WO2020199642A1

WO2020199642A1 - Method and device for route planning

Info

Publication number: WO2020199642A1
Application number: PCT/CN2019/124296
Authority: WO
Inventors: 张嘉琦; 王圣尧
Original assignee: 北京三快在线科技有限公司
Priority date: 2019-03-29
Filing date: 2019-12-10
Publication date: 2020-10-08
Also published as: CN111754151A

Abstract

A method and device for route planning. When an order to be assigned is present, determined, on the basis of a relative location corresponding to the order to be assigned, of the locations of deliverers in a deliverer set, and of relative locations corresponding to orders to be delivered by the deliverers in the deliverer set, are the degrees of fit between the deliverers in the deliverer set and the order to be assigned, and some of the deliverers are filtered on the basis of the determined degrees of fit for route planning. This effectively reduces the computational load brought to an online system when a new order is received.

Description

Method and device for path planning

Technical field

This application relates to the field of Internet technology, and in particular to a path planning method and device.

Background technique

With the rapid development of Internet technology, many services can be conducted online, which brings convenience to users. Some businesses that were originally carried out offline have been fully supported by online businesses, thereby improving efficiency and user experience, such as food delivery and small items flash delivery. When users use this kind of physical delivery service, they usually place an order on the corresponding mobile phone application, and specify the items to be delivered and their pickup location and delivery location. After the user successfully places the order, the online system will dispatch the order to a certain delivery person, and the delivery person can deliver it to the door or pick it up.

In related technologies, after the online system receives a new order from a user, it first regards the new order as a pending order to be assigned to the delivery staff, and then uses a preset path planning algorithm to determine all current orders (including all current orders). The orders to be distributed and the orders to be distributed that have been assigned to the distributors) and all distributors re-plan the route. Obviously, according to this path planning scheme, every new order received will bring a greater computational burden to the online system.

Summary of the invention

The embodiments of this specification provide a path planning method and device, which are used to reduce the computational burden of receiving new orders on the online system.

The route planning method provided in this manual includes: determining the relevant position corresponding to the order to be distributed; determining the set of dispatchers according to preset rules; for each dispatcher in the set of dispatchers, obtaining the position of the dispatcher, And the relevant position corresponding to the order to be delivered of each dispatcher; for each dispatcher in the set of dispatchers, according to the relevant position corresponding to the order to be allocated, the position of the dispatcher, and the dispatcher's pending order Corresponding relative position, determine the degree of matching between the dispatcher and the order to be allocated; according to the degree of matching, each dispatcher in the dispatcher set and the order to be allocated is selected from the dispatcher set A delivery person who meets a preset condition; according to a preset path planning algorithm, path planning is performed on the order to be distributed and the selected delivery person.

Optionally, the relevant location includes at least one of a pickup location and a delivery location. Correspondingly, the determining the degree of matching between the dispatcher and the order to be allocated includes: determining the first degree of matching between the dispatcher and the pickup location of the order to be allocated; determining the degree of matching between the dispatcher and the order to be allocated The second matching degree of the delivery location of the order; according to the first matching degree and the second matching degree, the matching degree between the delivery person and the order to be allocated is determined.

Optionally, determining the degree of matching between the dispatcher and the order to be dispatched according to the relevant position corresponding to the order to be allocated, the position of the dispatcher, and the relevant position corresponding to the dispatcher's order to be dispatched includes: The location of the delivery clerk and the relative location corresponding to the delivery order of the delivery clerk, determine the neighborhood range of the delivery clerk; determine the delivery clerk based on the neighborhood area of the delivery clerk and the relevant location corresponding to the order to be distributed The degree of matching with the order to be allocated.

Optionally, according to the location of the delivery person and the relevant position corresponding to the order to be delivered by the delivery person, determining the neighborhood range of the delivery person includes: taking the location of the delivery person as the regional center to determine a coverage area of a specified size ; Among the relevant positions corresponding to all pending orders of the delivery person, obtain the relevant positions that fall within the coverage area but have not been processed; determine the average coordinates of the obtained relevant positions as the new regional center, according to the determination The new regional center continues to determine the coverage area of the specified size until all the relevant positions of the delivery personnel's pending orders have been processed, and all the determined coverage areas are determined as the neighborhood area of the distributor.

Optionally, determining the degree of matching between the dispatcher and the order to be allocated according to the neighborhood range of the dispatcher and the relevant position corresponding to the order to be allocated includes: determining whether the relevant position corresponding to the order to be allocated is Within the neighborhood of the dispatcher; if it is, it is determined that the matching degree between the dispatcher and the order to be allocated is the preset maximum matching degree; otherwise, according to the relative position corresponding to the order to be allocated and the delivery The relevant position corresponding to the order to be delivered of the dispatcher determines the degree of matching between the dispatcher and the order to be dispatched.

Optionally, determining the degree of matching between the dispatcher and the order to be dispatched according to the relevant position corresponding to the order to be allocated and the relevant position corresponding to the order to be dispatched by the dispatcher includes: determining the order to be dispatched The minimum distance between the corresponding relevant position and the relevant position corresponding to the order to be dispatched by the dispatcher, and the first item of matching degree between the dispatcher and the order to be dispatched is determined according to the minimum distance, wherein the minimum The distance is negatively related to the first item of the matching degree; and/or the first direction from the position of the delivery person to the relevant position corresponding to the order to be allocated, and the distance from the position of the delivery person to the delivery person The second direction of the relevant position corresponding to the order to be delivered is determined according to the angle between the first direction and the second direction, and the second item of the degree of matching between the delivery person and the order to be allocated is determined, wherein the The included angle is negatively related to the second term of the matching degree.

Optionally, determining the first item of the degree of matching between the delivery person and the order to be allocated according to the minimum distance specifically includes: if the minimum distance is less than a preset distance threshold, determining that the delivery person is with the waiting order The matching degree of the allocated order is the maximum matching degree.

Optionally, the delivery person meeting the preset conditions specifically includes any one or more of the following: the degree of matching between the delivery person and the order to be allocated is higher than a preset threshold; according to each of the delivery person set The matching degree between the dispatcher and the order to be distributed is from high to low, the matching degree between the dispatcher and the order to be allocated is within a specified range; the current number of the dispatcher's pending orders is less than The preset quantity.

Optionally, the preset rule includes any one or more of the following: determine the dispatcher currently located in the area where the order to be allocated belongs to be a member of the set of dispatchers; and be responsible for the order to be allocated The delivery personnel in the area of which are determined to be members of the delivery personnel set; the current delivery personnel who are willing to continue to take orders are determined to be members of the delivery personnel set.

The route planning device provided in this specification includes: a first determining module, used to determine the relevant position corresponding to the order to be allocated; an acquisition module, used to determine the set of delivery personnel according to preset rules, and to target the set of delivery personnel Each dispatcher in, obtains the position of the dispatcher and the relevant position corresponding to the dispatcher’s pending order; the second determining module, for each dispatcher in the dispatcher set, corresponds to the order to be assigned The relevant position of the dispatcher, the position of the dispatcher, and the relevant position corresponding to the dispatcher’s order to be dispatched are determined to determine the degree of matching between the dispatcher and the order to be dispatched; According to the matching degree between the dispatcher and the order to be allocated, the dispatcher who meets the preset conditions is selected from the set of dispatchers; the path planning module, according to the preset path planning algorithm, selects the order to be allocated and the filter The outgoing delivery staff will plan the route.

This specification provides a computer-readable storage medium, where the storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned path planning method is implemented.

An electronic device provided in this specification includes a memory, a processor, and a computer program that is stored in the memory and can run on the processor, and the processor implements the above-mentioned path planning method when the program is executed.

The above-mentioned at least one technical solution adopted in the embodiment of this specification can achieve the following beneficial effects: When there is an order to be allocated, the relevant position corresponding to the order to be allocated, the location of each delivery person, and the relevant correlation corresponding to the order to be delivered by each delivery person Location, determine the respective matching degree of each delivery staff and the order to be assigned, and only screen out a part of the delivery staff according to the matching degree for subsequent path planning, instead of re-planning all the delivery staff, it can be seen that this manual provides The solution helps to reduce the computational burden on the online system when new orders are received.

Description of the drawings

The drawings described here are used to provide a further understanding of the application and constitute a part of the application. The exemplary embodiments and descriptions of the application are used to explain the application and do not constitute an improper limitation of the application. In the attached picture:

FIG. 1 is a schematic flowchart of a path planning method provided by an embodiment of this specification;

FIG. 2 is an exemplary schematic diagram of the principle of determining the neighborhood range of a distributor provided by an embodiment of this specification;

FIG. 3 is an exemplary schematic diagram of a principle for determining a second direction provided by an embodiment of this specification;

4 is a schematic structural diagram of a path planning device provided by an embodiment of this specification;

FIG. 5 is a schematic structural diagram of the electronic device corresponding to FIG. 1 provided in an embodiment of the specification.

detailed description

In order to make the purpose, technical solutions, and advantages of this specification clearer, the technical solutions of this application will be described clearly and completely below in conjunction with specific embodiments of this specification and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the specification, all other embodiments obtained by a person of ordinary skill in the art without creative work shall fall within the protection scope of this application.

The technical solutions provided by the embodiments of the present application will be described in detail below with reference to the accompanying drawings.

The solution of the present application first uses a relatively simple rough evaluation method to effectively use the matching degree between the dispatcher and the order to be delivered, and screen out the combination of the dispatcher with a relatively low matching degree and the order to be allocated. Accurate path planning is only carried out for the combination of relatively high matching delivery personnel and orders to be distributed, instead of accurate path planning for all possible combinations of delivery personnel and orders to be distributed, thereby helping to reduce the risk of receiving The computational burden on the online system when new orders are placed. The solution of this application will be described in detail below.

Fig. 1 is a schematic flow chart of a path planning method provided by an embodiment of this specification. For example, the process is executed by an online system and may specifically include the following steps:

S100: Determine the relevant position corresponding to the order to be allocated.

In the embodiments of the present specification, the new orders mentioned in the background art generally include orders to be allocated to a delivery person for delivery, that is, orders to be allocated. The following embodiments mainly take this situation as an example. In practical applications, it may also be allowed to reallocate orders that have been assigned to a delivery person but the delivery person has not yet started to deliver, that is, pending delivery orders, to other delivery employees. In this case, the new order may also include such pending orders, and reset such pending orders to pending distribution orders. The execution of the process in Figure 1 can be triggered every time one or more new orders are received.

In the embodiments of this specification, the relevant location generally includes at least one of the pick-up location and the delivery location. The following embodiments mainly take this situation as an example for description. For ease of description, the relevant position in this case is referred to as the taking position. Take takeaway delivery as an example. The pending order can include a new takeaway order initiated by the user to the online system. The pickup location is the location of the restaurant responsible for making the takeaway; the delivery location is the location where the user expects the takeaway to be delivered. , Generally the location of the user, for example, the user’s home or the user’s company. Related locations may also include locations other than the pickup location and the delivery location, such as the address of the delivery person. The relevant location can be expressed as coordinates in the electronic map.

S102: Determine a set of dispatchers, and for each dispatcher in the set of dispatchers, obtain the position of the dispatcher and the relevant position corresponding to the order to be dispatched by the dispatcher.

In the embodiment of this specification, the set of delivery personnel may be determined according to a preset rule. For example, a collection of multiple dispatchers currently located in the area to which an order is to be allocated (for example, a certain district in a city, a certain residential area, a certain street, etc.), or a collection of multiple dispatchers responsible for the area. For another example, there is currently a collection of multiple delivery personnel willing to continue to take orders; and so on.

In the embodiment of this specification, the location of the delivery person preferably refers to the current real-time location of the delivery person. Since the delivery person is usually on the move most of the time and the position changes frequently, the real-time accuracy requirements for the delivery person's position can be required according to the actual situation. In addition, the location of the delivery person is generally reported by the delivery person's mobile phone.

In the embodiment of this specification, the order to be delivered may refer to an order currently being delivered by a delivery person or an order that has been allocated but has not yet been delivered. The solution of this application mainly considers the situation that the delivery staff currently has at least one pending delivery order.

Of course, you can also consider assigning the pending orders to the delivery staff who currently do not have a pending order. However, for how to allocate orders in this case, those skilled in the art can refer to any well-known related technology, and therefore only a brief description is given here.

S104: For each delivery person in the delivery person set, determine the delivery person and the delivery person according to the relevant position corresponding to the order to be allocated, the location of the delivery person, and the relevant position corresponding to the order to be delivered by the delivery person. Describe the matching degree of the order to be allocated.

By observing and analyzing the distribution results of a large number of historical orders, it is concluded that the delivery personnel with a better matching degree and the orders to be assigned often have the following characteristics: the pick-up location of the pending orders and the delivery location of the delivery staff's pending orders Coincident or similar (that is, the distance is small, for example, less than 100 meters or only a few hundred meters away); the delivery position of the order to be allocated is in the travel direction of the delivery person, and the direction deviation is small.

Based on the above characteristics, we can consider whether the combination of the delivery person and the order to be allocated is appropriate from the two aspects of the distance relationship and the direction relationship. Among them, the distance relationship can indicate the distance between the pick-up location of the order to be allocated and the real-time location and possible future locations of the dispatcher, and the direction relationship can indicate the degree of deviation between the pick-up location of the order to be allocated and the forward direction of the dispatcher. Especially in the case where the delivery person is already carrying an order to be delivered, it is necessary to consider the distance relationship and the direction relationship between the pickup location of the order to be delivered and the pickup location of the order to be allocated. The degree of matching between the dispatcher and the order to be allocated can be calculated through intuitive mathematical formulas. For example, different terms can be used in the formula to calculate the influence of distance and direction on the matching degree, and the corresponding terms or key parts of the terms can be called distance factors and direction factors. Among them, different items can be given different weights to directly adjust the degree of influence of the distance factor and direction factor. Of course, the distance factor and direction factor can also be combined in the same term. The formula used to calculate the matching degree can be diverse, as long as it conforms to the idea of the solution of this application, and an example will be described later.

In the embodiment of this specification, the matching degree can be represented by a preset variable. The relationship between the value of the variable and the matching degree is not specifically limited, but depends on how the user prescribes it. For example, it can be specified that the smaller the value of the variable, the higher the matching degree; of course, the reverse is also possible.

S106: According to the degree of matching between each delivery person in the delivery person set and the order to be allocated, filter out the delivery person meeting preset conditions from the delivery person set.

In the embodiments of this specification, the preset conditions may be various. For example, the matching degree between the dispatcher and the order to be allocated is higher than the preset threshold; for another example, according to the order of the matching degree between the dispatcher and the order to be allocated, the matching degree between the dispatcher and the order to be allocated is in the specified range ( For example, the top 50%, or the top 50, etc.); etc.

In the embodiment of this specification, the dispatchers are screened according to the matching degree between the dispatcher and the order to be allocated, that is, the combination of the dispatcher with a relatively suitable matching degree and the order to be allocated is selected. In the selected combination, each dispatcher can match multiple orders to be allocated at the same time, and each order to be allocated can also be matched with multiple dispatchers at the same time. Later, path planning will be performed on these selected combinations, so that the overall matching result can be finally obtained. In other words, it can initially contain a lot of combinations of different dispatchers and orders to be allocated, and a part of the combinations deemed relatively suitable can be screened out through preset conditions, which may also be referred to as candidate combinations below.

S108: Perform path planning on the order to be allocated and the selected delivery personnel according to the preset path planning algorithm.

In the embodiment of the present specification, the screening in step S106 is coarse screening, and more precise path planning can be further performed based on the coarse screening results, that is, fine screening is performed to obtain the final order allocation result.

Through the method shown in Figure 1, when there is an order to be allocated, according to the relevant position corresponding to the order to be allocated, the position of each dispatcher in the set of dispatchers, and the relevant position of each dispatcher's order to be dispatched, each dispatcher and the dispatcher are determined The matching degree of the order, and according to the matching degree, select a part of the delivery staff for subsequent path planning, instead of re-planning all the delivery staff in the delivery staff set, it can effectively reduce the burden on the online system when new orders are received. Computational burden.

Based on the method in FIG. 1, the embodiments of this specification also provide other specific implementation methods and extension schemes of the method, which will be described below.

The relevant position was explained earlier. When determining the matching degree, generally only the pickup location or delivery location can be considered to improve the efficiency of the algorithm. However, after all, the delivery person has to go to both the pickup location and the delivery location. In order to obtain a more reasonable dispatch result, the pickup location and the delivery location can be fully considered when determining the matching degree. It can be considered separately and then integrated, or it can be considered comprehensively from the beginning. Take the previous method as an example. For example, you can determine the first matching degree between the delivery person and the pickup location of the order to be allocated, and determine the second matching degree between the delivery person and the delivery location of the order to be allocated, and then according to the first The matching degree and the second matching degree determine the matching degree of the delivery person with the order to be allocated.

When determining the matching degree, whether only one of the pick-up location and the delivery location is considered, or both, is not limited here, and there may be multiple specific implementation manners. For example, whether it is to determine the first degree of matching between the delivery person and the pickup location of the order to be allocated, or the second degree of matching between the delivery person and the delivery location of the order to be allocated, the pickup of the delivery person’s order to be delivered can be considered. Goods location and delivery location. For another example, when determining the degree of matching between the delivery person and the pickup location of the order to be distributed, the pickup location of the delivery person’s order to be delivered can be considered accordingly, regardless of the delivery person’s order to be delivered. When determining the second degree of matching between the delivery person and the delivery location of the order to be distributed, the delivery location of the delivery person’s order to be delivered is considered accordingly, regardless of the delivery person’s order to be delivered. Goods location.

The separately determined matching degrees can adopt differentiated formulas, or adopt differentiated formula parameter values. For example, when determining the first degree of matching between the delivery person and the pick-up location of the order to be assigned, the influence of distance can be more considered, and the distance factor can be given a relatively high weight. For another example, when determining the matching degree between the delivery person and the delivery location of the order to be assigned, more consideration can be given to the influence of direction, and the direction factor is given a relatively high weight.

In the embodiment of this specification, the concept of the neighborhood range of the dispatcher is used, and the degree of matching between the dispatcher and the order to be allocated is determined based on the neighborhood range. The pick-up location can be conveniently divided into two categories: within the neighborhood of the delivery person and not within the neighborhood of the delivery person. Approximate processing of the same type of situation is helpful to simplify the algorithm.

The neighborhood here refers to an area near the delivery person. For example, a circular area with the location of the delivery person as the center and a fixed distance as the radius may be determined as the neighborhood area of the delivery person. For another example, the location of the delivery person and the average coordinates of the delivery locations of all pending orders of the delivery person can be obtained; then, the average coordinates can be taken as the center of the circle and can cover the location of the delivery person and the delivery person The smallest circular area of the pickup position of all pending orders is determined as the neighborhood area of the delivery person.

In the embodiment of this specification, the neighborhood area of the delivery person can be determined according to the delivery person’s location and the delivery location of the delivery person’s order to be delivered, and then according to the delivery person’s neighborhood area and the order to be allocated. Delivery location to determine the degree of match between the delivery person and the order to be allocated. For example, the neighborhood range of the delivery person can be determined according to the location of the delivery person and the distance relationship and direction relationship between the delivery position of the delivery person's order to be delivered. The second example in the previous paragraph adopts this idea. In addition, the embodiment of this specification also provides a neighborhood range determination solution that has achieved good results in practice, which is described in detail below.

For example, the location of the delivery person can be used as the regional center to determine a coverage area of a specified size, and among all the relevant locations corresponding to the delivery person's pending orders, the relevant locations that fall within the coverage area but have not been processed are obtained , And determine the obtained average coordinates of the relevant position as the new area center; then, continue to determine the new coverage area of the specified size according to the determined new area center, and determine the new area center again based on the new coverage area. According to this, the determination of the coverage area and the regional center is repeated (multiple rounds may be carried out) until the relevant positions of all pending orders of the dispatcher have been processed. Finally, all the determined coverage areas are determined as the neighborhood range of the distributor. The shape of the coverage area can be various, such as circle, triangle, square, honeycomb, etc. The specified size is not easy to be too large, generally a few hundred meters to a few kilometers.

This specification also provides an exemplary schematic diagram of the principle of determining the neighborhood range of a distributor, as shown in FIG. 2.

In Figure 2, points 1 to 6 (marked with small circles) are the pickup positions of all orders to be delivered by the delivery staff. The shape of the coverage area is circular. The size of the coverage area determined each time is the same, for example, the radius is 300 meters. Each time, the average coordinates of the unprocessed pick-up locations (that is, the newly-added pick-up locations this time) that fall into the coverage area corresponding to all the pending orders of the delivery staff are determined as the new area center. The centers of the successively determined circular coverage areas are respectively marked as points A, B, C, and D (marked with a five-pointed star). The process of determining the neighborhood range of the delivery person is as follows: the location of the delivery person is point A, with point A as the center and 300 meters as the radius, determine the first circular coverage area, and the delivery person covers the first circle The pick-up position in the area includes points 1 and 2. Among them, points 1 and 2 have not been processed. The average coordinates of points 1 and 2 are calculated as point B; with point B as the center and 300 meters as the radius, determine the second Circular coverage area. The delivery position of the delivery person in the second circular coverage area includes points 1, 2, and 3. Among them, point 3 is the newly added delivery location, and its average coordinates are point 3 itself, Namely point C; with point C as the center and 300 meters as the radius, determine the third circular coverage area. The delivery position of the delivery person in the third circular coverage area includes

points

2, 3, 4, and 5. , 6, where

points

4, 5, and 6 are newly added delivery locations, and their average coordinates are point D; with point D as the center and 300 meters as the radius, determine the fourth circular coverage area, where the delivery person is The pick-up locations in the fourth circular coverage area include

points

3, 4, 5, and 6. There is no new pick-up location, that is, all pick-up locations of the delivery staff have been processed, and the above are determined in turn The sum of the four circular coverage areas is determined as the neighborhood area of the dispatcher.

In the embodiment of this specification, after determining the neighborhood range of the delivery person, the matching degree can be determined in the following manner. First, determine whether the relevant position corresponding to the order to be allocated is within the neighborhood of the dispatcher.

If the relevant position corresponding to the order to be allocated is within the neighborhood of the dispatcher, it can be considered that the cost of the dispatcher to deliver the order to be allocated is not too high, even if the order to be allocated is directly allocated to the dispatcher, it is reasonable . In other words, it can be considered that the dispatcher matches the order to be allocated, and the matching degree between the dispatcher and the order to be allocated may be determined as the preset maximum matching degree, or another matching degree high enough to be screened out. In this way, the influence of distance and direction can be ignored or no longer considered too carefully, which helps to reduce the computational complexity of the algorithm.

If the relevant position corresponding to the order to be allocated is not within the neighborhood of the dispatcher, the relevant position of the dispatcher and the dispatcher's order to be dispatched can be determined according to the relevant position corresponding to the order to be allocated suitability. For example, the minimum distance between the relevant position corresponding to the order to be distributed and the relevant position corresponding to the order to be distributed can be determined, and the first item of the matching degree between the dispatcher and the order to be distributed can be determined according to the minimum distance. Wherein, the minimum distance is negatively related to the first term of the matching degree. In practical applications, the minimum distance can also be replaced with the average distance. For another example, it is possible to determine the first direction from the position of the dispatcher to the relevant position corresponding to the order to be distributed, and the second direction from the position of the dispatcher to the relevant position corresponding to the order to be dispatched by the dispatcher (reflecting The overall trend of the delivery person's next itinerary), and the second item of matching degree between the delivery person and the order to be allocated is determined according to the angle between the first direction and the second direction. Wherein, the included angle is negatively related to the second term of the matching degree. Then, according to the first item of the matching degree and/or the second item of the matching degree, the degree of matching between the dispatcher and the order to be allocated can be determined. It should be noted that the negative correlation mentioned here can specifically mean that the relationship is generally negative (generally, the smaller the distance, the closer the distance, the higher the matching degree; the smaller the angle, the greater the degree of deviation Smaller, higher matching degree), but does not necessarily require strict negative correlation within the entire continuous range of values. In addition, the included angle can be expressed in degrees or radians.

Both the first direction and the second direction may include multiple specific directions. In actual calculations, the first direction and the second direction may use one of the multiple specific directions or a comprehensive measure of the multiple specific directions (for example, the average direction, or the most deviated direction). Said.

Assuming that the average direction is taken to represent the second direction, refer to FIG. 3, which is an exemplary schematic diagram of the principle of determining the second direction provided by an embodiment of this specification. In Figure 3, point A is the location of the delivery person, points 7 and 8 are the delivery positions of the delivery person’s orders to be delivered, and the vector from point A to point 7 and the vector from point A to point 8 can be added The vector AA' is obtained, and the direction of the vector AA' can be used as the second direction.

In the embodiment of this specification, for the situation where the relevant location corresponding to the order to be allocated is not within the neighborhood of the delivery person, it is also possible to consider setting appropriate conditions. When these conditions are met, the influence of distance and direction can be ignored or no longer considered too carefully. For example, the condition is: according to the historical delivery efficiency of the delivery person, the order to be allocated is assigned to the delivery person, and the delivery person can deliver it on time; or, the delivery position of at least one order to be delivered of the delivery person is to be allocated The pick-up location of the order is close enough; etc.

Take the second condition listed in the previous paragraph as an example. If the delivery position of the order to be allocated is not within the neighborhood of the dispatcher, the minimum distance between the pickup position of the order to be allocated and the delivery position of the dispatcher's order to be dispatched can be determined. If the minimum distance is less than the preset distance threshold, the matching degree between the dispatcher and the to-be-allocated order may be determined as the aforementioned maximum matching degree, or other matching degrees high enough to be screened out.

The embodiment of this specification also provides an exemplary formula for determining the degree of matching between the dispatcher and the order to be allocated. In order to facilitate understanding, some pre-defined variables related to the formula are first explained. Represents a distribution person matching metric order to be dispensed by Q, V _i represents the match metric distribution person position i, p is the order represents the pickup position to be dispensed, d represents the order of the delivery position to be dispensed, dist _i represents The distance factor, a _i represents the direction factor,

Indicates the direction of the vector x. Refer to the following formulas (1) to (4).

Q=αV _p +(1-α)V _d ; (1)

Among them, α and β represent the preset weight coefficients with a value range of [0,1], inner represents that the relevant location is within the neighborhood of the delivery person, outer represents that the relevant location is not within the neighborhood of the delivery person, and Angle represents Find the angle in radians,

Represents the first direction mentioned above,

Represents said second direction, matching metric (matching degree measure) Q, V _i smaller value indicates a higher degree of matching corresponding (matching degree).

Match formula (1) for calculating a distribution person to be dispensed and the order metric Q, particularly the degree of matching based on the first position pickup and delivery staff to be dispensed and the order of V _p metric distribution person to be assigned a position order delivery The second matching degree metric V _d is calculated. Among them, α and (1-α) are the weights of the first matching degree metric V _p and the second matching degree metric V _d , respectively. For example, α can be 0.5, which means that the weights of the first matching degree metric V _p and the second matching degree metric V _d are the same. Of course, the weights of the first matching degree metric V _p and the second matching degree metric V _d may also be different.

Both the first matching degree metric V _p and the second matching degree metric V _d in formula (1) can be calculated by formula (2), which can be specifically calculated based on the distance factor dist _i and the direction factor a _i , and normalized化处理. The formula (2) also has two parts, namely the first item of the matching degree metric determined based on the distance factor dist _i and the second item of the matching degree metric determined based on the direction factor a _i . For ease of description, the weights of the first item of the matching degree measurement and the second item of the matching degree measurement are β and (1-β) respectively. In formula (2), if the distance dist _i between the delivery position of the order to be allocated and the delivery position of the order to be delivered by the dispatcher exceeds 1000 meters (it can also be modified to other suitable values), the matching degree measures the first The value of one item is the maximum value 1; if the above first direction

And the second direction

Completely reverse, then a _i =π, and the second item of the matching degree metric takes the maximum value of 1.

Formula (3) is the calculation method of the distance factor dist _i . If the pickup location of the order to be allocated is within the neighborhood of the dispatcher, the distance factor dist _i can be ignored and set to 0 directly; and if the pickup location of the order to be allocated is not within the neighborhood of the dispatcher, then Calculate the distances between the pickup positions of the orders to be allocated and the pickup positions of all the orders to be delivered by the dispatcher, and select the minimum distance min(d _ij ). If the minimum distance is less than 100 meters (it can also be modified to other suitable values), the distance factor dist _i can also be ignored.

Formula (4) is the calculation method of the direction factor a _i . When the distance factor dist _i is 0, the direction factor a _i is also 0; and if the distance factor dist _{i is} not 0, the angle between the first direction and the second direction mentioned above is calculated as the direction factor a _i .

If the above formula is used to calculate the matching degree, the value of the above-mentioned matching degree metric Q is 0, which can indicate the maximum matching degree.

In the embodiment of this specification, after determining the matching degree between the dispatcher and the order to be distributed, the matching degree can be screened out according to the matching degree to be relatively high and/or the order to be delivered is relatively small (for example, less than the real-time average order quantity in the region) Half) the combination of the delivery staff and the orders to be allocated, and then use the set path planning algorithm to plan the paths of the multiple combinations selected to allocate the orders to be allocated.

Following the example of the above formula, for example, after calculating the Q value for all possible combinations of the order to be assigned and the delivery person, sorting according to the Q value from small to large, and filtering out the top n percent of the combinations reserved. Take the following table 1 as an example.

Table 1:

To	待分配订单1Pending order 1	待分配订单2Pending order 2	待分配订单3Pending order 3	待分配订单4 Pending order 4
配送员1Delivery person 1	YY	YY	NN	NN
配送员2Delivery person 2	NN	NN	YY	NN
配送员3Delivery person 3	YY	NN	YY	YY
配送员4Delivery person 4	NN	YY	NN	YY

Table 1 exemplarily shows the screening results of the combinations of some delivery personnel and orders to be assigned. Y represents the combination that is screened out, and N represents the combination that is screened out. Half of the combinations in Table 1 are screened out, and these are screened out. The combination of is preferably a combination with a relatively high Q value (indicating a relatively low matching degree).

In practical applications, if there are currently delivery staff with relatively few or no orders to be delivered, such delivery staff can also be screened out first. It is not necessary to examine the matching degree between these delivery staff and the orders to be allocated, which will help make full use of Delivery staff resources.

A large number of real data experiments show that, in the case of adopting the scheme of this application, the effect of selecting more than half of the delivery personnel and the combination of orders to be allocated for route planning has basically no effect on the distribution of orders without screening. difference. In a stand-alone environment, under the premise that the Key Performance Indicators (KPIs) will not deteriorate (for example, 95% accuracy), keeping the top 50% of the matching combinations can save computing time25 % Or so, keeping the top 75% of the matching combinations can save about 10% of computing time. In a distributed environment, the effect may be better.

The above is mainly based on the distance factor and the direction factor to allocate pending orders. In practical applications, of course, more influencing factors can be considered. For example, the historical timeout situation of the delivery staff, if the timeout situation is serious, the matching degree will be relatively reduced. For another example, if the number of dispatchers in the current area is lower than the set threshold (for example, 50), the matching degree determination and the selection of dispatchers may not be performed, but all dispatchers are reserved for path planning. Or, if the selected delivery staff is less than 50, you can also add other optional delivery staff to try to keep 50 delivery staff for route planning.

Based on the same idea, the embodiment of this specification also provides a path planning device corresponding to FIG. 1.

Fig. 4 is a schematic diagram of the structure of the device. The device in Fig. 4 includes: a first determining module 400 for determining the relevant position corresponding to an order to be allocated; an acquiring module 402 for determining a collection of delivery personnel according to preset rules and Each dispatcher in the dispatcher set obtains the position of the dispatcher and the relevant position corresponding to the dispatcher’s pending order; the second determination module 404 is used for each dispatcher in the dispatcher set, according to all According to the relevant position corresponding to the order to be distributed, the position of the dispatcher, and the relevant position corresponding to the order to be dispatched by the dispatcher, the degree of matching between the dispatcher and the order to be dispatched is determined; The matching degree of each delivery person in the delivery person set with the order to be distributed is selected from the delivery person set that meets the preset conditions; the path planning module 408 is used to determine the matching degree of the delivery person according to the preset path planning algorithm. The orders to be allocated and the selected delivery personnel perform path planning.

Optionally, the relevant location includes at least one of a pickup location and a delivery location. In this case, the second determining module 404 is specifically configured to: determine the first degree of matching between the delivery person and the pickup location of the order to be allocated; determine the first degree of matching between the delivery person and the delivery location of the order to be allocated Second degree of matching; according to the first degree of matching between the dispatcher and the pickup location and the second degree of matching between the dispatcher and the delivery location, the degree of matching between the dispatcher and the order to be distributed is determined.

Optionally, the second determining module 404 is specifically configured to: determine the neighborhood range of the delivery person according to the location of the delivery person and the relevant position corresponding to the order to be delivered; according to the neighborhood range of the delivery person and The relevant position corresponding to the order to be allocated determines the degree of matching between the dispatcher and the order to be allocated.

Optionally, the second determination module 404 is specifically configured to: determine a coverage area of a specified size with the delivery person’s location as the regional center; and obtain the location of the delivery person in all relevant positions corresponding to the orders to be delivered. The relevant locations within the coverage area but have not been processed; the average coordinates of the obtained relevant locations are determined as the new regional center, and the coverage area of the specified size is determined according to the determined new regional center, until all the delivery personnel waiting The relevant locations corresponding to the delivery order are all processed, and then all the determined coverage areas are determined as the neighborhood range of the delivery person.

Optionally, the second determining module 404 is specifically configured to: determine whether the relevant position corresponding to the order to be allocated is within the neighborhood of the dispatcher; if so, determine the match between the dispatcher and the order to be allocated The degree of matching is the preset maximum matching degree, or other matching degrees high enough to be screened out; otherwise, the delivery is determined according to the relevant position corresponding to the order to be allocated and the relevant position corresponding to the order to be delivered by the dispatcher The degree of match between the employee and the pending order.

Optionally, the second determining module 404 is specifically configured to: determine the minimum distance between the relevant position corresponding to the order to be distributed and the relevant position corresponding to the order to be distributed of the delivery person, and determine the delivery according to the minimum distance. The first item of the matching degree between the clerk and the order to be allocated, wherein the minimum distance is negatively related to the first item of the matching degree; and/or the correlation from the location of the delivery person to the order to be allocated is determined The first direction of the position, and the second direction from the delivery person’s position to the relevant position corresponding to the delivery person’s order to be delivered, which is determined according to the angle between the first direction and the second direction The second item of matching degree between the dispatcher and the order to be allocated, wherein the included angle is negatively related to the second item of matching degree.

Optionally, the second determining module 404 is specifically configured to: if the minimum distance is less than a preset distance threshold, determine that the degree of matching between the delivery person and the order to be distributed is the maximum degree of matching, or as high as Other matches sufficient to be filtered out.

Optionally, the screening module 406 is specifically configured to: filter out the dispatchers whose matching degree with the order to be allocated is higher than a preset threshold; or according to the matching degree of each dispatcher with the order to be allocated from high to low In order to filter the specified number of delivery personnel.

The embodiment of this specification also provides a computer-readable storage medium, the storage medium stores a computer program, and the computer program can be used to execute a path planning method in FIG. 1.

The embodiment of this specification also proposes a schematic structural diagram of the electronic device shown in FIG. 5 corresponding to FIG. 1. As shown in FIG. 5, at the hardware level, the electronic device includes a processor 510, an internal bus 520, a network interface 530, a memory 540, and a non-volatile memory 550. Of course, it may also include hardware required for other services. The processor 510 reads the corresponding computer program from the non-volatile memory 550 to the memory 540 and then runs it to implement a path planning method in FIG. 1. Of course, in addition to the software implementation, this specification does not exclude other implementations, such as logic devices or a combination of software and hardware, etc. That is to say, the execution body of the following processing flow is not limited to each logic unit, and can also be Hardware or logic device.

In the 1990s, the improvement of a technology can be clearly distinguished between hardware improvements (for example, improvements in circuit structures such as diodes, transistors, switches, etc.) or software improvements (improvements in method flow). However, with the development of technology, the improvement of many methods and processes of today can be regarded as a direct improvement of the hardware circuit structure. Designers almost always get the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that the improvement of a method flow cannot be realized by hardware entity modules. For example, a programmable logic device (Programmable Logic Device, PLD) (such as a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user's programming of the device. It is programmed by the designer to "integrate" a digital system on a PLD without requiring the chip manufacturer to design and manufacture a dedicated integrated circuit chip. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly realized by "logic compiler" software, which is similar to the software compiler used in program development and writing. The original code must also be written in a specific programming language, which is called Hardware Description Language (HDL), and there is not only one type of HDL, but many types, 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, RHDL (Ruby Hardware Description), etc., currently most commonly used It is VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. It should also be clear to those skilled in the art that just a little bit of logic programming of the method flow in the above-mentioned hardware description languages and programming into an integrated circuit, the hardware circuit that implements the logic method flow can be easily obtained.

The controller can be implemented in any suitable manner. For example, the controller can take the form of, for example, a microprocessor or a processor and a computer-readable medium storing computer-readable program codes (such as 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, the memory controller can also be implemented as a part of the memory control logic. Those skilled in the art also know that in addition to implementing the controller in a purely computer-readable program code manner, it is entirely possible to program the method steps to make the controller use logic gates, switches, application specific integrated circuits, programmable logic controllers and embedded The same function can be realized in the form of a microcontroller, etc. Therefore, such a controller can be regarded as a hardware component, and the devices included in it for implementing various functions can also be regarded as a structure within the hardware component. Or even, the device for realizing various functions can be regarded as both a software module for realizing the method and a structure within a hardware component.

The systems, devices, modules, or units illustrated in the above embodiments may be specifically implemented by computer chips or entities, or implemented by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cell phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or Any combination of these devices.

For the convenience of description, when describing the above device, the functions are divided into various units and described separately. Of course, when implementing this application, the functions of each unit can be implemented in the same one or more software and/or hardware.

Those skilled in the art should understand that the embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

The present invention is described with reference to flowcharts and/or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and/or block in the flowchart and/or block diagram, and the combination of processes and/or blocks in the flowchart and/or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing equipment to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing equipment are generated It is a device that realizes the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.

These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing equipment to work in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including the instruction device. The device implements the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.

These computer program instructions can also be loaded on a computer or other programmable data processing equipment, so that a series of operation steps are executed on the computer or other programmable equipment to produce computer-implemented processing, so as to execute on the computer or other programmable equipment. The instructions provide steps for implementing functions specified in a flow or multiple flows in the flowchart and/or a block or multiple blocks in the block diagram.

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

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

Computer-readable media include permanent and non-permanent, removable and non-removable media, and information storage can be realized by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, CD-ROM, digital versatile disc (DVD) or other optical storage, Magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media can be used to store information that can be accessed by computing devices. According to the definition in this article, computer-readable media does not include transitory media, such as modulated data signals and carrier waves.

It should also be noted that the terms "include", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, product or equipment including a series of elements not only includes those elements, but also includes Other elements that are not explicitly listed, or include elements inherent to this process, method, commodity, or equipment. If there are no more restrictions, the element defined by the sentence "including a..." does not exclude the existence of other identical elements in the process, method, commodity, or equipment that includes the element.

Those skilled in the art should understand that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, this application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

This application may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments. In these distributed computing environments, remote processing devices connected through a communication network perform tasks. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, as for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and for related parts, please refer to the part of the description of the method embodiment.

The above descriptions are only examples of this application and are not used to limit this application. For those skilled in the art, this application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this application shall be included in the scope of the claims of this application.

Claims

A path planning method including:

Determine the relevant position corresponding to the order to be allocated;

Determine the collection of delivery personnel according to preset rules;

For each dispatcher in the dispatcher set, obtain the position of the dispatcher and the relevant position corresponding to the order to be dispatched by the dispatcher;

For each delivery person in the delivery person set, determine the delivery person and the delivery person according to the relevant position corresponding to the order to be allocated, the position of the delivery person, and the relevant position corresponding to the order to be delivered by the delivery person. The matching degree of the allocated order;

According to the degree of matching between each of the dispatchers in the set of dispatchers and the order to be distributed, filter out the dispatchers meeting the preset conditions from the set of dispatchers;

According to a preset path planning algorithm, path planning is performed on the orders to be distributed and the selected delivery personnel.
The method of claim 1, wherein:

The relevant location includes at least one of a pickup location and a delivery location;

The determining the degree of matching between the dispatcher and the order to be allocated includes:

Determining the first degree of matching between the delivery person and the pickup location of the order to be allocated;

Determining the second degree of matching between the delivery person and the delivery location of the order to be allocated;

According to the first matching degree and the second matching degree, the matching degree between the dispatcher and the order to be allocated is determined.
8. The method of claim 1, wherein determining the degree of matching between the delivery person and the order to be allocated comprises:

Determine the neighborhood range of the delivery person according to the location of the delivery person and the relevant position corresponding to the delivery order of the delivery person;

According to the neighborhood range of the dispatcher and the relevant position corresponding to the order to be allocated, the degree of matching between the dispatcher and the order to be allocated is determined.
8. The method of claim 3, wherein determining the neighborhood range of the delivery person according to the location of the delivery person and the relative position corresponding to the delivery order of the delivery person includes:

Use the location of the delivery person as the regional center to determine the coverage area of the specified size;

Among the relevant positions corresponding to all pending orders of the dispatcher, obtain the relevant positions that fall within the coverage area but have not been processed;

Determine the obtained average coordinates of the relevant position as the new area center,

Continue to determine the coverage area of the specified size according to the determined new regional center, until all the relevant positions of the delivery personnel's pending orders have been processed, and determine all the determined coverage areas as the neighborhood area of the delivery personnel .
The method of claim 3, wherein determining the degree of matching between the dispatcher and the order to be allocated according to the neighborhood range of the dispatcher and the relative position corresponding to the order to be allocated comprises:

Determine whether the relevant position corresponding to the order to be allocated is within the neighborhood of the dispatcher;

If yes, it is determined that the matching degree between the dispatcher and the order to be distributed is the preset maximum matching degree;

Otherwise, the degree of matching between the dispatcher and the order to be dispatched is determined according to the relevant position corresponding to the order to be allocated and the relevant position corresponding to the order to be dispatched by the dispatcher.
The method of claim 5, wherein the degree of matching between the dispatcher and the dispatch order is determined based on the relevant position corresponding to the dispatch order and the dispatch dispatcher's dispatch order. ,include:

Determine the minimum distance between the relevant position corresponding to the order to be allocated and the relevant position corresponding to the order to be dispatched by the dispatcher, and determine the matching degree between the dispatcher and the order to be dispatched according to the minimum distance. , Wherein the minimum distance is negatively related to the first item of the matching degree.
The method according to claim 5 or 6, characterized in that, according to the relevant position corresponding to the order to be allocated and the relevant position corresponding to the order to be dispatched by the dispatcher, it is determined that the dispatcher and the order to be dispatched Matching degree, including:

Determine the first direction from the position of the dispatcher to the relevant position corresponding to the order to be distributed, and the second direction from the position of the dispatcher to the relevant position corresponding to the order to be dispatched by the dispatcher, according to the The included angle between the first direction and the second direction determines the degree of matching between the dispatcher and the order to be distributed, wherein the included angle is negatively related to the degree of matching.
7. The method of claim 6, wherein determining the first item of the matching degree between the delivery person and the order to be allocated according to the minimum distance specifically includes:

If the minimum distance is less than the preset distance threshold, it is determined that the degree of matching between the dispatcher and the order to be allocated is the maximum degree of matching.
The method according to claim 1, wherein the delivery person meeting the preset conditions specifically includes any one or more of the following:

The degree of matching between the delivery person and the order to be allocated is higher than a preset threshold;

According to the order of the matching degree between each distributor in the set of distributors and the order to be allocated from high to low, the degree of matching between the distributor and the order to be allocated is within a specified range;

The current number of orders to be delivered by the distributor is less than the preset number.
The method according to claim 1, wherein the preset rule includes any one or more of the following:

Determining the dispatchers currently located in the area where the orders to be allocated belong to be members of the dispatcher set;

Determine the dispatcher responsible for the area to which the order to be allocated belongs to be a member of the dispatcher set;

The current delivery personnel who are willing to continue to take orders are determined as members of the delivery personnel set.
A path planning device includes:

The first determining module is used to determine the relevant position corresponding to the order to be allocated;

The obtaining module is used to determine the set of dispatchers according to preset rules, and for each dispatcher in the set of dispatchers, obtain the position of the dispatcher and the relevant position corresponding to the order to be dispatched by the dispatcher;

The second determining module is used to determine, for each delivery person in the delivery person set, according to the relevant position corresponding to the order to be allocated, the position of the delivery person, and the relevant position corresponding to the order to be delivered of the delivery person The degree of matching between the delivery person and the order to be allocated;

The screening module is configured to screen out the dispatchers who meet the preset conditions from the set of dispatchers according to the degree of matching between each of the dispatchers in the set of dispatchers and the order to be distributed;

The path planning module is used to plan the path of the order to be distributed and the selected delivery personnel according to a preset path planning algorithm.
A computer-readable storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1-9 is realized.
An electronic device, comprising a memory, a processor, and a computer program stored on the memory and running on the processor, wherein the processor implements any one of claims 1-9 when the program is executed Methods.