Take-out delivery route planning method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a take-out delivery route planning method. The method comprises the following steps: acquiring a target delivery task; based on the distribution starting point and the distribution ending point, determining a plurality of distribution routes from the distribution starting point to the distribution ending point and historical distribution data corresponding to the plurality of distribution routes; inputting the historical distribution data into a preset analysis large model for redisk processing to obtain historical distribution influence factors of each distribution route; and determining a target distribution route based on the current distribution influence factor and the historical distribution influence factor of each distribution route. According to the method, the historical delivery data is subjected to redisk processing through the preset analysis large model, the target road is selected according to the historical delivery influence factors obtained through analysis, and the correlation between the historical delivery influence factors and road selection during take-out delivery route planning is comprehensively considered, so that the take-out delivery efficiency after take-out delivery route planning is improved.

Description

Technical Field

[0001] The present invention relates to the field of route planning, and particularly to a method, device, electronic device and storage medium for planning a food delivery route. Background Art

[0002] In the era of rapid development, people can enjoy the service of having food delivered to their homes without leaving home. On existing food delivery platforms, most recommend the shortest path calculated based on map navigation, but often ignore the impact of external factors on the delivery time. It is very easy to cause the actual route to take much longer than the estimated time on the map under certain external factors, resulting in a decrease or even overtime in the order completion efficiency of food delivery riders. Therefore, how to provide a food delivery route planning method that solves the low accuracy of route selection in existing food delivery route planning and thus improves the efficiency of food delivery has become an urgent problem to be solved. Summary of the Invention

[0003] An embodiment of the present invention provides a method for planning a food delivery route, aiming to solve the problem of low accuracy of route selection in existing food delivery route planning, which in turn reduces the efficiency of food delivery. By using a preset analysis large model to review historical delivery data, target roads are selected based on the analyzed historical delivery influencing factors, comprehensively considering the correlation between historical delivery influencing factors and road selection in food delivery route planning, thereby improving the efficiency of food delivery after food delivery route planning.

[0004] In a first aspect, an embodiment of the present invention provides a method for planning a food delivery route, characterized in that the method includes the following steps:

[0005] Obtain a target delivery task, where the target delivery task includes a delivery start point and a delivery end point;

[0006] Based on the delivery start point and the delivery end point, determine a plurality of delivery routes between the delivery start point and the delivery end point and the historical delivery data corresponding to the plurality of delivery routes;

[0007] Input the historical delivery data into a preset analysis large model for review processing to obtain the historical delivery influencing factors of each delivery route;

[0008] Based on the current delivery influencing factors and historical delivery influencing factors of each delivery route, determine a target delivery route.

[0009] Optionally, the determining a plurality of delivery routes between the delivery start point and the delivery end point based on the delivery start point and the delivery end point includes:

[0010] Based on the delivery start point and the delivery end point, divide the target task area;

[0011] Determine at least one passable route between the delivery starting point and the delivery ending point based on the roadmap within the target task area;

[0012] Sort each of the passable routes in ascending order according to the length of the driving mileage to obtain a sorted set of passable routes;

[0013] Extract the multiple delivery routes from the sorted set of passable routes according to preset conditions.

[0014] Optionally, the historical delivery influencing factors include historical delivery weather, historical delivery road damage conditions, historical delivery traffic congestion conditions, and historical delivery time. Inputting the historical delivery data into a preset analysis large model for review processing to obtain the historical delivery influencing factors of each delivery route includes:

[0015] Input the historical delivery data into a preset analysis large model for review processing to obtain the historical delivery weather, historical delivery road damage conditions, historical delivery traffic congestion conditions, and historical delivery time of each delivery route under different time and space.

[0016] Optionally, it is characterized in that the current delivery influencing factors include current delivery weather, current delivery road damage conditions, and current delivery traffic congestion conditions. Determining the target delivery route based on the current delivery influencing factors and historical delivery influencing factors of each delivery route includes:

[0017] Determine the first weight value of each delivery route based on the current delivery weather, historical delivery weather, and historical delivery time of each delivery route;

[0018] Modify the first weight value based on the current delivery road damage conditions and historical delivery road damage conditions of each delivery route to obtain the second weight value of each delivery route;

[0019] Modify the second weight value based on the current delivery traffic congestion conditions and historical delivery traffic congestion conditions of each delivery route to obtain the third weight value of each delivery route;

[0020] Determine the target delivery route from the multiple delivery routes based on the third weight value of each delivery route.

[0021] Optionally, the determining the first weight value of each delivery route based on the current delivery weather, historical delivery weather, and historical delivery time of each delivery route includes:

[0022] Determine the number of waterlogging positions, the waterlogging area occupying the road, and the waterlogging depth of each of the delivery routes based on the historical delivery weather of each of the delivery routes;

[0023] Determine the first delivery delay time of each of the delivery routes based on the number of waterlogging positions, the waterlogging area occupying the road, and the waterlogging depth of each of the delivery routes and the historical delivery time;

[0024] Determine the first weight value of each of the delivery routes based on the first delivery delay time of each of the delivery routes and the current delivery weather.

[0025] Optionally, the modifying the first weight value based on the current delivery road damage conditions and the historical delivery road damage conditions of each of the delivery routes to obtain the second weight value of each of the delivery routes includes:

[0026] Determine the road damage conditions of each of the delivery routes based on the historical delivery road damage conditions of each of the delivery routes;

[0027] Determine the second delivery delay time of each of the delivery routes based on the road damage conditions of each of the delivery routes and the historical delivery time;

[0028] Modify the first weight value based on the second delivery delay time and the current delivery road damage conditions to obtain the second weight value of each of the delivery routes.

[0029] Optionally, the modifying the second weight value based on the current delivery traffic congestion conditions and the historical delivery traffic congestion conditions of each of the delivery routes to obtain the third weight value of each of the delivery routes includes:

[0030] Determine the traffic congestion conditions of each of the delivery routes in different delivery directions based on the historical delivery traffic congestion conditions of each of the delivery routes;

[0031] Determine the third delivery delay time of each of the delivery routes based on the traffic congestion conditions of each of the delivery routes in different delivery directions and the historical delivery time;

[0032] Modify the second weight value based on the third delivery delay time and the current delivery traffic congestion conditions to obtain the third weight value of each of the delivery routes.

[0033] In a second aspect, an embodiment of the present invention further provides an off - premise food delivery route planning device, where the off - premise food delivery route planning device includes:

[0034] A first acquisition module, configured to acquire a target delivery task, where the target delivery task includes a delivery start point and a delivery end point;

[0035] A first determination module, configured to determine multiple delivery routes between the delivery starting point and the delivery ending point, and historical delivery data corresponding to the multiple delivery routes, based on the delivery starting point and the delivery ending point;

[0036] A first review module, configured to input the historical delivery data into a preset analysis large model for review processing, to obtain historical delivery influencing factors for each of the delivery routes;

[0037] A second determination module, configured to determine a target delivery route based on current delivery influencing factors and historical delivery influencing factors for each of the delivery routes.

[0038] In a third aspect, an embodiment of the present invention provides an electronic device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where when the processor executes the computer program, the steps in the method for planning a takeaway delivery route provided by the embodiment of the present invention are implemented.

[0039] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps in the method for planning a takeaway delivery route provided by the embodiment of the invention are implemented.

[0040] In an embodiment of the present invention, a target delivery task is obtained, and the target delivery task includes a delivery starting point and a delivery ending point; based on the delivery starting point and the delivery ending point, multiple delivery routes between the delivery starting point and the delivery ending point and historical delivery data corresponding to the multiple delivery routes are determined; the historical delivery data is input into a preset analysis large model for review processing, to obtain historical delivery influencing factors for each of the delivery routes; based on current delivery influencing factors and historical delivery influencing factors for each of the delivery routes, a target delivery route is determined. By performing review processing on historical delivery data through a preset analysis large model, and selecting a target road according to the analyzed historical delivery influencing factors, the correlation between historical delivery influencing factors and road selection in takeaway delivery route planning is comprehensively considered, thereby improving the efficiency of takeaway delivery after takeaway delivery route planning. Description of the Drawings

[0041] To more clearly illustrate the technical solutions in the embodiments of the present invention or in the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0042] Figure 1It is a flowchart of a method for planning a food delivery route provided by an embodiment of the present invention;

[0043] Figure 2 It is a flowchart of another method for planning a food delivery route provided by an embodiment of the present invention;

[0044] Figure 3 It is a schematic structural diagram of a device for planning a food delivery route provided by an embodiment of the present invention;

[0045] Figure 4 It is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. Detailed implementation manners

[0046] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0047] As Figure 1 shown, Figure 1 It is a flowchart of a method for planning a food delivery route provided by an embodiment of the present invention, including:

[0048] 101. Obtain a target delivery task.

[0049] In the embodiments of the present invention, the above-mentioned method for planning a food delivery route can be applied to a route planning platform, which can be constructed by a server or a server cluster. The server or the server cluster can be any electronic device with functions such as image recognition, data processing, data storage, and data transmission. The above-mentioned route planning platform can obtain a target delivery task according to the order input by the user, plan a route according to the target delivery task, and provide a high-quality route for the delivery personnel to select.

[0050] The above-mentioned target delivery task includes a delivery start point and a delivery end point. The above-mentioned delivery start point can be the merchant location or the current location of the delivery person, and the above-mentioned delivery end point can be the food delivery location. Specifically, when the user places an order through the food delivery platform, the food delivery platform can use the delivery address and the merchant address input by the user as the above-mentioned target delivery task.

[0051] In a possible embodiment, after the user places an order through the food delivery platform, the food delivery platform may use the delivery address input by the user and the merchant address as the above-mentioned target delivery task, and transmit the above-mentioned target delivery task to the above-mentioned route planning platform through the above-mentioned data transmission function. The above-mentioned route planning platform performs route planning based on the above-mentioned target delivery task to obtain a target delivery route, and sends the above-mentioned target delivery route to the terminal device of the delivery person for the delivery person to select.

[0052] 102. Based on the delivery starting point and the delivery ending point, determine multiple delivery routes between the delivery starting point and the delivery ending point and the historical delivery data corresponding to the multiple delivery routes.

[0053] In the embodiment of the present invention, the above-mentioned delivery route may be a route with a shorter driving distance. The driving distances of the above-mentioned multiple delivery routes should not differ too much from the shortest driving distance. For example, if the shortest driving distance is 4.5 kilometers, the driving distance of the No. 1 delivery route is 5 kilometers, the driving distance of the No. 2 delivery route is 5.8 kilometers, and the driving distance of the No. 3 delivery route is 10 kilometers, then since the No. 3 route differs too much from the shortest driving distance, the No. 3 delivery route will be excluded.

[0054] Specifically, the delivery starting point can be used as one boundary point, the delivery ending point can be used as another boundary point, and the two boundary points are connected by a straight line to obtain the shortest driving distance from the delivery starting point to the delivery ending point. Based on the above-mentioned shortest driving distance, determine the center point between the above-mentioned delivery starting point and the delivery ending point. Use the above-mentioned center point as the center of the circle and the above-mentioned shortest driving distance as the diameter to determine a target task area in the target city road map. In the above-mentioned target task area, determine multiple routes close to the above-mentioned shortest driving distance as the above-mentioned delivery routes.

[0055] The above-mentioned target city road map may include the location of the above-mentioned delivery starting point, the location of the above-mentioned delivery ending point, and the non-motor vehicle passage roads in the above-mentioned target city. The above-mentioned historical delivery data may include a historical delivery image sequence or historical delivery images. The above-mentioned historical delivery images or historical delivery image sequence are collected by road acquisition cameras on the delivery route, and the above-mentioned historical delivery data may be stored in the storage medium of the above-mentioned route planning platform.

[0056] In a possible embodiment, when the above-mentioned route planning platform obtains the above-mentioned target delivery task, based on the delivery starting point and the delivery ending point, in the above-mentioned target city road map, determine a route planning area, and in the above-mentioned route planning area, determine multiple routes close to the shortest driving distance as the above-mentioned delivery routes, and according to each of the above-mentioned delivery routes, determine the historical delivery data of each of the above-mentioned delivery routes.

[0057] 103. Input the historical delivery data into a preset analysis large model for review processing to obtain the historical delivery influencing factors for each delivery route.

[0058] In the embodiments of the present invention, the above-mentioned preset analysis large model can be understood as a large deep learning model for computer vision tasks, usually having a large number of parameters and a large amount of computation, and can be used to process a large amount of historical delivery data to extract the historical delivery influencing factors for each delivery route. The above-mentioned preset analysis large model can be the ChatGPT large model, the Wenxin Yiyan large model, the Cloud Lark large model, the Baichuan large model, etc.

[0059] Specifically, the historical delivery data of each delivery route can be input into the above-mentioned preset analysis large model to extract the delivery influencing features in the historical delivery image sequence of each delivery route. According to the above-mentioned delivery influencing features, the historical delivery influencing factors for each delivery route are determined, and according to the acquisition time of the start frame and the end frame of the historical delivery image sequence, the historical delivery time is determined. The above-mentioned delivery influencing features can be determined according to the historical delivery time.

[0060] In a possible embodiment, when the above-mentioned route planning platform determines multiple delivery routes between the delivery start point and the delivery end point and the historical delivery data corresponding to the multiple delivery routes based on the delivery start point and the delivery end point, the above-mentioned delivery routes and the corresponding historical delivery data are input into a preset analysis large model for review processing to extract the above-mentioned delivery influencing features, and according to the above-mentioned delivery influencing features and the above-mentioned historical delivery time, the above-mentioned historical delivery influencing factors are determined.

[0061] 104. Determine the target delivery route based on the current delivery influencing factors and the historical delivery influencing factors for each delivery route.

[0062] In the embodiments of the present invention, the above-mentioned current delivery influencing factors are determined according to the above-mentioned historical delivery influencing factors. For example, if the above-mentioned historical delivery influencing factors include thunderstorms and heavy rain days, then the current road image sequence can be collected through a road acquisition camera deployed on the above-mentioned delivery route, and image recognition is performed according to the current road image sequence to determine whether the current delivery influencing factors include thunderstorms or heavy rain days. The above-mentioned image recognition can be processed through the above-mentioned preset analysis large model.

[0063] Specifically, the delivery delay time caused by the historical delivery influencing factors in different situations can be determined according to the historical delivery data. Based on the above-mentioned delivery delay time and the above-mentioned current delivery influencing factors, the weight of the current delivery route is determined. According to the weight of the current delivery route, the delivery route with the highest weight is selected as the above-mentioned target delivery route and pushed to the terminal device of the delivery personnel.

[0064] For example, when the historical delivery influencing factors of the first delivery route and the second delivery route include thunderstorms and heavy rain days, and based on the historical delivery data of the first delivery route, the historical delivery time of the first delivery route on sunny days is 15 minutes, on heavy rain days is 30 minutes, and on thunderstorm days is 25 minutes. According to the historical delivery data of the second delivery route, the historical delivery time of the second delivery route on sunny days is 20 minutes, on heavy rain days is 40 minutes, and on thunderstorm days is 28 minutes. If the current delivery influencing factors of the first delivery route and the second delivery route are heavy rain days, then it can be determined that the delivery delay time of the first delivery route on heavy rain days is 15 minutes, and the delay time of the second delivery route on heavy rain days is 20 minutes. Based on the above delay times, the weight of the current first delivery route is determined to be 80%, and the weight of the second delivery route is 65%. When the historical delivery influencing factors of the first delivery route and the second delivery route do not include other delivery influencing factors, then the first delivery route can be determined as the target delivery route.

[0065] Or, when the historical delivery influencing factors of the first delivery route also include the number of congested vehicles, then the number of congested vehicles and the corresponding travel time can be calculated based on the historical number of congested vehicles. Based on the travel time corresponding to the number of congested vehicles and the travel time when the number of congested vehicles is zero, the delay time of the first delivery route at different numbers of congested vehicles can be determined. And the number of congested vehicles corresponding to the current delivery influencing factors of the first delivery route is 20, and the delay time is 5 minutes. At this time, the weight of the first delivery route can be adjusted downward based on the 5-minute delay time and determined to be 60%. Since the historical delivery influencing factors of the second delivery route do not include other delivery influencing factors, at this time, the second delivery route can be determined as the above target delivery route.

[0066] In a possible embodiment, when the above route planning platform inputs the historical delivery data into a preset analysis large model for review processing, and after obtaining the historical delivery influencing factors of each delivery route, the current road image sequence corresponding to the delivery route can be collected through a road acquisition camera according to the above historical delivery influencing factors. The current road image sequence and the historical delivery influencing factors are input into the above preset analysis large model for image recognition to determine the current delivery influencing factors corresponding to the historical delivery influencing factors. The delivery delay time is determined according to the above historical delivery influencing factors, the weights of each delivery route are determined according to the delivery delay time, and the delivery route with the largest weight is used as the above target delivery route.

[0067] In an embodiment of the present invention, a target delivery task is obtained, and the target delivery task includes a delivery starting point and a delivery ending point; based on the delivery starting point and the delivery ending point, a plurality of delivery routes between the delivery starting point and the delivery ending point and historical delivery data corresponding to the plurality of delivery routes are determined; the historical delivery data is input into a preset analysis large model for review processing to obtain historical delivery influencing factors for each of the delivery routes; based on the current delivery influencing factors and the historical delivery influencing factors for each of the delivery routes, a target delivery route is determined. By performing review processing on the historical delivery data through a preset analysis large model and selecting a target road according to the analyzed historical delivery influencing factors, the correlation between the historical delivery influencing factors and the road selection in the takeaway delivery route planning is comprehensively considered, thereby improving the efficiency of takeaway delivery after the takeaway delivery route planning.

[0068] It can be understood that in the specific implementation manner of the present application, data related to face images, vehicle images, road images, etc. are involved. When the embodiments in the present application are applied to specific products or technologies, user permission or consent needs to be obtained, and the collection, use, and processing of relevant data need to comply with relevant laws, regulations, and standards in relevant countries and regions.

[0069] Optionally, in the step of determining a plurality of delivery routes between the delivery starting point and the delivery ending point based on the delivery starting point and the delivery ending point, a target task area can also be divided based on the delivery starting point and the delivery ending point; based on the road map within the target task area, at least one passable route between the delivery starting point and the delivery ending point is determined; each passable route is sorted from small to large according to the length of the driving mileage to obtain a sorted set of passable routes; according to a preset condition, a plurality of delivery routes are extracted from the sorted set of passable routes.

[0070] In an embodiment of the present invention, the above target task area can be any regular shape. For example, it can be circular or rectangular. The delivery starting point can be used as one boundary point, the delivery ending point can be used as the other boundary point, and the two boundary points are connected by a straight line to obtain the shortest driving distance from the delivery starting point to the delivery ending point. Based on the above shortest driving distance, the center point between the above delivery starting point and the delivery ending point is determined. Based on the above center point as a reference and the above shortest driving distance as a side, the above target task area is determined. The road map within the above target task area can be obtained through real-time satellite images or map applications, etc.

[0071] The above preset condition can be set according to the above shortest driving distance. For example, if the shortest driving distance is 20 kilometers, the above preset condition can be set to use the route with a driving distance within 25 kilometers as the delivery route.

[0072] For example, if the above-mentioned shortest driving distance is 20 kilometers, then based on the above-mentioned central point, the area within a radius of 20 kilometers centered on the above-mentioned central point can be divided into a target task area. Based on the road map within the target task area, determine the passable routes between the delivery starting point and the delivery ending point, and extract the passable routes similar to the above-mentioned shortest driving distance from large to small according to the driving mileage of the passable routes as each delivery route.

[0073] Specifically, a sorting empty set can be established before sorting, and each passable route can be input into the above-mentioned sorting empty set in ascending order according to the length of the driving mileage to obtain a passable route sorting set. According to preset conditions, multiple passable routes are extracted from the above-mentioned passable route sorting set as the above-mentioned delivery routes.

[0074] It should be noted that the above-mentioned road map may include roads under repair or roads where non-motor vehicles are prohibited from passing. Therefore, it is necessary to determine the roads that can be passed when the delivery personnel ride non-motor vehicles as the above-mentioned passable roads.

[0075] Optionally, in the step of inputting historical delivery data into a preset analysis large model for review processing to obtain the historical delivery influencing factors of each delivery route, the historical delivery data can also be input into the preset analysis large model for review processing to obtain the historical delivery weather, historical delivery road damage conditions, historical delivery traffic congestion conditions, and historical delivery time of each delivery route under different time and space.

[0076] In the embodiment of the present invention, the above-mentioned historical delivery influencing factors may include historical delivery weather, historical delivery road damage conditions, historical delivery traffic congestion conditions, and historical delivery time. The above-mentioned historical delivery weather may include heavy rain, strong wind, snowy days, etc. The above-mentioned historical road damage conditions may be road potholes, road damage, road fractures, etc. Generally, the road traffic is often two-way (i.e., including two symmetric traffic directions). Therefore, the above-mentioned historical delivery traffic congestion conditions include the congestion conditions of both traffic directions.

[0077] It should be noted that the historical delivery traffic congestion conditions may change under different time and space. For example, during the morning rush hour on the first delivery route, the first traffic direction will be congested, and the second traffic direction will not be congested. During the evening rush hour, the second traffic direction will be congested, and the first traffic direction will not be congested. Similarly, the historical delivery weather and historical road damage conditions may also change.

[0078] Specifically, the above-mentioned historical delivery data can be input into a preset analysis large model for review processing to obtain the delivery influence characteristics of each delivery route, and according to the above-mentioned delivery influence characteristics, the historical delivery influencing factors of each delivery route are determined.

[0079] For example, it can be illustrated according to the weather characteristics in the historical delivery image sequence of the delivery route. The historical delivery time on a sunny day is 15 minutes, on a cloudy day is 15 minutes, on a partly cloudy day is 15 minutes, on a thunderstorm day is 18 minutes, and on a heavy rain day is 25 minutes. Then, based on the historical delivery time, it can be determined that the delivery impact characteristics include weather, and the corresponding historical delivery impact factors of the delivery impact characteristics include the historical delivery impact weather, that is, thunderstorm and heavy rain days.

[0080] Or it can be illustrated according to the road damage situation in the historical delivery image sequence of the delivery route. When the road of the delivery route is an intact road without damage, its historical delivery time is 15 minutes; when the road of the delivery route is a slightly damaged road, its historical delivery time is 18 minutes; when the road of the delivery route is a severely damaged road, its historical delivery time is 25 minutes. Then, based on the historical delivery time, it can be determined that the delivery impact characteristics include the road damage situation, and the corresponding historical delivery impact factors of the delivery impact characteristics include the historical delivery road disease situation, that is, slightly damaged roads and severely damaged roads.

[0081] Or it can also be illustrated according to the traffic congestion situation in the historical delivery image sequence of the delivery route. When there is traffic congestion on the delivery route and the number of congested vehicles is 50, its historical delivery time is 60 minutes; when there is traffic congestion on the delivery route and the number of congested vehicles is 30, its historical delivery time is 40 minutes; when there is no traffic congestion on the delivery route, its historical delivery time is 20 minutes. Then, based on the historical delivery time, it can be determined that the delivery impact characteristics include the road congestion situation, and the corresponding historical delivery impact factors of the delivery impact characteristics include the historical delivery traffic congestion situation, that is, the number of congested vehicles.

[0082] It should be noted that the delivery impact characteristics of different delivery routes are different, and the corresponding historical delivery impact factors are also different. For example, the first delivery route is a non-motor vehicle lane throughout the whole journey and there will be no traffic congestion. At this time, the delivery impact characteristics of the first delivery route do not include the road congestion situation. The second delivery route includes a motor vehicle lane. At this time, the delivery impact characteristics of the second delivery route include the road congestion situation.

[0083] Another example is that the first delivery route is a non-open-air road and is not affected by the weather. At this time, the delivery impact characteristics of the first delivery route do not include the weather. The second delivery route is an open-air road and is affected by the weather. At this time, the delivery impact characteristics of the second delivery route include the weather.

[0084] For another example, the first delivery route is a non-open-air road, but its rain shelter is made of glass. Due to the reflectivity of the glass material, it will affect the vision of the delivery personnel and cause the driving speed to decrease. At this time, the delivery impact characteristics of the first delivery route include the weather, but the corresponding historical delivery impact factors include sunny days, excluding thunderstorms and heavy rain days.

[0085] Optionally, in the step of determining the target delivery route based on the current delivery impact factors and historical delivery impact factors of each delivery route, the first weight value of each delivery route can also be determined based on the current delivery weather, historical delivery weather, and historical delivery time of each delivery route; based on the current delivery road damage condition and historical delivery road damage condition of each delivery route, the first weight value is corrected to obtain the second weight value of each delivery route; based on the current delivery traffic congestion condition and historical delivery traffic congestion condition of each delivery route, the second weight value is corrected to obtain the third weight value of each delivery route; based on the third weight value of each delivery route, the target delivery route is determined among multiple delivery routes.

[0086] In the embodiment of the present invention, the above-mentioned current delivery impact factors may include the current delivery weather, the current delivery road damage condition, and the current delivery traffic congestion condition, and the current delivery impact factors of each delivery route can be determined according to the corresponding historical delivery impact factors. For example, the historical delivery impact factors of the first delivery route include the historical delivery weather and the historical delivery traffic congestion condition, then the current road image sequence of each delivery route can be collected through a road acquisition camera, and based on the current road image sequence, vehicle recognition processing and weather recognition processing are performed to obtain the current delivery weather and the current delivery traffic congestion condition.

[0087] Specifically, an initial weight can be set according to the driving distance of the delivery route before determining the first weight value. The above-mentioned initial weight is inversely proportional to the above-mentioned driving distance. When the driving distance of the delivery route is longer, the initial weight is lower, and vice versa. The first delivery delay time is determined according to the current delivery weather, historical delivery weather, and historical delivery time, and the initial weight is adjusted up or down according to the first delivery delay time to obtain the above-mentioned first weight value. The above-mentioned first delivery delay time and the above-mentioned first weight value are negatively correlated.

[0088] After obtaining the above-mentioned first weight value, the second delivery delay time can be determined based on the current delivery road damage condition and historical delivery road damage condition, and the above-mentioned first weight value is adjusted up or down according to the second delivery delay time to obtain the second weight value. The above-mentioned second delivery delay time and the above-mentioned second weight value are negatively correlated.

[0089] After obtaining the above second weight value, the third delivery delay time can be determined based on the current delivery traffic congestion and the historical delivery traffic congestion. According to the third delivery delay time, the second weight value can be increased or decreased to obtain the third weight value of each delivery route. The above third delivery delay time and the above third weight value are negatively correlated.

[0090] According to the third weight value of each delivery route, determine the delivery route with the largest third weight value, and use the delivery route with the largest third weight value as the above target delivery route.

[0091] Optionally, in the step of determining the first weight value of each delivery route based on the current delivery weather, historical delivery weather, and historical delivery time of each delivery route, the number of water accumulation positions, the water accumulation occupation area, and the water accumulation depth of each delivery route can also be determined based on the historical delivery weather of each delivery route; based on the number of water accumulation positions, the water accumulation occupation area, the water accumulation depth, and the historical delivery time of each delivery route, determine the first delivery delay time of each delivery route; based on the first delivery delay time and the current delivery weather of each delivery route, determine the first weight value of each delivery route.

[0092] In the embodiment of the present invention, the number of water accumulation positions, the water accumulation occupation area, and the water accumulation depth of each delivery route at different rainfall amounts can be determined based on the historical delivery weather of each delivery route. Based on the number of water accumulation positions, the water accumulation occupation area, and the water accumulation depth of each delivery route at different rainfall amounts, determine the first delivery delay time of each delivery route at different rainfall amounts. Match the rainfall amount of the current delivery weather with the rainfall amounts corresponding to each first delivery delay time to obtain the first delivery delay time with the same rainfall amount as the above first delivery delay time. According to the first delivery delay time with the same rainfall amount, determine the first weight value of each delivery route.

[0093] Or, the reference historical delivery time of each delivery route can also be determined according to the maximum speed limit and the driving distance of each delivery route. Subtract the historical delivery time at different rainfall amounts from the above reference historical delivery time to obtain the first delivery delay time at different rainfall amounts. Match the rainfall amount of the current delivery weather with the rainfall amounts corresponding to each first delivery delay time to obtain the first delivery delay time with the same rainfall amount.

[0094] It should be noted that due to the different depths and positions of potholes and the different drainage capacities of the drainage systems between delivery routes, different water accumulation occupation areas and water accumulation depths may occur at different rainfall amounts, and the number of water accumulation positions will also increase with the increase of rainfall amount. And different degrees of water accumulation occupation area, water accumulation depth, and the number of water accumulation positions will affect the cycling of delivery personnel during the delivery process.

[0095] According to the above first delivery delay time, correct the above initial weight value to obtain the above first weight value. When the above first delivery delay time is longer, the above first weight value is lower; conversely, the above first weight value is higher.

[0096] Optionally, in the step of correcting the first weight value based on the current road damage conditions and historical road damage conditions of each delivery route to obtain the second weight value of each delivery route, the road damage conditions of each delivery route can also be determined based on the historical road damage conditions of each delivery route; the second delivery delay time of each delivery route can be determined based on the road damage conditions and historical delivery times of each delivery route; the first weight value is corrected based on the second delivery delay time and the current road damage conditions to obtain the second weight value of each delivery route.

[0097] In the embodiment of the present invention, the road damage conditions of each delivery route can be determined based on the historical road damage conditions of each delivery route, and the second delivery delay time of each delivery route can be determined based on the road damage conditions and historical delivery times of each delivery route.

[0098] For example, at the t-th moment, the road damage condition of the first delivery route is 20% damaged, the historical delivery time of the first delivery route is 20 minutes. At the (t + 1)-th moment, the road damage condition of the first delivery route is 25% damaged, the historical delivery time of the first delivery route is 25 minutes. At the (t + 2)-th moment, the road damage condition of the first delivery route is 30% damaged, the historical delivery time of the first delivery route is 30 minutes. At the last moment, the road damage condition of the first delivery route is 35% damaged, the historical delivery time of the first delivery route is 35 minutes. Then it can be inferred that the damage of the first delivery route at the current moment may be 40%. Based on the relative ratio of the delivery time and the damage condition of the first delivery route at the above last moment, the historical delayed delivery time is determined, and the second delivery delay time of the first delivery route is determined according to the above relative ratio and the damage at the current moment.

[0099] It should be noted that when the road damage condition of the delivery route is not manually intervened, it will become more serious as the number of vehicle passages increases, and the number of vehicle passages on a road is often roughly constant. Therefore, the inference according to the above method has a certain tolerance. And the road damage condition may affect the riding of the delivery personnel during the delivery.

[0100] After obtaining the above-mentioned second delivery delay time, the first weight value can be corrected according to the second delivery delay time to obtain a second weight value. When the second delivery delay time is longer, the second weight value is lower; conversely, when the second delivery delay time is shorter, the second weight value is higher.

[0101] Optionally, in the step of correcting the second weight value based on the current delivery traffic congestion situation and historical delivery traffic congestion situation of each delivery route to obtain the third weight value of each delivery route, the traffic congestion situation of each delivery route in different delivery directions can also be determined based on the historical delivery traffic congestion situation of each delivery route; based on the traffic congestion situation of each delivery route in different delivery directions and the historical delivery time, the third delivery delay time of each delivery route can be determined; based on the third delivery delay time and the current delivery traffic congestion situation, the second weight value can be corrected to obtain the third weight value of each delivery route.

[0102] In the embodiments of the present invention, the historical delivery traffic congestion situation may change in different time and space. For example, for the first delivery route during the morning rush hour, congestion occurs in the first traffic direction and no congestion occurs in the second traffic direction; during the evening rush hour, congestion occurs in the second traffic direction and no congestion occurs in the first traffic direction. Therefore, it is necessary to determine the traffic congestion situation of each delivery route in different delivery directions, determine the third delivery delay time in different delivery directions, and match the current delivery traffic congestion situation with the third delivery delay time in different delivery directions to obtain the above-mentioned third delivery delay time.

[0103] After obtaining the above-mentioned third delivery delay time, the second weight value can be corrected according to the third delivery delay time to obtain a third weight value. When the third delivery delay time is longer, the third weight value is lower; conversely, when the third delivery delay time is shorter, the third weight value is higher.

[0104] As Figure 2 shown, the embodiments of the present invention also provide a flowchart of another method for planning a food delivery route, including:

[0105] According to the starting point and the destination, obtain the historical route data of the group of food delivery riders in the same area of the platform or obtain the set of the shortest recommended routes on the map. Based on the above historical route data or the set of the shortest routes, determine the set of pre-recommended routes. Obtain the weather information of each pre-recommended route in the set of pre-recommended routes in real time. If it is sunny, do not correct the weight value of each pre-recommended route. If it is rainy, use the road waterlogging algorithm to obtain the road conditions in real time. According to the number of waterlogging positions, the waterlogging area occupying the road, the waterlogging depth, etc., judge the waterlogging situation of the pre-recommended road. When the waterlogging situation is no waterlogging, do not correct the weight value of the pre-recommended route. When the waterlogging situation is slight waterlogging, appropriately increase the weight value of the travel time and appropriately reduce the recommendation probability. When the waterlogging situation is severe waterlogging, increase the weight value of the travel time and reduce the recommendation probability.

[0106] Use the road damage algorithm to obtain the road conditions in real time, and determine whether the road is damaged. When there is no damage, do not correct the weight value of the travel time. When it is slightly damaged, appropriately increase the weight value of the travel time and appropriately reduce the recommendation probability. When it is severely damaged, increase the weight value of the travel time and reduce the recommendation probability.

[0107] Obtain the traffic congestion situation of each pre-recommended road in real time. When it is congested, appropriately increase the weight value of the travel time and reduce the recommendation probability.

[0108] Finally, obtain the corrected weight value, and use the pre-recommended road with the largest corrected weight value as the target road.

[0109] As Figure 3 shown, an embodiment of the present invention further provides a food delivery route planning device, including:

[0110] The first acquisition module 301 is used to acquire a target delivery task, and the target delivery task includes a delivery starting point and a delivery ending point;

[0111] The first determination module 302 is used to determine a plurality of delivery routes between the delivery starting point and the delivery ending point and the historical delivery data corresponding to the plurality of delivery routes based on the delivery starting point and the delivery ending point;

[0112] The first review module 303 is used to input the historical delivery data into a preset analysis large model for review processing to obtain the historical delivery influencing factors of each delivery route;

[0113] The second determination module 304 is used to determine a target delivery route based on the current delivery influencing factors and the historical delivery influencing factors of each delivery route.

[0114] Optionally, the first determination module 302 includes:

[0115] A sub-module for dividing a target task area based on the delivery origin and the delivery destination;

[0116] A first determination sub-module for determining at least one passable route between the delivery origin and the delivery destination based on the road map within the target task area;

[0117] A sorting sub-module for sorting each of the passable routes in ascending order according to the length of the driving mileage to obtain a sorted set of passable routes;

[0118] An extraction sub-module for extracting the plurality of delivery routes from the sorted set of passable routes according to preset conditions.

[0119] Optionally, the first review module 303 includes:

[0120] A review sub-module for inputting the historical delivery data into a preset analysis large model for review processing to obtain the historical delivery weather, historical delivery road damage conditions, historical delivery traffic congestion conditions, and historical delivery times of each of the delivery routes at different times and spaces.

[0121] Optionally, the second determination module 304 includes:

[0122] A second determination sub-module for determining a first weight value for each of the delivery routes based on the current delivery weather, historical delivery weather, and historical delivery times of each of the delivery routes;

[0123] A first correction sub-module for correcting the first weight value based on the current delivery road damage conditions and historical delivery road damage conditions of each of the delivery routes to obtain a second weight value for each of the delivery routes;

[0124] A second correction sub-module for correcting the second weight value based on the current delivery traffic congestion conditions and historical delivery traffic congestion conditions of each of the delivery routes to obtain a third weight value for each of the delivery routes;

[0125] A third determination sub-module for determining a target delivery route from the plurality of delivery routes based on the third weight value of each of the delivery routes.

[0126] Optionally, the second determination sub-module includes:

[0127] A first determination unit for determining the number of water accumulation positions, the water accumulation occupation area, and the water accumulation depth of each of the delivery routes based on the historical delivery weather of each of the delivery routes;

[0128] A second determination unit, configured to determine a first delivery delay time for each of the delivery routes based on the number of water accumulation positions, the water accumulation occupation area, the water accumulation depth of each of the delivery routes, and the historical delivery time;

[0129] A third determination unit, configured to determine a first weight value for each of the delivery routes based on the first delivery delay time of each of the delivery routes and the current delivery weather.

[0130] Optionally, the first correction sub-module includes:

[0131] A fourth determination unit, configured to determine the road damage condition of each of the delivery routes based on the historical delivery road damage condition of each of the delivery routes;

[0132] A fifth determination unit, configured to determine a second delivery delay time for each of the delivery routes based on the road damage condition of each of the delivery routes and the historical delivery time;

[0133] A first correction unit, configured to correct the first weight value based on the second delivery delay time and the current delivery road damage condition to obtain a second weight value for each of the delivery routes.

[0134] Optionally, the second correction sub-module includes:

[0135] A sixth determination unit, configured to determine the traffic congestion condition of each of the delivery routes in different delivery directions based on the historical delivery traffic congestion condition of each of the delivery routes;

[0136] A seventh determination unit, configured to determine a third delivery delay time for each of the delivery routes based on the traffic congestion condition of each of the delivery routes in different delivery directions and the historical delivery time;

[0137] A second correction unit, configured to correct the second weight value based on the third delivery delay time and the current delivery traffic congestion condition to obtain a third weight value for each of the delivery routes.

[0138] As Figure 4 shown, an embodiment of the present invention further provides an electronic device, which is characterized by including a processor, and the above processor can execute any one of the above takeaway delivery route planning methods.

[0139] Specifically, it includes a processor 401, a memory 402, and a computer program for executing the takeaway delivery route planning method stored on the memory 402 and capable of running on the processor 401, where:

[0140] The processor 401 runs the calculator program of the takeaway delivery route planning method stored in the memory 402 and executes the following steps:

[0141] Obtain a target delivery task, where the target delivery task includes a delivery starting point and a delivery ending point;

[0142] Based on the delivery starting point and the delivery ending point, determine multiple delivery routes between the delivery starting point and the delivery ending point and historical delivery data corresponding to the multiple delivery routes;

[0143] Input the historical delivery data into a preset analysis large model for review processing to obtain historical delivery influencing factors for each of the delivery routes;

[0144] Based on the current delivery influencing factors and historical delivery influencing factors for each of the delivery routes, determine a target delivery route.

[0145] Optionally, the determining, by the processor 401, multiple delivery routes between the delivery starting point and the delivery ending point based on the delivery starting point and the delivery ending point includes:

[0146] Based on the delivery starting point and the delivery ending point, divide a target task area;

[0147] Based on a road map within the target task area, determine at least one passable route between the delivery starting point and the delivery ending point;

[0148] Sort each of the passable routes in ascending order according to the length of the driving mileage to obtain a sorted set of passable routes;

[0149] Extract the multiple delivery routes from the sorted set of passable routes according to a preset condition.

[0150] Optionally, the historical delivery influencing factors executed by the processor 401 include historical delivery weather, historical delivery road disease conditions, historical delivery traffic congestion conditions, and historical delivery time. The inputting the historical delivery data into a preset analysis large model for review processing to obtain historical delivery influencing factors for each of the delivery routes includes:

[0151] Input the historical delivery data into a preset analysis large model for review processing to obtain historical delivery weather, historical delivery road disease conditions, historical delivery traffic congestion conditions, and historical delivery time for each of the delivery routes at different times and spaces.

[0152] Optionally, the current delivery influencing factors executed by the processor 401 include current delivery weather, current delivery road disease conditions, and current delivery traffic congestion conditions. The determining, based on the current delivery influencing factors and historical delivery influencing factors for each of the delivery routes, a target delivery route includes:

[0153] Determine the first weight value of each of the delivery routes based on the current delivery weather, historical delivery weather, and historical delivery time of each of the delivery routes;

[0154] Based on the current delivery road damage conditions and historical delivery road damage conditions of each of the delivery routes, correct the first weight value to obtain the second weight value of each of the delivery routes;

[0155] Based on the current delivery traffic congestion conditions and historical delivery traffic congestion conditions of each of the delivery routes, correct the second weight value to obtain the third weight value of each of the delivery routes;

[0156] Based on the third weight value of each of the delivery routes, determine the target delivery route among the multiple delivery routes.

[0157] Optionally, the determination of the first weight value of each of the delivery routes by the processor 401 based on the current delivery weather, historical delivery weather, and historical delivery time of each of the delivery routes includes:

[0158] Based on the historical delivery weather of each of the delivery routes, determine the number of water accumulation positions, the water accumulation area occupying the road, and the water accumulation depth of each of the delivery routes;

[0159] Based on the number of water accumulation positions, the water accumulation area occupying the road, the water accumulation depth of each of the delivery routes, and the historical delivery time, determine the first delivery delay time of each of the delivery routes;

[0160] Based on the first delivery delay time of each of the delivery routes and the current delivery weather, determine the first weight value of each of the delivery routes.

[0161] Optionally, the correction of the first weight value by the processor 401 based on the current delivery road damage conditions and historical delivery road damage conditions of each of the delivery routes to obtain the second weight value of each of the delivery routes includes:

[0162] Based on the historical delivery road damage conditions of each of the delivery routes, determine the road damage conditions of each of the delivery routes;

[0163] Based on the road damage conditions of each of the delivery routes and the historical delivery time, determine the second delivery delay time of each of the delivery routes;

[0164] Based on the second delivery delay time and the current delivery road damage conditions, correct the first weight value to obtain the second weight value of each of the delivery routes.

[0165] Optionally, the processor 401 corrects the second weight value based on the current delivery traffic congestion conditions and historical delivery traffic congestion conditions of each of the delivery routes to obtain a third weight value for each of the delivery routes, including:

[0166] Based on the historical delivery traffic congestion conditions of each of the delivery routes, determine the traffic congestion conditions of each of the delivery routes in different delivery directions;

[0167] Based on the traffic congestion conditions of each of the delivery routes in different delivery directions and the historical delivery time, determine the third delivery delay time for each of the delivery routes;

[0168] Based on the third delivery delay time and the current delivery traffic congestion conditions, correct the second weight value to obtain a third weight value for each of the delivery routes.

[0169] The embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements each process of the takeaway delivery route planning method or the application-side takeaway delivery route planning method provided by the embodiment of the present invention, and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0170] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The above computer program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, the above computer-readable storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM), etc.

[0171] The above-disclosed are only the preferred embodiments of the present invention. Of course, the scope of the rights of the present invention cannot be limited thereby. Therefore, equivalent changes made according to the claims of the present invention still fall within the scope covered by the present invention.

Claims

1. A method for planning a food delivery route, characterized in that, The method includes the following steps: Obtain a target delivery task, where the target delivery task includes a delivery starting point and a delivery ending point; Based on the delivery starting point and the delivery ending point, determine multiple delivery routes between the delivery starting point and the delivery ending point and the historical delivery data corresponding to the multiple delivery routes; Input the historical delivery data into a preset analysis large model for review processing to obtain the historical delivery influencing factors of each delivery route; Based on the current delivery influencing factors and historical delivery influencing factors of each delivery route, determine the target delivery route.

2. The method for planning a food delivery route according to claim 1, wherein, The determining of multiple delivery routes between the delivery starting point and the delivery ending point based on the delivery starting point and the delivery ending point includes: Based on the delivery starting point and the delivery ending point, divide the target task area; Based on the road map within the target task area, determine at least one passable route between the delivery starting point and the delivery ending point; Sort each of the passable routes in ascending order according to the length of the driving mileage to obtain a sorted set of passable routes; Extract the multiple delivery routes from the sorted set of passable routes according to preset conditions.

3. The method for planning the delivery route of takeout according to claim 1 or 2, characterized in that, The historical delivery influencing factors include historical delivery weather, historical delivery road disease conditions, historical delivery traffic congestion conditions, and historical delivery time. The inputting of the historical delivery data into a preset analysis large model for review processing to obtain the historical delivery influencing factors of each delivery route includes: Input the historical delivery data into a preset analysis large model for review processing to obtain the historical delivery weather, historical delivery road disease conditions, historical delivery traffic congestion conditions, and historical delivery time of each delivery route under different time and space.

4. The method for planning a food delivery route according to claim 3, wherein, The current delivery influencing factors include current delivery weather, current delivery road disease conditions, and current delivery traffic congestion conditions. The determining of the target delivery route based on the current delivery influencing factors and historical delivery influencing factors of each delivery route includes: Based on the current delivery weather, historical delivery weather, and historical delivery time of each delivery route, determine the first weight value of each delivery route; Based on the current delivery road disease conditions and historical delivery road disease conditions of each delivery route, correct the first weight value to obtain the second weight value of each delivery route; Based on the current delivery traffic congestion conditions and historical delivery traffic congestion conditions of each delivery route, correct the second weight value to obtain the third weight value of each delivery route; Based on the third weight value of each delivery route, determine the target delivery route among the multiple delivery routes.

5. The method for planning a food delivery route according to claim 4, wherein The determining of the first weight value of each delivery route based on the current delivery weather, historical delivery weather, and historical delivery time of each delivery route includes: Based on the historical delivery weather of each delivery route, determine the number of water accumulation positions, the water accumulation occupation area, and the water accumulation depth of each delivery route; Determine the first delivery delay time of each of the delivery routes based on the number of water accumulation positions, the water accumulation road occupation area, the water accumulation depth of each of the delivery routes, and the historical delivery time; Determine the first weight value of each of the delivery routes based on the first delivery delay time of each of the delivery routes and the current delivery weather.

6. The method for planning a food delivery route according to claim 4, wherein The method for correcting the first weight value based on the current delivery road damage condition and the historical delivery road damage condition of each of the delivery routes to obtain the second weight value of each of the delivery routes includes: Determine the road damage condition of each of the delivery routes based on the historical delivery road damage condition of each of the delivery routes; Determine the second delivery delay time of each of the delivery routes based on the road damage condition of each of the delivery routes and the historical delivery time; Correct the first weight value based on the second delivery delay time and the current delivery road damage condition to obtain the second weight value of each of the delivery routes.

7. The method for planning a food delivery route according to claim 4, wherein The method for correcting the second weight value based on the current delivery traffic congestion condition and the historical delivery traffic congestion condition of each of the delivery routes to obtain the third weight value of each of the delivery routes includes: Determine the traffic congestion condition of each of the delivery routes in different delivery directions based on the historical delivery traffic congestion condition of each of the delivery routes; Determine the third delivery delay time of each of the delivery routes based on the traffic congestion condition of each of the delivery routes in different delivery directions and the historical delivery time; Correct the second weight value based on the third delivery delay time and the current delivery traffic congestion condition to obtain the third weight value of each of the delivery routes.

8. An apparatus for planning a food delivery route, characterized in that, The food delivery route planning device includes: A first acquisition module, configured to acquire a target delivery task, where the target delivery task includes a delivery starting point and a delivery ending point; A first determination module, configured to determine a plurality of delivery routes between the delivery starting point and the delivery ending point and the historical delivery data corresponding to the plurality of delivery routes based on the delivery starting point and the delivery ending point; A first review module, configured to input the historical delivery data into a preset analysis large model for review processing to obtain the historical delivery influencing factors of each of the delivery routes; A second determination module, configured to determine a target delivery route based on the current delivery influencing factors and the historical delivery influencing factors of each of the delivery routes.

9. An electronic device, characterized in that, including: A memory, a processor, and a computer program stored on the memory and executable on the processor, where when the processor executes the computer program, the steps in the food delivery route planning method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, and when the computer program is executed by the processor, the steps in the food delivery route planning method according to any one of claims 1 to 7 are implemented.

Images