Delivery range determination method and apparatus

Abstract

The specification discloses a delivery range determination method and device. A starting interest area and a target interest area are determined from each interest area pre-divided in a specified area. Then, a transfer reward of the starting interest area to the target interest area and a transfer probability of the target interest area to each other interest area are determined according to order information of each historical order in the specified area. The score of the target interest area is determined iteratively according to the determined transfer reward, each transfer probability and the scores of each other interest area. Finally, when a preset iteration stop condition is met, the delivery range of each merchant in the specified area is determined according to the scores of each interest area. Each interest area in the specified area is scored based on order information of historical orders in the specified area from a global perspective, so as to determine the delivery range of each merchant in the specified area, and make the delivery range division more reasonable.

Description

Technical Field

[0001] This application relates to the field of order delivery technology, and in particular to a method and apparatus for determining the delivery range. Background Technology

[0002] In the context of on-demand delivery, in order to ensure delivery efficiency and user experience, delivery platforms typically set delivery ranges for each merchant, and only users within the merchant's delivery range can place orders with that merchant.

[0003] Currently, determining a merchant's delivery area can be based on a comprehensive consideration of factors such as delivery distance and order volume. Specifically, for each merchant, several AOIs within a pre-defined area of ​​interest (AOI) are selected as candidate AOIs, based on the merchant's location information. Then, for each candidate AOI, a score is determined based on the number of orders placed by users with that candidate AOI as their delivery address, and the distance between the merchant and the candidate AOI. Finally, the merchant's delivery area is determined based on the scores of all candidate AOIs corresponding to that merchant.

[0004] However, the above method of scoring each AOI based solely on the number of orders placed by the merchant within a single AOI and the distance between the two is rather limited, resulting in inaccurate division of delivery areas. Summary of the Invention

[0005] The delivery range determination method and apparatus provided in the embodiments of this specification are used to partially solve the problems in the prior art.

[0006] The embodiments in this specification adopt the following technical solutions:

[0007] The delivery range determination method provided in this manual includes:

[0008] Retrieve order information for several historical orders within a specified area;

[0009] Based on the pre-divided regions of interest within the specified area, determine the starting region of interest and the target region of interest;

[0010] Based on the order information of each historical order, determine the transfer reward from the starting interest area to the target interest area, and the transfer probability from the target interest area to other interest areas;

[0011] The score of the target interest area is determined iteratively based on the transfer reward from the starting interest area to the target interest area, the transfer probability from the target interest area to each other interest area, and the scores of each other interest area that have been determined.

[0012] When the preset iteration stopping condition is met, the score of each interest area is determined, and the delivery range of each merchant in the specified area is determined based on the score of each interest area.

[0013] The preset iteration stopping conditions include at least: the number of iterations reaches a first preset threshold; and / or the score difference between two consecutive iterations of each region of interest is less than a second preset threshold.

[0014] Optionally, based on the order information of each historical order obtained, a transfer reward is determined for the transfer from the initial area of ​​interest to the target area of ​​interest, specifically including:

[0015] Based on the delivery start and end locations in the order information of each historical order, determine each order that was transferred from the starting area of ​​interest to the target area of ​​interest;

[0016] Based on the order metrics of each order transferred from the starting area of ​​interest to the target area of ​​interest, the transfer reward for the transfer from the starting area of ​​interest to the target area of ​​interest is determined.

[0017] The order metrics include at least one of the following: average order value, order revenue, and delivery time.

[0018] Optionally, based on the order information of each historical order obtained, the transfer probability of the target region of interest to other regions of interest is determined, specifically including:

[0019] For each other interest area, the number of orders transferred from the target interest area to that other interest area is determined based on the delivery start and end locations in the order information of each historical order.

[0020] The transfer probability of the target interest area to the other interest area is determined based on the order volume transferred from the target interest area to the other interest area, and the order volume transferred from the target interest area to each other interest area.

[0021] Optionally, the score of the target interest area is iteratively determined based on the transfer reward from the initial interest area to the target interest area, the transfer probability from the target interest area to other interest areas, and the scores of the other interest areas already determined. Specifically, this includes:

[0022] The expected future reward of the target interest area is determined based on the transfer probability from the target interest area to other interest areas and the scores of the other interest areas.

[0023] The score of the target interest area is determined based on the transfer reward from the initial interest area to the target interest area, and the expected future reward of the target interest area.

[0024] The initial region of interest and the target region of interest are redefined, and the score of the target region of interest is determined iteratively.

[0025] Optionally, based on the transfer probability of the target interest region to other interest regions and the scores of the determined other interest regions, the expected future reward of the target interest region is determined, specifically including:

[0026] For each other region of interest, the expected future reward for the target region of interest to be transferred to that other region of interest is determined based on the transfer probability from the target region of interest to that other region of interest and the score of that other region of interest.

[0027] The future expected reward of the target interest area is determined based on the future expected reward of the target interest area moving to other interest areas.

[0028] Optionally, the newly determined starting region of interest is the previous target region of interest.

[0029] Optionally, the delivery range of each merchant within the designated area is determined based on the scores of each interest zone, specifically including:

[0030] For each merchant within the designated area, determine the distance between that merchant and each area of ​​interest.

[0031] Based on the distance between the merchant and each interest zone, and the score of each interest zone, the interest zones within the merchant's delivery range are determined.

[0032] The delivery range determination device provided in this manual includes:

[0033] The acquisition module is configured to acquire order information for several historical orders within a specified area;

[0034] The first determining module is configured to determine the starting region of interest and the target region of interest based on the pre-divided regions of interest within the specified area.

[0035] The second determining module is configured to determine the transfer reward from the starting interest area to the target interest area, and the transfer probability from the target interest area to other interest areas, based on the order information of each historical order obtained.

[0036] An iterative module is configured to iteratively determine the score of the target interest area based on the transfer reward from the initial interest area to the target interest area, the transfer probability from the target interest area to each other interest area, and the scores of each other interest area that have been determined.

[0037] The range division module is configured to determine the score of each interest area when a preset iteration stopping condition is met, and to determine the delivery range of each merchant within the specified area based on the score of each interest area. The preset iteration stopping condition includes at least: the number of iterations reaches a first preset threshold; and / or the score difference between two consecutive iterations of each interest area is less than a second preset threshold.

[0038] This specification provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for determining the delivery range.

[0039] This specification provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the above-described method for determining the delivery range.

[0040] The above-described at least one technical solution adopted in the embodiments of this specification can achieve the following beneficial effects:

[0041] In this specification, a starting interest zone and a target interest zone are first determined from pre-divided interest zones within a designated area. Then, based on order information from historical orders within the designated area, the transfer reward for moving from the starting interest zone to the target interest zone, and the transfer probability for moving from the target interest zone to other interest zones, are determined. Based on the determined transfer rewards, transfer probabilities, and scores of other interest zones, the score of the target interest zone is iteratively determined. Finally, when a preset iteration stop condition is met, the delivery range of each merchant within the designated area is determined based on the scores of each interest zone. From a global perspective, based on order information from historical orders within the designated area, each interest zone within the designated area is scored to determine the delivery range of each merchant within the designated area, making the division of delivery ranges more reasonable. Attached Figure Description

[0042] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0043] Figure 1 This is a schematic diagram illustrating the division of delivery areas in existing technologies.

[0044] Figure 2 A flowchart illustrating a method for determining a delivery range provided in an embodiment of this specification;

[0045] Figure 3 A schematic diagram of regions of interest within a designated area provided in the embodiments of this specification;

[0046] Figure 4 This is a schematic diagram of the structure of a delivery range determination device provided in the embodiments of this specification;

[0047] Figure 5 A schematic diagram of an electronic device for implementing the delivery range determination method provided in the embodiments of this specification. Detailed Implementation

[0048] To make the objectives, technical solutions, and advantages of this specification clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments in this specification without creative effort are within the scope of protection of this application.

[0049] Figure 1 This diagram illustrates the division of delivery areas in existing technology. The gray-filled areas represent pre-defined Areas of Interest (AOIs), which can be geographical entities such as business districts, hospitals, and shopping malls. The white circles in the diagram represent the location of merchant A. When determining the delivery area of ​​merchant A, several AOIs within a preset area surrounding the merchant can be selected from the pre-defined AOIs as candidate AOIs. Figure 1 The AOIs within the rectangle centered on Merchant A's location are selected as candidate AOIs.

[0050] Then, for each candidate AOI, the score of the candidate AOI is determined by the following formula (1) based on the order volume of each user with the candidate AOI as the delivery address at the merchant within the preset time period, and the distance between the center of the candidate AOI and the location of merchant A.

[0051]

[0052] Wherein, POI (Point of Interest) represents Merchant A, Order POI×AOI This represents the number of orders generated by Merchant A within this AOI during a preset time period, where α is a constant greater than 1, dist represents the distance between Merchant A's location and the center point of the AOI, and Score... POI×AOI This indicates the score of the candidate AOI for that merchant.

[0053] Finally, based on the scores of each candidate AOI, candidate AOIs with scores exceeding a preset threshold are determined as the merchant's delivery range, such as... Figure 1 The irregular area is enclosed by black lines.

[0054] However, the above method of determining a merchant's delivery range is limited to the distance between the merchant and a single AOI and the number of orders generated within that AOI. It is difficult to combine the order transfer between different AOIs and the delivery routes of delivery capacity to plan the merchant's delivery range from a global perspective.

[0055] For example, suppose Merchant A is located within the first Area of ​​Interest (AOI). Because users in the second AOI place fewer orders with Merchant A, the second AOI is outside Merchant A's delivery range. However, for Merchant B located in the second AOI, users in the first AOI place more orders with Merchant B, therefore the first AOI is within Merchant B's delivery range. From a global perspective, delivery capacity is used to deliver orders across regions from the first AOI to the second AOI, but users in the second AOI cannot place orders with Merchant A, resulting in a poor user experience and indicating an unreasonable overall delivery platform plan.

[0056] This specification provides a method for determining the delivery range. The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0057] Figure 2 This is a flowchart illustrating a method for determining a delivery range provided in an embodiment of this specification, which may specifically include the following steps:

[0058] S100: Retrieve order information for several historical orders within a specified area.

[0059] The delivery range determination method provided in this manual can plan the delivery range of each merchant within a specified area based on order information from historical orders generated within that area. For example, the delivery range of each merchant within the Zhongguancun area of ​​Beijing can be planned based on takeout orders generated last month.

[0060] Therefore, this specification allows access to several historical orders and their order information within a specified area. The order information includes at least the order's delivery start and end locations (delivery origin and destination), and may also include delivery start and end times, average order value, and order revenue.

[0061] To ensure the timeliness of delivery area division, historical orders from the most recent time period can be selected to determine the delivery area division for the next period. For example, when determining the delivery area for each merchant in June, order information from historical orders in May can be selected.

[0062] S102: Determine the starting region of interest and the target region of interest based on the pre-divided regions of interest within the specified area.

[0063] The delivery range determination method provided in this manual can pre-divide a designated area into several interest zones, and score each interest zone based on historical orders generated within that designated area and the transfer of orders between interest zones. The score of an interest zone represents its contribution to the overall order volume.

[0064] Specifically, the designated area can be pre-divided into several Areas of Interest (AOIs), where AOIs can be geographical entities such as business districts, hospitals, and shopping malls. Then, based on the AOIs within the designated area, the starting AOI and the target AOI are determined. The target AOI represents the AOI the delivery vehicle has currently arrived at, i.e., the current "state" of the delivery vehicle. The starting AOI represents the AOI the delivery vehicle most recently arrived at, i.e., the previous "state" of the delivery vehicle. The process of the delivery vehicle traveling from the starting AOI to the target AOI is, the transfer of the delivery vehicle's "state".

[0065] Furthermore, when determining the target AOI from among the AOIs within the specified area, it can be determined randomly or according to a preset AOI transfer order; this specification does not impose any restrictions on this.

[0066] In another embodiment of this specification, the starting AOI may also be randomly selected from the AOIs included in the designated area, that is, the transfer of delivery capacity between the AOIs is not continuous.

[0067] S104: Based on the order information of each historical order obtained, determine the transfer reward from the starting interest area to the target interest area, and the transfer probability from the target interest area to each other interest area.

[0068] In this specification, the score of the target AOI can be determined based on the rewards generated by delivered orders when the delivery capacity is at the target AOI, as well as the rewards that will be generated in the future, i.e., the expected rewards.

[0069] Specifically, based on the delivery start and end locations in the order information of each historical order, the orders transferred from the starting AOI to the target AOI can be determined. Then, based on the order metrics of each order transferred from the starting AOI to the target AOI, the transfer reward for the transfer from the starting AOI to the target AOI can be determined.

[0070] The orders transferred from the originating AOI to the target AOI refer to orders whose delivery origin is at the originating AOI and whose delivery destination is at the target AOI, and are delivered from the originating AOI to the target AOI. These order metrics can include average order value, order revenue, and delivery time metrics, used to evaluate the effectiveness of delivery capacity in completing order deliveries. Specific settings can be configured as needed, and this manual does not impose any restrictions on them.

[0071] When the order metric is the average order value, the transfer reward for transferring from the starting AOI to the target AOI can be determined based on the average order value of each order transferred from the starting AOI to the target AOI, i.e., the average order value.

[0072] Assuming the initial AOI is S1 and the target AOI is S2, the delivery capacity will move the goods from S1 to S2, that is, the "state" will change from S1 to S2. The resulting transfer reward is:

[0073] R(S2)=E[Price(S2|S1)] (1)

[0074] Where Price(S2|S1) represents the average order value of each order delivered from S1 to S2, and R(S2) represents the transfer reward generated from the transfer from S1 to S2, which is the average order value of each order.

[0075] When the order metric is an order revenue metric, the transfer reward from the starting AOI to the target AOI can be determined based on the average order revenue of each order transferred from the starting AOI to the target AOI, i.e., the average order revenue.

[0076] Assuming the initial AOI is S1 and the target AOI is S2, the delivery capacity will move the goods from S1 to S2, that is, the "state" will change from S1 to S2. The resulting transfer reward is:

[0077] R(S2)=E[UE(S2|S1)] (2)

[0078] Where UE(S2|S1) represents the order revenue of each order delivered from S1 to S2, R(S2) represents the transfer reward generated from the transfer from S1 to S2, and is the average order revenue of each order.

[0079] When the order metric is a delivery time metric, the transfer reward for transferring from the starting AOI to the target AOI can be determined based on the average delivery time of all orders transferred from the starting AOI to the target AOI. The shorter the average delivery time for each order, the higher the transfer reward.

[0080] Assuming the initial AOI is S1 and the target AOI is S2, the delivery capacity will move the goods from S1 to S2, that is, the "state" will change from S1 to S2. The resulting transfer reward is:

[0081] R(S2)=-E[T(S2|S1)]+α (3)

[0082] Where T(S2|S1) represents the delivery time of each order from S1 to S2, α is a preset constant, R(S2) represents the transfer reward generated from the transfer from S1 to S2, and is the average delivery time of each order.

[0083] Furthermore, for each other AOI, the order volume transferred from the target AOI to that other AOI is determined based on the delivery start and end locations in the order information of each historical order. Then, based on the order volume transferred from the target AOI to that other AOI and the order volume transferred from the target AOI to each other AOI, the transfer probability of the target AOI to that other AOI is determined.

[0084] As shown in the following formula:

[0085]

[0086] Where Order(S'|S) represents the number of orders transferred from target AOI S to other AOIs' within a preset time period, ∑ all Order(Sn|S) represents the sum of orders transferred from target AOI S' to other AOIsn within the same preset time period.

[0087] For example, assuming the target AOI is S2 and the other AOIs are S1, S3, ..., Sn, then the transition probability from target AOI S2 to other AOI S3 is determined as follows:

[0088]

[0089] Where Order(S3|S2) represents the number of orders transferred from target AOI S2 to other AOIs S3 within a preset time period, ∑ all Order(Sn|S2) represents the sum of orders transferred from target AOI S2 to other AOISn within the same preset time period.

[0090] It should be noted that, since the number of orders transferred between AOIs may be zero within a preset time period, to avoid this situation, the probability formula can be modified using Laplace smoothing:

[0091]

[0092] Where S' represents the target region of interest, and ε represents a preset constant that approaches 0.

[0093] S106: Based on the transfer reward from the starting region of interest to the target region of interest, the transfer probability from the target region of interest to other regions of interest, and the scores of the other regions of interest that have been determined, the score of the target region of interest is determined iteratively.

[0094] The delivery range division method provided in this manual takes into account the movement of delivery personnel (riders, couriers, etc.) within the designated area. It simulates the movement of delivery personnel between different AOIs within the designated area by continuously updating the target AOI, i.e., the continuous transition of their "state". Based on the continuous changes in the "state" of the delivery personnel, the rewards generated by each delivered order when the delivery personnel are in each AOI, as well as the rewards that may be generated in the future, are determined, thus scoring each AOI. The rewards can refer to the sum of the average order value, the sum of the order revenue, etc.

[0095] Specifically, the scores of the other AOIs most recently determined during the iteration process can be determined. Then, based on the transfer probability of the target AOI to each of the other AOIs and the scores of the other AOIs already determined, the future expected reward of the target AOI is determined. Next, based on the transfer reward from the starting AOI to the target AOI and the future expected reward of the target AOI, the score of the target AOI is determined. The starting AOI and target AOI are then re-determined from the AOIs in the specified region, and the score of the target AOI is iteratively determined again using the methods described in steps S104 to S106 above.

[0096] Furthermore, when determining the future expected reward of the target AOI, for each other AOI, the future expected reward of the target AOI to transfer to that other AOI can be determined based on the transfer probability of the target AOI to that other AOI and the score of that other AOI. And based on the future expected rewards of the target AOI to transfer to each other AOI, the future expected reward of the target AOI can be determined.

[0097] Furthermore, when redetermining the starting AOI, the target AOI determined in the previous iteration cycle can be used as the starting AOI in the current iteration cycle, so that delivery capacity can be continuously transferred between AOIs.

[0098] The following formula (6) is the expression for determining the AOI score provided in this specification:

[0099] V(S)=R(S)+γ∑ Sn [P(Sn|S)V(Sn)] (6)

[0100] Where S represents the target AOI, Sn represents other regions of interest, V(S) represents the score of the target AOI, R(S) represents the transfer reward from the initial AOI to the target AOI, γ represents the preset discount factor, P(Sn|S) represents the transfer probability from the target AOI to other AOIs, V(Sn) represents the score of other AOIs, and P(Sn|S)V(Sn) represents the expected future reward for transferring from the target AOI to other AOIs. Sn P(Sn|S)V(Sn) represents the sum of the expected future rewards for the target AOI to be transferred to other AOIs, which is the expected reward of the target AOI.

[0101] It should be noted that the initial score of each AOI is 0, that is, the initial value of V(S) is 0. The scores of other AOIs are also obtained iteratively using the method shown in formula (6).

[0102] S108: When the preset iteration stop condition is met, determine the score of each region of interest, and determine the delivery range of each merchant in the specified area based on the score of each region of interest.

[0103] In this specification, by continuously simulating the "state" transitions between each AOI in the designated area, the score of each AOI is determined when the overall reward of each AOI in the designated area is maximized, and the delivery range of the merchant is divided based on the score of each AOI.

[0104] Specifically, to maximize the overall reward within the delivery area, the iteration stopping condition can be set to at least one of the following: the number of iterations reaches a first preset threshold, or the score difference between two consecutive iterations of each AOI is less than a second preset threshold. Here, "the score difference between two consecutive iterations of each AOI is less than the second preset threshold" means that the difference between two scores for the same AOI is small, indicating that the reward generated within that AOI has reached its maximum. Both the first and second preset thresholds can be set as needed.

[0105] Therefore, when the above iteration stopping condition is met, the final score of each AOI iteration is determined. The AOI score represents the contribution of orders generated within that AOI to the overall performance. Finally, based on the scores of each AOI, the delivery range of each merchant within the specified area is determined.

[0106] Furthermore, in one embodiment of this specification, when determining the delivery range of each merchant, the distance between each merchant and each AOI is determined for each merchant within the designated area. Based on the distance between the merchant and each AOI and the score of each AOI, each AOI belonging to the merchant's delivery range is determined. The closer the distance between the merchant and the AOI, and the higher the AOI's score, the greater the probability that the AOI belongs to the merchant's delivery range.

[0107] based on Figure 2 The method for determining delivery range, as shown, first identifies the starting interest area (AOI) and the target interest area (AOI) from pre-divided interest areas within a designated area. Then, based on order information from historical orders within the designated area, it determines the transfer reward for moving from the starting AOI to the target AOI, as well as the transfer probability for moving from the target AOI to other interest areas. Based on the determined transfer rewards, transfer probabilities, and scores of other interest areas, iteratively determines the score of the target AOI. Finally, when a preset iteration stopping condition is met, the delivery range for each merchant within the designated area is determined based on the scores of each interest area. This method scores each interest area within the designated area from a global perspective, making the scoring more meaningful. Furthermore, based on the scores of each AOI obtained from this global perspective, the delivery range for merchants is divided, resulting in a more reasonable division of delivery ranges and maximizing rewards across the entire area.

[0108] Assuming the specified area is as follows Figure 3 As shown, S1 to S4 represent the pre-divided AOIs in the specified area. Assume that after several iterations, the scores of each AOI are V(S1) = F1, V(S2) = F2, V(S3) = F3, and V(S4) = F4, respectively.

[0109] If the starting AOI is randomly selected from each AOI as S1 and the target AOI is S2, in the first preset period of historical orders, there are 5 orders transferred from S1 to S2, with an average order value of 50. In the second preset period after the first preset period, there are 10 orders transferred from S2 to S3, 8 orders transferred from S2 to S4, and 2 orders transferred from S2 to S1.

[0110] Then, the transfer reward generated from the transfer from S1 to S2 can be determined by the above formula (1) as R(S2) = 50.

[0111] Then, using the above formula (4), the transition probabilities from S2 to S1, S3, and S4 can be determined as follows:

[0112]

[0113]

[0114]

[0115] The score of the target AOI is determined using the above formula (6):

[0116]

[0117] Then, the starting AOI and target AOI are re-determined from each AOI, and the score of the target AOI is determined iteratively until the preset iteration stopping condition is met.

[0118] based on Figure 2 The present invention provides a method for determining the delivery range, and also provides a corresponding structural diagram of a device for determining the delivery range, as illustrated in the embodiments of this specification. Figure 4 As shown.

[0119] Figure 4 A schematic diagram of a delivery range determination device provided in the embodiments of this specification includes:

[0120] The acquisition module 200 is configured to acquire order information of several historical orders within a specified area;

[0121] The first determining module 202 is configured to determine the starting interest region and the target interest region based on each interest region pre-divided within the specified area.

[0122] The second determining module 204 is configured to determine the transfer reward from the starting interest area to the target interest area and the transfer probability from the target interest area to other interest areas based on the order information of each historical order obtained.

[0123] Iteration module 206 is configured to iteratively determine the score of the target interest area based on the transfer reward from the starting interest area to the target interest area, the transfer probability from the target interest area to each other interest area, and the scores of each other interest area that have been determined.

[0124] The range division module 208 is configured to determine the score of each interest area when a preset iteration stopping condition is met, and to determine the delivery range of each merchant in the specified area based on the score of each interest area. The preset iteration stopping condition includes at least: the number of iterations reaches a first preset threshold; and / or the score difference between two consecutive iterations of each interest area is less than a second preset threshold.

[0125] Optionally, the second determining module 204 is specifically used to determine each order transferred from the starting interest area to the target interest area based on the delivery start and end locations in the order information of each historical order, and to determine the transfer reward for the transfer from the starting interest area to the target interest area based on the order indicators of each order transferred from the starting interest area to the target interest area, wherein the order indicators include at least one of the following: average order value indicator, order revenue indicator, and delivery time indicator.

[0126] Optionally, the second determining module 204 is specifically used to, for each other interest area, determine the number of orders transferred from the target interest area to the other interest area based on the delivery start and end locations in the order information of each historical order, and determine the transfer probability of the target interest area to the other interest area based on the number of orders transferred from the target interest area to the other interest area and the number of orders transferred from the target interest area to each other interest area.

[0127] Optionally, the iteration module 206 is specifically used to: determine the future expected reward of the target interest region based on the transfer probability of the target interest region to other interest regions and the scores of the other interest regions that have been determined; determine the score of the target interest region based on the transfer reward from the starting interest region to the target interest region and the future expected reward of the target interest region; redetermine the starting interest region and the target interest region; and iteratively determine the score of the target interest region.

[0128] Optionally, the iteration module 206 is specifically used to, for each other region of interest, determine the future expected reward of the target region of interest moving to that other region of interest based on the transfer probability of the target region of interest moving to that other region of interest and the score of that other region of interest, and determine the future expected reward of the target region of interest based on the future expected reward of the target region of interest moving to each other region of interest.

[0129] Optionally, the newly determined starting region of interest is the previous target region of interest.

[0130] Optionally, the range division module 208 is specifically used to determine the distance between each merchant and each interest area for each merchant in the specified area, and to determine each interest area belonging to the merchant's delivery range based on the distance between the merchant and each interest area and the score of each interest area.

[0131] This specification also provides a computer-readable storage medium storing a computer program that can be used to execute the above-described embodiments. Figure 2 Any of the provided methods for determining the delivery area.

[0132] based on Figure 2 The method for determining the delivery range shown in this specification also includes embodiments that propose... Figure 5 The diagram shows a schematic structural representation of the electronic device. Figure 5 At the hardware level, the electronic device includes a processor, internal bus, network interface, memory, and non-volatile storage, and may also include other hardware required for the business. The processor reads the corresponding computer program from the non-volatile storage into memory and then runs it to implement any of the above-mentioned delivery range determination methods.

[0133] Of course, in addition to software implementation, this specification does not exclude other implementation methods, such as logic devices or a combination of hardware and software. In other words, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0134] In the 1990s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the methodology). However, with technological advancements, many methodological improvements today can be considered direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved methodology into the hardware circuit. Therefore, it cannot be said that a methodological improvement cannot be implemented using hardware physical modules. For example, a Programmable Logic Device (PLD) (e.g., a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user programming the device. Designers can program and "integrate" a digital system onto a PLD themselves, without needing chip manufacturers to design and manufacture dedicated integrated circuit chips. Moreover, nowadays, instead of manually generating integrated circuit chips, this programming is mostly implemented using "logic compiler" software. Similar to the software compiler used in program development, the original code before compilation must be written in a specific programming language, called a Hardware Description Language (HDL). There are many HDLs, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, and RHDL (Ruby Hardware Description Language). Currently, the most commonly used are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also understand that by simply performing some logic programming on the method flow using one of these hardware description languages ​​and programming it into an integrated circuit, the hardware circuit implementing the logical method flow can be easily obtained.

[0135] The controller can be implemented in any suitable manner. For example, it can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicon Labs C8051F320. A memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also recognize that, in addition to implementing the controller in purely computer-readable program code form, the same functionality can be achieved by logically programming the method steps to make the controller take the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the means included therein for implementing various functions can also be considered as structures within the hardware component. Alternatively, the means for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0136] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0137] For ease of description, the above devices are described in terms of function, divided into various units. Of course, in implementing this specification, the functions of each unit can be implemented in one or more software and / or hardware components.

[0138] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0139] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0140] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0141] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0142] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0143] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0144] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0145] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0146] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, this specification may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this specification may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0147] This specification can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This specification can also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0148] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0149] The above description is merely an embodiment of this specification and is not intended to limit this specification. Various modifications and variations can be made to this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this specification should be included within the scope of the claims of this specification.

Claims

1. A method for determining delivery range, characterized in that, include: Retrieve order information for several historical orders within a specified area; Based on the pre-divided regions of interest within the specified area, determine the starting region of interest and the target region of interest; Based on the delivery start and end locations in the order information of each historical order, determine each order that was transferred from the starting area of ​​interest to the target area of ​​interest; Based on the order metrics of each order transferred from the starting area of ​​interest to the target area of ​​interest, the transfer reward for the transfer from the starting area of ​​interest to the target area of ​​interest is determined. The order metrics include at least one of the following: average order value, order revenue, and delivery time. For each other interest area, the number of orders transferred from the target interest area to that other interest area is determined based on the delivery start and end locations in the order information of each historical order. The transfer probability of the target interest area to the other interest area is determined based on the order volume transferred from the target interest area to the other interest area, and the order volume transferred from the target interest area to each other interest area. The expected future reward of the target interest area is determined based on the transfer probability from the target interest area to other interest areas and the scores of the other interest areas. The score of the target interest area is determined based on the transfer reward from the initial interest area to the target interest area, and the expected future reward of the target interest area. The initial region of interest and the target region of interest are redefined, and the score of the target region of interest is iteratively determined. The initial score for each region of interest is 0. When the preset iteration stopping condition is met, the score of each region of interest is determined; For each merchant within the designated area, determine the distance between that merchant and each area of ​​interest. Based on the distance between the merchant and each interest zone, and the score of each interest zone, the interest zones within the merchant's delivery range are determined. The preset iteration stopping condition includes at least the following: The number of iterations reaches a first preset threshold; And / or the score difference between two consecutive iterations of each region of interest is less than the second preset threshold.

2. The method as described in claim 1, characterized in that, Based on the transfer probability from the target region of interest to other regions of interest, and the scores of the other regions of interest, the expected future reward of the target region of interest is determined, including: The scores of each other interest region are multiplied by the transfer probability of the target interest region to each other interest region, and the results are summed to determine the future expected reward of the target interest region.

3. The method as described in claim 1, characterized in that, Redetermining the initial region of interest and the target region of interest includes: The target region of interest identified this time will be designated as the starting region of interest for the next time. The target region of interest for the next time is determined based on the starting region of interest for the next time and the order information of historical orders.

4. A delivery range determination device, characterized in that, include: The acquisition module is configured to acquire order information for several historical orders within a specified area; The first determining module is configured to determine the starting region of interest and the target region of interest based on the pre-divided regions of interest within the specified area. The second determining module is configured to determine each order that has been transferred from the starting area of ​​interest to the target area of ​​interest based on the delivery start and end locations in the order information of each historical order. Based on the order metrics of each order transferred from the starting area of ​​interest to the target area of ​​interest, the transfer reward for the transfer from the starting area of ​​interest to the target area of ​​interest is determined. The order metrics include at least one of the following: average order value, order revenue, and delivery time. The transfer probability determination module is configured to determine the number of orders transferred from the target area of ​​interest to the other area of ​​interest for each other area of ​​interest, based on the delivery start and end locations in the order information of each historical order. The transfer probability of the target interest area to the other interest area is determined based on the order volume transferred from the target interest area to the other interest area, and the order volume transferred from the target interest area to each other interest area. An iterative module is configured to determine the future expected reward of the target interest region based on the transfer probability of the target interest region to other interest regions and the scores of the other interest regions that have been determined. The score of the target interest area is determined based on the transfer reward from the initial interest area to the target interest area, and the expected future reward of the target interest area. The initial region of interest and the target region of interest are redefined, and the score of the target region of interest is iteratively determined. The initial score for each region of interest is 0. The range division module is configured to determine the score of each region of interest when a preset iteration stopping condition is met. For each merchant within the designated area, determine the distance between that merchant and each area of ​​interest. Based on the distance between the merchant and each interest zone, and the score of each interest zone, the interest zones within the merchant's delivery range are determined. The preset iteration stopping condition includes at least the following: The number of iterations reaches a first preset threshold; And / or the score difference between two consecutive iterations of each region of interest is less than the second preset threshold.

5. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the method described in any one of claims 1 to 3.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method described in any one of claims 1 to 3.

Images