WO2019037367A1 - 配送任务处理方法、装置及电子设备 - Google Patents

配送任务处理方法、装置及电子设备 Download PDF

Info

Publication number
WO2019037367A1
WO2019037367A1 PCT/CN2017/118772 CN2017118772W WO2019037367A1 WO 2019037367 A1 WO2019037367 A1 WO 2019037367A1 CN 2017118772 W CN2017118772 W CN 2017118772W WO 2019037367 A1 WO2019037367 A1 WO 2019037367A1
Authority
WO
WIPO (PCT)
Prior art keywords
task
similarity
distribution
resource
distribution resource
Prior art date
Application number
PCT/CN2017/118772
Other languages
English (en)
French (fr)
Inventor
黄绍建
徐明泉
咸珂
陈进清
杨秋源
Original Assignee
北京小度信息科技有限公司
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 北京小度信息科技有限公司 filed Critical 北京小度信息科技有限公司
Publication of WO2019037367A1 publication Critical patent/WO2019037367A1/zh

Links

Images

Classifications

    • 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
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06313—Resource planning in a project environment
    • 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 present disclosure relates to the field of data processing technologies, and in particular, to a delivery task processing method, apparatus, and electronic device.
  • O2O Online To Offline
  • Embodiments of the present disclosure provide a method, an apparatus, and an electronic device for processing a delivery task.
  • a delivery task processing method is provided in an embodiment of the present disclosure.
  • the delivery task processing method includes:
  • the similarity between the task to be delivered and the task to be assigned of the target delivery resource is the highest.
  • the determining the similarity between the task to be assigned and the task to be delivered includes:
  • the similarity evaluation element is used to calculate the similarity between the task to be assigned and the task to be delivered.
  • the first preset condition includes:
  • the similarity between the task to be assigned and the task to be delivered is higher than or equal to a preset similarity threshold; and/or,
  • the number of tasks to be assigned with the similarity higher than or equal to the preset similarity threshold is higher than or equal to the preset proportional threshold in all the tasks to be delivered of the distribution resource.
  • the method further includes:
  • the unallocated task is assigned to a distribution resource, and the distribution resource to be delivered task has the highest similarity with the unallocated task; if the unassigned task quantity is greater than or equal to the The first quantity threshold is calculated, the similarity between the unassigned tasks is calculated, and the unallocated task is assigned to the distribution resource according to the similarity.
  • the assigning the unallocated task according to the similarity Distribution resources including:
  • Each task class is grouped according to the similarity to obtain a task group
  • the unallocated task is assigned to the distribution resource according to the matching degree.
  • the calculating each task group and the distribution resource including:
  • the matching degree between the task group and the distribution resource is calculated by using the matching evaluation element.
  • the matching evaluation element includes: a distance between the location of the task group merchant and the location where the distribution resource is empty, a remaining time of the task group, a time required for the distribution resource to reach the no-load state, an estimated timeout information of the distribution resource delivery task group, One or more of the distribution resource speed and the distribution resource score.
  • the Assign tasks to distribution resources including:
  • the unallocated task is assigned to the distribution resource in response to the delivery information satisfying a second predetermined condition.
  • the second preset condition includes: the task group times out after the preset time, the number of the distribution resources to be delivered is lower than the second quantity threshold, and the time required for the delivery resource to reach the idling is lower than the preset time threshold. One or more.
  • an embodiment of the present disclosure provides a delivery task processing apparatus, where the apparatus includes:
  • a first determining module configured to determine a similarity between the task to be assigned and the task to be delivered
  • a second determining module configured to determine a corresponding distribution resource as a candidate distribution resource in response to the similarity meeting the first preset condition
  • the first allocation module is configured to allocate the to-be-assigned task to the target delivery resource in the candidate distribution resource, and the similarity between the task to be delivered and the task to be assigned of the target delivery resource is the highest.
  • the first determining module includes:
  • a first determining submodule configured to determine a similarity evaluation element
  • the first calculation sub-module is configured to calculate a similarity between the task to be assigned and the task to be delivered by using the similarity evaluation element.
  • the first preset condition includes:
  • the similarity between the task to be assigned and the task to be delivered is higher than or equal to a preset similarity threshold; and/or,
  • the number of tasks to be assigned with the similarity higher than or equal to the preset similarity threshold is higher than or equal to the preset proportional threshold in all the tasks to be delivered of the distribution resource.
  • the apparatus further includes:
  • a third determining module configured to determine the number of unassigned tasks
  • a second allocation module configured to allocate the unallocated task to a distribution resource if the number of unallocated tasks is less than a first quantity threshold, and the similarity between the delivery resource to be delivered task and the unallocated task is the highest;
  • the similarity between the unallocated tasks is calculated, and the unallocated tasks are assigned to the distribution resources according to the similarities.
  • the third distribution module includes:
  • a clustering submodule configured to perform clustering processing on the unallocated task according to the distance information of the unassigned task to obtain a task class
  • a grouping sub-module configured to group each task class according to the similarity to obtain a task group
  • a second calculation sub-module configured to calculate a degree of matching between each task group and a distribution resource
  • An allocation sub-module configured to allocate the unallocated task to a distribution resource according to the matching degree.
  • the second computing submodule includes:
  • a determining unit configured to determine a matching evaluation element
  • a computing unit configured to calculate a degree of matching between each task group and a distribution resource using the matching evaluation element.
  • the matching evaluation element includes: a distance between a location of the task group merchant and a location where the distribution resource is empty, a remaining time of the task group, a time required for the delivery resource to reach an idle state, an estimated timeout information of the distribution resource delivery task group, One or more of the distribution resource speed and the distribution resource score.
  • the distribution submodule includes:
  • a first allocating unit configured to pre-allocate the unallocated task to a distribution resource according to the size of the matching degree
  • the second allocating unit is configured to allocate the unallocated task to the distribution resource in response to the delivery information satisfying the second preset condition.
  • the second preset condition includes: the task group times out after the preset time, the number of the distribution resources to be delivered is lower than the second quantity threshold, and the time required for the delivery resource to reach the idling is lower than the preset time threshold. One or more.
  • an embodiment of the present disclosure provides an electronic device, including a memory and a processor, where the memory is configured to store one or more computer instructions that support a delivery task processing device to perform the delivery task processing method in the first aspect,
  • the processor is configured to execute computer instructions stored in the memory.
  • the delivery task processing device may also include a communication interface for the delivery task processing device to communicate with other devices or communication networks.
  • an embodiment of the present disclosure provides a computer readable storage medium, configured to store computer instructions used by a delivery task processing apparatus, where the method for processing a distribution task in the first aspect is performed by a delivery task processing apparatus Computer instructions involved.
  • Embodiments of the present disclosure provide a new delivery task processing solution, which provides stable, reliable, fast, and timely delivery to users by performing similarity-based processing and scheduling in a wide area, such as a city-wide distribution task.
  • the embodiments of the present disclosure have strong adaptability, wide service coverage, and high distribution efficiency, and can provide distribution solutions for various types of O2O platforms to meet the needs of merchants and users for wide-area distribution, and to facilitate the use of merchants and users.
  • FIG. 1 shows a flow chart of a delivery task processing method according to an embodiment of the present disclosure
  • FIG. 2 shows a flow chart of step S101 according to the embodiment shown in Figure 1;
  • FIG. 3 shows a flow chart of step S102 according to the embodiment shown in Figure 1;
  • FIG. 4 is a flowchart showing steps of allocating an unassigned task in a delivery task processing method according to another embodiment of the present disclosure
  • FIG. 5 shows a flow chart of step S403 according to the embodiment shown in Figure 4;
  • FIG. 6 shows a flow chart of step S503 according to the embodiment shown in Figure 5;
  • FIG. 7 shows a flow chart of step S504 according to the embodiment shown in Figure 5;
  • FIG. 8 is a block diagram showing the structure of a delivery task processing apparatus according to an embodiment of the present disclosure.
  • FIG. 9 is a block diagram showing the structure of the first determining module 801 according to the embodiment shown in FIG. 8;
  • FIG. 10 is a block diagram showing the structure of a second determining module 802 according to the embodiment shown in FIG. 8;
  • FIG. 11 is a structural block diagram showing a portion for allocating an unallocated task in a delivery task processing apparatus according to another embodiment of the present disclosure
  • Figure 12 is a block diagram showing the structure of the second distribution module 1102 according to the embodiment shown in Figure 11;
  • FIG. 13 is a block diagram showing the structure of a second calculation submodule 1203 according to the embodiment shown in FIG. 12;
  • Figure 14 is a block diagram showing the structure of the distribution sub-module 1204 according to the embodiment shown in Figure 12;
  • FIG. 15 is a block diagram showing the structure of an electronic device according to an embodiment of the present disclosure.
  • 16 is a block diagram of a computer system suitable for implementing a delivery task processing method in accordance with an embodiment of the present disclosure.
  • Embodiments of the present disclosure provide a new delivery task processing solution, which provides stable, reliable, fast, and timely delivery to users by performing similarity-based processing and scheduling in a wide area, such as a city-wide distribution task.
  • the embodiments of the present disclosure have strong adaptability, wide service coverage, and high distribution efficiency, and can provide distribution solutions for various types of O2O platforms to meet the needs of merchants and users for wide-area distribution, and to facilitate the use of merchants and users.
  • FIG. 1 illustrates a flow chart of a delivery task processing method in accordance with an embodiment of the present disclosure.
  • the delivery task processing method includes the following steps S101-S103:
  • step S101 determining a similarity between the task to be assigned and the task to be delivered;
  • step S102 in response to the similarity meeting the first preset condition, determining the corresponding delivery resource as the candidate delivery resource;
  • step S103 the task to be assigned is allocated to the target delivery resource in the candidate delivery resource, and the similarity between the task to be delivered and the task to be assigned of the target delivery resource is the highest.
  • Steps S101, S102, and S103 will be further described below, respectively.
  • the quality of service depends on stable, reliable, fast and punctual delivery services.
  • most of the relevant technologies are based on the distribution and scheduling of distribution tasks in the business circle. For example, multiple distributors responsible for different business districts. When the system receives a new delivery service, it first determines which business district the delivery address belongs to, and then assigns the corresponding delivery task to the distributor responsible for the business circle.
  • the distributors responsible for the adjacent business districts may have fewer tasks, which leads to a lot of dispatchers.
  • the users in the responsible business circle cannot receive the goods in time, while the dispatchers with few tasks are nearby, but they cannot serve the users.
  • Embodiments of the present disclosure provide a solution for allocating and processing a delivery task in a wide area, such as a city, to avoid problems existing in the related art.
  • a wide-area scope in order to achieve stable, reliable, fast, and timely delivery of services to users, it is necessary to accurately allocate tasks to be assigned.
  • the assignment of the distribution task is performed by using the similarity between the task to be assigned and the delivery task that has been allocated to the distribution resource but not completed, that is, the similarity between the tasks to be delivered, that is, the first need to calculate The similarity between the assignment task and the task to be delivered.
  • the distribution resource includes a distributor and other distribution resources.
  • the corresponding distribution resource is determined to be a distribution resource suitable for accepting the delivery task, that is, a candidate delivery resource.
  • the distribution resource with the highest similarity between the task to be delivered and the task to be assigned may be selected from among the plurality of candidate distribution resources, as the final acceptance of the to-be-distributed. Distribution resources for tasks.
  • the above embodiment provides a new delivery task processing solution, which provides stable, reliable, fast, and timely delivery to users by performing similarity-based processing and scheduling in a wide area, such as a citywide distribution task.
  • the purpose of the service The embodiments of the present disclosure have strong adaptability, wide service coverage, and high distribution efficiency, and can provide distribution solutions for various types of O2O platforms to meet the needs of merchants and users for wide-area distribution, and to facilitate the use of merchants and users.
  • the step S101 that is, determining the similarity between the task to be assigned and the task to be delivered, includes steps S201-S202:
  • step S201 determining a similarity evaluation element
  • step S202 the similarity evaluation element is used to calculate the similarity between the task to be assigned and the task to be delivered.
  • the similarity evaluation element includes one or more of a delivery task merchant address, a delivery task user address, and a desired delivery time.
  • the similarity between the task to be assigned and the task to be delivered is calculated based on one or more similarity evaluation elements of the delivery task merchant address, the delivery task user address, and the expected delivery time, for example, two The closer the merchants to be assigned tasks are, the closer the user's location is, and the closer the expected delivery time is, the more similar the two tasks to be assigned are, the more suitable they are to be assigned to the same distribution resource, or the more Suitable for merging with tasks to be delivered.
  • the similarity evaluation element may also adopt other elements that can reflect the similarity between the delivery tasks.
  • the disclosure is not listed one by one, and all the elements capable of evaluating the similarity between the delivery tasks fall within the protection scope of the disclosure.
  • the first preset condition includes:
  • the similarity between the task to be assigned and the task to be delivered is higher than or equal to a preset similarity threshold; and/or,
  • the number of tasks to be assigned with the similarity higher than or equal to the preset similarity threshold is higher than or equal to the preset proportional threshold in all the tasks to be delivered of the distribution resource.
  • the step S102 that is, the step of determining the corresponding distribution resource as the candidate distribution resource in response to the similarity meeting the first preset condition, includes steps S301-S302:
  • step S301 determining the proportion of the number of tasks whose similarity is higher than or equal to the preset similarity threshold in all the tasks to be delivered of the distribution resource;
  • step S302 if the ratio is higher than or equal to a preset ratio threshold, the distribution resource is determined as a candidate delivery resource.
  • the number of tasks whose similarity is higher than or equal to the preset similarity threshold is determined. Whether the proportion of all the tasks to be delivered in the distribution resource is higher than or equal to the preset ratio threshold to determine an appropriate distribution resource. For example, if the score between the tasks to be assigned and the tasks of the distribution resource that are half or more of the tasks to be delivered are higher than or equal to the preset similarity threshold, the task to be assigned is considered to be assignable to the distribution resource, and the distribution resource Can be considered as a candidate distribution resource.
  • the highest similarity obtained by comparing the task to be assigned with all the tasks to be delivered of the distribution resource may be used as the similarity of the distribution resource, and then the task to be assigned is allocated to the distribution resource with the highest similarity.
  • the values of the similarity threshold and the proportional threshold may be determined according to the needs of the actual application, and the disclosure is not specifically limited.
  • the distribution pressure value of the area where the distribution resource is located may be considered, and the size of the distribution pressure value is related to the number of tasks to be delivered in the area, and the distribution task has more distribution pressure values.
  • the similarity threshold is higher, which enables the distribution resource to complete the assigned delivery task as soon as possible and improve the user experience.
  • the method further includes steps S401-S403:
  • step S401 determining the number of unassigned tasks
  • step S402 if the unallocated task number is less than the first quantity threshold, the unallocated task is assigned to a distribution resource, and the similarity between the distribution resource to be delivered task and the unallocated task is the highest;
  • step S403 if the number of unassigned tasks is greater than or equal to the first number of thresholds, the similarity between the unassigned tasks is calculated, and the unallocated tasks are assigned to the distribution resources according to the similarities.
  • a task with a similarity enough that a task similar to a certain distribution resource has enough tasks to be distributed is likely to be allocated and processed.
  • the above allocation will be explained. After the remaining tasks, that is, the unbalanced tasks with other similar tasks to be delivered are not high enough, and the tasks similar to a certain distribution resource are not enough.
  • the number of delivery tasks remaining after the above-mentioned allocation operation is determined, that is, the number of unassigned tasks that are not high enough for other tasks to be delivered and whose tasks are similar to a certain distribution resource are insufficient; if the number of unassigned tasks is less than The first quantity threshold, for example, less than 2, directly assigns the unallocated task to the distribution resource with the highest similarity between the task to be delivered and the unallocated task; if the number of unassigned tasks is greater than or equal to the first quantity threshold For example, greater than or equal to 2, the similarity between these unallocated tasks needs to be calculated; then these unallocated tasks are assigned to the distribution resources according to the similarity, wherein the calculation of the similarity between the unassigned tasks can be used A similar method of calculating the similarity mentioned above.
  • the first quantity threshold for example, less than 2
  • the first quantity threshold for example, less than 2
  • the similarity between these unallocated tasks needs to be calculated; then these unallocated tasks
  • the step of assigning an unallocated task to a distribution resource according to the similarity in step S403 includes steps S501-S504:
  • step S501 clustering processing the unallocated task according to the distance information of the unallocated task to obtain a task class
  • step S502 each task class is grouped according to the similarity to obtain a task group
  • step S503 calculating a matching degree between each task group and a distribution resource
  • step S504 the unallocated task is assigned to the distribution resource according to the matching degree.
  • the unallocated task is clustered according to the distance information of the unassigned task to obtain one or more task classes, wherein the distance information of the unassigned task may include the distance between the unassigned task merchant addresses and / or the distance between the task user addresses is not assigned.
  • the classified business circle of the unassigned task business address or the user address may be classified, and the unallocated tasks belonging to the same business circle may be regarded as one task class; or may be classified according to the distance clustering method, for example: from any When the task A is started, the unassigned tasks whose merchant address distance is less than X kilometers and whose user address distance is less than Y kilometers are classified into one class.
  • the unassigned task B and the unassigned task C are also divided.
  • the size of the class gradually becomes larger. Iteratively, other unallocated tasks that are closer to the unassigned task B are selected to be merged into the class. If no new unassigned tasks can be merged, then another one is re-established.
  • the new class the generation of the new class is similar to the generation process of the previous class.
  • Each task class is then grouped according to the similarity to obtain one or more task groups.
  • the unassigned tasks in each task class can be grouped according to the similarity between the unassigned tasks, and one or more task groups are obtained, wherein the specific similarity grouping criteria can be performed according to the needs of the actual application.
  • the setting is not specifically limited in the present disclosure.
  • the above-described method of grouping the clusters first can reduce the time complexity, that is, reduce the time used, because in the case where the number of distribution tasks is very large, direct grouping can lead to long time consuming.
  • the degree of matching between each task group and the distribution resource is calculated, and the unallocated task is allocated to the distribution resource according to the matching degree.
  • the step S503 that is, the step of calculating the matching degree between each task group and the distribution resource, includes steps S601-S602:
  • step S601 determining a matching evaluation element
  • step S602 the matching degree between each task group and the distribution resource is calculated by using the matching evaluation element.
  • the matching evaluation element includes: a distance between a location of the task group merchant and a location where the distribution resource is empty, a remaining time of the task group, a time required for the delivery resource to reach an idle state, an estimated timeout information of the distribution resource delivery task group, One or more of the distribution resource speed and the distribution resource score.
  • One or more matching evaluation elements in the speed and distribution resource scores, and the matching degree between each task group and the distribution resource is calculated, thereby determining whether the task group is suitable for allocation to the distribution resource, wherein the distribution resource is empty
  • the term refers to the state when the distribution resource completes all the distribution tasks assigned to him; the distribution resource score refers to the rating of the service evaluation of the distribution resource by the merchant or the user; the remaining time of the task group refers to a task group from the merchant or the user.
  • the remaining time of the specified delivery time can be taken as the average of the remaining time in the task group, or the longest or shortest remaining time value in the task group.
  • each of the matching evaluation elements may be mapped into a specific evaluation value, and then each matching evaluation element is assigned a different weight, and finally weighted based on the evaluation value and the corresponding weight. Summing, you can get the match.
  • the conversion manner of the matching evaluation element to the evaluation value and the value of the weight of each matching evaluation element can be set according to the needs of the actual application, and the disclosure does not particularly limit it, and all reasonable and feasible conversion methods and setting methods are adopted. All fall within the scope of protection of the present disclosure.
  • other matching evaluation elements may also be selected according to the needs of the actual application, and the disclosure is not described one by one.
  • the matching degree lower than a preset matching threshold may be filtered first, so that the assignment of the task group to the matching degree can be excluded.
  • the step S504 that is, the step of allocating the unallocated task to the distribution resource according to the matching degree, includes steps S701-S702:
  • step S701 the unallocated task is pre-allocated to the distribution resource according to the size of the matching degree
  • step S702 the unallocated task is assigned to the distribution resource in response to the delivery information satisfying the second preset condition.
  • the second preset condition includes: the task group times out after the preset time, the number of the distribution resources to be delivered is lower than the second quantity threshold, and the time required for the delivery resource to reach the idling is lower than the preset time threshold. One or more.
  • a pre-allocation policy is adopted, that is, the unallocated task is pre-allocated to a certain distribution resource according to the size of the matching degree, and when the to-be-allocated information satisfies the second preset condition, the unallocated task is actually allocated to the unallocated task. If the matching degree is changed before the allocation information satisfies the second preset condition, the unallocated task may be pre-allocated to other distribution resources according to the updated matching degree, and then the remaining delivery information satisfies the second pre-requisite The final task assignment is performed when the condition is set.
  • the above pre-allocation strategy can help to find a global optimal solution, and assign the distribution task to a truly suitable distribution resource according to the global optimal solution.
  • FIG. 8 is a block diagram showing the structure of a delivery task processing apparatus according to an embodiment of the present disclosure, which may be implemented as part or all of an electronic device by software, hardware, or a combination of both.
  • the delivery task processing apparatus includes: a first determining module 801, a second determining module 802, and a first assigning module 803:
  • the first determining module 801 is configured to determine a similarity between the task to be assigned and the task to be delivered;
  • the second determining module 802 is configured to determine the corresponding distribution resource as the candidate distribution resource in response to the similarity meeting the first preset condition
  • the first allocating module 803 is configured to allocate the to-be-assigned task to the target delivery resource in the candidate distribution resource, and the similarity between the task to be delivered and the task to be assigned is the highest.
  • the first determining module 801, the second determining module 802, and the first assigning module 803 will be further described below.
  • the quality of service depends on stable, reliable, fast and punctual delivery services.
  • most of the relevant technologies are based on the distribution and scheduling of distribution tasks in the business circle. For example, multiple distributors responsible for different business districts. When the system receives a new delivery service, it first determines which business district the delivery address belongs to, and then assigns the corresponding delivery task to the distributor responsible for the business circle.
  • the distributors responsible for the adjacent business districts may have fewer tasks, which leads to a lot of dispatchers.
  • the users in the responsible business circle cannot receive the goods in time, while the dispatchers with few tasks are nearby, but they cannot serve the users.
  • Embodiments of the present disclosure provide a solution for allocating and processing a delivery task in a wide area, such as a city, to avoid problems existing in the related art.
  • a wide area such as a city
  • the assignment of the distribution task is performed by using the similarity between the task to be assigned and the delivery task that has been allocated to the delivery resource but not completed, that is, the similarity between the tasks to be delivered, that is, first through the first
  • the determination module 801 calculates the similarity between the task to be assigned and the task to be delivered.
  • the distribution resource includes a distributor and other distribution resources.
  • the determining module 802 determines the corresponding distribution resource as a distribution resource suitable for accepting the delivery task, that is, a candidate distribution resource.
  • the first distribution module 803 may select the distribution resource whose task to be delivered has the highest similarity to the task to be assigned from among the plurality of candidate distribution resources. Finally, the distribution resources of the task to be assigned are taken.
  • the above embodiment provides a new delivery task processing solution, which provides stable, reliable, fast, and timely delivery to users by performing similarity-based processing and scheduling in a wide area, such as a citywide distribution task.
  • the purpose of the service The embodiments of the present disclosure have strong adaptability, wide service coverage, and high distribution efficiency, and can provide distribution solutions for various types of O2O platforms to meet the needs of merchants and users for wide-area distribution, and to facilitate the use of merchants and users.
  • the first determining module 801 includes a first determining submodule 901 and a first calculating submodule 902:
  • a first determining submodule 901 configured to determine a similarity evaluation element
  • the first calculation sub-module 902 is configured to calculate the similarity between the task to be assigned and the task to be delivered by using the similarity evaluation element.
  • the similarity evaluation element includes one or more of a delivery task merchant address, a delivery task user address, and a desired delivery time.
  • the first calculation sub-module 902 calculates the to-be-allocated based on one or more similarity evaluation elements of the delivery task merchant address, the delivery task user address, and the expected delivery time determined by the first determination sub-module 901.
  • the similarity between the task and the task to be delivered For example, the closer the merchants of the two tasks to be assigned are, the closer the user is, and the closer the expected delivery time is, the more similar the two tasks to be assigned are. High, the more suitable for the same distribution resource, or the more suitable for the merger with the task to be delivered.
  • the similarity evaluation element may also adopt other elements that can reflect the similarity between the delivery tasks.
  • the disclosure is not listed one by one, and all the elements capable of evaluating the similarity between the delivery tasks fall within the protection scope of the disclosure.
  • the first preset condition includes:
  • the similarity between the task to be assigned and the task to be delivered is higher than or equal to a preset similarity threshold; and/or,
  • the number of tasks to be assigned with the similarity higher than or equal to the preset similarity threshold is higher than or equal to the preset proportional threshold in all the tasks to be delivered of the distribution resource.
  • the second determining module 802 includes a second determining submodule 1001 and a third determining submodule 1002:
  • the second determining sub-module 1001 is configured to determine a proportion of the number of tasks whose similarity is higher than or equal to the preset similarity threshold in all the tasks to be delivered of the distribution resource;
  • the third determining sub-module 1002 is configured to determine the distribution resource as a candidate distribution resource if the ratio is higher than or equal to a preset ratio threshold.
  • the third determining sub-module 1002 determines by determining the second determining sub-module 1001.
  • the proportion of the number of tasks whose similarity is higher than or equal to the preset similarity threshold in all the tasks to be delivered of the distribution resource is higher than or equal to the preset ratio threshold to determine an appropriate distribution resource. For example, if the score between the tasks to be assigned and the tasks of the distribution resource that are half or more of the tasks to be delivered are higher than or equal to the preset similarity threshold, the task to be assigned is considered to be assignable to the distribution resource, and the distribution resource Can be considered as a candidate distribution resource.
  • the highest similarity obtained by comparing the task to be assigned with all the tasks to be delivered of the distribution resource may be used as the similarity of the distribution resource, and then the task to be assigned is allocated to the distribution resource with the highest similarity.
  • the values of the similarity threshold and the proportional threshold may be determined according to the needs of the actual application, and the disclosure is not specifically limited.
  • the distribution pressure value of the area where the distribution resource is located may be considered, and the size of the distribution pressure value is related to the number of tasks to be delivered in the area, and the distribution task has more distribution pressure values.
  • the similarity threshold is higher, which enables the distribution resource to complete the assigned delivery task as soon as possible and improve the user experience.
  • the apparatus further includes a third determining module 1101 and a second assigning module 1102:
  • the third determining module 1101 is configured to determine the number of unassigned tasks
  • the second allocation module 1102 is configured to allocate the unallocated task to a distribution resource if the number of unallocated tasks is less than the first quantity threshold, and the similarity between the distribution resource to be delivered task and the unallocated task is the highest; If the number of unassigned tasks is greater than or equal to the first number of thresholds, the similarity between the unallocated tasks is calculated, and the unallocated tasks are assigned to the distribution resources according to the similarities.
  • the third determining module 1101 determines the number of the delivery tasks remaining after the above-mentioned allocation operation, that is, the number of unallocated tasks that are not sufficiently high in similarity with other tasks to be delivered, and which are not similar to a certain distribution resource; If the number of unassigned tasks is less than the first quantity threshold, for example, less than 2, the second allocation module 1102 directly assigns the unallocated task to the delivery resource with the highest similarity between the task to be delivered and the unallocated task; if the task is not assigned If the quantity is greater than or equal to the first quantity threshold, for example, greater than or equal to 2, the second allocation module 1102 needs to first calculate the similarity between the unallocated tasks; and then assign the unallocated tasks to the distribution according to the similarity.
  • a resource in which the calculation of the similarity between unallocated tasks can adopt a method similar to the calculation of the similarity mentioned above.
  • the second distribution module 1102 includes:
  • the clustering sub-module 1201 is configured to perform clustering processing on the unallocated tasks according to the distance information of the unassigned tasks to obtain one or more task classes;
  • the grouping sub-module 1202 is configured to group each task class according to the similarity to obtain one or more task groups;
  • a second calculation sub-module 1203 configured to calculate a degree of matching between each task group and a distribution resource
  • the assignment sub-module 1204 is configured to assign the unassigned task to a distribution resource based on the degree of matching.
  • the clustering sub-module 1201 performs clustering processing on the unallocated task according to the distance information of the unassigned task to obtain one or more task classes, where the distance information of the unassigned task may include the unassigned task merchant address.
  • the distance between the distance and/or the unassigned task user address For example, the classified business circle of the unassigned task business address or the user address may be classified, and the unallocated tasks belonging to the same business circle may be regarded as one task class; or may be classified according to the distance clustering method, for example: from any When the task A is started, the unassigned tasks whose merchant address distance is less than X kilometers and whose user address distance is less than Y kilometers are classified into one class.
  • the unassigned task B and the unassigned task C are also divided.
  • the size of the class gradually becomes larger. Iteratively, other unallocated tasks that are closer to the unassigned task B are selected to be merged into the class. If no new unassigned tasks can be merged, then another one is re-established.
  • the new class the generation of the new class is similar to the generation process of the previous class.
  • the grouping sub-module 1202 groups each task class according to the similarity to obtain one or more task groups.
  • the unassigned tasks in each task class can be grouped according to the similarity between the unassigned tasks, and one or more task groups are obtained, wherein the specific similarity grouping criteria can be performed according to the needs of the actual application.
  • the setting is not specifically limited in the present disclosure.
  • the above-described method of grouping the clusters first can reduce the time complexity, that is, reduce the time used, because in the case where the number of distribution tasks is very large, direct grouping can lead to long time consuming.
  • the second calculation sub-module 1203 calculates the degree of matching between each task group and the distribution resource, and the distribution sub-module 1204 assigns the unallocated task to the distribution resource according to the matching degree.
  • the second calculating submodule 1203 includes a determining unit 1301 and a calculating unit 1302:
  • a determining unit 1301 configured to determine a matching evaluation element
  • the calculating unit 1302 is configured to calculate a matching degree between each task group and the distribution resource by using the matching evaluation element.
  • the matching evaluation element includes: a distance between a location of the task group merchant and a location where the distribution resource is empty, a remaining time of the task group, a time required for the delivery resource to reach an idle state, an estimated timeout information of the distribution resource delivery task group, One or more of the distribution resource speed and the distribution resource score.
  • the calculating unit 1302 uses the determining unit 1301 to determine the distance between the task group merchant location and the location where the distribution resource is empty, the remaining time of the task group, the time required for the distribution resource to reach the no-load state, and the distribution resource distribution.
  • the task group estimates one or more matching evaluation elements in the timeout information, the distribution resource speed, and the distribution resource score, and calculates a matching degree between each task group and the distribution resource, thereby determining whether the task group is suitable for the assignment.
  • the distribution resource wherein the distribution resource empty refers to the state when the distribution resource completes all the distribution tasks assigned to him; the distribution resource score refers to the rating of the service evaluation of the distribution resource by the merchant or the user; the remaining time of the task group refers to It is the remaining time of the task group's delivery time specified by the merchant or user. It can take the average of the remaining time in the task group, or the longest or shortest remaining time value in the task group.
  • the calculating unit 1302 may map each of the matching evaluation elements into a specific evaluation value, and then assign different weights to each matching evaluation element, and finally based on the evaluation value and the corresponding The weights are weighted and summed to obtain the matching degree.
  • the conversion manner of the matching evaluation element to the evaluation value and the value of the weight of each matching evaluation element can be set according to the needs of the actual application, and the disclosure does not particularly limit it, and all reasonable and feasible conversion methods and setting methods are adopted. All fall within the scope of protection of the present disclosure.
  • other matching evaluation elements may also be selected according to the needs of the actual application, and the disclosure is not described one by one.
  • the matching degree below a preset matching threshold may also be filtered first, so that the task group can be excluded from being assigned.
  • the distribution submodule 1204 includes a first allocation unit 1401 and a second allocation unit 1402:
  • the first allocating unit 1401 is configured to pre-allocate the unallocated task to the distribution resource according to the size of the matching degree;
  • the second allocating unit 1402 is configured to allocate the unallocated task to the distribution resource in response to the delivery information satisfying the second preset condition.
  • the second preset condition includes: one of the task group times out after the preset time, the number of the distribution resource delivery tasks is lower than the second quantity threshold, and the time required for the delivery resource to reach the idling time is lower than the preset time threshold.
  • the pre-allocation policy is adopted, that is, the first allocating unit 1401 pre-allocates the unallocated task to a certain distribution resource according to the size of the matching degree, and when the to-be-allocated information satisfies the second preset condition, the second allocation The unit 1402 then real allocates the unallocated task to the distribution resource. If the matching degree changes before the allocation information satisfies the second preset condition, the unallocated task may be pre-allocated to other distribution resources according to the updated matching degree. Then, the final task assignment is performed when the delivery information satisfies the second preset condition.
  • the above pre-allocation strategy can help to find a global optimal solution, and assign the distribution task to a truly suitable distribution resource according to the global optimal solution.
  • FIG. 15 is a block diagram showing the structure of an electronic device according to an embodiment of the present disclosure. As shown in FIG. 15, the electronic device 1500 includes a memory 1501 and a processor 1502.
  • the memory 1501 is configured to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor 1502 to:
  • the similarity between the task to be delivered and the task to be assigned of the target delivery resource is the highest.
  • the one or more computer instructions can also be executed by the processor 1602 to:
  • the determining the similarity between the task to be assigned and the task to be delivered includes:
  • the similarity evaluation element is used to calculate the similarity between the task to be assigned and the task to be delivered.
  • the first preset condition includes:
  • the similarity between the task to be assigned and the task to be delivered is higher than or equal to a preset similarity threshold; and/or,
  • the number of tasks to be assigned with the similarity higher than or equal to the preset similarity threshold is higher than or equal to the preset proportional threshold in all the tasks to be delivered of the distribution resource.
  • the one or more computer instructions can also be executed by the processor to:
  • the unallocated task is assigned to a distribution resource, and the distribution resource to be delivered task has the highest similarity with the unallocated task.
  • the one or more computer instructions can also be executed by the processor to:
  • Unallocated tasks are assigned to distribution resources based on the similarity.
  • the assigning the unallocated task to the distribution resource according to the similarity includes:
  • Each task class is grouped according to the similarity to obtain a task group
  • the unallocated task is assigned to the distribution resource according to the matching degree.
  • the calculating the matching degree between each task group and the distribution resource includes:
  • the matching degree between the task group and the distribution resource is calculated by using the matching evaluation element.
  • the matching evaluation element includes: a distance between the location of the task group merchant and the location where the distribution resource is empty, a remaining time of the task group, a time required for the delivery resource to reach the no-load state, a distribution resource distribution, an estimated timeout information of the task group, and a distribution resource.
  • One or more of speed, distribution resource scores are included in the distribution resource.
  • the unallocated task is assigned to the distribution resource in response to the delivery information satisfying a second predetermined condition.
  • the second preset condition includes: one of a task group timeout after a preset time, a quantity of a distribution resource to be delivered is lower than a second quantity threshold, and a time required for the delivery resource to reach a no-load time is lower than a preset time threshold. Or a variety.
  • 16 is a block diagram showing a configuration of a computer system suitable for implementing a delivery task processing method according to an embodiment of the present disclosure.
  • computer system 1600 includes a central processing unit (CPU) 1601 that can be loaded into a program in random access memory (RAM) 1603 from a program stored in read only memory (ROM) 1602 or from storage portion 1608.
  • CPU central processing unit
  • RAM random access memory
  • ROM read only memory
  • storage portion 1608 stores data.
  • the various processes in the embodiment shown in Fig. 1 described above are executed.
  • RAM 1603 various programs and data required for the operation of the system 1600 are also stored.
  • the CPU 1601, the ROM 1602, and the RAM 1603 are connected to each other through a bus 1604.
  • An input/output (I/O) interface 1605 is also coupled to bus 1604.
  • the following components are connected to the I/O interface 1605: an input portion 1606 including a keyboard, a mouse, etc.; an output portion 1607 including a cathode ray tube (CRT), a liquid crystal display (LCD), and the like, and a speaker; a storage portion 1608 including a hard disk or the like And a communication portion 1609 including a network interface card such as a LAN card, a modem, or the like.
  • the communication section 1609 performs communication processing via a network such as the Internet.
  • Driver 1610 is also coupled to I/O interface 1605 as needed.
  • a removable medium 1611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory or the like, is mounted on the drive 1610 as needed so that a computer program read therefrom is installed into the storage portion 1608 as needed.
  • an embodiment of the present disclosure includes a computer program product comprising a computer program tangibly embodied on a readable medium therewith, the computer program comprising program code for performing the delivery task processing method of FIG.
  • the computer program can be downloaded and installed from the network via communication portion 1609, and/or installed from removable media 1611.
  • each block in the diagram or block diagram can represent a module, a program segment, or a portion of code that includes one or more of Executable instructions.
  • the functions noted in the blocks may also occur in a different order than that illustrated in the drawings. For example, two successively represented blocks may in fact be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending upon the functionality involved.
  • each block of the block diagrams and/or flowcharts, and combinations of blocks in the block diagrams and/or flowcharts can be implemented in a dedicated hardware-based system that performs the specified function or operation. Or it can be implemented by a combination of dedicated hardware and computer instructions.
  • the units or modules described in the embodiments of the present disclosure may be implemented by software or by hardware.
  • the described units or modules may also be provided in a processor, the names of which do not in any way constitute a limitation of the unit or module itself.
  • the present disclosure further provides a computer readable storage medium, which may be a computer readable storage medium included in the apparatus in the above embodiment; or may exist separately, not A computer readable storage medium that is assembled into the device.
  • a computer readable storage medium stores one or more programs that are used by one or more processors to perform the methods described in the present disclosure.

Landscapes

  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Engineering & Computer Science (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Development Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Educational Administration (AREA)
  • Game Theory and Decision Science (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

一种配送任务处理方法、装置及电子设备，所述方法包括：确定待分配任务与待配送任务之间的相似度（S101）；响应于相似度满足第一预设条件，将相应的配送资源确定为候选配送资源（S102）；将所述待分配任务分配给所述候选配送资源中的目标配送资源，所述目标配送资源的待配送任务与所述待分配任务之间的相似度最高（S103）。该方法适应性强、服务覆盖面广、配送效率高，能够为各类型的O2O平台提供配送解决方案，以适应商户、用户的广域配送需求，为商户、用户的使用提供便利。

Description

配送任务处理方法、装置及电子设备 技术领域
本公开涉及数据处理技术领域，具体涉及一种配送任务处理方法、装置及电子设备。
背景技术
随着互联网技术的快速发展，大量O2O(线上对线下，Online To Offline)平台如雨后春笋出现并快速成长，发展至今，O2O服务已经改变了人们的生活，比如，物流行业改变了人们的购物方式，外卖行业改变了人们的餐饮行为。但无论是物流还是外卖，其服务质量都依赖于稳定、可靠、快捷、准时的配送服务，可以说，高质量的配送服务是获得用户信赖和提高企业核心竞争力的重要手段。
发明内容
本公开实施例提供一种配送任务处理方法、装置及电子设备。
第一方面，本公开实施例中提供了一种配送任务处理方法。
具体的，所述配送任务处理方法，包括：
确定待分配任务与待配送任务之间的相似度；
响应于相似度满足第一预设条件，将相应的配送资源确定为候选配送资源；
将所述待分配任务分配给所述候选配送资源中的目标配送资源，所述目标配送资源的待配送任务与所述待分配任务之间的相似度最高。
结合第一方面，本公开在第一方面的第一种实现方式中，所述确定待分配任务与待配送任务之间的相似度，包括：
确定相似度评价元素；
利用所述相似度评价元素计算待分配任务与待配送任务之间的相似度。
其中，所述第一预设条件包括：
所述待分配任务与待配送任务之间的相似度高于或等于预设相似度阈值；和/或，
所述相似度高于或等于预设相似度阈值的待分配任务数量在配送资源所有待配送任务中所占比例高于或等于预设比例阈值。
结合第一方面或第一方面的第一种实现方式，本公开在第一方面的第二种实现方式中，所述方法还包括：
确定未分配任务数量；
若未分配任务数量小于第一数量阈值，将所述未分配任务分配给一配送资源，所述配送资源待配送任务与所述未分配任务的相似度最高；若未分配任务数量大于或等于所述第一数量阈值，计算未分配任务之间的相似度，并根据所述相似度将未分配任务分配给配送资源。
结合第一方面、第一方面的第一种实现方式或第一方面的第二种实现方式，本公开在第一方面的第三种实现方式中，所述根据相似度将未分配任务分配给配送资源，包括：
根据未分配任务的距离信息对于未分配任务进行聚类处理得到任务类；
根据所述相似度对于每一任务类进行分组，得到任务组；
计算每一任务组与配送资源之间的匹配度；
根据所述匹配度将所述未分配任务分配给配送资源。
结合第一方面、第一方面的第一种实现方式或第一方面的第二种实现方式，本公开在第一方面的第三种实现方式中，所述计算每一任务组与配送资源之间的匹配度，包括：
确定匹配评价元素；
利用所述匹配评价元素计算每一任务组与配送资源之间的匹配度。
其中，所述匹配评价元素包括：任务组商户位置与配送资源空载时所在位置的距离、任务组的剩余时间、配送资源达到空载状态所需时间、 配送资源配送该任务组估计超时信息、配送资源速度、配送资源评分中的一种或多种。
结合第一方面、第一方面的第一种实现方式或第一方面的第二种实现方式，本公开在第一方面的第三种实现方式中，所述根据所述匹配度将所述未分配任务分配给配送资源，包括：
按照所述匹配度的大小将所述未分配任务预分配给配送资源；
响应于配送信息满足第二预设条件，将所述未分配任务分配给所述配送资源。
其中，所述第二预设条件包括：任务组在预设时间后超时、配送资源待配送任务数量低于第二数量阈值、配送资源预计达到空载所需时间低于预设时间阈值中的一种或多种。
第二方面，本公开实施例提供了一种配送任务处理装置，所述装置包括：
第一确定模块，被配置为确定待分配任务与待配送任务之间的相似度；
第二确定模块，被配置为响应于相似度满足第一预设条件，将相应的配送资源确定为候选配送资源；
第一分配模块，被配置为将所述待分配任务分配给所述候选配送资源中的目标配送资源，所述目标配送资源的待配送任务与所述待分配任务之间的相似度最高。
结合第二方面，本公开在第二方面的第一种实现方式中，所述第一确定模块包括：
第一确定子模块，被配置为确定相似度评价元素；
第一计算子模块，被配置为利用所述相似度评价元素计算待分配任务与待配送任务之间的相似度。
其中，所述第一预设条件包括：
所述待分配任务与待配送任务之间的相似度高于或等于预设相似度阈值；和/或，
所述相似度高于或等于预设相似度阈值的待分配任务数量在配送 资源所有待配送任务中所占比例高于或等于预设比例阈值。
结合第二方面、第二方面的第一种实现方式或第二方面的第二种实现方式，本公开在第二方面的第三种实现方式中，所述装置还包括：
第三确定模块，被配置为确定未分配任务数量；
第二分配模块，被配置为若未分配任务数量小于第一数量阈值，将所述未分配任务分配给一配送资源，所述配送资源待配送任务与所述未分配任务的相似度最高；
若未分配任务数量大于或等于所述第一数量阈值，计算未分配任务之间的相似度，并根据所述相似度将未分配任务分配给配送资源。
结合第二方面、第二方面的第一种实现方式或第二方面的第二种实现方式，本公开在第二方面的第三种实现方式中，所述第三分配模块包括：
聚类子模块，被配置为根据未分配任务的距离信息对于未分配任务进行聚类处理得到任务类；
分组子模块，被配置为根据所述相似度对于每一任务类进行分组，得到任务组；
第二计算子模块，被配置为计算每一任务组与配送资源之间的匹配度；
分配子模块，被配置为根据所述匹配度将所述未分配任务分配给配送资源。
结合第二方面、第二方面的第一种实现方式或第二方面的第二种实现方式，本公开在第二方面的第三种实现方式中，所述第二计算子模块包括：
确定单元，被配置为确定匹配评价元素；
计算单元，被配置为利用所述匹配评价元素计算每一任务组与配送资源之间的匹配度。
其中，所述匹配评价元素包括：任务组商户位置与配送资源空载时所在位置的距离、任务组的剩余时间、配送资源达到空载状态所需时间、配送资源配送该任务组估计超时信息、配送资源速度、配送资源评分中 的一种或多种。
结合第二方面、第二方面的第一种实现方式或第二方面的第二种实现方式，本公开在第二方面的第三种实现方式中，所述分配子模块包括：
第一分配单元，被配置为按照所述匹配度的大小将所述未分配任务预分配给配送资源；
第二分配单元，被配置为响应于配送信息满足第二预设条件，将所述未分配任务分配给所述配送资源。
其中，所述第二预设条件包括：任务组在预设时间后超时、配送资源待配送任务数量低于第二数量阈值、配送资源预计达到空载所需时间低于预设时间阈值中的一种或多种。
第三方面，本公开实施例提供了一种电子设备，包括存储器和处理器，所述存储器用于存储一条或多条支持配送任务处理装置执行上述第一方面中配送任务处理方法的计算机指令，所述处理器被配置为用于执行所述存储器中存储的计算机指令。所述配送任务处理装置还可以包括通信接口，用于配送任务处理装置与其他设备或通信网络通信。
第四方面，本公开实施例提供了一种计算机可读存储介质，用于存储配送任务处理装置所用的计算机指令，其包含用于执行上述第一方面中配送任务处理方法为配送任务处理装置所涉及的计算机指令。
本公开实施例提供了一种新的配送任务处理方案，通过对于配送任务在广域，比如全城范围内进行基于相似度的处理和调度，来达到稳定、可靠、快捷、准时地为用户提供配送服务的目的。本公开实施例适应性强、服务覆盖面广、配送效率高，能够为各类型的O2O平台提供配送解决方案，以适应商户、用户的广域配送需求，为商户、用户的使用提供便利。
应当理解的是，以上的一般描述和后文的细节描述仅是示例性和解释性的，并不能限制本公开。
附图说明
结合附图，通过以下非限制性实施方式的详细描述，本公开的其它特征、目的和优点将变得更加明显。在附图中：
图1示出根据本公开一实施方式的配送任务处理方法的流程图；
图2示出根据图1所示实施方式的步骤S101的流程图；
图3示出根据图1所示实施方式的步骤S102的流程图；
图4示出根据本公开另一实施方式的配送任务处理方法中对未分配任务进行分配的步骤的流程图；
图5示出根据图4所示实施方式的步骤S403的流程图；
图6示出根据图5所示实施方式的步骤S503的流程图；
图7示出根据图5所示实施方式的步骤S504的流程图；
图8示出根据本公开一实施方式的配送任务处理装置的结构框图；
图9示出根据图8所示实施方式的第一确定模块801的结构框图；
图10示出根据图8所示实施方式的第二确定模块802的结构框图；
图11示出根据本公开另一实施方式的配送任务处理装置中对未分配任务进行分配的部分的结构框图；
图12示出根据图11所示实施方式的第二分配模块1102的结构框图；
图13示出根据图12所示实施方式的第二计算子模块1203的结构框图；
图14示出根据图12所示实施方式的分配子模块1204的结构框图；
图15示出根据本公开一实施方式的电子设备的结构框图；
图16是适于用来实现根据本公开一实施方式的配送任务处理方法的计算机系统的结构示意图。
具体实施方式
下文中，将参考附图详细描述本公开的示例性实施方式，以使本领域技术人员可容易地实现它们。此外，为了清楚起见，在附图中省略了与描述示例性实施方式无关的部分。
在本公开中，应理解，诸如“包括”或“具有”等的术语旨在指示本说明书中所公开的特征、数字、步骤、行为、部件、部分或其组合的存在，并且不欲排除一个或多个其他特征、数字、步骤、行为、部件、部分或其组合存在或被添加的可能性。
另外还需要说明的是，在不冲突的情况下，本公开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公开。
本公开实施例提供了一种新的配送任务处理方案，通过对于配送任务在广域，比如全城范围内进行基于相似度的处理和调度，来达到稳定、可靠、快捷、准时地为用户提供配送服务的目的。本公开实施例适应性强、服务覆盖面广、配送效率高，能够为各类型的O2O平台提供配送解决方案，以适应商户、用户的广域配送需求，为商户、用户的使用提供便利。
图1示出根据本公开一实施方式的配送任务处理方法的流程图。如图1所示，所述配送任务处理方法包括以下步骤S101-S103：
在步骤S101中，确定待分配任务与待配送任务之间的相似度；
在步骤S102中，响应于相似度满足第一预设条件，将相应的配送资源确定为候选配送资源；
在步骤S103中，将所述待分配任务分配给所述候选配送资源中的目标配送资源，所述目标配送资源的待配送任务与所述待分配任务之间的相似度最高。
在下文中将对步骤S101、S102和S103分别做进一步的描述。
步骤S101
上文提及，无论是物流还是外卖，其服务质量都依赖于稳定、可靠、快捷、准时的配送服务，目前有关技术大多基于商圈对于配送任务进行分配和调度，比如，多个配送者各自负责不同的商圈，当系统接收到新的配送服务时，首先判断收货地址属于哪个商圈，然后将相应的配送任务分配给负责这个商圈的配送者。但是上述基于商圈的配送服务处理方法有很多不足，比如负责某一商圈的配送者任务很多，但负责相邻商圈 的配送者有可能任务很少，这样就导致任务很多的配送者所负责的商圈里的用户不能及时收到货物，而任务很少的配送者就在附近，却不能够为用户进行服务。
本公开实施例提供一种在广域，比如全城范围内对于配送任务进行分配、处理的方案，以避免出现上述有关技术所存在的问题。在广域范围内，为了实现稳定、可靠、快捷、准时地为用户提供配送服务，需要对于待分配任务进行准确的分配。在本公开一实施例中，利用待分配任务与已分配给配送资源但并未完成的配送任务，即待配送任务之间的相似度来进行配送任务的分配，也就是说，首先需要计算待分配任务与待配送任务之间的相似度。其中，所述配送资源包括配送者也包括其他配送资源。
步骤S102
然后判断所述相似度是否满足一些预设条件，这些预设条件能够表征将某一配送任务分配给某一配送资源是否合适，那么当所述相似度确定满足第一预设条件时，就将相应的配送资源确定为适合接受该配送任务的配送资源，即候选配送资源。
步骤S103
适合的配送资源可能有很多，为了更快捷迅速地完成配送任务，可以从众多候选配送资源中，选择其待配送任务与所述待分配任务具有最高相似度的配送资源，作为最终承接该待分配任务的配送资源。
上述实施例提供了一种新的配送任务处理方案，通过对于配送任务在广域，比如全城范围内进行基于相似度的处理和调度，来达到稳定、可靠、快捷、准时地为用户提供配送服务的目的。本公开实施例适应性强、服务覆盖面广、配送效率高，能够为各类型的O2O平台提供配送解决方案，以适应商户、用户的广域配送需求，为商户、用户的使用提供便利。
在本实施例的一个可选实现方式中，如图2所示，所述步骤S101，即确定待分配任务与待配送任务之间的相似度的步骤，包括步骤S201-S202：
在步骤S201中，确定相似度评价元素；
在步骤S202中，利用所述相似度评价元素计算待分配任务与待配送任务之间的相似度。
其中，所述相似度评价元素包括：配送任务商户地址、配送任务用户地址、期望送达时间中的一种或多种。
在该实现方式中，基于配送任务商户地址、配送任务用户地址、期望送达时间中的一种或多种相似度评价元素来计算待分配任务与待配送任务之间的相似度，比如，两个待分配任务的商户离得越近、用户的位置越近、期望送达的时间越接近，就说明这两个待分配任务相似度越高，越适合分配给同一个配送资源，或者说越适合与待配送任务进行合并处理。当然，相似度评价元素还可以采用其他能够体现配送任务之间相似度的元素，本公开不再一一列举，所有能够评价配送任务之间相似度的元素均落入本公开的保护范围内。
在本实施例的一个可选实现方式中，所述第一预设条件包括：
所述待分配任务与待配送任务之间的相似度高于或等于预设相似度阈值；和/或，
所述相似度高于或等于预设相似度阈值的待分配任务数量在配送资源所有待配送任务中所占比例高于或等于预设比例阈值。
在该实现方式中，如图3所示，所述步骤S102，即响应于相似度满足第一预设条件，将相应的配送资源确定为候选配送资源的步骤，包括步骤S301-S302：
在步骤S301中，确定相似度高于或等于预设相似度阈值的任务数量在配送资源所有待配送任务中所占的比例；
在步骤S302中，若所述比例高于或等于预设比例阈值，将所述配送资源确定为候选配送资源。
为了更准确地判断将待分配任务分配给哪个配送资源合适，或者说与哪些待配送任务合并处理比较合适，在上述实现方式中，通过判断相似度高于或等于预设相似度阈值的任务数量在配送资源所有待配送任务中所占的比例，是否高于或等于预设比例阈值，来确定合适的配送资 源。比如，若待分配任务与配送资源所有待配送任务中一半及以上的任务之间的分值均高于或等于预设相似度阈值，则认为待分配任务可分配给该配送资源，该配送资源可被认为是候选配送资源。
满足以上条件的候选配送资源可能会有多个，那么就需要再在多个候选配送资源中选出最为适合的一个配送资源。可选地，可以将待分配任务与配送资源所有待配送任务相比较得到的最高相似度作为该配送资源的相似度，然后将所述待分配任务分配给相似度最高的这个配送资源。
其中，相似度阈值和比例阈值的取值均可根据实际应用的需要来确定，本公开不作具体限定。
需要说明的是，在确定相似度阈值的取值时，可考虑配送资源所在区域的配送压力值，配送压力值的大小与该区域需要配送的任务的多少有关，配送任务越多，配送压力值就越大，配送压力值越大，就说明配送任务越容易被合并处理，相似度阈值也就越低，这样能够减少配送资源行走的距离，节省运力；相反，某一区域需要配送的任务越少，配送压力值就越小，配送任务就越难被合并处理，相应的，相似度阈值也就越高，这样能够使得配送资源尽快完成已分配的配送任务，提升用户体验。
在本公开另一实施例中，如图4所示，所述方法还包括步骤S401-S403：
在步骤S401中，确定未分配任务数量；
在步骤S402中，若未分配任务数量小于第一数量阈值，将所述未分配任务分配给一配送资源，所述配送资源待配送任务与所述未分配任务的相似度最高；
在步骤S403中，若未分配任务数量大于或等于所述第一数量阈值，计算未分配任务之间的相似度，根据所述相似度将未分配任务分配给配送资源。
从上文的描述中可以看出，相似度足够大、与某一配送资源相似的任务足够多的待配送任务才有可能会被分配和处理，在本实施例中，将 解释对于经过上述分配后剩余的任务，即与其他待配送任务相似度不够高、与某一配送资源相似的任务也不够多的未分配任务如何处理。
首先确定经过上述分配操作后剩余的配送任务的数量，即上述与其他待配送任务相似度不够高、与某一配送资源相似的任务也不够多的未分配任务的数量；若未分配任务数量小于第一数量阈值，比如，小于2，则直接将该未分配任务分配给待配送任务与所述未分配任务相似度最高的那个配送资源；若未分配任务数量大于或等于所述第一数量阈值，比如，大于或等于2，则需要计算这些未分配任务之间的相似度；然后再根据相似度将这些未分配任务分配给配送资源，其中，未分配任务之间相似度的计算可以采用与上文提及的相似度的计算相似的方法。
在本实施例的一个可选实现方式中，如图5所示，所述步骤S403中根据所述相似度将未分配任务分配给配送资源的步骤，包括步骤S501-S504：
在步骤S501中，根据未分配任务的距离信息对于未分配任务进行聚类处理得到任务类；
在步骤S502中，根据所述相似度对于每一任务类进行分组，得到任务组；
在步骤S503中，计算每一任务组与配送资源之间的匹配度；
在步骤S504中，根据所述匹配度将所述未分配任务分配给配送资源。
在该实现方式中，首先根据未分配任务的距离信息对于未分配任务进行聚类处理得到一个或多个任务类，其中，未分配任务的距离信息可以包括未分配任务商户地址之间的距离和/或未分配任务用户地址之间的距离。比如，可以根据未分配任务商户地址或用户地址的归属商圈进行分类，将属于同一个商圈的未分配任务认为是一个任务类；也可以根据距离聚类方法进行分类，例如：从任意未分配任务A开始，将商户地址距离小于X公里内，且用户地址距离小于Y公里的未分配任务分到一个类中，随着分类操作的进行，未分配任务B、未分配任务C也被分入这个类中，类的规模逐渐变大，迭代的，选取距离未分配任务B较近的 其他未分配任务并入该类中，若没有新的未分配任务可并入，则再重新建立一个新类，新类的生成类似上一个类的生成过程。
然后根据所述相似度对于每一任务类进行分组，得到一个或多个任务组。这里可以完全依据未分配任务之间的相似度，对于每一任务类中的未分配任务进行分组，得到一个或多个任务组，其中，具体使用的相似度分组标准可以根据实际应用的需要进行设置，本公开对其不作具体限制。
需要特别说明的是，上述先聚类后分组的处理方式能够减少时间复杂度，即减少所使用的时间，因为在配送任务数量非常巨大的情况下，直接分组会导致长时间的耗时。
然后再计算每一任务组与配送资源之间的匹配度，根据所述匹配度将所述未分配任务分配给配送资源。
在本实施例的一个可选实现方式中，如图6所示，所述步骤S503，即计算每一任务组与配送资源之间的匹配度的步骤，包括步骤S601-S602：
在步骤S601中，确定匹配评价元素；
在步骤S602中，利用所述匹配评价元素计算每一任务组与配送资源之间的匹配度。
其中，所述匹配评价元素包括：任务组商户位置与配送资源空载时所在位置的距离、任务组的剩余时间、配送资源达到空载状态所需时间、配送资源配送该任务组估计超时信息、配送资源速度、配送资源评分中的一种或多种。
在该实现方式中，利用任务组商户位置与配送资源空载时所在位置的距离、任务组的剩余时间、配送资源达到空载状态所需时间、配送资源配送该任务组估计超时信息、配送资源速度、配送资源评分中的一种或多种匹配评价元素，计算得到每一任务组与配送资源之间的匹配度，以此判断该任务组是否适合分配给该配送资源，其中，配送资源空载指的是配送资源完成分配给他的所有配送任务时的状态；配送资源评分指的是商户或用户对于配送资源的服务评价打分；任务组的剩余时间指的 是一个任务组距离商户或者用户所指定的送达时间的剩余时间，可以取任务组中剩余时间的平均值，也可以取任务组中最长或者最短的剩余时间值。
在利用上述匹配评价元素计算匹配度时，可将上述每一匹配评价元素映射成一个具体的评价值，然后对每一匹配评价元素分配不同的权重，最后再基于评价值和对应的权重进行加权求和，即可得到匹配度。其中，匹配评价元素到评价值的转换方式、以及每一匹配评价元素权重的取值都可以根据实际应用的需要进行设置，本公开对其不作特别限定，所有合理、可行的转换方式、设置方式均落入本公开的保护范围内。当然，也可根据实际应用的需要，选择使用其它匹配评价元素，对此，本公开不再一一描述。
在该实现方式中，在计算得到每一任务组与配送资源之间的匹配度后，还可以先过滤掉低于一预设匹配阈值的匹配度，这样能够排除将任务组分配给匹配度较低的配送资源的可能性。
在本实施例的一个可选实现方式中，如图7所示，所述步骤S504，即根据所述匹配度将所述未分配任务分配给配送资源的步骤，包括步骤S701-S702：
在步骤S701中，按照所述匹配度的大小将所述未分配任务预分配给配送资源；
在步骤S702中，响应于配送信息满足第二预设条件，将所述未分配任务分配给所述配送资源。
其中，所述第二预设条件包括：任务组在预设时间后超时、配送资源待配送任务数量低于第二数量阈值、配送资源预计达到空载所需时间低于预设时间阈值中的一种或多种。
在该实现方式中，采用预分配策略，即先按照匹配度的大小将未分配任务预分配给某一配送资源，待分配信息满足上述第二预设条件时，再将未分配任务真正分配给该配送资源，若在分配信息满足上述第二预设条件之前，匹配度有变，则可根据更新的匹配度将未分配任务预分配给其它的配送资源，然后再待配送信息满足第二预设条件时执行最终的 任务分配。上述预分配策略能够有助于寻求全局最优解，按照全局最优解将配送任务分配给真正合适的配送资源。
下述为本公开装置实施例，可以用于执行本公开方法实施例。
图8示出根据本公开一实施方式的配送任务处理装置的结构框图，该装置可以通过软件、硬件或者两者的结合实现成为电子设备的部分或者全部。如图8所示，所述配送任务处理装置包括：第一确定模块801、第二确定模块802和第一分配模块803：
第一确定模块801，被配置为确定待分配任务与待配送任务之间的相似度；
第二确定模块802，被配置为响应于相似度满足第一预设条件，将相应的配送资源确定为候选配送资源；
第一分配模块803，被配置为将所述待分配任务分配给所述候选配送资源中的目标配送资源，所述目标配送资源的待配送任务与所述待分配任务之间的相似度最高。
在下文中将对第一确定模块801、第二确定模块802和第一分配模块803分别做进一步的描述。
第一确定模块801
上文提及，无论是物流还是外卖，其服务质量都依赖于稳定、可靠、快捷、准时的配送服务，目前有关技术大多基于商圈对于配送任务进行分配和调度，比如，多个配送者各自负责不同的商圈，当系统接收到新的配送服务时，首先判断收货地址属于哪个商圈，然后将相应的配送任务分配给负责这个商圈的配送者。但是上述基于商圈的配送服务处理方法有很多不足，比如负责某一商圈的配送者任务很多，但负责相邻商圈的配送者有可能任务很少，这样就导致任务很多的配送者所负责的商圈里的用户不能及时收到货物，而任务很少的配送者就在附近，却不能够为用户进行服务。
本公开实施例提供一种在广域，比如全城范围内对于配送任务进行分配、处理的方案，以避免出现上述有关技术所存在的问题。在广域范围内，为了实现稳定、可靠、快捷、准时地为用户提供配送服务，需要 对于待分配任务进行准确的分配。在本公开一实施例中，利用待分配任务与已分配给配送资源但并未完成的配送任务，即待配送任务之间的相似度来进行配送任务的分配，也就是说，首先通过第一确定模块801计算待分配任务与待配送任务之间的相似度。其中，所述配送资源包括配送者也包括其他配送资源。
第二确定模块802
然后判断所述相似度是否满足一些预设条件，这些预设条件能够表征将某一配送任务分配给某一配送资源是否合适，那么当所述相似度确定满足第一预设条件时，第二确定模块802就将相应的配送资源确定为适合接受该配送任务的配送资源，即候选配送资源。
第一分配模块803
适合的配送资源可能有很多，为了更快捷迅速地完成配送任务，第一分配模块803可以从众多候选配送资源中，选择其待配送任务与所述待分配任务具有最高相似度的配送资源，作为最终承接该待分配任务的配送资源。
上述实施例提供了一种新的配送任务处理方案，通过对于配送任务在广域，比如全城范围内进行基于相似度的处理和调度，来达到稳定、可靠、快捷、准时地为用户提供配送服务的目的。本公开实施例适应性强、服务覆盖面广、配送效率高，能够为各类型的O2O平台提供配送解决方案，以适应商户、用户的广域配送需求，为商户、用户的使用提供便利。
在本实施例的一个可选实现方式中，如图9所示，所述第一确定模块801包括第一确定子模块901和第一计算子模块902：
第一确定子模块901，被配置为确定相似度评价元素；
第一计算子模块902，被配置为利用所述相似度评价元素计算待分配任务与待配送任务之间的相似度。
其中，所述相似度评价元素包括：配送任务商户地址、配送任务用户地址、期望送达时间中的一种或多种。
在该实现方式中，第一计算子模块902基于第一确定子模块901确 定的配送任务商户地址、配送任务用户地址、期望送达时间中的一种或多种相似度评价元素来计算待分配任务与待配送任务之间的相似度，比如，两个待分配任务的商户离得越近、用户的位置越近、期望送达的时间越接近，就说明这两个待分配任务相似度越高，越适合分配给同一个配送资源，或者说越适合与待配送任务进行合并处理。当然，相似度评价元素还可以采用其他能够体现配送任务之间相似度的元素，本公开不再一一列举，所有能够评价配送任务之间相似度的元素均落入本公开的保护范围内。
在本实施例的一个可选实现方式中，所述第一预设条件包括：
所述待分配任务与待配送任务之间的相似度高于或等于预设相似度阈值；和/或，
所述相似度高于或等于预设相似度阈值的待分配任务数量在配送资源所有待配送任务中所占比例高于或等于预设比例阈值。
在该实现方式中，如图10所示，所述第二确定模块802包括第二确定子模块1001和第三确定子模块1002：
第二确定子模块1001，被配置为确定相似度高于或等于预设相似度阈值的任务数量在配送资源所有待配送任务中所占的比例；
第三确定子模块1002，被配置为若所述比例高于或等于预设比例阈值，将所述配送资源确定为候选配送资源。
为了更准确地判断将待分配任务分配给哪个配送资源合适，或者说与哪些待配送任务合并处理比较合适，在上述实现方式中，第三确定子模块1002通过判断第二确定子模块1001确定的相似度高于或等于预设相似度阈值的任务数量在配送资源所有待配送任务中所占的比例，是否高于或等于预设比例阈值，来确定合适的配送资源。比如，若待分配任务与配送资源所有待配送任务中一半及以上的任务之间的分值均高于或等于预设相似度阈值，则认为待分配任务可分配给该配送资源，该配送资源可被认为是候选配送资源。
满足以上条件的候选配送资源可能会有多个，那么就需要再在多个候选配送资源中选出最为适合的一个配送资源。可选地，可以将待分配 任务与配送资源所有待配送任务相比较得到的最高相似度作为该配送资源的相似度，然后将所述待分配任务分配给相似度最高的这个配送资源。
其中，相似度阈值和比例阈值的取值均可根据实际应用的需要来确定，本公开不作具体限定。
需要说明的是，在确定相似度阈值的取值时，可考虑配送资源所在区域的配送压力值，配送压力值的大小与该区域需要配送的任务的多少有关，配送任务越多，配送压力值就越大，配送压力值越大，就说明配送任务越容易被合并处理，相似度阈值也就越低，这样能够减少配送资源行走的距离，节省运力；相反，某一区域需要配送的任务越少，配送压力值就越小，配送任务就越难被合并处理，相应的，相似度阈值也就越高，这样能够使得配送资源尽快完成已分配的配送任务，提升用户体验。
在本公开另一实施例中，如图11所示，所述装置还包括第三确定模块1101和第二分配模块1102：
第三确定模块1101，被配置为确定未分配任务数量；
第二分配模块1102，被配置为若未分配任务数量小于第一数量阈值，将所述未分配任务分配给一配送资源，所述配送资源待配送任务与所述未分配任务的相似度最高；若未分配任务数量大于或等于所述第一数量阈值，计算未分配任务之间的相似度，并根据所述相似度将未分配任务分配给配送资源。
从上文的描述中可以看出，相似度足够大、与某一配送资源相似的任务足够多的待分配任务才有可能会被分配和处理，在本实施例中，将解释对于经过上述分配后剩余的任务，即与其他待配送任务相似度不够高、与某一配送资源相似的任务也不够多的未分配任务如何处理。
首先第三确定模块1101确定经过上述分配操作后剩余的配送任务的数量，即上述与其他待配送任务相似度不够高、与某一配送资源相似的任务也不够多的未分配任务的数量；若未分配任务数量小于第一数量阈值，比如，小于2，则第二分配模块1102直接将该未分配任务分配给 待配送任务与所述未分配任务相似度最高的那个配送资源；若未分配任务数量大于或等于所述第一数量阈值，比如，大于或等于2，则第二分配模块1102需要首先计算这些未分配任务之间的相似度；然后再根据相似度将这些未分配任务分配给配送资源，其中，未分配任务之间相似度的计算可以采用与上文提及的相似度的计算相似的方法。
在本实施例的一个可选实现方式中，如图12所示，所述第二分配模块1102包括：
聚类子模块1201，被配置为根据未分配任务的距离信息对于未分配任务进行聚类处理得到一个或多个任务类；
分组子模块1202，被配置为根据所述相似度对于每一任务类进行分组，得到一个或多个任务组；
第二计算子模块1203，被配置为计算每一任务组与配送资源之间的匹配度；
分配子模块1204，被配置为根据所述匹配度将所述未分配任务分配给配送资源。
在该实现方式中，聚类子模块1201根据未分配任务的距离信息对于未分配任务进行聚类处理得到一个或多个任务类，其中，未分配任务的距离信息可以包括未分配任务商户地址之间的距离和/或未分配任务用户地址之间的距离。比如，可以根据未分配任务商户地址或用户地址的归属商圈进行分类，将属于同一个商圈的未分配任务认为是一个任务类；也可以根据距离聚类方法进行分类，例如：从任意未分配任务A开始，将商户地址距离小于X公里内，且用户地址距离小于Y公里的未分配任务分到一个类中，随着分类操作的进行，未分配任务B、未分配任务C也被分入这个类中，类的规模逐渐变大，迭代的，选取距离未分配任务B较近的其他未分配任务并入该类中，若没有新的未分配任务可并入，则再重新建立一个新类，新类的生成类似上一个类的生成过程。
分组子模块1202根据所述相似度对于每一任务类进行分组，得到一个或多个任务组。这里可以完全依据未分配任务之间的相似度，对于每一任务类中的未分配任务进行分组，得到一个或多个任务组，其中， 具体使用的相似度分组标准可以根据实际应用的需要进行设置，本公开对其不作具体限制。
需要特别说明的是，上述先聚类后分组的处理方式能够减少时间复杂度，即减少所使用的时间，因为在配送任务数量非常巨大的情况下，直接分组会导致长时间的耗时。
第二计算子模块1203计算每一任务组与配送资源之间的匹配度，分配子模块1204根据所述匹配度将所述未分配任务分配给配送资源。
在本实施例的一个可选实现方式中，如图13所示，所述第二计算子模块1203包括确定单元1301和计算单元1302：
确定单元1301，被配置为确定匹配评价元素；
计算单元1302，被配置为利用所述匹配评价元素计算每一任务组与配送资源之间的匹配度。
其中，所述匹配评价元素包括：任务组商户位置与配送资源空载时所在位置的距离、任务组的剩余时间、配送资源达到空载状态所需时间、配送资源配送该任务组估计超时信息、配送资源速度、配送资源评分中的一种或多种。
在该实现方式中，计算单元1302利用确定单元1301确定的任务组商户位置与配送资源空载时所在位置的距离、任务组的剩余时间、配送资源达到空载状态所需时间、配送资源配送该任务组估计超时信息、配送资源速度、配送资源评分中的一种或多种匹配评价元素，计算得到每一任务组与配送资源之间的匹配度，以此判断该任务组是否适合分配给该配送资源，其中，配送资源空载指的是配送资源完成分配给他的所有配送任务时的状态；配送资源评分指的是商户或用户对于配送资源的服务评价打分；任务组的剩余时间指的是一个任务组距离商户或者用户所指定的送达时间的剩余时间，可以取任务组中剩余时间的平均值，也可以取任务组中最长或者最短的剩余时间值。
计算单元1302在利用上述匹配评价元素计算匹配度时，可将上述每一匹配评价元素映射成一个具体的评价值，然后对每一匹配评价元素分配不同的权重，最后再基于评价值和对应的权重进行加权求和，即可 得到匹配度。其中，匹配评价元素到评价值的转换方式、以及每一匹配评价元素权重的取值都可以根据实际应用的需要进行设置，本公开对其不作特别限定，所有合理、可行的转换方式、设置方式均落入本公开的保护范围内。当然，也可根据实际应用的需要，选择使用其它匹配评价元素，对此，本公开不再一一描述。
在该实现方式中，在计算单元1302计算得到每一任务组与配送资源之间的匹配度后，还可以先过滤掉低于一预设匹配阈值的匹配度，这样能够排除将任务组分配给匹配度较低的配送资源的可能性。
在本实施例的一个可选实现方式中，如图14所示，所述分配子模块1204包括第一分配单元1401和第二分配单元1402：
第一分配单元1401，被配置为按照所述匹配度的大小将所述未分配任务预分配给配送资源；
第二分配单元1402，被配置为响应于配送信息满足第二预设条件，将所述未分配任务分配给所述配送资源。
其中，所述第二预设条件包括：任务组在预设时间后超时、配送资源配送任务数量低于第二数量阈值、配送资源预计达到空载所需时间低于预设时间阈值中的一种或多种。
在该实现方式中，采用预分配策略，即第一分配单元1401先按照匹配度的大小将未分配任务预分配给某一配送资源，待分配信息满足上述第二预设条件时，第二分配单元1402再将未分配任务真正分配给该配送资源，若在分配信息满足上述第二预设条件之前，匹配度有变，则可根据更新的匹配度将未分配任务预分配给其它的配送资源，然后再待配送信息满足第二预设条件时执行最终的任务分配。上述预分配策略能够有助于寻求全局最优解，按照全局最优解将配送任务分配给真正合适的配送资源。
本公开还公开了一种电子设备，图15示出根据本公开一实施方式的电子设备的结构框图，如图15所示，所述电子设备1500包括存储器1501和处理器1502；其中，
所述存储器1501用于存储一条或多条计算机指令，其中，所述一条或多条计算机指令被所述处理器1502执行以实现：
确定待分配任务与待配送任务之间的相似度；
响应于相似度满足第一预设条件，将相应的配送资源确定为候选配送资源；
将所述待分配任务分配给所述候选配送资源中的目标配送资源，所述目标配送资源的待配送任务与所述待分配任务之间的相似度最高。
所述一条或多条计算机指令还可被所述处理器1602执行以实现：
所述确定待分配任务与待配送任务之间的相似度，包括：
确定相似度评价元素；
利用所述相似度评价元素计算待分配任务与待配送任务之间的相似度。
所述第一预设条件包括：
所述待分配任务与待配送任务之间的相似度高于或等于预设相似度阈值；和/或，
所述相似度高于或等于预设相似度阈值的待分配任务数量在配送资源所有待配送任务中所占比例高于或等于预设比例阈值。
所述一条或多条计算机指令还可被所述处理器执行以实现：
确定未分配任务数量；
若未分配任务数量小于第一数量阈值，将所述未分配任务分配给一配送资源，所述配送资源待配送任务与所述未分配任务的相似度最高。
所述一条或多条计算机指令还可被所述处理器执行以实现：
确定未分配任务数量；
若未分配任务数量大于或等于所述第一数量阈值，计算未分配任务之间的相似度；
根据所述相似度将未分配任务分配给配送资源。
所述根据相似度将未分配任务分配给配送资源，包括：
根据未分配任务的距离信息对于未分配任务进行聚类处理得到任务类；
根据所述相似度对于每一任务类进行分组，得到任务组；
计算每一任务组与配送资源之间的匹配度；
根据所述匹配度将所述未分配任务分配给配送资源。
所述计算每一任务组与配送资源之间的匹配度，包括：
确定匹配评价元素；
利用所述匹配评价元素计算每一任务组与配送资源之间的匹配度。
所述匹配评价元素包括：任务组商户位置与配送资源空载时所在位置的距离、任务组的剩余时间、配送资源达到空载状态所需时间、配送资源配送该任务组估计超时信息、配送资源速度、配送资源评分中的一种或多种。
所述根据所述匹配度将所述未分配任务分配给配送资源，包括：
按照所述匹配度的大小将所述未分配任务预分配给配送资源；
响应于配送信息满足第二预设条件，将所述未分配任务分配给所述配送资源。
所述第二预设条件包括：任务组在预设时间后超时、配送资源待配送任务数量低于第二数量阈值、配送资源预计达到空载所需时间低于预设时间阈值中的一种或多种。
图16适于用来实现根据本公开实施方式的配送任务处理方法的计算机系统的结构示意图。
如图16所示，计算机系统1600包括中央处理单元(CPU)1601，其可以根据存储在只读存储器(ROM)1602中的程序或者从存储部分1608加载到随机访问存储器(RAM)1603中的程序而执行上述图1所示的实施方式中的各种处理。在RAM1603中，还存储有系统1600操作所需的各种程序和数据。CPU1601、ROM1602以及RAM1603通过总线1604彼此相连。输入/输出(I/O)接口1605也连接至总线1604。
以下部件连接至I/O接口1605：包括键盘、鼠标等的输入部分1606；包括诸如阴极射线管(CRT)、液晶显示器(LCD)等以及扬声器等的输出部分1607；包括硬盘等的存储部分1608；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1609。通信部分1609经由诸如因 特网的网络执行通信处理。驱动器1610也根据需要连接至I/O接口1605。可拆卸介质1611，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1610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1608。
特别地，根据本公开的实施方式，上文参考图1描述的方法可以被实现为计算机软件程序。例如，本公开的实施方式包括一种计算机程序产品，其包括有形地包含在及其可读介质上的计算机程序，所述计算机程序包含用于执行图1的配送任务处理方法的程序代码。在这样的实施方式中，该计算机程序可以通过通信部分1609从网络上被下载和安装，和/或从可拆卸介质1611被安装。
附图中的流程图和框图，图示了按照本公开各种实施方式的系统、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，路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，所述模块、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。
描述于本公开实施方式中所涉及到的单元或模块可以通过软件的方式实现，也可以通过硬件的方式来实现。所描述的单元或模块也可以设置在处理器中，这些单元或模块的名称在某种情况下并不构成对该单元或模块本身的限定。
作为另一方面，本公开还提供了一种计算机可读存储介质，该计算机可读存储介质可以是上述实施方式中所述装置中所包含的计算机可读存储介质；也可以是单独存在，未装配入设备中的计算机可读存储介质。计算机可读存储介质存储有一个或者一个以上程序，所述程序被一 个或者一个以上的处理器用来执行描述于本公开的方法。
以上描述仅为本公开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，本公开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所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。例如上述特征与本公开中公开的(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 (28)

  1. 一种配送任务处理方法，其中，所述方法包括：
    确定待分配任务与待配送任务之间的相似度；
    响应于相似度满足第一预设条件，将相应的配送资源确定为候选配送资源；
    将所述待分配任务分配给所述候选配送资源中的目标配送资源，所述目标配送资源的待配送任务与所述待分配任务之间的相似度最高。
  2. 根据权利要求1所述的方法，其中，所述确定待分配任务与待配送任务之间的相似度，包括：
    确定相似度评价元素；
    利用所述相似度评价元素计算待分配任务与待配送任务之间的相似度。
  3. 根据权利要求1所述的方法，其中，所述第一预设条件包括：
    所述待分配任务与待配送任务之间的相似度高于或等于预设相似度阈值；和/或，
    所述相似度高于或等于预设相似度阈值的待分配任务数量在配送资源所有待配送任务中所占比例高于或等于预设比例阈值。
  4. 根据权利要求1所述的方法，其中，还包括：
    确定未分配任务数量；
    若未分配任务数量小于第一数量阈值，将所述未分配任务分配给一配送资源，所述配送资源待配送任务与所述未分配任务的相似度最高；
    若未分配任务数量大于或等于所述第一数量阈值，计算未分配任务之间的相似度，并根据所述相似度将未分配任务分配给配送资源。
  5. 根据权利要求4所述的方法，其中，所述根据相似度将未分配任务分配给配送资源，包括：
    根据未分配任务的距离信息对于未分配任务进行聚类处理得到任务类；
    根据所述相似度对于每一任务类进行分组，得到任务组；
    计算每一任务组与配送资源之间的匹配度；
    根据所述匹配度将所述未分配任务分配给配送资源。
  6. 根据权利要求5所述的方法，其中，所述计算每一任务组与配送资源之间的匹配度，包括：
    确定匹配评价元素；
    利用所述匹配评价元素计算每一任务组与配送资源之间的匹配度。
  7. 根据权利要求6所述的方法，其中，所述匹配评价元素包括：任务组商户位置与配送资源空载时所在位置的距离、任务组的剩余时间、配送资源达到空载状态所需时间、配送资源配送该任务组估计超时信息、配送资源速度、配送资源评分中的一种或多种。
  8. 根据权利要求5所述的方法，其中，所述根据所述匹配度将所述未分配任务分配给配送资源，包括：
    按照所述匹配度的大小将所述未分配任务预分配给配送资源；
    响应于配送信息满足第二预设条件，将所述未分配任务分配给所述配送资源。
  9. 根据权利要求8所述的方法，其中，所述第二预设条件包括：任务组在预设时间后超时、配送资源待配送任务数量低于第二数量阈值、配送资源预计达到空载所需时间低于预设时间阈值中的一种或多种。
  10. 一种配送任务处理装置，其中，所述装置包括：
    第一确定模块，被配置为确定待分配任务与待配送任务之间的相似度；
    第二确定模块，被配置为响应于相似度满足第一预设条件，将相应的配送资源确定为候选配送资源；
    第一分配模块，被配置为将所述待分配任务分配给所述候选配送资源中的目标配送资源，所述目标配送资源的待配送任务与所述待分配任务之间的相似度最高。
  11. 根据权利要求10所述的装置，其中，所述第一确定模块包括：
    第一确定子模块，被配置为确定相似度评价元素；
    第一计算子模块，被配置为利用所述相似度评价元素计算待分配任 务与待配送任务之间的相似度。
  12. 根据权利要求10所述的装置，其中，所述第一预设条件包括：
    所述待分配任务与待配送任务之间的相似度高于或等于预设相似度阈值；和/或，
    所述相似度高于或等于预设相似度阈值的待分配任务数量在配送资源所有待配送任务中所占比例高于或等于预设比例阈值。
  13. 根据权利要求10所述的装置，其中，还包括：
    第三确定模块，被配置为确定未分配任务数量；
    第二分配模块，被配置为若未分配任务数量小于第一数量阈值，将所述未分配任务分配给一配送资源，所述配送资源待配送任务与所述未分配任务的相似度最高；若未分配任务数量大于或等于所述第一数量阈值，计算未分配任务之间的相似度，并根据所述相似度将未分配任务分配给配送资源。
  14. 根据权利要求13所述的装置，其中，所述第二分配模块包括：
    聚类子模块，被配置为根据未分配任务的距离信息对于未分配任务进行聚类处理得到任务类；
    分组子模块，被配置为根据所述相似度对于每一任务类进行分组，得到任务组；
    第二计算子模块，被配置为计算每一任务组与配送资源之间的匹配度；
    分配子模块，被配置为根据所述匹配度将所述未分配任务分配给配送资源。
  15. 根据权利要求14所述的装置，其中，所述第二计算子模块包括：
    确定单元，被配置为确定匹配评价元素；
    计算单元，被配置为利用所述匹配评价元素计算每一任务组与配送资源之间的匹配度。
  16. 根据权利要求15所述的装置，其中，所述匹配评价元素包括：任务组商户位置与配送资源空载时所在位置的距离、任务组的剩余时间、 配送资源达到空载状态所需时间、配送资源配送该任务组估计超时信息、配送资源速度、配送资源评分中的一种或多种。
  17. 根据权利要求14所述的装置，其中，所述分配子模块包括：
    第一分配单元，被配置为按照所述匹配度的大小将所述未分配任务预分配给配送资源；
    第二分配单元，被配置为响应于配送信息满足第二预设条件，将所述未分配任务分配给所述配送资源。
  18. 根据权利要求17所述的装置，其中，所述第二预设条件包括：任务组在预设时间后超时、配送资源待配送任务数量低于第二数量阈值、配送资源预计达到空载所需时间低于预设时间阈值中的一种或多种。
  19. 一种电子设备，其中，包括存储器和处理器；其中，
    所述存储器用于存储一条或多条计算机指令，其中，所述一条或多条计算机指令被所述处理器执行以实现：
    确定待分配任务与待配送任务之间的相似度；
    响应于相似度满足第一预设条件，将相应的配送资源确定为候选配送资源；
    将所述待分配任务分配给所述候选配送资源中的目标配送资源，所述目标配送资源的待配送任务与所述待分配任务之间的相似度最高。
  20. 根据权利要求19所述的电子设备，其中，所述确定待分配任务与待配送任务之间的相似度，包括：
    确定相似度评价元素；
    利用所述相似度评价元素计算待分配任务与待配送任务之间的相似度。
  21. 根据权利要求19所述的电子设备，其中，所述第一预设条件包括：
    所述待分配任务与待配送任务之间的相似度高于或等于预设相似度阈值；和/或，
    所述相似度高于或等于预设相似度阈值的待分配任务数量在配送资源所有待配送任务中所占比例高于或等于预设比例阈值。
  22. 根据权利要求19所述的电子设备，其中，所述一条或多条计算机指令还可被所述处理器执行以实现：
    确定未分配任务数量；
    若未分配任务数量小于第一数量阈值，将所述未分配任务分配给一配送资源，所述配送资源待配送任务与所述未分配任务的相似度最高；若未分配任务数量大于或等于所述第一数量阈值，计算未分配任务之间的相似度，根据所述相似度将未分配任务分配给配送资源。
  23. 根据权利要求22所述的电子设备，其中，所述根据相似度将未分配任务分配给配送资源，包括：
    根据未分配任务的距离信息对于未分配任务进行聚类处理得到任务类；
    根据所述相似度对于每一任务类进行分组，得到任务组；
    计算每一任务组与配送资源之间的匹配度；
    根据所述匹配度将所述未分配任务分配给配送资源。
  24. 根据权利要求23所述的电子设备，其中，所述计算每一任务组与配送资源之间的匹配度，包括：
    确定匹配评价元素；
    利用所述匹配评价元素计算每一任务组与配送资源之间的匹配度。
  25. 根据权利要求24所述的电子设备，其中，所述匹配评价元素包括：任务组商户位置与配送资源空载时所在位置的距离、任务组的剩余时间、配送资源达到空载状态所需时间、配送资源配送该任务组估计超时信息、配送资源速度、配送资源评分中的一种或多种。
  26. 根据权利要求23所述的电子设备，其中，所述根据所述匹配度将所述未分配任务分配给配送资源，包括：
    按照所述匹配度的大小将所述未分配任务预分配给配送资源；
    响应于配送信息满足第二预设条件，将所述未分配任务分配给所述配送资源。
  27. 根据权利要求26所述的电子设备，其中，所述第二预设条件包括：任务组在预设时间后超时、配送资源待配送任务数量低于第二数 量阈值、配送资源预计达到空载所需时间低于预设时间阈值中的一种或多种。
  28. 一种计算机可读存储介质，其上存储有计算机指令，其中，该计算机指令被处理器执行时实现如权利要求1-9任一项所述的方法。
PCT/CN2017/118772 2017-08-24 2017-12-26 配送任务处理方法、装置及电子设备 WO2019037367A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710737403.8A CN107844882A (zh) 2017-08-24 2017-08-24 配送任务处理方法、装置及电子设备
CN201710737403.8 2017-08-24

Publications (1)

Publication Number Publication Date
WO2019037367A1 true WO2019037367A1 (zh) 2019-02-28

Family

ID=61682992

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/118772 WO2019037367A1 (zh) 2017-08-24 2017-12-26 配送任务处理方法、装置及电子设备

Country Status (2)

Country Link
CN (1) CN107844882A (zh)
WO (1) WO2019037367A1 (zh)

Families Citing this family (21)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109647719B (zh) * 2017-10-11 2020-07-31 北京京东振世信息技术有限公司 用于分拣货物的方法和装置
CN108564269B (zh) * 2018-04-09 2021-07-30 北京星选科技有限公司 配送任务分配方法、装置、电子设备及计算机存储介质
CN108711020A (zh) * 2018-04-24 2018-10-26 北京小度信息科技有限公司 配送任务分配方法、装置、电子设备及计算机存储介质
CN109064008B (zh) * 2018-07-27 2021-01-01 拉扎斯网络科技（上海）有限公司 配送任务处理方法、装置、电子设备及计算机存储介质
CN110969274A (zh) * 2018-09-28 2020-04-07 北京三快在线科技有限公司 一种预测配送时间的方法、装置及计算机可读存储介质
CN109784977A (zh) * 2018-12-18 2019-05-21 深圳壹账通智能科技有限公司 服务评分方法、装置、计算机设备和存储介质
CN109784766A (zh) * 2019-02-14 2019-05-21 中国联合网络通信集团有限公司 一种资源分配方法和系统
CN110310059A (zh) * 2019-05-23 2019-10-08 天津五八到家科技有限公司 运输任务分配方法、装置及电子设备
CN110472769A (zh) * 2019-07-03 2019-11-19 天津五八到家科技有限公司 运输任务处理方法、装置及电子设备
CN112241856A (zh) * 2019-07-16 2021-01-19 拉扎斯网络科技（上海）有限公司 配送资源管理方法、装置、电子设备及计算机存储介质
CN111008800B (zh) * 2019-10-18 2024-02-23 拉扎斯网络科技（上海）有限公司 配送任务的数据处理方法、装置、服务器和存储介质
CN110990152A (zh) * 2019-11-25 2020-04-10 泰康保险集团股份有限公司 一种共享资源的分配方法及装置
CN111340413A (zh) * 2020-02-10 2020-06-26 拉扎斯网络科技（上海）有限公司 配送任务的分配方法、装置、服务器和存储介质
CN111369137A (zh) * 2020-03-03 2020-07-03 拉扎斯网络科技（上海）有限公司 配送任务的分配方法、装置、服务器和存储介质
CN111353712B (zh) * 2020-03-03 2022-07-22 拉扎斯网络科技（上海）有限公司 配送任务调度方法及装置、服务器及存储介质
CN111652477B (zh) * 2020-05-19 2024-01-23 拉扎斯网络科技（上海）有限公司 订单处理、相似度计算模型获得方法、装置及电子设备
CN111667181B (zh) * 2020-06-08 2023-04-28 拉扎斯网络科技（上海）有限公司 任务处理方法、装置、电子设备及计算机可读存储介质
CN111985865B (zh) * 2020-07-01 2021-05-14 爱创互联网(深圳)有限公司 订单接收与配送管理方法、管理平台及终端设备
CN112036696A (zh) * 2020-07-28 2020-12-04 拉扎斯网络科技（上海）有限公司 任务分配方法、任务分配装置、存储介质和电子设备
CN112181968A (zh) * 2020-09-29 2021-01-05 京东数字科技控股股份有限公司 统一商品信息的方法、装置、系统及存储介质
CN114117328B (zh) * 2022-01-24 2022-05-24 浙江口碑网络技术有限公司 任务分配方法、装置、电子设备及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110087612A1 (en) * 2009-10-14 2011-04-14 Hitachi, Ltd. Product delivery system
CN105719010A (zh) * 2015-07-24 2016-06-29 北京小度信息科技有限公司 配送任务的处理方法及装置
CN105719009A (zh) * 2015-07-24 2016-06-29 北京小度信息科技有限公司 配送任务的处理方法及装置
CN106447470A (zh) * 2016-11-30 2017-02-22 北京小度信息科技有限公司 配送订单分配方法和装置
CN106779526A (zh) * 2016-11-23 2017-05-31 北京小度信息科技有限公司 订单组分配方法及装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110087612A1 (en) * 2009-10-14 2011-04-14 Hitachi, Ltd. Product delivery system
CN105719010A (zh) * 2015-07-24 2016-06-29 北京小度信息科技有限公司 配送任务的处理方法及装置
CN105719009A (zh) * 2015-07-24 2016-06-29 北京小度信息科技有限公司 配送任务的处理方法及装置
CN106779526A (zh) * 2016-11-23 2017-05-31 北京小度信息科技有限公司 订单组分配方法及装置
CN106447470A (zh) * 2016-11-30 2017-02-22 北京小度信息科技有限公司 配送订单分配方法和装置

Also Published As

Publication number Publication date
CN107844882A (zh) 2018-03-27

Similar Documents

Publication Publication Date Title
WO2019037367A1 (zh) 配送任务处理方法、装置及电子设备
US20200134558A1 (en) Order allocation method and device
US9749208B2 (en) Integrated global resource allocation and load balancing
WO2021147353A1 (zh) 订单调度
CN106453146B (zh) 私有云计算资源的分配方法、系统、设备和可读存储介质
CN106779910B (zh) 配送订单分配方法和装置
WO2018000991A1 (zh) 一种数据均衡方法和装置
WO2019153761A1 (zh) 配送任务分配方法、装置、电子设备及计算机存储介质
WO2019196561A1 (zh) 配送任务分配方法、装置、电子设备及计算机存储介质
WO2019205784A1 (zh) 配送任务分配方法、装置、电子设备及计算机存储介质
US20170339069A1 (en) Allocating Cloud Computing Resources In A Cloud Computing Environment
CN109710406B (zh) 数据分配及其模型训练方法、装置、及计算集群
CN105718316A (zh) 一种作业调度的方法及装置
CN109032800A (zh) 一种负载均衡调度方法、负载均衡器、服务器及系统
CN102932271A (zh) 负载均衡的实现方法和装置
Delavar et al. A synthetic heuristic algorithm for independent task scheduling in cloud systems
CN112148468A (zh) 一种资源调度方法、装置、电子设备及存储介质
CN106569892A (zh) 资源调度方法与设备
CN112559130A (zh) 容器分配方法、装置、电子设备及存储介质
CN103997515A (zh) 一种分布式云中计算中心选择方法及其应用
Manikandan et al. Virtualized load balancer for hybrid cloud using genetic algorithm
US20130166751A1 (en) Distributed resource management systems and methods for resource management thereof
US20210217083A1 (en) Method and system for optimizing resource redistribution
CN109788013B (zh) 分布式系统中作业资源分配方法、装置及设备
WO2019037368A1 (zh) 配送任务处理方法、装置、电子设备及计算机存储介质

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: 17922585

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 11/09/2020)

122 Ep: pct application non-entry in european phase

Ref document number: 17922585

Country of ref document: EP

Kind code of ref document: A1