CN112036696A

CN112036696A - Task allocation method, task allocation device, storage medium, and electronic apparatus

Info

Publication number: CN112036696A
Application number: CN202010739021.0A
Authority: CN
Inventors: 顾晟; 沈永新; 王卫其
Original assignee: Rajax Network Technology Co Ltd
Current assignee: Rajax Network Technology Co Ltd; Lazhasi Network Technology Shanghai Co Ltd
Priority date: 2020-07-28
Filing date: 2020-07-28
Publication date: 2020-12-04

Abstract

The embodiment of the invention discloses a task allocation method, a task allocation device, a storage medium and electronic equipment. The method and the device for allocating the tasks determine at least one similar task set according to at least one allocated task corresponding to a target provider, determine at least one task allocation scheme corresponding to the at least one similar task set and scheme attribute information corresponding to the task allocation scheme, simultaneously acquire resource attribute information of task processing resources corresponding to the allocated tasks and region attribute information of interest regions, and further determine the total task completion time of each task allocation scheme according to the information corresponding to each task allocation scheme, so that a target allocation scheme in the task allocation schemes is determined to allocate unallocated tasks. The method of the embodiment of the invention can simultaneously allocate a plurality of unallocated tasks to the same task processing resource, effectively improves the task allocation efficiency, reduces the labor cost and can ensure the reasonability of task allocation.

Description

Task allocation method, task allocation device, storage medium, and electronic apparatus

Technical Field

The invention relates to the technical field of data processing, in particular to a task allocation method, a task allocation device, a storage medium and electronic equipment.

Background

With the rapid development of the internet technology field and the continuous acceleration of the pace of life and work, more and more people choose to select the items of their own mood instruments by means of online transactions, which makes the O2O (online to offline) industry become more and more popular. With the increasing number of orders, for an online trading platform, how to improve the task allocation efficiency under the condition of ensuring the reasonability of task allocation such as orders (that is, avoiding negative effects on user experience due to overtime of orders as much as possible) becomes a problem to be solved urgently.

Disclosure of Invention

In view of this, embodiments of the present invention provide a task allocation method, a task allocation apparatus, a storage medium, and an electronic device, so as to improve task allocation efficiency while ensuring task allocation reasonableness and effectively reduce labor cost.

In a first aspect, an embodiment of the present invention provides a data processing method, where the method includes:

acquiring at least one similar task set corresponding to a target provider, wherein the similar task set comprises at least one distributed task and at least one unallocated task, and the distributed task and the unallocated task belong to the same interest area at delivery positions;

for each similar task set, determining at least one corresponding task allocation scheme and scheme attribute information corresponding to the task allocation scheme, where the task allocation scheme is used to allocate at least one of the unallocated tasks to task processing resources corresponding to the allocated tasks;

acquiring resource attribute information of task processing resources corresponding to the at least one allocated task and area attribute information of the interest area;

based on a duration prediction model, determining the total duration of task completion of the corresponding task allocation scheme according to the resource attribute information, the region attribute information and the scheme attribute information, wherein the duration prediction model is obtained by training according to historical task information of a plurality of historical tasks;

determining a target distribution scheme corresponding to the similar task set according to at least one task completion total time;

and determining a task allocation result of at least one unallocated task according to the target allocation scheme to perform task allocation.

Preferably, the determining the target allocation scheme corresponding to the similar task set according to at least one of the total task completion durations includes:

respectively determining the total completion time length corresponding to each task allocation scheme;

determining corresponding overtime parameters of the task allocation schemes according to the total completion time length corresponding to each task allocation scheme and the total task completion time length, wherein the overtime parameters are used for representing the overtime degree of the task allocation schemes;

and determining the target distribution scheme according to the timeout parameters corresponding to the task distribution schemes.

Preferably, the respectively determining the total completion time length corresponding to each task allocation scheme includes:

and determining the total completion time length corresponding to the corresponding task allocation scheme according to the task completion time length corresponding to each unprocessed task in each task allocation scheme, wherein the unprocessed task comprises at least one allocated task.

Preferably, the determining the total of the completion durations corresponding to the task allocation schemes further includes:

for each task allocation scheme, carrying out path planning according to the corresponding delivery position of the unprocessed task, and determining a corresponding predicted movement track;

and determining the task completion time length of each corresponding unprocessed task according to the predicted movement track.

Preferably, the determining the target allocation scheme according to the timeout parameter corresponding to each task allocation scheme includes:

and determining the target distribution scheme according to the number of unprocessed tasks in each task distribution scheme and the corresponding timeout parameter.

Preferably, the acquiring at least one similar task set corresponding to the target provider includes:

acquiring a first delivery position of at least one assigned task and a second delivery position of at least one unassigned task corresponding to a target provider;

extracting a first keyword set from each first delivery position and extracting a second keyword set from each second delivery position respectively;

respectively matching the first keywords in each first keyword set with the second keywords in each second keyword set to obtain at least one matching result;

and determining the task with the matching result as the matched task as the similar task set.

Preferably, each first keyword in the first keyword set is a keyword having a hierarchical relationship, and each second keyword in the second keyword set is a keyword having a hierarchical relationship;

the extracting of the first keyword sets from the first delivery positions respectively and the extracting of the second keyword sets from the second delivery positions respectively comprise:

extracting at least one first keyword from the first delivery positions respectively as the corresponding first keyword set based on an address model;

extracting at least one second keyword from the second delivery positions respectively as the corresponding second keyword set based on the address model;

the matching the first keywords in each first keyword set with the second keywords in each second keyword set respectively comprises:

and respectively matching each first keyword belonging to the same level with each second keyword belonging to the same level.

In a second aspect, an embodiment of the present invention provides a data processing apparatus, where the apparatus includes:

the system comprises a first acquisition unit, a second acquisition unit and a third acquisition unit, wherein the first acquisition unit is used for acquiring at least one similar task set corresponding to a target provider, the similar task set comprises at least one distributed task and at least one unallocated task, and the distributed task and the unallocated task belong to the same interest area at a delivery position;

a first determining unit, configured to determine, for each similar task set, at least one corresponding task allocation scheme and scheme attribute information corresponding to the task allocation scheme, where the task allocation scheme is used to allocate at least one of the unallocated tasks to a task processing resource corresponding to the allocated task;

a second obtaining unit, configured to obtain resource attribute information of a task processing resource corresponding to the at least one allocated task and area attribute information of the interest area;

a second determining unit, configured to determine, based on a duration prediction model, a total task completion duration of the corresponding task allocation scheme according to the resource attribute information, the region attribute information, and the scheme attribute information, where the duration prediction model is obtained by training according to historical task information of a plurality of historical tasks;

a third determining unit, configured to determine, according to at least one total task completion duration, a target allocation scheme corresponding to the similar task set;

and the first allocation unit is used for determining a task allocation result of at least one unallocated task according to the target allocation scheme so as to allocate the task.

In a third aspect, the present invention provides a computer-readable storage medium on which computer program instructions are stored, wherein the computer program instructions, when executed by a processor, implement the method according to any one of the first aspect.

In a fourth aspect, an embodiment of the present invention provides an electronic device, including a memory and a processor, where the memory is configured to store one or more computer program instructions, where the one or more computer program instructions are executed by the processor to implement the method according to any one of the first aspects.

The method and the device for allocating the tasks in the task allocation scheme determine at least one similar task set according to at least one allocated task corresponding to a target provider, determine at least one task allocation scheme corresponding to the at least one similar task set and scheme attribute information corresponding to the task allocation scheme, simultaneously acquire resource attribute information of task processing resources corresponding to the allocated tasks and region attribute information of interest regions, further determine the total task completion time of each task allocation scheme according to the information corresponding to each task allocation scheme, and accordingly determine a target allocation scheme in the task allocation schemes to allocate unallocated tasks in the target allocation scheme. The method of the embodiment of the invention can simultaneously allocate a plurality of unallocated tasks to the same task processing resource, effectively improves the task allocation efficiency, reduces the labor cost and can ensure the reasonability of task allocation.

Drawings

The above and other objects, features and advantages of the present invention will become more apparent from the following description of the embodiments of the present invention with reference to the accompanying drawings, in which:

FIG. 1 is a schematic diagram of a hardware system architecture of an embodiment of the present invention;

FIG. 2 is a flow chart of a data processing method of the first embodiment of the present invention;

FIG. 3 is a schematic diagram of an address tree of an embodiment of the present invention;

FIG. 4 is a schematic diagram of a task allocation scheme of a first embodiment of the present invention;

FIG. 5 is another schematic diagram of a task allocation scheme of the first embodiment of the present invention;

FIG. 6 is a flowchart of a task assignment method according to a second embodiment of the present invention;

FIG. 7 is a schematic view of a task assigning apparatus according to a third embodiment of the present invention;

fig. 8 is a schematic view of an electronic apparatus according to a fourth embodiment of the present invention.

Detailed Description

The present disclosure is described below based on examples, but the present disclosure is not limited to only these examples. In the following detailed description of the present disclosure, certain specific details are set forth. It will be apparent to those skilled in the art that the present disclosure may be practiced without these specific details. Well-known methods, procedures, components and circuits have not been described in detail so as not to obscure the present disclosure.

Further, those of ordinary skill in the art will appreciate that the drawings provided herein are for illustrative purposes and are not necessarily drawn to scale.

Unless the context clearly requires otherwise, throughout the description and the claims, the words "comprise", "comprising", and the like are to be construed in an inclusive sense as opposed to an exclusive or exhaustive sense; that is, what is meant is "including, but not limited to".

In the description of the present disclosure, it is to be understood that the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. In addition, in the description of the present disclosure, "a plurality" means two or more unless otherwise specified.

In the embodiment of the present invention, the uncompleted tasks (including the allocated tasks and the unallocated tasks described below) are taken as the food orders, and the task processing resources are taken as the delivery personnel. However, it is easily understood by those skilled in the art that the method of the present embodiment is also applicable when the incomplete task is a commodity order of another type or any task that needs to be completed by human task processing resources or non-human task processing resources (e.g., electronic devices such as a distribution robot and an unmanned aerial vehicle), such as any task issued in a task system, and the task processing resources are task processing personnel of another type or non-human resources.

FIG. 1 is a diagram of a hardware system architecture of an embodiment of the present invention. The system architecture shown in fig. 1 includes a plurality of task distribution terminals (user terminals described below) 11, a server 12, and a task processing terminal 13, and fig. 1 illustrates one user terminal 11, one server 12, and one task processing terminal 13 as an example. In the present embodiment, the user terminal 11, the server 12, and the task processing terminal 13 may be communicatively connected through a network. The user can perform a commodity purchasing operation in a predetermined application software, a predetermined web page, or the like through the user terminal 11. After the user completes the shopping (i.e., confirms placing an order), the user terminal 11 may transmit a food order generated according to the user shopping operation to the server 12. After receiving the food order, the server 12 may allocate the food order in various existing manners, and may send a task allocation result of the food order to the corresponding task processing terminal 13, so that the task processing resource corresponding to the task processing terminal 13 processes the food order.

Most of the time periods for purchasing the food are concentrated, so the online trading platform usually receives a large amount of food orders in the lunch time period, the dinner time period and other time periods. The existing order allocation method generally allocates orders by way of order grabbing (i.e., a process of sending an invitation notification of one food order to multiple delivery personnel and allocating the food order to the first delivery personnel who confirms reception), calculating a matching degree of the food order and the delivery personnel, allocating multiple similar orders to the same delivery personnel, and the like. However, the foregoing methods cannot ensure the rationality of order distribution, that is, the labor cost cannot be effectively reduced while ensuring that the order distribution is not overtime.

Fig. 2 is a flowchart of a data processing method according to a first embodiment of the present invention. As shown in fig. 2, the method of the present embodiment includes the following steps:

step S100, at least one similar task set corresponding to the target provider is obtained.

In this embodiment, the target provider is a provider of any ordering entity. When the order entity is a food, the target provider is also a merchant; the target provider may also be a collection of multiple merchants when multiple merchants are located within the same building (e.g., a building, etc.). The similar task set comprises at least one assigned task and at least one unassigned task, wherein the assigned task is a task whose delivery position belongs to the same area of interest. The Area Of Interest (AOI) is a representation Of a location range, and may be specifically an office Area, a home Area, an entertainment Area, and the like. When the assigned tasks and the unassigned tasks are both meal orders, the delivery position is also the position of the user corresponding to the assigned tasks or the unassigned tasks.

In an optional implementation manner, the server may obtain a first delivery position of at least one assigned task and a second delivery position of at least one unassigned task corresponding to the target provider, extract corresponding first keyword sets from the first delivery positions, extract corresponding second keyword sets from the second delivery positions, match the first keywords in the keyword sets with the second keywords in the second keywords, obtain at least one matching result, and determine that the matched task is a similar task set.

Specifically, each first keyword in the first keyword set and each second keyword in the second keyword set are obtained by extraction based on an address model. The address model may efficiently identify particular elements (e.g., "city", "zone", etc.) in the address to more accurately and quickly determine keywords (including the first keyword and the second keyword) in each delivery location (including the first delivery location and the second delivery location). In this embodiment, the address model may be an address tree. The tree is a multi-level structure, so the address tree is also a multi-level structure. For example, taking the region division mode of China as an example, a provincial region can be one level, a city region can be one level, a district region can be one level, and the like. Therefore, each first keyword in the same first keyword set is a keyword with a hierarchical relationship, and each second keyword in the same second keyword set is a keyword with a hierarchical relationship. For example, taking the address of our country as an example, the first delivery position of order 1 is the number of building G in street E, district D, city B, city C, district D, district F, and the first keyword set corresponding to order 1 may include "a", "B", "C", "D", "E", "F", and "G". It is easy to understand that the first keyword and the second keyword may also be other keywords, for example, both are longitude and latitude coordinates, zip codes, and the like, which is not limited in this embodiment. In this embodiment, the address tree can be implemented by, for example, the method described in "kangmen, dunn, wang mingjun" chinese extraction method of address tree model, journal of surveying and mapping, No. 2015, No. 1 month 1 ".

FIG. 3 is a diagram of an address tree according to a first embodiment of the present invention. Fig. 3 illustrates an address encoding method in our country as an example. As shown in fig. 2, a1, a2, A3, etc. are provincial regions, and for a1 provinces, the next hierarchy may include city regions such as B1, B2, and B3, and for B1 cities, the next hierarchy may include district regions such as C1, C2, C3, and C4.

After determining the at least one first keyword set and the at least one second keyword set, the server may match the first keywords and the second keywords belonging to the same hierarchy and determine at least one matching result, thereby determining a similar task set. Wherein a set pair of a first keyword set and a second keyword set corresponds to a matching result.

For example, the set 1 is a first keyword set including the first keywords A, B, C, D1 and E1, and the set is a second keyword set including the second keywords A, B, C, D2 and E2, and the server may match a and a up to E1 and E2 belonging to the same hierarchy and determine a matching result. D1 and D2 do not match, so the server can determine that the match of set 1 and set 2 does not match. Set 3 is a second keyword set, including second keywords A, B, C, D1 and E1, which match with the first keywords at the same level in set 1, so the server can determine the matching results of set 1 and set 3 as a match, and determine a similar task set according to set 1 and set 3.

Step S200, for each similar task set, at least one corresponding task allocation scheme and scheme attribute information corresponding to the task allocation scheme are determined.

Each similar task set corresponds to at least one task allocation scheme. The order allocation set is used for allocating at least one unallocated task to a task processing resource corresponding to an allocated task, that is, the task allocation scheme includes at least one allocated task in the similar task set. For example, if the task affinity set includes order 1, order 2, and order 3, where order 1 is an allocated task and order 2 and order 3 are unallocated tasks, the server may determine that task allocation scheme 1: allocating the order 2 to the task processing resource corresponding to the order 1 (i.e., the order 1 and the order 2 are the task allocation scheme 1) and the task allocation scheme 2: and allocating the order 2 and the order 3 to the task processing resources corresponding to the order 1 (namely, the order 1, the order 2 and the order 3 are task allocation schemes 2). It is easy to understand that when a task allocation scheme includes multiple allocated tasks, the multiple allocated tasks correspond to the same task processing resource.

Optionally, the server may further obtain resource attribute information of the task processing resource corresponding to the allocated task, and determine the task allocation scheme according to the resource attribute information. Specifically, the server may determine the number of unprocessed tasks in the task allocation scheme according to the number of tasks currently undertaken by the task processing resource and the maximum number of affordable tasks in the resource attribute information, thereby effectively ensuring that the task processing resource does not cause task timeout when completing the task. The number of the tasks which are currently undertaken represents the number of the tasks which are currently allocated to the task processing resources, and the maximum affordable task number represents the maximum affordable task number of the task processing resources under the condition that the tasks are not overtime. The maximum bearable task number may be determined according to an average value of the maximum number of tasks when the task processing resource completes the historical task for multiple times in the non-overtime state, or may be determined in other manners, which is not limited in this embodiment.

For example, if the number of tasks currently undertaken by the task processing resource 1 is 1 and the maximum number of affordable tasks is 5, the server may determine that the maximum number of unprocessed tasks in the task allocation scheme does not exceed 4, and specifically may be 1, 2, 3, or 4.

In this embodiment, the plan attribute information may include a total number of tasks corresponding to the uncompleted tasks and a receiving floor parameter corresponding to the uncompleted tasks, and the plan attribute information is used to determine a total task completion time corresponding to each task allocation plan. The total number of tasks and the receiving floor parameters have strong correlation with the total task completion time, so that the server can accurately predict the total task completion time according to the total number of tasks and the receiving floor parameters.

The larger the total number of tasks, the longer it typically takes for the task processing resources to receive the task object (e.g., meal, etc.), which results in a longer overall time for the task to complete. The total number of tasks may be determined as follows: for example, if the number of unallocated tasks in the task allocation scheme 1 is 5, and the number of currently assumed tasks for the task processing resource 1 is 2, the server may determine that the total number of tasks corresponding to the task allocation scheme 1 is 7 for the task processing resource 1. Similarly, the received floor parameters are used for reflecting the unallocated tasks and the floor information where the allocated tasks are located, and specifically may include a maximum value, a minimum value, a mean value, a variance and the like in floors corresponding to a plurality of unallocated tasks, for example, when the floor parameters are a maximum value and a variance, the larger the difference between the floor parameters is, the greater the difference between the floor parameters is, the task processing resources need to be moved to a floor with a larger span in receiving the task object, so the total task completion time is also longer, otherwise, the total task completion time is shorter. It is easy to understand that the scheme attribute information may further include other information, for example, the total number of task targets corresponding to the unassigned tasks and the assigned tasks in the task assignment scheme, and the embodiment is not particularly limited.

Step S300, acquiring resource attribute information of task processing resources corresponding to at least one allocated task and area attribute information of an interest area.

The resource attribute information and the area attribute information are also used for being similar to the resource attribute information, and the resource attribute information and the area attribute information have strong correlation with the total task completion time, so that the server can accurately predict the total task completion time according to the resource attribute information and the area attribute information. The resource attribute information includes the number of tasks currently undertaken by the task processing resource and the maximum number of tasks available for undertaking by the task processing resource. The region attribute information may include a region area of the region of interest, a region category, and a task delivery duration parameter corresponding to the task processing resource set completing different numbers of tasks in the region of interest. Peak hour identification, etc.

The larger the area, the longer the path of movement of the task processing resources within the area of interest may be, thus making the overall length of time for task completion longer. The movement paths of the task processing resources in the interest areas are different in area categories, and therefore the total time for completing the tasks is different, for example, in the lunch period, the number of user groups with the positions in the residential areas is generally less than that in the office areas, so that in the lunch period, the number of tasks at the delivery positions in the residential areas is generally less than that in the office areas, and therefore the movement paths of the task processing resources in the residential areas are generally shorter than those in the office areas. The task delivery duration is used for representing the duration consumed by the task processing resources from the time when the task object is received to the time when the task is delivered, the task delivery duration parameters may include a mean value, a standard deviation, a sample size and the like of the task delivery duration, and taking the task delivery duration parameter as the mean value, for example, the more the number of the tasks is, the larger the mean value of the task delivery duration is, so that the total duration of task completion is longer. The peak period identification is used for representing whether the current period is a peak period or not, and the peak period can be determined according to the total amount of tasks which are not completed in each time period. Optionally, the area attribute information may further include a task processing duration parameter consumed by a target provider in preparing a task object in the area of interest, where the task processing duration parameter is used to characterize a duration parameter consumed by the target provider in preparing a task object in the area of interest, and specifically may include an eighty-degree score, a ninety-five-degree score, and the like of the task processing duration. It is easy to understand that both the resource attribute information and the region attribute information may include other information, and this embodiment is not limited thereto.

And step S400, determining the total task completion time of the corresponding task allocation scheme according to the resource attribute information, the region attribute information and the scheme attribute information based on the time length prediction model.

Alternatively, the duration prediction model may be XGBoost. The XGBoost (eXtreme Gradient Boosting tree) uses ensemble learning to predict the result/label. The ensemble learning refers to combining a plurality of learning models to obtain a better prediction effect, so that the combined model has stronger generalization capability or universality. XGBoost may be commonly used to solve two problems, including classification and regression. In this embodiment, determining the total task completion time corresponding to the task allocation scheme is actually a value prediction (i.e., result prediction) problem, and thus belongs to one of the regression problems. Optionally, the duration prediction model may also be other models, such as a convolutional neural network, a cyclic neural network, and the like, which is not limited in this embodiment.

The duration prediction model is obtained by training according to historical task information of a plurality of historical tasks, wherein the historical task information comprises historical resource information of task processing resources corresponding to the historical tasks, historical region information of interest regions, historical scheme information of the historical task allocation schemes and the total duration of completion of the historical tasks corresponding to the historical task allocation schemes. It is easy to understand that the historical resource information and the resource attribute information, the historical region information and the region attribute information, the historical scheme information and the scheme attribute information, and the historical task completion total duration and the task completion total duration are all in one-to-one correspondence. Specifically, the plurality of historical tasks belong to the same or different historical task allocation schemes respectively, and the number of the historical tasks in the historical task allocation schemes may be the same or different.

When the time length prediction model is trained, the historical resource information, the historical region information and the historical scheme information corresponding to the historical task allocation schemes are input for determination, and the output is determined according to the total time length of the corresponding historical tasks. Therefore, after the resource attribute information, the area attribute information and the scheme attribute information corresponding to each task allocation scheme are input into the trained duration prediction model, the server can accurately determine the total duration of task completion corresponding to each task allocation scheme.

Fig. 4 is a schematic diagram of a task allocation scheme according to a first embodiment of the present invention, and fig. 4 illustrates three task allocation schemes corresponding to a similar task set as an example. It will be readily appreciated that a similar task set includes an assigned task. As shown in fig. 4, taking a task allocation scheme 1 as an example, in the resource attribute information, the number of currently assumed tasks (i.e., "current" in fig. 4) of the task processing resource corresponding to the allocated task is 1, and the maximum number of affordable tasks (i.e., "maximum" in fig. 4) is 5; in the scenario attribute information, the total number of tasks (i.e., "total number" in fig. 4) is 1, and the receiving floor parameter (i.e., "floor" in fig. 4, specifically, the average value of receiving floors) is 3; in the area attribute information, the area (i.e., "area" in fig. 4, in square kilometers) of the area of interest is 100, the area category (i.e., "category" in fig. 4) is a residential area, the time length parameter (i.e., "quantile" in fig. 4, in minutes) consumed by the target provider in preparing a target of the task in the area of interest is 5, and the time length parameter (i.e., "delivery time length" in fig. 4, specifically, the average value of the average delivery time lengths and the number of samples) of the task delivery time lengths is 10 and 1000.

And S500, determining a target distribution scheme corresponding to the similar task set according to the total time for completing at least one task.

In an optional implementation manner, the server may determine a total completion time length corresponding to each task allocation scheme, and determine an timeout parameter of each task allocation scheme according to the total completion time length corresponding to each task allocation scheme and the total task completion time length, respectively, so as to determine the target allocation scheme according to the timeout parameter corresponding to each task allocation scheme. The timeout parameter is used to characterize a timeout degree of the task allocation scheme, and may specifically be a timeout rate, a timeout duration, and the like, which is not limited in this embodiment.

And the total completion time length is determined according to the task completion time length of each uncompleted task in the task allocation scheme. Optionally, the server may perform path planning on delivery positions of unprocessed tasks according to the task allocation schemes, determine a predicted movement trajectory of each task allocation scheme, and determine task completion durations of the unprocessed tasks according to the predicted movement trajectory. The task completion time may be determined according to various existing manners, for example, by model prediction, by moving distance, and the like, which is not limited in this embodiment.

For example, the task allocation scheme 1 includes an order 1, an order 2, and an order 3, and the predicted movement trajectory is the delivery position of the order 1- > the delivery position of the order 3- > the delivery position of the order 2 by planning the delivery positions of the order 1, the order 2, and the order 3. Therefore, the server can respectively determine the task completion duration of each unprocessed task, and for the order 1, the server can determine according to the distance between the position of the target provider and the delivery position of the order 1; for order 2, the server may determine based on the distance between the target provider's location and the delivery location of order 1, the task delivery time length for order 1 (i.e., the length of time it takes from the task processing resource to reach the delivery location of order 1 to deliver the task object to the user and return to the delivery location of order 1), and the distance between the delivery location of order 1 and the delivery location of order 2.

After the completion duration sum corresponding to each task allocation scheme is determined according to each unprocessed task, the server can determine the overtime parameter of each task allocation scheme according to the completion duration sum corresponding to each task allocation scheme and the task completion duration sum, so that the target allocation scheme is determined according to the overtime parameter. Optionally, the server may further determine the target allocation scheme according to the number of unallocated tasks in each task allocation scheme, so that as many tasks as possible may be allocated to the same task processing resource, thereby effectively reducing the labor cost for task processing.

Fig. 5 is another schematic diagram of the task allocation scheme of the first embodiment of the present invention. Fig. 5 illustrates an example of four task allocation schemes corresponding to a similar task set. As shown in fig. 5, the task allocation schemes 1 to 4 include different numbers of unprocessed tasks, and the server can determine the total completion time length corresponding to each task allocation scheme through path planning and task delivery time length calculation for each unprocessed task; through the duration prediction model, the server can respectively determine the total duration of task completion corresponding to each task allocation scheme. Therefore, the server can determine the corresponding timeout duration (i.e., the timeout parameter) according to the total task completion duration and the total completion duration of each task allocation scheme. Therefore, the server can determine the task allocation scheme with the maximum total number of tasks and the supermarket duration less than 0 as the target allocation scheme, namely the task allocation scheme 3.

Step S600, determining a task allocation result of at least one unallocated task according to the target allocation scheme to perform task allocation.

After determining the target allocation scheme, the server may determine the task allocation result of each unallocated task in the target allocation scheme as a task processing resource corresponding to an allocated task in the target allocation scheme. For example, the target allocation plan includes an order 1, an order 2, and an order 3, where the order 1 is an allocated task and the corresponding task processing resource is a distributor 1, the server may determine that the task allocation results of both the order 2 and the order 3 are allocated to the distributor 1.

Optionally, after determining the task allocation result of the unallocated task, the method of this embodiment may further include the following steps:

step S700, sending a task allocation result to the corresponding task processing terminal.

After determining the task allocation result of the unassigned task, the server may send the task allocation result to the corresponding task processing terminal to notify the task processing resource.

In this embodiment, at least one similar task set is determined according to at least one allocated task corresponding to a target provider, at least one task allocation scheme corresponding to the at least one similar task set and scheme attribute information corresponding to the task allocation scheme are determined, resource attribute information of task processing resources corresponding to the allocated task and region attribute information of an interest region are simultaneously acquired, and then the total task completion duration of each task allocation scheme is determined according to the information corresponding to each task allocation scheme, so that a target allocation scheme in the task allocation schemes is determined to allocate unallocated tasks in the target allocation scheme. The method of the embodiment can simultaneously allocate a plurality of unallocated tasks to the same task processing resource, effectively improves the task allocation efficiency, reduces the labor cost, and can ensure the reasonability of task allocation.

Fig. 6 is a flowchart of a task assigning method according to a second embodiment of the present invention. The method of this embodiment may further include an assignment process of the assigned task. As shown in fig. 6, the method of this embodiment further includes, in addition to steps S100 to S600 of the first embodiment of the present invention:

in step S1, task attribute information of the assigned task is acquired.

The present embodiment may adopt various existing manners to perform task allocation. According to different task allocation methods, the server can obtain different task attribute information. For example, if the task allocation method allocates the allocated task to the task processing resource closest to the allocated task, the task attribute information may include location information of a task provider (i.e., a target provider) corresponding to the allocated task; if the task allocation method is to predict the matching degree of the allocated order and each task processing resource through a pre-trained model, so as to allocate the task according to the matching degree, the task attribute information may further include the weight of the task object, the task category, and the like. It is easy to understand that the task attribute information may also include other information, and this embodiment is not limited.

It is easily understood that step S1 is performed before step S100.

And step S2, distributing the distributed tasks according to the task attribute information and at least one resource attribute information.

For example, the server may allocate an allocated task to a task processing resource closest to the server for task allocation, or predict a matching degree between an allocated order and each task processing resource through a pre-trained model, so as to allocate the task according to the matching degree, or allocate the task to a task processing resource with a strong task processing capability, and the like, which is not limited in this embodiment.

It is easily understood that step S2 is performed before step S100.

In this embodiment, the implementation manner of step S700 is the same as the implementation manner of step S700 in the first embodiment of the present invention, and is not described herein again.

In this embodiment, allocated tasks are allocated according to task attribute information of at least one allocated task corresponding to a target provider and resource attribute information of at least one task processing resource, at least one similar task set is determined according to the at least one allocated task, at least one task allocation scheme corresponding to the at least one similar task set and scheme attribute information corresponding to the task allocation scheme are determined, resource attribute information of the task processing resource corresponding to the allocated tasks and region attribute information of an interest region are simultaneously acquired, and then the total task completion time of each task allocation scheme is determined according to the information corresponding to each task allocation scheme, so that a target allocation scheme in the task allocation schemes is determined to allocate unallocated tasks in the target allocation scheme. The method of the embodiment can allocate the allocated tasks, and can simultaneously allocate a plurality of unallocated tasks to the same task processing resource, thereby effectively improving the task allocation efficiency, reducing the labor cost and ensuring the reasonability of task allocation.

Fig. 7 is a schematic diagram of a task assigning apparatus according to a third embodiment of the present invention. As shown in fig. 7, the apparatus of the present embodiment includes a first acquisition unit 71, a first determination unit 72, a second acquisition unit 73, a second determination unit 74, a third determination unit 75, and a first allocation unit 76.

The first obtaining unit 71 is configured to obtain at least one similar task set corresponding to a target provider, where the similar task set includes at least one assigned task and at least one unassigned task, and the assigned task and the unassigned task are tasks whose delivery positions belong to the same area of interest. The first determining unit 72 is configured to determine, for each similar task set, at least one corresponding task allocation scheme and scheme attribute information corresponding to the task allocation scheme, where the task allocation scheme is used to allocate at least one of the unallocated tasks to a task processing resource corresponding to the allocated task. The second obtaining unit 73 is configured to obtain resource attribute information of a task processing resource corresponding to the at least one allocated task and area attribute information of the interest area. The second determining unit 74 is configured to determine, based on a duration prediction model, a total task completion duration of the corresponding task allocation scheme according to the resource attribute information, the area attribute information, and the scheme attribute information, where the duration prediction model is obtained by training according to historical task information of a plurality of historical tasks. The third determining unit 75 is configured to determine a target allocation scheme corresponding to the similar task set according to at least one total task completion time. The first allocation unit 76 is configured to determine a task allocation result of at least one of the unallocated tasks according to the target allocation scheme for task allocation.

Further, the third determining unit 75 includes a first determining subunit, a second determining subunit, and a third determining subunit.

The first determining subunit is configured to determine a total of completion durations corresponding to the task allocation schemes, respectively. The second determining subunit is configured to determine an timeout parameter of the corresponding task allocation scheme according to the total completion time length corresponding to each task allocation scheme and the total task completion time length, where the timeout parameter is used to characterize a timeout degree of the task allocation scheme. And the third determining subunit is used for determining the target distribution scheme according to the timeout parameters corresponding to the task distribution schemes.

Further, the first determining subunit includes a first determining module.

The first determining module is used for determining the total completion time length corresponding to the corresponding task allocation scheme according to the task completion time length corresponding to each unprocessed task in each task allocation scheme, wherein the unprocessed task comprises at least one allocated task.

Further, the first determining subunit further includes a path planning module and a second determining module.

And the path planning module is used for planning paths according to the delivery positions of the corresponding unprocessed tasks for the task allocation schemes and determining corresponding predicted movement tracks. And the second determination module is used for determining the task completion time of each corresponding unprocessed task according to the predicted movement track.

Further, the third determining subunit is configured to determine the target allocation scheme according to the number of unprocessed tasks in each of the task allocation schemes and the corresponding timeout parameter.

Further, the first obtaining unit 71 includes a first obtaining subunit, an extracting subunit, a matching subunit, and a fourth determining subunit.

The first acquiring subunit is configured to acquire a first delivery location of at least one assigned task and a second delivery location of at least one unassigned task, which correspond to the target provider. The extracting subunit is configured to extract a corresponding first keyword set from each of the first delivery positions, and extract a corresponding second keyword set from each of the second delivery positions. The matching subunit is configured to match the first keyword in each first keyword set with the second keyword in each second keyword set, respectively, to obtain at least one matching result. And the fourth determining subunit is used for determining the task with the matching result as the matching task as the similar task set.

Further, each first keyword in the first keyword set is a keyword having a hierarchical relationship, and each second keyword in the second keyword set is a keyword having a hierarchical relationship;

the extraction subunit comprises a first extraction module and a second extraction module.

The first extraction module is used for extracting at least one first keyword from the first delivery position respectively as the corresponding first keyword set based on an address model. And the second extraction module is used for respectively extracting at least one second keyword from the second delivery position as the corresponding second keyword set based on the address model.

The matching subunit is configured to match each of the first keywords belonging to the same hierarchy with each of the second keywords belonging to the same hierarchy, respectively.

Further, the resource attribute information includes the number of currently undertaken tasks and the maximum affordable task number corresponding to the task processing resource;

the first determining unit 72 is specifically configured to determine the number of unprocessed tasks in the task allocation scheme according to the number of currently assumed tasks and the maximum number of affordable tasks.

Further, the apparatus further comprises a third acquiring unit 77 and a second distributing unit 78.

Wherein the third obtaining unit 77 is configured to obtain task attribute information of the assigned task. The second allocating unit 78 is configured to allocate the allocated task according to the task attribute information and at least one resource attribute information.

Further, the apparatus further comprises a result sending unit 79.

The result sending unit 79 is configured to send the task allocation result to a corresponding task processing terminal, where the task processing terminal is a terminal corresponding to the task processing resource.

In this embodiment, allocated tasks are allocated according to task attribute information of at least one allocated task corresponding to a target provider and resource attribute information of at least one task processing resource, at least one similar task set is determined according to the at least one allocated task, at least one task allocation scheme corresponding to the at least one similar task set and scheme attribute information corresponding to the task allocation scheme are determined, resource attribute information of the task processing resource corresponding to the allocated tasks and region attribute information of an interest region are simultaneously acquired, and then the total task completion time of each task allocation scheme is determined according to the information corresponding to each task allocation scheme, so that a target allocation scheme in the task allocation schemes is determined to allocate unallocated tasks in the target allocation scheme. The device of this embodiment can distribute the task that has been distributed to can distribute a plurality of tasks that do not distribute to same task processing resource simultaneously, promote the distribution efficiency of task, reduce the human cost when effective, and can guarantee the rationality of task distribution.

Fig. 8 is a schematic view of an electronic apparatus according to a fourth embodiment of the present invention. As shown in fig. 8, the electronic device: includes at least one processor 801; and a memory 802 communicatively coupled to the at least one processor 801; and a communication component 803 communicatively coupled to the scanning device, the communication component 803 receiving and transmitting data under control of the processor 801; the memory 802 stores instructions executable by the at least one processor 801, where the instructions are executed by the at least one processor 801 to implement the methods of embodiments of the present invention.

Specifically, the electronic device includes: one or more processors 801 and a memory 802, one processor 801 being illustrated in fig. 8. The processor 801 and the memory 802 may be connected by a bus or other means, and fig. 8 illustrates an example of a connection by a bus. Memory 802, which is a non-volatile computer-readable storage medium, may be used to store non-volatile software programs, non-volatile computer-executable programs, and modules. The processor 801 executes various functional applications of the device and data processing by running nonvolatile software programs, instructions, and modules stored in the memory 802, that is, implements the above-described task assignment method.

The memory 802 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store a list of options, etc. Further, the memory 802 may include high speed random access memory and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some embodiments, the memory 802 may optionally include memory located remotely from the processor 801, which may be connected to an external device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

One or more modules are stored in the memory 802, and when executed by the one or more processors 801, perform the task assignment method of any of the method embodiments described above.

The product can execute the method provided by the embodiment of the application, has corresponding functional modules and beneficial effects of the execution method, and can refer to the method provided by the embodiment of the application without detailed technical details in the embodiment.

A fifth embodiment of the invention is directed to a non-volatile storage medium storing a computer-readable program for causing a computer to perform some or all of the above-described method embodiments.

That is, as can be understood by those skilled in the art, all or part of the steps in the method for implementing the embodiments described above may be implemented by a program instructing related hardware, where the program is stored in a storage medium and includes several instructions to enable a device (which may be a single chip, a chip, or the like) or a processor (processor) to execute all or part of the steps of the method described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

The embodiment of the invention discloses A1 and a task allocation method, wherein the method comprises the following steps:

A2, the method as in A1, wherein the determining the target allocation scheme corresponding to the similar task set according to at least one of the total task completion time includes:

A3, the method as in a2, wherein the determining a total of completion durations corresponding to the task allocation schemes respectively includes:

A4, the method as in A3, wherein the determining a total of completion durations corresponding to the task allocation schemes respectively further includes:

A5, the method as in a2, wherein the determining the target allocation plan according to the timeout parameter corresponding to each task allocation plan includes:

A6, the method as in A1, wherein the acquiring at least one similar task set corresponding to a target provider includes:

extracting corresponding first keyword sets from the first delivery positions respectively, and extracting corresponding second keyword sets from the second delivery positions respectively;

A7, wherein in the method as in a6, each first keyword in the first keyword set is a keyword having a hierarchical relationship, and each second keyword in the second keyword set is a keyword having a hierarchical relationship;

the extracting of the corresponding first keyword sets from the first delivery positions respectively and the extracting of the corresponding second keyword sets from the second delivery positions respectively comprise:

A8, the method as in A1, wherein the resource attribute information includes the number of tasks currently undertaken and the maximum number of tasks available for the task processing resource;

the determining of the corresponding at least one task allocation scheme specifically includes:

and determining the number of unprocessed tasks in the task allocation scheme according to the number of the current undertaken tasks and the maximum affordable task number.

A9, the method of a1, the method further comprising:

acquiring task attribute information of the distributed tasks;

and distributing the distributed tasks according to the task attribute information and at least one piece of resource attribute information.

In the method of a10, as in a1 or a9, the method further comprising:

and sending the task allocation result to a corresponding task processing terminal, wherein the task processing terminal is a terminal corresponding to the task processing resource.

The embodiment of the invention also discloses B1 and a task allocation device, wherein the device comprises:

B2, the apparatus as defined in B1, wherein the third determining unit includes:

the first determining subunit is used for respectively determining the total of the completion time lengths corresponding to the task allocation schemes;

a second determining subunit, configured to determine an timeout parameter of the corresponding task allocation scheme according to the total completion time and the total task completion time corresponding to each task allocation scheme, where the timeout parameter is used to characterize a timeout degree of the task allocation scheme;

and the third determining subunit is used for determining the target distribution scheme according to the timeout parameters corresponding to the task distribution schemes.

B3, the apparatus as described in B2, wherein the first determining subunit includes:

B4, the apparatus as described in B3, wherein the first determining subunit further comprises:

a path planning module, configured to perform path planning on each task allocation plan according to the delivery position of the corresponding unprocessed task, and determine a corresponding predicted movement trajectory;

and the second determination module is used for determining the task completion time of each corresponding unprocessed task according to the predicted movement track.

B5, the apparatus according to B2, wherein the third determining subunit is configured to determine the target allocation plan according to the number of unprocessed tasks in each of the task allocation plans and the corresponding timeout parameter.

B6, the apparatus as defined in B1, the first obtaining unit comprising:

the first acquisition subunit is used for acquiring a first delivery position of at least one assigned task and a second delivery position of at least one unassigned task corresponding to the target provider;

an extracting subunit, configured to extract a corresponding first keyword set from each of the first delivery positions, and extract a corresponding second keyword set from each of the second delivery positions;

a matching subunit, configured to match the first keyword in each first keyword set with the second keyword in each second keyword set, respectively, to obtain at least one matching result;

and the fourth determining subunit is used for determining the task with the matching result as the matched task as the similar task set.

B7, the apparatus according to B6, wherein each of the first keywords in the first keyword set is a keyword having a hierarchical relationship, and each of the second keywords in the second keyword set is a keyword having a hierarchical relationship;

the extraction subunit includes:

a first extracting module, configured to extract at least one first keyword from the first delivery location as the corresponding first keyword set based on an address model;

a second extracting module, configured to extract at least one second keyword from the second delivery location as the corresponding second keyword set based on the address model;

B8, in the apparatus according to B1, the resource attribute information includes the number of tasks currently undertaken and the maximum number of tasks available for the task processing resource;

the first determining unit is specifically configured to determine the number of unprocessed tasks in the task allocation scheme according to the current number of assumed tasks and the maximum number of the assumed tasks.

B9, the apparatus of B1, further comprising:

a third obtaining unit, configured to obtain task attribute information of the assigned task;

and the second distribution unit is used for distributing the distributed tasks according to the task attribute information and at least one piece of resource attribute information.

B10, the apparatus as described in B1 or B9, the apparatus further comprising:

and the result sending unit is used for sending the task allocation result to the corresponding task processing terminal, and the task processing terminal is a terminal corresponding to the task processing resource.

The embodiment of the invention also discloses C1, a computer readable storage medium, wherein the computer program instructions are stored on the computer readable storage medium, and when the computer program instructions are executed by a processor, the method of any one of A1-A10 is realized.

The embodiment of the invention also discloses D1, an electronic device, comprising a memory and a processor, wherein the memory is used for storing one or more computer program instructions, and the processor executes the one or more computer program instructions to realize the method according to any one of A1-A10.

It will be understood by those of ordinary skill in the art that the foregoing embodiments are specific embodiments for practicing the invention, and that various changes in form and details may be made therein without departing from the spirit and scope of the invention in practice.

Claims

1. A method of task allocation, the method comprising:

2. The method of claim 1, wherein the determining the target allocation plan corresponding to the similar task set according to at least one of the total task completion durations comprises:

3. The method of claim 2, wherein said separately determining a sum of completion durations for each of said task allocation plans comprises:

4. The method of claim 3, wherein said separately determining a total of completion durations for each of said task assignments further comprises:

5. The method of claim 2, wherein determining the target allocation plan according to the timeout parameter corresponding to each of the task allocation plans comprises:

6. The method of claim 1, wherein obtaining at least one similar task set corresponding to a target provider comprises:

7. The method of claim 6, wherein each of the first keywords in the first keyword set is a keyword having a hierarchical relationship, and each of the second keywords in the second keyword set is a keyword having a hierarchical relationship;

8. A task assigning apparatus, characterized in that the apparatus comprises:

9. A computer-readable storage medium on which computer program instructions are stored, which, when executed by a processor, implement the method of any one of claims 1-7.

10. An electronic device comprising a memory and a processor, wherein the memory is configured to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method of any of claims 1-7.