Planning Method, Device, Electronic Device and Storage Medium for Delivery Routes

Abstract

The present application discloses a method, apparatus, electronic device, and storage medium for planning a delivery route. The method includes: screening at least one route layout from a historical route layout set that is associated with a delivery planning task; constructing a candidate route layout template set for the delivery planning task according to the at least one screened route layout; matching each route layout template in the candidate route layout template set with each delivery point of the delivery planning task, and constructing a reference route layout template set for the delivery planning task according to the matching result; generating a delivery route including the delivery points of the delivery planning task based on the reference route layout template set. The beneficial effects are that it can give play to the role of historical delivery data, determine the route layout by using the spatial geometric features of historical delivery routes, provide important reference value in the process of delivery route planning, reduce the planning time and calculation amount, and make the generated delivery route closer to the business scenario and requirements.

Description

Technical Field

[0001] This application relates to the field of intelligent distribution, and particularly to a method, apparatus, electronic device, and storage medium for planning distribution routes. Background Art

[0002] One of the key points in intelligent distribution is how to plan distribution routes. Currently, in addition to manual route arrangement, automatic route arrangement using path planning algorithms is also included. Here, route arrangement refers to the planning of distribution routes. Manual route arrangement obviously has the defects of high labor cost and low efficiency, while automatic route arrangement often abstracts this technical problem into a mathematical problem and solves it using the idea of mathematical programming, and cannot make good use of some relevant information already available in the business. Summary of the Invention

[0003] In view of the above problems, this application is proposed to provide a method, apparatus, electronic device, and storage medium for planning distribution routes that overcome the above problems or at least partially solve the above problems.

[0004] According to one aspect of this application, a method for planning a distribution route is provided, including:

[0005] Screening out at least one route layout associated with the distribution planning task from the historical route layout set;

[0006] Constructing a candidate route layout template set for the distribution planning task according to the at least one screened route layout;

[0007] Matching each route layout template in the candidate route layout template set with each distribution point of the distribution planning task, and constructing a benchmark route layout template set for the distribution planning task according to the matching result;

[0008] Generating a distribution route including the distribution points of the distribution planning task based on the benchmark route layout template set.

[0009] Optionally, the historical route layout set is constructed in the following manner:

[0010] Projecting the historical distribution points included in the historical distribution route into a spatial coordinate system;

[0011] Determining the convex hull contour of the historical distribution points included in each historical distribution route according to the spatial coordinates of each historical distribution point in the spatial coordinate system, and obtaining a convex polygon corresponding to each historical distribution route;

[0012] Taking each convex polygon that meets the line constraint conditions as a route layout and storing it in the historical route layout set.

[0013] Optionally, the screening of the line layout maps associated with the distribution planning task from the historical line layout map set includes:

[0014] Determining candidate time conditions based on the distribution time of the distribution planning task, and determining candidate space conditions based on each distribution point of the distribution planning task;

[0015] Screening out the line layout maps that meet both the candidate time conditions and the candidate space conditions from the historical line layout map set.

[0016] Optionally, the construction of the candidate line layout map template set for the distribution planning task according to the screened line layout maps includes:

[0017] Selecting the line layout maps that match the specified time interval, constructing the line layout map templates corresponding to the specified time interval, and taking the constructed line layout map templates as elements in the candidate line layout map template set.

[0018] Optionally, the matching of each line layout map template in the candidate line layout map template set with each distribution point of the distribution planning task, and the construction of the reference line layout map template set for the distribution planning task according to the matching results includes:

[0019] Taking the ratio of the number of distribution points of the distribution planning task that fall into the line layout map template to the total number of distribution points of the distribution planning task as the matching rate of the line layout map template with the distribution planning task;

[0020] Screening out multiple line layout map templates from the candidate line layout map template set according to the matching rate;

[0021] Calculating the proportion of the overlapping part between the line layout map templates, and if the proportion of the overlapping part is greater than the preset threshold, taking the corresponding overlapping part as an element in the reference line layout map template set.

[0022] Optionally, the matching of each line layout map template in the candidate line layout map template set with each distribution point of the distribution planning task, and the construction of the reference line layout map template set for the distribution planning task further includes:

[0023] Assigning a first weight value to the original elements in the reference line layout map template set;

[0024] Screening out the elements that meet the conditions from the candidate line layout map template set, assigning a second weight value to the screened elements, and adding them to the reference line layout map template set;

[0025] The first weight value is greater than the second weight value.

[0026] Optionally, generating a delivery route that includes the delivery points of the delivery planning task based on the set of reference route layout templates includes:

[0027] According to a preset delivery route generation algorithm, using the elements in the set of reference route layout templates as reference data for delivery point clustering, generating a delivery route that includes the delivery points of the delivery planning task; if each element in the set of reference route layout templates includes a weight value, determining the reference priority according to the weight value.

[0028] According to another aspect of the present application, there is provided a device for planning a delivery route, including:

[0029] A route layout screening unit, configured to screen out route layouts associated with the delivery planning task from a historical route layout set;

[0030] A candidate route layout template set construction unit, configured to construct a candidate route layout template set for the delivery planning task according to the screened-out route layouts;

[0031] A reference route layout template set construction unit, configured to match each route layout template in the candidate route layout template set with each delivery point of the delivery planning task, and construct a reference route layout template set for the delivery planning task according to the matching results;

[0032] A planning unit, configured to generate a delivery route that includes the delivery points of the delivery planning task based on the set of reference route layout templates.

[0033] Optionally, the device further includes:

[0034] A historical route layout set unit, configured to project the historical delivery points included in the historical delivery route into a space coordinate system; according to the space coordinates of each historical delivery point in the space coordinate system, determining the convex hull contour of the historical delivery points included in each historical delivery route, obtaining a convex polygon corresponding to each historical delivery route; and storing the convex polygons that meet the route constraint conditions as route layouts in the historical route layout set.

[0035] Optionally, the route layout screening unit is configured to determine candidate time conditions based on the delivery time of the delivery planning task, and determine candidate space conditions based on each delivery point of the delivery planning task; screening out route layouts that meet both the candidate time conditions and the candidate space conditions from the historical route layout set.

[0036] Optionally, the candidate route layout template set construction unit is configured to select a route layout that matches a specified time interval, construct a route layout template corresponding to the specified time interval, and use the constructed route layout template as an element in the candidate route layout template set.

[0037] Optionally, the reference circuit layout template set construction unit is configured to match each circuit layout template in the candidate circuit layout template set with each distribution point of the distribution planning task, and construct the reference circuit layout template set of the distribution planning task according to the matching result, including: using the ratio of the number of distribution points of the distribution planning task falling into the circuit layout template to the total number of distribution points of the distribution planning task as the matching rate of the circuit layout template and the distribution planning task; screening out multiple circuit layout templates from the candidate circuit layout template set according to the matching rate; calculating the proportion of the overlapping part of the layout between the circuit layout templates, and if the proportion of the overlapping part of the layout is greater than a preset threshold, using the corresponding overlapping part of the layout as an element in the reference circuit layout template set.

[0038] Optionally, the reference circuit layout template set construction unit is configured to assign a first weight value to the original elements in the reference circuit layout template set; screen out eligible elements from the candidate circuit layout template set, assign a second weight value to the screened-out elements, and then add them to the reference circuit layout template set; the first weight value is greater than the second weight value.

[0039] Optionally, the planning unit is configured to generate a distribution route including the distribution points of the distribution planning task by using the elements in the reference circuit layout template set as reference data for distribution point clustering according to a preset distribution route generation algorithm; if each element in the reference circuit layout template set includes a weight value, determine the reference priority according to the weight value.

[0040] According to another aspect of the present application, there is provided an electronic device, including: a processor; and a memory arranged to store computer-executable instructions, the executable instructions, when executed, causing the processor to execute the method as described in any one of the above.

[0041] According to still another aspect of the present application, there is provided a computer-readable storage medium, wherein the computer-readable storage medium stores one or more programs, and the one or more programs, when executed by a processor, implement the method as described in any one of the above.

[0042] As can be seen from the above, in the technical solution of the present application, the circuit layout associated with the distribution planning task is screened from the historical circuit layout set, the candidate circuit layout template set for the distribution planning task is constructed according to the screened circuit layout, each circuit layout template in the candidate circuit layout template set is matched with each distribution point of the distribution planning task, and the benchmark circuit layout template set for the distribution planning task is constructed according to the matching result. Based on the benchmark circuit layout template set, the distribution route including the distribution points of the distribution planning task is generated. The beneficial effect of this technical solution is that it can give play to the role of historical distribution data, determine the circuit layout by using the spatial geometric features of the historical distribution route, provide important reference value in the process of distribution route planning, reduce the planning time and calculation amount, and make the generated distribution route closer to the business scenario and requirements.

[0043] The above description is only an overview of the technical solution of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the following specifically describes the embodiments of the present application. Brief Description of the Drawings

[0044] By reading the following detailed description of the preferred embodiments, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present application. And throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0045] Figure 1 A flowchart showing the planning method of the distribution route according to an embodiment of the present application;

[0046] Figure 2 A schematic structural diagram showing the planning device of the distribution route according to an embodiment of the present application;

[0047] Figure 3 A schematic structural diagram showing the electronic device according to an embodiment of the present application;

[0048] Figure 4 A schematic structural diagram showing the computer-readable storage medium according to an embodiment of the present application;

[0049] Figure 5 A schematic diagram showing the circuit layout template according to an embodiment of the present application;

[0050] Figure 6 A schematic diagram showing the planned distribution route according to an embodiment of the present application. Detailed Description of the Embodiments

[0051] Exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present application can be understood more thoroughly and the scope of the present application can be fully conveyed to those skilled in the art.

[0052] An ideal delivery route plan generally has at least one of the following characteristics:

[0053] (1) On a single delivery route, the merchant locations are clustered within a small radius, and neighboring merchants are assigned to the same delivery route; (2) The delivery routes do not cross as much as possible to avoid drivers detouring back and forth; (3) The order loading on the delivery routes is balanced, and the full load rates of neighboring routes are close; (4) The delivery merchants on the delivery routes within the fulfillment area are as fixed as possible, binding the driver to his delivery area / route as much as possible, so that the driver can be familiar with the delivery and improve the fulfillment timeliness; at the same time, "experienced drivers" are also a positive factor in ensuring merchant retention.

[0054] It can be seen that "fixed area - fixed route - fixed driver" is the core requirement in business. To achieve this effect, historical delivery data has important utilization value. The technical concept of the present application is proposed in view of this, using the morphological characteristics of historical delivery routes, and performing spatial similarity matching with the delivery points of the actual delivery planning task according to the spatial geometric characteristics of the route layout, so that the delivery routes obtained by subsequent algorithms can better meet the above requirements and be more efficient. This will be introduced below in combination with specific embodiments.

[0055] Figure 1 A flowchart showing the planning method of a delivery route according to an embodiment of the present application is shown. As Figure 1 shown, the method includes:

[0056] Step S110, screening at least one route layout associated with the delivery planning task from the historical route layout set.

[0057] Here, the historical route layout set stores the route layouts determined according to historical delivery data. In the embodiments of the present application, the route layout is a layout that can reflect the spatial morphological characteristics of historical delivery routes. In other words, the route layout can be determined based on the spatial geometric characteristics of historical delivery routes. For example, each historical delivery route may be distributed in a fixed block, and the route layout corresponds to the layout of each block in the map. Thus, the effective utilization of historical delivery data collected in the business scenario is achieved. In many business scenarios, the delivery points are relatively fixed. For example, many vegetable merchants need to prepare vegetables, and the vegetable merchants supplied by the supplier every day usually have a high repetition rate, which provides a practical basis for the utilization of historical delivery data.

[0058] Step S120: Construct a candidate route layout template set for the distribution planning task based on at least one screened route layout.

[0059] For the distribution of a large region, multiple distribution routes often need to be planned. The route layout obtained in step S110 corresponds to a single distribution route. Therefore, for an overall distribution planning task, multiple route layouts need to be combined to form a route layout template before it can be utilized.

[0060] Step S130: Match each route layout template in the candidate route layout template set with each distribution point of the distribution planning task, and construct a benchmark route layout template set for the distribution planning task according to the matching results.

[0061] This matching can be achieved based on spatial similarity. In the most ideal scenario, if each merchant to be distributed exactly corresponds to each merchant in a historical distribution scenario, then scene reproduction can be performed, and the historical distribution route can be reused to achieve the current distribution route planning. However, in most cases, the merchants for each distribution are not completely the same. Then it can be imagined that finding the historical distribution scenario that is most similar to the current distribution scenario and performing the current distribution route planning based on the corresponding historical distribution route can improve the planning efficiency and effect. This is achieved through matching in this step. The specific matching method can be selected according to actual needs. The following gives an optional example, which does not represent a limitation to the solution: If a sufficient number of distribution points (for example, setting a ratio of 90%) fall into a route layout template, then this route layout template is placed in the benchmark route layout template set as one of its elements. Taking a distribution planning task including 100 distribution points as an example, 95 distribution points fall into route layout template A, and 85 distribution points fall into route layout template B. Then route layout template A can be placed in the benchmark route layout template set, and route layout template B cannot be placed in the benchmark route layout template set.

[0062] Step S140: Generate a distribution route including the distribution points of the distribution planning task based on the benchmark route layout template set.

[0063] The elements in the reference route layout template set can be used as a reference when planning the distribution route. For example, using route layout template A in the reference route layout template set as a reference, the three route layouts a, b, and c in this route layout template A do not intersect with each other, and each route layout makes the distribution points covered by it form a corresponding cluster of distribution points. Then, the distribution routes for the distribution points in each cluster of distribution points can be planned, and the historical distribution routes corresponding to the corresponding route layouts can be referred to. For example, route layout a covers distribution points 1, 2... 10, and the historical distribution route corresponding to route layout a also happens to be corresponding to these 10 distribution points. Then, the historical distribution route corresponding to route layout a can be directly reused. Another example is that route layout b covers distribution points 11, 12... 20, and the historical distribution route corresponding to route layout b is corresponding to these distribution points 11, 12... 19. Then, according to the algorithm, distribution point 20 can be added to the historical distribution route corresponding to route layout b. Another example is that route layout template A does not completely cover the distribution points of the distribution planning task, and the uncovered distribution points are relatively close to route layout c. Then, these points and the distribution points covered by route layout c can be used as a cluster of distribution points to plan the distribution route. When planning the distribution route, various algorithms in the prior art can be referred to for implementation, such as heuristic algorithms, or new algorithms can be developed according to requirements. This application does not limit this. However, it can be seen that no matter which algorithm is adopted, the reference route layout template set adopted in the embodiments of this application provides more available information for the algorithm, thus reducing the calculation amount and improving the efficiency.

[0064] It can be seen that Figure 1 The method shown can give play to the role of historical distribution data, determine the route layout using the spatial geometric features of the historical distribution route, provide important reference value in the process of distribution route planning, reduce the planning time and calculation amount, and make the generated distribution route closer to the business scenario and requirements.

[0065] In an embodiment of this application, in the above method, the historical route layout set is constructed in the following manner: project the historical distribution points included in the historical distribution route into a spatial coordinate system; according to the spatial coordinates of each historical distribution point in the spatial coordinate system, determine the convex hull contour of the historical distribution points included in each historical distribution route to obtain a convex polygon corresponding to each historical distribution route; store the convex polygons that meet the route constraint conditions as route layouts in the historical route layout set.

[0066] For example, historical delivery routes save historical delivery data in the format of <delivery date, delivery route number, delivery point>. For the convenience of management and subsequent data processing, the data can be sorted in reverse order of the delivery date and in ascending order of the delivery number. Due to the time limitation of historical delivery data, the historical delivery data selected for constructing the historical route map set can be for a recent period, such as the last month.

[0067] One effect of projecting the historical delivery points in a historical delivery route onto a spatial coordinate system is to display multiple historical delivery points on the map. Then, based on the spatial coordinates of each historical delivery point in the spatial coordinate system, the convex hull contour of each historical delivery point can be determined. The resulting convex polygon can obviously cover all the historical delivery points in this historical delivery route, thus reflecting the spatial geometric characteristics of this historical delivery route.

[0068] In addition, it is also necessary to ensure that the obtained convex polygon does not violate business constraints such as prohibited cross-region, and the shape of the convex polygon should not be too special, such as being a long and thin strip, etc. For these, line constraint conditions can be set respectively, so as to store each convex polygon that meets the line constraint conditions as a route map in the historical route map set.

[0069] In an embodiment of the present application, in the above method, screening out the route maps associated with the delivery planning task from the historical route map set includes: determining candidate time conditions based on the delivery time of the delivery planning task, and determining candidate space conditions based on each delivery point of the delivery planning task; screening out the route maps that meet both the candidate time conditions and the candidate space conditions from the historical route map set.

[0070] One way to determine the candidate time conditions is to select the route maps of the historical delivery routes on the dates of date_cur - 1, date_cur - 2, … date_cur - n, date_cur - 14, date_cur - 21, etc. based on the delivery date date_cur of the current delivery planning task. For example, if the delivery time of the delivery planning task is June 1st, then May 31st, May 30th … May 18th can be selected as the candidate time conditions, that is, only the route maps of the historical delivery routes on these dates are selected. Preferably, n does not exceed 14, that is, the route maps of the historical delivery routes within 14 days are selected, which is more time-sensitive.

[0071] In addition, it is also necessary to ensure that the selected route maps meet the candidate space conditions. Here, for example, it can be required that there is an intersection between the historical delivery points included in the historical delivery route and the delivery points of the current delivery planning task.

[0072] In one embodiment of the present application, in the above method, constructing a candidate line layout template set for the distribution planning task according to the selected line layout includes: selecting a line layout that matches a specified time interval, constructing a line layout template corresponding to the specified time interval, and using the constructed line layout template as an element in the candidate line layout template set.

[0073] For example, for each day from May 31st, May 30th... to May 18th, construct a line layout template respectively, and use the constructed line layout template as an element in the candidate line layout template set. A specific line layout template is as Figure 5 shown Figure 5 where each block area (convex polygon) is a line layout.

[0074] In one embodiment of the present application, in the above method, matching each line layout template in the candidate line layout template set with each distribution point of the distribution planning task, and constructing a benchmark line layout template set for the distribution planning task according to the matching result includes: taking the ratio of the number of distribution points of the distribution planning task that fall into the line layout template to the total number of distribution points of the distribution planning task as the matching rate of the line layout template and the distribution planning task; screening out multiple line layout templates from the candidate line layout template set based on the matching rate; calculating the proportion of the overlapping part of the layouts between each line layout template, and if the proportion of the overlapping part of the layouts is greater than a preset threshold, taking the corresponding overlapping part of the layouts as an element in the benchmark line layout template set.

[0075] If the number of distribution points falling into a line layout template is more, it indicates that the spatial similarity between this line layout template and the current distribution planning task is higher, and then the effect of distribution route planning based on this line layout template is better. Moreover, the embodiment of the present application also provides a method of screening out multiple line layout templates from the candidate line layout template set based on the matching rate. By finding the intersection of regions (that is, the overlapping part of the shapes) between these line layout templates, extracting the overlapping part of the shapes with a proportion of the overlapping part of the shapes greater than a preset value as an element in the benchmark line layout template set, the robustness is improved. For example, select 5 line layout templates from the candidate line layout template set according to the coverage rate of the distribution points by the line layout template from high to low, and then perform pairwise superposition on these 5 line layout templates to obtain a total of 10 overlapping parts of the shapes. Then, the proportion of the overlapping part of the shapes to the original line layout template can be obtained. For example, in line layout template A, the pixel area of the line layout is 750, and in line layout template B, the pixel area of the line layout is 800. After the two are superimposed, the pixel area of the overlapping part of the shapes is 730, then the proportion of the overlapping part of the shapes is 730 * 2 / (750 + 800) ≈ 94%.

[0076] In one embodiment of the present application, in the above method, matching each circuit layout template in the candidate circuit layout template set with each delivery point of the delivery planning task, and constructing the reference circuit layout template set of the delivery planning task according to the matching result further includes: assigning a first weight value to the original elements in the reference circuit layout template set; screening out the qualified elements from the candidate circuit layout template set, assigning a second weight value to the screened-out elements, and then adding them to the reference circuit layout template set; the first weight value is greater than the second weight value.

[0077] In some cases (for example, the merchants to be delivered vary greatly every day), if only the morphological superposition part is used, the historical delivery data is not fully utilized. Therefore, the embodiments of the present application also propose a way to further obtain information from the candidate circuit layout template set. Since the elements first placed in the reference circuit layout template set (i.e., the original elements) can better reflect the historical consistency, a higher weight is assigned; under the condition of setting some screening conditions, then screening out the qualified elements from the candidate circuit layout template set and putting them into the reference circuit layout template set, and assigning a lower weight to these elements, which not only reflects the difference in the strength of historical features but also makes full use of historical features.

[0078] In one embodiment of the present application, in the above method, generating a delivery route including the delivery points of the delivery planning task based on the reference circuit layout template set includes: according to the preset delivery route generation algorithm, using the elements in the reference circuit layout template set as the reference data for delivery point clustering, and generating a delivery route including the delivery points of the delivery planning task; if each element in the reference circuit layout template set includes a weight value, then determining the reference priority according to the weight value.

[0079] Such as Figure 5As shown, the circuit layout can be a convex polygon area, and the circuit layout template divides multiple areas. Therefore, through the circuit layout template, the delivery points of this delivery planning task can be included in the corresponding areas, that is, clustering is achieved. The circuit layout template cannot ensure that all delivery points of this delivery planning task are covered, that is, some points may be omitted. Therefore, based on the circuit layout template, heuristic algorithms such as dynamic step search and grid clustering can be combined for processing and adjustment. For the delivery points within each circuit layout, the corresponding historical delivery routes can be referred to for planning. Finally, the multiple candidate delivery routes obtained can be scored to determine the final delivery route. A heuristic algorithm is an algorithm constructed based on intuition or experience that gives a feasible solution for each instance of the combinatorial optimization problem to be solved at an acceptable cost (referring to computing time and space). Then, it can be seen that the circuit layout template given by the embodiments of this application can provide better empirical knowledge. If the circuit layout template has weight values, the circuit layout template with a higher weight value can be referred to first. According to the effect diagram of a specific embodiment as Figure 6 shown, in which it can be seen that the delivery points are basically included in the convex polygon area, forming multiple clusters. The numbers on the delivery points in the same cluster represent the delivery order, that is, the delivery route can be determined.

[0080] Figure 2 shows a schematic structural diagram of a device for planning a delivery route according to an embodiment of this application. As Figure 2 shown, the device 200 for planning a delivery route includes:

[0081] A circuit layout screening unit 210, configured to screen out the circuit layouts associated with the delivery planning task from the historical circuit layout set.

[0082] Here, the historical circuit layout set stores the circuit layouts determined according to historical delivery data. In the embodiments of this application, the circuit layout is a layout that can reflect the spatial morphological characteristics of the historical delivery routes. In other words, the circuit layout can be determined based on the spatial geometric characteristics of the historical delivery routes. For example, each historical delivery route may be distributed in a fixed block, and the circuit layout corresponds to the layout of each block in the map. Thus, the effective utilization of the historical delivery data collected in the business scenario is realized. In many business scenarios, the delivery points are relatively fixed. For example, many vegetable merchants need to prepare vegetables, and the vegetable merchants supplied by the supplier usually have a high repetition rate every day, which provides a practical basis for the utilization of historical delivery data.

[0083] A candidate circuit layout template set construction unit 220, configured to construct a candidate circuit layout template set for the delivery planning task according to the screened circuit layouts.

[0084] For the distribution of a large area, multiple distribution routes often need to be planned. The route layout obtained in step S110 corresponds to a single distribution route. Therefore, for an overall distribution planning task, multiple route layouts need to be combined to form a route layout template before it can be utilized.

[0085] The reference route layout template set construction unit 230 is used to match each route layout template in the candidate route layout template set with each distribution point of the distribution planning task, and construct a reference route layout template set for the distribution planning task according to the matching results.

[0086] The matching here can be achieved based on spatial similarity. In the most ideal scenario, if each merchant to be distributed exactly corresponds to each merchant in a historical distribution scenario, then the scenario can be reproduced, and the historical distribution route can be reused to achieve the distribution route planning for this time. However, in most cases, the merchants for each distribution are not completely the same. Then it can be imagined that finding the historical distribution scenario that is most similar to the current distribution scenario and planning the current distribution route based on the corresponding historical distribution route can improve the planning efficiency and effect. This is achieved through matching in this step. The specific matching method can be selected according to actual needs. The following gives an optional example, which does not represent a limitation to the solution: If a sufficient number of distribution points (for example, setting a ratio of 90%) fall into a route layout template, then this route layout template is put into the reference route layout template set as one of its elements. Taking a distribution planning task including 100 distribution points as an example, 95 distribution points fall into route layout template A, and 85 distribution points fall into route layout template B. Then route layout template A can be put into the reference route layout template set, and route layout template B cannot be put into the reference route layout template set.

[0087] The planning unit 240 is used to generate a distribution route including the distribution points of the distribution planning task based on the reference route layout template set.

[0088] The elements in the reference route layout template set can be used as a reference when planning the distribution route. For example, using route layout template A in the reference route layout template set as a reference, the three route layouts a, b, and c in this route layout template A do not intersect with each other, and each route layout makes the distribution points it covers form a corresponding cluster of distribution points. Then, the distribution routes of the distribution points in each cluster of distribution points can be planned, and the historical distribution routes corresponding to the corresponding route layouts can be referred to. For example, route layout a covers distribution points 1, 2... 10, and the historical distribution route corresponding to route layout a also exactly corresponds to these 10 distribution points. Then, the historical distribution route corresponding to route layout a can be directly reused. Another example is that route layout b covers distribution points 11, 12... 20, and the historical distribution route corresponding to route layout b corresponds to distribution points 11, 12... 19. Then, according to the algorithm, distribution point 20 can be added to the historical distribution route corresponding to route layout b. Another example is that the route layout template A does not completely cover the distribution points of the distribution planning task, and the distribution points not covered are relatively close to route layout c. Then, these points and the distribution points covered in route layout c can be used as a cluster of distribution points for distribution route planning. When planning the distribution route, various algorithms in the prior art can be referred to for implementation, such as heuristic algorithms, or new algorithms can be developed according to requirements. This application does not limit this. However, it can be seen that no matter which algorithm is adopted, the reference route layout template set adopted in the embodiments of this application provides more available information for the algorithm, thus reducing the calculation amount and improving the efficiency.

[0089] It can be seen that Figure 2 The device shown can give play to the role of historical distribution data, determine the route layout using the spatial geometric characteristics of the historical distribution route, provide important reference value in the process of distribution route planning, reduce the planning time and calculation amount, and make the generated distribution route closer to the business scenario and requirements.

[0090] In an embodiment of this application, the above device further includes: a historical route layout set unit, configured to project the historical distribution points included in the historical distribution route into a spatial coordinate system; determine the convex hull contour of the historical distribution points included in each historical distribution route according to the spatial coordinates of each historical distribution point in the spatial coordinate system, and obtain a convex polygon corresponding to each historical distribution route; and store the convex polygons that meet the route constraint conditions as route layouts in the historical route layout set.

[0091] In an embodiment of the present application, in the above device, the circuit layout screening unit 210 is configured to determine candidate time conditions based on the delivery time of the delivery planning task, and determine candidate space conditions based on each delivery point of the delivery planning task; screen out circuit layouts that meet both the candidate time conditions and the candidate space conditions from the historical circuit layout set.

[0092] In an embodiment of the present application, in the above device, the candidate circuit layout template set construction unit 220 is configured to select a circuit layout that matches a specified time interval, construct a circuit layout template corresponding to the specified time interval, and use the constructed circuit layout template as an element in the candidate circuit layout template set.

[0093] In an embodiment of the present application, in the above device, the reference circuit layout template set construction unit 230 is configured to match each circuit layout template in the candidate circuit layout template set with each delivery point of the delivery planning task, and construct a reference circuit layout template set for the delivery planning task according to the matching results, including: taking the ratio of the number of delivery points of the delivery planning task that fall into the circuit layout template to the total number of delivery points of the delivery planning task as the matching rate of the circuit layout template and the delivery planning task; screening out multiple circuit layout templates from the candidate circuit layout template set according to the matching rate; calculating the proportion of the overlapping part between each circuit layout template, and if the proportion of the overlapping part is greater than a preset threshold, taking the corresponding overlapping part as an element in the reference circuit layout template set.

[0094] In an embodiment of the present application, in the above device, the reference circuit layout template set construction unit 230 is configured to assign a first weight value to the original elements in the reference circuit layout template set; screen out eligible elements from the candidate circuit layout template set, assign a second weight value to the screened elements and then add them to the reference circuit layout template set; the first weight value is greater than the second weight value.

[0095] In an embodiment of the present application, in the above device, the planning unit 240 is configured to generate a delivery route including the delivery points of the delivery planning task by using the elements in the reference circuit layout template set as reference data for delivery point clustering according to a preset delivery route generation algorithm; if each element in the reference circuit layout template set includes a weight value, determine the reference priority according to the weight value.

[0096] It should be noted that the specific implementation manners of the above device embodiments can refer to the specific implementation manners of the corresponding method embodiments described above, and will not be elaborated here.

[0097] In summary, for the technical solution of the present application, the circuit layout associated with the distribution planning task is screened from the historical circuit layout set, the candidate circuit layout template set for the distribution planning task is constructed according to the screened circuit layout, each circuit layout template in the candidate circuit layout template set is matched with each distribution point of the distribution planning task, the reference circuit layout template set for the distribution planning task is constructed according to the matching result, and based on the reference circuit layout template set, the distribution route including the distribution points of the distribution planning task is generated. The beneficial effect of this technical solution is that it can give play to the role of historical distribution data, determine the circuit layout by using the spatial geometric features of the historical distribution routes, provide important reference value in the process of distribution route planning, reduce the planning time and calculation amount, and make the generated distribution route closer to the business scenario and requirements.

[0098] It should be noted that:

[0099] The algorithms and displays provided herein are not inherently related to any particular computer, virtual device, or other equipment. Various general-purpose devices can also be used in conjunction with the teachings provided herein. Based on the above description, the structures required to construct such devices are obvious. In addition, the present application is not directed to any specific programming language. It should be understood that the content of the present application described herein can be implemented using various programming languages, and the description of the specific language above is to disclose the best implementation mode of the present application.

[0100] In the specification provided herein, a large number of specific details are described. However, it can be understood that the embodiments of the present application can be practiced without these specific details. In some instances, well-known methods, structures, and technologies are not shown in detail so as not to obscure the understanding of this specification.

[0101] Similarly, it should be understood that, in order to streamline the present application and help understand one or more of the various inventive aspects, in the above description of the exemplary embodiments of the present application, the various features of the present application are sometimes grouped together into a single embodiment, figure, or description thereof. However, the disclosed method should not be construed as reflecting the intention that the claimed present application requires more features than are expressly recited in each claim. Rather, as reflected in the following claims, the inventive aspects lie in less than all the features of the single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into the detailed description, where each claim itself serves as a separate embodiment of the present application.

[0102] Those skilled in the art can understand that the modules in the devices in the embodiments can be adaptively changed and set in one or more devices different from the embodiments. The modules or units or components in the embodiments can be combined into one module or unit or component, and in addition, they can be divided into multiple sub-modules or sub-units or sub-components. Except that at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all the features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all the processes or units of any method or device so disclosed. Unless otherwise clearly stated, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) can be replaced by an alternative feature that provides the same, equivalent, or similar purpose.

[0103] In addition, those skilled in the art can understand that although some of the embodiments described herein include certain features included in other embodiments rather than other features, the combination of the features of different embodiments means that it is within the scope of this application and forms different embodiments. For example, in the following claims, any one of the claimed embodiments can be used in any combination.

[0104] Each component embodiment of the present application can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art should understand that a microprocessor or a digital signal processor (DSP) can be used in practice to implement some or all of the functions of some or all of the components in the distribution route planning device according to the embodiments of the present application. The present application can also be implemented as a device or device program (such as a computer program and a computer program product) for executing part or all of the methods described herein. Such a program implementing the present application can be stored on a computer-readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0105] For example, Figure 3The structural schematic diagram of an electronic device according to an embodiment of the present application is shown. The electronic device 300 includes a processor 310 and a memory 320 arranged to store computer-executable instructions (computer-readable program code). The memory 320 can be an electronic memory such as flash memory, EEPROM (electrically erasable programmable read-only memory), EPROM, hard disk, or ROM. The memory 320 has a storage space 330 for storing computer-readable program code 331 for executing any method step in the above methods. For example, the storage space 330 for storing computer-readable program code may include respective computer-readable program codes 331 for implementing various steps in the above methods. The computer-readable program code 331 can be read from or written into one or more computer program products. These computer program products include program code carriers such as hard disks, compact discs (CDs), memory cards, or floppy disks. Such computer program products are typically, for example Figure 4 the computer-readable storage medium described above. Figure 4 The structural schematic diagram of a computer-readable storage medium according to an embodiment of the present application is shown. The computer-readable storage medium 400 stores computer-readable program code 331 for executing the method steps according to the present application and can be read by the processor 310 of the electronic device 300. When the computer-readable program code 331 runs on the electronic device 300, it causes the electronic device 300 to execute each step in the method described above. Specifically, the computer-readable program code 331 stored in the computer-readable storage medium can execute the method shown in any of the above embodiments. The computer-readable program code 331 can be compressed in an appropriate form.

[0106] It should be noted that the above embodiments illustrate the present application rather than limit the present application, and those skilled in the art can design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present application can be implemented by means of hardware including several different elements and by means of a suitably programmed computer. In a unit claim listing several devices, several of these devices may be embodied by the same item of hardware. The use of the words first, second, and third, etc. does not denote any order. These words can be interpreted as names.

Claims

1. A method for planning a delivery route, comprising: Screening at least one route layout associated with the delivery planning task from a historical route layout set; Constructing a candidate route layout template set for the delivery planning task according to the at least one screened route layout; Matching each route layout template in the candidate route layout template set with each delivery point of the delivery planning task, and constructing a reference route layout template set for the delivery planning task according to the matching result; Generating a delivery route including the delivery points of the delivery planning task based on the reference route layout template set; The historical route layout set is constructed in the following manner: projecting the historical delivery points included in the historical delivery route into a spatial coordinate system, determining the convex hull contour of the historical delivery points included in each historical delivery route according to the spatial coordinates of each historical delivery point in the spatial coordinate system, obtaining a convex polygon corresponding to each historical delivery route, and storing each convex polygon that meets the route constraint conditions as a route layout in the historical route layout set.

2. The method according to claim 1, characterized in that, The screening of the route layout associated with the delivery planning task from the historical route layout set includes: Determining candidate time conditions based on the delivery time of the delivery planning task, and determining candidate space conditions based on each delivery point of the delivery planning task; Screening out the route layouts that meet both the candidate time conditions and the candidate space conditions from the historical route layout set.

3. The method according to claim 2, wherein The constructing of the candidate route layout template set for the delivery planning task according to the screened route layouts includes: Selecting a route layout that matches a specified time interval, constructing a route layout template corresponding to the specified time interval, and taking the constructed route layout template as an element in the candidate route layout template set.

4. The method according to claim 1, characterized in that, The matching of each route layout template in the candidate route layout template set with each delivery point of the delivery planning task, and constructing the reference route layout template set for the delivery planning task according to the matching result includes: Taking the ratio of the number of delivery points of the delivery planning task that fall into the route layout template to the total number of delivery points of the delivery planning task as the matching rate of the route layout template and the delivery planning task; Screening out multiple route layout templates from the candidate route layout template set according to the matching rate; Calculating the proportion of the overlapping part of the layout between each route layout template, and if the proportion of the overlapping part of the layout is greater than a preset threshold, taking the corresponding overlapping part of the layout as an element in the reference route layout template set.

5. The method according to claim 4, wherein The matching of each route layout template in the candidate route layout template set with each delivery point of the delivery planning task, and constructing the reference route layout template set for the delivery planning task according to the matching result further includes: Assigning a first weight value to the original elements in the reference route layout template set; Screening out the elements that meet the conditions from the candidate route layout template set, assigning a second weight value to the screened elements, and adding them to the reference route layout template set; The first weight value is greater than the second weight value.

6. The method according to any one of claims 1-5, characterized in that, Generating a delivery route that includes the delivery points of the delivery planning task based on the reference route layout template set includes: According to a preset delivery route generation algorithm, using the elements in the reference route layout template set as reference data for delivery point clustering, generating a delivery route that includes the delivery points of the delivery planning task; if each element in the reference route layout template set includes a weight value, determining the reference priority according to the weight value.

7. A device for planning a delivery route, comprising: A route layout screening unit, configured to screen at least one route layout associated with a delivery planning task from a historical route layout set; The historical route layout set is constructed in the following manner: projecting the historical delivery points included in a historical delivery route into a spatial coordinate system, determining the convex hull contour of the historical delivery points included in each historical delivery route according to the spatial coordinates of the historical delivery points in the spatial coordinate system, obtaining a convex polygon corresponding to each historical delivery route, and storing the convex polygons that meet the route constraint conditions as route layouts in the historical route layout set; A candidate route layout template set construction unit, configured to construct a candidate route layout template set for the delivery planning task according to the at least one screened route layout; A reference route layout template set construction unit, configured to match each route layout template in the candidate route layout template set with each delivery point of the delivery planning task, and construct a reference route layout template set for the delivery planning task according to the matching result; A planning unit, configured to generate a delivery route that includes the delivery points of the delivery planning task based on the reference route layout template set.

8. An electronic device, wherein, The electronic device includes: a processor; and a memory arranged to store computer-executable instructions, which when executed cause the processor to execute the method according to any one of claims 1-6.

9. A computer-readable storage medium, wherein, The computer-readable storage medium stores one or more programs, which when executed by a processor, implement the method according to any one of claims 1-6.

Images