WO2021253918A1 - 路径规划 - Google Patents

路径规划 Download PDF

Info

Publication number
WO2021253918A1
WO2021253918A1 PCT/CN2021/084071 CN2021084071W WO2021253918A1 WO 2021253918 A1 WO2021253918 A1 WO 2021253918A1 CN 2021084071 W CN2021084071 W CN 2021084071W WO 2021253918 A1 WO2021253918 A1 WO 2021253918A1
Authority
WO
WIPO (PCT)
Prior art keywords
sequence
waybill
target
visited
delivery location
Prior art date
Application number
PCT/CN2021/084071
Other languages
English (en)
French (fr)
Inventor
郑环宇
王圣尧
王兴
王凌
Original Assignee
北京三快在线科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京三快在线科技有限公司 filed Critical 北京三快在线科技有限公司
Publication of WO2021253918A1 publication Critical patent/WO2021253918A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3407—Route searching; Route guidance specially adapted for specific applications
    • G01C21/3415—Dynamic re-routing, e.g. recalculating the route when the user deviates from calculated route or after detecting real-time traffic data or accidents
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3407—Route searching; Route guidance specially adapted for specific applications
    • G01C21/3423—Multimodal routing, i.e. combining two or more modes of transportation, where the modes can be any of, e.g. driving, walking, cycling, public transport
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3453—Special cost functions, i.e. other than distance or default speed limit of road segments
    • G01C21/3469—Fuel consumption; Energy use; Emission aspects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • G06Q10/083—Shipping

Definitions

  • the embodiments of the present application relate to the field of computer technology, and specifically relate to path planning.
  • the service platform needs to plan the route of the distribution capacity in order to provide a more reasonable retrieval, distribution route and order for the distribution capacity, thereby reducing the occurrence of delays in the delivery of items.
  • the embodiments of the present application propose path planning methods, devices, electronic equipment, and computer-readable media to solve the technical problems of inapplicability of online scenes due to the slow solution process in the prior art and the inability to generate path planning results.
  • an embodiment of the present application provides a route planning method.
  • the method includes: obtaining a waybill with a target capacity that has not been processed, wherein the location to be visited is recorded in the waybill; and the waybill is sorted, and the waybill is sorted in the order Plan the path of the to-be-visited locations in, to obtain the sequence of the to-be-visited locations; take the sequence of the to-be-visited locations as the initial sequence, and perform the following path adjustment steps: randomly remove part of the to-be-visited locations from the initial sequence to obtain the remaining sequence; remove The to-be-visited location is re-inserted into the remaining sequence to obtain the recombination sequence; the recombination sequence is partially adjusted to obtain the target sequence; in the case of meeting the preset end conditions, the path planning result is generated based on the target sequence.
  • an embodiment of the present application provides a path planning device, the device includes: an acquiring unit configured to acquire an unprocessed waybill of a target capacity, and the waybill records the location to be visited; the path planning unit is configured as a pair The waybill is sorted, and the route planning is performed on the places to be visited in the waybill according to the sorting order of the waybill to obtain the sequence of the places to be visited; the path adjustment unit is configured to take the sequence of the places to be visited as the initial sequence, and perform the following path adjustment steps: randomly from Part of the site to be visited is removed from the initial sequence to obtain the remaining sequence; the removed site to be visited is reinserted into the remaining sequence to obtain the recombination sequence; the recombination sequence is partially adjusted to obtain the target sequence; when the preset end conditions are met , Generate path planning results based on the target sequence.
  • an embodiment of the present application provides an electronic device, including: one or more processors; a storage device, on which one or more programs are stored, when one or more programs are used by one or more processors Execution enables one or more processors to implement the method as described in the first aspect.
  • an embodiment of the present application provides a computer-readable medium on which a computer program is stored, and when the program is executed by a processor, the method as described in the first aspect is implemented.
  • the route planning method, device, electronic equipment, and computer readable medium provided by the embodiments of the present application sort the obtained waybills for which the target capacity has not been processed, and plan the route of the destinations to be visited in the waybill according to the sort order,
  • the sequence of places to be visited is thus obtained; then the sequence of places to be visited is used as the initial sequence, a part of the places to be visited is randomly removed from the initial sequence, and the removed places to be visited are reinserted into the remaining sequence to obtain a recombination sequence; Afterwards, the recombination sequence is partially adjusted to obtain the target sequence; finally, when the preset end condition is met, the path planning result is generated based on the target sequence.
  • the above process of obtaining the initial sequence can obtain a feasible solution to the initial path planning problem, the process of reorganizing the initial sequence can achieve a rough search for the optimal solution, and the process of partially adjusting the reorganization sequence can achieve a fine search for the optimal solution.
  • the path planning results obtained in the process of rough search and fine search compared with the direct calculation in the prior art method of calculating the optimal solution based on a large amount of data, can effectively obtain the path planning results, avoiding the optimal solution Failure situation.
  • the local optimal solution is used in the process of determining the path planning result, which reduces the amount of data calculation and improves the solution efficiency of path planning problems, thus improving the applicability of online scenarios.
  • Fig. 1 is a flowchart of an embodiment of a path planning method according to the present application
  • Figure 2 is an exploded flow chart of the steps of generating a recombinant sequence according to the present application
  • Fig. 3 is a flowchart of an implementation manner of partially adjusting the recombination sequence according to the present application
  • Fig. 4 is a flowchart of another implementation manner of partially adjusting the recombination sequence according to the present application.
  • Fig. 5 is a flowchart of another implementation manner of partially adjusting the recombination sequence according to the present application.
  • Fig. 6 is a flowchart of another implementation manner of partially adjusting the recombination sequence according to the present application.
  • Fig. 7 is a flowchart of another embodiment of a path planning method according to the present application.
  • Fig. 8 is a schematic structural diagram of an embodiment of a path planning device according to the present application.
  • Fig. 9 is a schematic structural diagram of a computer system suitable for implementing an electronic device according to an embodiment of the present application.
  • FIG. 1 shows a process 100 of an embodiment of a path planning method according to the present application.
  • the execution subject of the path planning method may be a server.
  • the server can be hardware or software.
  • the server When the server is hardware, it can be implemented as a distributed device cluster composed of multiple devices, or as a single device.
  • the server When the server is software, it can be implemented as multiple software or software modules, or as a single software or software module. There is no specific limitation here.
  • the execution subject of the path planning method may also be the terminal device.
  • the aforementioned terminal device may be an electronic device such as a mobile phone, a smart phone, a tablet computer, a laptop portable computer, a wearable device, and the like.
  • the path planning method includes the following steps:
  • Step 101 Obtain the unprocessed waybill of the target capacity.
  • the execution subject of the path planning method can obtain the waybill that has not been processed and completed by the target capacity.
  • each obtained waybill can record the location to be visited.
  • the location to be visited may include a delivery location.
  • the delivery location can refer to the destination to which the target capacity delivers items (such as express delivery, meals), etc., such as a location designated by a user, a delivery cabinet, etc.
  • the location to be visited can include not only the delivery location, but also the pick-up location, such as the meal pick-up store, the meal cabinet, etc.
  • the target capacity can be various types of distribution capacity.
  • it may include, but is not limited to: delivery personnel, delivery robots, unmanned aerial vehicles, unmanned vehicles, and so on.
  • the distribution capacity can collect the list of wireless network information to be tested in real time or periodically, and send the collected list of wireless network information to be tested to the above-mentioned executive body.
  • Step 102 Sort the waybills, and perform path planning on the places to be visited in the waybills according to the sorting order of the waybills to obtain the sequence of the places to be visited.
  • the above-mentioned execution subject may sort the waybills according to multiple sorting methods, so as to obtain the sorting result of each waybill.
  • each waybill may record the target arrival time of the delivery location.
  • the above-mentioned executive body can sort the air waybills in the order of the target delivery time of the delivery location from first to last.
  • the above-mentioned execution subject may sort the waybills in order of importance of the delivery objects of the waybill, so that the waybills of important users are ranked first, and the waybills of non-important users are ranked second.
  • the above-mentioned execution subject may sort the waybills in descending order of urgency.
  • the degree of urgency here can be determined based on the location of the target capacity, the current time, and the target arrival time of the delivery location. For example, you can refer to the following formula to determine the urgency of the waybill:
  • each waybill may also be based on other sorting methods, and the specific sorting method is not limited in this embodiment.
  • the above-mentioned execution subject can plan the route of the locations to be visited in each waybill according to the sorting order of each waybill to obtain the sequence of the locations to be visited. Specifically, follow the steps below:
  • the first waybill can be taken out in the sort order. Since there is no path planning problem when there is only one place to be visited, the place to be visited can be directly recorded as the first place to be visited.
  • the second waybill can be taken out according to the sort order, and the place to be visited in the second waybill is used as the second place to be visited. Since the second place to be visited may be located before or after the first place to be visited, it can be determined whether the second place to be visited meets the preset constraint conditions in both cases before and after the first place to be visited. If only one situation satisfies the constraint condition, the sequence of the first location to be visited and the second location to be visited in this situation can be recorded. If both of these two situations meet the constraints, the objective function value in these two situations can be determined, and based on the objective function value, the order of the first location to be visited and the second location to be visited in one of the cases can be selected. record.
  • the location to be visited includes not only the delivery location, but also the pick up location. Therefore, the sorting of the location to be visited can refer to the items in the location to be visited. (Including pick-up location and delivery location) for sorting.
  • the first place to be visited includes the place to be visited recorded in the first waybill, including the first pick-up place (can be recorded as A1) and the first delivery Location (can be recorded as B1)
  • the location to be visited recorded in the second waybill includes the second pick-up location (can be recorded as A2) and delivery location (can be recorded as B2).
  • the constraint condition may be a condition for restricting the order of the places to be visited.
  • the restriction conditions may include, but are not limited to: the access time of the pick-up location is later than the item shipment time, the access time of the pick-up location of the same waybill is earlier than the visit time of the delivery location, and so on.
  • the objective function value is a preset objective function value.
  • the objective function can be used to characterize the goal of path planning.
  • the objective function can be used to characterize minimizing the delivery timeout period, minimizing the delivery distance, or simultaneously minimizing the delivery timeout period and delivery distance.
  • the following functional formula can be used as the objective function:
  • t i is the target arrival time of the delivery location in the waybill i.
  • T i is the estimated arrival time of the delivery location in the waybill i, that is, the estimated time when the target capacity reaches the delivery location.
  • d i is the distance traveled by the target capacity to complete the order i.
  • the sequence of the locations to be visited is obtained, so that a dynamic planning result can be initialized, that is, an initial feasible solution to a path planning problem can be obtained. Since the feasible solution is obtained by path planning successively according to the sorting order of the waybill, the greedy strategy is adopted. Compared with random initialization to obtain feasible solutions, the effectiveness and rationality of the initial feasible solutions are improved.
  • Step 103 Use the sequence of locations to be visited as the initial sequence.
  • the above-mentioned execution subject may use the sequence of locations to be visited as the initial sequence, and execute the path adjustment steps including the following steps 104 to 107.
  • Step 104 Randomly remove part of the to-be-visited locations from the initial sequence to obtain the remaining sequence.
  • the above-mentioned execution subject may randomly remove part of the places to be visited from the initial sequence, and use the initial sequence after removing the part of the places to be visited as the remaining sequence. For example, a fixed number of some places to be visited may be removed, or some places to be visited according to a number related to the total number of places to be visited.
  • the above-mentioned execution subject may determine the target quantity based on the total number of places to be visited.
  • the target quantity is recorded as the quantity of the waybill to be removed from the place to be visited. For example, if the total number of locations to be visited is denoted as n, the target number can be n/2. Then, a target number of waybills (ie, n/2) can be randomly selected, and the randomly selected place to be visited in the waybill can be removed from the initial sequence.
  • the number of removed locations to be visited is related to the total number of locations to be visited. Since the total number of locations to be visited can represent the scale of the path planning problem, the number of removed locations to be visited is related to the scale of the path planning problem, and the rationality of the number of reorganized locations to be visited can be ensured.
  • Step 105 Re-insert the removed site to be visited into the remaining sequence to obtain a recombined sequence.
  • the above-mentioned execution subject may reinsert the removed locations to be visited into the remaining sequence to obtain the recombined sequence.
  • the objective function value of the reorganization sequence is better than (for example, less than) the objective function value of the initial sequence and the reorganization sequence satisfies the preset constraint conditions, and the removed locations to be visited can be re-inserted.
  • sub-step S11 the removed locations to be visited are summarized as a removal sequence (may be denoted as ⁇ R ).
  • sub-step S12 the objective function and constraint conditions of the path planning are obtained.
  • the objective function and constraint conditions can be referred to the description in step 102, which will not be repeated here.
  • sub-step S13 the locations to be visited in the above removal sequence are taken out one by one, and the following steps are performed:
  • the feasible position is the position that satisfies the constraint condition.
  • the feasible position when the objective function value is the smallest is taken as the target position, and the fetched place to be visited is inserted into the target position in the remaining sequence.
  • each location to be visited in ⁇ R can be inserted into each feasible location in ⁇ D one by one, so as to select the best one for placement, until there is no place to be visited in ⁇ R.
  • sub-step S14 the remaining sequence inserted with the site to be visited in the removal sequence is determined as a recombination sequence.
  • Step 106 Partially adjust the recombination sequence to obtain the target sequence.
  • the above-mentioned execution subject can locally adjust the recombination sequence to obtain the target sequence.
  • one or more methods can be used to locally adjust the recombination sequence.
  • the location to be visited in the waybill includes the delivery location, and the target arrival time of the delivery location is recorded in the waybill.
  • the above-mentioned execution subject can locally adjust the recombination sequence according to the following sub-steps S21 to S24:
  • Sub-step S21 based on the recombination sequence, determine the estimated arrival time of the delivery location of the waybill.
  • the visiting sequence of each location to be visited can be determined, and the target can be estimated based on information such as the visiting sequence of each location to be visited, the location of the target capacity, the distance between the target capacity and each location to be visited, and road conditions.
  • the estimated time of arrival of the shipping capacity to the delivery location of each waybill can be carried out in an existing manner, and will not be repeated here.
  • sub-step S22 it is determined that the waybill is delivered in advance, and a first mark is added to each waybill delivered in advance.
  • the waybill delivered in advance is the waybill whose estimated arrival time at the delivery location is earlier than the target arrival time.
  • the position of the first target delivery location in the recombination sequence can be adjusted according to the following steps:
  • the first step the position of the first target delivery location in the recombination sequence is taken as the first original position, and the first target delivery location is removed from the recombination sequence.
  • a target delivery location A target delivery location.
  • the second step is to obtain the objective function and constraint conditions of the path planning.
  • the third step is to insert the first target delivery location into each feasible position after the first original position in the recombination sequence, and determine the objective function value when inserting into each feasible position, and the feasible position is a position that satisfies the constraint condition.
  • the feasible position when the objective function value is the smallest is used as the first update position, and the first target delivery location is inserted into the first update position.
  • sub-step S24 in response to the first target delivery location being at the end of the recombination sequence, sub-step S24 can be directly executed.
  • sub-step S24 it is detected whether there is a waybill with the first mark, and if it exists, the first partial adjustment step is re-executed.
  • the delivery order of each early delivered waybill can be moved backward, so that more urgent waybills can be processed first.
  • the quality and rationality of the solution to the path planning problem can be further improved.
  • the location to be visited in the waybill includes the delivery location, and the target arrival time of the delivery location is recorded in the waybill.
  • the above-mentioned execution subject can locally adjust the recombination sequence according to the following sub-steps S31 to S34:
  • Sub-step S31 based on the recombination sequence, determine the estimated arrival time of the delivery location of the waybill.
  • the delayed delivery waybill is determined, and a second mark is added to each delayed delivery waybill.
  • the delayed delivery waybill is the waybill whose estimated arrival time at the delivery location is later than the target arrival time.
  • the position of the second target delivery location in the recombination sequence can be adjusted according to the following steps:
  • the first step the position of the second target delivery location in the recombination sequence is taken as the second original position, and the second target delivery location is removed from the recombination sequence.
  • Target delivery location The second step is to obtain the objective function and constraint conditions of the path planning.
  • the third step is to insert the second target delivery location into each feasible position before the second original position in the recombination sequence, and determine the objective function value when inserting into each feasible position, and the feasible position is a position that satisfies the constraint condition.
  • the feasible position when the objective function value is the smallest is used as the second update position, and the second target delivery location is inserted into the second update position.
  • the delivery order of the delayed delivery waybill can be advanced, but also the delivery address in the delayed delivery waybill can be adjusted to the most reasonable position, which further improves the quality and rationality of the solution to the path planning problem.
  • sub-step S34 may be directly executed.
  • Sub-step S34 detecting whether there is a waybill with a second mark, and if so, re-execute the second partial adjustment step.
  • each delayed delivery waybill By moving forward the location of the delivery location in each delayed delivery waybill to partially adjust the reorganization sequence, the delivery order of each delayed delivery waybill can be advanced, thereby avoiding delayed delivery of orders or reducing the timeout period of delayed delivery orders. As a result, the quality and rationality of the solution to the path planning problem can be further improved.
  • the location to be visited in the waybill includes a delivery location.
  • the above-mentioned execution subject can locally adjust the recombination sequence according to the following sub-steps S41 to S43:
  • Sub-step S41 adding a third mark to each delivery location in the recombination sequence.
  • any delivery location with a third mark in the recombination sequence is taken as the third target delivery location, and the third target delivery location is taken out of the recombination sequence.
  • the third target delivery location is inserted into each feasible position in the recombination sequence, and the objective function value when inserted into each feasible position is determined, and the feasible position is a position that satisfies the constraint condition.
  • the feasible position when the objective function value is the smallest is taken as the third update position, the third target delivery location is inserted into the third update position, and the third mark of the third target delivery location is deleted.
  • Sub-step S43 detecting whether there is a delivery location with a third mark in the recombination sequence, and if so, re-execute the third local adjustment step.
  • each delivery location in the recombination sequence can be taken as the third target delivery location one by one, and the recombination sequence can be taken out and reinserted. Therefore, more feasible solutions are further searched, and the optimal solution (that is, the sequence when the objective function value is the smallest) is selected among these feasible solutions, which can further improve the quality of the solution of the path planning problem.
  • the location to be visited in the waybill includes a delivery location.
  • the above-mentioned execution subject can locally adjust the recombination sequence according to the following sub-steps S51 to S53:
  • Sub-step S51 adding a fourth mark to the delivery location in the recombination sequence.
  • sub-step S52 the following fourth partial adjustment step is performed:
  • any delivery location with a fourth mark in the reorganization sequence is used as the fourth target delivery location, and the fourth target delivery location is exchanged with each of the remaining locations to be visited in the reorganization sequence to obtain the target under each exchange mode. Function value, and determine whether each exchange method satisfies the constraint conditions.
  • the exchange mode when the objective function value is the smallest and meets the constraint conditions is taken as the target exchange mode, the location of the fourth target delivery location is exchanged in the target exchange mode, and the fourth mark of the fourth target delivery location is deleted.
  • Sub-step S53 detecting whether there is a delivery location with a fourth mark in the recombination sequence, and if so, re-execute the fourth local adjustment step.
  • each delivery location in the recombination sequence can be used as the fourth target delivery location one by one, and the quality of feasible solutions when exchanging with the remaining locations to be visited can be detected. Therefore, more feasible solutions are further searched, and the optimal solution (that is, the sequence when the objective function value is the smallest) is selected among these feasible solutions, which can further improve the quality of the solution of the path planning problem.
  • the above-mentioned executive body can also use the above-mentioned various optional implementation methods to perform partial adjustments of the recombination sequence to obtain the target sequence; it can also perform any combination of the above-mentioned optional implementation methods to perform partial adjustments to the recombination sequence. Adjust to obtain the target sequence; other methods can also be used to perform partial adjustment of the recombination sequence to obtain the target sequence.
  • Step 107 When the preset end condition is met, a path planning result is generated based on the target sequence.
  • the above-mentioned execution subject may first detect whether the preset end condition is satisfied.
  • the aforementioned preset end condition may refer to the condition for the end of the path planning solution.
  • the preset end conditions here can be preset as needed. For example, it may be set that the iterative execution order of the path adjustment step is greater than or equal to a preset value, and the processing time is greater than or equal to a preset threshold value, and so on.
  • the above-mentioned execution subject may generate a path planning result based on the target sequence.
  • the path planning result here may include information such as each to-be-visited location in the target sequence to the visiting sequence, route, etc., so that the target capacity can process the waybill based on the path planning result, such as fetching, delivering, etc.
  • the execution subject may use the target sequence obtained in step 107 as the initial sequence, and continue to execute the path adjustment step until the preset end condition is met.
  • the preset end condition is not met, multiple path adjustment steps can be executed iteratively. Since the more you execute here, the better the final path planning result, which can balance the quality of the path planning result and the time-consuming path planning.
  • the above-mentioned execution subject may detect whether the processing duration meets the preset end condition by the following steps: First, the time difference between the current time and the acquisition time of the air waybill of the target capacity is taken as the processing duration, and the processing duration is detected. Whether the processing time is greater than or equal to the preset threshold. In response to the processing time being greater than or equal to the preset threshold, it may be determined that the preset end condition is satisfied; in response to the time difference being less than the preset threshold, it may be determined that the preset end condition is not satisfied. As a result, the length of path planning and solving can be limited from time, and the applicability to online scenes is further improved.
  • the preset threshold may be related to the total number of places to be visited. For example, if the total number of places to be visited is n, the preset threshold may be 2n milliseconds or n 2 milliseconds. Since the total number of locations to be visited can represent the scale of the path planning problem, setting the preset threshold to a number related to the scale of the path planning problem can ensure the rationality of the preset threshold.
  • the above-mentioned execution subject may also return the path planning result to the target capacity, so that the target capacity can be delivered or picked up according to the path planning result.
  • the above-mentioned execution subject also applies the path planning result to allocate orders for target capacity, etc.
  • the application of the path planning result is not limited in this embodiment.
  • the method provided in the above-mentioned embodiment of the present application sorts the obtained waybills for which the target capacity has not been processed, and performs path planning on the places to be visited in the waybills according to the sorting order, thereby obtaining the sequence of the places to be visited; Take the sequence of the place to be visited as the initial sequence, randomly remove part of the place to be visited from the initial sequence, and reinsert the removed place to be visited into the remaining sequence to obtain the recombination sequence; then partially adjust the recombination sequence to obtain the target sequence; Finally, when the preset end condition is met, the path planning result is generated based on the target sequence.
  • the above process of obtaining the initial sequence can obtain a feasible solution to the initial path planning problem, the process of initial sequence reorganization can achieve a rough search for the optimal solution, and the process of partially adjusting the reorganization sequence can achieve a fine search for the optimal solution.
  • the path planning results obtained in the process of rough search and fine search compared with the direct calculation in the prior art method of calculating the optimal solution based on a large amount of data, can effectively obtain the path planning results, avoiding the optimal solution Failure situation.
  • the local optimal solution is used in the process of determining the path planning result, which reduces the amount of data calculation and improves the solution efficiency of path planning problems, thus improving the applicability of online scenarios.
  • FIG. 7 shows a process 700 of another embodiment of a path planning method.
  • the process 700 of the path planning method includes the following steps:
  • Step 701 Obtain an unprocessed waybill of the target capacity.
  • step 701 in this embodiment reference may be made to step 101 in the embodiment corresponding to FIG. 1, which will not be repeated here.
  • step 702 the waybill with the delivery location to be visited is taken as the first type of waybill, and the waybill with the place to be visited including the pick-up location and the delivery location is taken as the second type of waybill, and the first type of waybill and the second type of waybill are sorted respectively .
  • the execution subject of the route planning method may regard the waybill whose destination to be visited is the delivery location as the first type of waybill, and the waybill whose location to be visited includes the pick-up location and the delivery location as the second type of waybill.
  • the first type of waybill and the second type of waybill are sorted.
  • One or more methods can be used for sorting here.
  • the first type of waybill and the second type of waybill can be sorted according to the order of the target delivery time of the delivery location.
  • the waybills can be sorted according to the order of importance of the delivery objects of the waybill, so that the waybills of important users are sorted first, and the waybills of non-important users are sorted back.
  • the waybills can be sorted in descending order of urgency.
  • the destination arrival time of the delivery location is also recorded in the waybill.
  • the above-mentioned execution subject can sort all types of waybills (including the first type of waybill and the second type of waybill) according to the first sorting method and the second sorting method, respectively.
  • the above-mentioned first sorting method is a sorting method according to the order of the target delivery time of the delivery location from first to last.
  • the above-mentioned second sorting method is a method of sorting the waybills in descending order of urgency.
  • the above-mentioned urgency is determined based on the location of the target capacity, the current time, and the target arrival time of the delivery location. For example, it can be determined by referring to the method described in step 102 in the corresponding embodiment in FIG. 1, and details are not described herein again.
  • Step 703 Set the sorted first-type waybill before the sorted second-type waybill to obtain the sorting order of the waybill.
  • the above-mentioned execution subject may set the sorted first-type waybill before the sorted second-type waybill to obtain the sort order of each waybill.
  • the first type of waybills in the sorting mode may be set for each sorting mode.
  • the sorting order of each waybill under various sorting methods is obtained.
  • the first sorting method can be sorted according to the above-mentioned first sorting method.
  • the first type of waybill is set before the second type of waybills sorted according to the above-mentioned first sorting method, and the first sorting order of each waybill is obtained;
  • the second sort order of each waybill is obtained before the second type of waybill after sorting.
  • Step 704 Perform path planning on the locations to be visited in each waybill according to the sorting order of the waybills to obtain a sequence of locations to be visited.
  • the above-mentioned execution subject may plan the route of the places to be visited in each waybill according to the order of the waybills to obtain the sequence of the places to be visited.
  • step 102 refers to step 102, which will not be repeated here.
  • the sorting order of each waybill in various sorting modes can be obtained.
  • route planning can be performed on the locations to be visited in each waybill according to the sorting order of the waybills sorted by the sorting method to obtain at least two sequence of locations to be visited. Then, the optimal sequence of places to be visited can be selected from it.
  • the first sorting order and the second sorting order of each waybill can be obtained order.
  • the objective function and constraint conditions of the path planning can be obtained first.
  • path planning may be performed on the locations to be visited in each waybill according to the first sort order of each waybill to obtain the first sequence of locations to be visited.
  • the objective function can be used to minimize the delivery timeout period and delivery distance.
  • the above constraint conditions may include, but are not limited to: the access time of the pick-up location is later than the item shipment time, and the access time of the pick-up location of the same waybill is earlier than the visit time of the delivery location.
  • path planning can be performed on the locations to be visited in each waybill according to the second sort order of the waybill to obtain the second sequence of locations to be visited.
  • the objective function value corresponding to each sequence of locations to be visited one of the sequence of locations to be visited can be selected. For example, if the objective function is used to minimize the delivery timeout period and the delivery distance, the smaller the objective function value, the better the sequence of locations to be visited, so a sequence of locations to be visited with a smaller value of the objective function can be selected.
  • Sorting through multiple sorting methods, and respectively determining the sequence of locations to be visited corresponding to various sorting methods, so as to select the optimal sequence of locations to be visited, which can improve the quality of path planning.
  • Step 705 Use the sequence of places to be visited as the initial sequence.
  • Step 706 Randomly remove part of the places to be visited from the initial sequence to obtain the remaining sequence.
  • Step 707 Re-insert the removed site to be visited into the remaining sequence to obtain a recombined sequence.
  • Step 708 Partially adjust the recombination sequence to obtain the target sequence.
  • step 709 when the preset end condition is met, a path planning result is generated based on the target sequence.
  • steps 705 to 709 in this embodiment reference may be made to steps 103 to 107 in the embodiment corresponding to FIG. 1, which will not be repeated here.
  • the process 700 of the route planning method in this embodiment involves dividing order categories, and sorting orders that do not contain pick-up locations to those containing pick-up locations
  • this application provides an embodiment of a path planning device, which can be specifically applied to various electronic devices.
  • the path planning device 800 of this embodiment includes: an obtaining unit 801 configured to obtain an unprocessed waybill with a target capacity, and the location to be visited is recorded in the waybill; a path planning unit 802 is configured to The above-mentioned waybills are sorted, and route planning is performed on the places to be visited in the waybill according to the order of the waybills to obtain the sequence of places to be visited; the path adjustment unit 803 is configured to take the above-mentioned sequence of places to be visited as the initial sequence and execute the following path Adjustment steps: randomly remove part of the locations to be visited from the initial sequence to obtain the remaining sequence; insert the removed locations to be visited into the remaining sequence to obtain the recombination sequence; locally adjust the recombination sequence to obtain the target sequence; When the preset end condition is met, the path planning result is generated based on the above-mentioned target sequence.
  • the above process of obtaining the initial sequence can obtain a feasible solution to the initial path planning problem, the process of reorganizing the initial sequence can achieve a rough search for the optimal solution, and the process of partially adjusting the reorganization sequence can achieve a fine search for the optimal solution.
  • the path planning results obtained in the process of rough search and fine search compared with the direct calculation in the prior art method of calculating the optimal solution based on a large amount of data, can effectively obtain the path planning results, avoiding the optimal solution Failure situation.
  • the local optimal solution is used in the process of determining the path planning result, which reduces the amount of data calculation and improves the solution efficiency of path planning problems, thus improving the applicability of online scenarios.
  • the foregoing device further includes: an execution unit configured to: when the foregoing preset end condition is not met, use the foregoing target sequence as an initial sequence to continue to perform the foregoing path adjustment step.
  • the above-mentioned path planning unit 802 is further configured to: regard the waybill whose location to be visited is the delivery location as the first type of waybill, and include the location to be visited including the pick-up location and the delivery location.
  • As the second type of waybill sort the above-mentioned first type of waybill and the above-mentioned second type of waybill respectively; set the sorted first type of waybill before the sorted second type of waybill to get the sort order of the waybill.
  • the above-mentioned waybill also records the target arrival time of the delivery location; and, the above-mentioned path planning unit 802 is further configured to: according to the first sorting mode and the second sorting mode, respectively Sort all types of waybills, where the first sorting method is sorting according to the target delivery time of the delivery location from first to last, and the second sorting method is sorting according to the urgency of the waybill in ascending order
  • the way of sorting in order, the above-mentioned degree of urgency is determined based on the location of the target capacity, the current time, and the target arrival time of the delivery location.
  • Sorting through multiple sorting methods, respectively determining the sequence of locations to be visited corresponding to various sorting methods, so as to select the optimal sequence of locations to be visited, which can improve the quality of path planning.
  • the above-mentioned path planning unit 802 is further configured to: set the first type of waybills sorted according to the above-mentioned first sorting method to the first type of waybills sorted according to the above-mentioned first sorting method. Before the second type of waybill, get the first sort order of the waybill; set the first type of waybill sorted according to the above second sorting method before the second type of waybill sorted according to the above second sorting way, and get the second sorting of the waybill order.
  • the aforementioned path planning unit 802 is further configured to: obtain an objective function and constraint conditions for path planning; Path planning is performed on the locations to be visited in, to obtain the first sequence of locations to be visited; based on the above objective function and the above constraints, path planning is performed on the locations to be visited in the waybill according to the second sort order of the waybill to obtain the second location to be visited Sequence: Based on the objective function value corresponding to each sequence of locations to be visited, select one of the sequence of locations to be visited.
  • Sorting through multiple sorting methods, respectively determining the sequence of locations to be visited corresponding to various sorting methods, so as to select the optimal sequence of locations to be visited, which can improve the quality of path planning.
  • the above objective function is used to minimize the delivery timeout period and the delivery distance
  • the above constraints include: the access time of the pick-up location is later than the delivery time of the item, and the pick-up of the same waybill The visit time of the location is earlier than the visit time of the delivery location.
  • the path adjustment unit 803 is further configured to: determine the target quantity based on the total number of locations to be visited; randomly select the consignment note of the target quantity and move it from the initial sequence. Except the locations to be visited in the randomly selected waybill.
  • the number of removed locations to be visited is related to the total number of locations to be visited. Since the total number of locations to be visited can represent the scale of the path planning problem, the number of removed locations to be visited is related to the scale of the path planning problem, and the rationality of the number of reorganized locations to be visited can be ensured.
  • the above-mentioned path adjustment unit 803 is further configured to: summarize the removed locations to be visited into a removal sequence; obtain the objective function and constraint conditions of the path planning; To remove the locations to be visited in the above sequence, perform the following steps: insert the retrieved locations to be visited into each feasible position in the remaining sequence, and determine the objective function value when inserting to each feasible position, the above feasible position is The position that satisfies the above constraint conditions; the feasible position when the objective function value is the smallest is taken as the target position, and the retrieved location to be visited is inserted into the above-mentioned target position in the above-mentioned remaining sequence; the place to be visited in the above-mentioned removal sequence is inserted The remaining sequence of is determined as the recombination sequence.
  • the location to be visited in the above-mentioned waybill includes a delivery location, and the above-mentioned waybill records the target arrival time of the delivery location; and the above-mentioned path adjustment unit 803 is further configured to:
  • the above reorganization sequence determines the estimated arrival time of the delivery location of the above-mentioned waybill; confirms the early delivery of the waybill, and adds the first mark to the above-mentioned early delivery waybill, the above-mentioned early-delivered waybill means that the estimated arrival time of the delivery location is earlier than the target
  • the air waybill of the arrival time perform the following first partial adjustment step: from the air waybill with the above first mark, select the air waybill with the largest difference between the target arrival time and the estimated arrival time as the first target air waybill.
  • the delivery location in a target air waybill serves as the first target delivery location; in response to the first target delivery location being not located at the end of the recombination sequence, move the first target delivery location back to the position of the recombination sequence, and delete the first target delivery location.
  • the first mark of the destination waybill It is detected whether there is a waybill with the above-mentioned first mark, and if there is, the above-mentioned first partial adjustment step is performed again.
  • the path adjustment unit 803 is further configured to: use the position of the first target delivery location in the recombination sequence as the first original position, and extract from the recombination sequence Remove the above-mentioned first target delivery location; obtain the objective function and constraint conditions of the path planning; insert the above-mentioned first target delivery location into each feasible position after the first original position in the recombination sequence, and determine the insertion to each The value of the objective function at a feasible position, where the feasible position is a position that satisfies the above constraint condition; the feasible position when the objective function value is the smallest is taken as the first update position, and the first target delivery location is inserted into the first update position.
  • the location to be visited in the waybill includes a delivery location, and the destination time of arrival of the delivery location is recorded in the waybill; and the above-mentioned path adjustment unit 803 is further configured to : Determine the estimated arrival time of the delivery location of the waybill based on the above recombination sequence; determine the delayed delivery waybill, and add a second mark to the delayed delivery waybill, the above-mentioned delayed delivery waybill is the estimated arrival at the delivery location A waybill whose time is later than the target arrival time; perform the following second partial adjustment step: from the waybill with the above second mark, select the waybill with the largest difference between the estimated arrival time and the target arrival time as the second target waybill, And take the delivery location in the second target waybill as the second target delivery location; in response to the second target delivery location not being located at the beginning of the recombination sequence, move the second target delivery location forward to the position of the recombination sequence, And delete the
  • each delayed delivery waybill By moving forward the location of the delivery location in each delayed delivery waybill to partially adjust the reorganization sequence, the delivery order of each delayed delivery waybill can be advanced, thereby avoiding delayed delivery of orders or reducing the timeout period of delayed delivery orders. As a result, the quality and rationality of the solution to the path planning problem can be further improved.
  • the above-mentioned path adjustment unit 803 is further configured to: use the position of the above-mentioned second target delivery location in the above-mentioned reorganization sequence as the second original position, and extract from the above-mentioned reorganization sequence Remove the above-mentioned second target distribution location; obtain the objective function and constraint conditions of the path planning; insert the above-mentioned second target distribution location into each feasible position before the above-mentioned second original position in the above-mentioned reorganization sequence, and confirm the insertion to each The value of the objective function at a feasible position, where the feasible position is a position that satisfies the above constraint condition; the feasible position when the objective function value is the smallest is used as the second update position, and the second target delivery location is inserted into the second update position.
  • the delivery order of the delayed delivery waybill can be advanced, but also the delivery address in the delayed delivery waybill can be adjusted to the most reasonable position, which further improves the quality and rationality of the solution to the path planning problem.
  • the location to be visited in the waybill includes a delivery location; and, the aforementioned route adjustment unit 803 is further configured to: add a third mark to the delivery location in the aforementioned reorganization sequence ; Perform the following third partial adjustment step: take any delivery location with the third mark in the reorganization sequence as the third target delivery location, and extract the third target delivery location from the reorganization sequence; obtain the path planning target Function and preset conditions; insert the above-mentioned third target delivery location into each feasible position in the above-mentioned reorganization sequence, and determine the value of the objective function when inserting into each feasible position, the above-mentioned feasible position is a position that satisfies the above-mentioned constraint condition; The feasible position when the objective function value is the smallest is used as the third update position, the third target delivery location is inserted into the third update position, and the third mark of the third target delivery location is deleted. It is detected whether there is a delivery location with the third mark
  • each delivery location in the recombination sequence can be taken as the third target delivery location one by one, and the recombination sequence can be taken out and reinserted. Therefore, more feasible solutions are further searched, and the optimal solution (that is, the sequence when the objective function value is the smallest) is selected among these feasible solutions, which can further improve the quality of the solution of the path planning problem.
  • the location to be visited in the above-mentioned waybill includes a delivery location; and, the aforementioned route adjustment unit 803 is further configured to: add a fourth mark to the delivery location in the aforementioned reorganization sequence; Perform the following fourth partial adjustment steps: obtain the objective function and constraint conditions of the path planning; take any delivery location with the fourth mark in the reorganization sequence as the fourth target delivery location, and set the fourth target delivery location to The remaining locations to be visited in the above reorganization sequence are exchanged to obtain the objective function value under each exchange mode, and determine whether each exchange mode meets the above constraint conditions; the exchange mode when the objective function value is the smallest and meets the above constraint conditions is taken as the target
  • the exchange method is to exchange the location of the fourth target delivery location in the target exchange method, and delete the fourth mark of the fourth target delivery location. It is detected whether there is a delivery location with the above-mentioned fourth mark in the above-mentioned recombination sequence, and if there is
  • each delivery location in the recombination sequence can be used as the fourth target delivery location one by one, and the quality of feasible solutions when exchanging with the remaining locations to be visited can be detected. Therefore, more feasible solutions are further searched, and the optimal solution (that is, the sequence when the objective function value is the smallest) is selected among these feasible solutions, which can further improve the quality of the solution of the path planning problem.
  • the path adjustment unit 803 is further configured to: use the time difference between the current time and the acquisition time of the air waybill of the target capacity as the processing time, and detect whether the processing time is greater than or equal to A preset threshold; in response to the processing time being greater than or equal to the preset threshold, it is determined that the preset end condition is satisfied, and the preset threshold is related to the total number of places to be visited; in response to the time difference being less than the preset threshold, it is determined that the foregoing is not satisfied Preset ending conditions.
  • the length of path planning and solving can be limited from time, and the applicability to online scenes is further improved.
  • the total number of locations to be visited can represent the scale of the path planning problem
  • setting the preset threshold to a number related to the scale of the path planning problem can ensure the rationality of the preset threshold.
  • FIG. 9 shows a schematic structural diagram of a computer system 900 suitable for implementing an electronic device according to an embodiment of the present application.
  • the electronic device shown in FIG. 9 is only an example, and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
  • the computer system 900 includes a central processing unit (CPU) 901, which can be based on a program stored in a read-only memory (ROM) 902 or a program loaded from a storage portion 908 into a random access memory (RAM) 903 And perform various appropriate actions and processing.
  • ROM read-only memory
  • RAM random access memory
  • various programs and data required for the operation of the system 900 are also stored.
  • the CPU 901, the ROM 902, and the RAM 903 are connected to each other through a bus 904.
  • An input/output (I/O) interface 905 is also connected to the bus 904.
  • the following components are connected to the I/O interface 905: an input section 906 including a keyboard, a mouse, etc.; an output section 907 including a liquid crystal display (LCD), etc., and speakers, etc.; a storage section 908 including a hard disk, etc.;
  • the communication section 909 performs communication processing via a network such as the Internet.
  • the drive 910 is also connected to the I/O interface 905 as needed.
  • a removable medium 911 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 910 as needed, so that the computer program read from it is installed into the storage portion 908 as needed.
  • the process described above with reference to the flowchart can be implemented as a computer software program.
  • the embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart.
  • the computer program may be downloaded and installed from the network through the communication part 909, and/or installed from the removable medium 911.
  • the central processing unit (CPU) 901 the above-mentioned functions defined in the method of the present application are executed.
  • the computer-readable medium described in this application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two.
  • the computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or a combination of any of the above. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable Programmable read only memory (EPROM or flash memory), optical fiber, portable compact disk read only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
  • a computer-readable storage medium may be any tangible medium that contains or stores a program, and the program may be used by or in combination with an instruction execution system, apparatus, or device.
  • a computer-readable signal medium may include a data signal propagated in a baseband or as a part of a carrier wave, and a computer-readable program code is carried therein.
  • This propagated data signal can take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • the computer-readable signal medium may also be any computer-readable medium other than the computer-readable storage medium.
  • the computer-readable medium may send, propagate or transmit the program for use by or in combination with the instruction execution system, apparatus, or device .
  • the program code contained on the computer-readable medium can be transmitted by any suitable medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.
  • each block in the flowchart or block diagram can represent a module, program segment, or part of code, and the module, program segment, or part of code contains one or more for realizing the specified logic function.
  • Executable instructions can also occur in a different order from the order marked in the drawings. For example, two blocks shown one after the other can actually be executed substantially in parallel, or they can sometimes be executed in the reverse order, depending on the functions involved.
  • each block in the block diagram and/or flowchart, and the combination of the blocks in the block diagram and/or flowchart can be implemented by a dedicated hardware-based system that performs the specified functions or operations Or it can be realized by a combination of dedicated hardware and computer instructions.
  • the units involved in the embodiments described in this application can be implemented in software or hardware.
  • the described units can also be arranged in the processor, where the names of these units do not constitute a limitation on the unit itself under certain circumstances.
  • the present application also provides a computer-readable medium, which may be included in the device described in the above embodiment; or it may exist alone without being assembled into the device.
  • the above-mentioned computer-readable medium carries one or more programs.
  • the device obtains the unprocessed waybill of the target capacity, and records the location to be visited in the waybill; sorts the waybill , And perform path planning on the locations to be visited in the waybill according to the sorting order of the waybill to obtain the sequence of the locations to be visited; take the sequence of the locations to be visited as the initial sequence, and randomly remove part of the locations to be visited from the initial sequence to obtain the remaining sequence; The removed location to be visited is reinserted into the remaining sequence to obtain a recombination sequence; the recombination sequence is partially adjusted to obtain the target sequence; in the case that the preset end condition is met, a path planning result is generated based on the target sequence.

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Economics (AREA)
  • Automation & Control Theory (AREA)
  • Development Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

一种路径规划方法，包括：获取目标运力未处理完成的运单（101），运单中记录有待访问地点；对运单进行排序，按照运单的排序顺序对运单中的待访问地点进行路径规划，得到待访问地点序列（102）；将待访问地点序列作为初始序列（103），随机从初始序列中移除部分待访问地点，得到剩余序列（104）；将所移除的待访问地点重新插入至剩余序列，得到重组序列（105）；局部调整重组序列，得到目标序列（106）；在满足预设结束条件时，基于目标序列生成路径规划结果（107）。

Description

路径规划
本申请要求在2020年6月16日提交中国专利局、申请号为202010550940.3、发明名称为“路径规划方法、装置、电子设备和计算机可读介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请实施例涉及计算机技术领域，具体涉及路径规划。
背景技术
随着互联网技术的快速发展，即时配送服务逐渐成为现代生活中不可或缺的一部分。在配送过程中，服务平台需要为配送运力进行路径规划，以便于为配送运力提供更为合理的取物、配送路线和顺序，从而降低物品送达延时的情况发生。
发明内容
本申请实施例提出了路径规划方法、装置、电子设备和计算机可读介质，以解决现有技术由于求解过程缓慢导致线上场景不适用的技术问题以及无法生成路径规划结果的技术问题。
第一方面，本申请实施例提供了一种路径规划方法，该方法包括：获取目标运力未处理完成的运单，其中，运单中记录有待访问地点；对运单进行排序，按照运单的排序顺序对运单中的待访问地点进行路径规划，得到待访问地点序列；将待访问地点序列作为初始序列，执行如下路径调整步骤：随机从初始序列中移除部分待访问地点，得到剩余序列；将所移除的待访问地点重新插入至剩余序列，得到重组序列；局部调整重组序列，得到目标序列；在满足预设结束条件的情况下，基于目标序列生成路径规划结果。
第二方面，本申请实施例提供了一种路径规划装置，该装置包括：获取单元，被配置成获取目标运力未处理完成的运单，运单中记录有待访问地点；路径规划单元，被配置成对运单进行排序，按照运单的排序顺序对运单中的待访问地点进行路径规划，得到待访问地点序列；路径调整单元，被配置成将待访问地点序列作为初始序列，执行如下路径调整步骤：随机从初始序列中移除部分待访问地点，得到剩余序列；将所移除的待访问地点重新插入至剩余序列，得到重组序列；局部调整重组序列，得到目标序列；在满足预设结束条件的情况下，基于目标序列生成路径规划结果。
第三方面，本申请实施例提供了一种电子设备，包括：一个或多个处理器；存储装置，其上存储有一个或多个程序，当一个或多个程序被一个或多个处理器执行，使得一个或多个处理器实现如第一方面中所描述的方法。
第四方面，本申请实施例提供了一种计算机可读介质，其上存储有计算机程序，该程序被处理器执行时实现如第一方面中所描述的方法。
本申请实施例提供的路径规划方法、装置、电子设备和计算机可读介质，通过 对所获取的目标运力未处理完成的运单进行排序，并按照排序顺序对运单中的待访问地点进行路径规划，从而得到待访问地点序列；而后将该待访问地点序列作为初始序列，随机从初始序列中移除部分待访问地点，并将所移除的待访问地点重新插入至剩余序列，从而得到重组序列；之后局部调整重组序列，得到目标序列；最后在满足预设结束条件时，基于目标序列生成路径规划结果。上述得到初始序列的过程可得到初始的路径规划问题的可行解，对初始序列重组的过程可实现对最优解的粗略搜索，局部调整重组序列的过程可实现最优解的精细搜索，经过初始化、粗略搜索、精细搜索的过程所得到的路径规划结果，相较于现有技术中直接计算根据大量数据整体计算最优解的方式，能够有效获取到路径规划结果，避免了最优解求取失败的情况。同时，确定路径规划结果的过程中采用局部最优解，降低了数据的计算量，提高了路径规划问题的求解效率，因而提高了在线场景的适用性。
附图说明
通过阅读参照以下附图所作的对非限制性实施例所作的详细描述，本申请的其它特征、目的和优点将会变得更明显：
图1是根据本申请的路径规划方法的一个实施例的流程图；
图2是根据本申请的重组序列生成步骤的分解流程图；
图3是根据本申请的局部调整重组序列的一个实现方式的流程图；
图4是根据本申请的局部调整重组序列的又一个实现方式的流程图；
图5是根据本申请的局部调整重组序列的又一个实现方式的流程图；
图6是根据本申请的局部调整重组序列的又一个实现方式的流程图；
图7是根据本申请的路径规划方法的又一个实施例的流程图；
图8是根据本申请的路径规划装置的一个实施例的结构示意图；
图9是适于用来实现本申请实施例的电子设备的计算机系统的结构示意图。
具体实施例
下面结合附图和实施例对本申请作进一步的详细说明。可以理解的是，此处所描述的具体实施例仅仅用于解释相关发明，而非对该发明的限定。另外还需要说明的是，为了便于描述，附图中仅示出了与有关发明相关的部分。
需要说明的是，在不冲突的情况下，本申请中的实施例及实施例中的特征可以相互组合。下面将参考附图并结合实施例来详细说明本申请。
请参考图1，其示出了根据本申请的路径规划方法的一个实施例的流程100。路径规划方法的执行主体可以是服务器。服务器可以是硬件，也可以是软件。当服务器为硬件时，可以实现成多个设备组成的分布式设备集群，也可以实现成单个设备。当服务器为软件时，可以实现成多个软件或软件模块，也可以实现成单个软件或软件模块。在此不做具体限定。
此外，在终端设备具有实现本申请的信息获取方法的能力时，路径规划方法的执行主体也可以是终端设备。上述终端设备可以是如手机、智能手机、平板电脑、膝上型便携计算机、可穿戴设备等的电子设备。
该路径规划方法，包括以下步骤：
步骤101，获取目标运力未处理完成的运单。
在本实施例中，路径规划方法的执行主体可以获取目标运力未处理完成的运单。其中，所获取的各运单中可以记录有待访问地点。上述待访问地点可以包括配送地点。配送地点可以指目标运力将物品(如快递、餐品)等送达的目的地，如用户指定的地点、配送柜等。对于餐品等类别的运单以及尚未取物的运单，待访问地点除包括配送地点外，还可以包括取物地点，如取餐门店、取餐柜等。
实践中，目标运力可以是各种类型的配送运力。例如，可以包括但不限于：配送人员、配送机器人、无人机、无人车等。配送运力在配送过程中，可以实时地或者周期性地采集待测无线网信息列表，并将所采集的待测无线网信息列表发送给上述执行主体。
步骤102，对运单进行排序，并按照运单的排序顺序对运单中的待访问地点进行路径规划，得到待访问地点序列。
在本实施例中，上述执行主体可以按照多种排序方式对各运单进行排序，从而得到各运单的排序结果。
作为一个示例，各运单中可以记录有配送地点的目标到达时间。上述执行主体可以按照配送地点的目标送达时间由先到后的顺序，对各运单进行排序。
作为又一示例，上述执行主体可以按照运单配送对象的重要程度由高到底的顺序，对各运单进行排序，以将重要用户的运单排序在前，将非重要用户的运单排序在后。
作为再一示例，上述执行主体可以按照运单的紧迫程度由大到小的顺序，对各运单进行排序。此处的紧迫程度可以基于目标运力的位置、当前时间以及配送地点的目标到达时间确定。例如，可参考如下公式确定运单的紧迫程度：
Figure PCTCN2021084071-appb-000001
其中，其中δ i为用于表征运单i的紧迫程度的数值，d i为订单i中的配送地点与目标运力的位置的距离，ETA i为运单i的配送地点的目标到达时间，ct为当前时间。
需要说明的是，还可以基于其他排序方式对各运单，本实施例对具体的排序方式不作限定。
在本实施例中，在得到各运单的排序顺序之后，上述执行主体可以按照各运单的排序顺序对各运单中的待访问地点进行路径规划，得到待访问地点序列。具体可按照如下步骤执行：
首先，可以按照排序顺序取出第一个运单。由于在只有一个待访问地点时，不存在路径规划问题，因而可直接将该待访问地点作为第一待访问地点进行记录。
而后，可以按照排序顺序取出第二个运单，并将第二个运单中的待访问地点作为第二待访问地点。由于第二待访问地点可以位于第一待访问地点之前或之后，因而可以分别确定第二待访问地点在第一待访问地点之前和之后这两种情况下是否满足预设的约束条件。若只有一种情况满足约束条件，则可以将该情况下的第一待访问地点与第二待访问地点的顺序进行记录。若这两种情况均满足约束条件，则可以 确定这两种情况下的目标函数值，并基于目标函数值，选取其中一种情况下的第一待访问地点与第二待访问地点的顺序进行记录。
对于后续运单，可参照第二个运单的处理方式，依次对后续各运单中的待访问地点的位置进行插入，从而得到最终的待访问地点的顺序，按照该顺序可生成待访问地点序列。
需要说明的是，由于餐品等类别的运单以及尚未取物的运单，待访问地点除包括配送地点外，还包括取物地点，因而，对待访问地点进行排序可以指对待访问地点中的各项(包括取物地点和配送地点)进行排序。例如，若第一个运单和第二个运单均未取货，则第一待访问地点包括第一个运单所记录的待访问地点包括第一取物地点(可记为A1)和第一配送地点(可记为B1)，第二个运单所记录的待访问地点包括第二取物地点(可记为A2)和配送地点(可记为B2)。取出第一个运单后，可得到序列A1-B1。取出第二个运单后，由于同一运单的取物地点的访问时间早于配送地点的访问时间，因而有如下几种排序方式：A2-B2-A1-B1、A2-A1-B2-B1、A2-A1-B1-B2、A1-A2-B2-B1、A1-A2-B1-B2、A1-B1-A2-B2共6种排序方式。若这6中排序方式均满足预设的约束条件，则可以确定这6中排序方式下的目标函数值，并基于目标函数值，选取其中一种最优的排序方式进行记录。
需要指出的是，约束条件可以是用于对待访问地点的顺序进行约束的条件。可选的，约束条件可以包括但不限于：取物地点的访问时间晚于物品出货时间、同一运单的取物地点的访问时间早于配送地点的访问时间等。目标函数值为预设的目标函数的值。目标函数可用于表征路径规划的目标。可选的，目标函数可以用于表征最小化配送超时时长、最小化配送距离、或者同时最小化配送超时时长以及配送距离等。作为示例，可以采用如下函数式作为目标函数：
Figure PCTCN2021084071-appb-000002
其中，其中t i是运单i中的配送地点的目标到达时间。T i是运单i中的配送地点的预估到达时间，即预估出的目标运力到达配送地点的时间。d i为目标运力处理完成订单i所行驶的距离。
通过按照运单的排序顺序对各运单中的待访问地点进行路径规划，得到待访问地点序列，从而可以初始化一个动态规划结果，即得到一个路径规划问题的初始的可行解。由于该可行解按照运单的排序顺序逐次进行路径规划得到，因而采用了贪心策略。相较于随机初始化得到可行解的方式，提高了初始的可行解的有效性和合理性。
步骤103，将待访问地点序列作为初始序列。
在本实施例中，上述执行主体可以将待访问地点序列作为初始序列，执行包含如下步骤104至步骤107的路径调整步骤。
步骤104，随机从初始序列中移除部分待访问地点，得到剩余序列。
在本实施例中，上述执行主体可以随机从初始序列中移除部分待访问地点，并将移除上述部分待访问地点后的初始序列作为剩余序列。例如，可以移除固定数量的部分待访问地点，也可以按照与待访问地点的总数相关的数量的部分待访问地点。
在本实施例的一些可选的实现方式中，上述执行主体可以基于待访问地点的总数，确定目标数量。该目标数量记为待移除其待访问地点的运单的数量。例如，待访问地点的总数记为n，则目标数量可以为n/2。而后，可以随机选取目标数量(即n/2)的运单，并从上述初始序列中移除所随机选取的运单中的待访问地点。
由此，移除的待访问地点的数量与待访问地点的总数相关。由于待访问地点的总数可表征路径规划问题的规模，因而移除的待访问地点的数量与路径规划问题的规模相关，可保证重组的待访问地点的数量的合理性。
步骤105，将所移除的待访问地点重新插入至剩余序列，得到重组序列。
在本实施例中，上述执行主体可以将所移除的各待访问地点重新插入至剩余序列，得到重组序列。实践中，可以以重组序列的目标函数值优于(如小于)初始序列的目标函数值且重组序列满足预设的约束条件为原则，对所移除的各待访问地点进行重新插入。
在本实施例的一些可选的实现方式中，请参见图2所示的重组序列生成步骤的分解流程图。如图2所示，上述执行主体可以按照如下子步骤S11至子步骤S14得到重组序列：
子步骤S11，将所移除的待访问地点汇总为移除序列(可记为π R)。
子步骤S12，获取路径规划的目标函数和约束条件。目标函数和约束条件可参见步骤102中的描述，此处不再赘述。
子步骤S13，逐一取出上述移除序列中的待访问地点，执行如下步骤：
首先，将所取出的待访问地点分别插入至剩余序列(可记为π D)中的各可行位置，并确定插入至各可行位置时的目标函数值。其中，可行位置为满足约束条件的位置。
而后，将目标函数值最小时的可行位置作为目标位置，将所取出的待访问地点插入至剩余序列中的目标位置。
由此，可将π R中的各待访问地点一一插入π D中的每个可行的位置，从而从中选择最优的进行放置，直到π R中不存在任何待访问地点。
子步骤S14，将插入有移除序列中的待访问地点的剩余序列，确定为重组序列。
通过将随机取出的待访问地点重新插入至剩余序列得到重组序列，实现了对路径规划的解的粗略搜索。此过程中由于采用逐一插入方式进行序列重组，因而采用了基于贪心策略的求解方式。相较于现有技术中直接确定整体最优解的方式，提高了路径规划问题的求解效率，提高了在线场景的适用性。同时，够有效获取到路径规划结果，避免了最优解求取失败的情况。相较于直接使用初始序列，可提高提升解的质量。
步骤106，局部调整重组序列，得到目标序列。
在本实施例中，上述执行主体可以局部调整重组序列，得到目标序列。实践中，可以采用一种或多种方式对重组序列进行局部调整。
在本实施例的一些可选的实现方式中，运单中的待访问地点包括配送地点，运单中记录有配送地点的目标到达时间。如图3所示，上述执行主体可以按照如下子步骤S21至子步骤S24局部调整重组序列：
子步骤S21，基于重组序列，确定运单的配送地点的预估到达时间。
实践中，基于重组序列可确定各待访问地点的访问顺序，基于各待访问地点的该访问顺序、目标运力的位置、目标运力与各待访问地点的距离和路况等信息，可预估出目标运力到达各运单的配送地点的预估到达时间。预估到达时间的过程可以采用现有的方式进行，此处不再赘述。
子步骤S22，确定提前送达运单，并为各提前送达运单添加第一标记，提前送达运单为配送地点的预估到达时间早于目标到达时间的运单。
子步骤S23，执行如下第一局部调整步骤：
首先，从带有第一标记的运单中，选取目标到达时间与预估到达时间的差值最大的运单，作为第一目标运单，并将第一目标运单中的配送地点作为第一目标配送地点。
而后，响应于第一目标配送地点不位于重组序列的末端，后移第一目标配送地点在重组序列的位置，并删除第一目标运单的第一标记。后移第一目标配送地点在重组序列的位置，可以将提前送达运单更改为稍晚送达，从而使更紧急的运单更早处理，由此，可以进一步提高路径规划问题的解的质量和合理性。
可选的，可以按照如下步骤调整第一目标配送地点在重组序列的位置：第一步，将第一目标配送地点在重组序列中的位置作为第一原始位置，并从重组序列中移除第一目标配送地点。第二步，获取路径规划的目标函数和约束条件。第三步，将第一目标配送地点分别插入至重组序列中的第一原始位置之后的各可行位置，并确定插入至各可行位置时的目标函数值，可行位置为满足约束条件的位置。此处所使用的目标函数和约束条件可参见步骤102中的描述，此处不再赘述。第四步，将目标函数值最小时的可行位置作为第一更新位置，将第一目标配送地点插入至第一更新位置。
由此，不仅可以将提前送达运单更改为稍晚送达，使更紧急的运单更早处理，还能够可以将提前送达运单中的配送地址调整至最为合理的位置，进一步提高路径规划问题的解的质量和合理性。
需要说明的是，响应于第一目标配送地点位于重组序列的末端，可以直接执行子步骤S24。
子步骤S24，检测是否存在带有第一标记的运单，若存在，重新执行第一局部调整步骤。
通过后移各个延迟送达运单中的配送地点的位置来局部调整重组序列，可将各个提前送达运单的配送次序后移，从而能够使更紧急的运单优先处理。由此，可以进一步提高路径规划问题的解的质量和合理性。
在本实施例的一些可选的实现方式中，运单中的待访问地点包括配送地点，运单中记录有配送地点的目标到达时间。如图4所示，上述执行主体可以按照如下子步骤S31至子步骤S34局部调整重组序列：
子步骤S31，基于重组序列，确定运单的配送地点的预估到达时间。
子步骤S32，确定延迟送达运单，并为各延迟送达运单添加第二标记，延迟送达运单为配送地点的预估到达时间晚于目标到达时间的运单。
子步骤S33，执行如下第二局部调整步骤：
首先，从带有第二标记的运单中，选取预估到达时间与目标到达时间的差值最大的运单，作为第二目标运单，并将第二目标运单中的配送地点作为第二目标配送地点。
之后，响应于第二目标配送地点不位于重组序列的首端，前移第二目标配送地点在重组序列的位置，并删除第二目标运单的第二标记。前移第二目标配送地点在重组序列的位置，可将各个延迟送达运单的配送次序提前，从而能够避免订单延迟送达或降低延迟送达订单的超时时间，由此，可以进一步提高路径规划问题的解的质量和合理性。
可选的，可以按照如下步骤调整第二目标配送地点在重组序列的位置：第一步，将第二目标配送地点在重组序列中的位置作为第二原始位置，并从重组序列中移除第二目标配送地点。第二步，获取路径规划的目标函数和约束条件。第三步，将第二目标配送地点分别插入至重组序列中的第二原始位置之前的各可行位置，并确定插入至各可行位置时的目标函数值，可行位置为满足约束条件的位置。此处所使用的目标函数和约束条件可参见步骤102中的描述，此处不再赘述。第四步，将目标函数值最小时的可行位置作为第二更新位置，将第二目标配送地点插入至第二更新位置。
由此，不仅可以将延迟送达运单的配送次序提前，还能够可以将延迟送达运单中的配送地址调整至最为合理的位置，进一步提高路径规划问题的解的质量和合理性。
需要说明的是，响应于第二目标配送地点位于重组序列的首端，可以直接执行子步骤S34。
子步骤S34，检测是否存在带有第二标记的运单，若存在，重新执行第二局部调整步骤。
通过前移各个延迟送达运单中的配送地点的位置来局部调整重组序列，可将各个延迟送达运单的配送次序提前，从而能够避免订单延迟送达或降低延迟送达订单的超时时间。由此，可以进一步提高路径规划问题的解的质量和合理性。
在本实施例的一些可选的实现方式中，运单中的待访问地点包括配送地点。如图5所示，上述执行主体可以按照如下子步骤S41至子步骤S43局部调整重组序列：
子步骤S41，为重组序列中的各配送地点添加第三标记。
子步骤S42，执行如下第三局部调整步骤：
首先，将重组序列中的任一带有第三标记的配送地点作为第三目标配送地点，从重组序列中取出第三目标配送地点。
之后，获取路径规划的目标函数和预设条件。
之后，将第三目标配送地点分别插入至重组序列中的各可行位置，并确定插入至各可行位置时的目标函数值，可行位置为满足约束条件的位置。
最后，将目标函数值最小时的可行位置作为第三更新位置，将第三目标配送地点插入至第三更新位置，并删除第三目标配送地点的第三标记。
子步骤S43，检测重组序列中是否存在带有第三标记的配送地点，若存在，重新 执行第三局部调整步骤。
由此，可逐一地将重组序列中的各配送地点作为第三目标配送地点，从重组序列中取出并重新插入。从而，进一步搜索了更多的可行解，在这些可行解中选择最优的解(即目标函数值最小时的序列)，可进一步提高提高路径规划问题的解的质量。
在本实施例的一些可选的实现方式中，运单中的待访问地点包括配送地点。如图6所示，上述执行主体可以按照如下子步骤S51至子步骤S53局部调整重组序列：
子步骤S51，为重组序列中的配送地点添加第四标记。
子步骤S52，执行如下第四局部调整步骤：
首先，获取路径规划的目标函数和约束条件。
之后，将重组序列中的任一带有第四标记的配送地点作为第四目标配送地点，将第四目标配送地点分别与重组序列中的各其余待访问地点进行交换，得到各交换方式下的目标函数值，并确定各交换方式是否满足约束条件。
最后，将目标函数值最小且满足约束条件时的交换方式作为目标交换方式，以目标交换方式对第四目标配送地点进行位置交换，并删除第四目标配送地点的第四标记。
子步骤S53，检测重组序列中是否存在带有第四标记的配送地点，若存在，重新执行第四局部调整步骤。
由此，可逐一地将重组序列中的各配送地点作为第四目标配送地点，检测与其余各待访问地点进行交换时的可行解质量。从而，进一步搜索了更多的可行解，在这些可行解中选择最优的解(即目标函数值最小时的序列)，可进一步提高提高路径规划问题的解的质量。
需要说明的是，上述执行主体还可以依次采用上述各种可选的实现方式进行重组序列的局部调整，得到目标序列；也可以对采用上述可选的实现方式进行任意组合，对重组序列的局部调整，得到目标序列；还可以采用其他方式进行重组序列的局部调整，得到目标序列。
步骤107，在满足预设结束条件的情况下，基于目标序列生成路径规划结果。
在本实施例中，上述执行主体可以首先检测是否满足预设结束条件。上述预设结束条件可以指路径规划求解结束的条件。此处的预设结束条件可以根据需要预先设定。例如，可以设定为路径调整步骤的迭代执行次序大于或等于预设数值、处理时间大于或等于预设阈值等。
在本实施例中，响应于满足预设结束条件，上述执行主体可以基于目标序列生成路径规划结果。此处的路径规划结果可以包括目标序列中的各待访问位置到访问次序、路线等信息，从而便于目标运力基于该路径规划结果进行运单的处理，如取物、配送等。
需要说明的是，响应于检测出不满足上述预设结束条件，上述执行主体可以将步骤107所得到的目标序列作为初始序列，继续执行上述路径调整步骤，直至满足预设结束条件。由此，可以在未满足预设结束条件时，迭代执行多次路径调整步骤。由于执行此处越多，最终的路径规划结果越优，因而可平衡路径规划结果的质量和路径规划的耗时。
在本实施例的一些可选的实现方式中，上述执行主体可以通过如下步骤检测处理时长是否满足预设结束条件：首先，将当前时间与目标运力的运单的获取时间的时间差作为处理时长，检测处理时长是否大于或等于预设阈值。响应于处理时长大于或等于预设阈值，可以确定满足预设结束条件；响应于时间差小于预设阈值，可以确定不满足预设结束条件。由此，可从时间中限制路径规划求解的时长，进一步提高对线上场景的适用性。
此处，预设阈值可以与待访问地点的总数相关。例如，若待访问地点的总数为n，则预设阈值可以是2n毫秒或者n 2毫秒等。由于待访问地点的总数可表征路径规划问题的规模，因而将预设阈值设置为与路径规划问题的规模相关的数，可保证预设阈值的合理性。
在本实施例的一些可选的实现方式中，在生成路径规划结果后，上述执行主体还可以将该路径规划结果返回给目标运力，从而便于目标运力按照该路径规划结果进行配送或取货。此外，在生成路径规划结果后，上述执行主体还应用该路径规划结果为目标运力分配订单等，本实施例对该路径规划结果的应用不作限定。
本申请的上述实施例提供的方法，通过对所获取的目标运力未处理完成的运单进行排序，并按照排序顺序对运单中的待访问地点进行路径规划，从而得到待访问地点序列；而后将该待访问地点序列作为初始序列，随机从初始序列中移除部分待访问地点，并将所移除的待访问地点重新插入至剩余序列，从而得到重组序列；之后局部调整重组序列，得到目标序列；最后在满足预设结束条件时，基于目标序列生成路径规划结果。上述得到初始序列的过程可得到初始的路径规划问题的可行解，对初始序列重组的过程可实现对最优解的粗略搜索，局部调整重组序列的过程可实现最优解的精细搜索，经过初始化、粗略搜索、精细搜索的过程所得到的路径规划结果，相较于现有技术中直接计算根据大量数据整体计算最优解的方式，能够有效获取到路径规划结果，避免了最优解求取失败的情况。同时，确定路径规划结果的过程中采用局部最优解，降低了数据的计算量，提高了路径规划问题的求解效率，因而提高了在线场景的适用性。
进一步参考图7，其示出了路径规划方法的又一个实施例的流程700。该路径规划方法的流程700，包括以下步骤：
步骤701，获取目标运力未处理完成的运单。
本实施例的步骤701可参见图1对应实施例的步骤101，此处不再赘述。
步骤702，将待访问地点为配送地点的运单作为第一类运单，将待访问地点包括取物地点和配送地点的运单作为第二类运单，分别对第一类运单和第二类运单进行排序。
在本实施例中，路径规划方法的执行主体可以将待访问地点为配送地点的运单作为第一类运单，将待访问地点包括取物地点和配送地点的运单作为第二类运单，分别对第一类运单和第二类运单进行排序。此处可以采用一种或多种方式进行排序。
例如，可以按照配送地点的目标送达时间由先到后的顺序，分别对第一类运单和第二类运单进行排序。再例如，可以按照运单配送对象的重要程度由高到底的顺 序，对各运单进行排序，以将重要用户的运单排序在前，将非重要用户的运单排序在后。再例如，可以按照运单的紧迫程度由大到小的顺序，对各运单进行排序等。
在本实施例的一些可选的实现方式中，运单中还记录有配送地点的目标到达时间。上述执行主体可以分别按照第一排序方式和第二排序方式对各类运单(包括第一类运单和第二类运单)进行排序。其中，上述第一排序方式为按照配送地点的目标送达时间由先到后的顺序进行排序的方式。上述第二排序方式为按照运单的紧迫程度由大到小的顺序进行排序的方式。上述紧迫程度基于目标运力的位置、当前时间以及配送地点的目标到达时间确定。例如，可参见图1对应实施例中的步骤102所描述的方式进行确定，此处不再赘述。
步骤703，将排序后的第一类运单设置于排序后的第二类运单之前，得到运单的排序顺序。
在本实施例中，上述执行主体可以将排序后的第一类运单设置于排序后的第二类运单之前，得到各运单的排序顺序。由此，可以优先对已取物但尚未配送的订单进行配送。有助于提高路径规划的合理性。
在本实施例的一些可选的实现方式中，在以至少两个排序方式对各类运单进行排序的情况下，可以分别针对每一种排序方式，将该排序方式下的第一类运单设置于相同排序方式排序后的第二类运单之前，得到各种排序方式下的各运单的排序顺序。作为示例，在分别按照第一排序方式和第二排序方式对各类运单(包括第一类运单和第二类运单)进行排序的情况下，则可以将按照上述第一排序方式排序后的第一类运单设置于按照上述第一排序方式排序后的第二类运单之前，得到各运单的第一排序顺序；并将按照上述第二排序方式排序后的第一类运单设置于按照上述第二排序方式排序后的第二类运单之前，得到各运单的第二排序顺序。
步骤704，按照运单的排序顺序对各运单中的待访问地点进行路径规划，得到待访问地点序列。
在本实施例中，上述执行主体可以按照运单的排序顺序对各运单中的待访问地点进行路径规划，得到待访问地点序列。具体执行方式可参见步骤102，此处不再赘述。
在本实施例的一些可选的实现方式中，在以至少两个排序方式对各类运单进行排序的情况下，可得到各种排序方式下的各运单的排序顺序。此时，可以分别针对每一种排序方式，按照该排序方式排序下的运单的排序顺序，对各运单中的待访问地点进行路径规划，得到至少两个待访问地点序列。而后，可以从中选取最优的一个待访问地点序列。
作为示例，在分别按照第一排序方式和第二排序方式对各类运单(包括第一类运单和第二类运单)进行排序的情况下，可得到各运单的第一排序顺序和第二排序顺序。此时，可以首先获取路径规划的目标函数和约束条件。而后，可以基于上述目标函数和上述约束条件，按照各运单的第一排序顺序对各运单中的待访问地点进行路径规划，得到第一待访问地点序列。可选的，目标函数可以用于最小化配送超时时长与配送距离。上述约束条件可以包括但不限于：取物地点的访问时间晚于物品出货时间、同一运单的取物地点的访问时间早于配送地点的访问时间。之后，可 以基于上述目标函数和上述约束条件，按照运单的第二排序顺序对各运单中的待访问地点进行路径规划，得到第二待访问地点序列。最后，可以基于各待访问地点序列对应的目标函数值，选取其中一个待访问地点序列。例如，若目标函数用于最小化配送超时时长与配送距离，则目标函数值越小，待访问地点序列越优，因而可以选取目标函数值较小的待访问地点序列。
通过多种排序方式进行排序，并分别确定各种排序方式对应的待访问地点序列，从而选择最优的待访问地点序列，可以提高路径规划的质量。
步骤705，将待访问地点序列作为初始序列。
步骤706，随机从初始序列中移除部分待访问地点，得到剩余序列。
步骤707，将所移除的待访问地点重新插入至剩余序列，得到重组序列。
步骤708，局部调整重组序列，得到目标序列。
步骤709，在满足预设结束条件的情况下，基于目标序列生成路径规划结果。
本实施例的步骤705至步骤709可参见图1对应实施例的步骤103至步骤107，此处不再赘述。
从图7中可以看出，与图1对应的实施例相比，本实施例中的路径规划方法的流程700涉及了划分订单类别，并将不含取物地点的订单排序于含有取物地点的但之前，从而可以优先对已取物但尚未配送的订单进行配送。有助于提高路径规划的合理性。
进一步参考图8，本申请提供了一种路径规划装置的一个实施例，该装置具体可以应用于各种电子设备中。
如图8所示，本实施例所述的路径规划装置800包括：获取单元801，被配置成获取目标运力未处理完成的运单，上述运单中记录有待访问地点；路径规划单元802，被配置成对上述运单进行排序，按照运单的排序顺序对上述运单中的待访问地点进行路径规划，得到待访问地点序列；路径调整单元803，被配置成将上述待访问地点序列作为初始序列，执行如下路径调整步骤：随机从上述初始序列中移除部分待访问地点，得到剩余序列；将所移除的待访问地点重新插入至上述剩余序列，得到重组序列；局部调整上述重组序列，得到目标序列；在满足预设结束条件的情况下，基于上述目标序列生成路径规划结果。
上述得到初始序列的过程可得到初始的路径规划问题的可行解，对初始序列重组的过程可实现对最优解的粗略搜索，局部调整重组序列的过程可实现最优解的精细搜索，经过初始化、粗略搜索、精细搜索的过程所得到的路径规划结果，相较于现有技术中直接计算根据大量数据整体计算最优解的方式，能够有效获取到路径规划结果，避免了最优解求取失败的情况。同时，确定路径规划结果的过程中采用局部最优解，降低了数据的计算量，提高了路径规划问题的求解效率，因而提高了在线场景的适用性。
在本实施例的一些可选的实现方式中，上述装置还包括：执行单元，被配置成：在不满足上述预设结束条件的情况下，将上述目标序列作为初始序列，继续执行上述路径调整步骤。
由此，可以在未满足预设结束条件时，迭代执行多次路径调整步骤。由此执行此处越多，最终的路径规划结果越优，因而可平衡路径规划结果的质量和路径规划的耗时。
在本实施例的一些可选的实现方式中，上述路径规划单元802，进一步被配置成：将待访问地点为配送地点的运单作为第一类运单，将待访问地点包括取物地点和配送地点的运单作为第二类运单，分别对上述第一类运单和上述第二类运单进行排序；将排序后的第一类运单设置于排序后的第二类运单之前，得到运单的排序顺序。
由此，可以优先对已取物品但尚未配送的订单进行配送。有助于提高路径规划的合理性。
在本实施例的一些可选的实现方式中，上述运单中还记录有配送地点的目标到达时间；以及，上述路径规划单元802，进一步被配置成：分别按照第一排序方式和第二排序方式对各类运单进行排序，其中，上述第一排序方式为按照配送地点的目标送达时间由先到后的顺序进行排序的方式，上述第二排序方式为按照运单的紧迫程度由大到小的顺序进行排序的方式，上述紧迫程度基于目标运力的位置、当前时间以及配送地点的目标到达时间确定。
通过多种排序方式进行排序，分别确定各种排序方式对应的待访问地点序列，从而选择最优的待访问地点序列，可以提高路径规划的质量。
在本实施例的一些可选的实现方式中，上述路径规划单元802，进一步被配置成：将按照上述第一排序方式排序后的第一类运单设置于按照上述第一排序方式排序后的第二类运单之前，得到运单的第一排序顺序；将按照上述第二排序方式排序后的第一类运单设置于按照上述第二排序方式排序后的第二类运单之前，得到运单的第二排序顺序。
由此，可以优先对已取物但尚未配送的订单进行配送。有助于提高路径规划的合理性。
在本实施例的一些可选的实现方式中，上述路径规划单元802，进一步被配置成：获取路径规划的目标函数和约束条件；基于上述目标函数和上述约束条件，按照第一排序顺序对运单中的待访问地点进行路径规划，得到第一待访问地点序列；基于上述目标函数和上述约束条件，按照运单的第二排序顺序对运单中的待访问地点进行路径规划，得到第二待访问地点序列；基于各待访问地点序列对应的目标函数值，选取其中一个待访问地点序列。
通过多种排序方式进行排序，分别确定各种排序方式对应的待访问地点序列，从而选择最优的待访问地点序列，可以提高路径规划的质量。
在本实施例的一些可选的实现方式中，上述目标函数用于最小化配送超时时长与配送距离，上述约束条件包括：取物地点的访问时间晚于物品出货时间、同一运单的取物地点的访问时间早于配送地点的访问时间。
在本实施例的一些可选的实现方式中，上述路径调整单元803，进一步被配置成：基于待访问地点的总数，确定目标数量；随机选取上述目标数量的运单，并从上述初始序列中移除所随机选取的运单中的待访问地点。
由此，移除的待访问地点的数量与待访问地点的总数相关。由于待访问地点的 总数可表征路径规划问题的规模，因而移除的待访问地点的数量与路径规划问题的规模相关，可保证重组的待访问地点的数量的合理性。
在本实施例的一些可选的实现方式中，上述路径调整单元803，进一步被配置成：将所移除的待访问地点汇总为移除序列；获取路径规划的目标函数和约束条件；逐一取出上述移除序列中的待访问地点，执行如下步骤：将所取出的待访问地点分别插入至上述剩余序列中的各可行位置，并确定插入至各可行位置时的目标函数值，上述可行位置为满足上述约束条件的位置；将目标函数值最小时的可行位置作为目标位置，将所取出的待访问地点插入至上述剩余序列中的上述目标位置；将插入有上述移除序列中的待访问地点的剩余序列，确定为重组序列。
通过将随机取出的待访问地点重新插入至剩余序列得到重组序列，实现了对路径规划的解的粗略搜索。此过程中由于采用逐一插入方式进行序列重组，因而采用了基于贪心策略的求解方式。相较于现有技术中直接确定整体最优解的方式，提高了路径规划问题的求解效率，提高了在线场景的适用性。同时，够有效获取到路径规划结果，避免了最优解求取失败的情况。相较于直接使用初始序列，可提高提升解的质量。
在本实施例的一些可选的实现方式中，上述运单中的待访问地点包括配送地点，上述运单中记录有配送地点的目标到达时间；以及，上述路径调整单元803，进一步被配置成：基于上述重组序列，确定上述运单的配送地点的预估到达时间；确定提前送达运单，并为上述提前送达运单添加第一标记，上述提前送达运单为配送地点的预估到达时间早于目标到达时间的运单；执行如下第一局部调整步骤：从带有上述第一标记的运单中，选取目标到达时间与预估到达时间的差值最大的运单，作为第一目标运单，并将上述第一目标运单中的配送地点作为第一目标配送地点；响应于上述第一目标配送地点不位于上述重组序列的末端，后移上述第一目标配送地点在上述重组序列的位置，并删除上述第一目标运单的第一标记。检测是否存在带有上述第一标记的运单，若存在，重新执行上述第一局部调整步骤。
由此，不仅可以将提前送达运单更改为稍晚送达，使更紧急的运单更早处理，还能够可以将提前送达运单中的配送地址调整至最为合理的位置，进一步提高路径规划问题的解的质量和合理性。
在本实施例的一些可选的实现方式中，上述路径调整单元803，进一步被配置成：将上述第一目标配送地点在上述重组序列中的位置作为第一原始位置，并从上述重组序列中移除上述第一目标配送地点；获取路径规划的目标函数和约束条件；将上述第一目标配送地点分别插入至上述重组序列中的上述第一原始位置之后的各可行位置，并确定插入至各可行位置时的目标函数值，上述可行位置为满足上述约束条件的位置；将目标函数值最小时的可行位置作为第一更新位置，将上述第一目标配送地点插入至上述第一更新位置。
由此，不仅可以将提前送达运单更改为稍晚送达，使更紧急的运单更早处理，还能够可以将提前送达运单中的配送地址调整至最为合理的位置，进一步提高路径规划问题的解的质量和合理性。
在本实施例的一些可选的实现方式中，所述运单中的待访问地点包括配送地点， 所述运单中记录有配送地点的目标到达时间；以及，上述路径调整单元803，进一步被配置成：基于上述重组序列，确定所述运单的配送地点的预估到达时间；确定延迟送达运单，并为所述延迟送达运单添加第二标记，上述延迟送达运单为配送地点的预估到达时间晚于目标到达时间的运单；执行如下第二局部调整步骤：从带有上述第二标记的运单中，选取预估到达时间与目标到达时间的差值最大的运单，作为第二目标运单，并将上述第二目标运单中的配送地点作为第二目标配送地点；响应于上述第二目标配送地点不位于上述重组序列的首端，前移上述第二目标配送地点在上述重组序列的位置，并删除上述第二目标运单的第二标记。检测是否存在带有上述第二标记的运单，若存在，重新执行上述第二局部调整步骤。
通过前移各个延迟送达运单中的配送地点的位置来局部调整重组序列，可将各个延迟送达运单的配送次序提前，从而能够避免订单延迟送达或降低延迟送达订单的超时时间。由此，可以进一步提高路径规划问题的解的质量和合理性。
在本实施例的一些可选的实现方式中，上述路径调整单元803，进一步被配置成：将上述第二目标配送地点在上述重组序列中的位置作为第二原始位置，并从上述重组序列中移除上述第二目标配送地点；获取路径规划的目标函数和约束条件；将上述第二目标配送地点分别插入至上述重组序列中的上述第二原始位置之前的各可行位置，并确定插入至各可行位置时的目标函数值，上述可行位置为满足上述约束条件的位置；将目标函数值最小时的可行位置作为第二更新位置，将上述第二目标配送地点插入至上述第二更新位置。
由此，不仅可以将延迟送达运单的配送次序提前，还能够可以将延迟送达运单中的配送地址调整至最为合理的位置，进一步提高路径规划问题的解的质量和合理性。
在本实施例的一些可选的实现方式中，所述运单中的待访问地点包括配送地点；以及，上述路径调整单元803，进一步被配置成：为上述重组序列中的配送地点添加第三标记；执行如下第三局部调整步骤：将上述重组序列中的任一带有上述第三标记的配送地点作为第三目标配送地点，从上述重组序列中取出上述第三目标配送地点；获取路径规划的目标函数和预设条件；将上述第三目标配送地点分别插入至上述重组序列中的各可行位置，并确定插入至各可行位置时的目标函数值，上述可行位置为满足上述约束条件的位置；将目标函数值最小时的可行位置作为第三更新位置，将上述第三目标配送地点插入至上述第三更新位置，并删除上述第三目标配送地点的第三标记。检测上述重组序列中是否存在带有上述第三标记的配送地点，若存在，重新执行上述第三局部调整步骤。
由此，可逐一地将重组序列中的各配送地点作为第三目标配送地点，从重组序列中取出并重新插入。从而，进一步搜索了更多的可行解，在这些可行解中选择最优的解(即目标函数值最小时的序列)，可进一步提高提高路径规划问题的解的质量。
在本实施例的一些可选的实现方式中，上述运单中的待访问地点包括配送地点；以及，上述路径调整单元803，进一步被配置成：为上述重组序列中的配送地点添加第四标记；执行如下第四局部调整步骤：获取路径规划的目标函数和约束条件；将上述重组序列中的任一带有上述第四标记的配送地点作为第四目标配送地点，将上 述第四目标配送地点分别与上述重组序列中的各其余待访问地点进行交换，得到各交换方式下的目标函数值，并确定各交换方式是否满足上述约束条件；将目标函数值最小且满足上述约束条件时的交换方式作为目标交换方式，以上述目标交换方式对上述第四目标配送地点进行位置交换，并删除上述第四目标配送地点的第四标记。检测上述重组序列中是否存在带有上述第四标记的配送地点，若存在，重新执行上述第四局部调整步骤。
由此，可逐一地将重组序列中的各配送地点作为第四目标配送地点，检测与其余各待访问地点进行交换时的可行解质量。从而，进一步搜索了更多的可行解，在这些可行解中选择最优的解(即目标函数值最小时的序列)，可进一步提高提高路径规划问题的解的质量。
在本实施例的一些可选的实现方式中，上述路径调整单元803，进一步被配置成：将当前时间与上述目标运力的运单的获取时间的时间差作为处理时长，检测上述处理时长是否大于或等于预设阈值；响应于上述处理时长大于或等于上述预设阈值，确定满足预设结束条件，上述预设阈值与待访问地点的总数相关；响应于上述时间差小于上述预设阈值，确定不满足上述预设结束条件。
由此，可从时间中限制路径规划求解的时长，进一步提高对线上场景的适用性。此外，由于待访问地点的总数可表征路径规划问题的规模，因而将预设阈值设置为与路径规划问题的规模相关的数，可保证预设阈值的合理性。
下面参考图9，其示出了适于用来实现本申请实施例的电子设备的计算机系统900的结构示意图。图9示出的电子设备仅仅是一个示例，不应对本申请实施例的功能和使用范围带来任何限制。
如图9所示，计算机系统900包括中央处理单元(CPU)901，其可以根据存储在只读存储器(ROM)902中的程序或者从存储部分908加载到随机访问存储器(RAM)903中的程序而执行各种适当的动作和处理。在RAM 903中，还存储有系统900操作所需的各种程序和数据。CPU 901、ROM 902以及RAM 903通过总线904彼此相连。输入/输出(I/O)接口905也连接至总线904。
以下部件连接至I/O接口905：包括键盘、鼠标等的输入部分906；包括诸如液晶显示器(LCD)等以及扬声器等的输出部分907；包括硬盘等的存储部分908；以及包括诸如LAN卡、调制解调器等的网络接口卡的通信部分909。通信部分909经由诸如因特网的网络执行通信处理。驱动器910也根据需要连接至I/O接口905。可拆卸介质911，诸如磁盘、光盘、磁光盘、半导体存储器等等，根据需要安装在驱动器910上，以便于从其上读出的计算机程序根据需要被安装入存储部分908。
特别地，根据本公开的实施例，上文参考流程图描述的过程可以被实现为计算机软件程序。例如，本公开的实施例包括一种计算机程序产品，其包括承载在计算机可读介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中，该计算机程序可以通过通信部分909从网络上被下载和安装，和/或从可拆卸介质911被安装。在该计算机程序被中央处理单元(CPU)901执行时，执行本申请的方法中限定的上述功能。需要说明的是，本申请所述的计算 机可读介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本申请中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。而在本申请中，计算机可读的信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读的信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于：无线、电线、光缆、RF等等，或者上述的任意合适的组合。
附图中的流程图和框图，图示了按照本申请各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
描述于本申请实施例中所涉及到的单元可以通过软件的方式实现，也可以通过硬件的方式来实现。所描述的单元也可以设置在处理器中，其中，这些单元的名称在某种情况下并不构成对该单元本身的限定。
作为另一方面，本申请还提供了一种计算机可读介质，该计算机可读介质可以是上述实施例中描述的装置中所包含的；也可以是单独存在，而未装配入该装置中。上述计算机可读介质承载有一个或者多个程序，当上述一个或者多个程序被该装置执行时，使得该装置：获取目标运力未处理完成的运单，运单中记录有待访问地点；对运单进行排序，并按照运单的排序顺序对运单中的待访问地点进行路径规划，得到待访问地点序列；将待访问地点序列作为初始序列，随机从初始序列中移除部分待访问地点，得到剩余序列；将所移除的待访问地点重新插入至剩余序列，得到重组序列；局部调整重组序列，得到目标序列；在满足预设结束条件的情况下，基于目标序列生成路径规划结果。
以上描述仅为本申请的较佳实施例以及对所运用技术原理的说明。本领域技术人员应当理解，本申请中所涉及的发明范围，并不限于上述技术特征的特定组合而 成的技术方案，同时也应涵盖在不脱离上述发明构思的情况下，由上述技术特征或其等同特征进行任意组合而形成的其它技术方案。例如上述特征与本申请中公开的(但不限于)具有类似功能的技术特征进行互相替换而形成的技术方案。

Claims (19)

  1. 一种路径规划方法，包括：
    获取目标运力未处理完成的运单，其中，所述运单中记录有待访问地点；
    对所述运单进行排序，按照所述运单的排序顺序对所述运单中的待访问地点进行路径规划，得到待访问地点序列；
    将所述待访问地点序列作为初始序列，执行如下路径调整步骤：随机从所述初始序列中移除部分待访问地点，得到剩余序列；将所移除的待访问地点重新插入至所述剩余序列，得到重组序列；局部调整所述重组序列，得到目标序列；在满足预设结束条件的情况下，基于所述目标序列生成路径规划结果。
  2. 根据权利要求1所述的方法，还包括：
    在不满足所述预设结束条件的情况下，将所述目标序列作为初始序列，继续执行所述路径调整步骤。
  3. 根据权利要求1所述的方法，其中，所述对所述运单进行排序，包括：
    将待访问地点为配送地点的运单作为第一类运单，将待访问地点包括取物地点和配送地点的运单作为第二类运单，分别对所述第一类运单和所述第二类运单进行排序；
    将排序后的第一类运单设置于排序后的第二类运单之前，得到运单的排序顺序。
  4. 根据权利要求3所述的方法，其中，所述运单中还记录有配送地点的目标到达时间；以及，
    所述分别对所述第一类运单和所述第二类运单进行排序，包括：
    分别按照第一排序方式和第二排序方式对各类运单进行排序，其中，所述第一排序方式为按照配送地点的目标送达时间由先到后的顺序进行排序的方式，所述第二排序方式为按照运单的紧迫程度由大到小的顺序进行排序的方式，所述紧迫程度基于目标运力的位置、当前时间以及配送地点的目标到达时间确定。
  5. 根据权利要求4所述的方法，其中，所述将排序后的第一类运单设置于排序 后的第二类运单之前，得到运单的排序顺序，包括：
    将按照所述第一排序方式排序后的第一类运单设置于按照所述第一排序方式排序后的第二类运单之前，得到运单的第一排序顺序；
    将按照所述第二排序方式排序后的第一类运单设置于按照所述第二排序方式排序后的第二类运单之前，得到运单的第二排序顺序。
  6. 根据权利要求5所述的方法，其中，所述按照运单的排序顺序对所述运单中的待访问地点进行路径规划，得到待访问地点序列，包括：
    获取路径规划的目标函数和约束条件；
    基于所述目标函数和所述约束条件，按照所述第一排序顺序对运单中的待访问地点进行路径规划，得到第一待访问地点序列；
    基于所述目标函数和所述约束条件，按照所述第二排序顺序对运单中的待访问地点进行路径规划，得到第二待访问地点序列；
    基于各待访问地点序列对应的目标函数值，选取其中一个待访问地点序列。
  7. 根据权利要求6所述的方法，其中，所述目标函数用于最小化配送超时时长与配送距离，所述约束条件包括：取物地点的访问时间晚于物品出货时间、同一运单的取物地点的访问时间早于配送地点的访问时间。
  8. 根据权利要求1所述的方法，其中，所述随机从所述初始序列中移除部分待访问地点，得到剩余序列，包括：
    基于待访问地点的总数，确定目标数量；
    随机选取所述目标数量的运单，并从所述初始序列中移除所随机选取的运单中的待访问地点。
  9. 根据权利要求1所述的方法，其中，所述将所移除的待访问地点重新插入至所述剩余序列，得到重组序列，包括：
    将所移除的待访问地点汇总为移除序列；
    获取路径规划的目标函数和约束条件；
    逐一取出所述移除序列中的待访问地点，执行如下步骤：将所取出的待访问地 点分别插入至所述剩余序列中的各可行位置，并确定插入至各可行位置时的目标函数值，所述可行位置为满足所述约束条件的位置；将目标函数值最小时的可行位置作为目标位置，将所取出的待访问地点插入至所述剩余序列中的所述目标位置；
    将插入有所述移除序列中的待访问地点的剩余序列，确定为重组序列。
  10. 根据权利要求1所述的方法，其中，所述运单中的待访问地点包括配送地点，所述运单中记录有配送地点的目标到达时间；以及，
    所述局部调整所述重组序列，得到目标序列，包括：
    基于所述重组序列，确定所述运单的配送地点的预估到达时间；
    确定提前送达运单，并为所述提前送达运单添加第一标记，所述提前送达运单为配送地点的预估到达时间早于目标到达时间的运单；
    执行如下第一局部调整步骤：从带有所述第一标记的运单中，选取目标到达时间与预估到达时间的差值最大的运单，作为第一目标运单，并将所述第一目标运单中的配送地点作为第一目标配送地点；响应于所述第一目标配送地点不位于所述重组序列的末端，后移所述第一目标配送地点在所述重组序列的位置，并删除所述第一目标运单的第一标记；
    检测是否存在带有所述第一标记的运单，若存在，重新执行所述第一局部调整步骤。
  11. 根据权利要求10所述的方法，其中，所述调整所述第一目标配送地点在所述重组序列的位置，包括：
    将所述第一目标配送地点在所述重组序列中的位置作为第一原始位置，并从所述重组序列中移除所述第一目标配送地点；
    获取路径规划的目标函数和约束条件；
    将所述第一目标配送地点分别插入至所述重组序列中的所述第一原始位置之后的各可行位置，并确定插入至各可行位置时的目标函数值，所述可行位置为满足所述约束条件的位置；
    将目标函数值最小时的可行位置作为第一更新位置，将所述第一目标配送地点插入至所述第一更新位置。
  12. 根据权利要求1所述的方法，其中，所述运单中的待访问地点包括配送地点，所述运单中记录有配送地点的目标到达时间；以及，
    所述局部调整所述重组序列，得到目标序列，包括：
    基于所述重组序列，确定所述运单的配送地点的预估到达时间；
    确定延迟送达运单，并为所述延迟送达运单添加第二标记，所述延迟送达运单为配送地点的预估到达时间晚于目标到达时间的运单；
    执行如下第二局部调整步骤：从带有所述第二标记的运单中，选取预估到达时间与目标到达时间的差值最大的运单，作为第二目标运单，并将所述第二目标运单中的配送地点作为第二目标配送地点；响应于所述第二目标配送地点不位于所述重组序列的首端，前移所述第二目标配送地点在所述重组序列的位置，并删除所述第二目标运单的第二标记；
    检测是否存在带有所述第二标记的运单，若存在，重新执行所述第二局部调整步骤。
  13. 根据权利要求12所述的方法，其中，所述调整所述第二目标配送地点在所述重组序列的位置，包括：
    将所述第二目标配送地点在所述重组序列中的位置作为第二原始位置，并从所述重组序列中移除所述第二目标配送地点；
    获取路径规划的目标函数和约束条件；
    将所述第二目标配送地点分别插入至所述重组序列中的所述第二原始位置之前的各可行位置，并确定插入至各可行位置时的目标函数值，所述可行位置为满足所述约束条件的位置；
    将目标函数值最小时的可行位置作为第二更新位置，将所述第二目标配送地点插入至所述第二更新位置。
  14. 根据权利要求1所述的方法，其中，所述运单中的待访问地点包括配送地点；以及，
    所述局部调整所述重组序列，得到目标序列，包括：
    为所述重组序列中的配送地点添加第三标记；
    执行如下第三局部调整步骤：将所述重组序列中的任一带有所述第三标记的配 送地点作为第三目标配送地点，从所述重组序列中取出所述第三目标配送地点；获取路径规划的目标函数和预设条件；将所述第三目标配送地点分别插入至所述重组序列中的各可行位置，并确定插入至各可行位置时的目标函数值，所述可行位置为满足所述约束条件的位置；将目标函数值最小时的可行位置作为第三更新位置，将所述第三目标配送地点插入至所述第三更新位置，并删除所述第三目标配送地点的第三标记；
    检测所述重组序列中是否存在带有所述第三标记的配送地点，若存在，重新执行所述第三局部调整步骤。
  15. 根据权利要求1所述的方法，其中，所述运单中的待访问地点包括配送地点；以及，
    所述局部调整所述重组序列，得到目标序列，包括：
    为所述重组序列中的配送地点添加第四标记；
    执行如下第四局部调整步骤：获取路径规划的目标函数和约束条件；将所述重组序列中的任一带有所述第四标记的配送地点作为第四目标配送地点，将所述第四目标配送地点分别与所述重组序列中的各其余待访问地点进行交换，得到各交换方式下的目标函数值，并确定各交换方式是否满足所述约束条件；将目标函数值最小且满足所述约束条件时的交换方式作为目标交换方式，以所述目标交换方式对所述第四目标配送地点进行位置交换，并删除所述第四目标配送地点的第四标记；
    检测所述重组序列中是否存在带有所述第四标记的配送地点，若存在，重新执行所述第四局部调整步骤。
  16. 根据权利要求1所述的方法，其中，通过如下步骤检测是否满足预设结束条件：
    将当前时间与所述目标运力的运单的获取时间的时间差作为处理时长，检测所述处理时长是否大于或等于预设阈值；
    响应于所述处理时长大于或等于所述预设阈值，确定满足预设结束条件，所述预设阈值与待访问地点的总数相关；
    响应于所述时间差小于所述预设阈值，确定不满足所述预设结束条件。
  17. 一种路径规划装置，包括：
    获取单元，被配置成获取目标运力未处理完成的运单，所述运单中记录有待访问地点；
    路径规划单元，被配置成对所述运单进行排序，按照运单的排序顺序对所述运单中的待访问地点进行路径规划，得到待访问地点序列；
    路径调整单元，被配置成将所述待访问地点序列作为初始序列，执行如下路径调整步骤：随机从所述初始序列中移除部分待访问地点，得到剩余序列；将所移除的待访问地点重新插入至所述剩余序列，得到重组序列；局部调整所述重组序列，得到目标序列；在满足预设结束条件的情况下，基于所述目标序列生成路径规划结果。
  18. 一种电子设备，包括：
    一个或多个处理器；
    存储装置，其上存储有一个或多个程序，
    当所述一个或多个程序被所述一个或多个处理器执行，使得所述一个或多个处理器实现如权利要求1-16中任一所述的方法。
  19. 一种计算机可读介质，其上存储有计算机程序，该程序被处理器执行时实现如权利要求1-16中任一所述的方法。
PCT/CN2021/084071 2020-06-16 2021-03-30 路径规划 WO2021253918A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010550940.3A CN113804206A (zh) 2020-06-16 2020-06-16 路径规划方法、装置、电子设备和计算机可读介质
CN202010550940.3 2020-06-16

Publications (1)

Publication Number Publication Date
WO2021253918A1 true WO2021253918A1 (zh) 2021-12-23

Family

ID=78943303

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/084071 WO2021253918A1 (zh) 2020-06-16 2021-03-30 路径规划

Country Status (2)

Country Link
CN (1) CN113804206A (zh)
WO (1) WO2021253918A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116934207A (zh) * 2023-09-19 2023-10-24 弥费科技(上海)股份有限公司 半导体传送运单任务处理方法、装置和计算机设备

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105184412A (zh) * 2015-09-21 2015-12-23 北京农业信息技术研究中心 基于地理位置的物流配送路径规划方法和系统
CN106500686A (zh) * 2016-10-12 2017-03-15 北京小度信息科技有限公司 导航界面显示方法、物流导航方法和装置
US20190392368A1 (en) * 2018-06-23 2019-12-26 Mitsubishi Electric Research Laboratories, Inc. System and Method for Scheduling Multiple Modes of Transport
CN110796402A (zh) * 2018-08-03 2020-02-14 阿里巴巴集团控股有限公司 订单批次调度方法、装置及计算机系统
CN111044062A (zh) * 2018-10-15 2020-04-21 北京京东尚科信息技术有限公司 路径规划、推荐方法和装置
CN111256718A (zh) * 2020-02-12 2020-06-09 上海东普信息科技有限公司 派件路线规划方法、装置、系统、设备及存储介质

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105184412A (zh) * 2015-09-21 2015-12-23 北京农业信息技术研究中心 基于地理位置的物流配送路径规划方法和系统
CN106500686A (zh) * 2016-10-12 2017-03-15 北京小度信息科技有限公司 导航界面显示方法、物流导航方法和装置
US20190392368A1 (en) * 2018-06-23 2019-12-26 Mitsubishi Electric Research Laboratories, Inc. System and Method for Scheduling Multiple Modes of Transport
CN110796402A (zh) * 2018-08-03 2020-02-14 阿里巴巴集团控股有限公司 订单批次调度方法、装置及计算机系统
CN111044062A (zh) * 2018-10-15 2020-04-21 北京京东尚科信息技术有限公司 路径规划、推荐方法和装置
CN111256718A (zh) * 2020-02-12 2020-06-09 上海东普信息科技有限公司 派件路线规划方法、装置、系统、设备及存储介质

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116934207A (zh) * 2023-09-19 2023-10-24 弥费科技(上海)股份有限公司 半导体传送运单任务处理方法、装置和计算机设备
CN116934207B (zh) * 2023-09-19 2024-01-19 弥费科技(上海)股份有限公司 半导体传送运单任务处理方法、装置和计算机设备

Also Published As

Publication number Publication date
CN113804206A (zh) 2021-12-17

Similar Documents

Publication Publication Date Title
CN110378732B (zh) 信息显示方法、信息关联方法、装置、设备及存储介质
WO2019114391A1 (zh) 信息输出方法和装置
CN108492068B (zh) 用于路径规划的方法和装置
CN107798109A (zh) 对账清算的方法、装置、计算机设备及存储介质
US20080077594A1 (en) Providing a user access to data files distributed in a plurality of different types of user devices
CN111028009B (zh) 可领取业务实体处理方法和装置
CN102446118A (zh) 聚焦于上下文和任务的计算
CN113918622B (zh) 基于区块链的信息溯源方法及系统
CN109542352A (zh) 用于存储数据的方法和装置
CN110222775A (zh) 图像处理方法、装置、电子设备及计算机可读存储介质
CN109658018A (zh) 提高仓储出库效率的方法和装置
WO2021253918A1 (zh) 路径规划
CN110287201A (zh) 数据访问方法、装置、设备及存储介质
WO2016113648A1 (en) Database statistical histogram forecasting
CN105468623A (zh) 数据处理方法及装置
CN107066588A (zh) 一种数据库及相应的方法与设备
CN113077319B (zh) 针对微详情页面的动态推荐方法及装置
Lin et al. Sequence optimization for media objects with due date constraints in multimedia presentations from digital libraries
CN112241396B (zh) 基于Spark的对Delta进行小文件合并的方法及系统
CN111782933B (zh) 用于推荐书单的方法和装置
WO2021137768A1 (en) Method, apparatus and device for consuming messages based on message queue
CN104391947A (zh) 海量gis数据实时处理方法及系统
CN113326095A (zh) 一种佣金数据处理方法和装置
CN108537057A (zh) 用于处理相册浏览请求的方法和装置
CN112559483A (zh) 基于hdfs的数据管理方法、装置、电子设备及介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21824767

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21824767

Country of ref document: EP

Kind code of ref document: A1