[0172] Then, the scheduling plan generation module 10222 is trained through reinforcement learning. Reinforcement learning is suitable for dynamic decision-making problems and can learn and improve through interaction with the environment. The training process of the deep learning model is as follows:

[0173] State definition: Order information.

[0174] Action space: Alternative monitoring schedules.

[0175] Reward function: Design a reward mechanism based on optimizing the completion of monitoring tasks, maximizing efficiency, and minimizing resource usage to drive the deep learning model to learn in the direction of improving the overall effect.

[0176] Reinforcement learning algorithm selection: such as Q-learning or Proximal Policy Optimization (PPO).

[0177] Training process: Continuously iterate in a simulation environment, and the deep learning model gradually optimizes the strategy through trial and error.

[0178] like Figure 6 The following is an example of a matrix output by the second output layer: Figure 7 Shown is an example of another matrix output by the second output layer.

[0179] The above describes an embodiment of the present invention, but this embodiment is not limited to the above-mentioned specific implementation mode. The above-mentioned specific implementation mode is merely illustrative and not restrictive. Under the guidance of this embodiment, ordinary technicians in this field can also make more forms of equivalent embodiments, all of which are within the protection of this embodiment.

Claims

1. A communication engineering construction site anomaly detection system based on visual recognition, comprising a video monitoring system, the video monitoring system comprising an image acquisition unit arranged at a monitoring point, and an image storage device for storing images acquired by the image acquisition unit, characterized in that: Also includes: A monitoring and scheduling system, comprising a monitoring and scheduling information acquisition unit for acquiring associated information of monitoring and scheduling tasks and a monitoring and scheduling unit for generating a monitoring and scheduling plan, wherein the monitoring and scheduling unit comprises a monitoring and scheduling task identification module and a scheduling plan generation module, wherein the task identification module is used to identify the monitoring tasks of the next scheduling cycle from the associated information of the monitoring and scheduling tasks, and the scheduling plan generation module is used to analyze and obtain the monitoring and scheduling plan of the next scheduling cycle from the associated information of the monitoring and scheduling tasks and the monitoring tasks of the next scheduling cycle; The monitoring scheduling plan includes the location of the monitoring points in the next scheduling period and / or the monitoring tasks that need to be implemented at each monitoring point.

2. According to claim 1, a communication engineering construction site anomaly detection system based on visual recognition is characterized in that: The associated information of the monitoring and scheduling tasks includes the task plan of the communication project, the information of the monitoring tasks implemented in the historical scheduling cycle, the information of the monitoring points in the historical scheduling cycle, and the information of the subtasks of the communication project performed in the historical scheduling cycle.

3. According to claim 2, a communication engineering construction site anomaly detection system based on visual recognition is characterized in that: The task plan of a communication project is an orderly arrangement of all subtasks of the communication project and the information on the order in which all subtasks should be implemented.

4. According to the visual recognition-based communication engineering construction site anomaly detection system according to claim 1, it is characterized in that: The associated information of the monitoring and scheduling tasks is structured before being input into the monitoring and scheduling unit to obtain the ordered information of two structural dimensions. The basic structural elements included in the first structural dimension are objects, including: monitoring points, communication links, monitoring tasks, subtasks, and construction areas; the basic structural elements included in the second structural dimension are timing units.

5. According to the visual recognition-based communication engineering construction site anomaly detection system according to claim 1, it is characterized in that: Methods for processing and obtaining ordered information include: Objects for extracting orderliness information; Monitoring point object: represents a monitoring point; Communication link object: represents the communication link between monitoring points or the communication link between a monitoring point and an image storage device; Monitoring task object: represents a monitoring task; Subtask object: represents a subtask of a communication project; Construction area object: represents a construction area; Extract specific features associated with the object, and divide the extracted specific features into multiple parts according to the scheduling period, and map one part to a timing unit. The order of the timing units is consistent with the time order of the scheduling period of the specific features. Establishing a mapping between the extracted objects and their associated specific features; For any two objects, if there is a correlation between the associated specific features related to the monitoring and scheduling task or there is a correlation between the objects related to the monitoring and scheduling task, an object relationship is established between the two objects.

6. A communication engineering construction site anomaly detection system based on visual recognition according to claim 5, characterized in that: The dependencies related to monitoring and scheduling tasks include: The monitoring points are adjacent in space; The monitoring point is connected with the communication link; The image acquisition unit at the monitoring point performs the monitoring task; Monitor the association between tasks and subtasks; The monitoring point is located in the construction area; Association of subtasks with construction areas.

7. The communication engineering construction site anomaly detection system based on visual recognition according to claim 1 is characterized in that: A deep learning model is used as a monitoring and scheduling unit. The deep learning model includes a first graph network layer, a first timing layer, a first output layer, a second graph network layer, a second timing layer, a feature fusion layer and a second output layer. The first graph network layer inputs the associated information of the monitoring and scheduling task, outputs the first hidden feature to the first timing layer, the first timing layer outputs the second hidden feature to the first output layer and the feature fusion layer, the second graph network layer inputs the associated information of the monitoring and scheduling task, outputs the third hidden feature to the second timing layer, the second timing layer outputs the fourth hidden feature to the feature fusion layer, the feature fusion layer outputs the fused feature to the second output layer, the first output layer outputs the result of the monitoring task of the next scheduling period, and the second output layer outputs the result of the monitoring scheduling plan of the next scheduling period.

8. A communication engineering construction site anomaly detection system based on visual recognition according to claim 7, characterized in that: The first graph network layer, the first temporal layer, and the first output layer constitute the task identification module; The second graph network layer, the second timing layer, the feature fusion layer and the second output layer constitute a scheduling plan generation module.

9. A method for detecting abnormalities at a communication engineering construction site based on visual recognition, characterized in that: The following steps are involved: Get the associated information of monitoring and scheduling tasks; Identify the monitoring task of the next scheduling cycle from the associated information of the monitoring scheduling task; Analyze and obtain the monitoring scheduling plan for the next scheduling period from the associated information of the monitoring scheduling task and the monitoring tasks of the next scheduling period; The monitoring scheduling plan includes the location of the monitoring points in the next scheduling cycle and / or the monitoring tasks to be implemented at each monitoring point; Execute monitoring scheduling plan and arrange image acquisition units; Read the image data collected by the image acquisition unit and identify the image data to perform monitoring tasks.

10. A computer-readable storage medium, characterized in that: It is used to store computer-readable instructions, and when the computer-readable instructions are read by a computer, it can run the communication engineering construction site anomaly detection system based on visual recognition as described in any one of claims 1-8.

Images