CN110969382A - Method and device for determining distribution range - Google Patents
Method and device for determining distribution range Download PDFInfo
- Publication number
- CN110969382A CN110969382A CN201811143347.6A CN201811143347A CN110969382A CN 110969382 A CN110969382 A CN 110969382A CN 201811143347 A CN201811143347 A CN 201811143347A CN 110969382 A CN110969382 A CN 110969382A
- Authority
- CN
- China
- Prior art keywords
- delivery
- candidate
- distribution
- range
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000005457 optimization Methods 0.000 claims description 25
- 238000004422 calculation algorithm Methods 0.000 claims description 24
- 238000010801 machine learning Methods 0.000 claims description 13
- 238000013144 data compression Methods 0.000 claims description 10
- 230000008901 benefit Effects 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 9
- 238000007477 logistic regression Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000003066 decision tree Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Quality & Reliability (AREA)
- Entrepreneurship & Innovation (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a method and a device for determining a distribution range, a computer-readable storage medium and electronic equipment. Wherein the method comprises the following steps: drawing a plurality of candidate delivery ranges aiming at a target delivery requester; estimating the distribution efficiency data of each candidate distribution range according to the historical order information in the candidate distribution range; and determining an optimal distribution range from the plurality of candidate distribution ranges according to the distribution efficiency data of each candidate distribution range. By applying the method and the device, the distribution range can be determined more accurately, more efficiently and more objectively.
Description
Technical Field
The present application relates to the field of internet technologies, and in particular, to a method and an apparatus for determining a distribution range, a computer storage medium, and an electronic device.
Background
In the instant delivery scenario, each delivery requester has a unique delivery scope.
In the related art, the distribution range of the distribution requester is usually drawn off-line manually, and the distribution range of each distribution requester can be drawn and determined one by one according to manual experience. Taking the instant delivery scene of take-away delivery as an example, the delivery requester can be a merchant; distribution platform staff draw distribution ranges for each merchant one by one based on experience. However, manual drawing is mainly based on the working experience of workers, so that not only are subjective factors large and deviation easily occurs, but also manual drawing is time-consuming and labor-consuming and is low in efficiency; therefore, there is a need to provide a more accurate, efficient and objective delivery scope determination scheme.
Disclosure of Invention
In view of the above, the present application provides a method and an apparatus for determining a distribution range, a computer storage medium, and an electronic device, which are used to solve at least one of the above problems.
Specifically, the method is realized through the following technical scheme:
a method of determining a delivery range, the method comprising:
drawing a plurality of candidate delivery ranges aiming at a target delivery requester;
estimating the distribution efficiency data of each candidate distribution range according to the historical order information in the candidate distribution range;
and determining an optimal distribution range from the plurality of candidate distribution ranges according to the distribution efficiency data of each candidate distribution range.
Optionally, the drawing a plurality of candidate delivery ranges for the target delivery requester specifically includes:
and drawing a plurality of candidate delivery ranges by taking the target delivery requester as a center and using a plurality of different navigation radii.
Optionally, the delivery efficiency data includes an order amount and/or an average delivery duration.
Optionally, the method further includes:
optimizing the candidate distribution range;
the estimating of the delivery efficiency data of each candidate delivery range specifically includes:
and estimating the order quantity and/or the average distribution time length in each optimized candidate distribution range.
Optionally, the optimizing the candidate delivery range specifically includes:
determining a road boundary nearest to the boundary of the candidate delivery range;
and redrawing the candidate delivery range according to the road boundary.
Optionally, the optimizing the candidate delivery range specifically includes:
and performing data compression on the distribution reference point set forming the candidate distribution range.
Optionally, the data compression of the delivery reference point set constituting the candidate delivery range specifically includes:
traversing a distribution reference point set forming the candidate distribution range;
and combining the two adjacent distribution reference points into one after the distance between the two adjacent distribution reference points is smaller than a threshold value.
Optionally, the merging the two adjacent distribution reference points into one includes:
deleting any one of the two adjacent delivery reference points from the delivery reference point set;
or,
calculating an average distribution reference point of the two adjacent distribution reference points, and replacing the two adjacent distribution reference points in the distribution reference point set with the average distribution reference point.
Optionally, the optimizing the candidate delivery range specifically includes:
acquiring hot spot blocks within a preset radius outside the candidate distribution range;
and taking the hot spot blocks as a part of the candidate delivery range, thereby forming a new candidate delivery range.
Optionally, the predicting the order quantity and/or the average delivery duration in each candidate delivery range specifically includes:
and estimating the order quantity and/or the average distribution time length in each candidate distribution range based on a machine learning algorithm.
Optionally, the determining an optimal distribution range from the multiple candidate distribution ranges specifically includes:
and determining an optimal delivery range from the plurality of candidate delivery ranges based on a combined optimization algorithm.
Optionally, the objective of the combinatorial optimization algorithm is: the revenue of the target delivery requesters in the candidate delivery envelope is maximized.
Optionally, the benefit includes a deal amount of the order average delivery duration.
Optionally, the determining an optimal distribution range from the multiple candidate distribution ranges based on a combinatorial optimization algorithm according to the distribution efficiency data of each candidate distribution range specifically includes:
solving the transaction amount of the single average distribution time length in the maximized candidate distribution range according to the order amount and/or the average distribution time length of each candidate distribution range;
and determining the candidate delivery range with the maximum transaction amount of the single average delivery time length as the optimal delivery range.
A delivery range determination apparatus, the apparatus comprising:
a drawing unit that draws a plurality of candidate delivery ranges for a target delivery requester;
the calculation unit is used for estimating the distribution efficiency data of each candidate distribution range according to the historical order information in the candidate distribution range;
and a determining unit for determining an optimal distribution range from the plurality of candidate distribution ranges according to the distribution efficiency data of each candidate distribution range.
Optionally, the storage medium stores a computer program for executing the method for determining a distribution range according to any one of the above.
An electronic device, comprising:
a processor;
a memory for storing processor-executable instructions;
the processor is configured to the method of determining a delivery range of any of the above.
The embodiment of the application provides a distribution range determining scheme, a plurality of candidate distribution ranges are provided for a target distribution request, distribution efficiency data of each candidate distribution range are calculated by using historical distribution data of each candidate distribution range, and finally an optimal candidate distribution range is selected from the candidate distribution ranges as a distribution range of the target distribution request according to the distribution efficiency data of each candidate distribution range. In this way, the delivery range of the target delivery requester can be automatically generated. On one hand, since the historical delivery data exist objectively, the scheme for finally determining the optimal delivery range based on the historical delivery data can be considered to be considerable, so that the influence of subjective factors is eliminated; on the other hand, historical distribution data can truly reflect the historical order activity condition of the candidate distribution range, so that the distribution range determined based on the historical distribution data is more accurate; in yet another aspect, automatically drawing the delivery range is more efficient than manually drawing.
Drawings
FIG. 1 is a flow chart illustrating a method for determining a delivery range in accordance with an exemplary embodiment of the present application;
FIG. 2a is a plan map view of a city area shown in an exemplary embodiment of the present application;
FIG. 2b is a schematic illustration of a candidate delivery area of a navigation radius shown in an exemplary embodiment of the present application;
FIG. 3a is a schematic diagram of a hot spot block according to an exemplary embodiment of the present application;
FIG. 3b is a schematic diagram of a new candidate delivery area after optimization of the candidate delivery range in FIG. 3 a;
FIG. 4a is a schematic diagram illustrating a candidate delivery range boundary crossing a neighborhood in accordance with an exemplary embodiment of the present application;
FIG. 4b is a schematic view of the road boundary closest to the candidate delivery range boundary of FIG. 4 a;
FIG. 4c is a schematic illustration of candidate delivery ranges redrawn according to the road boundary determined in FIG. 4 b;
fig. 5 is a hardware configuration diagram of a distribution range determination apparatus according to an exemplary embodiment of the present application;
fig. 6 is a block diagram of a distribution range determining apparatus according to an exemplary embodiment of the present application.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It is to be understood that although the terms first, second, third, etc. may be used herein to describe various information, such information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present application. The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.
As described above, in the instant delivery scenario, each delivery requester has a separate delivery range.
In the related art, the determination of the delivery range of the delivery requester is usually performed manually offline. And drawing and determining the distribution range of each distribution requester one by one according to manual experience. Taking the timely delivery such as takeaway delivery as an example, the delivery requester can be a merchant; distribution platform staff draw distribution ranges for each merchant one by one based on experience. However, manual drawing is mainly based on the working experience of workers, so that not only are subjective factors large and deviation easily occurs, but also manual drawing is time-consuming and labor-consuming and is low in efficiency; it is desirable to provide a more accurate, efficient and objective delivery scope determination scheme.
It is worth mentioning that the delivery area is a geographical conceptual area where a merchant is only visible to users located within the merchant's delivery area on the takeaway platform. That is, order relationships only result for users within the merchant and distribution boundaries. The distribution range is directly related to the income of the merchant, so that the distribution range of the merchant is a hard constraint and directly determines the order quantity, the distribution efficiency and the user experience. If the distribution range of the merchant is set to be too small, the potential user group is small, and order flow and income are small; if the distribution range of the merchant is set to be too large, although the potential user group is large, the generated order flow may be improved to a certain extent, but the overall distribution efficiency may be greatly influenced, and further the user experience is influenced.
Therefore, how to balance the relationship among the distribution range, the distribution efficiency and the profit is a problem to be solved urgently.
According to the method, firstly, a plurality of candidate distribution ranges are provided for a target distribution request, then, the distribution efficiency data of each candidate distribution range is calculated by utilizing the historical distribution data of each candidate distribution range, and finally, an optimal candidate distribution range is selected from the candidate distribution ranges to serve as the distribution range of the target distribution request party according to the distribution efficiency data of each candidate distribution range. In this way, the delivery range of the target delivery requester can be automatically generated. Because the historical delivery data exist objectively, the real delivery condition of the candidate delivery range can be objectively reflected by parameters including delivery efficiency, income and the like, so that the scheme provided by the application ensures objectivity and accuracy, and the automatic delivery range drawing is more efficient than manual delivery range drawing.
Specifically, the profit conditions of the candidate delivery ranges can be predicted maximally according to the delivery efficiency data, and then the candidate delivery range with the largest profit is selected as the final delivery range. Thus, the distribution efficiency of the distribution range is considered, and the income condition of the distribution range can be maximized.
The technical solution of the present application is described in detail below, and fig. 1 is a flowchart of a method for determining a distribution range according to an exemplary embodiment of the present application, where the method may be applied to a server (hereinafter, referred to as a server) for determining a distribution range, and the method specifically includes the following steps:
step 110: and drawing a plurality of candidate delivery ranges for the target delivery requester.
The server can refer to a server, a server cluster or a cloud platform constructed by the server cluster.
The target delivery requester may refer to an object whose delivery range is to be determined. For example, a merchant who wants to determine a distribution range in a take-out business scenario; or, an express delivery network point of a distribution range to be determined in an express delivery service scene, and the like.
In an embodiment, the step 110 may specifically include:
a plurality of candidate delivery ranges are drawn with a plurality of different radii centering on the position of the target delivery requester.
In the present application, the plurality may mean 2 or more. The radius may be preset. E.g., 1 km, 3 km, 5 km, etc. In general, the radius can be flexibly changed based on actual traffic needs.
A plan map schematic of a certain urban area as shown in fig. 2 a. In fig. 2a, point P represents the position of the target delivery requester, and it can be seen that there are 3 delivery ranges with different radii, with the radius being r1 km, r2 km and r3 km respectively, plotted with point P as the center.
In an implementation, the radius may refer to a straight radius. The delivery area of the straight radius may refer to an area having a straight distance of R (a preset radius value) from a point P (a position of a target delivery requester). Referring to the dispensing area shown in fig. 2a, it can be seen that all the dispensing areas are regular circles, that is, the straight line distance from any point on the boundary of the same dispensing range to point P is the same.
In another implementation, the radius may refer to a navigation radius. The delivery area of the navigation radius may refer to an area having a navigation distance of R (a preset radius value) from a point P (a position of a target delivery requester). That is, the navigation distance may refer to a distance from a point to a real path between points. Since the logistics distribution process requires distribution personnel to distribute along the roads, the distribution paths are not always straight, and the people may need to detour from one location to another, the actual distribution distance is often greater than the straight distance. The navigation radius can truly measure the actual distance between two points and the distribution cost, so that the method is more reasonable and accurate in the actual geographical position scene.
A schematic diagram of a candidate delivery area of the navigation radius as shown in fig. 2 b. It can be seen that the candidate delivery area is not a regular circle as in fig. 2a, and although the straight-line distance from the point on the same delivery range boundary to the point P in fig. 2b may be different, the navigation distances are the same, and the navigation distances are navigation radii.
In an embodiment, after the step 110, the method may further include:
and optimizing the candidate distribution range.
In practical applications, various inaccurate places may exist due to planned candidate delivery areas. For example, the distribution range boundary crosses a block, and the distribution range boundary is not a road boundary.
In one implementation:
the optimizing the candidate delivery range may specifically include:
acquiring hot spot blocks within a preset radius outside the candidate distribution range;
and taking the hot spot blocks as a part of the candidate delivery range, thereby forming a new candidate delivery range.
The hotspot tiles described herein may refer to geographic areas where orders perform better. Whether the order belongs to the hot area block is generally judged, and the judgment can be carried out according to the historical order quantity. Specifically, a clustering algorithm may be used to cluster out blocks with a historical order number exceeding a certain threshold, and such blocks may be referred to as hot-spot blocks.
Wherein the preset radius and the preset radius are not the same radius value. For the convenience of distinction, the radius of the planned candidate delivery area may be referred to as a first radius, and the preset radius outside the candidate delivery area may be referred to as a second radius. Typically, the second radius is greater than the first radius.
In one embodiment, the second radius may be obtained by adding a predetermined value to the first radius.
Fig. 3a is a schematic diagram of a hot spot block. In fig. 3a, there are two ranges of a first radius range ((abbreviated as small circle) and a second radius range (abbreviated as large circle). in the area inside the large circle outside the small circle, it is seen that there are hot spot blocks a and hot spot areas B, so that the hot spot blocks a and hot spot blocks B can be used as part of the candidate distribution range, thereby forming a new candidate distribution range as shown in fig. 3B.
Through the embodiment, the geographical location block with high user popularity is added, namely, the candidate delivery range covers some places with intensive user exposure, so that the candidate delivery range of the delivery requester can be generated more reasonably.
As mentioned above, in practical applications, the boundary of the candidate delivery range drawn in the above steps may not be a road boundary, such as the schematic diagram of FIG. 4a illustrating the boundary of the candidate delivery range crossing the block. Taking a take-out scene in the instant delivery service as an example, if the delivery range of a merchant crosses a block, it may cause that some users in the block may order at the merchant, and some other users may not order at the merchant, which is obviously unreasonable; moreover, generally, the more the number of customers ordering in the same block is, the better, and for a distributor, the customers in the block can be distributed at the same time, so that not only is the time cost lower, but also the income is more. Crossing the neighborhood for the platform significantly reduces GMV (Gross merchandisc Volume). Therefore, it is necessary to perform optimization processing on the candidate delivery range so that the boundary of the candidate delivery range is divided by taking the road as the boundary.
To this end, in one implementation:
the optimizing the candidate delivery range may specifically include:
determining a road boundary nearest to the boundary of the candidate delivery range;
and redrawing the candidate delivery range according to the road boundary.
Still taking FIG. 4a as an example, it can be seen that the boundary of the candidate delivery area spans the block road; at this time, it is necessary to determine the road boundary closest to the boundary. As shown in fig. 4b, the road boundary closest to the boundary is a dashed line segment; therefore, the candidate delivery range redrawn according to the determined road boundary is shown in fig. 4 c.
In one implementation:
the optimizing the candidate delivery range may specifically include:
and performing data compression on the distribution reference point set forming the candidate distribution range.
The data compression of the delivery reference point set constituting the candidate delivery range may specifically include:
traversing a distribution reference point set forming the candidate distribution range;
and combining the two adjacent distribution reference points into one after the distance between the two adjacent distribution reference points is smaller than a threshold value.
In general, the candidate delivery range may be composed of a series of delivery reference points on a boundary. And connecting the distribution reference points to plan a boundary line. Specifically, the navigation paths between two adjacent delivery reference points are connected to form a closed polygon, and the area in the polygon is the candidate delivery range.
Typically, the delivery reference points are stored in the form of a set. In order to improve the storage space utilization, the delivery reference point set can be compressed.
The merging mode may include:
and deleting any one of the two adjacent delivery datum points from the delivery datum point set.
Or,
calculating an average distribution reference point of the two adjacent distribution reference points;
replacing two adjacent delivery reference points in the set of delivery reference points with the average delivery reference point.
By compressing the delivery reference point set constituting the candidate delivery range, the amount of stored data can be effectively reduced without affecting the size of the candidate delivery range.
Step 120: and estimating the distribution efficiency data of each candidate distribution range according to the historical order information in the candidate distribution range.
The delivery efficiency data may be used to represent revenue generated by the delivery requester after the candidate delivery areas are adopted. In one embodiment, the delivery efficiency data may include an order size and an average delivery duration.
In an embodiment, the delivery efficiency data may include an order amount and/or an average delivery duration.
That is, the step 120 may specifically include:
and estimating the order quantity and/or the average distribution time length according to the historical order information in the candidate distribution range.
Wherein, aiming at the estimated order quantity:
the historical order information may include the counted merchant information in the candidate delivery range, the delivery difficulty information, and the like.
In particular, the merchant information may include characteristics of merchant dimensions, such as number of merchants within a candidate delivery range, historical order quantity, merchant ratings, merchant categories, and the like.
The delivery difficulty information may include a rider idle rate, a number of riders, and the like within the candidate delivery range.
In one embodiment, the server may pre-train a machine learning model for estimating the order quantity and/or the average delivery duration of the candidate delivery range based on a machine learning technique. That is, the estimating of the order quantity and/or the average delivery duration in each candidate delivery range specifically includes:
and estimating the order quantity and/or the average distribution time length in each candidate distribution range based on a machine learning algorithm.
Specifically, the server side can collect a large number of historical order information samples in different distribution ranges in advance, and train an order quantity estimation model based on a machine learning algorithm; the order quantity estimation model can be continuously improved through continuous learning, and when the order quantity estimation model reaches the prediction (for example, the estimation accuracy meets the service requirement), the order quantity estimation model can be online and used. When the system is used in business, after historical order information of the candidate distribution range is counted, the counted historical order information is output to an order quantity estimation model, and then order quantity can be calculated. The machine learning model may employ, for example, Logistic Regression (LR), GBDT (gradient enhanced decision tree), and the like.
Wherein, aiming at the estimated average delivery time:
the historical order information may include statistical rider information within candidate delivery ranges. In particular, the rider information may include a delivery duration for the rider to deliver the historical order.
Specifically, the server can collect a large number of historical order information samples in different distribution ranges in advance, and train an average distribution time length estimation model based on a machine learning algorithm; the average distribution time length estimation model can be continuously perfected through continuous learning, and when the average distribution time length estimation model reaches the prediction (for example, the estimation accuracy meets the service requirement), the average distribution time length estimation model can be online and used. When the system is used in business, after historical order information of a candidate distribution range is counted, the counted historical order information is output to an average distribution time length estimation model, and then the average distribution time length can be calculated. The machine learning model may employ, for example, Logistic Regression (LR), GBDT (gradient enhanced decision tree), and the like.
Step 130: and determining an optimal distribution range from the plurality of candidate distribution ranges according to the distribution efficiency data of each candidate distribution range.
After the delivery efficiency data of each candidate delivery range is estimated, an optimal candidate delivery range can be selected from the estimated candidate delivery ranges according to the delivery efficiency data to serve as a delivery range finally determined by the target delivery requester.
Generally, this selection of an optimal item from the plurality of selectable items can be implemented by using an optimization algorithm. Specifically, after an optimization target is determined according to business requirements, the optimization target is taken as a jump-out condition, an optimization algorithm is called for calculation, and when a calculation result meets the jump-out condition, namely the optimization target is reached, a selectable item in the jump-out process can be taken as an optimal item.
In an embodiment, the step 130 may specifically include:
and determining an optimal delivery range from the plurality of candidate delivery ranges based on a combined optimization algorithm.
Wherein, the combined optimization algorithm aims at: maximizing the profit of the target delivery requester in the candidate delivery range; the constraint conditions are as follows: the order quantity weighted area of the candidate delivery area meets the preset condition.
In one embodiment, the benefit may include a deal amount for an average delivery length. Generally, the deal amount can be represented by GMV (Gross merchandisc Volume). I.e. the amount of deal for the average delivery duration is expressed as GMV (order amount/average dispensing duration).
Specifically, the GMV that maximizes the single average delivery duration of the target delivery requesters in the candidate delivery range may be calculated by the following formula:
wherein, cmnA 0-1 mark (which is also a variable to be solved by the combinatorial optimization algorithm) representing whether the merchant m adopts the candidate delivery range n; order _ nummnRepresenting the estimated order quantity of the merchant m predicted by the machine learning model when the candidate delivery range n is adopted; pricemRepresents the average customer unit price (i.e., sum of historical order amounts divided by historical order quantities) for merchant m; timemnRepresenting the estimated average delivery duration of the m merchants predicted by the machine learning model when adopting the candidate delivery range n, α representing a smoothing factor (the denominator is 0), AmnA delivery area representing a candidate delivery range n for a merchant m;
indicating a manually set scale factor (used to regulate the enlargement/reduction of the order quantity weighted average delivery area).
According to the method and the device for the target distribution request, multiple candidate distribution ranges are provided for the target distribution request, the distribution efficiency data of each candidate distribution range are calculated by using the historical distribution data of each candidate distribution range, and finally an optimal candidate distribution range is selected from the multiple candidate distribution ranges to serve as the distribution range of the target distribution request party according to the distribution efficiency data of each candidate distribution range. In this way, the delivery range of the target delivery requester can be automatically generated.
Corresponding to the foregoing embodiments of the method for determining a delivery range, the present application also provides embodiments of a device for determining a delivery range.
The embodiment of the distribution range determining device can be applied to a server. The device embodiments may be implemented by software, or by hardware, or by a combination of hardware and software. The software implementation is taken as an example, and is formed by reading corresponding computer program instructions in the nonvolatile memory into the memory for operation through the processor in which the software implementation is located. From a hardware aspect, as shown in fig. 5, a hardware structure diagram of the device for determining a distribution range of the present application is shown, except for the processor, the memory, the network interface, and the nonvolatile memory shown in fig. 5, in an embodiment, an actual function generally determined according to the distribution range may also include other hardware, which is not described again.
Referring to fig. 6, in a software implementation, the device for determining the distribution range may include:
a drawing unit 610 that draws a plurality of candidate delivery ranges for a target delivery requester;
the calculating unit 620 estimates the distribution efficiency data of each candidate distribution range according to the historical order information in the candidate distribution range;
the determining unit 630 determines an optimal distribution range from the plurality of candidate distribution ranges according to the distribution efficiency data for each of the candidate distribution ranges.
Optionally, the drawing unit 610 specifically includes:
and drawing a plurality of candidate delivery ranges by taking the target delivery requester as a center and using a plurality of different navigation radii.
Optionally, the delivery efficiency data includes an order amount and/or an average delivery duration.
Optionally, the apparatus further comprises:
the optimization unit is used for optimizing the candidate distribution range;
the calculating unit 620 specifically includes:
and estimating the optimized order quantity and/or average distribution time length in each candidate distribution range according to the historical order information in the candidate distribution range.
Optionally, the optimization unit specifically includes:
a road boundary determining subunit that determines a road boundary closest to a boundary of the candidate delivery range;
and the redrawing subunit redraws the candidate delivery range according to the road boundary.
Optionally, the optimization unit specifically includes:
and a data compression subunit that performs data compression on the delivery reference point set constituting the candidate delivery range.
Optionally, the data compression subunit specifically includes:
the merging subunit traverses a distribution reference point set forming the candidate distribution range; and combining the two adjacent distribution reference points into one after the distance between the two adjacent distribution reference points is smaller than a threshold value.
Optionally, the merging the two adjacent distribution reference points into one includes:
deleting any one of the two adjacent delivery reference points from the delivery reference point set;
or,
calculating an average distribution reference point of the two adjacent distribution reference points, and replacing the two adjacent distribution reference points in the distribution reference point set with the average distribution reference point.
Optionally, the optimization unit specifically includes:
the hot spot block acquisition subunit acquires the hot spot blocks within a preset radius outside the candidate distribution range;
and the redrawing subunit takes the hot spot block as a part of the candidate delivery range so as to form a new candidate delivery range.
Optionally, the predicting the order quantity and/or the average delivery duration in each candidate delivery range specifically includes:
and estimating the order quantity and/or the average distribution time length in each candidate distribution range based on a machine learning algorithm.
Optionally, the determining unit 630 specifically includes:
and the determining subunit determines an optimal distribution range from the plurality of candidate distribution ranges based on a combined optimization algorithm according to the distribution efficiency data of each candidate distribution range.
Optionally, the objective of the combinatorial optimization algorithm is: the revenue of the target delivery requesters in the candidate delivery envelope is maximized.
Optionally, the benefit includes a deal amount of the order average delivery duration.
Optionally, the determining the subunit specifically includes:
solving the transaction amount of the single average distribution time length in the maximized candidate distribution range according to the order amount and/or the average distribution time length of each candidate distribution range; and determining the candidate delivery range with the maximum transaction amount of the single average delivery time length as the optimal delivery range.
The implementation process of the functions and actions of each unit in the above device is specifically described in the implementation process of the corresponding step in the above method, and is not described herein again.
For the device embodiments, since they substantially correspond to the method embodiments, reference may be made to the partial description of the method embodiments for relevant points. The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of the application. One of ordinary skill in the art can understand and implement it without inventive effort.
Fig. 6 above describes the internal functional modules and the structural schematic of the service monitoring apparatus, and the actual execution subject of the service monitoring apparatus may be an electronic device, including:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to:
drawing a plurality of candidate delivery ranges aiming at a target delivery requester;
estimating the distribution efficiency data of each candidate distribution range according to the historical order information in the candidate distribution range;
and determining an optimal distribution range from the plurality of candidate distribution ranges according to the distribution efficiency data of each candidate distribution range.
Optionally, the drawing a plurality of candidate delivery ranges for the target delivery requester specifically includes:
and drawing a plurality of candidate delivery ranges by taking the target delivery requester as a center and using a plurality of different navigation radii.
Optionally, the delivery efficiency data includes an order amount and/or an average delivery duration.
Optionally, the method further includes:
optimizing the candidate distribution range;
the estimating of the delivery efficiency data of each candidate delivery range specifically includes:
and estimating the order quantity and/or the average distribution time length in each optimized candidate distribution range.
Optionally, the optimizing the candidate delivery range specifically includes:
determining a road boundary nearest to the boundary of the candidate delivery range;
and redrawing the candidate delivery range according to the road boundary.
Optionally, the optimizing the candidate delivery range specifically includes:
and performing data compression on the distribution reference point set forming the candidate distribution range.
Optionally, the data compression of the delivery reference point set constituting the candidate delivery range specifically includes:
traversing a distribution reference point set forming the candidate distribution range;
and combining the two adjacent distribution reference points into one after the distance between the two adjacent distribution reference points is smaller than a threshold value.
Optionally, the merging the two adjacent distribution reference points into one includes:
deleting any one of the two adjacent delivery reference points from the delivery reference point set;
or,
calculating an average distribution reference point of the two adjacent distribution reference points, and replacing the two adjacent distribution reference points in the distribution reference point set with the average distribution reference point.
Optionally, the optimizing the candidate delivery range specifically includes:
acquiring hot spot blocks within a preset radius outside the candidate distribution range;
and taking the hot spot blocks as a part of the candidate delivery range, thereby forming a new candidate delivery range.
Optionally, the predicting the order quantity and/or the average delivery duration in each candidate delivery range specifically includes:
and estimating the order quantity and/or the average distribution time length in each candidate distribution range based on a machine learning algorithm.
Optionally, the determining an optimal distribution range from the multiple candidate distribution ranges specifically includes:
and determining an optimal delivery range from the plurality of candidate delivery ranges based on a combined optimization algorithm.
Optionally, the objective of the combinatorial optimization algorithm is: the revenue of the target delivery requesters in the candidate delivery envelope is maximized.
Optionally, the benefit includes a deal amount of the order average delivery duration.
Optionally, the determining an optimal distribution range from the multiple candidate distribution ranges based on a combinatorial optimization algorithm according to the distribution efficiency data of each candidate distribution range specifically includes:
solving the transaction amount of the single average distribution time length in the maximized candidate distribution range according to the order amount and/or the average distribution time length of each candidate distribution range;
and determining the candidate delivery range with the maximum transaction amount of the single average delivery time length as the optimal delivery range.
In the above embodiments of the electronic device, it should be understood that the Processor may be a Central Processing Unit (CPU), other general-purpose processors, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), etc. The general-purpose processor may be a microprocessor, or the processor may be any conventional processor, and the aforementioned memory may be a read-only memory (ROM), a Random Access Memory (RAM), a flash memory, a hard disk, or a solid state disk. The steps of a method disclosed in connection with the embodiments of the present invention may be directly implemented by a hardware processor, or may be implemented by a combination of hardware and software modules in the processor.
The embodiments in the present application are described in a progressive manner, and the same and similar parts among the embodiments can be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the embodiment of the electronic device, since it is substantially similar to the embodiment of the method, the description is simple, and for the relevant points, reference may be made to part of the description of the embodiment of the method.
The above description is only exemplary of the present application and should not be taken as limiting the present application, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the scope of protection of the present application.
Claims (17)
1. A method for determining a delivery range, the method comprising:
drawing a plurality of candidate delivery ranges aiming at a target delivery requester;
estimating the distribution efficiency data of each candidate distribution range according to the historical order information in the candidate distribution range;
and determining an optimal distribution range from the plurality of candidate distribution ranges according to the distribution efficiency data of each candidate distribution range.
2. The method of claim 1, wherein the mapping the plurality of candidate delivery areas to the target delivery requester comprises:
and drawing a plurality of candidate delivery ranges by taking the target delivery requester as a center and using a plurality of different navigation radii.
3. The method of claim 1, wherein the delivery efficiency data comprises an order amount and/or an average delivery duration.
4. The method of claim 3, further comprising:
optimizing the candidate distribution range;
the estimating of the delivery efficiency data of each candidate delivery range specifically includes:
and estimating the order quantity and/or the average distribution time length in each optimized candidate distribution range.
5. The method according to claim 4, wherein the optimizing the candidate delivery range specifically comprises:
determining a road boundary nearest to the boundary of the candidate delivery range;
and redrawing the candidate delivery range according to the road boundary.
6. The method according to claim 4, wherein the optimizing the candidate delivery range specifically comprises:
and performing data compression on the distribution reference point set forming the candidate distribution range.
7. The method of claim 6, wherein the data compressing the set of delivery reference points that constitute the candidate delivery range comprises:
traversing a distribution reference point set forming the candidate distribution range;
and combining the two adjacent distribution reference points into one after the distance between the two adjacent distribution reference points is smaller than a threshold value.
8. The method of claim 7, wherein said merging the two adjacent delivery datum points into one comprises:
deleting any one of the two adjacent delivery reference points from the delivery reference point set;
or,
calculating an average distribution reference point of the two adjacent distribution reference points, and replacing the two adjacent distribution reference points in the distribution reference point set with the average distribution reference point.
9. The method according to claim 4, wherein the optimizing the candidate delivery range specifically comprises:
acquiring hot spot blocks within a preset radius outside the candidate distribution range;
and taking the hot spot blocks as a part of the candidate delivery range, thereby forming a new candidate delivery range.
10. The method of claim 3, wherein the predicting the order quantity and/or the average delivery duration within each candidate delivery range comprises:
and estimating the order quantity and/or the average distribution time length in each candidate distribution range based on a machine learning algorithm.
11. The method of claim 1, wherein the determining an optimal delivery envelope from the plurality of candidate delivery envelopes comprises:
and determining an optimal delivery range from the plurality of candidate delivery ranges based on a combined optimization algorithm.
12. The method of claim 11, wherein the combinatorial optimization algorithm targets: the revenue of the target delivery requesters in the candidate delivery envelope is maximized.
13. The method of claim 12, wherein the benefit comprises a deal amount for an average delivery length.
14. The method of claim 13, wherein determining an optimal delivery envelope from the plurality of candidate delivery envelopes based on a combinatorial optimization algorithm based on the delivery efficiency data for each candidate delivery envelope comprises:
solving the transaction amount of the single average distribution time length in the maximized candidate distribution range according to the order amount and/or the average distribution time length of each candidate distribution range;
and determining the candidate delivery range with the maximum transaction amount of the single average delivery time length as the optimal delivery range.
15. An apparatus for determining a delivery range, the apparatus comprising:
a drawing unit that draws a plurality of candidate delivery ranges for a target delivery requester;
the calculation unit is used for estimating the distribution efficiency data of each candidate distribution range according to the historical order information in the candidate distribution range;
and a determining unit for determining an optimal distribution range from the plurality of candidate distribution ranges according to the distribution efficiency data of each candidate distribution range.
16. A computer-readable storage medium, characterized in that the storage medium stores a computer program for performing the method of any of the preceding claims 1-14.
17. An electronic device, comprising:
a processor;
a memory for storing processor-executable instructions;
the processor is configured as the method of any of the above claims 1-14.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811143347.6A CN110969382A (en) | 2018-09-28 | 2018-09-28 | Method and device for determining distribution range |
| PCT/CN2019/108572 WO2020063875A1 (en) | 2018-09-28 | 2019-09-27 | Determination of delivery range |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811143347.6A CN110969382A (en) | 2018-09-28 | 2018-09-28 | Method and device for determining distribution range |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110969382A true CN110969382A (en) | 2020-04-07 |
Family
ID=69953392
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811143347.6A Pending CN110969382A (en) | 2018-09-28 | 2018-09-28 | Method and device for determining distribution range |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110969382A (en) |
| WO (1) | WO2020063875A1 (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2014075108A (en) * | 2012-10-04 | 2014-04-24 | Millet Co Ltd | Delivery temperature zone automatic optimization shopping cart system |
| CN105825360A (en) * | 2016-03-31 | 2016-08-03 | 北京小度信息科技有限公司 | Adjustment method and apparatus of merchant distribution scope |
| CN107180324A (en) * | 2017-05-05 | 2017-09-19 | 百度在线网络技术（北京）有限公司 | One kind spells single method and apparatus |
| CN107437122A (en) * | 2016-05-26 | 2017-12-05 | 北京三快在线科技有限公司 | Determine that businessman dispenses the method and device of scope |
| CN107590242A (en) * | 2017-09-14 | 2018-01-16 | 北京三快在线科技有限公司 | A kind of address information processing method and device |
| CN108364085A (en) * | 2018-01-02 | 2018-08-03 | 拉扎斯网络科技（上海）有限公司 | Takeout delivery time prediction method and device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2002005153A2 (en) * | 2000-07-07 | 2002-01-17 | 2020Me Holdings Ltd. | System, method and medium for facilitating transactions over a network |
-
2018
- 2018-09-28 CN CN201811143347.6A patent/CN110969382A/en active Pending
-
2019
- 2019-09-27 WO PCT/CN2019/108572 patent/WO2020063875A1/en active Application Filing
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2014075108A (en) * | 2012-10-04 | 2014-04-24 | Millet Co Ltd | Delivery temperature zone automatic optimization shopping cart system |
| CN105825360A (en) * | 2016-03-31 | 2016-08-03 | 北京小度信息科技有限公司 | Adjustment method and apparatus of merchant distribution scope |
| CN107437122A (en) * | 2016-05-26 | 2017-12-05 | 北京三快在线科技有限公司 | Determine that businessman dispenses the method and device of scope |
| CN107180324A (en) * | 2017-05-05 | 2017-09-19 | 百度在线网络技术（北京）有限公司 | One kind spells single method and apparatus |
| CN107590242A (en) * | 2017-09-14 | 2018-01-16 | 北京三快在线科技有限公司 | A kind of address information processing method and device |
| CN108364085A (en) * | 2018-01-02 | 2018-08-03 | 拉扎斯网络科技（上海）有限公司 | Takeout delivery time prediction method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020063875A1 (en) | 2020-04-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220156696A1 (en) | System and method for dynamic pairing function optimization | |
| CN109165895B (en) | Pricing method and device based on distribution service | |
| US9235620B2 (en) | Updating cached database query results | |
| CN105825360A (en) | Adjustment method and apparatus of merchant distribution scope | |
| KR101932608B1 (en) | Management method for bike sharing system, management server for bike sharing system, and computer readable recording medium | |
| JP2019145088A (en) | System and method for dynamically distributing energy between exchangeable energy storage device stations | |
| CN108615129B (en) | Transport capacity monitoring method and device and electronic equipment | |
| US11188932B2 (en) | Method, apparatus, and computer program product for providing mobile location based sales lead identification | |
| CN108154275A (en) | Automobile residual value prediction model and Forecasting Methodology based on big data | |
| US9785897B2 (en) | Methods and systems for optimizing efficiency of a workforce management system | |
| CN109636013A (en) | Distribution range generation method and device, electronic equipment and storage medium | |
| CA3117138A1 (en) | Method and system for identifying, tracking, and predicting the location of moving merchants | |
| CN110956296A (en) | User loss probability prediction method and device | |
| US20190116464A9 (en) | System for Analyzing and Improving Device Location as a Function of Time | |
| CN110310153A (en) | A kind of transaction prediction technique and device | |
| CN109523152A (en) | Order processing method, storage medium and device | |
| CN108664605B (en) | Model evaluation method and system | |
| AU2018217973A1 (en) | Dynamic selection of geo-based service options in a network system | |
| CN108171530B (en) | Method and device for improving unit price and repurchase rate of customers | |
| KR101606322B1 (en) | Method and apparatus for evaluating value of used car | |
| CN110969382A (en) | Method and device for determining distribution range | |
| US11861579B1 (en) | Intelligent inventory system | |
| CN111464337A (en) | Resource allocation method and device and electronic equipment | |
| KR20230026835A (en) | Apparatus and method for calculating sale price of real estate of development prearranged area | |
| KR102161321B1 (en) | Apparatus for estimating a floating population and method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |