Intelligent port operation vehicle scheduling system and scheduling robot

Abstract

The invention discloses an intelligent port operation vehicle scheduling system and a scheduling robot, and relates to the technical field of intelligent port operation. The problems that in traditional port vehicle scheduling, the manual scheduling response is slow, the error rate is high, resource distribution is uneven, the labor cost is too high, and the efficient and intelligent requirements of modern ports are difficult to meet are solved. The vehicle no-load distance is reduced and the heavy load rate is improved by using a bipartite graph matching strategy, the prediction scheduling module plans in advance, task overstock and vehicle idleness are reduced, the operation efficiency is effectively improved, the constraint processing module optimizes task allocation according to task and vehicle conditions, and the multi-target optimization module gives consideration to the heavy load rate and order dispatching fairness. The scheduling robot integrates system functions, and can adapt to different working environments and realize intelligent scheduling through data acquisition and continuous optimization of an online learning technology, so that the scheduling accuracy and efficiency are improved, the labor cost is reduced, and the overall competitiveness of a port is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of smart port operations, and in particular to a smart port operation vehicle dispatching system and a dispatching robot. Background Art

[0002] As key hubs for international trade, ports' operational efficiency is crucial to the smooth operation of the logistics chain and cost control. Vehicle scheduling in port operations directly impacts cargo loading and unloading efficiency, vehicle turnover, and overall operating costs. However, traditional manual scheduling methods suffer from significant drawbacks, including slow response times, high error rates, uneven resource allocation, and high labor costs. As modern ports pursue efficient and intelligent operations, traditional scheduling methods are no longer able to meet the demands of modern ports. Summary of the Invention

[0003] The purpose of the present invention is to provide a smart port operation vehicle dispatching system and dispatching robot, which uses a bipartite graph strategy to perform intelligent operation vehicle dispatching, improve port operation efficiency, optimize the vehicle dispatching process, and reduce operating costs, so as to solve the problems raised in the above background technology.

[0004] To achieve the above object, the present invention provides the following technical solutions: A smart port operation vehicle dispatching system, comprising: A task matching module is configured to match the obtained work tasks and vehicle information based on a bipartite graph matching strategy to obtain a task allocation result; a constraint processing module configured to assign priorities to job tasks, adjust corresponding vehicle information weights based on weight factors, and optimize task assignment results based on a bipartite graph matching strategy based on task priorities and vehicle information weights; A multi-objective optimization module is configured to obtain a reload rate and a dispatch fairness evaluation index based on the optimized task allocation result, and adjust weight factors based on the reload rate and the dispatch fairness evaluation index; The predictive scheduling module is configured to obtain historical data on port vehicle scheduling, predict vehicle locations and future task arrivals based on historical data, integrate the prediction results with current task allocation results to generate a scheduling strategy, and monitor and issue early warnings for the scheduling routes of vehicles during port transportation.

[0005] Furthermore, the bipartite graph matching strategy specifically includes: Convert the port vehicle scheduling task into a bipartite graph matching problem and build a bipartite graph framework; Each job task to be assigned is regarded as a vertex set of a bipartite graph framework, and the dispatchable vehicle information is regarded as another vertex set of the bipartite graph framework; Between the vertex set of the task and the vertex set of the vehicle information, edges are constructed based on the potential association between the task and the vehicle information, and the weight of each edge is determined. In this case, no two edges have a common vertex. The weight of each edge is set based on the distance between the vehicle's current location and the starting point of the corresponding task; Based on the weight of each edge, each job task to be assigned is matched with the dispatchable vehicle information, and the status of the corresponding job task and vehicle information is marked based on the matching result.

[0006] Furthermore, before matching the acquired work tasks and vehicle information, the following steps are also included: Read the acquired work tasks and vehicle information, and segment the work tasks and vehicle information into a multi-layer theme tree, where each layer is divided into multiple clusters based on task type and vehicle attributes; Perform clustering on the data information corresponding to each layer, analyze the task characteristics of the task and the attribute information of the vehicle, obtain several cluster sets, and assign each cluster set to the corresponding cluster; Perform word segmentation on the task description sentences and vehicle information description sentences contained in the cluster set in each cluster, and perform cleaning and deduplication processing to obtain a keyword set and perform word vector conversion; According to the word vector representing the core features of the cluster set by the port business standard, the keyword corresponding to the word vector with the smallest distance is selected from the keyword set as the target keyword in the cluster. Keyword tagging is performed on the key information corresponding to the work tasks and vehicle information based on the target keywords to determine the key features of the work tasks and vehicle information.

[0007] Furthermore, the constraint processing module optimizes the task allocation results, specifically: Determine the importance and urgency of the task and the type of cargo involved based on the key characteristics of the task, determine the priority score of the task, and sort the tasks from high to low based on the priority score; Evaluate vehicle performance based on key vehicle information features to determine the vehicle's comprehensive performance coefficient. Also, extract the driver's work hours and experience corresponding to the vehicle information to evaluate the driver's work efficiency coefficient. Comparing the comprehensive performance coefficient of the vehicle with a preset vehicle performance reference value to obtain a vehicle performance ratio, and comparing the driver's work efficiency coefficient with a preset driver efficiency reference value to obtain a corresponding driver efficiency ratio; The vehicle weight is adjusted based on the vehicle performance ratio and the corresponding driver efficiency ratio. Combined with the priority of the work task, priority is given to vehicles with higher vehicle weights and that meet the vehicle type and cargo type required for the task.

[0008] Furthermore, the multi-objective optimization module obtains evaluation indicators for overload rate and dispatch fairness, including: During the task allocation process, the task load of the assigned vehicles is continuously monitored, the ratio of the actual load weight of the vehicle to the maximum load weight of the vehicle is obtained, and the overload rate of each vehicle is calculated; Conduct statistical analysis on the overload rates of all vehicles to obtain overall vehicle overload rate data; The number of tasks received by each vehicle within a certain period of time is counted, and the variance of the number of tasks received by different vehicles is calculated to evaluate the fairness of dispatching. The larger the variance, the greater the difference in the number of tasks between vehicles, and the worse the fairness of dispatching. The smaller the variance, the better the fairness of dispatching.

[0009] Furthermore, the multi-objective optimization module also includes: Based on the results, the historical driving data of the driver corresponding to the vehicle information is extracted, and based on the weight value of the driver's historical driving data in the total historical driving data, the driving experience value of the driver under the priority of the current task is analyzed; Determine the driver's maximum continuous driving time based on historical driving data; Input the maximum speed of the vehicle and all historical speeds in the historical speed list of historical driving data into a preset data axis to obtain the speed difference between the maximum speed and each historical speed; adjusting the maximum driving speed based on the average value of the speed differences to generate an adjusted speed; Generate a recommended driving speed range based on the adjusted speed and driving experience value. At the same time, adjust the maximum continuous driving time based on the driving experience value to generate a recommended driving time. Generate a driving plan for the task based on the recommended speed range and recommended driving duration, and analyze the driver's driving behavior in real time to see if it complies with the driving plan while the driver is performing the task. If it does not meet the requirements, the driver's abnormal items will be extracted and corresponding alarms will be issued.

[0010] Furthermore, the prediction scheduling module also includes: During the task allocation process, if it is predicted that a large number of tasks will be required in the target area and there are insufficient vehicles in the area, vehicles in non-target areas will be directed to the target area to wait. At the same time, the task type and vehicle status of the corresponding task are determined based on the prediction results, and the corresponding vehicle is matched to perform the corresponding task; Obtain feedback data in real time, compare the actual monitoring scheduling situation with the predicted results, and dynamically adjust the predicted results based on the comparison results.

[0011] Furthermore, the predictive scheduling module monitors and issues early warnings on the vehicle's scheduled route during port transportation, specifically including: Determine the initial dispatch path of the vehicle based on the dispatch transportation starting point and transportation focus of the vehicle and the road condition information of the road network system; Obtaining real-time information on traffic flow, weather conditions, accidents, and road maintenance along the initial dispatch path; Determining a congestion value of the initial dispatch path based on the traffic flow, determining a driving difficulty value of the initial dispatch path based on the weather conditions, and determining an emergency probability value of the initial dispatch path based on accident and road maintenance information; Based on the congestion value, the driving difficulty value, and the emergency probability value, a comprehensive evaluation is performed on the initial scheduling path to obtain a path evaluation value, and whether the path evaluation value is greater than a first preset evaluation value is determined; if so, the initial scheduling path is determined to be the optimal scheduling path; otherwise, whether the path evaluation value is greater than a second preset evaluation value is determined; If so, determining the initial scheduling path as an alternative scheduling path; Otherwise, determining that the initial scheduling path is an unqualified scheduling path; When the initial scheduling path is the optimal scheduling path, obtaining road condition characteristics and surrounding environment characteristics of the optimal scheduling path, and formulating abnormal alarm conditions based on the road condition characteristics and surrounding environment characteristics; When the initial scheduling path is an alternative scheduling path, other alternative scheduling paths are obtained based on the comprehensive evaluation value determined by the road network system and the alternative scheduling path, and the alternative scheduling paths and other alternative scheduling paths are integrated to obtain a comprehensive scheduling path; when the initial scheduling path is an unqualified scheduling path, other scheduling paths with a comprehensive evaluation value greater than a second preset evaluation value are determined based on the road network system, and the other scheduling paths are integrated to obtain a comprehensive scheduling path; Based on the road condition characteristics and surrounding environment characteristics of the comprehensive scheduling path, abnormal alarm conditions are formulated.

[0012] Furthermore, based on the road condition characteristics and surrounding environment characteristics of the comprehensive dispatch path, abnormal alarm conditions are formulated, including: Marking important nodes in the comprehensive scheduling path based on the road network system to obtain important road condition nodes and important environmental nodes; Based on the traffic conditions at important nodes, the maximum stay time at the important nodes is calculated according to the following formula; T_l=T_0×(1+δ_0 / δ_2 +1 / n ∑_(i=1)^n▒〖(δ_i-δ_2))〗 Wherein, T_1 represents the maximum stay time at the important road condition node, T_0 represents the preset minimum stay time, δ_2 represents the second preset evaluation value, δ_0 represents the path evaluation value at the important road condition node, n represents the number of other important road condition nodes adjacent to the important road condition node, and δ_i represents the path evaluation value of the i-th other important road condition node; Based on the environment of the important nodes, the maximum stay time at the important nodes is calculated according to the following formula; T_h=T_0*(1+e^(γ_0 / γ_h )) Wherein, T_h represents the maximum stay time at the important node in the environment, e represents a natural constant with a value of 2.72, γ_0 represents the probability of an operational anomaly under a standard environment, and γ_h represents the probability of an operational anomaly under the environment of the important node in the environment; Establish positioning abnormal conditions based on the route of the comprehensive scheduling path, establish residence time abnormal conditions based on the maximum residence time of important road nodes and the maximum residence time of important environmental nodes, and formulate abnormal alarm conditions based on positioning abnormal conditions and residence time abnormal conditions.

[0013] The present invention provides another technical solution, a smart port operation vehicle dispatching robot, comprising: configuring a port operation vehicle dispatching system in the operation vehicle dispatching robot, the operation vehicle dispatching robot operates to obtain overload rate and dispatch fairness evaluation indicators, performs task and vehicle matching, handles complex task constraints, realizes multi-objective optimization, and makes dispatching decisions based on prediction results, and builds a data interaction channel with the vehicle in the port operation scenario, intelligently dispatches the vehicle, and collects data in the dispatching process in real time through the data interaction channel.

[0014] Compared with the prior art, the present invention has the following beneficial effects: By utilizing the bipartite graph matching strategy to reduce the empty distance of vehicles and increase the overload rate, the predictive scheduling module plans in advance to reduce task backlogs and vehicle idleness, effectively improving operational efficiency. The constraint processing module optimizes task allocation based on task and vehicle conditions. The multi-objective optimization module takes into account both overload rate and dispatch fairness, making resource allocation more reasonable. The scheduling robot integrates system functions and continuously optimizes through data collection and online learning technology. It can adapt to different operating environments and realize intelligent scheduling, which not only improves scheduling accuracy and efficiency, but also reduces labor costs, enhances the overall competitiveness of the port, promotes the intelligent development of the port, and brings efficient and intelligent solutions to port operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a module diagram of the smart port operation vehicle scheduling system of the present invention. DETAILED DESCRIPTION

[0016] 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.

[0017] See also Figure 1 , this embodiment provides the following technical solutions: A smart port operation vehicle dispatching system, comprising: The task matching module is configured to match the obtained work tasks and vehicle information based on a bipartite graph matching strategy, with the primary goal of improving the reload rate to obtain the task allocation result; a constraint processing module configured to assign priorities to job tasks, adjust corresponding vehicle information weights based on weight factors, and optimize task assignment results based on a bipartite graph matching strategy based on task priorities and vehicle information weights; The multi-objective optimization module is configured to obtain the overload rate and dispatch fairness evaluation indicators based on the optimized task allocation results, and further dynamically optimize the task allocation results based on the adjusted weight factors of the overload rate and dispatch fairness evaluation indicators to achieve the optimization of the overall scheduling effect; The predictive scheduling module is configured to obtain historical data on port vehicle scheduling, including vehicle driving trajectories, task completion times, and changes in task volume over different time periods. Based on this historical data, it predicts vehicle locations and future task arrivals. For example, by analyzing past data, it learns vehicle driving patterns and the time and location distribution patterns of task occurrences. It predicts the likely locations of vehicles within a specific time period and area, as well as the probability and approximate time of occurrence of different types of tasks. It then integrates the predicted results with the current task allocation results to generate a scheduling strategy, assisting in developing a more scientific and reasonable scheduling plan. The module also includes: During the task allocation process, if it is predicted that a large number of tasks will be required in the target area and there are insufficient vehicles in that area, vehicles in non-target areas will be directed to the target area to wait for orders, thus avoiding task backlogs and idle vehicles. At the same time, the task type and vehicle status of the corresponding task are determined based on the prediction results, and the corresponding vehicle is matched to perform the corresponding task, thereby improving task execution efficiency and vehicle utilization; Acquire feedback data in real time, compare the actual dispatching situation monitored with the forecast results, and dynamically adjust the forecast results based on the comparison results to continuously improve the accuracy of the forecast and the scientific nature of the dispatching decisions, ensuring that the port vehicle dispatching system can adapt to the ever-changing operating environment and achieve efficient and intelligent dispatching.

[0018] In this embodiment, vehicle resources, including vehicle type, capacity, and operating capacity, are initialized through real-time information such as the location, status, and task requirements of port operation vehicles. Task requests from the port management system are received, including information such as cargo type, weight, and destination. Tasks are classified and prioritized, and VIP tasks and ordinary tasks are distinguished. Through clear classification and prioritization of vehicle resources and tasks, a basis is provided for the reasonable arrangement of vehicle execution tasks, ensuring that important and urgent tasks are handled first, thereby improving the overall operational efficiency of the port.

[0019] In this embodiment, the bipartite graph matching strategy specifically includes: Convert the port vehicle scheduling task into a bipartite graph matching problem and build a bipartite graph framework; Each job task to be assigned is regarded as a vertex set of a bipartite graph framework, and the dispatchable vehicle information is regarded as another vertex set of the bipartite graph framework; Between the vertex set of the task and the vertex set of the vehicle information, edges are constructed based on the potential association between the task and the vehicle information, and the weight of each edge is determined. In this case, no two edges have a common vertex. The weight of each edge is set based on the distance between the vehicle's current location and the starting point of the corresponding task; Based on the weight of each edge, each task to be assigned is matched with the dispatchable vehicle information, and based on the matching result, the corresponding task and vehicle information are marked as "assigned"; In this embodiment, if a vehicle has the ability to perform a certain task, an edge is connected between the vertex representing the task and the vehicle, and a corresponding weight is assigned to each edge. Through this setting, the goal of reducing the empty distance in port vehicle scheduling is converted into a minimum weight maximum matching problem in a bipartite graph. The complex port vehicle scheduling problem is converted into a solvable mathematical model through the bipartite graph matching strategy. Through the setting of edge weights and the matching algorithm, the optimal or better task allocation plan can be quickly found, which can effectively reduce the empty distance of vehicles and increase the overload rate, thereby improving the transportation efficiency of port vehicles and reducing resource waste.

[0020] In this embodiment, before matching the acquired work tasks and vehicle information, the following steps are also included: The acquired task and vehicle information is read and segmented into a multi-layer theme tree. Each layer is divided into multiple clusters based on task type and vehicle attributes. For example, based on cargo type, task information is divided into clusters such as general cargo and dangerous cargo; based on vehicle usage, vehicle information is divided into clusters such as container transport vehicles and bulk cargo transport vehicles. Clustering is performed on the data information corresponding to each layer. Task characteristics such as weight and destination of the task as well as attribute information such as vehicle cargo capacity and driving area restrictions are analyzed to obtain several cluster sets, and each cluster set is assigned to the corresponding cluster. The task description sentences and vehicle information description sentences contained in each cluster set are segmented, cleaned, and deduplicated to remove some meaningless words or words that do not fit the port business scenario. This results in a keyword set and word vector conversion. According to the word vector representing the core features of the cluster set by the port business standard, the keyword corresponding to the word vector with the smallest distance is selected from the keyword set as the target keyword in the cluster. Keyword tagging of key information corresponding to the work tasks and vehicle information based on target keywords to determine the key features of the work tasks and vehicle information; In this embodiment, key features include the type of cargo for the mission (whether it is high-value cargo, dangerous goods, etc.), the urgency of the mission (delivery time requirements), special operational requirements corresponding to the type of vehicle required for the mission (container truck, flatbed truck, etc.), as well as vehicle type (cargo capacity, volume), vehicle speed, vehicle maintenance status (whether it has been maintained recently, frequency of failures), driver's working hours and work experience (type of cargo they are good at transporting, ability to cope with complex road conditions), etc.

[0021] In this embodiment, the constraint processing module optimizes the task allocation result, specifically: Based on the key characteristics of the task, the importance and urgency of the task, as well as the type of cargo involved, are determined, and a priority score is assigned to the task. Tasks are then ranked from high to low based on the priority score. For example, VIP tasks involving important customers, urgent tasks with strict delivery deadlines, and tasks transporting dangerous goods are given higher priority; while ordinary cargo transport tasks with ample delivery time are given a relatively lower priority. Evaluate vehicle performance based on key vehicle information features to determine the vehicle's comprehensive performance coefficient. Also, extract the driver's work hours and experience corresponding to the vehicle information to evaluate the driver's work efficiency coefficient. Comparing the comprehensive performance coefficient of the vehicle with a preset vehicle performance reference value to obtain a vehicle performance ratio, and comparing the driver's work efficiency coefficient with a preset driver efficiency reference value to obtain a corresponding driver efficiency ratio; The vehicle weight is adjusted based on the vehicle performance ratio and the corresponding driver efficiency ratio. If both the vehicle performance ratio and the driver efficiency ratio are high, the vehicle is given a higher overall adaptation weight; if one of the ratios is low and the other is high, the overall adaptation weight is determined by weighted summation based on the actual operating needs and focus of the port. Combined with the priority of the operation task, priority is given to vehicles with higher vehicle weights and that meet the vehicle type and cargo type required for the task. For example, high-priority dangerous goods transportation tasks are given priority to vehicles with dangerous goods transportation qualifications, good comprehensive performance and experienced drivers; for ordinary priority tasks, vehicles are allocated in sequence according to the overall adaptation weight and task requirements, while ensuring that the high-priority tasks are allocated.

[0022] In this embodiment, by analyzing the key features of the operation tasks, the importance, urgency and cargo type of the tasks are determined, and the operation tasks are assigned priority scores. They are then sorted according to the scores. At the same time, the comprehensive performance coefficient of the vehicle and the work efficiency coefficient of the driver are evaluated, and the vehicle performance ratio and the driver efficiency ratio are compared to adjust the vehicle weights. Vehicles with high weights that meet the task requirements are allocated first, ensuring priority processing of important and urgent tasks, optimizing the allocation of vehicle resources, improving the execution efficiency and accuracy of operation tasks, reducing operating costs, and improving the overall efficiency and safety of port operations.

[0023] In this embodiment, the multi-objective optimization module obtains the overload rate and dispatch fairness evaluation indicators, specifically including: During the task allocation process, the task load of the assigned vehicles is continuously monitored, the ratio of the actual load weight of the vehicle to the maximum load weight of the vehicle is obtained, and the overload rate of each vehicle is calculated; Statistically analyze the overload rates of all vehicles to obtain overall vehicle overload rate data. For example, calculate the average, minimum, and maximum overload rates of all vehicles operating at the port within a certain period of time to comprehensively assess the overload situation under the current task allocation. The number of tasks received by each vehicle within a certain period of time is counted, and the variance of the number of tasks received by different vehicles is calculated to evaluate the fairness of dispatching. The larger the variance, the greater the difference in the number of tasks between vehicles, and the worse the fairness of dispatching. The smaller the variance, the better the fairness of dispatching. For example, the variance of the number of tasks received by each vehicle in the past hour is calculated as an evaluation indicator of the current fairness of dispatching.

[0024] In this embodiment, the multi-objective optimization module obtains data during the task execution process in real time, updates the overload rate and dispatch fairness evaluation indicators, and at the same time adjusts the weight factor according to the evaluation indicators to provide a more accurate basis for the next task allocation. As the task continues to proceed and the data continues to accumulate, the multi-objective optimization module continuously iterates and optimizes the task allocation plan, and further adjusts the weight factor and task allocation strategy.

[0025] In this embodiment, the obtained work tasks and vehicle information are constructed using a linear programming method, and decision variables and constraints are set to obtain the optimal task and vehicle matching solution; The decision variables are x_ij, which is set for each edge (i, j) between the task and vehicle information vertices (where i represents the task vertex and j represents the vehicle information vertex). When task i is assigned to vehicle j, x_ij = 1 (i.e., set to "assigned"); otherwise, x_ij = 0 (i.e., set to "unassigned"). Based on this, an objective function is constructed. Based on this objective function, the matching solution with the minimum total unloaded vehicle distance is extracted from all task assignment results. The constraints include: for any task i in the vertex set of job tasks, ∑_(j∈B)▒〖x_ij=1〗 must be satisfied, ensuring that each task must and can only be assigned to one vehicle; for any vehicle j in the vertex set of vehicle information, ∑_(i∈A)▒〖x_ij=1〗 must be satisfied, ensuring that each vehicle can only perform at most one task; when x_ij≥0, and when there is a connection between task i and vehicle j, the corresponding variable x_ij is input into the task assignment calculation, as shown below: Minimize ∑_(i∈A,j∈B)▒〖c_ij x_ij 〗 Subject to ∑_(j∈B)▒〖x_ij=1,∀i∈A〗 ∑_(i∈A)▒〖x_ij=1,∀j∈B〗 x_ij≥0,∀(i,j)∈E Where x_ij represents the decision variable, i represents the vertex of the task, j represents the vertex of the vehicle information, c_ij represents the distance from vehicle j to the starting point of task i, A represents the vertex set of the task, B represents the vertex set of the vehicle information, and E represents the edge set; In this embodiment, a linear programming method is used to construct a task and vehicle matching plan. By accurately setting the decision variables, objective functions and constraints, the optimal task allocation plan is solved, which effectively reduces the total distance traveled by vehicles with no load and increases the vehicle overload rate. This provides a scientific and accurate method for port vehicle scheduling, further improving port operating efficiency and resource utilization.

[0026] Furthermore, the predictive scheduling module also includes monitoring and early warning of the vehicle's scheduling route during port transportation, including: Determine the initial dispatch path of the vehicle based on the dispatch transportation starting point and transportation focus of the vehicle and the road condition information of the road network system; Obtaining real-time information on traffic flow, weather conditions, accidents, and road maintenance along the initial dispatch path; Determining a congestion value of the initial dispatch path based on the traffic flow, determining a driving difficulty value of the initial dispatch path based on the weather conditions, and determining an emergency probability value of the initial dispatch path based on accident and road maintenance information; Based on the congestion value, the driving difficulty value, and the emergency probability value, a comprehensive evaluation is performed on the initial scheduling path to obtain a path evaluation value, and whether the path evaluation value is greater than a first preset evaluation value is determined; if so, the initial scheduling path is determined to be the optimal scheduling path; otherwise, whether the path evaluation value is greater than a second preset evaluation value is determined; If so, determining the initial scheduling path as an alternative scheduling path; Otherwise, determining that the initial scheduling path is an unqualified scheduling path; When the initial scheduling path is the optimal scheduling path, obtaining road condition characteristics and surrounding environment characteristics of the optimal scheduling path, and formulating abnormal alarm conditions based on the road condition characteristics and surrounding environment characteristics; When the initial scheduling path is an alternative scheduling path, other alternative scheduling paths are obtained based on the comprehensive evaluation value determined by the road network system and the alternative scheduling path, and the alternative scheduling paths and other alternative scheduling paths are integrated to obtain a comprehensive scheduling path; when the initial scheduling path is an unqualified scheduling path, other scheduling paths with a comprehensive evaluation value greater than a second preset evaluation value are determined based on the road network system, and the other scheduling paths are integrated to obtain a comprehensive scheduling path; Based on the road condition characteristics and surrounding environment characteristics of the comprehensive scheduling path, abnormal alarm conditions are formulated.

[0027] In this embodiment, the initial scheduling path of the vehicle during port operations only considers the optimal path determined based on basic information such as path information such as distance and road width.

[0028] In this embodiment, the greater the congestion value, the greater the driving difficulty value, the greater the probability value of an emergency, and the smaller the corresponding path evaluation value.

[0029] In this embodiment, the first preset evaluation value is greater than the second preset evaluation value. The path greater than the first preset evaluation value can be regarded as an excellent path, and the path greater than the second preset evaluation value and less than the first preset evaluation value can be regarded as a qualified path.

[0030] In this embodiment, the comprehensive scheduling path includes the route information of all scheduling paths.

[0031] In this embodiment, the abnormal alarm conditions include that the position of the vehicle cannot deviate from the set path, and that the vehicle's stay time cannot exceed the set time.

[0032] The beneficial effects of the above design scheme are: determining the final executable scheduling path through path evaluation based on traffic flow, weather conditions, accidents and road maintenance information of the port path, and formulating abnormal alarm conditions based on two indicators: vehicle location and vehicle residence time, ensuring the accuracy of the formulated abnormal alarm conditions, and providing an accurate pre-judgment mechanism for the reliability of vehicle operations in the port.

[0033] Furthermore, based on the road condition characteristics and surrounding environment characteristics of the comprehensive dispatch path, abnormal alarm conditions are formulated, including: Marking important nodes in the comprehensive scheduling path based on the road network system to obtain important road condition nodes and important environmental nodes; Based on the traffic conditions at important nodes, the maximum stay time at the important nodes is calculated according to the following formula; T_l=T_0×(1+δ_0 / δ_2 +1 / n ∑_(i=1)^n▒〖(δ_i-δ_2))〗 Wherein, T_1 represents the maximum stay time at the important road condition node, T_0 represents the preset minimum stay time, δ_2 represents the second preset evaluation value, δ_0 represents the path evaluation value at the important road condition node, n represents the number of other important road condition nodes adjacent to the important road condition node, and δ_i represents the path evaluation value of the i-th other important road condition node; Based on the environment of the important nodes, the maximum stay time at the important nodes is calculated according to the following formula; T_h=T_0*(1+e^(γ_0 / γ_h )) Wherein, T_h represents the maximum stay time at the important node in the environment, e represents a natural constant with a value of 2.72, γ_0 represents the probability of an operational anomaly under a standard environment, and γ_h represents the probability of an operational anomaly under the environment of the important node in the environment; Establish positioning abnormal conditions based on the route of the comprehensive scheduling path, establish residence time abnormal conditions based on the maximum residence time of important road nodes and the maximum residence time of important environmental nodes, and formulate abnormal alarm conditions based on positioning abnormal conditions and residence time abnormal conditions.

[0034] In this embodiment, the evaluation values ​​are in the range of (0, 1).

[0035] In this embodiment, the path evaluation value of the important traffic node of the port is the evaluation value of the preset length path passing through the important traffic node. The evaluation method is the same as the evaluation method of the overall scheduling path, and the path evaluation value of the important traffic node is greater than the second preset evaluation value.

[0036] In this embodiment, the probability of an operational anomaly occurring in an environment of an environmentally important node is related to the environmental conditions. For example, the probability of an operational anomaly occurring increases when there are many people nearby. The operational anomaly includes traffic jams, collisions, or accidents.

[0037] The beneficial effects of the above design scheme are: by marking important nodes in the comprehensive scheduling path based on the road network system, important road condition nodes and important environmental nodes are obtained, the maximum stay time at the important road condition nodes and the maximum stay time at the important environmental nodes are determined, positioning abnormal conditions are established based on the route of the comprehensive scheduling path, and based on the maximum stay time of important road condition nodes and the maximum stay time of important environmental nodes, stay time abnormal conditions are established. Abnormal alarm conditions are formulated based on the positioning abnormal conditions and the stay time abnormal conditions, ensuring the accuracy and comprehensiveness of the formulated abnormal alarm conditions and providing an accurate judgment mechanism for identifying vehicle operation abnormalities.

[0038] In this embodiment, the multi-objective optimization module further includes: Based on the results, the driver's historical driving data corresponding to the vehicle information is extracted. The weight of the driver's historical driving data in the total historical driving data is determined based on factors such as the driver's duration of participation in port operations and the number of tasks completed. The driver's driving experience value is analyzed based on the priority of the current operation task. If the driver is experienced in transporting heavy loads, his driving experience value for heavy load tasks is higher. Determine the driver's maximum continuous driving time based on historical driving data; Input the vehicle's maximum speed (which can be obtained from vehicle information) and all historical speeds in the historical speed list of historical driving data into the preset data axis to obtain the speed difference between the maximum speed and each historical speed; The maximum driving speed is adjusted based on the average of the speed differences to generate an adjusted speed. For example, if the historical driving speed is generally low, it means that the driver is used to driving conservatively, and the maximum driving speed can be appropriately reduced to obtain the adjusted speed. The recommended driving speed range is generated based on the adjusted speed and driving experience. Experienced drivers can appropriately relax the speed range; otherwise, the range can be narrowed. At the same time, the maximum continuous driving time is adjusted based on driving experience to generate a recommended driving time. Experienced drivers can appropriately extend the continuous driving time, but they still need to comply with safety regulations. Generate a driving plan for the task based on the recommended speed range and recommended driving duration, and analyze the driver's driving behavior in real time to see if it complies with the driving plan while the driver is performing the task. If it does not meet the requirements, the driver's abnormal items, such as speeding, excessive driving time, etc., are extracted and corresponding alarms are issued. For example, for speeding behavior, a speed alarm is issued; for excessive driving time, a fatigue driving alarm is issued to ensure the safety of port operation vehicles.

[0039] In this embodiment, by comprehensively considering factors such as driving experience and historical driving data to generate a reasonable driving plan and monitoring driving behavior in real time, it not only helps to improve vehicle driving safety and reduce accident risks, but also can reasonably arrange tasks according to the actual situation of the driver, improve the driver's work efficiency and comfort, further improve the function of the port vehicle dispatching system, and ensure the safety and stability of port operations.

[0040] The present invention provides another technical solution, a smart port operation vehicle dispatching robot, comprising: configuring a port operation vehicle dispatching system in the operation vehicle dispatching robot, the operation vehicle dispatching robot operates to obtain overload rate and dispatch fairness evaluation indicators, performs task and vehicle matching, handles complex task constraints, realizes multi-objective optimization, and makes dispatching decisions based on prediction results, and builds a data interaction channel with the vehicle in the port operation scenario, intelligently dispatches the vehicle, and collects data in the dispatching process in real time through the data interaction channel, and uses online learning technology to continuously optimize its own model to improve dispatching performance and adapt to different port operation conditions.

[0041] In this embodiment, the smart port operation vehicle dispatching robot integrates the core functions of the dispatching system, collects data in real time through the data interaction channel with the vehicle, and continuously optimizes its own model in combination with online learning technology, so that the robot can continuously adapt to changes in the port operation environment and realize intelligent and efficient dispatching. It not only improves the accuracy and efficiency of dispatching, but also reduces labor costs, promotes the development of port operations towards intelligence and automation, and enhances the overall competitiveness of the port.

[0042] The above description is only a preferred specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with the technical field, within the technical scope disclosed by the present invention, who makes equivalent replacements or changes based on the technical solution and inventive concept of the present invention, should be covered by the scope of protection of the present invention.

Claims

1. A smart port operation vehicle dispatching system, characterized in that: include: A task matching module is configured to match the obtained work tasks and vehicle information based on a bipartite graph matching strategy to obtain a task allocation result; a constraint processing module configured to assign priorities to job tasks, adjust corresponding vehicle information weights based on weight factors, and optimize task assignment results based on a bipartite graph matching strategy based on task priorities and vehicle information weights; A multi-objective optimization module is configured to obtain a reload rate and a dispatch fairness evaluation index based on the optimized task allocation result, and adjust weight factors based on the reload rate and the dispatch fairness evaluation index; The predictive scheduling module is configured to obtain historical data on port vehicle scheduling, predict vehicle locations and future task arrivals based on historical data, integrate the prediction results with current task allocation results to generate a scheduling strategy, and monitor and issue early warnings for the scheduling routes of vehicles during port transportation.

2. The intelligent port operation vehicle dispatching system according to claim 1, characterized in that: The bipartite graph matching strategy specifically includes: Convert the port vehicle scheduling task into a bipartite graph matching problem and build a bipartite graph framework; Each job task to be assigned is regarded as a vertex set of a bipartite graph framework, and the dispatchable vehicle information is regarded as another vertex set of the bipartite graph framework; Between the vertex set of the task and the vertex set of the vehicle information, edges are constructed based on the potential association between the task and the vehicle information, and the weight of each edge is determined. In this case, no two edges have a common vertex. The weight of each edge is set based on the distance between the vehicle's current location and the starting point of the corresponding task; Based on the weight of each edge, each job task to be assigned is matched with the dispatchable vehicle information, and the status of the corresponding job task and vehicle information is marked based on the matching result.

3. The intelligent port operation vehicle dispatching system according to claim 2, characterized in that: Before matching the acquired work tasks and vehicle information, the following steps are also required: Read the acquired work tasks and vehicle information, and segment the work tasks and vehicle information into a multi-layer theme tree, where each layer is divided into multiple clusters based on task type and vehicle attributes; Perform clustering on the data information corresponding to each layer, analyze the task characteristics of the task and the attribute information of the vehicle, obtain several cluster sets, and assign each cluster set to the corresponding cluster; Perform word segmentation on the task description sentences and vehicle information description sentences contained in the cluster set in each cluster, and perform cleaning and deduplication processing to obtain a keyword set and perform word vector conversion; According to the word vector representing the core features of the cluster set by the port business standard, the keyword corresponding to the word vector with the smallest distance is selected from the keyword set as the target keyword in the cluster. Keyword tagging is performed on the key information corresponding to the work tasks and vehicle information based on the target keywords to determine the key features of the work tasks and vehicle information.

4. The intelligent port operation vehicle dispatching system according to claim 3, characterized in that: The constraint processing module optimizes the task allocation results, specifically: Determine the importance and urgency of the task and the type of cargo involved based on the key characteristics of the task, determine the priority score of the task, and sort the tasks from high to low based on the priority score; Evaluate vehicle performance based on key vehicle information features to determine the vehicle's comprehensive performance coefficient. Also, extract the driver's work hours and experience corresponding to the vehicle information to evaluate the driver's work efficiency coefficient. Comparing the comprehensive performance coefficient of the vehicle with a preset vehicle performance reference value to obtain a vehicle performance ratio, and comparing the driver's work efficiency coefficient with a preset driver efficiency reference value to obtain a corresponding driver efficiency ratio; The vehicle weight is adjusted based on the vehicle performance ratio and the corresponding driver efficiency ratio. Combined with the priority of the work task, priority is given to vehicles with higher vehicle weights and that meet the vehicle type and cargo type required for the task.

5. The intelligent port operation vehicle dispatching system according to claim 4, characterized in that: The multi-objective optimization module obtains evaluation indicators for overload rate and dispatch fairness, including: During the task allocation process, the task load of the assigned vehicles is continuously monitored, the ratio of the actual load weight of the vehicle to the maximum load weight of the vehicle is obtained, and the overload rate of each vehicle is calculated; Conduct statistical analysis on the overload rates of all vehicles to obtain overall vehicle overload rate data; The number of tasks received by each vehicle within a certain period of time is counted, and the variance of the number of tasks received by different vehicles is calculated to evaluate the fairness of dispatching. The larger the variance, the greater the difference in the number of tasks between vehicles, and the worse the fairness of dispatching. The smaller the variance, the better the fairness of dispatching.

6. The intelligent port operation vehicle dispatching system according to claim 5, characterized in that: The multi-objective optimization module also includes: Based on the results, the historical driving data of the driver corresponding to the vehicle information is extracted, and based on the weight value of the driver's historical driving data in the total historical driving data, the driving experience value of the driver under the priority of the current task is analyzed; Determine the driver's maximum continuous driving time based on historical driving data; Input the maximum speed of the vehicle and all historical speeds in the historical speed list of historical driving data into a preset data axis to obtain the speed difference between the maximum speed and each historical speed; adjusting the maximum driving speed based on the average value of the speed differences to generate an adjusted speed; Generate a recommended driving speed range based on the adjusted speed and driving experience value. At the same time, adjust the maximum continuous driving time based on the driving experience value to generate a recommended driving time. Generate a driving plan for the task based on the recommended speed range and recommended driving duration, and analyze the driver's driving behavior in real time to see if it complies with the driving plan while the driver is performing the task. If it does not meet the requirements, the driver's abnormal items will be extracted and corresponding alarms will be issued.

7. The intelligent port operation vehicle dispatching system according to claim 6, characterized in that: The prediction scheduling module also includes: During the task allocation process, if it is predicted that a large number of tasks will be required in the target area and there are insufficient vehicles in the area, vehicles in non-target areas will be directed to the target area to wait. At the same time, the task type and vehicle status of the corresponding task are determined based on the prediction results, and the corresponding vehicle is matched to perform the corresponding task; Obtain feedback data in real time, compare the actual monitoring scheduling situation with the predicted results, and dynamically adjust the predicted results based on the comparison results.

8. The intelligent port operation vehicle dispatching system according to claim 1, characterized in that: The predictive scheduling module monitors and issues early warnings on the vehicle's scheduled routes during port transportation, specifically including: Determine the initial dispatch path of the vehicle based on the dispatch transportation starting point and transportation focus of the vehicle and the road condition information of the road network system; Obtaining real-time information on traffic flow, weather conditions, accidents, and road maintenance along the initial dispatch path; Determining a congestion value of the initial dispatch path based on the traffic flow, determining a driving difficulty value of the initial dispatch path based on the weather conditions, and determining an emergency probability value of the initial dispatch path based on accident and road maintenance information; Based on the congestion value, the driving difficulty value, and the emergency probability value, a comprehensive evaluation is performed on the initial scheduling path to obtain a path evaluation value, and whether the path evaluation value is greater than a first preset evaluation value is determined; if so, the initial scheduling path is determined to be the optimal scheduling path; otherwise, whether the path evaluation value is greater than a second preset evaluation value is determined; If so, determining the initial scheduling path as an alternative scheduling path; Otherwise, determining that the initial scheduling path is an unqualified scheduling path; When the initial scheduling path is the optimal scheduling path, obtaining road condition characteristics and surrounding environment characteristics of the optimal scheduling path, and formulating abnormal alarm conditions based on the road condition characteristics and surrounding environment characteristics; When the initial scheduling path is an alternative scheduling path, other alternative scheduling paths are obtained based on the comprehensive evaluation value determined by the road network system and the alternative scheduling path, and the alternative scheduling paths and other alternative scheduling paths are integrated to obtain a comprehensive scheduling path; when the initial scheduling path is an unqualified scheduling path, other scheduling paths with a comprehensive evaluation value greater than a second preset evaluation value are determined based on the road network system, and the other scheduling paths are integrated to obtain a comprehensive scheduling path; Based on the road condition characteristics and surrounding environment characteristics of the comprehensive scheduling path, abnormal alarm conditions are formulated.

9. The intelligent port operation vehicle dispatching system according to claim 8, characterized in that: Based on the road condition characteristics and surrounding environment characteristics of the comprehensive dispatch path, abnormal alarm conditions are formulated, including: Marking important nodes in the comprehensive scheduling path based on the road network system to obtain important road condition nodes and important environmental nodes; Based on the traffic conditions at the important nodes, the maximum stay time at the important nodes is calculated; Based on the environment of the important environmental nodes, the maximum stay time at the important environmental nodes is calculated; Establish positioning abnormal conditions based on the route of the comprehensive scheduling path, establish residence time abnormal conditions based on the maximum residence time of important road nodes and the maximum residence time of important environmental nodes, and formulate abnormal alarm conditions based on positioning abnormal conditions and residence time abnormal conditions.

10. A smart port operation vehicle dispatching robot, using the smart port operation vehicle dispatching system according to claim 1, characterized in that: include: A port operation vehicle dispatching system is configured in the operation vehicle dispatching robot. The operation vehicle dispatching robot operates to obtain overload rate and dispatch fairness evaluation indicators, performs task and vehicle matching, handles complex task constraints, realizes multi-objective optimization, and makes dispatching decisions based on prediction results. In addition, a data interaction channel is established with the vehicle in the port operation scenario to intelligently dispatch the vehicle, and data in the dispatching process is collected in real time through the data interaction channel.

Images