CN113222308B

CN113222308B - Order distribution method, order distribution device, electronic equipment and storage medium

Info

Publication number: CN113222308B
Application number: CN202010072549.7A
Authority: CN
Inventors: 谭佳楠; 邹鹏; 张国伟; 张涛; 孔兵
Original assignee: Beijing Sankuai Online Technology Co Ltd
Current assignee: Beijing Sankuai Online Technology Co Ltd
Priority date: 2020-01-21
Filing date: 2020-01-21
Publication date: 2023-05-30
Anticipated expiration: 2040-01-21
Also published as: CN113222308A

Abstract

The embodiment of the application discloses an order distribution method and an order distribution device. The method comprises the following steps: determining the target capacity of a target type to accept the non-order taking according to the capacity supply and demand tension degree of a target area and the estimated timeout duration of the non-order taking in the target area; and under the condition that the capacity supply and demand tension degree meets a first preset condition, determining whether to distribute the non-order taking to the target capacity according to the estimated income and cost of the target capacity for receiving the non-order taking. The invention can reduce the tail single rate in the target area.

Description

Order distribution method, order distribution device, electronic equipment and storage medium

Technical Field

Embodiments of the present disclosure relate to the field of computer technologies, and in particular, to an order allocation method, an order allocation device, an electronic device, and a computer readable storage medium.

Background

The capacity of the distribution field can be divided into two categories, crowdsourcing and specializing. In crowd-sourced mode, due to lack of strong control over capacity, there may be situations where a rider is unwilling to pick up a part of a difficult-to-distribute order, resulting in frequent occurrence of a tail order. The tail orders generated by the order picking of the rider are mainly divided into two types, one is an order cancelled by a user/merchant due to unmanned order taking, and the other is an order with serious overtime distribution due to overlong order taking time.

In order to reduce the generation of the tail order, the related art mainly uses a model to predict that an order with a higher probability of becoming the tail order exists in the orders, or determines an order without taking the tail order for a long time through a manual rule, and increases the delivery cost for the two orders possibly becoming the tail order to attract the crowd-sourced riders to take the tail order for digestion.

However, only the pricing layer attracts and guides the crowd-sourced riders to accept the tail bill, and the problem of tail bill protrusion in the crowd-sourced mode cannot be fundamentally solved.

Disclosure of Invention

The embodiment of the application provides an order distribution method for solving the problem of tail order prominence in the related art.

In order to solve the above problem, in a first aspect, an embodiment of the present application provides an order allocation method, including:

determining the target capacity of a target type to accept the non-order taking according to the capacity supply and demand tension degree of a target area and the estimated timeout duration of the non-order taking in the target area;

and under the condition that the capacity supply and demand tension degree meets a first preset condition, determining whether to distribute the non-order taking to the target capacity according to the estimated income and cost of the target capacity for receiving the non-order taking.

Optionally, under the condition that the target capacity is switched from receiving a new order to receiving a tail order, performing a first preset weighting operation on a first overtime probability of the tail order, a second probability of damage to a real object corresponding to the tail order and an order price of the tail order, and generating estimated benefits of the target capacity for receiving the non-received order;

optionally, in the case where the target capacity is switched from accepting a new order to accepting a tail order and the new order is accepted by a first capacity, calculating a second timeout probability that the new order is switched from accepting the target capacity to accepting the first capacity, calculating route information that the new order is switched from accepting the target capacity to accepting the first capacity to increasing, and calculating a loss of efficiency of dispatch in the target area that the new order is switched from accepting the target capacity to accepting the first capacity; and performing a second preset weighting operation on the journey information and the dispatch efficiency loss of the second overtime probability, and generating the estimated cost of the target capacity for receiving the non-order taking.

In a second aspect, an embodiment of the present application provides an order allocation apparatus, including:

The first determining module is used for determining the target capacity of the target type to accept the non-order taking according to the capacity supply and demand tension degree of the target area and the estimated timeout duration of the non-order taking in the target area;

and the second determining module is used for determining whether to distribute the non-order taking to the target capacity according to the estimated income and the estimated cost of the target capacity for receiving the non-order taking under the condition that the capacity supply and demand tension degree meets the first preset condition.

Optionally, the apparatus further comprises:

the first generation module is used for carrying out first preset weighting operation on the first overtime probability of the tail list, the second probability of damage of a real object corresponding to the tail list and the order price of the tail list under the condition that the target capacity is switched from receiving a new order to receiving the tail list, so as to generate estimated benefits of the target capacity for receiving the non-received order;

optionally, the apparatus further comprises:

a second generation module, configured to, when the target capacity is switched from accepting a new order to accepting a tail order and the new order is accepted by a first capacity, calculate a second timeout probability that the new order is switched from accepting the target capacity to accepting the first capacity, calculate route information that the new order is switched from accepting the target capacity to accepting the first capacity to increasing, and calculate a single-effect loss in the target area that is generated when the new order is switched from accepting the target capacity to accepting the first capacity; and performing a second preset weighting operation on the journey information and the dispatch efficiency loss of the second overtime probability, and generating the estimated cost of the target capacity for receiving the non-order taking.

In a third aspect, the embodiment of the application further discloses an electronic device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the order allocation method described in the embodiment of the application is implemented when the processor executes the computer program.

In a fourth aspect, embodiments of the present application provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the order allocation method disclosed in embodiments of the present application.

In the embodiment of the invention, the target capacity of the target type which is involved in receiving the non-order taking possibly becoming the tail order can be determined according to the overall capacity supply and demand tension degree of the target area and the estimated timeout period of the non-order taking in the target area, and whether the non-order taking is allocated to the target capacity or not is determined according to the estimated return and cost of the target capacity receiving the non-order taking possibly becoming the tail order under the condition that the capacity supply and demand tension degree meets the first preset condition, so that the tail order taking rate in the target area can be reduced by means of the capacity of the target type, the problem that the tail order taking rate in the target area is reduced due to the reduction of the tail order taking rate in the target area can be avoided, and a certain receiving rate can be maintained while the tail order taking rate is ensured to be reduced.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required for the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a flow chart of the steps of an order allocation method of one embodiment of the present application;

FIG. 2 is a flow chart of steps of an order allocation method according to another embodiment of the present application;

FIG. 3 is a schematic diagram of a coordinate system of an order allocation method according to one embodiment of the present application;

FIG. 4 is a second coordinate system diagram of an order allocation method according to one embodiment of the present application;

FIG. 5 is a block diagram of an order distribution device according to one embodiment of the present application;

FIG. 6 schematically illustrates a block diagram of a computing processing device for performing a method according to the present disclosure; and

fig. 7 schematically illustrates a storage unit for holding or carrying program code implementing a method according to the present disclosure.

Detailed Description

The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.

At present, the crowdsourcing capacity is easy to generate tail bills, so that the tail experience problem of crowdsourcing is still more outstanding, and a larger gap is left between the crowdsourcing capacity and the special delivery capacity under strong control.

The related art attracts crowd sourcing capacity to accept orders that may become tail orders, mainly through price policies, but it does not optimize tail experience at capacity management and scheduling level. In contrast, price strategies can only solve a part of the problems, and the tail order experience of the crowd-sourced whole is still quite different from special delivery. In order to optimize user experience of a tail order in a crowdsourcing mode, a distribution platform corresponding to the method of the embodiment of the present invention builds a set of strongly managed capacity, that is, capacity of a target type hereinafter, which may be named as a running rider (not belonging to special delivery) in one example, and for convenience of explanation, each embodiment hereinafter represents capacity of the target type by the running rider. The distribution platform can give the jogger a certain degree of inclination in scheduling, ensure a certain time and firewood advantage, and enable the platform to be assisted in digesting orders which are possibly to be tail orders.

Under the condition that the strong management and control capability of the running rider exists, the method can distribute the order which possibly becomes the tail order to the running rider through a technical means, so that the optimal solution of the whole experience is realized, and the tail order in the crowdsourcing mode is reduced.

Specifically, the embodiment of the application discloses an order allocation method, as shown in fig. 1, the method may include steps 100 and 105:

step 100, determining a target capacity of a target type to accept the non-order taking according to the capacity supply and demand tension degree of a target area and the estimated timeout duration of the non-order taking in the target area;

the difference in the capacity supply and demand tension of the target area and the difference in the estimated timeout period of the non-taking order in the target area may cause a difference in the target capacity (i.e., specific to which of the running riders) of the target type (e.g., the running rider) to accept the non-taking order, where the difference may be represented by a difference in the timing of distributing the non-taking order to the running rider and a difference in the timing of distributing the non-taking order to which of the running riders.

Furthermore, the target area is a geographical area. For example, a region in which a city is located may be divided into a plurality of geographical areas, where the target area is a geographical area in which a tail order needs to be reduced by a jogger.

A geographical area may have an indication of the tension in capacity supply and demand.

In determining the capacity supply and demand tension of a geographic area, the method can be implemented by pre-training a completed neural network model, wherein input features of the model comprise: a rate of non-orders received within a predetermined time period (e.g., 10 minutes) within the geographic area, a capacity load within the geographic area (e.g., a sum of the number of joggers and crowd-sourced riders within the geographic area); the output of the model is the value of the capacity supply and demand tension or the level of the capacity supply and demand tension (each level may correspond to a range of values of the capacity supply and demand tension, for example, 5 levels including 1 to 5 levels).

Wherein, the lower the value, the lower the level, which means that the less the capacity supply and demand is tight, i.e. the capacity in the geographical area is enough; the higher the value, the higher the level, which means that the capacity supply and demand is more intense, i.e. the capacity in the geographical area is insufficient.

Then in this step the model can be used to obtain the capacity supply and demand tension of the target area, for example the level of capacity supply and demand tension.

Step 105, determining whether to distribute the non-order taking to the target capacity according to the estimated profit and cost of the target capacity for receiving the non-order taking when the capacity supply and demand tension degree meets the first preset condition.

That is, in the case where there is no shortage of capacity supply and demand in the target area, it is necessary to calculate, after determining the target capacity to be allocated to the missed order M and before allocating the missed order to the target capacity, for example, the running rider S1, that is, each time after obtaining the scheduling result for the missed order which may become the tail order, the profit reward obtained by the running rider S1 to allocate the tail order and the cost of allocating the tail order (both the profit reward and the cost of allocating are non-dimensional units). Thereby determining whether to distribute the order M to the jogger S1.

Alternatively, on the basis of the above embodiment, in one embodiment, when performing the above step 100, it may be implemented by the steps 401 and 402:

step 401, determining an order allocation strategy corresponding to the capacity of the target type according to the capacity supply and demand tension degree of the target area;

in this step, the difference of the capacity supply and demand tension degree of the target area can be combined to reasonably determine an order allocation policy corresponding to the capacity of the target type (i.e. the running rider), that is, the difference of the capacity supply and demand tension degree, so that the order allocation policy for allocating the non-taken order to the running rider is different.

The specific distinction of the order allocation strategy can be represented by the distinction of the early and late moments of receiving and stopping receiving the non-taken orders which may become the tail orders by the jogger, and the distinction of the degree of forward travel of the jogger and the non-taken orders to be received.

For example, the more intense the capacity supply and demand, the later the time to control the intervention of the running rider to take an unanswered order that may become a tail order.

Step 402, if the estimated timeout period of the non-order taking in the target area matches the order allocation policy, determining a target capacity of the target type to accept the non-order taking according to the order allocation policy.

Wherein, for an order distribution strategy configured for the capacity of a target type (such as a jogger), the order distribution strategy can carry information about overtime time length of the order and screening conditions for the capacity of the target type, and in the order distribution strategy, the overtime time length can be differentiated to make the screening conditions for the jogger different.

For example, in this step, when the estimated timeout period for the non-taking order matches the timeout period in the order allocation policy, a specific rider of the jogger to receive the non-taking order may be determined based on a screening condition for, for example, the jogger corresponding to the estimated timeout period in the order allocation policy.

In the embodiment of the invention, the order allocation strategy corresponding to the capacity of the target type can be reasonably determined according to the capacity supply and demand tension degree of the target area, and then the order allocation strategy matched with the estimated overtime time length of the non-order taking in the target area is determined, so that the target capacity of the target type for accepting the non-order taking is determined according to the order allocation strategy, and the target capacity of the tail order can be flexibly and accurately positioned by setting the order allocation strategy, so that the certainty of digesting the tail order can be ensured by utilizing the capacity of the target type under strong control, and the problem of tail protrusion is solved.

Optionally, on the basis of the foregoing embodiment, another embodiment of an order allocation method is disclosed in the present application, as shown in fig. 2, where the method may include step 101, step 102, step 103, step 104, and step 105 described above:

in combination with the above embodiment, in the present embodiment, when the above step 401 is performed, it can be realized by the following step 101; in performing the above step 402, this may be achieved by the following

steps

102 and 103; in addition, step 104 in the present embodiment is an optional step.

The order distribution method according to the embodiment of the present invention is described in detail below with reference to fig. 2:

step 101, determining a target overtime interval corresponding to the capacity of a target type and a target corresponding relation between overtime time corresponding to the capacity of the target type and a dispatch threshold according to the capacity supply and demand tension degree of the target area, wherein the target overtime interval comprises the overtime time;

since the core idea of the embodiment of the present invention is to digest orders that may become tail orders in the target area by the jogger, and these orders, i.e., orders to be allocated (i.e., non-order taking), are mainly due to long unmanned order taking or long order taking time, so that it is necessary to determine a target timeout interval for taking the possible tail orders by the jogger (i.e., here, non-order taking is an order that may become tail orders), i.e., when the estimated timeout time of the non-order taking is within what numerical range, the jogger takes the non-order;

in addition, since the number of joggers is large, it is also necessary to determine which jogger receives the missed order, and in particular which jogger receives the missed order, which is related to the dispatch condition of the jogger, and therefore, it is also necessary to determine the target correspondence between the timeout period and the dispatch threshold. Wherein the target correspondence is associated with a capacity of a target type. In addition, the timeout duration in the target correspondence is taken from the target timeout interval, and the timeout duration may be one or more of the target timeout intervals, preferably each timeout duration. In addition, the different values of the dispatch threshold value correspond to different dispatch conditions.

In one example, the order threshold may be an order threshold, with a higher order threshold representing a lower order requirement for the ordered rider, and a lower order threshold representing a higher order requirement for the ordered rider.

In order to reasonably allocate orders which may fall into tail orders to the running riders under the condition that the tension levels of the drifts are different, a target timeout interval corresponding to the orders to be allocated to the running riders and a target corresponding relation between timeout duration and a dispatch threshold value in the target timeout interval are required to be determined according to the tension levels of the drifts in the target area. Because, there is a difference in the timing at which the intervention of the jogger takes over may become the tail bill in both cases of tension and non-tension in the drivability.

Optionally, in an embodiment, when step 101 is performed, a first preset timeout period may be determined as a target timeout period and a first correspondence between a first timeout period and a first dispatch threshold may be determined as the target correspondence when the capacity supply and demand tension degree meets a second preset condition, where each timeout period in the first preset timeout period is the first timeout period;

Optionally, in one embodiment, when executing step 101, if the capacity supply and demand tension degree meets a first preset condition, determining a duration threshold according to the capacity supply and demand tension degree; adding the time threshold to each time-out time length in the first preset time-out interval to generate the target time-out interval; adding the time threshold to each first timeout time in the first correspondence, and generating a second correspondence between a second timeout time and the first dispatch threshold; and determining the second corresponding relation as the target corresponding relation.

Specifically, the fact that the capacity supply-demand tension degree satisfies the second preset condition may be understood as that the capacity supply-demand is not tensioned (for example, the level of the capacity supply-demand tension degree is less than or equal to a preset level (for example, level 3)); a capacity supply and demand tension degree satisfying the first preset condition may be understood as a capacity supply and demand tension (for example, a capacity supply and demand tension degree is rated to be greater than a preset rating (for example, 3 rating)).

In one example, as shown in fig. 3, the method of the embodiment of the present invention may generate a curve 1a in advance, where in the coordinate system of fig. 3, the horizontal axis x represents the estimated timeout period of the order to be allocated, and the units are minutes, that is, each number of the horizontal axis represents a corresponding minute; the vertical axis Y represents the forward threshold.

As can be seen from FIG. 3, the estimated timeout period x E [8,18] is shown in curve 1a, and curve 1a reflects the functional correspondence between the forward threshold Y and the estimated timeout period x. The curve 1a expresses the correspondence between the forward threshold and the estimated timeout period when the capacity supply and demand is not tight, i.e. the capacity supply and demand is tight, which satisfies the second preset condition.

Therefore, according to the pre-generated curve 1a, a first preset timeout period (x e [8,18] in minutes) can be determined as a target timeout period, and a first corresponding relation between each first timeout period (x e [8,18 ]) in the first preset timeout period (x e [8,18 ]) and a first dispatch threshold value (Y) can be determined as the target corresponding relation;

that is, the range of the horizontal axis in the curve 1a is the target time-out interval corresponding to the order to be allocated to the running rider when the capacity supply and demand are not tight, and the functional relationship represented by the curve 1a is the target corresponding relationship between the target time-out interval corresponding to the order to be allocated to the running rider and the dispatch threshold when the capacity supply and demand are not tight.

As can be seen from curve 1a in fig. 3, the target correspondence expresses the moment when the running rider intervenes to accept an order to be allocated that may become a tail order (i.e., the order is estimated to timeout 8 minutes), the moment when the forward threshold is triggered to be expanded to dispatch an order (i.e., the order is estimated to timeout 12 minutes), and the moment when the forward threshold is stopped to be expanded to dispatch an order (i.e., the order is estimated to timeout 18 minutes).

For ease of understanding, a specific example is used to describe the method of the embodiment of the present invention in detail, for example, if the capacity supply and demand tension level of a certain geographic area is 1 level, a target timeout period expressed by the curve 1a and a functional relationship between the estimated timeout period and the forward threshold in the target timeout period may be obtained.

For example, a certain order M in the geographic area is not ordered by people at present, the estimated timeout period of the order M can be determined to be 8 minutes through prediction, and then the forward threshold y1 corresponding to the 8 minutes can be queried according to the functional relation of the curve 1 a; then, a running rider with the order sending condition meeting the target order sending condition corresponding to the forward threshold y1 can be found from the running riders in the geographic area, for example, the running rider S1 is found, and then the order M received by no person is distributed to the running rider S1, so that the effect that the running rider digests the order M possibly becoming a tail order is achieved.

The previous example is described in terms of an embodiment in which there is no tension in the capacity supply and demand, and when the capacity supply and demand in the target area is tension, for example, the capacity supply and demand tension level is 5, a time period threshold value is determined according to the capacity supply and demand tension level, and the time period threshold value is used to make an overall shift on the horizontal axis x of the curve 1a in fig. 3. In the case that the capacity supply and demand tension degree satisfies the first preset condition, the higher the capacity supply and demand tension degree, that is, the tension degree, the greater the duration threshold (for example, the preset correspondence between the capacity supply and demand tension degree and the duration threshold and/or the preset correspondence between the capacity supply and demand tension degree and the duration), that is, the greater the offset of the overall offset of the curve 1a on the horizontal axis x. Of course, the offset also has a maximum value, i.e., the duration threshold is at most 5 (minutes). In this example, since the capacity supply and demand tension level is the maximum level 5, the time period threshold here is the maximum time period threshold, 5 minutes.

Therefore, in this embodiment, the first preset timeout period (xε [8,18 ]) can be increased by 5 minutes to obtain the target timeout period xε [13,23], and the curve 1b in the case of the capacity supply and demand is obtained when the curve 1a in FIG. 3 is shifted by 5 units to the right on the horizontal axis.

The process of obtaining the curve 1b based on the curve 1a and the time length threshold (5 minutes) is essentially to increase the time length threshold for each of the first timeout periods in the first correspondence, and generate a second correspondence between the second timeout period and the first dispatch threshold (i.e. the forward threshold of the ordinate Y of the curve 1b is not changed from the curve 1a in fig. 3, but the value of x corresponding to each forward threshold is increased by 5 minutes); and determining the second corresponding relation as the target corresponding relation.

Therefore, the value ranges [13,23] of the horizontal axis in the curve 1b are target time-out intervals corresponding to orders to be distributed to the running rider in the case of the shortage of the capacity supply and demand, and the function relationship represented by the curve 1b is a target correspondence relationship between the target time-out intervals corresponding to orders to be distributed to the running rider and the order-distribution threshold (forward threshold in this case) in the case of the shortage of the capacity supply and demand.

As can be seen from curve 1b in fig. 3, the target correspondence expresses the moment when the running rider intervenes to accept an order to be allocated that may become a tail order (i.e., order forecast timeout 13 minutes), the moment when the expansion forward threshold is triggered to dispatch an order (i.e., order forecast timeout 17 minutes), and the moment when the expansion forward threshold is stopped to dispatch an order (i.e., order forecast timeout 23 minutes).

Curve 1b expresses that the capacity supply and demand is tension compared to curve 1a, the moment of the running rider taking the order to be allocated, which may become the tail order, is delayed by 5 minutes, the moment of triggering the expansion of the forward threshold to dispatch the order is delayed by 5 minutes, and the moment of stopping the expansion of the forward threshold to dispatch the order is delayed by 5 minutes. That is, the curve 1b for dispatching orders when the capacity supply and demand are in tension is shifted to the right as a whole compared with the estimated timeout time in the curve 1a, and the time for the race rider to intervene to accept orders that may become tail orders is delayed.

Because the tension degree of the drivability supply and demand in the target area can be continuously changed, the method of the embodiment of the invention can flexibly adjust the intervention time of dispatching the running rider to accept the non-order taking possibly becoming the tail order, the time of triggering the expansion forward threshold to dispatch the order and the time of stopping expanding the forward threshold to dispatch the order according to the change of the tension degree of the drivability supply and demand, and determines the latest forward threshold corresponding to the moment according to the determined latest various times, thereby searching the running rider meeting the dispatching condition by means of the latest forward threshold.

Thus, in the embodiment of the present invention, when the capacity supply and demand tension degree meets the first preset condition, it is indicated that the capacity supply and demand degree is relatively tension, for example, it is indicated that the capacity (sum of the number of running+crowded riders) in the target area is relatively small, and the non-order receiving rate is relatively high. Because the capacity supply and demand in the target area is tense, the order receiving rate in the target area needs to be ensured, compared with the condition that the capacity supply and demand tense degree meets the second preset condition (the capacity supply and demand degree is less tense), the overtime time in the target corresponding relation can be prolonged, so that the time for receiving the overtime non-order receiving by the estimated overtime capacity intervention of the target type is delayed, and the order receiving rate of the target area which is tense can be reduced because the capacity of the target type is controlled to receive the order which possibly becomes a tail order too early. Therefore, the method of the embodiment of the invention can avoid the problem that the order receiving rate in the target area is reduced due to the fact that the order which possibly becomes the tail order is accepted due to the capacity of the dispatching target type under the condition that the capacity supply and demand of the target area is tense, thereby influencing the user experience.

It should be noted that, the target correspondence in the embodiment of the present invention is not limited to the correspondence shown by the curve 1a or the curve 1b in fig. 3, which includes two straight lines and one linearly increasing line, but may be a curve in which the dispatch threshold linearly increases with the estimated timeout duration in the target timeout interval, or a correspondence expressed by other non-enumerated curves.

Optionally, the target correspondence between the timeout period corresponding to the capacity of the target type and the dispatch threshold may include:

when the timeout duration in the target timeout interval is within a first time interval [ t1, t2], the timeout duration corresponds to a first threshold;

in one example, the target correspondence is shown as curve 1a in fig. 3, or the target correspondence is shown as curve 1 b.

In curve 1a, t1=8 minutes here, t2=12 minutes here, and the first threshold value is y1.

In curve 1b, t1=13 minutes here, t2=17 minutes here, and the first threshold value is y1.

When the timeout duration in the target timeout interval is within a second duration interval [ t2, t3], the dispatch threshold value and the timeout duration are in a linear increasing relation, and the dispatch threshold value is linearly increased from the first threshold value to a second threshold value;

in one example, in curve 1a, where t3=15 minutes, the second threshold is y2.

In curve 1b, where t3=20 minutes, the second threshold is y2.

Taking the order sending threshold as an example, in the target corresponding relationship represented by the curve 1a, when the estimated timeout period of the order is in the range of 12-15 minutes, the order sending threshold and the estimated timeout period are in a linear function relationship represented by the curve 1a, and as the estimated timeout period increases, the order sending threshold also increases, so that the order sending threshold is in a linear increasing function relationship.

When the timeout duration in the target timeout interval is within a third duration interval [ t3, t4], the timeout duration corresponds to the second threshold;

in one example, in curve 1a, where t4=18 minutes.

In curve 1b, t4=23 minutes here.

Wherein the first threshold is smaller than the second threshold, and t1 is smaller than t2 and smaller than t3 and smaller than t4.

In this way, in the embodiment of the invention, in the defined corresponding relation of the order targets for which the capacity dispatch of the target type may become the tail order, when the timeout period is shorter, the same dispatch threshold is adopted to find the target capacity meeting the target dispatch condition corresponding to the dispatch threshold; in the process that the timeout period starts to be increased from the shorter timeout period to the longer timeout period, the dispatch threshold is adjusted continuously along with the continuous increase of the timeout period, and the dispatch threshold is larger as the timeout period is longer. That is, because the timeout duration of the missed order of the estimated timeout is continuously increased, if the stricter order dispatching condition corresponding to the smaller order dispatching threshold is used for searching the capacity of the target type meeting the requirement, the proper target capacity is difficult to find, and the probability that the missed order becomes the tail order is increased, therefore, the order dispatching threshold can be moderately increased along with the increase of the estimated timeout duration, thereby reducing the severity of the order dispatching condition, and the target capacity capable of receiving the order can be found in the range of insufficient forward road, for example, and the tail order rate is reduced; finally, if the estimated timeout period for the missed order has been very long, if the target capacity meeting the dispatch condition is not found under the least severe dispatch condition corresponding to the second threshold corresponding to the estimated timeout period, the attempt to dispatch the capacity of the target type to accept the missed order is stopped, because it is indicated that the order may be an order beyond the dispatch range, without wasting capacity to accept the order. The method of the embodiment of the invention can adjust the used order dispatching threshold along with the change of the estimated overtime time of the non-order taking, thereby reducing the target order dispatching condition along with the increase of the estimated overtime time, finding the target capacity meeting the target order dispatching condition to the greatest extent and optimizing the tail order.

102, if the estimated timeout period of the non-order taking in the target area is matched with the target timeout period, acquiring a target order assignment threshold matched with the estimated timeout period according to the target corresponding relation;

wherein the order-missing may be each order-missing within the target area, or a partially designated order-missing.

The method of the embodiment of the invention can predict the timeout duration of any non-order taking, namely the estimated timeout duration.

The estimated timeout period of an unacquired order may change continuously with the lapse of time, i.e. it is a change value, so this step may query the latest target dispatch threshold value matching the estimated timeout period from the target correspondence according to the latest value of the estimated timeout period.

Alternatively, in determining the estimated timeout period for non-taking orders in the target area in step 102, the following steps S201 to S203 may be implemented:

s201, for the non-order taking in the target area, estimating the time-consuming time of delivering the non-order taking according to the route planning information of the non-order taking and the historical order data between the buyers and sellers corresponding to the non-order taking;

Specifically, for an unanswered order, the order may have a buyer address and a seller address, and thus, a path plan (ETR) may be obtained from the seller address to the buyer address; and acquiring historical order data (e.g., the time taken to ship the historical order, i.e., the length of time from the time of placement to the time of ship) between the buyer and the seller; and estimating the time length between the order placing time and the delivery time of the non-taken order according to the path planning and the historical order data, namely the time length of the delivery time.

For an unanswered order, the estimated time period for delivery is not dynamically changed, but is a fixed value.

S202, calculating the sum of the system time and the time-consuming time to obtain a first estimated delivery time;

the system time is the time used by the system in the embodiment of the present invention, for example, beijing time, and the sum of the system time and the time duration of the delivery time can be calculated to obtain the first expected delivery time.

Wherein, since the system time is continuously changing, the first estimated delivery time is also continuously changing.

S203, calculating the difference between the first expected delivery time and the second expected delivery time of the non-order taking output by the client side, and obtaining the estimated timeout duration of the non-order taking.

After the client side submits an order, the system may automatically generate a second estimated time of delivery (ETA) of the order, where the second estimated time of delivery (ETA) is the estimated time of delivery of the order for viewing by the user output at the client side, and the method for calculating the second estimated time of delivery may use various methods in the conventional technology, which will not be described herein.

The first estimated time of delivery corresponds to the actual time of delivery of the missed order estimated by the method of the embodiment of the present invention, and ETA is the estimated time of delivery that can be seen by the user output from the client side, so that the embodiment of the present invention can obtain the estimated timeout period of the missed order by subtracting the second estimated time of delivery from the first estimated time of delivery. And then, the estimated timeout period is used to query the target corresponding relationship, for example, a curve 1a or a curve 1b shown in fig. 3 or other curves with offsets of larger than zero and smaller than 5 on the horizontal axis, which are not shown, so as to obtain a target forward threshold value for searching for the running rider, and the target forward threshold value is used to schedule the target capacity, namely, a certain running rider.

In the embodiment of the invention, the time-consuming time of delivering the missed order can be estimated by utilizing the route planning of the missed order and the historical order data between the buyer and the seller, so that the accuracy of the estimated time-consuming time of delivering is higher, the real time delivering time of the missed order, namely the first estimated delivering time, is estimated by utilizing the time-consuming time of delivering, and the first estimated delivering time and the second estimated delivering time of the missed order output by the client side are calculated, thereby obtaining the timeout time of the missed order in an estimated mode; the estimated timeout period is accurate, so that whether the missed order is an order which is likely to fall into a tail order or not can be determined based on the estimated timeout period and the target corresponding relation, namely, whether the estimated timeout period is within a target timeout interval (if yes, the estimated timeout period is likely to fall into the tail order) can be accurately positioned in time to the missed order which is likely to be the tail order, the determined target dispatch threshold is utilized to schedule the target capacity of the target type to accept the missed order, and the tail order rate of the target area is reduced.

It should be noted that the missed orders described in the various embodiments described throughout this disclosure represent orders that the seller has accepted, but that the order has not yet been accepted by the capacity (i.e., rider).

Alternatively, based on the first estimated time of delivery of the non-order taking, the first estimated time of delivery is the actual time of delivery estimated in the embodiment of the present invention, and the first estimated time of delivery is continuously changed, so in the embodiment of the present invention, the curves 1a and 1b shown in fig. 3 may be obtained from the

curves

2a and 2b shown in fig. 4.

In other words, the target correspondence described in the embodiment of the present invention may be a correspondence between the first predicted delivery time when no order is taken and the dispatch threshold, and when the target correspondence is used, the abscissa value in the curve 2a or the curve 2b is located by determining that the specific time of the predicted first predicted delivery time is ETA plus several minutes.

The curve 2a in fig. 4 corresponds to the curve 1a in fig. 3, the curve 2b in fig. 4 corresponds to the curve 1b in fig. 3, and the principle is similar, and the description of fig. 3 is omitted herein.

Whereas 8 in eta+8, for example, on the horizontal axis in fig. 4 is 8 minutes, indicating that the estimated real delivery time for the non-order taking is 8 minutes later than the estimated delivery time ETA displayed on the client side. I.e. the order forecast times out for 8 minutes.

Step 103, determining that the dispatch conditions in the target area meet the target capacity of the target type of the target dispatch conditions corresponding to the target dispatch threshold;

taking a order-dispatching threshold as an example to illustrate, for the carrying capacity of each target type in the target area, for example, a running rider can calculate one order-dispatching condition corresponding to the carrying capacity, for example, an order-dispatching value, then it can be judged whether the running rider with the difference value smaller than a preset threshold value exists between the order-dispatching value and the target order-dispatching threshold value, if the running rider with the difference value smaller than the preset threshold value exists, it is illustrated that the target carrying capacity of the order-dispatching condition is met in the target area, and if the running rider with the difference value smaller than the preset threshold value does not exist, it is illustrated that the target carrying capacity of the order-dispatching condition is not met in the target area.

It should be noted that, the number of the target capacity is one, and when there are multiple running riders with multiple dispatch conditions meeting the target dispatch conditions in the target area, the running rider with the forward road value closest to the target forward road threshold value among the multiple running riders is determined as the target capacity.

Of course, when the target forward threshold is determined according to the estimated timeout period of a certain missed order M, and the target capacity of the target type is used by the target forward threshold, the target capacity meeting the target dispatch condition may not be found. However, the estimated timeout period for the non-order taking is continuously changed, so that the corresponding relationship of the target can be queried in real time according to the latest estimated timeout period, so as to find whether the target capacity exists in the target area according to the latest target order assignment threshold, such as the target forward threshold.

The following description will take, as an example, the correspondence relationship with respect to the curve 1a in fig. 3.

The longer the estimated timeout period of the missed order M is, for example, when the estimated timeout period is 8 minutes, the running rider meeting the target order sending condition is not found based on the forward threshold y1, and then in the process that the estimated timeout period is continuously increased (for example, the estimated timeout period is in the interval of 8 minutes to 12 minutes), the method of the embodiment of the invention can find whether the running rider meeting the target order sending condition exists in the geographic area based on the forward threshold y1 in real time; if the target forward threshold is not found, the forward threshold corresponding to the estimated timeout time is queried according to the forward threshold (in y 1-y 2) corresponding to the estimated timeout time in the curve 1a in the process that the estimated timeout time exceeds 12 minutes and continuously increases to 15 minutes, and the forward requirement for searching the target capacity is lower and lower, and the target dispatch condition is lower and lower; if the running rider meeting the latest target forward threshold is not found, the running rider is found by the target forward threshold y2 in the process of continuously increasing the estimated timeout (for example, the estimated timeout duration is in the interval of 15-18 minutes); and stopping searching the running rider when the estimated timeout period reaches 18 minutes.

That is, when searching and determining the target capacity, step 103 of the embodiment of the present invention may search for the latest target dispatch threshold according to the estimated timeout period of the real-time change, so as to search whether the target capacity of the target type of the target dispatch condition is satisfied by the dispatch condition in the target area according to the latest target dispatch condition.

When the estimated time of the missed order M is out of 8 minutes, attempting to dispatch the order to the running rider in the range of higher forward-path performance requirement of the forward-path threshold y 1; if the estimated timeout period reaches 12 minutes, triggering an action of expanding the forward threshold to dispatch a bill (namely, increasing the forward threshold with the increase of the value of the estimated timeout period, namely, reducing the smoothness requirement, and searching for the happy running rider meeting the smoothness requirement in a larger geographic range), wherein the forward threshold at this stage is linearly increased along with the system time or the estimated timeout period; when the estimated timeout period reaches 15 minutes, then the forward threshold for the order is no longer increased and remains unchanged (because the timeout is too long, it is unnecessary to schedule the rider to deliver the order from the more unsophisticated running rider); when the estimated timeout period exceeds 18 minutes, if a jogger meeting the forward-drive requirement has not been found, the jogger is discarded from being dispatched for the missed order (because the timeout period is too long, it is unnecessary to dispatch the jogger again to dispatch the order).

Wherein, the higher the forward threshold value is, the lower the forward requirement of the sped-up rider is, for example, the less forward can be used for receiving orders.

In addition, when searching and determining the target capacity, step 103 of the embodiment of the present invention may also adjust the corresponding relationship of the target used in real time according to the change of the capacity supply and demand tension degree in the target area, and further search the latest target dispatch threshold according to the latest estimated timeout period, so as to search whether the target capacity of the target type of the target dispatch condition is satisfied by the dispatch condition in the target area according to the latest target dispatch condition.

Alternatively, in executing step 103, it may be realized by S301 to S302:

s301, acquiring dispatch conditions of each capacity of the target type according to positioning information of each capacity of the target type in the target area, the distributed and unfinished order data of the capacity and the order data of the non-order taking;

wherein location information for each of the joggers within the target area may be obtained, as well as order data for each of the joggers that has been assigned but has not yet completed (i.e., not yet been delivered to the buyer), as well as order data such as missed order M (e.g., including buyer location, seller location, etc.);

Then, a dispatch piece, such as a forward road value, of each jogger is calculated from these data.

In one example, the distance between the jogger and the buyers of the missed order M may be determined from the jogger's positioning information; calculating the forward parameters of the running rider on the non-taken order M according to the data of the orders which have been accepted by the running rider but have not been completed by the running rider; then, the forward road parameter, the distance between the running rider and the buyer, and the distance between the running rider and the seller are weighted to obtain a forward road value. In this way, the dispatch condition for each jogger in the target area can be obtained.

Of course, the method of calculating the race rider dispatch conditions is not limited to the above examples, but may be implemented by other known or future developed methods.

S302, determining that the dispatch piece meets the capacity of the target dispatch condition corresponding to the target dispatch threshold as the target capacity.

Specifically, if a candidate capacity of which the difference between the value (e.g., the forward road value) of the dispatch condition and the target dispatch threshold is smaller than a preset threshold exists in the jogger in the target area, determining the candidate capacity as the target capacity if the candidate capacity is one; if the number of the candidate capacity is a plurality of, determining the capacity corresponding to the smallest difference value in the plurality of candidate capacities as the target capacity;

If the value (for example, the forward value) of the order sending condition does not exist in the running rider in the target area and the candidate capacity of the difference value between the target order sending threshold value and the target order sending threshold value is smaller than the preset threshold value, determining the target order sending condition corresponding to the latest target forward threshold value according to the estimated timeout time of the latest non-order taking M after the change, and searching whether the target capacity of the latest target order sending condition is met or not again.

In the embodiment of the invention, the dispatch conditions of each capacity of the target type can be acquired according to the positioning information of each capacity of the target type in the target area, the data of the order which is distributed and not completed for the capacity and the data of the order which is not taken, so that the dispatch conditions of each capacity are combined with the data of the order which is not taken, the current positioning of the capacity and the data of the condition that the capacity still needs to be distributed and not taken, and then the determined dispatch conditions can more accurately express the actual order taking capacity of the corresponding capacity on the order which is not taken, thereby being capable of finding the target capacity of the target type with the strongest actual order taking capacity on the order which is not taken in the target area to accept the order, reducing the tail order rate and reducing the influence on the distribution efficiency of new orders in the target area.

The new order may be an order in which the time difference between the time of placement and the system time is less than a threshold, such as 5 minutes.

Optionally, step 104, in the case that the capacity supply and demand tension meets a second preset condition, allocating the non-order taking to the target capacity;

that is, in the case where the capacity supply and demand of the target area is not tight, the non-taken order M, for example, may be directly assigned to the target capacity, for example, the jogger S1 for distribution.

Because the capacity supply and demand of the target area is not tension, that is, the capacity is sufficient, the order can be directly dispatched without considering the income and the cost corresponding to the allocation order M to the running rider S1, the tail order in the target area can be quickly reduced, the running rider which accords with the target order dispatching condition is prone to be directly dispatched to receive the order M possibly becoming the tail order, and the tail order rate is reduced.

The description of step 105 is specifically referred to in the embodiment of fig. 1, and is not repeated here.

In the embodiment of the invention, a target overtime interval corresponding to an unoccupied order which possibly becomes a tail order is determined according to the overall capacity supply and demand tension degree of a target area, and a target corresponding relation between the overtime time in the target overtime interval and a dispatch threshold is determined, so that the target corresponding relation can be queried according to the estimated overtime time of the unoccupied order, and the time for the unoccupied order to be accepted by the capacity of the target type and the target dispatch threshold are determined; under the condition that the non-order taking is not seriously overtime or is not cancelled, the target capacity of the target type of the corresponding target order taking condition is timely determined based on the target order taking threshold, tail experience of a target area can be optimized at the capacity management and control and scheduling layer, certainty of digestion of the tail order is guaranteed by utilizing the capacity of the strongly managed target type, and the problem of tail order protrusion is solved. In addition, under the condition that the tension degree of the supply and demand of the transport capacity meets the second preset condition, the non-order taking is directly distributed to the target transport capacity, so that the tail order rate of the target area can be timely reduced under the condition that the transport capacity is not tension; and under the condition that the tension degree of the supply and demand of the transport capacity meets the first preset condition, determining whether to distribute the non-order taking to the target transport capacity according to the estimated income and the estimated cost of the non-order taking possibly becoming the tail order, thereby avoiding the problem of the reduction of the order taking rate in the target area caused by the reduction of the tail order rate in the target area.

Alternatively, in performing step 105, this may be achieved by: if the estimated return of the target capacity to accept the non-order taking is greater than or equal to the cost, distributing the non-order taking to the target capacity; and if the estimated return of the target capacity to accept the non-order taking is smaller than the cost, refusing to distribute the non-order taking to the target capacity.

In this step, the benefits obtained by estimating the target capacity if receiving the non-taken order M and the cost are mainly estimated.

When estimating the return and cost, the return and cost of the order M is estimated for the missed order M which may become the tail order based on the related data of the generated tail order.

Specifically, the following two types of orders are first defined:

new order: the time difference between the client side order time and the system time is less than a threshold (e.g., 5 minutes).

Tail sheet: including orders that are cancelled by the user/merchant due to unmanned order taking, orders that are too long to be taken, and orders that are severely timed out to be delivered (e.g., actual time out times longer than 15 minutes).

For example, in the case of tension in the capacity supply and demand, the determined target capacity is the jogger S1, and the jogger S1 is the jogger whose order-sending condition is matched with the target order-sending condition corresponding to the target order-sending threshold value y1 (refer to the curve 1a of fig. 3) found when the target order-sending threshold value y1 corresponding to the estimated timeout period 13 minutes of a certain non-taken order M

Specifically, in the order pool 1 formed by new orders in the target area, the new orders in the order pool are distributed to crowd-sourced riders and jogger riders in the target area according to a greedy algorithm, so that it is determined which new orders, such as an order B and an order C (both new orders), are distributed to the jogger S1.

In addition, the tail order in the target area is added into the order pool (definition refers to the above) to form a new order pool 2 (wherein, a large proportion, for example, more than 80 percent of the order pool 2 is new orders); when a greedy algorithm is utilized to dispatch a rider in a target area, a new order in the order pool 2 is ignored, the tail order in the order pool 2 is preferentially distributed to a running rider according to the greedy algorithm, and after the tail order in the order pool 2 is completely distributed, the new order in the order pool 2 is distributed to each rider (the crowded rider can be selected or the running rider) according to the greedy algorithm. For example, via allocation, such that the jogger S1 allocates the tail order A, and the rider S2 (not limiting whether the jogger or the crowd-sourced rider) allocates the order B and the order C (both new orders).

That is, it is estimated that the jogger S1 would have to deliver the new order B and the new order C, but it did not deliver the two new orders, but delivered the tail order A.

It is necessary to estimate the cost of delivering the missed order M, caused by the fact that the jogger S1 did not deliver the new order (here, new order B and new order C are taken as an example), based on the delivery tail order (here, tail order a); and estimating the return review obtained by the jogger S1 because of the delivery of the missed order M based on the delivery of the tail order (here, tail order A).

Then when review is greater than or equal to cost, the method of embodiments of the present invention will distribute the missed order M to the running rider S1 for distribution;

conversely, if review < cost, the scheduling of the non-taken order M to the running rider S1 is abandoned, that is, when the estimated timeout period of the non-taken order M is 13 minutes listed above, the scheduling result is the running rider S1, but the scheduling is abandoned, and the non-taken order is not allocated to the running rider S1 for distribution; when the next scheduling is performed, for example, the estimated timeout period of the non-order taking M changes, or the capacity supply and demand tension degree of the target area changes, the cost and the benefit are recalculated when the target order dispatching threshold value determined according to the target corresponding relation changes.

In addition, when review < cost, then the running rider S1 may continue to be assigned a new order.

Optionally, in an embodiment, when estimating the benefit, a first preset weighting operation may be performed on the first timeout probability of the tail form, the second probability of the real object corresponding to the tail form being damaged, and the order price of the tail form, where the target capacity is switched from receiving a new order to receiving a tail form, so as to generate a benefit estimated by receiving the non-received order by the target capacity;

continuing with the above example:

for example, tail order A was assigned to jogger S1, resulting in new order B and new order C being most forward to rider S1 being assigned to next forward rider S2:

calculating a return review obtained by the running rider S1 distributing the tail order A through the formula 1, and taking the return as a predicted return obtained by the running rider S1 distributing the non-taken order M:

reward=α_risk1 (a, t) +β_price (a) _risk2 (a, t), equation 1;

wherein risk1 (a, t) represents the risk of overtime of tail sheet a at scheduling instant t;

risk2 (a, t) represents the risk of the tail sheet a creating a meal loss at scheduling instant t;

price (a) represents the real price paid by the user of order a.

Wherein, risk1 (a, t) and risk2 (a, t) are both predicted by using models.

Optionally, in one embodiment, in the case where the target capacity is switched from accepting a new order to accepting an end bill and the new order is accepted by a first capacity, calculating a second timeout probability that the new order is switched from accepting the target capacity to increasing from accepting the first capacity, calculating route information that the new order is switched from accepting the target capacity to increasing from accepting the first capacity, and calculating a loss of efficiency of dispatch within the target area that the new order is switched from accepting the target capacity to accepting from accepting the first capacity; and performing a second preset weighting operation on the journey information and the dispatch efficiency loss of the second overtime probability, and generating the estimated cost of the target capacity for receiving the non-order taking.

Continuing with the above example:

the cost of delivering the tail order A by the jogger S1 is calculated by the formula 2 and is taken as the estimated cost of delivering the non-order taking M by the jogger S1:

cost=γ [ Δrisk1 (B, t) +Δrisk1 (C, t) ]+δ [ loss (B, s1, s 2) +loss (C, s1, s 2) ]+θ×f (t), equation 2;

where Δrisk1 (B, t) represents the increased risk of timeout of new order B to secondary road rider S2;

Δrisk1 (C, t) represents the increased risk of timeout of new order C to secondary road rider S2;

loss (B, S1, S2) represents the incremental distance that new order B increases to replace from most forward rider S1 to next forward rider S2;

loss (C, S1, S2) represents the incremental distance that new order C increases to replace from most forward rider S1 to next forward rider S2;

f (t) represents the scheduling time t as the running rider S1 loses new order B and new order C resulting in a subsequent possible overall dispatch efficiency loss within the target area.

In one example, f (t) is a constant associated with the target region and the scheduling time t, i.e., different target regions, different scheduling times, the value of this constant being different.

In summary, the method of embodiments of the present invention utilizes scheduling efficiency and order value for orders to evaluate the reward and cost described above.

It should be noted that, the scheduling time t described by the above formula of the present invention is the time for determining the running rider for receiving the non-taking order M in each embodiment of the present invention, that is, the method of each embodiment of the present invention is performed at the scheduling time t, and includes a series of operations of selecting the non-taking order M to receive the order rider and evaluating the review and cost.

In the embodiment of the invention, in order to avoid the drop of the order receiving rate in the target area caused by the decrease of the tail order under the condition of the shortage of the capacity supply and demand, the method in the embodiment of the invention takes the digested order as the main target, namely only if the estimated return of the target capacity receiving the tail order is larger than the cost of receiving the tail order, the target capacity which can be allocated with the new order is allocated with the non-received order which can become the tail order instead, thereby ensuring that the scheduling capacity receives the new order preferentially under the condition of the shortage of the capacity and ensuring the order receiving efficiency. In addition, the profit and the cost brought by the capacity receiving tail order of the scheduling target type can be comprehensively evaluated from the aspects of scheduling efficiency and order value, so that the estimated profit and cost are accurate, and then the final decision of scheduling the non-order taking is determined based on the profit and the cost, so that the overall experience in the target area can be optimized.

The inventor considers that only the pricing layer is used for attracting and guiding the crowd-sourced tail bill and cannot fundamentally solve the problem of tail bill protrusion in the crowd-sourced mode, and by means of the technical scheme of the various embodiments, the tail experience problem can be solved through scheduling capacity, and particularly, the crowd-sourced tail experience is optimized in the capacity management and control and scheduling layer, and the forced management and control music running rider is used for guaranteeing the digestion of the tail bill and guaranteeing the certainty of the digestion of the tail bill; meanwhile, the time and the dispatch Shan Yuzhi (such as the forward threshold) of the intervention of the running rider for receiving the tail order are adjusted according to the capacity supply and demand tension degree of the current crowd-sourced whole; under the situation of tension in transportation capacity supply and demand, the cost and the benefit of each tail monotone decision are fully considered, the scheduling decision of the non-order taking possibly becoming the tail list is executed only when the benefit > =loss, and the tail monotone decision of the large-scale damage experience is reduced, so that the overall experience is optimal.

The embodiment discloses an order distribution device, as shown in fig. 5, the device includes:

a first determining module 51, configured to determine a target capacity of a target type to accept an order that is not accepted according to a capacity supply and demand tension degree of a target area and an estimated timeout period of the order that is not accepted in the target area;

The second determining module 52 is configured to determine whether to allocate the non-order taking to the target capacity according to the estimated profit and cost of the target capacity for receiving the non-order taking if the capacity supply and demand tension meets the first preset condition.

Optionally, the first determining module 51 includes:

the first determining submodule is used for determining an order allocation strategy corresponding to the capacity of the target type according to the capacity supply and demand tension degree of the target area;

And the second determining submodule is used for determining the target capacity of the target type to accept the non-order according to the order distribution strategy if the estimated timeout duration of the non-order in the target area is matched with the order distribution strategy.

Optionally, the first determining submodule includes:

the first determining unit is used for determining a target overtime interval corresponding to the capacity of a target type and a target corresponding relation between overtime time corresponding to the capacity of the target type and a dispatch threshold according to the capacity supply and demand tension degree of the target area, wherein the target overtime interval comprises the overtime time;

Optionally, the second determining submodule includes:

the acquiring unit is used for acquiring a target dispatch threshold matched with the estimated timeout duration according to the target corresponding relation if the estimated timeout duration of the non-taken order in the target area is matched with the target timeout interval;

and the second determining unit is used for determining the target capacity of the target type of the target dispatch condition corresponding to the target dispatch threshold value, which is met by the dispatch condition in the target area.

In the embodiment of the invention, a target overtime interval corresponding to an unoccupied order which possibly becomes a tail order is determined according to the overall capacity supply and demand tension degree of a target area, and a target corresponding relation between the overtime time in the target overtime interval and a dispatch threshold is determined, so that the target corresponding relation can be queried according to the estimated overtime time of the unoccupied order, and the time for the unoccupied order to be accepted by the capacity of the target type and the target dispatch threshold are determined; under the condition that the non-order taking is not seriously overtime or is not cancelled, the target capacity of the target type of the corresponding target order taking condition is timely determined based on the target order taking threshold, tail experience of a target area can be optimized at the capacity management and control and scheduling layer, certainty of digestion of the tail order is guaranteed by utilizing the capacity of the strongly managed target type, and the problem of tail order protrusion is solved. In addition, under the condition that the tension degree of the supply and demand of the capacity meets the first preset condition, whether the order is distributed to the target capacity is determined according to the estimated income and the estimated cost of the order which possibly becomes the tail order, so that the problem that the order receiving rate in the target area is reduced due to the fact that the tail order rate in the target area is reduced is avoided.

Optionally, the first determining unit includes:

a first determining subunit, configured to determine a first preset timeout period as a target timeout period and determine a first correspondence between a first timeout period and a first dispatch threshold as the target correspondence when the capacity supply and demand tension degree meets a second preset condition, where each timeout period in the first preset timeout period is the first timeout period;

the second determining subunit is configured to determine a duration threshold according to the capacity supply-demand tension level if the capacity supply-demand tension level meets a first preset condition; adding the time threshold to each time-out time length in the first preset time-out interval to generate the target time-out interval; adding the time threshold to each first timeout time in the first correspondence, and generating a second correspondence between a second timeout time and the first dispatch threshold; and determining the second corresponding relation as the target corresponding relation.

Optionally, the target correspondence between the timeout duration corresponding to the capacity of the target type and the dispatch threshold includes:

Optionally, the acquiring unit includes:

the estimating subunit is used for estimating the time-consuming time of delivering the non-order according to the route planning information of the non-order and the historical order data between the buyers and sellers corresponding to the non-order for the non-order in the target area;

the first calculating subunit is used for calculating the sum of the system time and the time-consuming time to obtain a first estimated delivery time;

a second calculating subunit, configured to calculate a difference between the first expected delivery time and a second expected delivery time of the non-taken order output by the client side, to obtain an estimated timeout period of the non-taken order;

the first obtaining subunit is configured to obtain, according to the target correspondence, a target dispatch threshold value that matches the estimated timeout duration if the estimated timeout duration matches the target timeout interval.

Optionally, the second determining module 52 includes:

a distribution sub-module, configured to distribute the non-order taking to the target capacity if the estimated benefit of the target capacity receiving the non-order taking is greater than or equal to the cost;

and the rejecting sub-module is used for rejecting the allocation of the non-order taking to the target capacity if the estimated benefit of the target capacity for receiving the non-order taking is less than the cost.

Optionally, the apparatus further comprises:

optionally, the apparatus further comprises:

Optionally, the second determining unit includes:

the second obtaining subunit is used for obtaining the dispatch condition of each capacity of the target type according to the positioning information of each capacity of the target type in the target area, the distributed and unfinished order data of the capacity and the order data of the unfinished order;

And the third determining subunit is used for determining the capacity of the dispatch piece meeting the target dispatch condition corresponding to the target dispatch threshold as the target capacity.

Optionally, the apparatus further comprises:

and the allocation module is used for allocating the non-order taking to the target capacity under the condition that the capacity supply and demand tension degree meets a second preset condition.

According to the embodiment of the invention, under the condition that the tension degree of the supply and demand of the transport capacity meets the second preset condition, the missed order can be directly distributed to the target transport capacity, and the tail order rate of the target area can be timely reduced under the condition that the transport capacity is not tension.

The order distribution device disclosed in the embodiments of the present application is configured to implement each step of the order distribution method described in each embodiment of the present application, and specific embodiments of each module of the device refer to corresponding steps, which are not described herein again.

Correspondingly, the application also discloses electronic equipment, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the order distribution method according to any one of the embodiments of the application is realized when the processor executes the computer program. The electronic device may be a PC, a mobile terminal, a personal digital assistant, a tablet computer, etc.

The present application also discloses a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the order allocation method according to any of the embodiments described herein above.

In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described by differences from other embodiments, and identical and similar parts between the embodiments are all enough to be referred to each other. For the device embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points.

The foregoing has described in detail a method and apparatus for distributing orders provided herein, and specific examples have been applied herein to illustrate the principles and embodiments of the present application, the above examples being provided only to assist in understanding the method and core ideas of the present application; meanwhile, as those skilled in the art will have modifications in the specific embodiments and application scope in accordance with the ideas of the present application, the present description should not be construed as limiting the present application in view of the above.

The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.

Various component embodiments of the present disclosure may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that some or all of the functions of some or all of the components in a computing processing device according to embodiments of the present disclosure may be implemented in practice using a microprocessor or Digital Signal Processor (DSP). The present disclosure may also be embodied as a device or apparatus program (e.g., computer program and computer program product) for performing a portion or all of the methods described herein. Such a program embodying the present disclosure may be stored on a computer readable medium, or may have the form of one or more signals. Such signals may be downloaded from an internet website, provided on a carrier signal, or provided in any other form.

For example, FIG. 6 illustrates a computing processing device that may implement methods according to the present disclosure. The computing processing device conventionally includes a processor 1010 and a computer program product in the form of a memory 1020 or a computer readable medium. The memory 1020 may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read only memory), an EPROM, a hard disk, or a ROM. Memory 1020 has storage space 1030 for program code 1031 for performing any of the method steps described above. For example, the storage space 1030 for the program code may include respective program code 1031 for implementing the various steps in the above method, respectively. The program code can be read from or written to one or more computer program products. These computer program products comprise a program code carrier such as a hard disk, a Compact Disc (CD), a memory card or a floppy disk. Such a computer program product is typically a portable or fixed storage unit as described with reference to fig. 7. The storage unit may have memory segments, memory spaces, etc. arranged similarly to the memory 1020 in the computing processing device of fig. 6. The program code may be compressed, for example, in a suitable form. In general, the storage unit includes computer readable code 1031', i.e., code that can be read by a processor such as 1010, for example, which when executed by a computing processing device causes the computing processing device to perform the steps in the method described above.

Reference herein to "one embodiment," "an embodiment," or "one or more embodiments" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present disclosure. Furthermore, it is noted that the word examples "in one embodiment" herein do not necessarily all refer to the same embodiment.

In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the disclosure may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.

In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The disclosure may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, third, etc. do not denote any order. These words may be interpreted as names.

Finally, it should be noted that: the above embodiments are merely for illustrating the technical solution of the present disclosure, and are not limiting thereof; although the present disclosure has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present disclosure.

From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or may be implemented by hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.

Claims

1. An order allocation method, comprising:

determining a target capacity of a target type to be accepted for the non-order taking according to the capacity supply and demand tension degree of a target area and the estimated timeout period of the non-order taking in the target area, wherein the target timeout period corresponding to the capacity of the target type is different according to the capacity supply and demand tension degree of the target area, and the non-order taking is accepted by the capacity of the target type when the estimated timeout period of the non-order taking is within the target timeout period;

2. The method of claim 1, wherein the determining the target capacity of the target type to accept the non-order taking based on the capacity supply and demand tension of the target area and the estimated timeout period of the non-order taking in the target area comprises:

determining an order allocation strategy corresponding to the capacity of the target type according to the capacity supply and demand tension degree of the target area;

And if the estimated timeout duration of the non-order taking in the target area is matched with the order allocation strategy, determining the target capacity of the target type to accept the non-order taking according to the order allocation strategy.

3. The method of claim 2, wherein the step of determining the position of the substrate comprises,

the determining an order allocation strategy corresponding to the capacity of the target type according to the capacity supply and demand tension degree of the target area comprises the following steps:

determining a target overtime interval corresponding to the capacity of a target type and a target corresponding relation between overtime time corresponding to the capacity of the target type and a dispatch threshold according to the capacity supply and demand tension degree of the target area, wherein the target overtime interval comprises the overtime time;

if the estimated timeout period of the non-order taking in the target area is matched with the order allocation policy, determining a target capacity of the target type to accept the non-order taking according to the order allocation policy, including:

if the estimated time-out time length of the non-order taking in the target area is matched with the target time-out interval, acquiring a target order-dispatching threshold matched with the estimated time-out time length according to the target corresponding relation;

And determining the target capacity of the target type of the target dispatch conditions corresponding to the target dispatch threshold value, which is met by the dispatch conditions in the target area.

4. The method of claim 3, wherein determining a target timeout period corresponding to the capacity of the target type and a target correspondence between a timeout period corresponding to the capacity of the target type and a dispatch threshold according to the capacity supply and demand tension of the target area comprises:

under the condition that the capacity supply and demand tension degree meets a second preset condition, determining a first preset timeout interval as a target timeout interval, and determining a first corresponding relation between a first timeout duration and a first dispatch threshold value as the target corresponding relation, wherein each timeout duration in the first preset timeout interval is the first timeout duration;

under the condition that the capacity supply and demand tension degree meets a first preset condition, determining a duration threshold according to the capacity supply and demand tension degree; adding the time threshold to each time-out time length in the first preset time-out interval to generate the target time-out interval; adding the time threshold to each first timeout time in the first correspondence, and generating a second correspondence between a second timeout time and the first dispatch threshold; and determining the second corresponding relation as the target corresponding relation.

5. The method of claim 3, wherein the target correspondence between the timeout period corresponding to the capacity of the target type and the dispatch threshold comprises:

6. The method of claim 3, wherein if the estimated timeout period of the non-order taking in the target area matches the target timeout period, obtaining a target dispatch threshold matching the estimated timeout period according to the target correspondence, comprises:

for the non-order taking in the target area, estimating the time-consuming time of delivering the non-order taking according to the route planning information of the non-order taking and the historical order data between the buyers and sellers corresponding to the non-order taking;

Calculating the sum of the system time and the time-consuming time to obtain a first estimated delivery time;

calculating the difference between the first estimated time of delivery and the second estimated time of delivery of the non-order taking output by the client side, and obtaining the estimated timeout duration of the non-order taking;

and if the estimated timeout duration is matched with the target timeout interval, acquiring a target dispatch threshold matched with the estimated timeout duration according to the target corresponding relation.

7. The method of claim 1, wherein the determining whether to allocate the order for the target capacity based on the estimated return and cost of receiving the order for the target capacity comprises:

if the estimated return of the target capacity to accept the non-order taking is greater than or equal to the cost, distributing the non-order taking to the target capacity;

and if the estimated return of the target capacity to accept the non-order taking is less than the cost, refusing to distribute the non-order taking to the target capacity.

8. An order dispensing device, comprising:

the first determining module is used for determining a target capacity of a target type to accept the non-order taking according to the capacity supply and demand tension degree of a target area and the estimated time-out time length of the non-order taking in the target area, wherein the target time-out interval corresponding to the capacity of the target type is different according to the different capacity supply and demand tension degree of the target area, and the non-order taking is accepted by the capacity of the target type when the estimated time-out time length of the non-order taking is within the target time-out interval;

9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the order allocation method of any of claims 1 to 7 when executing the computer program.

10. A computer readable storage medium having stored thereon a computer program, characterized in that the program when executed by a processor realizes the steps of the order allocation method of any of claims 1 to 7.