CN115689132A - Order allocation method and device - Google Patents

Abstract

The specification discloses an order distribution method and device, and various time combinations of taking and delivering of the distributed objects at various distributed object receiving and delivering points related to the to-be-distributed order package can be referred to by candidate distributors, and comprehensive distribution efficiency when the candidate distributors perform distribution tasks corresponding to the to-be-distributed order package is comprehensively determined, so that the selected target distributors can complete the distribution tasks corresponding to the to-be-distributed order package according to the specified time limit of the orders contained in the to-be-distributed order package as far as possible, and the distribution efficiency of the distributors is effectively guaranteed.

Description

Order allocation method and device

Technical Field

The present disclosure relates to the field of computer technologies, and in particular, to a method and an apparatus for order allocation.

Background

With the continuous development of computer technology, the service platform provides various forms of online shopping services for users, such as takeaway services, fresh food express services and the like, and the users can select and purchase commodities online at any time and any place according to the actual demands of the users, so that great convenience is brought to the lives of the users.

For the take-away service, the service platform needs to determine a distributor who executes the take-away order according to the estimated distribution time length for the take-away order, and then distribute the take-away order to the distributor for execution. The service platform usually estimates the delivery duration of the take-away order according to the riding speed of the deliverer, the time of taking-away meal, the time of taking-away delivery (i.e. the time consumed by the deliverer to deliver the take-away to the user after the deliverer arrives at the delivery address specified by the user), the distance between the merchant and the delivery address specified by the user, and other information.

However, in practical applications, the takeout meal time and the takeout delivery time mentioned above are fixed values that are preset manually according to practical experience, which results in that the takeout meal time and the takeout delivery time may be greatly different from the real situation, thereby causing great inconvenience to the takeout delivery of the deliverer and the user who orders the takeout.

For example, the deliverer arrives at the merchant according to the takeout meal time determined by the service platform, but the merchant has a slow meal, and the takeout is not delivered to the deliverer according to the takeout meal time determined by the service platform, which results in that the deliverer is likely to wait for a long time before taking the takeout, thereby possibly affecting the delivery tasks of other orders that the deliverer needs to execute, and reducing the delivery efficiency of the deliverer.

Disclosure of Invention

The present disclosure provides a method and an apparatus for order allocation, which partially solve the above problems in the prior art.

The technical scheme adopted by the specification is as follows:

the present specification provides a method of order allocation, comprising:

acquiring an order package to be distributed, wherein the order package to be distributed comprises at least one order;

determining various time combinations of the candidate delivery staff for completing delivery of the delivered objects at delivery points related to the to-be-distributed order package when the candidate delivery staff executes a delivery task corresponding to the to-be-distributed order package;

determining the distribution efficiency of the candidate distributor when executing the distribution tasks corresponding to the order packages to be distributed according to each time combination, and taking the distribution efficiency of the candidate distributor under the time combination;

determining the matching degree of the candidate delivery staff for the order package to be distributed according to the delivery efficiency of the candidate delivery staff under the various time combinations;

and selecting target delivery personnel from the candidate delivery personnel according to the matching degree of each candidate delivery personnel for the order package to be distributed, and distributing the order package to be distributed to the target delivery personnel for execution.

Optionally, for each candidate dispenser, determining various time combinations of the candidate dispenser completing the picking and delivering of the dispensed goods at the delivery points related to the to-be-distributed order package when the candidate dispenser performs the delivery task corresponding to the to-be-distributed order package, specifically includes:

determining characteristic information corresponding to at least one order contained in the order package to be distributed;

and inputting the characteristic information into a preset time estimation model, and determining various time combinations of the candidate delivery staff for completing delivery of the delivered objects at delivery points of the delivered objects related to the to-be-distributed order package when the candidate delivery staff executes the delivery tasks corresponding to the to-be-distributed order package through the time estimation model.

Optionally, the inputting of the feature information into a preset time estimation model to determine, through the time estimation model, various time combinations of the candidate deliverer completing delivery of the delivered items at delivery points related to the to-be-distributed order package when the candidate deliverer executes a delivery task corresponding to the to-be-distributed order package includes:

inputting characteristic information corresponding to the order of the distribution object pick-up point in the order package to be distributed into the time estimation model aiming at each distribution object pick-up point related to the order package to be distributed, and obtaining time length probability distribution of various time lengths consumed by the candidate distributor for completing distribution object pick-up and distribution at the distribution object pick-up point as the time length probability distribution corresponding to the distribution object pick-up point;

and determining various time combinations of the candidate delivery staff for completing delivery of the delivery at the delivery points related to the to-be-distributed order package when the candidate delivery staff executes the delivery task corresponding to the to-be-distributed order package according to the time length probability distribution corresponding to the delivery points of each delivery related to the to-be-distributed order package.

Optionally, determining, according to the time length probability distribution corresponding to each delivery point involved in the order to be allocated, various time combinations of the candidate deliverer completing delivery of the delivery at each delivery point involved in the order package to be allocated when the candidate deliverer executes the delivery task corresponding to the order package to be allocated, specifically including:

sampling in each preset time length range aiming at each distribution object receiving and sending point related to the order package to be distributed to obtain each sampling time length serving as each sampling time length corresponding to the distribution object receiving and sending point, wherein the number of the sampling time lengths obtained by sampling in each time length range is positively correlated with the probability distribution of the time length corresponding to the distribution object receiving and sending point in the time length probability distribution corresponding to each time length range;

and determining various time combinations of the candidate delivery staff for completing delivery of the delivery at the delivery points related to the order package to be distributed when the candidate delivery staff executes the delivery task corresponding to the order package to be distributed according to the sampling time lengths corresponding to the delivery points of the delivery related to the order package to be distributed.

Optionally, for each time combination, determining a delivery efficiency of the candidate delivery member when executing the delivery task corresponding to the to-be-distributed order package according to the time combination, as the delivery efficiency of the candidate delivery member in the time combination, specifically includes:

determining the arrangement sequence of the delivery points of the dispatches related to the order package to be distributed according to the time sequence of each order related to the order package to be distributed;

according to the arrangement sequence, determining that the candidate delivery staff completes the schedule of the delivery tasks corresponding to the to-be-distributed order packages under the condition that the candidate delivery staff consumes fixed time for taking and delivering the delivery goods at the delivery points of the to-be-distributed order packages;

determining a time deviation between a time length consumed by the candidate dispenser for taking and delivering the dispenser at the dispenser pick-and-place point and a fixed time length consumed by the candidate dispenser for taking and delivering the dispenser at the dispenser pick-and-place point in the time combination as a time deviation corresponding to the dispenser pick-and-place point for each dispenser pick-and-place point related to the to-be-distributed order package;

correcting the timetable according to the time deviation corresponding to each distribution article receiving and sending point related to the order packet to be distributed to obtain a corrected timetable corresponding to the time combination;

and determining the distribution efficiency of the candidate distributor when executing the distribution tasks corresponding to the to-be-distributed order packages according to the time combination according to the corrected time table corresponding to the time combination.

Optionally, for each delivery object pick-up point related to the to-be-distributed order package, if the delivery object pick-up point is a delivery object pick-up point, in the modified schedule corresponding to the time combination, a later time between a time when the delivery object pick-up point determined according to the time combination finishes preparation of a delivery object and a time when the candidate delivery person arrives at the delivery object pick-up point is taken as a departure time of the candidate delivery person at the delivery object pick-up point.

Optionally, the delivery efficiency of the candidate deliverer at the various time combinations includes: the comprehensive distribution index duration after the candidate distributor executes the distribution task of the to-be-executed order under the various time combinations includes: at least one of a comprehensive order overtime time, a comprehensive delivery consumption time and a comprehensive delivery waiting time after the candidate deliverer executes the delivery task of the to-be-executed order under the various time combinations, wherein the to-be-executed order comprises: orders contained in the order package to be distributed and orders which are accepted by the candidate distributor and need to be executed;

determining the matching degree of the candidate delivery staff for the order package to be distributed according to the delivery efficiency of the candidate delivery staff under the various time combinations, wherein the determining step specifically comprises the following steps:

for each time combination, determining the distribution index duration after the candidate distributor executes the to-be-executed order which needs to be executed by the candidate distributor according to the time combination, and taking the distribution index duration as the distribution index duration corresponding to the time combination;

determining the comprehensive distribution index duration of the candidate distributor after executing the distribution tasks of the orders to be executed under the various time combinations according to the distribution index duration corresponding to each time combination;

and determining the matching degree of the candidate distributor for the order packet to be distributed according to the comprehensive distribution index duration, wherein if the comprehensive distribution index duration is shorter, the matching degree of the candidate distributor for the order packet to be distributed is higher.

Optionally, the delivery efficiency of the candidate deliverer at the various time combinations includes: the candidate dispatchers execute the comprehensive risk scores after the dispatching tasks of the orders to be executed under the various time combinations;

determining the matching degree of the candidate delivery staff for the order package to be distributed according to the delivery efficiency of the candidate delivery staff under the various time combinations, specifically comprising:

sequencing the time combinations according to the sequence from large to small of the distribution index duration corresponding to each time combination to obtain time combination sequencing;

determining the comprehensive risk score according to the distribution index duration corresponding to the time combination positioned before the first set ranking in the time combination ranking;

and determining the matching degree of the candidate distributor for the order package to be distributed according to the comprehensive risk score, wherein if the comprehensive risk score is lower, the matching degree of the candidate distributor for the order package to be distributed is higher.

Optionally, determining, according to the delivery efficiency of the candidate delivery staff in the various time combinations, a matching degree of the candidate delivery staff for the order package to be distributed, specifically including:

and determining the matching degree of the candidate distributor for the order package to be distributed according to the comprehensive distribution index duration, the comprehensive risk score and the risk weight corresponding to the comprehensive risk score, wherein if the order quantity of the users is more in the distribution time period corresponding to the order package to be distributed, the risk weight is higher.

Optionally, selecting a target delivery member from the candidate delivery members according to the matching degree of each candidate delivery member for the order package to be distributed, specifically including:

for each candidate dispenser, determining the basic delivery efficiency of the candidate dispenser when executing the delivery task corresponding to the to-be-distributed order package according to the fixed time length consumed by the candidate dispenser for taking and delivering the dispenser at each delivery point related to the to-be-distributed order package, and taking the basic delivery efficiency as the basic delivery efficiency corresponding to the candidate dispenser;

determining a basic sorting result of each candidate dispenser for the order package to be distributed according to the descending order of the basic dispensing efficiency of each candidate dispenser;

and selecting target dispatchers from the candidate dispatchers according to the basic sorting result and the matching degree of each candidate dispatcher for the order package to be distributed.

Optionally, selecting a target delivery person from the candidate delivery persons according to the basic sorting result and the matching degree of each candidate delivery person for the order package to be distributed, specifically including:

determining candidate distributors positioned at a second set ranking from the basic ranking result to be used as reference distributors;

selecting candidate dispatchers from the candidate dispatchers, wherein the matching degree of the candidate dispatchers for the order package to be distributed is higher than that of the reference dispatcher;

and determining a target distributor according to the selected candidate distributors.

Optionally, determining a target dispenser according to the selected candidate dispensers includes:

determining candidate dispatchers meeting preset conditions from the selected candidate dispatchers;

determining a target distributor according to the candidate distributors meeting the preset conditions; wherein

For each selected candidate dispenser, if it is determined that the distance difference between the distance required by the candidate dispenser to execute the delivery task corresponding to the order packet to be distributed and the distance required by the reference dispenser to execute the delivery task corresponding to the order packet to be distributed is less than a set distance threshold, and/or

If the order number difference between the order number of the to-be-executed orders distributed to the candidate distributor after the to-be-distributed order package is distributed to the candidate distributor and the order number of the to-be-executed orders distributed to the benchmark distributor after the to-be-distributed order package is distributed to the benchmark distributor is smaller than the set order number threshold value, the candidate distributor is determined to meet the preset condition.

Optionally, if it is determined that the more orders are placed by the user in the delivery time period corresponding to the order package to be allocated, the larger the set distance threshold and/or the set order number threshold is.

The present specification provides an order distribution apparatus comprising:

the system comprises an acquisition module, a distribution module and a distribution module, wherein the acquisition module is configured to acquire an order package to be distributed, and the order package to be distributed comprises at least one order;

a time combination determination module configured to determine, for each candidate dispenser, various time combinations at which the candidate dispenser completes delivery of the delivery at each delivery point related to the to-be-distributed order package when the candidate dispenser performs the delivery task corresponding to the to-be-distributed order package;

a delivery efficiency determination module configured to determine, for each time combination, a delivery efficiency of the candidate delivery member when executing the delivery task corresponding to the order package to be distributed according to the time combination, as the delivery efficiency of the candidate delivery member in the time combination;

a matching degree determination module configured to determine a matching degree of the candidate distributor with respect to the order package to be distributed according to distribution efficiency of the candidate distributor under the various time combinations;

and the distribution module is configured to select a target delivery person from the candidate delivery persons according to the matching degree of each candidate delivery person for the order package to be distributed, and distribute the order package to be distributed to the target delivery person for execution.

The present specification provides a computer-readable storage medium storing a computer program which, when executed by a processor, implements the above-described method of order allocation.

The present specification provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the order distribution method when executing the program.

The technical scheme adopted by the specification can achieve the following beneficial effects:

in the order distribution method provided by the present specification, an order package to be distributed including at least one order may be obtained, then, for each candidate distributor, various time combinations of the candidate distributor completing the delivery of the distributed orders at the delivery points of the distributed orders related to the candidate distributor when the candidate distributor executes the delivery task corresponding to the order package to be distributed are determined, for each time combination, the delivery efficiency of the candidate distributor when the candidate distributor executes the delivery task corresponding to the order package to be distributed according to the time combination is determined as the delivery efficiency of the candidate distributor under the time combination, then, according to the delivery efficiency of the candidate distributor under the various time combinations, the matching degree of the candidate distributor for the order package to be distributed is determined, further, according to the matching degree of each candidate distributor for the order package to be distributed, the target distributor is selected from the candidate distributors, and the order package to be distributed is distributed to the target distributor for execution.

It can be seen from the above method that, since various time combinations of the candidate suppliers completing the taking and delivering of the supplies at the delivery points of the supplies related to the order package to be allocated can be referred to, the comprehensive delivery efficiency when the candidate suppliers perform the delivery tasks corresponding to the order package to be allocated is determined comprehensively, so that the selected target suppliers can complete the delivery tasks corresponding to the order package to be allocated as much as possible according to the specified time limit of the orders included in the order package to be allocated, thereby effectively ensuring the delivery efficiency of the suppliers.

Drawings

The accompanying drawings, which are included to provide a further understanding of the specification and are incorporated in and constitute a part of this specification, illustrate embodiments of the specification and together with the description serve to explain the principles of the specification and not to limit the specification in a limiting sense. In the drawings:

FIG. 1 is a flow chart illustrating a method for order distribution according to the present disclosure;

FIG. 2 is a schematic diagram of an arrangement of dispenser pick-up points provided herein;

FIG. 3 is a schematic diagram of an order distribution apparatus provided herein;

fig. 4 is a schematic diagram of an electronic device corresponding to fig. 1 provided in the present specification.

Detailed Description

To make the objects, technical solutions and advantages of the present specification clearer and more complete, the technical solutions of the present specification will be described in detail and completely with reference to the specific embodiments of the present specification and the accompanying drawings. It is to be understood that the embodiments described are only a few embodiments of the present disclosure, and not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present specification without any creative effort belong to the protection scope of the present specification.

The technical solutions provided by the embodiments of the present description are described in detail below with reference to the accompanying drawings.

Fig. 1 is a schematic flow chart of an order allocation method in this specification, including the following steps:

s101: and acquiring an order packet to be distributed, wherein the order packet to be distributed comprises at least one order.

In this specification, for an order of a user, some orders may be packaged to obtain an order package to be allocated, and then in a subsequent process, the obtained order package to be allocated is entirely allocated to a distributor for execution. The order package to be allocated may include at least one order, that is, the order package to be allocated may include only one order or a plurality of orders, and the number range of the orders included in the order package to be allocated may be determined according to actual needs, and the present specification is not limited specifically.

For convenience of description, the order distribution method provided in this specification will be described in detail below only by taking the server as an execution subject.

In the process of packaging the orders to be executed, the server can package the orders with relatively close receiving addresses and/or relatively close picking addresses, or package the orders placed by the same user at different times with short time intervals into an order package to be distributed, so that the order package is convenient for a distributor to distribute.

In addition, the order allocation method provided in the present specification can be applied to various service scenarios, such as takeaway delivery, online commodity delivery, city-sharing express delivery, fresh and fresh delivery, and other services related to delivery, and the present specification does not limit specific service scenarios.

S102: and determining various time combinations of the candidate delivery staff for completing delivery of the delivered objects at the delivery points related to the to-be-distributed order packages when the candidate delivery staff execute the delivery tasks corresponding to the to-be-distributed order packages.

After the order package to be distributed is obtained, the server may determine a plurality of candidate distributors, and select the distributor for executing the distribution task corresponding to the order package to be distributed from among the candidate distributors. The server may determine, from a plurality of distributors, a distributor that is closer to the receiving address and/or the picking address corresponding to the order related to the to-be-distributed order package as each candidate distributor, and may, of course, use, as a candidate distributor, a distributor whose current position is located within the distribution range, or a distributor responsible for the distribution task within the distribution range, according to the distribution range in which the order related to the to-be-distributed order package is located.

In practice, an order will often refer to at least one delivery pick-up point, for example, for a take-away order, the take-away order refers to a place where a delivery person takes a meal, typically a merchant, and a delivery point refers to a place where the delivery person delivers the take-away to a user, typically a receiving place of the user, or a delivery place where the user and the delivery person meet (e.g., a main gate of a building, a main gate of a cell, etc.).

In the prior art, when predicting the delivery efficiency of a delivery person for executing an order, the server usually predicts the total time consumed by the delivery person for executing the order according to the fixed time consumed by the delivery person at each delivery point related to the order, and then determines whether to allocate the order to the delivery person for execution. For example, the server may determine the delivery efficiency of the order by the distributor when determining the total time taken by the distributor to execute the order, as a function of the time the distributor spends traveling to the meal and the delivery point as predicted by the distributor's travel speed, for a fixed 10 minutes spent by the distributor at the meal and delivery points.

However, the time spent by the dispatcher at the meal taking and delivery points is not a relatively fixed time, and sometimes the time spent by the dispatcher at the meal taking or delivery points is short, and sometimes the time spent at the meal taking or delivery points is long. If the delivery efficiency of the deliverer is predicted in a fixed time period, the predicted delivery efficiency is often low in accuracy, and thus the order distribution may be unreasonable.

Therefore, in this specification, the server may determine, for each candidate dispenser, various time combinations at which the candidate dispenser completes delivery of the delivery at each delivery pick-up point related to the to-be-distributed order package when the candidate dispenser executes the delivery task corresponding to the to-be-distributed order package, and further determine the delivery efficiency of the candidate dispenser for executing the delivery task corresponding to the to-be-distributed order package according to the determined various time combinations.

Specifically, the server may count a time length range consumed by each distributor historically at the meal taking point or the delivery point, perform random sampling in the time length range to obtain each specific time length, and perform random combination on each specific time length to obtain each time combination. For example, assuming that the order package to be distributed contains only one order, which relates to two delivery points a and B, the server counts that the time period consumed by each distributor historically at the point of serving or at the point of delivery is in the range of 1-30 min, and can sample out 5min and 13min in this time period range, and obtain the time combination: the consumed time of the distribution article receiving and sending point A is 5min, and the consumed time of the distribution article receiving and sending point B is 13min. Then, the server can sample out 21min and 2min in this time length range, and obtain the time combination: the consumption time of the distribution article receiving and sending point A is 21min, and the consumption time of the distribution article receiving and sending point B is 2min. And so on, thereby obtaining various time combinations. The server may count the time length range for each delivered article pickup point by using the time length historically consumed by the deliverer at the delivered article pickup point, that is, the time length ranges counted by the server may be different for different delivered article pickup points.

Of course, in this specification, the server may also determine feature information corresponding to at least one order included in the to-be-distributed order package, and input the extracted feature information into a preset time estimation model, so as to determine, through the time estimation model, that when the candidate distributor executes the distribution task corresponding to the to-be-distributed order package, the candidate distributor completes various time combinations of distribution at each distribution pick-up point related to the to-be-distributed order package.

The characteristic information extracted from the order contained in the order package to be distributed by the server can be set according to actual requirements. For example, for each order contained in the order package to be allocated, the characteristic information extracted from the order may include: the amount of the order, the average time to stock by the merchant corresponding to the order, the average time spent by the user in historically picking up the shipment, the type of shipment involved in the order, and the like. The characteristic information often has a certain relation with a final output result of the time estimation model, taking the amount of an order as an example, in a take-out scene, the larger the amount of an order is, the more dishes ordered by a user are often meant, or the dishes ordered by the user are more valuable, so that a merchant may need to spend longer time for preparing meals, and therefore, the larger the amount of the order is, the longer the time consumed by a distributor at a meal taking point may be. For another example, also taking a take-away scenario as an example, if the type of the dish corresponding to the order is a dish requiring a long cooking time, the merchant also needs a long time to prepare the dish, and therefore, the time consumed by the distributor at the meal taking place may be longer.

Of course, in addition to extracting the feature information from the orders included in the order package to be distributed, the feature information of the candidate deliverer, such as the order timeout rate, the average speed of driving, and the like, may also be determined, so that the feature information and the feature information extracted from the order package to be distributed are input into the time estimation model together to obtain various corresponding time combinations.

Further, the server may input, for each delivery point to which the order package to be distributed relates, feature information corresponding to an order related to the delivery point in the order package to be distributed into the time estimation model, to obtain a time length probability distribution of various time lengths consumed by the candidate distributor to complete delivery of the distribution at the delivery point, and the time length probability distribution is used as the time length probability distribution corresponding to the delivery point.

The time length probability distribution corresponding to the distribution receiving and dispatching point is used for representing the possibility of various time lengths consumed by the candidate distributor at the distribution receiving and dispatching point and the corresponding probability. In other words, in the time length probability distribution corresponding to the delivery destination, the probability that the time consumed by the candidate delivery person at the delivery destination is within each time length range can be reflected. For example, suppose that the probability distribution of the duration corresponding to a distribution pickup point is: l. the ₁ ～12％、l ₂ ～5％、l ₃ ～34％、l ₄ ～22％、l ₅ ～18％、l ₆ ～9％，l ₁ ～l ₆ Is 6 time length ranges. The 6 duration ranges may be equally divided, e.g., l ₁ 1-10min ₂ Is 11-20 min ₃ The time is 21-30 min, and so on.

After determining the time length probability distribution corresponding to each delivery point, the server may further determine that when the candidate deliverer executes the delivery task corresponding to the to-be-distributed order package, the candidate deliverer completes various time combinations of delivery at each delivery point related to the to-be-distributed order package. Specifically, the server may determine various time combinations in an inverse sampling manner. The server samples each distribution object receiving and sending point related to the order package to be distributed in each preset time length range to obtain each sampling time length which is used as each sampling time length corresponding to the distribution object receiving and sending point, and then determines that the candidate distributor completes each time combination of distribution objects at each distribution object receiving and sending point related to the order package to be distributed when the candidate distributor executes the distribution task corresponding to the order package to be distributed according to each sampling time length corresponding to each distribution object receiving and sending point related to the order package to be distributed.

That is, the server may sample each sampling duration according to the determined duration probability distribution according to preset duration ranges (the duration range mentioned here may be different from each duration range in the duration probability distribution). For example, assuming a duration range of 1-10 min, the server may sample each sampling duration such as 3min, 7min, 4.6min, 2.1min in the duration range according to the duration probability distribution.

And aiming at each duration range, the number of the sampling durations sampled in the duration range is in positive correlation with the probability distribution of the duration corresponding to the delivery object receiving and sending point in the duration probability distribution corresponding to the duration range. That is, if the probability of a duration range in the duration probability distribution is higher, the number of sampling durations sampled from the duration range is higher.

The various time combinations determined by the server can be represented in the form of a matrix, which is as follows:

in the matrix, L represents each delivery point, and N represents the number of time combinations, so each row of the matrix can be regarded as a time combination. Each time combination can be obtained by randomly combining the sampling durations obtained by the sampling.

The time length estimation model can be in various forms, such as a neural network, a convolutional neural network and other conventional algorithms, and the specific form of the time length estimation model is not limited in the specification. Further, the duration estimation model may be trained by a conventional method, for example, by using KL divergence and other loss functions to implement training of the duration estimation model in a supervised manner, and the specific training process is not described in detail herein.

S103: and determining the distribution efficiency of the candidate distributor when executing the distribution task corresponding to the order package to be distributed according to each time combination as the distribution efficiency of the candidate distributor under the time combination.

After determining the various time combinations, the server may determine the order sequence of the delivery points of the distributed articles related to the order package to be distributed according to the time sequence of each order related to the order package to be distributed. For example, suppose that the order package to be distributed contains two orders a and B, where the order a corresponds to a meal a and a delivery a, and the order B corresponds to a meal B and a delivery B. If the order placing time corresponding to the order a is earlier than the order placing time corresponding to the order B, the server may determine that the arrangement order of the four delivery points is as follows: taking a meal A-delivering point A-taking a meal B-delivering point B.

Of course, there may be various ways for the server to determine the arrangement order of the delivery points, and if the deliverer is arranged to take the food in a unified manner first and then deliver the food in a unified manner, the arrangement order may be: taking a meal A, taking a meal B, delivering a meal A and delivering a meal B. For another example, when determining the ranking order, the server may not only refer to the order placing time of the order, but also determine the order by combining the current location of the candidate deliverer, for example, if the current location of the candidate deliverer is closer to the meal taking point B, the ranking order may be: taking a meal B, taking a meal A, delivering a meal A and delivering a meal B. Other ways of determining the arrangement order of the delivery points of the distributed objects by the server are not necessarily illustrated here.

Further, the server may determine, according to the ranking order, a schedule of the candidate delivery staff completing the delivery task corresponding to the order package to be distributed under the condition that it takes a fixed time for the candidate delivery staff to take and deliver the delivery goods at the delivery points related to the order package to be distributed. That is, the server determines the total time consumed by the candidate delivery member to complete the delivery task corresponding to the to-be-distributed order package under the condition that the candidate delivery member consumes the fixed time at each delivery point, as shown in fig. 2.

Fig. 2 is a schematic diagram of an arrangement of the dispensing receiving and delivering points provided in the present specification.

In fig. 2, four delivery pickup points, namely, a meal pickup point 1, a delivery point 1, a meal pickup point 2, and a delivery point 2, the time consumed by the candidate dispenser to reach the meal pickup point 1 and the time consumed by the candidate dispenser at two adjacent delivery pickup points may be determined according to the traveling speed and the route corresponding to the candidate dispenser, and in combination with the fixed time duration consumed by the candidate dispenser at each delivery pickup point, a schedule at which the candidate dispenser performs the delivery task corresponding to the to-be-assigned order package may be determined. The schedule may indicate the time at which the candidate dispenser arrived at and departed from each of the dispenser pick-up points.

Then, the server may determine, for each delivery pick-up point related to the to-be-distributed order package, a time deviation between a time length consumed by the candidate dispenser to pick up the delivery at the delivery pick-up point and a fixed time length consumed by the candidate dispenser to pick up the delivery at the delivery pick-up point in the time combination as a time deviation corresponding to the delivery pick-up point, and correct the time schedule according to the time deviation corresponding to each delivery pick-up point related to the to-be-distributed order package to obtain a corrected time schedule corresponding to the time combination.

In this specification, the time deviation occurs in the time length, which is mainly reflected in the time length consumed by the candidate dispenser at each delivery point, that is, the time length consumed by the candidate dispenser to reach an initial delivery point and the time length consumed by the candidate dispenser between any two adjacent delivery points are determined according to the route and the driving speed corresponding to the candidate dispenser, so the time length consumed by the candidate dispenser on the route can be regarded as no time deviation occurs or the time deviation is small.

Based on the time, the server can correct the schedule by determining the time deviation of the candidate distributors at the delivery points of the distributed objects, and further determine the distribution efficiency of the candidate distributors to execute the distribution tasks corresponding to the to-be-distributed order packages according to the corrected schedule. With specific reference to the following formula:

taking the taking of the food as an example,

for indicating the time at which the candidate deliverer arrives at the meal I, as determined by the candidate deliverer consuming a fixed amount of time at the meal I

It indicates the time at which the candidate dispenser determined according to one time combination reaches meal i,

the time offset for the candidate dispenser to arrive at meal i is determined in these two different ways.

For leaving a meal/according to the time at which the candidate deliverer will consume a fixed length of time at the meal/as determined by the candidate deliverer

It indicates the time at which the candidate dispenser determined according to one time combination leaves the meal/,

the time offset for the candidate dispenser to leave the meal/is determined in these two different ways.

The same is true for the delivery point, and in particular, the server may determine the time offset of the candidate deliverer to the delivery point by the following formula.

If the distribution material receiving and delivering point is the delivery point, the distribution material receiving and delivering point is the delivery point

For indicating when the candidate deliverer arrives at delivery point l, as determined by the candidate deliverer consuming a fixed amount of time at delivery point l, and

it indicates the time at which the candidate dispenser determined according to one time combination arrives at delivery point l,

it indicates the time offset of the candidate dispenser to reach delivery point/as determined by these two different approaches.

Further, the server may determine the time offset of the candidate dispenser from the delivery point by the following equation.

For the time at which the candidate dispenser leaves delivery point l, as determined by the candidate dispenser consuming a fixed length of time at delivery point l, and

it indicates the time at which the candidate dispenser determined according to one time combination leaves delivery point/,

the time offset at which the candidate dispenser leaves delivery point/is determined in these two different ways.

For the first formulaIn a case where the number of the first and second electrodes is small,

for indicating the length of time that the candidate dispenser needs to wait after reaching delivery point l in such a time combination, and therefore,

the determination may be performed according to the determined time when the candidate delivery person reaches the delivery point l and the waiting time required after the candidate delivery person reaches the delivery point l.

If the delivery pick-up point is the delivery pick-up point, in the modified schedule corresponding to the time combination, the later time of the time when the candidate delivery person arrives at the delivery pick-up point and the time when the candidate delivery person arrives at the delivery pick-up point is taken as the departure time of the candidate delivery person at the delivery pick-up point, which may be specifically referred to as the following formula:

for indicating when a merchant is preparing a meal at a pick-up point, i.e. a delivery pick-up point, for which the meal is taken

And

the reason why the time when the candidate deliverer leaves the meal taking point l is determined in practical application because, in case the deliverer has not reached the merchant when the merchant takes the meal, the time when the candidate deliverer leaves the merchant depends on when the candidate deliverer reaches the merchant, and in case the candidate has reached the merchant, the merchant has not completed preparing the meal, the time when the candidate deliverer leaves the merchant depends on when the merchant completes preparing the meal.

In this way, the server may correct the schedule by determining a time deviation of the candidate deliverer at each delivery point of the deliveries, to obtain a corrected schedule corresponding to the time combination, and then determine delivery efficiency of the candidate deliverer when executing the delivery task corresponding to the to-be-distributed order package according to the corrected schedule corresponding to the time combination. In this specification, the delivery efficiency may be expressed in various forms, for example, it may be expressed in a form of score, or it may be expressed in a time length consumed by the candidate delivery staff to execute the delivery task corresponding to the order package to be distributed.

Of course, when determining the delivery efficiency, the server may directly deduce, from the time combination, the time at which the candidate delivery person arrives at each delivery destination from the time at which the candidate delivery person arrives at the first delivery destination. For example, assume that the server determines that the time when the candidate delivery person arrives at the first delivery point is 10, according to the location of the candidate delivery person and the location of the first delivery point: 00, in such a time combination, the time consumed by the candidate dispenser at the first dispenser pickup point is 20min, the time when the candidate dispenser departs from the first dispenser pickup point is 10, and then the server determines that the candidate dispenser takes 5min to reach the second dispenser pickup point according to the distance between the first dispenser pickup point and the second dispenser pickup point, so the time taken for the candidate dispenser to reach the second dispenser pickup point is: 10, and so on to determine when the candidate dispenser reaches each of the delivery pick-up points.

S104: and determining the matching degree of the candidate delivery staff for the order package to be distributed according to the delivery efficiency of the candidate delivery staff under the various time combinations.

The server can sequentially determine the distribution efficiency of the candidate distributor under each time combination through the mode, and then comprehensively measures the matching degree between the candidate distributor and the order package to be distributed through the distribution efficiencies. If the determined matching degree is higher, it indicates that it is more appropriate to allocate the order package to be allocated to the candidate distributor for execution, and the candidate distributor has a lower possibility of overtime of the order corresponding to the order package to be allocated in the process of executing the distribution task corresponding to the order package to be allocated, and correspondingly, if the determined matching degree is lower, it indicates that it is less appropriate to allocate the order package to be allocated to the candidate distributor for execution, and the candidate distributor has a higher possibility of overtime of the order corresponding to the order package to be allocated in the process of executing the distribution task corresponding to the order package to be allocated.

Specifically, in this specification, the delivery efficiency of the candidate deliverer at various time combinations may include: the comprehensive distribution index duration after the candidate distributor executes the distribution task of the order to be executed under various time combinations comprises the following steps: and executing at least one of a comprehensive order overtime time, a comprehensive delivery consumption time and a comprehensive delivery waiting time after the candidate delivery person performs the delivery task of the order to be executed under various time combinations.

For example, for the composite order timeout duration, if the total order timeout duration is longer in the process of executing the delivery tasks of the to-be-executed orders by the candidate deliverer under various time combinations, it is not appropriate to allocate the to-be-allocated order package to the candidate deliverer. For another example, for the comprehensive delivery consumed time length, if the total delivery consumed time length is long in the process that the candidate delivery person performs the delivery task of the to-be-executed order in various time combinations, it indicates that the delivery efficiency is low when the candidate delivery person performs the delivery task corresponding to the to-be-distributed order package.

The above-mentioned orders to be executed include: orders contained in the order package to be distributed, and orders that have been accepted by the candidate dispatchers and subsequently need to be executed.

Based on the comprehensive distribution index duration, the server can further determine the matching degree of the candidate distributor for the order package to be distributed. Specifically, for each time combination, the server may determine, as the delivery index duration corresponding to the time combination, the delivery index duration after the candidate dispenser executes the to-be-executed order that needs to be executed by the candidate dispenser according to the time combination, and then, the server may determine, according to the delivery index duration corresponding to each time combination, the comprehensive delivery index duration after the candidate dispenser executes the delivery task of the to-be-executed order in each time combination, and further determine, according to the determined comprehensive delivery index duration, the matching degree of the candidate dispenser for the to-be-distributed order package, where if the determined comprehensive delivery index duration is shorter, the matching degree of the candidate dispenser for the to-be-distributed order package is higher.

Taking the comprehensive order timeout duration as an example, the server may determine the comprehensive order timeout duration by the following formula:

f _t (x _n ) And is used to indicate the timeout duration corresponding to each time combination, for example, when n takes 1, the timeout duration after the candidate deliverer executes the to-be-executed order according to the first time combination is indicated.

The time-out duration for the composite order is determined. According to the formula, the server can determine the overtime duration of the comprehensive order by taking the average value of the overtime durations of the candidate distributors after executing the order to be executed according to each time combination. Of course, other comprehensive delivery indicator durations may also be determined in a similar manner, and are not illustrated in detail herein.

The server can determine the matching degree of the candidate distributor for the order package to be distributed according to any one comprehensive distribution index duration, and can also determine the matching degree of the candidate distributor for the order package to be distributed according to various comprehensive distribution index durations. For example, the server may perform a weighted summation on the three types of the comprehensive delivery index durations to determine a matching degree of the candidate delivery staff for the order package to be distributed.

In this specification, the delivery efficiency of the candidate deliverer at various time combinations may further include: the candidate dispatchers perform the post-delivery tasks of the orders to be fulfilled at various time combinations.

Further, the server may sort the time combinations according to a sequence from a large time duration to a small time duration of the delivery indexes corresponding to each time combination to obtain a time combination sort, then determine the comprehensive risk score according to the time duration of the delivery indexes corresponding to the time combinations located before the first set ranking in the time combination sort, and further determine the matching degree of the candidate deliverer for the order package to be distributed according to the comprehensive risk score, wherein if the comprehensive risk score is lower, the matching degree of the candidate deliverer for the order package to be distributed is higher.

As can be seen from this description, the server determines the composite risk score based on the delivery index duration with a relatively long duration, so the composite risk score is mainly used to measure the risk condition when the candidate delivery staff performs the delivery task corresponding to the order package to be distributed. That is, if the composite risk score is lower, it indicates that the candidate delivery person can still ensure a certain delivery efficiency and reduce the possibility that the orders included in the to-be-distributed order package will time out even if the candidate delivery person performs the delivery task corresponding to the to-be-distributed order package under some special circumstances (e.g., the number of orders placed by users is too large in a period of time and the capacity pressure is great).

Further, in this specification, the server may also determine, according to the above-mentioned duration of the comprehensive delivery index, the comprehensive risk score, and the risk weight corresponding to the comprehensive risk score, the matching degree of the candidate delivery staff for the order package to be distributed. The matching degree of the candidate delivery staff for the order package to be distributed is comprehensively determined through the condition of coping with risks when the candidate delivery staff execute the delivery tasks corresponding to the order package to be distributed and various comprehensive delivery index durations for measuring the delivery efficiency of the candidate delivery staff when the candidate delivery staff execute the delivery tasks corresponding to the order package to be distributed, and therefore the rationality of the server in the follow-up distribution of the order package to be distributed is further ensured.

It should be noted that, if the number of orders placed by the user is greater in the delivery time period corresponding to the order package to be allocated, the risk weight may be higher, that is, in the case of higher transportation pressure, the ratio of the risk scores is further integrated in the process of determining the matching degree, so as to ensure that the order package to be allocated can be allocated to a more appropriate delivery person for execution, and further reduce the possibility of timeout of orders included in the order package to be allocated.

In this specification, the delivery time period corresponding to the order package to be distributed may refer to an order placing time of a user corresponding to an order included in the order package to be distributed, may refer to a delivery commitment time corresponding to an order included in the order package to be distributed (that is, a time when a delivery person is delivered to a hand of the user by a delivery commitment user), may refer to a time period from the order placing time to the delivery commitment time, may refer to a time period in which the delivery time of the user is a starting time and a next set time period, or a time period in which the user desires to deliver a delivery to his/her hand is located, and the specific form of the delivery time period corresponding to the order package to be distributed is not further limited in this specification.

S105: and selecting target delivery personnel from the candidate delivery personnel according to the matching degree of each candidate delivery personnel for the order package to be distributed, and distributing the order package to be distributed to the target delivery personnel for execution.

The server determines the matching degree of each candidate dispenser for the order package to be distributed, the candidate dispensers can be ranked according to the sequence from high matching degree to low matching degree, the candidate dispensers not lower than the designated ranking are selected as target dispensers, and the order package to be distributed is distributed to the target dispensers for execution.

For example, the server may take the candidate distributor with the highest matching degree for the order package to be distributed as the target distributor, and distribute the order package to be distributed to the target distributor for execution. For another example, after the server sorts the candidate dispatchers in the order from high to low matching degrees, one candidate dispatcher may be randomly selected from the top N (N is a positive integer determined according to actual needs) candidate dispatchers as a target dispatcher, and the to-be-distributed order package is distributed to the target dispatcher for execution.

In addition to the above-mentioned manner, for each candidate dispenser, the server may determine, as the basic delivery efficiency corresponding to the candidate dispenser, a basic delivery efficiency when the candidate dispenser executes the delivery task corresponding to the order to be distributed according to a fixed time period consumed by the candidate dispenser to take and deliver the delivery at each delivery point related to the order package to be distributed. Then, the server may determine a basic sorting result of each candidate dispenser for the order to be distributed according to a descending order of the basic dispensing efficiency of each candidate dispenser, and further select a target dispenser from the candidate dispensers according to the basic sorting result and the matching degree of each candidate dispenser for the order package to be distributed.

As mentioned above, the candidate dispatchers are sorted according to the fixed time length consumed by the candidate dispatchers to fetch and deliver the dispatches at the delivery points related to the order package to be distributed, it can be understood that the server determines the delivery efficiency of each candidate dispatcher when executing the delivery task corresponding to the order package to be distributed according to the mode adopted by the prior art, that is, each candidate dispatcher consumes the fixed set time length at each delivery point.

Further, the server may determine candidate dispatchers located at the second set ranking from the basic ranking result as reference dispatchers, select, from the candidate dispatchers, a candidate dispatcher whose matching degree for the order package to be allocated is higher than that of the reference dispatcher, and determine a target dispatcher from the selected candidate dispatchers.

That is, the server may select one candidate having a higher basic delivery efficiency (e.g., the candidate having the highest basic delivery efficiency) from the basic ranking results as a reference dispenser, and determine the candidate having a higher matching degree with respect to the order package to be distributed than the reference dispenser by using the reference dispenser as a baseline.

The server can determine candidate delivery parks meeting preset conditions from the selected candidate delivery personnel, and determine target delivery personnel according to the candidate delivery personnel meeting the preset conditions. In order to further ensure the delivery efficiency of the delivery staff when executing the delivery tasks, the server may determine, for each selected candidate delivery staff, that the candidate delivery staff meets a preset condition if the distance difference between the distance length required for the candidate delivery staff to execute the delivery task corresponding to the order to be distributed and the distance length required for the benchmark delivery staff to execute the delivery task corresponding to the order package to be distributed is smaller than a set distance threshold, and may further use the candidate delivery staff as the target delivery staff.

That is, if the distance that the candidate dispenser needs to travel to execute the corresponding delivery job when the order package to be allocated is not much different from the distance that the reference dispenser needs to travel to execute the corresponding delivery job when the order package to be allocated is executed, the delivery efficiency of the candidate dispenser as compared with the reference dispenser will not be low or may be higher, and thus the candidate dispenser can be selected as the target dispenser.

Of course, for each selected candidate deliverer, if the order number difference between the order number of the to-be-executed orders allocated to the candidate deliverer after determining that the to-be-allocated order package is allocated to the candidate deliverer and the order number of the to-be-executed orders allocated to the benchmark deliverer after determining that the to-be-allocated order package is allocated to the benchmark deliverer is smaller than the set order number threshold, it may be determined that the candidate deliverer meets the preset condition, and may further be used as the target deliverer.

That is, if it is assumed that after the order package to be distributed is distributed to the candidate distributor and the benchmark distributor, the order quantity of the orders to be executed by the candidate distributor (the order quantity of the orders included in the order package to be distributed + the order quantity of the orders that have been accepted by the candidate distributor and need to be executed by the candidate distributor) is not much different from the order quantity of the orders to be executed by the benchmark distributor (the order quantity of the orders included in the order package to be distributed + the order quantity of the orders that have been accepted by the benchmark distributor and need to be executed by the benchmark distributor), the distribution efficiency of the candidate distributor compared with the benchmark distributor will not be low or may be higher, so that the candidate distributor can be selected as the target distributor.

Further, the preset conditions shown in the above examples may also be used in combination, and specifically, the server may use candidate dispatchers that satisfy both of the preset conditions as target dispatchers. Of course, the server may also determine, from the selected candidate suppliers (i.e., the candidate suppliers whose matching degree for the order package to be allocated is higher than that of the reference distributor), the length of the route required to be traveled when executing the delivery task corresponding to the order package to be allocated, and/or after receiving the order package to be allocated, the number of orders to be executed that need to be executed is smaller than that of the candidate suppliers of the reference distributor, and the candidate suppliers serve as the target suppliers, and allocate the order package to be allocated to the target suppliers for execution.

In the present specification, the set distance threshold and the set order number threshold mentioned above may be dynamically adjusted according to actual delivery conditions. Specifically, if it is determined that the more the order placing number of the user is in the distribution time period corresponding to the order package to be distributed, the value of at least one of the set distance threshold and the set order number threshold is increased. That is, if the pressure of the whole transport capacity is large in the distribution time period corresponding to the order package to be distributed, the standard of selecting the target distributor can be reduced appropriately, so as to ensure the whole distribution efficiency under the condition that the whole transport capacity faces large pressure.

It should be noted that, the above-mentioned reference deliverer may also be finally used as a target deliverer to execute a delivery task corresponding to the order package to be distributed, that is, if the matching degree of the order package to be distributed does not have a candidate deliverer higher than the reference deliverer or does not have a candidate deliverer higher than the reference deliverer meeting the above-mentioned preset condition, the server may select the reference deliverer as the target deliverer.

It can be seen from the above method that, various time combinations of the candidate distributors completing the distribution of the distributed items at the distribution points related to the to-be-distributed order packages can be referred to, and the comprehensive distribution efficiency when the candidate distributors perform the distribution tasks corresponding to the to-be-distributed order packages is comprehensively determined, so that the selected target distributors can complete the distribution tasks corresponding to the to-be-distributed order packages as much as possible according to the specified time limit of the orders contained in the to-be-distributed order packages, and the distribution efficiency of the distributors is effectively ensured.

The order allocation method provided above for one or more embodiments of the present specification also provides a corresponding order allocation device, based on the same idea, as shown in fig. 3.

Fig. 3 is a schematic diagram of an order allocation apparatus provided in the present specification, including:

an obtaining module 301, configured to obtain an order package to be distributed, where the order package to be distributed includes at least one order;

a time combination determination module 302 configured to determine, for each candidate dispenser, various time combinations of the candidate dispenser completing the delivery of the delivery at the delivery points related to the to-be-distributed order package when the candidate dispenser performs the delivery task corresponding to the to-be-distributed order package;

a delivery efficiency determining module 303 configured to determine, for each time combination, a delivery efficiency of the candidate deliverer when the candidate deliverer executes the delivery task corresponding to the order package to be distributed according to the time combination, as the delivery efficiency of the candidate deliverer in the time combination;

a matching degree determination module 304, configured to determine the matching degree of the candidate distributor with respect to the order package to be distributed according to the distribution efficiency of the candidate distributor under the various time combinations;

and an allocating module 305 configured to select a target delivery member from the candidate delivery members according to the matching degree of each candidate delivery member for the order package to be allocated, and allocate the order package to be allocated to the target delivery member for execution.

Optionally, the time combination determining module 302 is configured to determine feature information corresponding to at least one order included in the to-be-allocated order package; and inputting the characteristic information into a preset time estimation model, and determining various time combinations of the candidate delivery staff for completing delivery of the delivered objects at delivery points of the delivered objects related to the to-be-distributed order package when the candidate delivery staff executes the delivery tasks corresponding to the to-be-distributed order package through the time estimation model.

Optionally, the time combination determining module 302 is configured to, for each distribution pickup point related to the to-be-distributed order package, input feature information corresponding to an order related to the distribution pickup point in the to-be-distributed order package into the time estimation model, and obtain a time length probability distribution of various time lengths that the candidate distributor needs to consume to complete the pickup and delivery of the distribution at the distribution pickup point, as the time length probability distribution corresponding to the distribution pickup point; and determining various time combinations of the candidate distributors for completing the delivery of the distributed objects at the delivery points of the distributed order packages when the candidate distributors execute the delivery tasks corresponding to the distributed order packages according to the time length probability distribution corresponding to the delivery points of the distributed objects related to the distributed orders.

Optionally, the time combination determining module 302 is configured to, for each distribution object pick-up point related to the to-be-distributed order package, sample in each preset time length range to obtain each sampling time length, which is used as each sampling time length corresponding to the distribution object pick-up point, where, for each time length range, the number of the sampling time lengths obtained by sampling in the time length range is in positive correlation with the probability corresponding to the time length range in the time length probability distribution corresponding to the distribution object pick-up point; and determining various time combinations of the candidate distributors for completing the delivery of the distributed objects at the delivery points of the distributed order packages when the candidate distributors execute the delivery tasks corresponding to the distributed order packages according to the sampling durations corresponding to the delivery points of the distributed objects related to the distributed order packages.

Optionally, the distribution efficiency determining module 303 is configured to determine an arrangement order of the delivery points of the to-be-distributed order package according to a time order of each order involved in the to-be-distributed order package; according to the arrangement sequence, determining that the candidate delivery staff completes the schedule of the delivery tasks corresponding to the to-be-distributed order packages under the condition that the candidate delivery staff consumes fixed time for taking and delivering the delivery goods at the delivery points of the to-be-distributed order packages; determining a time deviation between a time length consumed by the candidate dispenser for taking and delivering the dispenser at the dispenser pick-and-place point and a fixed time length consumed by the candidate dispenser for taking and delivering the dispenser at the dispenser pick-and-place point in the time combination as a time deviation corresponding to the dispenser pick-and-place point for each dispenser pick-and-place point related to the to-be-distributed order package; correcting the timetable according to the time deviation corresponding to each distribution article receiving and sending point related to the order packet to be distributed to obtain a corrected timetable corresponding to the time combination; and determining the distribution efficiency of the candidate distributor when executing the distribution tasks corresponding to the to-be-distributed order packages according to the time combination according to the corrected time table corresponding to the time combination.

Optionally, for each delivery object pick-up point related to the to-be-distributed order package, if the delivery object pick-up point is a delivery object pick-up point, in the modified schedule corresponding to the time combination, a later time between a time when the delivery object pick-up point determined according to the time combination finishes preparation of a delivery object and a time when the candidate delivery person arrives at the delivery object pick-up point is taken as a departure time of the candidate delivery person at the delivery object pick-up point.

Optionally, the delivery efficiency of the candidate deliverer at the various time combinations includes: the comprehensive distribution index duration after the candidate distributor executes the distribution task of the to-be-executed order under the various time combinations includes: at least one of a comprehensive order timeout duration, a comprehensive delivery consumption duration and a comprehensive delivery waiting duration after the candidate deliverer executes the delivery task of the to-be-executed order under the various time combinations, wherein the to-be-executed order comprises: orders contained in the order package to be distributed and orders which are accepted by the candidate distributor and need to be executed;

the matching degree determining module 304 is configured to determine, for each time combination, a delivery index duration after the candidate delivery person executes the to-be-executed order that needs to be executed by the candidate delivery person according to the time combination, as a delivery index duration corresponding to the time combination; determining the comprehensive distribution index duration of the candidate distributor after executing the distribution tasks of the orders to be executed under the various time combinations according to the distribution index duration corresponding to each time combination; and determining the matching degree of the candidate distributor for the order package to be distributed according to the comprehensive distribution index duration, wherein if the comprehensive distribution index duration is shorter, the matching degree of the candidate distributor for the order package to be distributed is higher.

Optionally, the delivery efficiency of the candidate deliverer at the various time combinations includes: the candidate dispatchers execute the comprehensive risk scores after the dispatching tasks of the orders to be executed under the various time combinations;

the matching degree determining module 304 is configured to sort the time combinations according to a sequence from large to small of the distribution index duration corresponding to each time combination to obtain a time combination sort; determining the comprehensive risk score according to the distribution index duration corresponding to the time combination positioned before the first set ranking in the time combination ranking; and determining the matching degree of the candidate distributor for the order package to be distributed according to the comprehensive risk score, wherein if the comprehensive risk score is lower, the matching degree of the candidate distributor for the order package to be distributed is higher.

Optionally, the matching degree determining module 304 is configured to determine the matching degree of the candidate distributor for the order package to be distributed according to the comprehensive distribution index duration, the comprehensive risk score and a risk weight corresponding to the comprehensive risk score, where if the number of orders placed by the user is greater in a distribution time period corresponding to the order package to be distributed, the risk weight is higher.

Optionally, the allocating module 305 is configured to, for each candidate dispenser, determine, according to a fixed time period consumed by the candidate dispenser to fetch and deliver the supplies at the respective delivery points related to the order package to be allocated, a basic delivery efficiency when the candidate dispenser executes the delivery task corresponding to the order package to be allocated, as the basic delivery efficiency corresponding to the candidate dispenser; determining a basic sorting result of each candidate dispenser for the order package to be distributed according to the descending order of the basic dispensing efficiency of each candidate dispenser; and selecting target dispatchers from the candidate dispatchers according to the basic sorting result and the matching degree of each candidate dispatcher for the order package to be distributed.

Optionally, the allocating module 305 is configured to determine, from the basic sorting result, a candidate dispenser in a second set ranking as a reference dispenser; selecting candidate distributors from the candidate distributors, wherein the matching degree of the order packages to be distributed is higher than that of the benchmark distributors; and determining a target distributor according to the selected candidate distributors.

Optionally, the allocating module 305 is configured to determine, from the selected candidate dispatchers, a candidate dispatcher meeting a preset condition; determining a target distributor according to the candidate distributors meeting the preset conditions; wherein

Aiming at each selected candidate dispenser, if the distance difference between the distance length required by the candidate dispenser to execute the delivery task corresponding to the order package to be distributed and the distance length required by the benchmark dispenser to execute the delivery task corresponding to the order package to be distributed is determined to be smaller than a set distance threshold, and/or

And if the order number difference between the order number of the to-be-executed orders distributed to the candidate distributor after the to-be-distributed order package is distributed to the candidate distributor and the order number of the to-be-executed orders distributed to the standard distributor after the to-be-distributed order package is distributed to the standard distributor is smaller than the set order number threshold value, determining that the candidate distributor meets the preset condition.

Optionally, if it is determined that the more the number of orders placed by the user is in the distribution time period corresponding to the order package to be distributed, the larger the set distance threshold and/or the set order number threshold is.

The present specification also provides a computer readable storage medium having stored thereon a computer program operable to execute a method of order distribution as provided above with respect to fig. 1.

This specification also provides a schematic block diagram of an electronic device corresponding to that of figure 1, shown in figure 4. As shown in fig. 4, at the hardware level, the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, and may also include hardware required for other services. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs the computer program to implement the order allocation method described in fig. 1. Of course, besides the software implementation, this specification does not exclude other implementations, such as logic devices or combination of software and hardware, and so on, that is, the execution subject of the following processing flow is not limited to each logic unit, and may be hardware or logic devices.

In the 90 s of the 20 th century, improvements in a technology could clearly distinguish between improvements in hardware (e.g., improvements in circuit structures such as diodes, transistors, switches, etc.) and improvements in software (improvements in process flow). However, as technology advances, many of today's process flow improvements have been seen as direct improvements in hardware circuit architecture. Designers almost always obtain the corresponding hardware circuit structure by programming an improved method flow into the hardware circuit. Thus, it cannot be said that an improvement in the process flow cannot be realized by hardware physical modules. For example, a Programmable Logic Device (PLD) (e.g., a Field Programmable Gate Array (FPGA)) is an integrated circuit whose Logic functions are determined by a user programming the Device. A digital system is "integrated" on a PLD by the designer's own programming without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Furthermore, nowadays, instead of manually manufacturing an Integrated Circuit chip, such Programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development and writing, but the original code before compiling is also written by a specific Programming Language, which is called Hardware Description Language (HDL), and HDL is not only one but many, such as ABEL (Advanced Boolean Expression Language), AHDL (alternate Hardware Description Language), traffic, CUPL (core universal Programming Language), HDCal, jhddl (Java Hardware Description Language), lava, lola, HDL, PALASM, rhyd (Hardware Description Language), and vhigh-Language (Hardware Description Language), which is currently used in most popular applications. It will also be apparent to those skilled in the art that hardware circuitry for implementing the logical method flows can be readily obtained by a mere need to program the method flows with some of the hardware description languages described above and into an integrated circuit.

The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include, but are not limited to, the following microcontrollers: ARC 625D, atmel AT91SAM, microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic for the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may thus be considered a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.

The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functionality of the various elements may be implemented in the same one or more pieces of software and/or hardware in the practice of this description.

As will be appreciated by one skilled in the art, embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, the description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and so forth) having computer-usable program code embodied therein.

The description has been presented with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the description. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include forms of volatile memory in a computer readable medium, random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

Computer-readable media, including both permanent and non-permanent, removable and non-removable media, may implement the information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising one of 8230; \8230;" 8230; "does not exclude the presence of additional like elements in a process, method, article, or apparatus that comprises that element.

As will be appreciated by one skilled in the art, embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, the description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

This description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

The above description is only an example of the present specification, and is not intended to limit the present specification. Various modifications and alterations to this description will become apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification should be included in the scope of the claims of the present specification.

Claims (16)

1. A method of order distribution, comprising:

acquiring an order packet to be distributed, wherein the order packet to be distributed comprises at least one order;

for each candidate distributor, determining various time combinations of the candidate distributor for completing the delivery of the distributed goods at the delivery points related to the to-be-distributed order packages when the candidate distributor executes the delivery tasks corresponding to the to-be-distributed order packages;

determining the distribution efficiency of the candidate distributor when executing the distribution tasks corresponding to the order packages to be distributed according to each time combination, and taking the distribution efficiency of the candidate distributor under the time combination;

determining the matching degree of the candidate delivery staff for the order package to be distributed according to the delivery efficiency of the candidate delivery staff under the various time combinations;

and selecting target delivery personnel from the candidate delivery personnel according to the matching degree of each candidate delivery personnel for the order package to be distributed, and distributing the order package to be distributed to the target delivery personnel for execution.

2. The method as claimed in claim 1, wherein determining, for each candidate dispenser, various combinations of times at which the candidate dispenser completes the delivery of the delivery at the delivery points related to the to-be-distributed order package when the candidate dispenser performs the delivery task corresponding to the to-be-distributed order package, specifically comprises:

determining characteristic information corresponding to at least one order contained in the order package to be distributed;

and inputting the characteristic information into a preset time estimation model, and determining various time combinations of the candidate delivery staff for completing delivery of the delivered objects at delivery points of the delivered objects related to the to-be-distributed order package when the candidate delivery staff executes the delivery tasks corresponding to the to-be-distributed order package through the time estimation model.

3. The method as claimed in claim 2, wherein the inputting the characteristic information into a predetermined time estimation model to determine, through the time estimation model, various time combinations of the candidate delivery member completing delivery of the delivery at the delivery points related to the to-be-distributed order package when the candidate delivery member performs the delivery task corresponding to the to-be-distributed order package, specifically comprises:

inputting characteristic information corresponding to the order related to the distribution object pick-up point in the to-be-distributed order package into the time pre-estimation model aiming at each distribution object pick-up point related to the to-be-distributed order package to obtain time length probability distribution of various time lengths consumed by the candidate distributor for completing the distribution object pick-up and delivery at the distribution object pick-up point, wherein the time length probability distribution is used as the time length probability distribution corresponding to the distribution object pick-up point;

and determining various time combinations of the candidate delivery staff for completing delivery of the delivery at the delivery points related to the to-be-distributed order package when the candidate delivery staff executes the delivery task corresponding to the to-be-distributed order package according to the time length probability distribution corresponding to the delivery points of each delivery related to the to-be-distributed order package.

4. The method according to claim 3, wherein determining, according to the time length probability distribution corresponding to each delivery point involved in the order to be distributed, when the candidate delivery person performs the delivery task corresponding to the order package to be distributed, various time combinations of delivery taking of the candidate delivery person at each delivery point involved in the order package to be distributed are completed by the candidate delivery person, specifically comprising:

sampling in each preset time length range aiming at each distribution object receiving and sending point related to the order package to be distributed to obtain each sampling time length serving as each sampling time length corresponding to the distribution object receiving and sending point, wherein the number of the sampling time lengths obtained by sampling in each time length range is positively correlated with the probability distribution of the time length corresponding to the distribution object receiving and sending point in the time length probability distribution corresponding to each time length range;

and determining various time combinations of the candidate delivery staff for completing delivery of the delivery at the delivery points related to the order package to be distributed when the candidate delivery staff executes the delivery task corresponding to the order package to be distributed according to the sampling time lengths corresponding to the delivery points of the delivery related to the order package to be distributed.

5. The method as claimed in claim 1, wherein determining, for each time combination, a delivery efficiency of the candidate delivery person for performing the delivery task corresponding to the order package to be distributed according to the time combination as the delivery efficiency of the candidate delivery person at the time combination specifically comprises:

determining the arrangement sequence of the delivery points of the distribution objects related to the order package to be distributed according to the time sequence of each order related to the order package to be distributed;

according to the arrangement sequence, determining a time schedule of the candidate delivery person for executing the delivery tasks corresponding to the order packages to be distributed under the condition that the candidate delivery person consumes fixed time for taking and delivering the delivery goods at the delivery points related to the order packages to be distributed;

determining a time deviation between a time length consumed by the candidate distributor for taking and delivering the distribution at the distribution pick-up point and a fixed time length consumed by the candidate distributor for taking and delivering the distribution at the distribution pick-up point in the time combination as a time deviation corresponding to the distribution pick-up point for each distribution pick-up point related to the order package to be distributed;

correcting the timetable according to the time deviation corresponding to each distribution article receiving and sending point related to the order packet to be distributed to obtain a corrected timetable corresponding to the time combination;

and determining the distribution efficiency of the candidate distributor when executing the distribution tasks corresponding to the to-be-distributed order packages according to the time combination according to the corrected time table corresponding to the time combination.

6. The method according to claim 5, wherein, for each delivery item pickup point related to the order package to be distributed, if the delivery item pickup point is a delivery item pickup point, a later time of a time when the delivery item pickup point determined according to the time combination prepares the delivery item and a time when the candidate delivery member arrives at the delivery item pickup point in the modified schedule corresponding to the time combination is used as a departure time of the candidate delivery member at the delivery item pickup point.

7. The method of claim 1, wherein the delivery efficiency of the candidate deliverer at the various time combinations comprises: the comprehensive distribution index duration after the candidate distributor executes the distribution tasks of the orders to be executed under the various time combinations includes: at least one of a comprehensive order timeout duration, a comprehensive delivery consumption duration and a comprehensive delivery waiting duration after the candidate deliverer executes the delivery task of the to-be-executed order under the various time combinations, wherein the to-be-executed order comprises: orders contained in the order package to be distributed and orders which are accepted by the candidate distributor and need to be executed;

determining the matching degree of the candidate delivery staff for the order package to be distributed according to the delivery efficiency of the candidate delivery staff under the various time combinations, wherein the determining step specifically comprises the following steps:

for each time combination, determining the distribution index duration after the candidate distributor executes the to-be-executed order which needs to be executed by the candidate distributor according to the time combination, and taking the distribution index duration as the distribution index duration corresponding to the time combination;

determining the comprehensive distribution index duration of candidate distributors after executing the distribution tasks of the orders to be executed under various time combinations according to the distribution index duration corresponding to each time combination;

and determining the matching degree of the candidate distributor for the order package to be distributed according to the comprehensive distribution index duration, wherein if the comprehensive distribution index duration is shorter, the matching degree of the candidate distributor for the order package to be distributed is higher.

8. The method of claim 7, wherein the delivery efficiencies of the candidate deliverer at the various time combinations include: the candidate dispatchers execute the comprehensive risk scores after the dispatching tasks of the orders to be executed under the various time combinations;

determining the matching degree of the candidate delivery staff for the order package to be distributed according to the delivery efficiency of the candidate delivery staff under the various time combinations, specifically comprising:

sequencing the time combinations according to the sequence from large to small of the distribution index duration corresponding to each time combination to obtain time combination sequencing;

determining the comprehensive risk score according to the distribution index duration corresponding to the time combination positioned before the first set ranking in the time combination ranking;

and determining the matching degree of the candidate delivery staff for the order package to be distributed according to the comprehensive risk score, wherein if the comprehensive risk score is lower, the matching degree of the candidate delivery staff for the order package to be distributed is higher.

9. The method as claimed in claim 8, wherein determining the matching degree of the candidate distributor to the order package to be distributed according to the distribution efficiency of the candidate distributor in the various time combinations comprises:

and determining the matching degree of the candidate distributor for the order package to be distributed according to the comprehensive distribution index duration, the comprehensive risk score and the risk weight corresponding to the comprehensive risk score, wherein if the order placing quantity of the users is more in the distribution time period corresponding to the order package to be distributed, the risk weight is higher.

10. The method of claim 1, wherein selecting a target distributor from the candidate distributors based on a matching degree of each candidate distributor for the order package to be distributed comprises:

for each candidate dispenser, determining the basic delivery efficiency of the candidate dispenser when executing the delivery task corresponding to the to-be-distributed order package according to the fixed time length consumed by the candidate dispenser for taking and delivering the dispenser at each delivery point related to the to-be-distributed order package, and taking the basic delivery efficiency as the basic delivery efficiency corresponding to the candidate dispenser;

determining a basic sorting result of each candidate dispenser for the order package to be distributed according to the descending order of the basic dispensing efficiency of each candidate dispenser;

and selecting a target delivery person from the candidate delivery persons according to the basic sequencing result and the matching degree of each candidate delivery person for the order package to be distributed.

11. The method of claim 10, wherein selecting a target dispenser from the candidate dispensers according to the basic ranking result and the matching degree of each candidate dispenser to the order package to be distributed comprises:

determining candidate distributors located in a second set ranking from the basic ranking result to serve as reference distributors;

selecting candidate distributors from the candidate distributors, wherein the matching degree of the order packages to be distributed is higher than that of the benchmark distributors;

and determining a target distributor according to the selected candidate distributors.

12. The method of claim 11, wherein determining the target dispenser based on the selected candidate dispensers comprises:

determining candidate dispatchers meeting preset conditions from the selected candidate dispatchers;

determining a target distributor according to the candidate distributors meeting the preset conditions; wherein

For each selected candidate dispenser, if it is determined that the distance difference between the distance required by the candidate dispenser to execute the delivery task corresponding to the order packet to be distributed and the distance required by the reference dispenser to execute the delivery task corresponding to the order packet to be distributed is less than a set distance threshold, and/or

If the order number difference between the order number of the to-be-executed orders distributed to the candidate distributor after the to-be-distributed order package is distributed to the candidate distributor and the order number of the to-be-executed orders distributed to the benchmark distributor after the to-be-distributed order package is distributed to the benchmark distributor is smaller than the set order number threshold value, the candidate distributor is determined to meet the preset condition.

13. The method of claim 12, wherein the set distance threshold and/or the set order number threshold is/are larger if it is determined that the larger the number of orders placed by the user is within the delivery time period corresponding to the order package to be allocated.

14. An order distribution apparatus, comprising:

the system comprises an acquisition module, a distribution module and a distribution module, wherein the acquisition module is configured to acquire an order package to be distributed, and the order package to be distributed comprises at least one order;

a time combination determination module configured to determine, for each candidate dispenser, various time combinations at which the candidate dispenser completes delivery of the delivery at each delivery point related to the to-be-distributed order package when the candidate dispenser performs the delivery task corresponding to the to-be-distributed order package;

a delivery efficiency determining module configured to determine, for each time combination, a delivery efficiency of the candidate delivery member when executing the delivery task corresponding to the order package to be distributed according to the time combination, as the delivery efficiency of the candidate delivery member in the time combination;

a matching degree determination module configured to determine a matching degree of the candidate distributor with respect to the order package to be distributed according to distribution efficiency of the candidate distributor under the various time combinations;

and the distribution module is configured to select a target delivery person from the candidate delivery persons according to the matching degree of each candidate delivery person for the order package to be distributed, and distribute the order package to be distributed to the target delivery person for execution.

15. A computer-readable storage medium, characterized in that the storage medium stores a computer program which, when executed by a processor, implements the method of any of the preceding claims 1 to 13.

16. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any of claims 1 to 13 when executing the program.

Images