Remote dispatching method and system for roadbed and pavement construction equipment

Abstract

The invention relates to the technical field of remote scheduling, in particular to a remote scheduling method and system for roadbed and pavement construction equipment, and the method comprises the following steps: carrying out the division based on task units, recognizing an equipment track inflection point and an operation state conversion sudden change interval, analyzing the equipment operation direction consistency and operation state distribution, and evaluating the linkage task scheduling efficiency. And analyzing a stress distribution trend of the construction area, calibrating an abnormal level, identifying a corresponding number, and outputting an intelligent collaborative scheduling instruction set of the construction equipment. According to the method, by accurately extracting and analyzing the running track and the operation state of the equipment, the abnormal interval and the deviation area can be effectively recognized, resource allocation can be balanced, operation consistency can be improved, resource waste and low efficiency caused by improper task allocation can be avoided, risk level calibration of task units can be achieved, and the method is suitable for popularization and application. Potential problems are found in advance, effective countermeasures are taken, scheduling decision precision and flexibility are improved, and efficient and smooth execution of construction tasks is ensured.

Description

Technical Field

[0001] This invention relates to the field of remote scheduling technology, and in particular to a method and system for remote scheduling of roadbed and pavement construction equipment. Background Technology

[0002] Remote dispatching technology falls under the category of information management and control applications. Its core aspects include real-time coordination and unified arrangement of work equipment, personnel, and work progress in a distributed environment; cross-regional data transmission via communication networks; and unified resource scheduling and utilization through positioning, monitoring, and task allocation. In this field, remote dispatching involves not only the collection and transmission of equipment operating status data but also the sequential management of work processes based on the collected information and the handling of abnormal situations during the work process, thus forming a comprehensive technical system covering data acquisition, data transmission, task instruction issuance, and execution feedback. Traditional remote dispatching methods for roadbed and pavement construction equipment involve manually collecting the operating location and status of construction vehicles and machinery during road construction. Dispatchers then allocate tasks based on experience or predetermined construction plans, relying on telephones, walkie-talkies, or simple information transmission terminals for communication. Dispatching instructions are mostly issued manually, and equipment operating information collection largely depends on manual recording or fixed-point detection. Systematic remote management is achieved through a single communication network and basic data reporting.

[0003] Current technologies rely on manual collection of equipment location and operational status, issuing task instructions via telephone, walkie-talkie, or simple information transmission methods. This lack of real-time, systematic data monitoring and analysis easily leads to problems such as inaccurate task allocation and uneven resource utilization. Equipment operation information collection depends on manual recording or fixed-point detection, making it difficult to promptly detect abnormal or deviating equipment behavior. This makes it difficult for dispatchers to effectively control changes during construction, thus affecting overall construction efficiency and quality. For example, inconsistent orientation or uneven load at task unit boundaries is difficult to quickly identify manually, resulting in resource waste and construction delays. Summary of the Invention

[0004] The purpose of this invention is to overcome the shortcomings of the existing technology and to propose a method and system for remote scheduling of roadbed and pavement construction equipment.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: a method for remote scheduling of roadbed and pavement construction equipment, comprising the following steps: S1: Based on the task units divided by road construction area, extract the equipment operation trajectory and operation status within the unit, identify trajectory inflection points and status change intervals on the time axis, and generate an equipment operation abnormal status identification dataset by combining unit number and spatial boundary coordinates. S2: Based on the equipment operation abnormality status identification dataset, extract the equipment operation direction vector and the operation status distribution curve of the task unit, analyze the consistency of the two directions at the intersection of the task unit, filter the task units with connectivity and abnormal equipment operation trajectory, and form the equipment behavior deviation area identification result. S3: Based on the identification results of the equipment behavior deviation area, extract the equipment load distribution matrix and operation frequency characteristics within the task unit, analyze the consistency of load balance and operation frequency, filter and match abnormal task units, and obtain the linkage task scheduling efficiency evaluation data table. S4: Based on the location number of the linkage task scheduling efficiency evaluation data table, analyze the stress distribution trend of the construction area corresponding to the task unit, evaluate the degree of deviation from the original flatness curve of the construction area, mark the abnormality level of the task unit according to the deviation range, and output the remote scheduling decision risk rating table.

[0006] As a further aspect of the present invention, the equipment operation abnormality status identification dataset includes the equipment operation trajectory change task unit number, abnormal operation status transition point, task unit coordinate marker, and time series change identifier; the equipment behavior deviation area identification result includes the equipment operation trajectory abnormal task unit identifier, task unit boundary connectivity unit, and task unit boundary consistency block; the linkage task scheduling efficiency evaluation data table includes load abnormal continuous task units, operation frequency irregular area, load change overlapping area, and linkage abnormal task number; and the remote scheduling decision risk rating table includes risk level label, task response deviation value, local stress abnormality index, and flatness offset level.

[0007] As a further aspect of the present invention, the steps for obtaining the device abnormal operation status identification dataset are as follows: S111: Based on the task units divided by road construction areas, extract the equipment running trajectory and operation status distribution curves within the task unit, calculate the difference between the two types of data within the same task unit, and obtain the trend value of the difference between the equipment running trajectory and the operation status distribution. S112: Based on the trend value of the difference between the equipment running trajectory and the operation status distribution, identify the inflection point value in the equipment running trajectory and the conversion value of the operation status distribution curve, superimpose the two types of values ​​on time periods, extract the time interval where the inflection point exceeds the benchmark value and the conversion value exceeds the set threshold, and generate a set of high-frequency mutation interval time periods. S113: For the set of time periods with high frequency mutation intervals, match the corresponding task unit number and spatial boundary information, extract the location of the task unit where the signal occurred, and generate a dataset for identifying abnormal operating conditions of equipment.

[0008] As a further aspect of the present invention, the step of obtaining the device behavior deviation area identification result specifically includes: S211: Based on the equipment abnormal operation status identification dataset, extract the equipment operation direction vector and the operation status distribution curve of the task unit, extract the projection trajectory of the two at the boundary of the task unit, identify the distribution number and aggregation degree of the boundary point in the task unit, and obtain the task unit boundary consistency map. S212: Based on the task unit boundary consistency map, filter the boundary areas with a higher degree of aggregation than the average level, compare the spatial boundary of the overall structure map of the construction area, identify the continuous boundary concentration areas belonging to the same task unit, and obtain the abnormal zoning of equipment operation trajectory within the construction task unit. S213: Call the abnormal zone of equipment running trajectory within the construction task unit, perform integrated analysis on the consistency of task unit boundary, dispersion of equipment running trajectory, load distribution balance and operation status delay, calculate the abnormal high sensitivity response coefficient, match task units according to the response blocks in the layer, and form the equipment behavior deviation area identification result.

[0009] As a further aspect of the present invention, the steps for obtaining the linkage task scheduling performance evaluation data table are as follows: S311: Based on the equipment behavior deviation area identification results, extract the equipment load distribution matrix and operation frequency features of the numbered task units in the layer, perform timestamp alignment on the data in the task units, identify the load intensity fluctuation value and the consistency offset of the operation frequency, and obtain the local abnormal response feature set of the construction task. S312: Based on the local abnormal response feature set of the construction task, perform joint analysis on the load balance and operation frequency consistency within the task unit, calculate the load operation coupling feature value, filter the task units with load operation coupling degree in the layer, and establish a load operation collaborative response spatial distribution map. S313: Call the load job collaborative response spatial distribution map, cluster the task units in the coupled feature value layer that exceed the collaborative identification benchmark, label the task unit codes and coordinates corresponding to the continuous abnormal areas, and obtain the linkage task scheduling efficiency evaluation data table.

[0010] As a further aspect of the present invention, the steps for obtaining the remote scheduling decision risk rating table are as follows: S411: Based on the location number of the linkage task scheduling efficiency evaluation data table, extract the stress distribution curve of the task unit under the specified number, perform time uniform processing, identify the stress change per unit time, and obtain the set of abnormal stress change rate of the task unit. S412: Based on the set of abnormal stress change rates of the task units, identify the stress distribution curve of the original flatness stage, compare the current stress change sequence with the reference curve, identify the stress deviation level of the task units, extract and mark the task units whose deviation level exceeds the warning upper limit, and obtain the set of task units with sudden increase in deviation. S413: Based on the set of task units with sudden deviations, bind the deviation level value of each task unit to the location number in the structural space map of the construction area, sort them according to risk level, and output the risk rating table for remote scheduling decision.

[0011] As a further aspect of the present invention, the method further includes step S5: S5: Call the remote scheduling decision risk rating table, identify the corresponding number of the task unit in the road construction function map, extract the list of repair response units, compare the response level with the construction protection priority sequence, filter the task unit number that needs to adjust the response coverage, and output the intelligent collaborative scheduling instruction set for construction equipment. The intelligent collaborative scheduling instruction set for construction equipment includes adjusting the target task unit number, response level adjustment parameters, protection priority comparison items, and linkage response trigger types.

[0012] As a further aspect of the present invention, the steps for obtaining the intelligent collaborative scheduling instruction set for construction equipment are as follows: S511: Call the remote scheduling decision risk classification table, extract the task unit number in the road construction function map, map the task unit risk level value with the regional coordinate boundary, identify the task unit information corresponding to the construction protection level, and generate a construction task risk distribution map. S512: Based on the construction task risk distribution map, extract the repair response unit number and response level, match the task unit risk level with the repair response level, identify the unit number with insufficient response coverage, and obtain the construction task response risk disconnect list. S513: Based on the construction task response risk disconnect list, extract the key task unit number that needs to improve the response coverage according to the level number in the construction protection priority sequence, output the adjustment control parameters linked with the original repair unit in sequence, and output the intelligent collaborative scheduling instruction set for construction equipment.

[0013] The remote scheduling system for roadbed and pavement construction equipment is used to execute the aforementioned remote scheduling method for roadbed and pavement construction equipment. The system includes: The trajectory monitoring module is based on the task units divided by the road construction area. It compares the inflection points of the equipment operation trajectory and the time of operation status transition within the same time period, filters the synchronous change intervals of the two, extracts the task unit number and spatial boundary coordinates, summarizes the abnormal time period and task unit number, and generates a dataset for identifying abnormal equipment operation status. Based on the equipment operation abnormality status identification dataset, the task localization module identifies the consistency between the equipment operation direction vector and the operation status distribution curve, calibrates the task unit boundary number, matches the overall structure map of the construction area, extracts the task unit number range of the abnormal equipment operation trajectory area, and establishes the equipment behavior deviation area identification result. Based on the identification results of the equipment behavior deviation area, the task linkage module retrieves the continuous data sequence of the equipment load distribution matrix and the operation frequency characteristics in the area, determines the consistency between the load abnormal boundary connectivity and the operation frequency, marks the task unit number that meets the linkage threshold of both, and outputs the linkage task scheduling efficiency evaluation data table. Based on the task unit number in the linked task scheduling efficiency evaluation data table, the stress early warning module analyzes the stress distribution trend of the corresponding task unit and the degree of deviation from the original flatness curve, extracts the task unit number that deviates from the trend, completes the level identification according to the risk classification standard, and generates a remote scheduling decision risk classification table. Based on the remote scheduling decision risk classification table, the repair and optimization module finds the corresponding position number of the risk level task unit in the road construction function diagram, retrieves the current repair response unit configuration list, compares the matching situation between the construction protection priority and the current response level, filters the task unit numbers that need to be updated, and outputs the intelligent collaborative scheduling instruction set for construction equipment.

[0014] Compared with the prior art, the advantages and positive effects of the present invention are as follows: In this invention, by accurately extracting and analyzing the equipment's operating trajectory and operational status, abnormal intervals and deviation areas of equipment behavior can be effectively identified. This enables precise screening and scheduling of abnormal task units. Combined with the analysis of load distribution and operational frequency characteristics, it helps optimize equipment resource allocation, improve the balance and consistency of operations, and avoid resource waste and inefficiency caused by unreasonable task unit scheduling. By assessing the stress distribution trend and the degree of deviation of the original flatness curve in the construction area, the risk level of task units can be calibrated. This helps to identify potential problems in advance and take effective countermeasures, improving the accuracy and flexibility of scheduling decisions. Ultimately, it forms intelligent collaborative scheduling instructions, ensuring the efficient and smooth execution of various tasks during construction. Attached Figure Description

[0015] Figure 1 This is a schematic diagram of the workflow of the present invention; Figure 2 This is a flowchart illustrating the process of obtaining the dataset for identifying abnormal operating states of equipment in this invention. Figure 3 This is a flowchart illustrating the process of obtaining the identification results of device behavior deviation areas in this invention. Figure 4 This is a flowchart illustrating the process of obtaining the collaborative task scheduling performance evaluation data table in this invention. Figure 5 This is a flowchart illustrating the process of obtaining the risk rating table for remote scheduling decisions in this invention. Figure 6 This is a flowchart illustrating the acquisition process of the intelligent collaborative scheduling instruction set for construction equipment in this invention. Detailed Implementation

[0016] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0017] In the description of this invention, it should be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships, are based on the orientation or positional relationships shown in the accompanying drawings and are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, in the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0018] Example 1: Please refer to Figure 1 This invention provides a technical solution: a method for remote scheduling of roadbed and pavement construction equipment, comprising the following steps: S1: Based on the task units divided by the road construction area, extract the equipment running trajectory and operation status distribution within the task unit, identify the synchronous change interval of the inflection point of the equipment running trajectory and the time of operation status transition on the time axis, extract the corresponding task unit number and spatial boundary coordinates, and generate a dataset for identifying abnormal equipment operation status. S2: Based on the equipment operation abnormal status identification dataset, extract the equipment operation direction vector and the operation status distribution curve of the task unit, analyze the consistency of the two directions at the boundary of the task unit, combine the task unit boundary connectivity, filter the task units with connectivity and abnormal equipment operation trajectory, and form the equipment behavior deviation area identification result. S3: Based on the identification results of equipment behavior deviation areas, extract the equipment load distribution matrix and operation frequency characteristics within the task unit, analyze the consistency of load balance and operation frequency, screen and match abnormal task units, and obtain the linkage task scheduling efficiency evaluation data table. S4: Based on the location number of the linkage task scheduling efficiency evaluation data table, analyze the stress distribution trend of the construction area corresponding to the task unit, evaluate the degree of deviation from the original flatness curve of the construction area, mark the abnormality level of the task unit according to the deviation range, and output the remote scheduling decision risk rating table. S5: Call the remote scheduling decision risk classification table, identify the corresponding number of the task unit in the road construction function diagram, extract the list of repair response units, compare the response level with the construction protection priority sequence, filter the task unit numbers that need to adjust the response coverage, and output the intelligent collaborative scheduling instruction set for construction equipment.

[0019] The equipment operation abnormality status identification dataset includes the task unit number of equipment operation trajectory change, abnormal point of operation status transition, task unit coordinate mark, and time series change identifier. The equipment behavior deviation area identification results include the equipment operation trajectory abnormal task unit identifier, task unit boundary connectivity unit, and task unit boundary consistency block. The linkage task scheduling efficiency evaluation data table includes continuous task units with abnormal load, irregular operation frequency area, overlapping area of ​​load change, and linkage abnormal task number. The remote scheduling decision risk rating table includes risk level label, task response deviation value, local stress anomaly index, and flatness offset level. The intelligent collaborative scheduling instruction set for construction equipment includes adjusting the target task unit number, response level adjustment parameters, protection priority comparison item, and linkage response trigger type.

[0020] Please see Figure 2 The specific steps for obtaining the dataset for identifying abnormal equipment operation states are as follows: S111: Based on the task units divided by road construction areas, extract the equipment running trajectory and operation status distribution curves within the task unit, calculate the difference between the two types of data within the same task unit, and obtain the trend value of the difference between the equipment running trajectory and the operation status distribution. Based on the task units defined by road construction areas, for example, a 1000-meter-long urban main road widening and renovation project is divided into several task units, such as task unit TU001 (chainage K0+000 to K0+100). The operating trajectory and operational status distribution curves of the equipment within each task unit are extracted. For the vibratory roller performing subgrade compaction within task unit TU001, the operating trajectory data is collected in real-time via an onboard GPS receiver, recording position coordinates and speed data once per second to form a trajectory time series. The trajectory points are compared with the preset compaction path of task unit TU001, and the vertical deviation distance is calculated and normalized to the 0-1 range. The maximum allowable trajectory deviation distance is set to 2.0 meters, and the actual deviation distance of 1.0 meter is normalized to 0.5. Simultaneously, the roller's operational status data is collected in real-time via sensors, including engine speed, hydraulic... Pressure, vibration frequency, and amplitude constitute a time sequence set of operating states. Ideal operating state ranges are preset for engine speed, hydraulic pressure, vibration frequency, and amplitude. The deviation of each operating state parameter from its ideal range center value is calculated and normalized to the interval 0 to 1. Speed ​​deviation is normalized; for example, a deviation of 150 RPM is normalized to 0.5. A weighted average of all normalized operating state deviation values ​​is calculated to obtain the comprehensive operating state deviation value. The weights for each parameter are set as follows: engine speed 0.3, hydraulic system pressure 0.3, vibration frequency 0.2, and amplitude 0.2. If the normalized deviations are 0, 0, 0, and 0, the comprehensive operating state deviation is 0. If the deviations are 0.2, 0.1, 0.3, and 0.1, the value 0.17 is obtained by multiplying each deviation by its weight and then summing the results (0.2 * 0.3). + 0.1*0.3 + 0.3*0.2 + 0.1*0.2 = 0.06 + 0.03 + 0.06 + 0.02 = 0.17), calculate the difference between two types of data within the same task unit. At the common sampling time, calculate the absolute difference between the normalized deviation of the equipment running trajectory and the normalized comprehensive deviation of the operation state. At time t2, the trajectory normalized deviation is 0.4, the operation state normalized comprehensive deviation is 0.17, and the difference is 0.23. Obtain the trend value of the difference between the equipment running trajectory and the operation state distribution. The trend value is a time series difference sequence, reflecting the temporal synchronicity and difference between the deviation of the equipment trajectory and the deviation of the operation state.

[0021] S112: Based on the trend value of the difference between the equipment running trajectory and the operation status distribution, identify the inflection point value in the equipment running trajectory and the transformation value of the operation status distribution curve, superimpose the two types of values ​​on time periods, extract the time interval where the inflection point exceeds the baseline value and the transformation value exceeds the set threshold, and generate a set of high-frequency mutation interval time periods. Based on the trend value of the difference between the equipment's operating trajectory and its operational status distribution, and using this trend value as input, for the road roller in task unit TU001, the inflection point value in the equipment's operating trajectory and the transition value of the operational status distribution curve are identified through a continuous sequence of trend values. The trajectory inflection point value is determined by calculating the second derivative of the equipment's speed and direction changes, detecting increases or decreases in the instantaneous rate of change. A benchmark value of 0.05 is set, indicating that an inflection point occurs when the second derivative exceeds this value. This benchmark value is set using the 95th percentile based on statistical analysis of thousands of hours of historical data. The transition value of the operational status distribution curve is determined by monitoring the continuous rate of change of key operational parameters. When a parameter's change exceeds its stable range within a short period (within 2 seconds), it is identified as a transition value. The vibration frequency transition threshold is 10Hz, meaning a transition occurs when the frequency change exceeds 10Hz within 2 seconds. This threshold is calibrated based on expert experience and equipment start-up / stop and mode switching data. The values ​​are superimposed over time periods. The identified trajectory inflection point time and the operation state transition time are aligned on the time axis. At the 65th second of the roller's operation, the peak value of the second derivative of the trajectory direction is 0.08, which exceeds 0.05, and is judged as a trajectory inflection point. At the 66th second, the vibration frequency suddenly changes from 0Hz to 32Hz. The change amount is 32Hz, which exceeds 10Hz, and is judged as an operation state transition. The time interval between the inflection point exceeding the baseline value and the transition value exceeding the set threshold is extracted. The 65th to 66th second is the preliminary time interval. Within the continuous time window (10-second window), if the number of trajectory inflection points exceeds 3 and the number of operation state transitions exceeds 2, it is judged as a high-frequency sudden change interval. A high-frequency sudden change interval time period set is generated. For task unit TU001, the time period set is [00:01:25-00:01:35][00:03:10-00:03:20][00:05:40-00:05:50].

[0022] S113: For high-frequency mutation interval time sets, match the corresponding task unit number and spatial boundary information, extract the location of the task unit where the signal occurs, and generate a dataset for identifying abnormal equipment operation status. For the set of time periods with high-frequency abrupt changes, the corresponding task unit number and spatial boundary information are matched. For the high-frequency abrupt change intervals, the task unit number to which the equipment belongs is traced by timestamp. Combined with the unit's preset spatial boundary coordinates, time and spatial information are bound. Within the time period [00:01:25-00:01:35], the roller trajectory data shows that it is mostly located within the spatial boundary range of task unit TU001. The location of the task unit that generated the signal is extracted, and the specific location of the task unit corresponding to the abrupt change interval in the construction area is determined. The matching results show that task units TU001 and TU005 have high-frequency abrupt change signals in equipment operation trajectory and working status within a specific time period, generating equipment... Run the abnormal state identification dataset. The dataset contains the task unit number, spatial boundary information, abnormal time period, and frequency level of the abnormal signal. For example, TU001: spatial boundary longitude 120.123E to 120.125E, latitude 30.678N to 30.680N, abnormal time period [00:01:25-00:01:35][00:03:10-00:03:20], high frequency level; TU005: spatial boundary longitude 120.135E to 120.137E, latitude 30.685N to 30.687N, abnormal time period [00:07:00-00:07:10], medium frequency level.

[0023] Please see Figure 3 The specific steps for obtaining the device behavior deviation area identification results are as follows: S211: Based on the equipment operation abnormal status identification dataset, extract the equipment operation direction vector and the operation status distribution curve of the task unit, extract the projection trajectory of the two at the boundary of the task unit, identify the distribution number and aggregation degree of the boundary point in the task unit, and obtain the task unit boundary consistency map. Based on the equipment operation anomaly identification dataset, TU001 and TU005 were identified as abnormal task units. The equipment running direction vector and operational status distribution curve for each task unit were extracted. For task unit TU001, detailed operating trajectory data of the road roller was retrieved. The instantaneous running direction vector of the equipment was calculated using the coordinate difference between adjacent GPS points. The operational status distribution curve for the time period was retrieved, including real-time parameters such as engine speed, hydraulic pressure, vibration frequency, and amplitude. The projection trajectory of the two at the boundary between the task units was extracted. The boundary line between task units TU001 and TU002 was defined as the K0+100 station line. The projection trajectory of the equipment running direction vector on the boundary line reflects the direction and angle relationship and trajectory point sequence when the equipment crosses or approaches the boundary line. The projection trajectory of the operational status distribution curve at the boundary reflects the situation when the equipment crosses or approaches the boundary line. The trend of changes in work status parameters is analyzed to identify the distribution and aggregation degree of boundary points in task units. By recording multiple crossings near the equipment boundary line, the distribution density of trajectory projection points on the boundary line and the concentration of work status transition points near the boundary line are statistically analyzed. The frequent U-turns of the road roller at the boundary of TU001 and TU002 resulted in 20 trajectory projection points and 5 work mode transitions within a 10-meter-wide boundary area. It was determined that the number of boundary points was large and the aggregation degree was high. A consistency map of task unit boundaries was obtained. The map records the distribution density of equipment trajectory projections and the aggregation degree of work status transitions at the boundaries of all task units in the construction area. Each boundary area is assigned a consistency score from 0 to 100. The consistency score at the boundary of TU001 and TU002 is 85, and the consistency score at the boundary of TU002 and TU003 is 60.

[0024] S212: Based on the boundary consistency map of the task unit, filter the boundary areas with a higher degree of aggregation than the average level, compare the spatial boundary of the overall structure map of the construction area, identify the continuous boundary concentration areas that belong to the same task unit, and obtain the abnormal zoning of equipment operation trajectory within the construction task unit. Based on the task unit boundary consistency map, which includes consistency scores for each task unit boundary, and considering that the consistency score at the boundary between TU001 and TU002 is 85 and the score at the boundary between TU002 and TU003 is 60, boundary areas with a higher degree of aggregation than the average are selected. The average consistency score of all task unit boundary is calculated. For example, if the average is 70, the boundary area between TU001 and TU002 with a consistency score of 85 and other areas with a score higher than 70 are selected. By comparing the spatial boundaries of the overall construction area structure map, the selected high-aggregation boundary areas are spatially overlaid with the road construction plan layout map to verify the physical spatial continuity and the corresponding task units. The boundary range of the meta-element is used to identify continuous and concentrated areas belonging to the same task unit. If the boundary between TU001 and TU002 (station K0+100) shows high aggregation and the area is connected to the abnormal area inside TU001, it is identified as a continuous abnormal concentrated area. This results in the abnormal zoning of equipment operation trajectory within the construction task unit. The zoning marks which specific areas of the task unit on the construction area map deviate due to frequent abnormal boundary behavior of equipment operation trajectory and operation status. The zoning marks the area from K0+095 to K0+105 of TU001 and the area from K0+490 to K0+500 of TU005 as trajectory abnormal zoning.

[0025] S213: Invoke the abnormal zone classification of equipment running trajectory within the construction task unit, and perform integrated analysis on the consistency of task unit boundaries, equipment running trajectory dispersion, load distribution balance, and operation status delay, using the following formula: ; Calculate the abnormal high sensitivity response coefficient, perform task unit matching based on the response blocks in the layer, and form the device behavior deviation area identification result; in, Represents an abnormally high sensitivity response coefficient. This represents the dispersion value of the i-th device's operating trajectory. This represents the average value of the dispersion of the operating trajectories of all devices. This represents the total number of device operating trajectories involved in the calculation. This represents the job status delay value of the j-th task unit. This represents the average delay value for all job statuses. Represents the total number of task units; The system calls upon the abnormal zone delineation of equipment running trajectories within the construction task unit. For example, it identifies the area from K0+095 to K0+105 of TU001 as an abnormal zone. It then performs integrated analysis on task unit boundary consistency, equipment running trajectory dispersion, load distribution balance, and operational status delay. The dispersion of equipment running trajectories within the task unit is obtained from historical data (e.g., by calculating the standard deviation of deviations of multiple trajectories within the same task unit; a larger value indicates higher dispersion). Load distribution balance is obtained from equipment operation logs (e.g., the range of engine load rate fluctuations over a period of time; a large fluctuation range indicates poor balance). Operational status delay is obtained from operation logs (e.g., the time difference between receiving an instruction and actually executing an operation). All parameters are quantified numerically. For example, the boundary consistency score for task unit TU001 is 85, the equipment running trajectory dispersion is 1.5 seconds (standard deviation), the load distribution balance is 10% (load rate fluctuation percentage), and the operational status delay is 0.8 seconds. The formula used is: Calculate the abnormally high sensitivity response coefficient, in the formula, The value represents the abnormally high sensitivity response coefficient; the larger the value, the higher the degree of abnormal response, indicating a more significant deviation in equipment behavior. Representing the The dispersion value of the equipment's operating trajectory, expressed in time (T), refers to the standard deviation of a single equipment trajectory point relative to its average trajectory within a specific time period. This represents the average value of the dispersion of the operating trajectories of all devices, expressed in time (T). This represents the total number of device trajectories involved in the calculation, in dimensionless form, and takes the value of a positive integer greater than or equal to 1. Representing the The job status delay value of each task unit, in time (T). This represents the average value of all job status delays, expressed in time (T). The value represents the total number of task units, is dimensionless, and is a positive integer greater than or equal to 1. This formula calculates the dispersion of the trajectory of each device through the numerator. Its average The sum of the absolute differences reflects the overall degree of deviation from the equipment trajectory, and the denominator calculates the delay of the operation status of each task unit. Its average The sum of absolute differences reflects the overall lag in operational efficiency. By taking the square root of the ratio between the variability of trajectory dispersion and the variability of operational delay, the overall abnormal high-sensitivity response of the equipment in terms of both trajectory and operation can be comprehensively evaluated. The advantage of this formula lies in its ability to more sensitively reflect complex anomalies during construction by taking the square root of the ratio between the dispersion of the equipment's operating trajectory and the delay in the operational status. This is especially true when trajectory chaos is accompanied by operational response lag. This combined assessment makes anomaly identification more comprehensive and has higher response sensitivity. For example, if there are three equipment operating trajectories with dispersions of... ,but If there are two task units with job status delays of respectively ,but ; but: ; ; therefore, Based on the response blocks in the layer, task units are matched, and the calculated abnormally high sensitivity response coefficient is obtained. Associated with specific task units, and The values ​​are mapped onto a digital map of the construction area, forming response blocks of different colors, with darker colors representing... The higher the value, the more significant the anomaly, resulting in the identification of areas where device behavior deviates. This result is a... The construction area map, marked with values, clearly shows which task units or their internal areas exhibit significant deviations in equipment behavior. For example, the area from K0+095 to K0+105 of task unit TU001 is shown... It was marked as a high deviation region.

[0026] Please see Figure 4 The specific steps for obtaining the collaborative task scheduling performance evaluation data table are as follows: S311: Based on the identification results of equipment behavior deviation area, extract the equipment load distribution matrix and operation frequency features of the numbered task units in the layer, align the data in the task unit with timestamps, identify the load intensity fluctuation value and the consistency offset of operation frequency, and obtain the local abnormal response feature set of the construction task. Based on the equipment behavior deviation area identification results, deviations were identified in the K0+095 to K0+105 region of TU001. The equipment load distribution matrix and operation frequency features of the numbered task units within the layer were extracted. For the deviation area task unit TU001, the load distribution matrix from its internal historical equipment operation data was obtained. The matrix records load parameters such as power output and fuel consumption rate at different times and under different operating modes, as well as the average engine load rate data of the road roller from 8:00 to 12:00 per minute. Operation frequency features were also extracted, including the number of times the equipment completes a specific operation per unit time. The data within the task unit was timestamped, and data from different equipment and parameter sources were synchronized according to precise timestamps to ensure data point time consistency. The road roller's GPS trajectory, engine load, and vibration status data were aligned to... Every second, identify the load intensity fluctuation value and the consistency offset of the operation frequency. The load intensity fluctuation value is obtained by calculating the standard deviation or peak-valley difference of the equipment load rate. A large standard deviation or peak-valley difference indicates a violent fluctuation. The standard deviation of the engine load rate of the road roller within 30 minutes is 8%. The normal fluctuation range is within 5%. 8% indicates the existence of load intensity fluctuation. The consistency offset of the operation frequency is calculated by comparing the actual operation frequency with the preset or historical average operation frequency. A large difference indicates a large offset. The preset number of compaction cycles per hour is 60, the actual number is 45, and the offset is 15. Obtain the local abnormal response feature set of the construction task. The feature set records the load intensity fluctuation value and the consistency offset of the operation frequency of the equipment in each task unit where the behavior deviates. For TU001, the feature set includes the task unit number TU001, the load fluctuation is 8%, and the frequency offset is 15.

[0027] S312: Based on the local abnormal response characteristic set of the construction task, a joint analysis of load balance and operation frequency consistency within the task unit is performed, using the following formula: ; Calculate the load operation coupling characteristic value, filter the task units with load operation coupling degree in the layer, and establish a load operation collaborative response spatial distribution map; in, Represents the load job coupling characteristic value. This represents the load balancing value of the k-th job unit. This represents the average load balancing value across all job units. This represents the consistency value of the job frequency for the k-th job unit. This represents the average value of the consistency of operation frequency across all work units. Represents the number of work units involved in the calculation; Based on the local anomaly response feature set of the construction task, for example, for TU001, the load intensity fluctuation value is 8% and the operation frequency consistency offset is 15 times, a joint analysis is performed on the load balance and operation frequency consistency within the task unit. This is obtained by inversely quantifying the load intensity fluctuation value. For example, if the load fluctuation percentage is 8%, the smaller the fluctuation, the higher the balance. Consistency of work frequency This is obtained by inversely quantizing the job frequency consistency offset. For example, an offset of 15 times indicates higher consistency, with smaller offsets. (Assuming a preset frequency of 60 times per hour), the formula is as follows: Calculate the load job coupling characteristic value, in the formula, This represents the load-job coupling characteristic value. The larger the value, the higher the coupling between the load and the job, and the easier it is to trigger a cascading effect. Representing the The load balancing value for each job unit, expressed as a percentage. This represents the average load balancing value across all job units, expressed as a percentage. Representing the The consistency value of the work frequency of each work unit, expressed as a percentage. This represents the average value of the consistency of operation frequency across all work units, expressed as a percentage. The numerator represents the number of job units involved in the calculation and is a positive integer greater than or equal to 1. This formula calculates the load balance of each job unit through the numerator. Its average The absolute difference is consistent with the operation frequency. Its average The sum of the products of the squared differences, which amplifies the impact of simultaneous load balance deviation and job frequency consistency deviation, while the denominator is calculated using the number of job units. With average load balancing The product is standardized by taking the square root, so that... The value can comprehensively assess the degree of coordination deviation between load and operation; The advantage of the formula is that the coupling characteristic value can accurately quantify the degree of coordination anomaly between load and operation status during equipment operation by taking the square root of the product of load balance and operation frequency consistency deviation. In particular, the square term strengthens the impact of operation frequency consistency deviation on the overall coupling degree, thereby more sensitively identifying potential linkage risks. For example, the load balance and operation frequency consistency data of the existing three task units are shown in Table 1. As shown in Table 1, based on the data in the table, first calculate the average value: , ; Then calculate the molecule: ; ; ; ; Denominator: ; therefore, ; The result indicates that TU003 has the highest load operation coupling. The task units with the highest load operation coupling in the filter layer are then analyzed based on the calculated... Value, setting a collaborative identification benchmark ,For example, All Value exceeds The task units are selected, and a spatial distribution map of the load operation collaborative response is established. This map will... The values ​​are mapped onto the construction area map, and the degree of load coupling of each task unit is represented by color depth or numerical labels.

[0028] S313: Call the load job collaborative response spatial distribution map, cluster the task units in the coupled feature value layer that exceed the collaborative identification benchmark, label the task unit codes and coordinates corresponding to continuous abnormal areas, and obtain the linkage task scheduling efficiency evaluation data table. The load operation collaborative response spatial distribution map is invoked. The coupling characteristic value of TU003 is 1.006, exceeding the baseline value of 1.0. Task units in the coupling characteristic value layer that exceed the collaborative identification baseline are clustered. All task units whose coupling characteristic value Q exceeds the set collaborative identification baseline are clustered based on spatial adjacency. If the coupling characteristic value of TU003 is 1.006 and that of TU004 is 1.01, and they are spatially adjacent, then TU003 and TU004 are classified as continuous abnormal regions. The task unit codes and coordinates corresponding to the continuous abnormal regions are labeled, and the task unit numbers and the precise spatial coordinate range of the construction area of ​​the continuous abnormal regions after clustering are recorded. For example, continuous abnormal region A contains task units TU003 and TU004, and its coordinate range is from longitude 120.128E to 120.132E and latitude 30.683N to 30.685N. The linkage task scheduling efficiency evaluation data table is obtained. The data table contains the task unit codes, spatial coordinates, load operation coupling characteristic values, and evaluation indicators of all identified continuous abnormal regions.

[0029] Please see Figure 5The specific steps for obtaining the remote scheduling decision risk rating table are as follows: S411: Based on the location number of the linkage task scheduling efficiency evaluation data table, extract the stress distribution curve of the task unit under the specified number, perform time uniform processing, identify the stress change per unit time, and obtain the set of abnormal stress change rate of the task unit. Based on the location numbers in the linkage task scheduling efficiency evaluation data table, including the location numbers and data of continuous abnormal areas A (TU003TU004), the stress distribution curves of task units under the specified numbers are extracted. For task unit TU003 with the specified number in the data table, the stress distribution curve data over a past period is extracted. The stress data comes from stress sensors on key components of construction equipment, such as the vibration stress of road roller drums and the torque stress of engines. Time-unified processing is performed to convert stress data from different sources and with different sampling frequencies into the same time scale and sampling interval, unifying the data to one sampling point per second. The stress change per unit time is identified, and for each stress parameter, its change per unit time is calculated. If the sensor... The time reading is , The time reading is The stress change per unit time is Obtain the set of abnormal stress change rates for each task unit. The set records the stress change sequence per unit time for each key stress parameter of each task unit. For TU003, the set of abnormal stress change rates includes the change in vibration stress per second of the roller drum of the road roller of 0.05MPa / s, 0.08MPa / s, and 0.12MPa / s.

[0030] S412: Based on the set of abnormal stress change rates of task units, identify the stress distribution curve of the original flatness stage, compare the current stress change sequence with the reference curve, identify the stress deviation level of task units, extract and mark task units whose deviation level exceeds the warning upper limit, and obtain the set of task units with sudden increase in deviation. Based on the set of abnormal stress change rates for the task unit, the stress change rates of the TU003 drum vibration are 0.05, 0.08, and 0.12. The stress distribution curve for the initial leveling stage is identified. Historical stress data from the initial leveling stage of the task unit is retrieved and considered as the equipment's baseline stress distribution curve for subsequent comparison. The current stress change sequence is compared with the reference curve. A point-by-point or statistical comparison is performed between the current set of abnormal stress change rates for the task unit and the stress distribution curve for the initial leveling stage. By calculating the mean square error between the current stress change rate sequence and the baseline stress change rate sequence, the stress deviation level of the task unit is identified. Based on the magnitude of the mean square error, the stress deviation level is classified as: less than... 0.01 is considered low deviation, 0.01 to 0.05 is medium deviation, and greater than 0.05 is high deviation. The threshold for classifying the levels is set by analyzing the stress characteristics of historical equipment fault data and normal operation data, combined with expert experience. Task units whose deviation levels exceed the upper limit of the warning are extracted and marked. The upper limit of the stress deviation warning is set as medium deviation, that is, the mean square error is greater than 0.01. All task units whose stress deviation levels reach or exceed medium deviation are marked, and a set of task units with sudden deviation increases is obtained. The set contains all task units whose stress deviation levels exceed the upper limit of the warning. The mean square error of task unit TU003 is 0.06, which exceeds 0.01, so it is marked as high deviation, and TU003 is included in the set of task units with sudden deviation increases.

[0031] S413: Based on the set of task units with sudden deviations, bind the deviation level value of each task unit to the location number in the structural space diagram of the construction area, sort them according to risk level, and output the risk rating table for remote scheduling decision. Based on the set of task units with sudden deviation increases, TU003 is identified as a task unit with sudden deviation increases. The deviation level value of each task unit is bound to its location number on the structural spatial map of the construction area. Task units are sorted by risk level, from highest to lowest, based on their stress deviation level, with high-deviation task units listed first, followed by medium-deviation units. A remote scheduling decision risk rating table is output, listing the task units within the construction area that exhibit sudden stress deviation increases, their deviation levels, and spatial location information. For example: As shown in Table 2, this table provides a risk priority basis for remote scheduling decisions.

[0032] Please see Figure 6 The specific steps for obtaining the intelligent collaborative scheduling instruction set for construction equipment are as follows: S511: Call the remote scheduling decision risk classification table, extract the task unit number in the road construction function map, map the task unit risk level value with the area coordinate boundary, identify the task unit information corresponding to the construction protection level, and generate a construction task risk distribution map. The remote scheduling decision risk grading table is invoked to identify TU003 as high deviation risk and TU007 and TU002 as medium deviation risk. The task unit numbers within the road construction functional map are extracted, and all task unit numbers are retrieved from the risk grading table and matched with the road construction functional map. The functional map divides road construction into various functional zones, such as roadbed leveling zones, asphalt paving zones, and traffic control zones. The risk level values ​​of the task units are mapped to the regional coordinate boundaries, and the risk level of the task unit is associated with its specific spatial coordinate boundaries on the road construction functional map to display risk areas on the map. The task unit information corresponding to the construction protection level is identified. According to the road construction safety management specifications, different risk levels are matched with preset construction protection levels. High deviation risk task units correspond to the highest protection, and medium deviation risk task units correspond to medium protection. A construction task risk distribution map is generated. The map is a construction area map, with different colors or icons representing task units of different risk levels and their protection levels. The area where TU003 is located is displayed in red on the map and marked as "Level 1 Protection Zone," indicating high risk.

[0033] S512: Based on the risk distribution map of construction tasks, extract the repair response unit number and response level, match the risk level of the task unit with the repair response level, identify the unit number with insufficient response coverage, and obtain the list of construction task response risk disconnection. Based on the risk distribution map of construction tasks, TU003 is marked as a Level 1 protection zone. The repair response unit number and response level are extracted, and preset repair response units (such as emergency repair teams and equipment maintenance teams) and their response levels (e.g., Level 1 response: arrival within 15 minutes, Level 2 response: arrival within 30 minutes) are obtained. The risk level of the task unit is matched with the repair response level. The risk level of the task unit identified in the map is compared with the response level of the existing repair response units. The high-risk task unit TU003 requires a Level 1 response, and the emergency repair team is set to a Level 2 response. The unit number with insufficient response coverage is identified. If the response level of the repair response unit configured for a high-risk task unit is lower than the required protection level, the task unit is identified as having insufficient response coverage. Task unit TU003 is a high-risk deviation and requires a Level 1 response. The emergency repair team only provides a Level 2 response. TU003 is identified as having insufficient response coverage. A list of construction task response risk disconnects is obtained. The list clearly lists all task unit numbers with insufficient response coverage, the required response level, and the currently available response level.

[0034] S513: Based on the list of risk disconnection in construction task response, extract the key task unit number that needs to improve the response coverage according to the level number in the construction protection priority sequence, output the adjustment control parameters linked with the original repair unit in sequence, and output the intelligent collaborative scheduling instruction set for construction equipment. According to the construction task response risk disconnect list, TU003 is listed as having insufficient response coverage, requiring a Level 1 response but only having a Level 2 response. Based on the level number in the construction protection priority sequence, the preset construction protection priority sequence in construction management is consulted. The sequence specifies the priority of resource allocation for task units with different risk levels and importance. The Level 1 protection zone has the highest priority for emergency repair, followed by the Level 2 protection zone. The key task unit numbers that need to improve response coverage are extracted, and the highest priority task units, i.e., high-risk task units with insufficient response coverage, such as TU003, are selected from the list. Adjustment control parameters linked to the original repair unit are output in sequence. For key task units, specific scheduling instructions are generated. For example, the TU003 instruction includes: mobilizing a Level 1 emergency repair team that is closer and has a higher response level, or instructing the existing Level 2 emergency repair team to accelerate the response and change the driving route, and providing equipment fault diagnosis parameters. The parameters are directly called by the remote control of the equipment, and a set of intelligent collaborative scheduling instructions for construction equipment is output. The instruction set is a structured data package containing instructions for equipment scheduling, operation mode adjustment, and resource reallocation for the task unit, which are directly issued to the intelligent equipment and management platform at the construction site for execution.

[0035] The remote dispatching system for roadbed and pavement construction equipment is used to execute the aforementioned remote dispatching method for roadbed and pavement construction equipment. The system includes: The trajectory monitoring module is based on the task units divided by the road construction area. It compares the inflection points of the equipment operation trajectory and the time of operation status transition within the same time period, filters the synchronous change intervals of the two, extracts the task unit number and spatial boundary coordinates, summarizes the abnormal time period and task unit number, and generates a dataset for identifying abnormal equipment operation status. The task localization module is based on the equipment operation abnormal status identification dataset. It identifies the consistency between the equipment operation direction vector and the operation status distribution curve, marks the task unit boundary number, matches the overall structure map of the construction area, extracts the task unit number range of the abnormal equipment operation trajectory area, and establishes the equipment behavior deviation area identification result. Based on the identification results of equipment behavior deviation from the area, the task linkage module retrieves the continuous data sequence of equipment load distribution matrix and operation frequency characteristics in the area, judges the consistency between load abnormality boundary connectivity and operation frequency, marks the task unit number that meets the linkage threshold of both, and outputs a linkage task scheduling efficiency evaluation data table. The stress early warning module analyzes the stress distribution trend and the degree of deviation of the original flatness curve of the corresponding task unit based on the task unit number of the linkage task scheduling efficiency evaluation data table, extracts the task unit number that deviates from the trend, completes the level identification according to the risk classification standard, and generates a remote scheduling decision risk classification table. The repair and optimization module uses the remote scheduling decision risk classification table to find the corresponding position number of the risk level task unit in the road construction function map, retrieves the current repair response unit configuration list, compares the construction protection priority with the current response level, filters the task unit numbers that need to be updated, and outputs the intelligent collaborative scheduling instruction set for construction equipment.

[0036] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention in any other way. Any person skilled in the art may make changes or modifications to the above-disclosed technical content to create equivalent embodiments that can be applied to other fields. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the protection scope of the present invention.

Claims

1. A method for remote scheduling of roadbed and pavement construction equipment, characterized in that, Includes the following steps: S1: Based on the task units divided by road construction area, extract the equipment operation trajectory and operation status within the unit, identify trajectory inflection points and status change intervals on the time axis, and generate an equipment operation abnormal status identification dataset by combining unit number and spatial boundary coordinates. S2: Based on the equipment operation abnormality status identification dataset, extract the equipment operation direction vector and the operation status distribution curve of the task unit, analyze the consistency of the two directions at the intersection of the task unit, filter the task units with connectivity and abnormal equipment operation trajectory, and form the equipment behavior deviation area identification result. S3: Based on the identification results of the equipment behavior deviation area, extract the equipment load distribution matrix and operation frequency characteristics within the task unit, analyze the consistency of load balance and operation frequency, filter and match abnormal task units, and obtain the linkage task scheduling efficiency evaluation data table. S4: Based on the location number of the linkage task scheduling efficiency evaluation data table, analyze the stress distribution trend of the construction area corresponding to the task unit, evaluate the degree of deviation from the original flatness curve of the construction area, mark the abnormality level of the task unit according to the deviation range, and output the remote scheduling decision risk rating table.

2. The remote scheduling method for roadbed and pavement construction equipment according to claim 1, characterized in that, The equipment operation abnormality status identification dataset includes the equipment operation trajectory change task unit number, abnormal operation status transition point, task unit coordinate marker, and time series change identifier. The equipment behavior deviation area identification result includes the equipment operation trajectory abnormal task unit identifier, task unit boundary connectivity unit, and task unit boundary consistency block. The linkage task scheduling efficiency evaluation data table includes load abnormal continuous task units, operation frequency irregular area, load change overlapping area, and linkage abnormal task number. The remote scheduling decision risk rating table includes risk level label, task response deviation value, local stress abnormality index, and flatness offset level.

3. The remote scheduling method for roadbed and pavement construction equipment according to claim 1, characterized in that, The specific steps for obtaining the dataset for identifying abnormal device operation states are as follows: S111: Based on the task units divided by road construction areas, extract the equipment running trajectory and operation status distribution curves within the task unit, calculate the difference between the two types of data within the same task unit, and obtain the trend value of the difference between the equipment running trajectory and the operation status distribution. S112: Based on the trend value of the difference between the equipment running trajectory and the operation status distribution, identify the inflection point value in the equipment running trajectory and the conversion value of the operation status distribution curve, superimpose the two types of values ​​on time periods, extract the time interval where the inflection point exceeds the benchmark value and the conversion value exceeds the set threshold, and generate a set of high-frequency mutation interval time periods. S113: For the set of time periods with high frequency mutation intervals, match the corresponding task unit number and spatial boundary information, extract the location of the task unit where the signal occurred, and generate a dataset for identifying abnormal operating conditions of equipment.

4. The remote scheduling method for roadbed and pavement construction equipment according to claim 3, characterized in that, The specific steps for obtaining the device behavior deviation area identification result are as follows: S211: Based on the equipment abnormal operation status identification dataset, extract the equipment operation direction vector and the operation status distribution curve of the task unit, extract the projection trajectory of the two at the boundary of the task unit, identify the distribution number and aggregation degree of the boundary point in the task unit, and obtain the task unit boundary consistency map. S212: Based on the task unit boundary consistency map, filter the boundary areas with a higher degree of aggregation than the average level, compare the spatial boundary of the overall structure map of the construction area, identify the continuous boundary concentration areas belonging to the same task unit, and obtain the abnormal zoning of equipment operation trajectory within the construction task unit. S213: Call the abnormal zone of equipment running trajectory within the construction task unit, perform integrated analysis on the consistency of task unit boundary, dispersion of equipment running trajectory, load distribution balance and operation status delay, calculate the abnormal high sensitivity response coefficient, match task units according to the response blocks in the layer, and form the equipment behavior deviation area identification result.

5. The remote scheduling method for roadbed and pavement construction equipment according to claim 4, characterized in that, The specific steps for obtaining the linked task scheduling performance evaluation data table are as follows: S311: Based on the equipment behavior deviation area identification results, extract the equipment load distribution matrix and operation frequency features of the numbered task units in the layer, perform timestamp alignment on the data in the task units, identify the load intensity fluctuation value and the consistency offset of the operation frequency, and obtain the local abnormal response feature set of the construction task. S312: Based on the local abnormal response feature set of the construction task, perform joint analysis on the load balance and operation frequency consistency within the task unit, calculate the load operation coupling feature value, filter the task units with load operation coupling degree in the layer, and establish a load operation collaborative response spatial distribution map. S313: Call the load job collaborative response spatial distribution map, cluster the task units in the coupled feature value layer that exceed the collaborative identification benchmark, label the task unit codes and coordinates corresponding to the continuous abnormal areas, and obtain the linkage task scheduling efficiency evaluation data table.

6. The remote scheduling method for roadbed and pavement construction equipment according to claim 5, characterized in that, The specific steps for obtaining the remote scheduling decision risk rating table are as follows: S411: Based on the location number of the linkage task scheduling efficiency evaluation data table, extract the stress distribution curve of the task unit under the specified number, perform time uniform processing, identify the stress change per unit time, and obtain the set of abnormal stress change rate of the task unit. S412: Based on the set of abnormal stress change rates of the task units, identify the stress distribution curve of the original flatness stage, compare the current stress change sequence with the reference curve, identify the stress deviation level of the task units, extract and mark the task units whose deviation level exceeds the warning upper limit, and obtain the set of task units with sudden increase in deviation. S413: Based on the set of task units with sudden deviations, bind the deviation level value of each task unit to the location number in the structural space map of the construction area, sort them according to risk level, and output the risk rating table for remote scheduling decision.

7. The method for remote scheduling of roadbed and pavement construction equipment according to claim 1, characterized in that, The method also includes step S5: S5: Call the remote scheduling decision risk rating table, identify the corresponding number of the task unit in the road construction function map, extract the list of repair response units, compare the response level with the construction protection priority sequence, filter the task unit number that needs to adjust the response coverage, and output the intelligent collaborative scheduling instruction set for construction equipment. The intelligent collaborative scheduling instruction set for construction equipment includes adjusting the target task unit number, response level adjustment parameters, protection priority comparison items, and linkage response trigger types.

8. The method for remote scheduling of roadbed and pavement construction equipment according to claim 7, characterized in that, The specific steps for obtaining the intelligent collaborative scheduling instruction set for construction equipment are as follows: S511: Call the remote scheduling decision risk classification table, extract the task unit number in the road construction function map, map the task unit risk level value with the regional coordinate boundary, identify the task unit information corresponding to the construction protection level, and generate a construction task risk distribution map. S512: Based on the construction task risk distribution map, extract the repair response unit number and response level, match the task unit risk level with the repair response level, identify the unit number with insufficient response coverage, and obtain the construction task response risk disconnect list. S513: Based on the construction task response risk disconnect list, extract the key task unit number that needs to improve the response coverage according to the level number in the construction protection priority sequence, output the adjustment control parameters linked with the original repair unit in sequence, and output the intelligent collaborative scheduling instruction set for construction equipment.

9. A remote dispatching system for roadbed and pavement construction equipment, characterized in that, The system is used to implement the remote scheduling method for roadbed and pavement construction equipment according to any one of claims 1-8, the system comprising: The trajectory monitoring module is based on the task units divided by the road construction area. It compares the inflection points of the equipment operation trajectory and the time of operation status transition within the same time period, filters the synchronous change intervals of the two, extracts the task unit number and spatial boundary coordinates, summarizes the abnormal time period and task unit number, and generates a dataset for identifying abnormal equipment operation status. Based on the equipment operation abnormality status identification dataset, the task localization module identifies the consistency between the equipment operation direction vector and the operation status distribution curve, calibrates the task unit boundary number, matches the overall structure map of the construction area, extracts the task unit number range of the abnormal equipment operation trajectory area, and establishes the equipment behavior deviation area identification result. Based on the identification results of the equipment behavior deviation area, the task linkage module retrieves the continuous data sequence of the equipment load distribution matrix and the operation frequency characteristics in the area, determines the consistency between the load abnormal boundary connectivity and the operation frequency, marks the task unit number that meets the linkage threshold of both, and outputs the linkage task scheduling efficiency evaluation data table. Based on the task unit number in the linked task scheduling efficiency evaluation data table, the stress early warning module analyzes the stress distribution trend of the corresponding task unit and the degree of deviation from the original flatness curve, extracts the task unit number that deviates from the trend, completes the level identification according to the risk classification standard, and generates a remote scheduling decision risk classification table. Based on the remote scheduling decision risk classification table, the repair and optimization module finds the corresponding position number of the risk level task unit in the road construction function diagram, retrieves the current repair response unit configuration list, compares the matching situation between the construction protection priority and the current response level, filters the task unit numbers that need to be updated, and outputs the intelligent collaborative scheduling instruction set for construction equipment.

Images