Logistics transportation scheduling method, system and device and storage medium

Abstract

In order to solve the problems that in the logistics scheduling process, the state of a schedulable driver is not fully considered, and the rationality of a logistics transportation scheduling scheme is insufficient, the embodiment of the specification provides a logistics transportation scheduling method, system and device and a storage medium, the method is executed by a processor, and the method comprises the steps of obtaining resources to be scheduled from an Internet of Things unit, and sending the resources to be scheduled to the Internet of Things unit; the Internet of Things unit is configured in at least one terminal, and the to-be-scheduled resources comprise candidate drivers and candidate vehicles; determining the remaining driving time of the candidate driver according to the environment information and the driving information of the candidate driver; determining a candidate scheduling scheme of the candidate vehicle according to the remaining driving time and the vehicle information and load characteristics of the candidate vehicle, the scheduling scheme at least comprising the target driver; and determining a logistics transportation scheduling scheme according to the candidate scheduling scheme. Through the method, the driving safety of logistics transportation can be guaranteed, and the efficiency and rationality of logistics transportation scheduling are improved.

Description

Technical Field

[0001] The present invention relates to the field of vehicle dispatching, and in particular to a logistics transportation dispatching method, system, device and storage medium. Background Art

[0002] In recent years, the logistics industry has been developing rapidly and has gradually become a basic industry for economic development. The problem of logistics vehicle scheduling has gradually become a hot topic of research. Excellent vehicle scheduling can reduce distribution costs and maximize profits while meeting customer requirements. However, current research on logistics vehicle scheduling mainly focuses on vehicle attributes, such as vehicle performance and load capacity, while ignoring human factors. This leads to different execution effects of different personnel under the same vehicle and distribution task.

[0003] In response to the above problems, CN108122045B proposes a logistics vehicle scheduling device and a logistics vehicle scheduling method, which determines similar tasks similar to the target task based on the scheduling data of multiple historical tasks recorded in advance, and schedules logistics vehicles for the target task by combining the scheduling data of similar tasks and multiple performance indicators of the corresponding combination of logistics vehicles and drivers. However, it does not consider information such as the status of the dispatchable drivers, which reduces the rationality of the logistics transportation scheduling plan.

[0004] Therefore, it is hoped to provide a logistics transportation scheduling method, system, device and storage medium to better schedule the combination of logistics vehicles and drivers and improve the rationality of logistics transportation scheduling. Summary of the invention

[0005] One of the embodiments of this specification provides a logistics transportation scheduling method. The method includes: obtaining resources to be scheduled from an Internet of Things unit, the Internet of Things unit is configured in at least one terminal, and the resources to be scheduled include candidate drivers and candidate vehicles; determining the remaining driving time of the candidate driver according to environmental information and the driving information of the candidate driver; determining a candidate scheduling plan for the candidate vehicle according to the remaining driving time, as well as the vehicle information and load characteristics of the candidate vehicle, the scheduling plan at least includes a target driver; and determining a logistics transportation scheduling plan according to the candidate scheduling plan.

[0006] One of the embodiments of the present specification provides a logistics transportation scheduling system, the system includes an acquisition module, a first determination module and a second determination module; the acquisition module is used to acquire resources to be scheduled from an Internet of Things unit, the Internet of Things unit is configured in at least one terminal, and the resources to be scheduled include candidate drivers and candidate vehicles; the first determination module is used to determine the remaining driving time of the candidate driver based on environmental information and the driving information of the candidate driver; the second determination module is used to: determine a candidate scheduling plan for the candidate vehicle based on the remaining driving time, as well as the vehicle information and load characteristics of the candidate vehicle, the scheduling plan at least including a target driver; and determine a logistics transportation scheduling plan based on the candidate scheduling plan.

[0007] One of the embodiments of the present specification provides a logistics transportation scheduling device, including a processor, wherein the processor is used to execute a logistics transportation scheduling method.

[0008] One of the embodiments of the present specification provides a computer-readable medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes a logistics transportation scheduling method. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 is an exemplary module diagram of a logistics transportation scheduling system according to some embodiments of this specification;

[0010] Figure 2 is an exemplary flow chart of a logistics transportation scheduling method according to some embodiments of this specification;

[0011] Figure 3 is a schematic diagram of determining the remaining driving time according to some embodiments of this specification;

[0012] Figure 4 It is a schematic diagram of determining a scheduling scheme according to some embodiments of this specification. DETAILED DESCRIPTION

[0013] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0014] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0015] As shown in this specification and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprise" and "include" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0016] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0017] In order to solve the problem that human factors are not considered in logistics transportation scheduling, the prior art CN108122045B proposes a logistics vehicle scheduling device and a logistics vehicle scheduling method. However, the prior art does not consider the impact of information such as the fatigue level of the dispatchable driver and the driver's proficiency in the transportation route on logistics transportation scheduling, thereby affecting the rationality of logistics transportation scheduling.

[0018] In view of this, some embodiments of the present specification determine the logistics transportation scheduling plan based on the driving information and vehicle information of the dispatchable drivers and the load characteristics during logistics transportation scheduling, thereby improving the rationality of the logistics transportation plan.

[0019] Figure 1 is an exemplary module diagram of a logistics transportation scheduling system according to some embodiments of this specification. Figure 1 As shown, the logistics transportation scheduling system 100 may include an acquisition module 110 , a first determination module 120 and a second determination module 130 .

[0020] The acquisition module 110 may be configured to acquire resources to be scheduled from the IoT unit.

[0021] The first determination module 120 may be configured to determine the remaining driving time of the candidate driver based on the environmental information and the driving information of the candidate driver.

[0022] In some embodiments, the first determination module 120 may determine the candidate driver's fatigue level based on environmental information and driving information; and determine the remaining driving time based on the fatigue level and driving information.

[0023] The second determination module 130 can be used to determine candidate scheduling plans for candidate vehicles based on the remaining driving time, vehicle information and load characteristics of the candidate vehicles; and determine a logistics transportation scheduling plan based on the candidate scheduling plans.

[0024] In some embodiments, the second determination module 130 may be used to determine the driving difficulty of the candidate vehicle based on the vehicle information and the load characteristics; and determine the candidate scheduling scheme based on the driving difficulty and the remaining driving time.

[0025] In some embodiments, the driving difficulty of a vehicle may include the driving difficulty of the vehicle and the driving difficulty of a route. The driving difficulty of the vehicle is related to the state, type and other information of the vehicle. For example, a special vehicle is more difficult to drive than an ordinary truck. The driving difficulty of a route is related to the complexity of the route to be driven. For example, a route with more traffic volume is more difficult to drive than a route with less traffic volume.

[0026] In some embodiments, the second determination module 130 can also be used to generate at least one reference driving route and its corresponding reference departure time based on road information, the departure position, destination position and latest arrival time of the candidate vehicles; and determine the departure time and candidate driving routes based on at least one reference driving route, reference departure time, remaining driving time, and driving difficulty.

[0027] For more information about the functions implemented by the above modules, please refer to this manual. Figure 2-Figure 4 and related instructions.

[0028] Figure 2 is an exemplary flow chart of a logistics transportation scheduling method according to some embodiments of this specification. In some embodiments, process 200 may be executed by a processor. Figure 2 As shown, process 200 includes the following steps:

[0029] Step 210: Obtain resources to be scheduled from the IoT unit.

[0030] The IoT unit refers to an intelligent unit used to obtain resources to be scheduled.

[0031] In some embodiments, the IoT unit may include at least one sub-IoT unit, and the at least one sub-IoT unit is deployed in at least one vehicle terminal and / or at least one driver's user terminal.

[0032] The IoT unit deployed at the vehicle terminal can be connected to the vehicle central control system for communication to obtain vehicle-related information, such as vehicle location information, vehicle scheduling, etc. The IoT unit deployed at the vehicle terminal can include hardware IoT devices and / or IoT software.

[0033] The IoT unit deployed in the user terminal can obtain at least one of user input and user location information. The user input can at least include the user's current state. The IoT unit deployed in the user terminal can include application software deployed on the user's mobile phone.

[0034] In some embodiments, the processor may obtain relevant information of the resources to be scheduled through the Internet of Things unit.

[0035] Resources to be dispatched refer to resources that can be used to complete logistics transportation.

[0036] In some embodiments, the resources to be dispatched may include at least candidate drivers and candidate vehicles. The candidate driver refers to at least one driver who can perform logistics transportation work, and the candidate vehicle refers to at least one vehicle that can be used for logistics transportation.

[0037] Step 220, determining the remaining driving time of the candidate driver based on the environmental information and the driving information of the candidate driver.

[0038] Environmental information refers to information related to the driving environment of the vehicle, for example, the environmental information may include season, temperature, etc.

[0039] In some embodiments, the environmental information can be obtained by the processor in a variety of ways. For example, the processor can obtain weather information and season information through the network based on the location information of the candidate vehicle and / or the candidate driver. For another example, the processor can communicate with a sensor set at the location of the vehicle or the target location to obtain environmental information, and the sensor can include at least a temperature sensor, a humidity sensor, a wind speed sensor, etc.

[0040] Driving information refers to information related to the driver's driving behavior.

[0041] In some embodiments, the driving information includes at least driving experience. In some embodiments, the driving information also includes a route feature sequence within a first preset time. The route feature sequence refers to the features of the driving route that the idle driver has completed within the first preset time. For more information about the route feature sequence, please refer to this specification. Figure 3 Related description in .

[0042] In some embodiments, the driving information may be acquired by the processor by querying the personal information and historical driving routes of the candidate drivers.

[0043] The remaining driving time is the time that the candidate driver can still drive safely under the current state.

[0044] In some embodiments, the remaining driving time can be determined in a variety of ways. For example, the average driving time of the target type driver can be counted, the longest safe driving time of the candidate driver can be determined based on the average driving time, and the remaining driving time can be determined based on the longest safe driving time and the driving time of the candidate driver. The target type driver can be a driver of the same age group and the same driving experience as the candidate driver.

[0045] In some embodiments, the remaining driving time can be determined based on the environment information, the driving information of the candidate driver, and the remaining safe driving time prediction model. For more information on determining the remaining driving time, see Figure 3 and its related description.

[0046] Step 230 , determining a candidate dispatching scheme for the candidate vehicle based on the remaining driving time, and the vehicle information and load characteristics of the candidate vehicle.

[0047] Vehicle information refers to data related to the inherent properties of the candidate vehicle, and the vehicle information includes but is not limited to the vehicle type. For example, the vehicle type can be a van, a truck, or other vehicle types that can be used for logistics transportation.

[0048] In some embodiments, vehicle information can be obtained by querying vehicle registration information.

[0049] The load characteristics refer to data used to characterize vehicle load information. For example, the load characteristics may include the load object form (eg, liquid or solid), load mass, load volume, idle vehicle mass, idle vehicle volume, etc.

[0050] The candidate dispatching scheme refers to a transportation plan of at least one candidate vehicle that can be selected. The candidate dispatching scheme at least includes a target driver.

[0051] The candidate dispatching scheme can be determined in a variety of ways. In some embodiments, the processor can organize and save a candidate driver recommendation table based on historical logistics transportation data, the recommendation table including vehicle information and load characteristics of at least one candidate vehicle and their corresponding recommended drivers. The processor can determine the recommended driver by looking up the table based on the vehicle information and load characteristics of the current vehicle, and determine the target driver based at least on the recommended driver.

[0052] In some embodiments, the candidate scheduling schemes also include the departure time of at least one candidate vehicle and its corresponding candidate driving route.

[0053] In some embodiments, the processor may determine the departure time of each candidate vehicle and the candidate driving route based on at least one candidate driving route, the candidate departure time, the delivery time, the remaining safe driving time of at least one idle driver, and the driving difficulty of at least one candidate vehicle. For example, the processor may determine the departure time of the candidate vehicle based on the target arrival time, the delivery time, and the driving difficulty of the candidate vehicle. For another example, the processor may determine the candidate driving route based on the remaining safe driving time and driving difficulty of the idle driver.

[0054] In some embodiments, the departure time and candidate driving routes can be determined based on the starting point information, destination point information and the latest arrival time of the candidate vehicles. For more information about determining the departure time and candidate driving routes, see Figure 4 and its related description.

[0055] Step 240, determining a logistics transportation scheduling plan based on the candidate scheduling plans.

[0056] The logistics transportation scheduling plan refers to the scheduling plan actually used for logistics transportation.

[0057] In some embodiments, the processor may score at least one candidate scheduling scheme based on the comprehensive transportation revenue of at least one candidate scheduling scheme, and the higher the comprehensive transportation revenue, the higher the score, and the candidate scheduling scheme with the highest score is determined as the logistics transportation scheduling scheme. The comprehensive transportation revenue can be determined based on the total price of the transportation order and the transportation cost, the total price of the transportation order can be obtained based on the transportation order, and the transportation cost can be determined based on the vehicle driving cost and the driver cost.

[0058] In some embodiments, the vehicle driving cost includes at least various expenses incurred by the vehicle during driving, such as vehicle tolls, vehicle fuel costs, vehicle maintenance costs, etc. The driver cost includes at least various expenses incurred by the driver in completing the logistics transportation order, such as accommodation fees, food fees, and labor costs, etc.

[0059] In some embodiments of the present specification, the remaining driving time of candidate drivers is determined based on environmental information and driving information, so as to ensure driving safety of logistics transportation; candidate scheduling plans for candidate vehicles are determined based on the remaining driving time, as well as vehicle information and load characteristics, so as to obtain a more reasonable scheduling plan for each candidate vehicle; and a logistics transportation scheduling plan is determined based on the candidate scheduling plans, so as to improve the efficiency and rationality of logistics transportation scheduling.

[0060] It should be noted that the above description of the relevant process is only for example and explanation, and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to the process under the guidance of this specification. However, these modifications and changes are still within the scope of this specification.

[0061] Figure 3 It is a schematic diagram of determining the remaining driving time according to some embodiments of the present specification.

[0062] In some embodiments, the processor may determine the candidate driver's fatigue level 340 based on the environmental information 310 and the driving information 320 ; and determine the remaining driving time 380 based on the fatigue level 340 and the driving information 320 .

[0063] The driving information 320 may include driving experience 320-1 and route feature sequence 320-2. For more information about the environment information 310, the driving information 320, and the remaining driving time 380, see Figure 2 and its related contents.

[0064] Fatigue level 340 refers to an indicator that measures the driver's fatigue level.

[0065] In some embodiments, the processor may determine the driver's fatigue level based on matching the driver feature vector in a reference fatigue level database.

[0066] The driver feature vector can be determined based on the driver's age, driving experience, driving time, current season and current temperature. For example, the driver feature vector can be represented by (Y1, Y2, T1, S, T0), where Y1 represents the driver's age, Y2 represents the driver's driving experience, T1 represents the driver's driving time, S represents the current season, and T0 represents the current temperature.

[0067] The reference fatigue database includes at least one reference driver feature vector and at least one reference fatigue level corresponding thereto. In some embodiments, the reference fatigue database can be determined based on historical driving data. The historical driving data can include the historical driver age, historical driver driving experience, historical driver driving time, historical season, historical temperature and historical fatigue level in historical logistics transportation. The processor can determine the historical driver feature vector and its corresponding historical fatigue level based on the historical driving data, cluster the historical driver feature vectors, determine at least one cluster center, use the vector corresponding to the cluster center as the reference driver feature vector, and use the historical fatigue level corresponding to the cluster center as the reference fatigue level. Among them, the determination of the historical driver feature vector is the same as the determination of the driver feature vector, and the details can be found in the above description.

[0068] In some embodiments, the processor may determine a reference driver feature vector that is closest to the driver feature vector by matching the driver feature vector in a reference fatigue level database, and determine the fatigue level of the current driver based on a reference fatigue level corresponding to the reference driver feature vector.

[0069] The processor can determine the remaining driving time 380 in a variety of ways. In some embodiments, the processor presets at least one fatigue level and at least one remaining driving time corresponding to driving information based on historical data. The processor can determine the remaining driving time 380 based on fatigue level 340 and driving information 320 by looking up a table or the like.

[0070] In some embodiments, the processor may determine the remaining driving time 380 based on the environmental information 310 and the driving information 320 through a duration prediction model.

[0071] The duration prediction model refers to a model used to determine the remaining driving time of the driver. In some embodiments, the duration prediction model can be a machine learning model of a custom structure as described below. The duration prediction model can also be a machine learning model of other structures, such as a neural network model.

[0072] In some embodiments, the duration prediction model may include a first determination layer 330 and a second determination layer 370 .

[0073] In some embodiments, the input of the duration prediction model is the input of the first determination layer 330, the output of the first determination layer 330 can be used as the input of the second determination layer 370, and the output of the second determination layer 370 is the output of the duration prediction model.

[0074] In some embodiments, the input of the first determination layer 330 may include environmental information 310 and driving information 320 , and the output may be fatigue level 340 .

[0075] In some embodiments, if the driver has already performed driving activities, the driving information also includes a route feature sequence of the driving route that the driver has completed within the first preset time. The route feature sequence includes the route features of the driving route that the candidate driver has completed within the first preset time. The route features include at least the number and field of vision of speed bumps, zebra crossings, intersections, traffic lights, etc. Among them, the field of vision includes the type of vegetation on the road, the planting interval, the age of the trees, etc. The first preset time is a pre-set period of time. The first preset time can be determined based on the amount of data actually required. In some embodiments, the route feature sequence can be based on historical driving routes and obtained by accessing traffic maps or satellite images through the network.

[0076] In some embodiments, the input of the second determination layer 370 may include fatigue level 340 and driving information 320 , and the output may be remaining driving time 380 .

[0077] In some embodiments, the input of the second determination layer 370 also includes a road change degree 350 and a scenery change degree 360 ​​of the candidate driving route.

[0078] A candidate driving route refers to the driving route corresponding to a candidate vehicle in a candidate scheduling solution. For more information on determining candidate driving routes, see Figure 4 Related content in .

[0079] The road change degree can represent the complexity of the road conditions along the driving route, and the scenery change degree can represent the changes in the scenery along the driving route. For more information about the road change degree and scenery change degree, see Figure 4 and its related contents.

[0080] If the degree of road change and scenery change of a candidate driving route is poor, the driver needs to deal with more road condition changes and a single visual experience, the driver is more likely to feel fatigued, and the remaining safe driving time may be affected and shortened. In some embodiments of this specification, the degree of road change and scenery change are considered when determining the remaining driving time, which can better evaluate the driver's driving ability and status, thereby selecting a more suitable driver and avoiding safety problems during logistics transportation.

[0081] In some embodiments, the first determination layer and the second determination layer may be trained separately.

[0082] In some embodiments, the first determination layer may be obtained by training a first training sample with a first label. The first training sample may include sample environment information and sample driving information collected from a sample driver during historical driving, and the first label may be the actual fatigue level of the sample driver.

[0083] In some embodiments, the first training sample can be obtained based on historical data, and the first label can be obtained by analyzing various physiological indicators collected from the driver. For example, physiological indicators can include complexion, sweating, breathing characteristics, heart rate, blinking characteristics, etc. In some embodiments, the first label can be obtained based on the heart rate, breathing rate and blinking rate in the physiological indicators through formula (1):

[0084]

[0085] in, is the correlation coefficient, which can be determined based on historical data or prior knowledge.

[0086] In some embodiments, the second determination layer can be obtained by training a second training sample with a second label. The second training sample can include sample fatigue and sample driving information collected from a sample driver during historical driving, and the second label can be the actual remaining driving time of the sample driver.

[0087] In some embodiments, the second training sample can be obtained based on historical data, and the second label can be determined in two situations: 1) Select the driving time from the subsequent driving to the first stop, and the vehicle has not broken down, the vehicle has not waited for a red light, and the duration of the stop is greater than a set threshold as the second label; 2) Select the time when the accident caused by fatigue driving occurs, and the time from the time of the state corresponding to the training sample (i.e., the time when the second training sample is collected) as the second label.

[0088] When the input of the second determination layer further includes the road change degree and the scenery change degree of the candidate driving route, the second training sample may further include the sample road change degree and the sample scenery change degree of the sample route.

[0089] In some embodiments of the present specification, environmental information and driving information are processed through a duration prediction model. The self-learning ability of the machine learning model can be used to find patterns from a large amount of environmental information and driving information, obtain the correlation between the remaining driving time and the driving information, and improve the accuracy and efficiency of determining the remaining driving time.

[0090] Some embodiments of the present specification determine the fatigue level of candidate drivers based on environmental information and driving information, and then determine the remaining driving time, which can provide a more accurate and reliable prediction of the remaining driving time to ensure that the driver can complete the transportation task while ensuring safety.

[0091] In some embodiments, the processor may determine a driving difficulty 430 - 1 of the candidate vehicle based on the vehicle information 420 and the load characteristics 410 ; and determine a candidate dispatching solution 490 based on the driving difficulty 430 - 1 and the remaining driving time 380 .

[0092] For more information about vehicle information 420 and load characteristics 410, see Figure 2 and its related description.

[0093] Driving difficulty 430-1 refers to the degree of difficulty for a driver to drive a vehicle for transportation work. Driving difficulty may include vehicle driving difficulty. Vehicle driving difficulty is related to the characteristics of the vehicle itself. For example, different types of vehicles have different driving difficulties, and tanker trucks are generally more difficult to drive than vans; for another example, vehicles of different specifications have different driving difficulties, and large trucks are generally more difficult to drive than small trucks.

[0094] In some embodiments, the processor may determine the driving difficulty by matching the load feature vector in a reference driving difficulty database.

[0095] The load characteristic vector can be determined based on the load shape, load mass, load volume, remaining vehicle mass and remaining vehicle volume. For example, the load characteristic vector can be expressed as (N, M1, V1, M2, V2), where N represents the load shape, M1 represents the load mass, V1 represents the load volume, M2 represents the remaining vehicle mass, and V2 represents the remaining vehicle volume.

[0096] The reference driving difficulty database includes at least one reference load characteristic vector and at least one reference driving difficulty corresponding thereto. In some embodiments, the reference driving difficulty database can be determined based on historical load data. The historical load data may include historical load forms, historical load masses, historical load volumes, historical remaining vehicle masses, historical remaining vehicle volumes, and historical driving difficulties in historical logistics transportation. The processor can determine the historical load characteristic vector and its corresponding historical driving difficulty based on the historical load data, cluster the historical load characteristic vectors, determine at least one cluster center, use the vector corresponding to the cluster center as the reference load characteristic vector, and use the historical driving difficulty corresponding to the cluster center as the reference driving difficulty. Among them, the determination of the historical load characteristic vector is the same as the determination of the load characteristic vector, and the details can be found in the above description.

[0097] In some embodiments, the processor may match the load characteristic vector in a reference driving difficulty database, determine a reference load characteristic vector that is closest to the load characteristic vector, and determine the current driving difficulty based on a reference driving difficulty corresponding to the reference load characteristic vector.

[0098] In some embodiments, the driving difficulty also includes route driving difficulty.

[0099] Route driving difficulty can represent the complexity of the vehicle's driving route. The more complex the vehicle's driving route is, the higher the corresponding route driving difficulty is.

[0100] The processor can obtain the route driving difficulty based on a variety of methods. In some embodiments, the route driving difficulty can be obtained based on the road conditions of the candidate driving route. For example, a road with heavy traffic requires more attention than a road with light traffic, and the route driving difficulty is greater.

[0101] In some embodiments, the route driving difficulty can be determined based on the degree of road change and the degree of scenery change. For more information on determining the route driving difficulty based on the degree of road change and the degree of scenery change, see below.

[0102] In some embodiments, the processor may determine the driving difficulty by weighted summation based on the vehicle driving difficulty and the route driving difficulty. The weight of the weighted summation may be determined based on a variety of methods, for example, based on prior experience, based on actual needs, etc.

[0103] In some embodiments of the present specification, by considering the driving difficulty of the route, the driving difficulty can be better assessed, and corresponding safe driving suggestions and warnings can be provided for routes of different difficulty levels, which helps drivers better cope with various road and traffic conditions and improve safety and efficiency.

[0104] In some embodiments, the processor may determine a candidate dispatching scheme for each candidate vehicle based on the driving difficulty of at least one candidate vehicle and the remaining driving time of at least one idle driver. For example, the processor may assign an idle driver with a longer remaining driving time and a longer driving experience as a candidate driver 450 to a to-be-departed vehicle with a high driving difficulty, and then determine a candidate dispatching scheme.

[0105] In some embodiments of the present specification, candidate scheduling plans are determined based on driving difficulty and remaining driving time, which helps the driver consider the matching of his own ability and adaptability when selecting a driving route and a vehicle, so as to avoid encountering an unmanageable route and increasing safety risks.

[0106] In some embodiments, the selection of candidate driver 450 is also related to delivery time 440 .

[0107] Delivery time 440 refers to the time required for the vehicle to travel from the departure location to the destination location. In some embodiments, the processor can obtain the delivery time by accessing a traffic map through a network based on the driving route.

[0108] In some embodiments, the processor may select an idle driver whose remaining driving time 380 is greater than or equal to the delivery time as a candidate driver 450 .

[0109] In some embodiments of the present specification, the selection of candidate drivers is also related to the delivery time, and a suitable candidate driver can be selected to achieve safe and efficient logistics transportation scheduling.

[0110] In some embodiments, the scheduling plan also includes the departure time 480 - 2 of the candidate vehicle and the candidate driving route 480 - 1 .

[0111] The departure time 480-2 refers to the departure time of the vehicle.

[0112] In some embodiments, the processor can generate at least one reference driving route 470-1 and its corresponding reference departure time 470-2 based on road information 460-1, the starting position 460-2 of the candidate vehicle, the destination position 460-3 and the latest arrival time 460-4; determine the departure time 480-2 and the candidate driving route 480-1 based on at least one reference driving route 470-1, the candidate departure time 470-2, the remaining driving time 380, and the driving difficulty 430-1.

[0113] In some embodiments, the processor may access a traffic map or satellite image through a network to obtain road information 460-1. The road information may include at least one destination station and a route connecting the destination stations.

[0114] In some embodiments, the departure location 460 - 2 , the destination location 460 - 3 , and the latest arrival time 460 - 4 may be obtained based on a logistics order.

[0115] The processor can determine the candidate driving route 480-1 in a variety of ways. The reference driving route 470-1 refers to a driving route that can reach the destination site from the departure site. In some embodiments, the processor can obtain the candidate driving route 480-1 based on historical driving routes and / or network access traffic maps.

[0116] The processor may determine the reference departure time 470-2 in a variety of ways. In some embodiments, the processor may determine at least one latest departure time by subtracting the latest arrival time from the delivery time corresponding to at least one reference driving route, and determine at least one corresponding waiting reference vehicle time 470-2 based on the at least one latest departure time. For example, the reference departure time 470-2 may be selected within the time interval from the current time to the latest departure time.

[0117] In some embodiments, the processor may construct a road network diagram based on the road information 460 - 1 ; and determine at least one candidate driving route and a corresponding candidate departure time based on the road network diagram, the departure location 460 - 2 , the destination location 460 - 3 , and the latest arrival time 460 - 4 .

[0118] A road network graph is a graph that reflects information related to sites and roads. A graph is a data structure consisting of nodes and edges, where edges connect nodes and nodes and edges can have features.

[0119] In some embodiments, the nodes of the road network diagram may correspond to various sites in the logistics transportation process. The node characteristics may reflect the relevant characteristics of the corresponding site. For example, the node characteristics include the target arrival time. The node characteristics may be determined based on the logistics transportation demand, for example, according to the required arrival time of the goods in the logistics order.

[0120] In some embodiments, the edge may correspond to a road between sites. The edge feature may reflect the relevant features of the corresponding road. For example, the edge feature includes the estimated time of the road. The edge feature may be determined based on historical logistics transportation information, for example, based on the average travel time of the same road during historical logistics transportation.

[0121] In some embodiments, the processor may determine at least one reference driving route based on a road network diagram, a departure location, a destination location, and a latest arrival time. For example, for a certain logistics transport order, the departure location is A and the destination location is B. According to the road network diagram, at least one reference driving route between A and B may be determined. The reference driving route may directly connect A and B, or may include at least one intermediate station. The processor may determine the estimated delivery time of the reference driving route based on the latest arrival time at the destination location B and the estimated road time between at least one intermediate station, and determine the reference departure time based on the target arrival time and the delivery time.

[0122] In some embodiments, if the reference departure time meets the preset conditions, the corresponding reference route is used as a candidate driving route, and the corresponding reference departure time is determined as a candidate departure time. Sufficient preparation is usually required before the start of logistics transportation, so the preset conditions may include that the departure time meets the departure preparation requirements.

[0123] In some embodiments, the processor may determine the candidate driving route and the candidate departure time based on at least one reference driving route and its corresponding reference departure time, remaining driving time, and driving difficulty. For example, the processor may evaluate at least one reference driving route based on the remaining driving time and driving difficulty, and determine the candidate driving route and the candidate departure time based on the reference driving route with the highest evaluation score and its corresponding reference departure time. The evaluation value of the reference driving route is positively correlated with the remaining driving time and negatively correlated with the driving difficulty.

[0124] In some embodiments, the processor may evaluate the reference driving route based on formula (2):

[0125] (2)

[0126] in, represents the evaluation value of the reference driving route, refers to the driving time evaluation value, Refers to the driving difficulty assessment value, , They are the coefficients of the driving time assessment value and the driving route difficulty assessment value respectively.

[0127] In some embodiments, the driving time evaluation value may be determined based on the remaining driving time. The longer the remaining driving time, the higher the driving time evaluation value. The driving difficulty evaluation value may be determined based on the driving difficulty. The higher the driving difficulty, the higher the driving difficulty evaluation value. , Can be determined based on prior experience.

[0128] For more information about the remaining driving time 380, see Figure 2 and its related contents.

[0129] Some embodiments of the present specification use road information to construct a road network diagram, and determine at least one candidate driving route and a corresponding candidate departure time in combination with the departure location, destination location, and latest arrival time, which can help users find the optimal driving route and appropriate departure time and better arrange logistics transportation scheduling plans.

[0130] In some embodiments, the processor may calculate the degree of road change based on the road feature distribution of each candidate driving route; determine the degree of road scenery change based on the road feature distribution and weather feature distribution; and determine the route driving difficulty based on the road change degree and the scenery change degree.

[0131] The road change degree 350 refers to the degree to which the road characteristics have changed. The road characteristics may include at least one sub-feature, such as road length, average road slope, number of road speed bumps, road type, road speed limit, road surrounding scenery characteristics, and road vision characteristics.

[0132] In some embodiments, the processor may calculate the road change degree 350 based on the road feature distribution of each candidate driving route. For example, the processor may calculate the road similarity of road features of adjacent road segments in the candidate driving route; determine a road similarity vector based on the road similarity; and determine the road change degree 350 based on the road similarity vector.

[0133] The road similarity can be determined based on the similarity of at least one sub-feature in the road features of adjacent road segments. The at least one sub-feature can include road type, average road slope, number of road speed bumps, road speed limit, etc.

[0134] In some embodiments, the processor may determine the road similarity of adjacent road segments based on the similarity of at least one sub-feature in the road features of the adjacent road segments. For example, the road similarity may be calculated based on formula (3):

[0135] (3)

[0136] in, Indicates adjacent road segments and The similarity of represents the number of sub-features in the road feature, Indicates adjacent road segments and No. The similarity between the sub-features, For the The coefficient corresponding to the similarity of the sub-features. It can be determined based on prior experience or actual needs.

[0137] In some embodiments, the processor may construct a road similarity vector based on the road similarity of at least one group of adjacent roads, wherein each element in the road similarity vector represents the road similarity between two adjacent road segments.

[0138] In some embodiments, the processor may perform a weighted summation on each element in the road similarity vector and determine the road change degree based on the weighted summation result, wherein the weight of the weighted summation is positively correlated to the sum of the road lengths of the two road segments corresponding to each similarity.

[0139] The road feature distribution is the distribution of road features of at least one road segment. The candidate driving route includes at least one road segment. For example, the road features may include road length, average road slope, number of road speed bumps, road type, road speed limit, road surrounding scenery features, road distant view features, etc.

[0140] In some embodiments, the processor may access traffic maps or satellite images through a network to obtain road feature distribution.

[0141] The degree of scenery change 360 ​​refers to the degree to which the characteristics of the scenery change.

[0142] In some embodiments, the processor may determine the degree of scenery change 360 ​​of the road based on the road feature distribution and the weather feature distribution. For example, the processor may calculate the degree of scenery similarity between adjacent road segments in the candidate driving route; determine a scenery similarity vector based on the scenery similarity; and determine the degree of scenery change 360 ​​based on the scenery similarity vector.

[0143] The degree of scenery similarity can be determined based on the road surrounding scenery features, road distant view features and light intensity in the weather feature distribution. The road surrounding scenery features and road distant view features can be determined based on the historical image data of the same road through an image recognition algorithm, and the historical image data can be obtained based on the driving recorder of the vehicle traveling on the same road.

[0144] In some embodiments, the processor may construct a scenery similarity vector based on the scenery similarity of at least one group of adjacent roads, wherein each element in the scenery similarity vector represents the scenery similarity between two adjacent road segments.

[0145] In some embodiments, the processor may perform a weighted summation on each element in the scenery similarity vector and determine the scenery change degree based on the weighted summation result, wherein the weight of the weighted summation is positively correlated to the sum of the road lengths of the two road segments corresponding to each similarity.

[0146] The weather characteristic distribution is the distribution of weather characteristics at the time of arriving at at least one road segment. The time of arriving at at least one road segment may be the sum of the departure time and the cumulative time of the previous multiple road segments. For example, the weather characteristics may include temperature, humidity, light intensity, etc.

[0147] If the degree of road change is greater, it means that the driver needs to change the driving style frequently, so the driving difficulty will increase accordingly. For example, switching from the national highway to the expressway, then to the rural road, and finally back to the national highway, such route changes require the driver to constantly adjust his driving style to adapt to different road characteristics, which increases the driving difficulty. If the scenery on the transportation route is too monotonous or changes little, the driver is prone to visual fatigue, which increases the driving difficulty. For example, when driving on the expressway, due to the small changes in the scenery, the driver needs to keep staring at the front, which is easy to cause visual fatigue. Therefore, if the scenery on the transportation route changes less, the driver is more likely to feel tired, which increases the driving difficulty.

[0148] In some embodiments, the route driving difficulty is positively correlated with the degree of road change and negatively correlated with the degree of scenery change. The higher the degree of road change, the greater the driving difficulty. The greater the degree of scenery change, the lower the driving difficulty.

[0149] In some embodiments of the present specification, the driving difficulty of a route is determined according to the degree of road change and the degree of scenery change, so that more comprehensive and accurate route information can be obtained, and corresponding adjustments can be made to the logistics transportation scheduling plan to improve driving safety and efficiency.

[0150] Some embodiments of the present specification determine the departure time and candidate driving routes based on at least one reference driving route, reference departure time, remaining driving time, and driving difficulty, and comprehensively consider various factors to provide a more reasonable and feasible scheduling solution for logistics transportation, which helps to improve the efficiency of logistics transportation, reduce costs, and ensure safety.

[0151] Some embodiments of the present specification provide a logistics transportation scheduling device, including a processor, and the processor is used to execute the logistics transportation scheduling method described in any one of the embodiments of the present specification.

[0152] Some embodiments of the present specification provide a computer-readable storage medium, which stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the logistics transportation scheduling method described in any one of the embodiments of the present specification.

[0153] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0154] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0155] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0156] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0157] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining the digits. Although the numerical domains and parameters used to confirm the breadth of the range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0158] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification is hereby incorporated by reference in its entirety. Except for application history documents that are inconsistent with or conflicting with the contents of this specification, documents that limit the broadest scope of the claims of this specification (currently or later attached to this specification) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the materials attached to this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions, and / or use of terms in this specification shall prevail.

[0159] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A logistics transportation scheduling method, characterized in that: The method is executed by a processor, comprising: Acquire resources to be scheduled from an Internet of Things unit, where the Internet of Things unit is configured in at least one terminal, and the resources to be scheduled include candidate drivers and candidate vehicles; Determining the remaining driving time of the candidate driver according to the environmental information and the driving information of the candidate driver; Determining a candidate dispatching scheme for the candidate vehicle according to the remaining driving time, and the vehicle information and load characteristics of the candidate vehicle, wherein the candidate dispatching scheme includes at least a target driver; A logistics transportation scheduling plan is determined based on the candidate scheduling plans.

2. The logistics transportation scheduling method according to claim 1, characterized in that: The determining the remaining driving time of the candidate driver according to the environmental information and the driving information of the candidate driver comprises: determining the fatigue level of the candidate driver according to the environmental information and the driving information; The remaining driving time is determined based on the fatigue level and the driving information.

3. The logistics transportation scheduling method according to claim 1, characterized in that: Determining the candidate scheduling scheme for the candidate vehicle according to the remaining driving time and the vehicle information and load characteristics of the candidate vehicle includes: Determining the driving difficulty of the candidate vehicle based on the vehicle information and the load characteristics; The candidate scheduling solutions are determined based on the driving difficulty and the remaining driving time.

4. The logistics transportation scheduling method according to claim 3, characterized in that: The candidate scheduling scheme also includes the departure time of the candidate vehicle and the candidate driving route. The determining of the candidate scheduling scheme based on the driving difficulty and the remaining driving time includes: Generate at least one reference driving route and its corresponding reference departure time based on the road information, the departure position, the destination position and the latest arrival time of the candidate vehicle; The departure time and the candidate driving routes are determined based on the at least one reference driving route, the reference departure time, the remaining driving time, and the driving difficulty.

5. A logistics transportation scheduling system, characterized in that: The system comprises an acquisition module, a first determination module and a second determination module; The acquisition module is used to acquire resources to be scheduled from an Internet of Things unit, where the Internet of Things unit is configured in at least one terminal, and the resources to be scheduled include candidate drivers and candidate vehicles; The first determination module is used to determine the remaining driving time of the candidate driver according to the environmental information and the driving information of the candidate driver; The second determining module is used for: Determining a candidate dispatching scheme for the candidate vehicle according to the remaining driving time, and the vehicle information and load characteristics of the candidate vehicle, wherein the dispatching scheme at least includes a target driver; A logistics transportation scheduling plan is determined based on the candidate scheduling plans.

6. The logistics transportation scheduling system according to claim 5, characterized in that: The first determining module is further configured to: determining the fatigue level of the candidate driver according to the environmental information and the driving information; The remaining driving time is determined based on the fatigue level and the driving information.

7. The logistics transportation scheduling system according to claim 5, characterized in that: The second determining module is further used for: Determining the driving difficulty of the candidate vehicle based on the vehicle information and the load characteristics; The candidate scheduling solutions are determined based on the driving difficulty and the remaining driving time.

8. The logistics transportation scheduling system according to claim 5, characterized in that: The second determining module is further used for: Generate at least one reference driving route and its corresponding reference departure time based on the road information, the departure position, the destination position and the latest arrival time of the candidate vehicle; The departure time and candidate driving routes are determined based on the at least one reference driving route, the reference departure time, the remaining driving time, and the driving difficulty.

9. A logistics transportation scheduling device, characterized in that: It includes a processor, and the processor is used to execute the logistics transportation scheduling method described in any one of claims 1 to 4.

10. A computer-readable storage medium, characterized in that: The storage medium stores computer instructions. When the computer reads the computer instructions in the storage medium, the computer executes the logistics transportation scheduling method as described in any one of claims 1 to 4.

Images