Intelligent transport vehicle scheduling method and system

Abstract

The invention discloses an intelligent transport vehicle scheduling method and system, and relates to the technical field of transport vehicle scheduling data processing. The intelligent transport vehicle scheduling method comprises the following steps: S1, collecting transport vehicle scheduling data in a task execution process, and carrying out denoising, complementation, alignment and normalization processing on the transport vehicle scheduling data; s2, monitoring the state change of the task in real time, analyzing the order insertion capability of the vehicle after the recognition task is cancelled, and screening out candidate vehicles entering an order insertion scheduling process according to an order insertion threshold value; s3, matching a task to be inserted for the candidate vehicle, analyzing an order insertion task matching effect, and completing task path reconstruction and order insertion task marking; and S4, executing an order insertion task and recording a state, analyzing a deviation between an order insertion task score and actual execution, proposing a score structure updating suggestion, completing feedback archiving and recovering a vehicle scheduling state. The problem that when the task is cancelled, an original path and an original time window cannot be rapidly recycled and reused, and waste is caused is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of transport vehicle scheduling data processing, and in particular to an intelligent transport vehicle scheduling method and system. Background Art

[0002] Existing transport vehicle scheduling systems mainly rely on preset task paths and static task allocation mechanisms. They usually adopt a centralized scheduling strategy, which allocates tasks to specific vehicles through initial planning and continuously tracks their status during task execution. They are suitable for large-scale, low-variability conventional transportation scenarios.

[0003] For example, the invention with publication number CN118278844A discloses an intelligent dispatching method and system for freight transportation. It includes the following steps: A. Creating an order or entering upstream customer entrustment information through a customer service terminal and generating a pre-scheduled plan; B. Using a route analysis and processing unit in a dispatch center to calculate and analyze the route and match vehicle-related information based on the capacity in the dispatch center's capacity pool; C. An order response system assigns a target vehicle. If the target vehicle accepts the assignment, the information is fed back to the customer service terminal. If the target vehicle rejects the assignment, the system continues to match other vehicles.

[0004] For example, the invention with publication number CN115409308A relates to the field of transportation management, specifically an intelligent dispatching system based on TMS transportation management. Its transportation operation management module includes a vehicle allocation component, which incorporates an intelligent dispatching algorithm. This intelligent dispatching algorithm establishes a multi-order aggregation module based on a threshold range search, which aggregates orders within the same region that are close together into regional orders for unified delivery. It also establishes a truck matching rule based on matching factors, assigning different weights to these matching factors. The truck with the highest total weight is then assigned to the corresponding regional order.

[0005] However, in actual operations, mission cancellations and interruptions frequently occur due to a variety of dynamic factors, including sudden order changes, traffic fluctuations, customer cancellations, and abnormal vehicle status. Existing systems have relatively inefficient resource response mechanisms for mission cancellations. This often leads to issues such as delayed release of routes and time windows, temporary vehicle stalls, redundant resource allocation, and delayed response to intervening missions, resulting in decreased scheduling efficiency and increased energy waste.

[0006] Therefore, in response to the above problems, there is an urgent need for an intelligent transport vehicle scheduling method and system. Summary of the Invention

[0007] Technical problems solved In response to the deficiencies of the prior art, the present invention provides an intelligent transport vehicle scheduling method and system, which solves the problem of waste caused by the original path and time window not being quickly recovered and reused when a task is canceled.

[0008] Technical solution. To achieve the above objectives, the present invention is implemented through the following technical solutions: an intelligent transport vehicle scheduling method and system, comprising the following steps: S1, collecting transport vehicle scheduling data during task execution, and denoising, completing, aligning and normalizing the transport vehicle scheduling data; S2, monitoring task status changes in real time, analyzing the vehicle's insertion capability after identifying task cancellation, and screening out candidate vehicles entering the insertion scheduling process based on the insertion threshold; S3, matching candidate vehicles with tasks to be inserted based on path, time and load conditions, analyzing the matching effect of insertion tasks, and completing task path reconstruction and insertion task marking; S4, executing insertion tasks and recording status, analyzing the deviation between the insertion task score and actual execution, proposing suggestions for updating the score structure, completing feedback archiving and restoring the vehicle scheduling status.

[0009] Furthermore, the specific steps for collecting transport vehicle scheduling data during task execution are as follows: through the coordinated collection of integrated geographic positioning unit, path inertia measurement module, energy consumption sensor, and vehicle execution status feedback unit, transport vehicle scheduling data is collected in real time; wherein, transport vehicle scheduling data includes vehicle task status, scheduling distance, vehicle speed, vehicle speed change rate, scheduling energy consumption, remaining transport fuel, remaining scheduling time, and idle capacity ratio; wherein, the vehicle task status is obtained in real time through the task life cycle management module in the scheduling system, and the cancellation of the current task is recorded as 1, and the normal progress of the current task is recorded as 0; the latitude and longitude coordinates of the original task starting point, the current latitude and longitude coordinates of the vehicle and the latitude and longitude coordinates of the starting point of the task to be inserted are obtained through the high-precision satellite positioning system integrated in the transport vehicle control unit, and the original scheduling distance and the scheduling distance to be inserted are obtained; through The speed sensor installed in the vehicle's main control board obtains the vehicle's speed; the inertial measurement module installed in the vehicle's main control board continuously measures the vehicle's linear acceleration and angular velocity, calculates the speed change rate over continuous time periods, and obtains the vehicle's speed change rate; the current and voltage sensors deployed in the battery management system jointly measure the vehicle's energy release rate per unit driving distance, and the scheduling energy consumption is obtained in combination with the drive motor load parameters; the on-board fuel management system collects the current remaining fuel percentage, and combines the remaining task distance in the vehicle's task execution list with the historical unit fuel consumption data to obtain the remaining transport fuel; the main control task unit reads the current time and compares it with the earliest execution time of the next task in the task scheduling table to obtain the remaining scheduling time; the empty capacity ratio is obtained by retrieving the proportional relationship between the vehicle's current loading information and its maximum loading capacity.

[0010] Furthermore, the specific steps for denoising, completing, aligning and normalizing the transport vehicle scheduling data are as follows: using sliding median filtering combined with the interquartile range method to identify and eliminate local outliers in data such as scheduling distance, vehicle speed and energy consumption; using bidirectional timestamp interpolation and local trend extrapolation to fill the short-term missing transport vehicle scheduling data caused by data delays and interruptions; by aligning the vehicle number with the positioning time, the time of multiple source data such as scheduling distance, speed, fuel volume and task status under the same scheduling trajectory is unified to complete data synchronization; using exponential weighted average and sliding polynomial regression methods to denoise the transport vehicle scheduling data, retaining the trend while reducing fluctuations; using a combination of Z-score standardization and logarithmic scaling to normalize the transport vehicle scheduling data, unify the dimension and compress the numerical range.

[0011] Furthermore, the specific steps of monitoring the changes in task status in real time, analyzing the vehicle's insertion capability after identifying task cancellation, and screening candidate vehicles entering the insertion scheduling process according to the insertion threshold are as follows: real-time monitoring and detection of all executing task statuses, when the system identifies that the vehicle task status of a vehicle changes from 0 to 1, immediately mark the vehicle as a scheduling interruption, and at the same time terminate the execution of the original scheduling path of the vehicle, and cancel the corresponding scheduling record in the system task queue; after removing the vehicle from the current scheduling queue, mark its status as waiting for insertion and write it to the scheduling status buffer; the vehicle is stripped of the scheduling master right in the task control center at the same time, and is controlled by the insertion scheduling module, the original path segment resources are released and exit the path map allocation table; query the current transport vehicle scheduling data, read the vehicle speed, remaining transport fuel, scheduling energy consumption, remaining scheduling time, original scheduling distance, empty capacity ratio and vehicle speed The first part is to calculate the value of the power function by dividing the remaining transport oil by the dispatching energy consumption, dividing the vehicle speed by 1 and adding the vehicle speed change rate; the first part is to calculate the value of the power function by dividing the remaining dispatching time by the sum of the dispatching distance and the remaining dispatching time, using the ratio as the base and the time weight as the exponent; the second part is to calculate the value of the power function by multiplying the empty capacity ratio by the empty load weight and adding 1; the third part is to multiply the above three parts in sequence to obtain the order insertion capability evaluation value; the obtained order insertion capability evaluation value is normalized and compared with the order insertion threshold: when the order insertion capability evaluation value is greater than or equal to the order insertion threshold, the vehicle is pushed into the order insertion candidate queue and a new dispatch entry is assigned to it; when the order insertion capability evaluation value is less than the order insertion threshold, the vehicle is pushed into the standby buffer queue and does not participate in this round of order insertion matching process.

[0012] Furthermore, the specific steps for matching candidate vehicles with pending tasks based on path, time and load conditions are as follows: the current latitude and longitude coordinates, remaining scheduling time, insertion capability evaluation value, current task sequence and scheduling status of the vehicles to be inserted are read from the insertion candidate queue in sequence, and the path attempt status identifier is initialized for each vehicle; all pending tasks that have not yet been assigned in the task pool are queried, the estimated execution time of the pending tasks, the load ratio required for the pending tasks and the pending scheduling distance are extracted, and loaded as a set of optional tasks; for each candidate vehicle, each optional task is traversed, the pending scheduling distance is obtained, and the pending scheduling distance is compared with the set maximum insertion distance. If the distance exceeds, the current task is skipped; for tasks with path distances within the acceptable range, whether the start and end ranges of the task time window and the remaining scheduling time of the vehicle are intersected is continued to be determined. If there is no intersection, the task is skipped; then whether the load ratio required for the pending task is within the current empty capacity ratio range of the vehicle is determined. If the ratio exceeds, the task is skipped; for all tasks that meet the path distance, time window overlap and load constraints, a pending task attempt record is generated.

[0013] Furthermore, the specific steps for analyzing the matching effect of the insertion task and completing the task path reconstruction and insertion task marking are as follows: obtain the scheduling distance to be inserted, the maximum insertion distance, the estimated execution time of the task to be inserted, the load ratio required for the task to be inserted, the remaining scheduling time, the idle capacity ratio and the insertion capacity evaluation value, and calculate the insertion task matching evaluation value of the task to be inserted: divide the scheduling distance to be inserted by the maximum insertion distance, and subtract the ratio from 1, and multiply the difference by the matching weight and the product as the first part; divide the estimated execution time of the task to be inserted by the remaining scheduling time plus the minimum term, subtract the load ratio required for the task to be inserted from the vehicle's idle capacity ratio and divide it by the idle capacity ratio plus the minimum term, and combine the above two ratios. The product of the value, the insertion capability evaluation value and 1 minus the matching weight is used as the second part; the first part is added to the second part to obtain the insertion task matching evaluation value; the calculated insertion task matching evaluation values ​​are sorted in descending order, and the task with the highest insertion task matching evaluation value is extracted as the current vehicle path reconstruction attempt object to generate a new task sequence structure; the scheduling legitimacy of the reconstructed path is checked, including path distance, time window overlap, load constraints and other conditions. If the check passes, the insertion task is marked as the intended execution state, written into the vehicle task structure and the path is numbered; if the check fails, the vehicle will not participate in the insertion in this round, and will be marked as on standby and unassigned, waiting for scheduling in the next cycle.

[0014] Furthermore, the specific steps of executing the insertion task and recording the status are as follows: extract the insertion task marked as the intended execution status, and synchronously write the path structure, scheduling distance to be inserted, estimated execution time of the task to be inserted, load ratio required by the task to be inserted and the task number of the task into the task execution list of the corresponding vehicle, and generate an updated scheduling chain according to the current task sequence of the vehicle; send the new task chain after the insertion of the insertion task to the vehicle scheduling unit, update the execution mark of the insertion task, and record the structural changes of the current insertion position and the original scheduling path; the vehicle starts to execute the insertion task, and the scheduling module receives the task execution status in real time; after the insertion task is completed, read the actual execution result of the insertion task. If the task is completed on time and is not cancelled, it is recorded as 1; otherwise, it is recorded as 0.

[0015] Furthermore, the specific steps for analyzing the deviation between the insertion task score and the actual execution are as follows: calculate the average of the current insertion capacity evaluation value of the insertion batch, and for each insertion task, obtain the actual execution result of the insertion task, the insertion task matching evaluation value, the waiting insertion scheduling distance, the original scheduling distance, the estimated execution time of the waiting insertion task, the load ratio of the waiting insertion task, the remaining scheduling time, the empty capacity ratio and the insertion capacity evaluation value, and calculate the insertion task residual evaluation value: take the square of the difference between the insertion task matching evaluation value and the actual execution result of the insertion task as the first part; divide the estimated execution time of the waiting insertion task by the remaining scheduling time plus the minimum term, subtract the load ratio of the waiting insertion task from the empty capacity ratio of the vehicle and then divide it by the empty capacity ratio plus the minimum term, divide the original scheduling distance by the waiting insertion scheduling distance, divide the insertion capacity evaluation value by the absolute value of the insertion capacity evaluation value minus the average of the current insertion batch insertion capacity evaluation value plus a minimum term, multiply the above four ratios, and the product is the second part; multiply the first part by the second part to obtain the insertion task residual evaluation value.

[0016] Furthermore, the specific steps for proposing a scoring structure update, completing feedback archiving and restoring the vehicle scheduling status are as follows: using the insertion task residual evaluation value as the basis for modifying the scheduling strategy, and comparing the insertion task residual evaluation value with the task matching threshold in real time: if the insertion task residual evaluation value of a certain insertion task is greater than or equal to the task matching threshold, it is determined to be a strategy deviation sample, and the insertion task matching evaluation value, insertion capacity evaluation value, remaining scheduling time, original scheduling distance, scheduling distance to be inserted, idle capacity ratio, load ratio required for the task to be inserted and other parameters of the sample are all written into the strategy deviation sample table and marked as high residual samples; such samples will be analyzed in detail in the subsequent scoring function structure optimization; if the insertion task residual evaluation value of a certain insertion task is less than the task matching threshold, it is determined to be a scoring stable sample, and the sample will still record the residual score and execution parameters to maintain the integrity of the sample data, but will not enter the deviation sample buffer. , it is only used as the control data for the subsequent stability evaluation of the scoring function and does not participate in the weight correction; when all the insertion tasks in this round are completed, the scheduling module summarizes the strategy deviation samples and the scoring stable samples to form an insertion sample set; statistical analysis is performed on the high residual samples to identify the variable combinations that appear frequently in the high residual samples and mark them as parameter abnormality combinations; based on the parameter abnormality combinations, structural adjustment suggestions are made for the relevant variable items in the insertion task matching evaluation value formula, and an updated scoring function draft is generated as the candidate scoring structure for the next cycle; the scoring function draft is written into the scoring function version control table together with the insertion task residual evaluation value distribution and deviation sample proportion of the current cycle, and a version number is generated for use in the next cycle scheduling decision; after all insertion task feedback records are completed, the vehicle scheduling status is updated, the insertion control right is released, the vehicle is re-written into the main scheduling queue, the system enters the next scheduling cycle, and the insertion process is closed.

[0017] The second aspect of the present invention provides an intelligent transport vehicle scheduling system, including: a transport vehicle scheduling data acquisition and preprocessing module, a task cancellation detection and resource status modeling module, an insertion task screening and path reconstruction module, and an insertion task execution and feedback correction module, wherein: the transport vehicle scheduling data acquisition and preprocessing module is used to collect transport vehicle scheduling data during task execution, and to denoise, complete, align and normalize the transport vehicle scheduling data; the task cancellation detection and insertion vehicle screening module is used to monitor task status changes in real time, analyze the vehicle's insertion capability after identifying task cancellation, and screen out candidate vehicles entering the insertion scheduling process based on the insertion threshold; the insertion task screening and path reconstruction module is used to match candidate vehicles with tasks to be inserted based on path, time and load conditions, analyze the insertion task matching effect, and complete task path reconstruction and insertion task marking; the insertion task execution and feedback correction module is used to execute the insertion task and record the status, analyze the deviation between the insertion task score and the actual execution, propose score structure update suggestions, complete feedback archiving and restore the vehicle scheduling status.

[0018] Beneficial effects The present invention has the following beneficial effects: (1) This intelligent transport vehicle scheduling method and system constructs an insertion capability evaluation model, takes the remaining transport fuel volume, scheduling energy consumption, vehicle speed, speed change rate, remaining scheduling time, and empty capacity ratio as input variables, and uses an exponential power function structure to output an insertion capability evaluation value, which is used to measure the current likelihood of a vehicle taking on a new task. This evaluation mechanism performs dynamic calculations based on the actual scheduling status, making the selection of insertion candidates more accurate and efficient.

[0019] (2) This intelligent transport vehicle scheduling method and system designs an insertion task matching evaluation function, combines the distance to be inserted, the expected execution time of the task to be inserted, the proportion of the load required by the task to be inserted and the ratio of the empty capacity, the remaining scheduling time and the insertion capacity evaluation value to score, and prioritizes all insertable tasks. This scoring structure uniformly quantifies spatial adaptation, time coordination and resource carrying capacity, improving the rationality of the selection of insertion path reconstruction and the scheduling flexibility.

[0020] (3) This intelligent transport vehicle scheduling method and system constructs a residual scoring expression for insertion tasks, combines the deviation between the predicted score and the actual execution result with the task execution time ratio, load ratio, path distance ratio, and the degree of deviation from the insertion capacity, and forms a residual indicator that can be used to correct the scoring structure. This mechanism can identify key samples with inaccurate scoring and generate optimization suggestions for the scoring function structure based on this, thereby achieving continuous evolution of the scoring model and strategy adjustment.

[0021] (4) This intelligent transport vehicle scheduling method and system monitors the task status field of the transport vehicle in real time. When it detects that the task changes from being executed to being canceled, it immediately terminates the execution of the original scheduling path, releases the corresponding path segment and time window resources, and switches the vehicle status to the waiting state to complete the transfer of scheduling control. This mechanism effectively ensures the connection between resource cleanup and vehicle scheduling status after task interruption, providing basic resource space for subsequent order matching.

[0022] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 This is a flow chart of an intelligent transport vehicle scheduling method; Figure 2 This is a structural diagram of an intelligent transport vehicle scheduling system; Figure 3 A radar chart driven by the order insertion capability assessment value; Figure 4A histogram of evaluation values ​​for matching single-item tasks. DETAILED DESCRIPTION

[0024] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0025] See also Figures 1-4 , an embodiment of the present invention provides a technical solution: an intelligent transport vehicle scheduling method and system, comprising the following steps: S1, collecting transport vehicle scheduling data during task execution, and denoising, completing, aligning and normalizing the transport vehicle scheduling data; S2, monitoring task status changes in real time, analyzing the vehicle's insertion capability after identifying task cancellation, and screening out candidate vehicles entering the insertion scheduling process based on the insertion threshold; S3, matching candidate vehicles with tasks to be inserted based on path, time and load conditions, analyzing the insertion task matching effect, and completing task path reconstruction and insertion task marking; S4, executing the insertion task and recording the status, analyzing the deviation between the insertion task score and the actual execution, proposing a score structure update suggestion, completing feedback archiving and restoring the vehicle scheduling status.

[0026] Specifically, the specific steps for collecting transport vehicle scheduling data during task execution are as follows: collect transport vehicle scheduling data in real time through collaborative collection by integrating geographic positioning unit, path inertia measurement module, energy consumption sensor, and vehicle execution status feedback unit; wherein, transport vehicle scheduling data includes vehicle task status, scheduling distance, vehicle speed, vehicle speed change rate, scheduling energy consumption, remaining transport fuel, remaining scheduling time, and empty capacity ratio; wherein, the vehicle task status is obtained in real time through the task life cycle management module in the scheduling system, and the cancellation of the current task is recorded as 1, and the normal progress of the current task is recorded as 0; the longitude and latitude coordinates of the original task starting point, the current longitude and latitude coordinates of the vehicle and the longitude and latitude coordinates of the starting point of the task to be inserted are obtained through the high-precision satellite positioning system integrated in the transport vehicle control unit, and the original scheduling distance and the scheduling distance to be inserted are obtained; through The speed sensor installed in the vehicle's main control board obtains the vehicle's speed; the inertial measurement module installed in the vehicle's main control board continuously measures the vehicle's linear acceleration and angular velocity, calculates the speed change rate over continuous time periods, and obtains the vehicle's speed change rate; the current and voltage sensors deployed in the battery management system jointly measure the vehicle's energy release rate per unit driving distance, and the scheduling energy consumption is obtained in combination with the drive motor load parameters; the on-board fuel management system collects the current remaining fuel percentage, and combines the remaining task distance in the vehicle's task execution list with the historical unit fuel consumption data to obtain the remaining transport fuel; the main control task unit reads the current time and compares it with the earliest execution time of the next task in the task scheduling table to obtain the remaining scheduling time; the empty capacity ratio is obtained by retrieving the proportional relationship between the vehicle's current loading information and its maximum loading capacity.

[0027] In this implementation, comprehensive acquisition of transport vehicle dispatch data is achieved through multi-module collaborative collection. This ensures real-time perception and quantitative expression of key parameters such as vehicle mission status, dispatch distance, vehicle speed, vehicle speed change rate, dispatch energy consumption, remaining transport fuel, remaining dispatch time, and empty capacity ratio. By integrating hardware modules such as geolocation, inertial measurement, energy consumption monitoring, mission management, and vehicle feedback, this process ensures the spatiotemporal synchronization and physical consistency of various dispatch data. This provides a stable data foundation for subsequent order insertion capability assessment, mission matching determination, and route reconstruction, improving the dispatch process's response accuracy to changes in transport status and its ability to support structural modeling.

[0028] Specifically, the specific steps for denoising, completing, aligning and normalizing the transport vehicle dispatching data are as follows: First, a sliding median filter combined with the interquartile range method is used to identify and eliminate local outliers in data such as dispatching distance, vehicle speed and dispatching energy consumption, effectively avoiding the interference of instantaneous errors on subsequent calculations; in response to possible delays or instantaneous interruptions during data transmission, a two-way timestamp interpolation and local trend extrapolation method is used to complete the short-term missing data of key indicators such as dispatching distance, vehicle speed and vehicle speed change rate, and restore the continuous time series; then, by accurately aligning the vehicle number and positioning time, the dispatching distance and vehicle speed from different sources are aligned. Multi-source asynchronous data such as the remaining transport oil volume and vehicle task status are mapped to a unified scheduling trajectory timeline to complete the time series synchronization processing; in order to further reduce the impact of measurement noise and external disturbances, the exponential weighted average and sliding polynomial regression methods are used to dynamically denoise the transport vehicle scheduling data, extract stable change trends and smooth local mutations; finally, by using a combination of Z-score standardization and logarithmic scaling, all transport vehicle scheduling data are uniformly normalized, which not only eliminates the dimensional differences of each scheduling data on the numerical scale, but also compresses its dynamic fluctuation range, providing standardized input for the stable modeling of subsequent insertion capability evaluation values ​​and insertion task matching evaluation values.

[0029] This implementation effectively improves the continuity, accuracy, and comparability of key data such as dispatch distance, vehicle speed, vehicle speed change rate, dispatch energy consumption, remaining transport fuel, and vehicle mission status through systematic denoising, completion, alignment, and normalization of transport vehicle dispatch data. This process eliminates local outliers, repairs short-term gaps, and achieves time alignment of multi-source data. Through dynamic denoising and scale normalization, this process provides dispatch data with a unified time base and numerical specifications. This provides high-quality, low-noise data support for the stable calculation of insertion capability and insertion task matching assessments, ensuring the executable nature of subsequent dispatch calculation logic and the reliability of the evaluation structure.

[0030] Specifically, the specific steps of monitoring the changes in task status in real time, analyzing the vehicle's insertion capability after identifying task cancellation, and screening candidate vehicles entering the insertion scheduling process according to the insertion threshold are as follows: real-time monitoring and detection of all executing task statuses. When the system identifies that the vehicle task status of a vehicle changes from 0 to 1, the vehicle is immediately marked as scheduling interrupted, and the execution of the original scheduling path of the vehicle is terminated, and the corresponding scheduling record is cancelled in the system task queue; after the vehicle is removed from the current scheduling queue, its status is marked as waiting for insertion and written into the scheduling status buffer; the vehicle is stripped of the scheduling control right in the task control center at the same time, and is controlled by the insertion scheduling module, the original path segment resources are released and exit the path map allocation table; query the current transport vehicle scheduling data, read the vehicle speed, remaining transport fuel, scheduling energy consumption, remaining scheduling time, original scheduling distance, empty capacity ratio and vehicle speed change rate; divide the remaining transport fuel by the scheduling energy consumption, divide the vehicle speed by 1 and add the vehicle speed change rate, and multiply these two ratios as the base number. The capability weight is the most indicative The power function is calculated as the first part. The remaining dispatch time is divided by the sum of the dispatch distance and the remaining dispatch time, with the ratio as the base and the time weight as the exponent. The power function is calculated as the second part. The idle capacity ratio is multiplied by the idle weight and then added with 1 as the third part. The minimum mean square error method is used to fit successful and failed order insertion samples in historical order insertion execution data. The residual model is established and trained and optimized using the dispatch energy consumption, vehicle speed change rate, remaining dispatch time, idle capacity ratio, and task completion status before the order insertion. The capacity weight, time weight, and idle weight are all in the range of [0, 1]. The above three parts are multiplied in sequence to obtain the order insertion capability evaluation value. The obtained order insertion capability evaluation value is normalized and compared with the order insertion threshold. When the order insertion capability evaluation value is greater than or equal to the order insertion threshold, the vehicle is pushed into the order insertion candidate queue and assigned a new dispatch entry. When the order insertion capability evaluation value is less than the order insertion threshold, the vehicle is pushed into the standby buffer queue and does not participate in the current order insertion matching process.

[0031] The specific calculation formula for the order insertion capability evaluation value is: ; Where, Indicates the insertion capability evaluation value. Indicates the remaining transport oil volume, represents the scheduling energy consumption, Indicates the vehicle speed, represents the rate of change of vehicle speed, Indicates the remaining scheduling time, represents the original dispatch distance, Indicates the no-load capacity ratio, Represents the ability weight, represents the time weight, Indicates no-load weight.

[0032] In this embodiment, as shown in Table 1, five groups of vehicle dispatch status samples are recorded, and the data include seven parameters: remaining transport fuel, dispatch energy consumption, vehicle speed, vehicle speed change rate, remaining dispatch time, original dispatch distance, and empty capacity ratio. The corresponding order insertion capability evaluation value of each group of samples is calculated based on this. In sample 1, the remaining transport fuel is 0.37, the dispatch energy consumption is 0.62, the vehicle speed is 0.09, the vehicle speed change rate is 0.39, the remaining dispatch time is 0.97, the original dispatch distance is 0.00, the empty capacity ratio is 0.84, and the corresponding order insertion capability evaluation value is 7.14; in sample 2, the remaining transport fuel is increased to 0.98, the dispatch energy consumption is reduced to 0.10, the vehicle speed is 0.49, the vehicle speed change rate is 0.27, the remaining dispatch time is 0.69, the original dispatch distance is 0.67, the empty capacity ratio is 0.93, and the corresponding order insertion capability evaluation value is The value is 18.64; in sample 3, the vehicle speed is 0.00, the vehicle speed change rate is 0.83, the original scheduling distance is 0.31, the idle capacity ratio is 0.33, and the corresponding insertion capability evaluation value is 6.31; in sample 4, the vehicle speed is 0.94, the vehicle speed change rate is 0.36, the remaining scheduling time is 0.04, the idle capacity ratio is 0.10, and the corresponding insertion capability evaluation value is 12.49; in sample 5, the remaining transport oil volume is 0.14, the original scheduling distance is 0.98, the idle capacity ratio is 0.23, and the corresponding insertion capability evaluation value is 5.79.

[0033] Table 1 Insertion capability evaluation value data table

[0034] like Figure 3 The radar chart shown is driven by the insertion capability evaluation value. Figure 3 The chart shows significant differences in the order-interception capabilities of different vehicles. Vehicle 2 demonstrates balanced performance and high values ​​across key variables such as fuel level, remaining time, and empty capacity, achieving the highest order-interception capability assessment and demonstrating significant potential for priority scheduling. Vehicles 1 and 4 excel in certain dimensions, such as vehicle 1's strong remaining time and capacity, and vehicle 4's high speed, but their overall capabilities are intermediate due to high energy consumption or insufficient time resources. Vehicles 3 and 5 exhibit weaker performance across multiple dimensions, including speed, time, and capacity, achieving the lowest order-interception capability assessments. The thickness and color of the radar lines in the figure directly reflect capability strength, while the graph's expansion and balance reveal each vehicle's scheduling resource structure, helping to intuitively determine scheduling priorities and task matching suitability.

[0035] In this implementation plan, through real-time monitoring of vehicle task status and identification of scheduling interruptions, a dynamic assessment of the transport vehicle's ability to insert an order after the task is canceled is achieved. This process is based on the vehicle speed, remaining transport fuel, scheduling energy consumption, remaining scheduling time, original scheduling distance, vehicle speed change rate, and empty capacity ratio in the transport vehicle scheduling data. The resource status of each interrupted vehicle is quantitatively modeled through the order insertion capability assessment model to generate an order insertion capability assessment value. After normalization, by comparing with the order insertion threshold, it is possible to accurately distinguish whether the vehicle has the scheduling potential to participate in the order insertion, thereby pushing vehicles with the order insertion capability into the order insertion candidate queue, building a stable and controllable scheduling entry screening mechanism, and improving the resource recovery efficiency and scheduling response flexibility in the task cancellation scenario.

[0036] Specifically, the specific steps for matching candidate vehicles with tasks to be inserted based on path, time and load conditions are as follows: read the current latitude and longitude coordinates, remaining scheduling time, insertion capability evaluation value, current task sequence and scheduling status of the vehicles to be inserted from the insertion candidate queue in sequence, and initialize the path attempt status identifier for each vehicle to facilitate subsequent recording of scheduling path changes; at the same time, query all unassigned tasks to be executed in the task pool, extract the estimated execution time of the tasks to be inserted, the load ratio required for the tasks to be inserted and the scheduling distance to be inserted, and load them as the optional task set for the current batch; for each candidate vehicle, traverse the optional tasks one by one, obtain its corresponding scheduling distance to be inserted, and compare it with the set maximum insertion distance Compare them one by one. If the scheduling distance of the current task to be inserted exceeds the maximum range, the task is skipped and marked as path inconsistent. For tasks whose path distance is within the acceptable range, further determine whether there is an intersection between the start and end range of their time window and the remaining scheduling time of the vehicle. If the time windows do not overlap, the task is skipped. Then, determine whether the load ratio required by the task to be inserted is less than or equal to the current empty capacity ratio of the vehicle. If it exceeds, it is considered a load conflict and the current task is skipped. Finally, for all tasks that meet the path distance conditions, time window conditions and load conditions at the same time, generate a single task attempt record to be inserted, and mark its task number and candidate vehicle association information as input data for subsequent matching evaluation and path reconstruction.

[0037] In this implementation plan, by extracting and conditionally screening the transport vehicle scheduling data of the vehicles in the candidate queue for insertion, a task screening mechanism for insertion is established with the distance to be inserted, the remaining scheduling time, and the proportion of empty capacity as core constraints. This process ensures the coordination and consistency of the task to be inserted with the current status of the vehicle in terms of scheduling trajectory, task timeliness, and resource load, based on path range judgment, time window overlap analysis, and load matching verification. By generating records of task attempts to be inserted that meet the path distance, time window, and load constraints, a task set with clear goals and boundaries is provided for subsequent matching evaluation value calculation and path reconstruction, effectively improving the logical rigor and execution efficiency of the insertion process in the task screening stage.

[0038] Specifically, the specific steps for analyzing the matching effect of the insertion task and completing the task path reconstruction and insertion task marking are as follows: obtain the scheduling distance to be inserted, the maximum insertion distance, the estimated execution time of the task to be inserted, the load ratio required for the task to be inserted, the remaining scheduling time, the empty capacity ratio and the insertion ability evaluation value, and calculate the insertion task matching evaluation value of the task to be inserted: divide the scheduling distance to be inserted by the maximum insertion distance, and subtract the ratio from 1, and multiply this difference by the matching weight and take the product as the first part; divide the estimated execution time of the task to be inserted by the remaining scheduling time plus the minimum term, subtract the load ratio required for the task to be inserted from the empty capacity ratio of the vehicle and then divide it by the empty capacity ratio plus the minimum term, multiply the above two ratios, the insertion ability evaluation value and 1 minus the matching weight, and take the product as the second part; among them, through grid search combined with cross-validation algorithm, in the historical In the insertion task, the estimated execution time of the task to be inserted, the proportion of the load required by the task to be inserted, the scheduling distance to be inserted, and the scoring error between the insertion capacity evaluation value and the actual success result are minimized to obtain the matching weight, and the value range of the matching weight is [0,1]; the first part is added to the second part to obtain the insertion task matching evaluation value; the calculated insertion task matching evaluation values ​​are sorted in descending order, and the task with the highest insertion task matching evaluation value is extracted as the current vehicle path reconstruction attempt object to generate a new task sequence structure; the scheduling legitimacy of the reconstructed path is checked, including path distance, time window overlap, load constraint and other conditions. If the check passes, the insertion task is marked as the intended execution state, written into the vehicle task structure and the path is numbered; if the check fails, the vehicle does not participate in the insertion in this round, is marked as on standby and unassigned, and waits for scheduling in the next cycle.

[0039] The specific calculation formula for the insertion task matching evaluation value is: ; Where, Indicates the matching evaluation value of the insertion task. Indicates the distance to be inserted. Indicates the maximum insertion distance. Indicates the estimated execution time of the task to be inserted. Indicates the load ratio required by the task to be inserted, Indicates the remaining scheduling time, Indicates the no-load capacity ratio, represents a minimum term, Indicates the insertion capability evaluation value. Indicates the matching weight.

[0040] In this example, as shown in Table 2, five sets of scheduling parameter combinations for insertion tasks and their corresponding matching evaluation values ​​are recorded. Each task group includes six data items: the distance to be inserted, the estimated execution time of the task to be inserted, the remaining scheduling time, the required load ratio of the task to be inserted, the idle capacity ratio, and the insertion capacity evaluation value. The matching evaluation value of the task to be inserted is calculated based on the aforementioned scoring model under the current vehicle state. In Task 1, the waiting scheduling distance is 4.58, the estimated execution time of the waiting task is 44.21, the remaining scheduling time is 116.69, the required load ratio of the waiting task is 0.35, the idle capacity ratio is 0.79, the insertion capability evaluation value is 13.39, and the corresponding insertion task matching evaluation value is 2.93; in Task 2, the waiting scheduling distance increases to 11.91, the estimated execution time of the waiting task is 41.35, the remaining scheduling time is 101.38, the required load ratio of the waiting task is 0.55, the idle capacity ratio is 0.90, the insertion capability evaluation value is 24.83, and the corresponding insertion task matching evaluation value is 2.01; the waiting scheduling distance of Task 3 is 10.21, the estimated execution time of the waiting task is 25.07, and the remaining scheduling time is 124.8 1, the required load ratio of the task to be inserted is 0.27, the idle capacity ratio is 0.91, the insertion capability evaluation value is 18.52, and the insertion task matching evaluation value is 2.49; the waiting scheduling distance of task 4 is 6.01, the estimated execution time of the task to be inserted is 66.41, the remaining scheduling time is 95.74, the required load ratio of the task to be inserted is 0.41, the idle capacity ratio is 0.59, the insertion capability evaluation value is 8.52, and the insertion task matching evaluation value is 1.68; in task 5, the waiting scheduling distance is 6.73, the estimated execution time of the task to be inserted is 53.98, the remaining scheduling time is 86.56, the required load ratio of the task to be inserted is 0.31, the idle capacity ratio is 0.71, the insertion capability evaluation value is 20.52, and the insertion task matching evaluation value is 3.86 Table 2 Insertion task matching evaluation value data table

[0041] like Figure 4 As shown in Table 2, it is a bar chart of the evaluation value of the insertion task matching. Figure 4As can be seen, the scores of the five tasks differ significantly. Task 5 has the highest matching evaluation value, indicating the strongest overall compatibility in terms of insertion distance, task duration, idle capacity, and vehicle capabilities, and possesses the optimal scheduling matching conditions. Task 4 has the lowest matching evaluation value, possibly due to factors such as long distance, insufficient time, or load mismatch, resulting in weaker overall compatibility. The remaining tasks fall in the middle tier, indicating average compatibility. Overall, the scoring results in the figure effectively reflect the matching quality of each task under multiple scheduling parameters, providing an intuitive basis for scheduling sorting and insertion decisions.

[0042] In this implementation plan, by constructing a calculation process for the evaluation value of the task matching, a comprehensive consideration of transport vehicle scheduling data such as the distance to be scheduled, the maximum distance to be scheduled, the estimated execution time of the task to be scheduled, the proportion of load required for the task to be scheduled, the remaining scheduling time, the proportion of empty capacity, and the evaluation value of the ability to insert the task is achieved, thereby achieving a quantitative judgment of the adaptation relationship between the task and the vehicle. Based on the sorting mechanism of the matching evaluation value, it is possible to effectively screen out the task to be inserted that best matches the current state of the vehicle, and complete the reconstruction of the task path structure and the proposed execution mark of the task to be inserted based on the verification of the legality of the scheduling path, thereby ensuring the consistency and executability of the scheduling behavior in the three dimensions of resources, timing, and path structure, and improving the scheduling success rate of the task to be inserted and the structural rationality of the scheduling path.

[0043] Specifically, the specific steps for executing the insertion task and recording the status are as follows: extract the insertion task marked as the intended execution status, and synchronously write the path structure of the task, the scheduling distance to be inserted, the estimated execution time of the task to be inserted, the load ratio required for the task to be inserted and the task number into the task execution list of the corresponding vehicle, and generate an updated scheduling chain based on the current task sequence of the vehicle to ensure the logical continuity of the task sequence; at the same time, the new task chain structure after the insertion of the insertion task is sent to the vehicle scheduling unit, and the execution mark of the insertion task is updated to clarify the execution identity and control ownership of the current task; the system synchronously records the current insertion position and the original scheduling The structural changes of the path, including the task numbers before and after the insertion point, the path reconstruction identifier, and the resource configuration change field; when the vehicle starts to execute the insertion task, the scheduling module continuously receives feedback on the task execution status and monitors in real time whether its execution process meets the task setting parameters; after the insertion task is completed, the system reads the actual execution result of the task. If the task is completed within the specified time window and is not canceled midway, the task execution result is marked as 1; if the task is not completed as planned or is canceled midway, it is marked as 0, and the execution status record is written into the task status history table for subsequent scheduling strategy correction and scoring function backtracking analysis.

[0044] In this implementation plan, a complete closed loop for insert task execution is constructed by writing the path structure, updating the scheduling chain, monitoring the execution status, and recording the results for the insert task marked as being in the intended execution state. In this process, key scheduling parameters such as the distance to be scheduled, the estimated execution time of the task to be inserted, and the proportion of the load required by the task to be inserted are synchronously written into the task execution list and form an updated task sequence, ensuring the sequential integrity and path structure continuity of the tasks in the scheduling chain. At the same time, by receiving the execution status of the insert task in real time and recording the actual execution results of the insert task, an effective association mechanism between the task execution process and the results is established, providing real and reliable data support for subsequent scoring function optimization, strategy deviation identification, and scheduling logic correction.

[0045] Specifically, the specific steps for analyzing the deviation between the score of the insertion task and the actual execution are as follows: calculate the average of the current insertion batch insertion capacity evaluation value as a reference benchmark for batch scheduling capacity; for each insertion task, obtain the complete scheduling data such as the actual execution result of the insertion task, the insertion task matching evaluation value, the scheduling distance to be inserted, the original scheduling distance, the estimated execution time of the task to be inserted, the load ratio required for the task to be inserted, the remaining scheduling time, the idle capacity ratio and the insertion capacity evaluation value, and construct the score-execution analysis sample of the task; when calculating the residual evaluation value of the insertion task, first take the square of the difference between the insertion task matching evaluation value and the actual execution result of the insertion task as the first part, which is used to reflect the difference between the score and the execution result. The direct deviation between the results; secondly, calculate the following four ratios in sequence: divide the expected execution time of the task to be inserted by the remaining scheduling time plus the minimum term; subtract the vehicle's empty capacity ratio from the load ratio required for the task and divide it by the empty capacity ratio plus the minimum term; divide the original scheduling distance by the scheduling distance to be inserted; divide the insertion capability evaluation value by the absolute value of the difference between itself and the average insertion capability evaluation value of the current insertion batch plus a minimum term; multiply these four ratios, and the product is used as the second part to characterize the indirect coupling relationship between the task parameters and the system state; finally, multiply the first part and the second part to obtain the insertion task residual evaluation value, which is used to measure the degree of deviation of the insertion task matching score under the current scheduling state.

[0046] The specific formula for the residual evaluation value of the insertion task is: ; Where, Represents the residual evaluation value of the insertion task, Indicates the actual execution result of the insertion task. Indicates the matching evaluation value of the insertion task. Indicates the distance to be inserted. represents the original dispatch distance, Indicates the estimated execution time of the task to be inserted. Indicates the load ratio required by the task to be inserted, Indicates the remaining scheduling time, Indicates the no-load capacity ratio, represents a minimum term, Indicates the insertion capability evaluation value. Indicates the average evaluation value of the order insertion capability of the current order insertion batch.

[0047] This implementation establishes a process for calculating the residual evaluation value of insertion tasks. This process quantifies the deviation between scoring results and actual execution performance based on transport vehicle scheduling data, including the actual execution results of insertion tasks, the matching evaluation value of insertion tasks, the insertion capacity evaluation value, the distance to be scheduled, the original scheduling distance, the estimated execution time of the insertion tasks, the required load ratio of the insertion tasks, the remaining scheduling time, and the ratio of empty capacity. The residual evaluation value comprehensively considers the coupling strength between scoring errors and task parameters, providing a key error feedback basis for the scheduling system in identifying strategy deviations, optimizing the scoring model structure, and improving task screening accuracy. This enhances the scheduling logic's ability to adapt to and correct actual operating conditions.

[0048] Specifically, the specific steps for proposing scoring structure update suggestions, completing feedback archiving and restoring vehicle scheduling status are as follows: Use the insertion task residual evaluation value as the basis for scheduling strategy correction, and compare the insertion task residual evaluation value with the task matching threshold in real time: If the insertion task residual evaluation value of a certain insertion task is greater than or equal to the task matching threshold, it is determined to be a strategy deviation sample, and the insertion task matching evaluation value, insertion capacity evaluation value, remaining scheduling time, original scheduling distance, to-be-inserted scheduling distance, idle capacity ratio, load ratio required for the task to be inserted, and other parameters of the sample are all written into the strategy deviation sample table and marked as high residual samples; such samples will be analyzed in detail in the subsequent scoring function structure optimization; if the insertion task residual evaluation value of a certain insertion task is less than the task matching threshold, it is determined to be a scoring stable sample, and the sample will still record the residual score and execution parameters to maintain the integrity of the sample data, but will not enter the deviation sample buffer. It is only used as control data for the subsequent stability evaluation of the scoring function and does not participate in the weight correction; when all the insertion tasks in this round are completed, the scheduling module summarizes the strategy deviation samples and the scoring stable samples to form an insertion sample set; statistical analysis is performed on the high residual samples to identify the variable combinations that appear frequently in the high residual samples and mark them as parameter abnormality combinations; based on the parameter abnormality combinations, structural adjustment suggestions are made for the relevant variable items in the insertion task matching evaluation value formula, and an updated scoring function draft is generated as the candidate scoring structure for the next cycle; the scoring function draft is written into the scoring function version control table together with the insertion task residual evaluation value distribution and deviation sample ratio of the current cycle, and a version number is generated for use in decision-making before scheduling the next cycle; after all insertion task feedback records are completed, the vehicle scheduling status is updated, the insertion control right is released, the vehicle is rewritten into the main scheduling queue, the system enters the next scheduling cycle, and the insertion process is closed.

[0049] In this implementation plan, a feedback mechanism for identifying scheduling strategy deviations and correcting scoring structures is established by comparing the residual evaluation value of the insertion task with the task matching threshold in real time. After the execution of the insertion task is completed, the system divides the samples into strategy deviation samples and scoring stable samples based on the residual evaluation value of the insertion task, and records key transport vehicle scheduling data such as the insertion task matching evaluation value, insertion capacity evaluation value, remaining scheduling time, original scheduling distance, waiting scheduling distance, empty capacity ratio, and load ratio required for the task to be inserted. Through centralized statistics and variable combination analysis of high residual samples, the source of scoring deviation is identified, and structural adjustment suggestions for the insertion task matching evaluation value formula are proposed, and then a draft scoring function is generated and version archive management is performed. After completing all insertion task feedback records, the system synchronously updates the vehicle scheduling status, releases the insertion control right, and writes the vehicle back to the main scheduling queue, realizing a closed loop of insertion task execution and scheduling logic correction, providing a traceable and optimizable scoring structure evolution basis for the next cycle.

[0050] like Figure 2 As shown, the second aspect of the present invention provides an intelligent transport vehicle scheduling system, including: a transport vehicle scheduling data acquisition and preprocessing module, a task cancellation detection and resource status modeling module, an insertion task screening and path reconstruction module, and an insertion task execution and feedback correction module, wherein: the transport vehicle scheduling data acquisition and preprocessing module is used to collect the transport vehicle scheduling data during the task execution process, and denoise, complete, align and normalize the transport vehicle scheduling data; the task cancellation detection and insertion vehicle screening module is used to monitor the task status changes in real time, analyze the vehicle's insertion capability after identifying the task cancellation, and screen out candidate vehicles entering the insertion scheduling process according to the insertion threshold; the insertion task screening and path reconstruction module is used to match the candidate vehicles with the tasks to be inserted based on the path, time and load conditions, analyze the insertion task matching effect, and complete the task path reconstruction and insertion task marking; the insertion task execution and feedback correction module is used to execute the insertion task and record the status, analyze the deviation between the insertion task score and the actual execution, propose a score structure update suggestion, complete the feedback archiving and restore the vehicle scheduling status.

[0051] In this implementation plan, a complete scheduling system consisting of a transport vehicle scheduling data collection and preprocessing module, a task cancellation detection and insertion vehicle screening module, an insertion task screening and path reconstruction module, and an insertion task execution and feedback correction module is constructed. The transport vehicle scheduling data collection and preprocessing module is used to realize the standardized collection and cleaning of scheduling data during task execution, providing high-quality input for subsequent processing; the task cancellation detection and insertion vehicle screening module can perceive task status changes in real time, identify interruption resources and quantify insertion capabilities, ensuring the timeliness and accuracy of scheduling responses; the insertion task screening and path reconstruction module screens tasks and reconstructs path structures under path distance, time window and load constraints, improving the rationality of insertion task matching and scheduling continuity; the insertion task execution and feedback correction module realizes dynamic closed-loop and adaptive optimization of the scheduling process by recording task status, evaluating execution deviations and correcting the scoring structure. The four modules work together to form a full-process chain of insertion scheduling based on transport vehicle scheduling data, enhancing scheduling flexibility, stability and strategy adjustability in complex scenarios.

[0052] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0053] The preferred embodiments of the present invention disclosed above are intended only to help illustrate the present invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the present invention to the specific embodiments described. Obviously, many modifications and variations are possible based on the content of this specification. These embodiments are selected and described in detail in this specification to better explain the principles and practical applications of the present invention, thereby enabling those skilled in the art to better understand and utilize the present invention. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A method for dispatching intelligent transport vehicles, characterized in that: The following steps are involved: S1, collects the transport vehicle scheduling data during the task execution process, and performs denoising, completion, alignment and normalization on the transport vehicle scheduling data; S2 monitors task status changes in real time, identifies task cancellations, analyzes the vehicle's order insertion capabilities, and selects candidate vehicles for the order insertion scheduling process based on the order insertion threshold. S3: Match the candidate vehicles with the task to be inserted based on the path, time, and load conditions, analyze the task matching results, and complete the task path reconstruction and task marking; S4, execute the insertion task and record the status, analyze the deviation between the insertion task score and the actual execution, propose suggestions for updating the scoring structure, complete the feedback archiving and restore the vehicle scheduling status.

2. The intelligent transport vehicle scheduling method according to claim 1, characterized in that: The specific steps for collecting the transport vehicle scheduling data during the execution of the task are as follows: The transport vehicle scheduling data is collected in real time through the collaborative collection of the integrated geographic positioning unit, the path inertia measurement module, the energy consumption sensor, and the vehicle execution status feedback unit; wherein, the transport vehicle scheduling data includes vehicle task status, scheduling distance, vehicle speed, vehicle speed change rate, scheduling energy consumption, remaining transport fuel, remaining scheduling time, and empty capacity ratio; wherein, the vehicle task status is obtained in real time through the task life cycle management module in the scheduling system, and the cancellation of the current task is recorded as 1, and the normal progress of the current task is recorded as 0; the latitude and longitude coordinates of the original task starting point, the current latitude and longitude coordinates of the vehicle and the latitude and longitude coordinates of the starting point of the task to be inserted are obtained through the high-precision satellite positioning system integrated in the transport vehicle control unit, and the original scheduling distance and the scheduling distance to be inserted are obtained; through the speed sensor installed in the vehicle main control board , obtain the vehicle speed; continuously measure the vehicle's linear acceleration and angular velocity through the inertial measurement module installed in the vehicle's main control board, calculate the speed change rate in continuous time periods, and obtain the vehicle speed change rate; jointly measure the vehicle's energy release rate per unit driving distance through the current and voltage sensors deployed in the battery management system, and obtain the scheduling energy consumption in combination with the drive motor load parameters; collect the current remaining fuel percentage through the on-board fuel management system, and combine the remaining task distance in the vehicle task execution list with the historical unit fuel consumption data to obtain the remaining transport fuel; read the current time through the main control task unit and compare it with the earliest execution time of the next task in the task scheduling table to obtain the remaining scheduling time; obtain the empty capacity ratio by retrieving the proportional relationship between the vehicle's current loading information and its maximum loading capacity.

3. The intelligent transport vehicle scheduling method according to claim 1, characterized in that: The specific steps of denoising, completing, aligning and normalizing the transport vehicle scheduling data are as follows: A sliding median filter combined with the interquartile range method is used to identify and eliminate local outliers in data such as dispatch distance, vehicle speed and energy consumption; bidirectional timestamp interpolation and local trend extrapolation are used to fill the short-term gaps in transport vehicle dispatch data caused by data delays and interruptions; by aligning vehicle numbers with positioning times, the time of multi-source data such as dispatch distance, speed, fuel volume and task status under the same dispatch trajectory is unified to complete data synchronization; exponential weighted average and sliding polynomial regression methods are used to denoise the transport vehicle dispatch data, retaining trends while reducing fluctuations; and the transport vehicle dispatch data is normalized by using a combination of Z-score standardization and logarithmic scaling to unify the dimensions and compress the numerical range.

4. The intelligent transport vehicle scheduling method according to claim 1, characterized in that: The specific steps of monitoring task status changes in real time, analyzing the vehicle's order insertion capability after identifying task cancellation, and screening candidate vehicles for the order insertion scheduling process based on the order insertion threshold are as follows: Monitor and detect the status of all executing tasks in real time. When the system identifies that the vehicle task status of a vehicle changes from 0 to 1, it immediately marks the vehicle as scheduling interrupted, suspends the execution of the vehicle's original scheduling path, and cancels the corresponding scheduling record in the system task queue; After the vehicle is removed from the current dispatch queue, its status is marked as pending order insertion and written into the dispatch status buffer. At the same time, the vehicle is stripped of the dispatch master control in the mission control center and is controlled by the order insertion scheduling module. The original path segment resources are released and removed from the path map allocation table. Query the current transport vehicle dispatch data and read the vehicle speed, remaining transport fuel, dispatch energy consumption, remaining dispatch time, original dispatch distance, no-load capacity ratio, and vehicle speed change rate. Divide the remaining transport fuel by the dispatch energy consumption, divide the vehicle speed by 1, and add the vehicle speed change rate. Multiply these two ratios as the base, use the capacity weight as the exponent, and calculate the value of this power function as the first part. Divide the remaining dispatch time by the sum of the dispatch distance and the remaining dispatch time, use the ratio as the base, and use the time weight as the exponent to calculate the value of this power function as the second part. Multiply the no-load capacity ratio by the no-load weight and add 1 as the third part. Multiply the above three parts in sequence to obtain the order insertion capacity assessment value. The obtained order insertion capability evaluation value is normalized and compared with the order insertion threshold: when the order insertion capability evaluation value is greater than or equal to the order insertion threshold, the vehicle is pushed into the order insertion candidate queue and a new scheduling entry is assigned to it; when the order insertion capability evaluation value is less than the order insertion threshold, the vehicle is pushed into the standby buffer queue and does not participate in this round of order insertion matching process.

5. The intelligent transport vehicle scheduling method according to claim 1, characterized in that: The specific steps of matching candidate vehicles with tasks to be inserted based on path, time and load conditions are as follows: The current latitude and longitude coordinates, remaining scheduling time, order insertion capability assessment value, current task sequence, and scheduling status of each vehicle to be inserted are read from the order insertion candidate queue in sequence, and the path attempt status flag is initialized for each vehicle. All unassigned pending tasks in the task pool are queried, and the estimated execution time, required load ratio, and scheduling distance of the pending tasks are extracted, and loaded into the optional task set. For each candidate vehicle, traverse each optional task, obtain the waiting scheduling distance, and compare the waiting scheduling distance with the set maximum insertion distance. If it exceeds, skip the current task; for tasks within the acceptable path distance, continue to determine whether the start and end ranges of the task time window and the remaining scheduling time of the vehicle intersect. If there is no intersection, skip it; then determine whether the load ratio required by the waiting task is within the current empty load capacity ratio range of the vehicle. If it exceeds, skip it; for all tasks that meet the path distance, time window overlap, and load constraints, generate a waiting task attempt record.

6. The intelligent transport vehicle scheduling method according to claim 1, characterized in that: The specific steps of analyzing the matching effect of the insertion task and completing the task path reconstruction and insertion task marking are as follows: Obtain the scheduling distance to be inserted, the maximum insertion distance, the estimated execution time of the task to be inserted, the load ratio required for the task to be inserted, the remaining scheduling time, the idle capacity ratio, and the insertion capability evaluation value, and calculate the insertion task matching evaluation value of the task to be inserted: divide the scheduling distance to be inserted by the maximum insertion distance, subtract the ratio from 1, and multiply this difference by the matching weight. The product is used as the first part; divide the estimated execution time of the task to be inserted by the remaining scheduling time plus the minimum term, subtract the load ratio required for the task to be inserted from the idle capacity ratio of the vehicle, and then divide it by the idle capacity ratio plus the minimum term. Multiply the above two ratios, the insertion capability evaluation value, and 1 minus the matching weight, and the product is used as the second part. Add the first part and the second part to obtain the insertion task matching evaluation value. The calculated insertion task matching evaluation values ​​are sorted in descending order, and the task with the highest insertion task matching evaluation value is extracted as the current vehicle path reconstruction attempt object to generate a new task sequence structure; the scheduling legitimacy of the reconstructed path is checked, including path distance, time window overlap, load constraints and other conditions. If the check passes, the insertion task is marked as the intended execution state, written into the vehicle task structure and the path is numbered; if the check fails, the vehicle will not participate in the insertion in this round and will be marked as on standby and unassigned, waiting for scheduling in the next cycle.

7. The intelligent transport vehicle scheduling method according to claim 1, characterized in that: The specific steps of executing the insertion task and recording the status are as follows: Extract the insertion task marked as being in the intended execution state, and synchronously write the task's path structure, scheduling distance to be inserted, estimated execution time of the task to be inserted, required load ratio of the task to be inserted, and task number into the task execution list of the corresponding vehicle. Generate an updated scheduling chain based on the vehicle's current task sequence; send the new task chain after the insertion task is inserted to the vehicle scheduling unit, update the execution mark of the insertion task, and record the structural changes between the current insertion position and the original scheduling path; The vehicle starts to execute the insertion task, and the scheduling module receives the task execution status in real time. After the insertion task is completed, the actual execution result of the insertion task is read. If the task is completed on time and not cancelled, it is recorded as 1; otherwise it is recorded as 0.

8. The intelligent transport vehicle scheduling method according to claim 1, characterized in that: The specific steps of analyzing the deviation between the insertion task score and the actual execution are as follows: Calculate the mean of the current insertion capacity evaluation value of the insertion batch. For each insertion task, obtain the actual execution result of the insertion task, the insertion task matching evaluation value, the waiting insertion scheduling distance, the original scheduling distance, the estimated execution time of the waiting insertion task, the load ratio of the waiting insertion task, the remaining scheduling time, the empty capacity ratio and the insertion capacity evaluation value, and calculate the insertion task residual evaluation value: take the square of the difference between the insertion task matching evaluation value and the actual execution result of the insertion task as the first part; divide the estimated execution time of the waiting insertion task by the remaining scheduling time plus the minimum term, subtract the load ratio of the waiting insertion task from the empty capacity ratio of the vehicle and then divide it by the empty capacity ratio plus the minimum term, divide the original scheduling distance by the waiting insertion scheduling distance, divide the insertion capacity evaluation value by the absolute value of the insertion capacity evaluation value minus the average of the current insertion batch insertion capacity evaluation value plus a minimum term, multiply the above four ratios, and the product is taken as the second part; multiply the first part by the second part to obtain the insertion task residual evaluation value.

9. The intelligent transport vehicle scheduling method according to claim 1, characterized in that: The specific steps for proposing a rating structure update, completing feedback archiving, and restoring vehicle dispatch status are as follows: The insertion task residual evaluation value is used as the basis for scheduling policy corrections. The insertion task residual evaluation value is compared with the task matching threshold in real time. If the insertion task residual evaluation value of a certain insertion task is greater than or equal to the task matching threshold, it is determined to be a strategy deviation sample. The sample's insertion task matching evaluation value, insertion capacity evaluation value, remaining scheduling time, original scheduling distance, pending scheduling distance, idle capacity ratio, and required load ratio of the pending task are all written into the strategy deviation sample table and marked as a high residual sample. Such samples will be analyzed in detail in the subsequent scoring function structure optimization. If the residual evaluation value of an insertion task is less than the task matching threshold, it is determined to be a scoring stable sample. The residual score and execution parameters of this sample are still recorded to maintain the integrity of the sample data, but it will not be included in the deviation sample buffer. It is only used as reference data for the subsequent scoring function stability evaluation and will not be included in the weight correction. After all insertion tasks in this round are completed, the scheduling module aggregates the strategy deviation samples and the scoring stable samples to form an insertion sample set. Statistical analysis is performed on the high residual samples to identify variable combinations that frequently appear in these samples and mark them as parameter anomaly combinations. Based on the parameter anomaly combinations, structural adjustment suggestions are made for the relevant variable terms in the insertion task matching evaluation value formula, and an updated scoring function draft is generated as the candidate scoring structure for the next cycle. The scoring function draft, along with the current cycle's insertion task residual evaluation value distribution and the deviation sample ratio, is written into the scoring function version control table and a version number is generated for use in decision-making before scheduling the next cycle. After all order insertion task feedback records are completed, the vehicle scheduling status is updated, the order insertion control is released, the vehicle is rewritten into the main scheduling queue, the system enters the next scheduling cycle, and the order insertion process is closed.

10. An intelligent transport vehicle dispatching system, characterized by: include: Transport vehicle scheduling data collection and preprocessing module, task cancellation detection and resource status modeling module, insertion task screening and path reconstruction module, and insertion task execution and feedback correction module, among which: The transport vehicle scheduling data collection and preprocessing module is used to collect the transport vehicle scheduling data during the task execution process and perform denoising, completion, alignment and normalization on the transport vehicle scheduling data; The task cancellation detection and order insertion vehicle screening module is used to monitor task status changes in real time, analyze the order insertion capability of vehicles after identifying task cancellations, and screen candidate vehicles for entry into the order insertion scheduling process based on the order insertion threshold; The insertion task screening and path reconstruction module is used to match the candidate vehicles with the insertion tasks based on the path, time and load conditions, analyze the insertion task matching results, and complete the task path reconstruction and insertion task marking; The insertion task execution and feedback correction module is used to execute the insertion task and record the status, analyze the deviation between the insertion task score and the actual execution, propose scoring structure update suggestions, complete feedback archiving and restore the vehicle scheduling status.

Images