Anti-conventional scheduling take-out high-efficiency intelligent delivery and order distribution system under special weather order explosion scene

Abstract

The invention discloses a take-out high-efficiency intelligent delivery and dispatch system for anti-conventional dispatching in a special weather order explosion scene, and relates to the technical field of take-out delivery dispatching. In order to solve the problems of overload order receiving of a rider, overtime order chain, resource waste and the like caused by the fact that order dispatching logic is not adaptive to a merchant in a special weather order explosion scene of an existing delivery platform, and cross-platform data isolation occurs, the system adopts a double-layer framework of basic order dispatching and order explosion special scheduling; the pain point is solved through the following core scheme: monitoring a rider load, a weather condition and a single amount growth rate in real time, and triggering a special weather burst mode; the order delivery time efficiency is prolonged, the real-time meal delivery state of the merchant is set as the order delivery core weight, and the order delivery interval of 10-15 minutes is dynamically adjusted; the slow meal delivery penalty of the merchant is canceled to guarantee the authenticity of meal delivery data; and preferentially matching a new online rider or an in-transit rider of which the distribution path is close to the meal taking address. According to the system, the order timeout rate can be reduced, the rider resource utilization efficiency and the consumer experience are improved, the distribution optimization target of small-step fast running and overall fast circulation is achieved, and the system is suitable for various take-out and city distribution scenes.

Description

Technical Field

[0001] This invention relates to the field of food delivery scheduling technology, specifically to an unconventional intelligent system for handling surges in orders during extreme weather conditions. The order dispatch system is suitable for scenarios that require dynamic scheduling of delivery resources, such as food delivery and same-city delivery. Background Technology

[0002] Existing food delivery scheduling algorithms have formed relatively mature technical solutions in normal scenarios, and their core logic usually revolves around principles such as "distance priority, empty order priority, and route priority." However, in scenarios where orders surge due to special weather conditions (such as heavy rain), existing algorithm systems have significant technical limitations, as follows: In scenarios with a surge in orders, existing algorithms still tend to prioritize maximizing the number of orders a rider can accept in a single instance. This may result in orders being concentrated on riders, failing to effectively adapt to the reduced food preparation efficiency of merchants due to the surge in orders and weather conditions. This can easily lead to riders being stuck in congestion at merchants with slow food preparation processes after carrying multiple orders. During the order dispatching process, the real-time food preparation status of the merchants was not taken as a key reference factor. Furthermore, due to information barriers, it was difficult to obtain cross-platform order data and the dine-in busyness of the same merchant, which further increased the food preparation pressure on merchants with a surge in orders and severely reduced the overall food preparation efficiency. The system's order dispatch interval is usually fixed (e.g., once every 3 minutes), and it cannot adaptively adjust to dynamic changes such as a surge in order volume and fluctuations in food preparation efficiency in a scenario of high order volume, resulting in a disconnect between order dispatch decisions and the actual scenario. Furthermore, the existing penalty rules for merchants who are late in preparing food may encourage merchants to falsely mark food as prepared in order to avoid penalties. In order to avoid penalties for late orders, riders often have to wait ineffectively at merchants marked as "prepared", which can lead to a chain of late orders and cause a serious decline in overall delivery efficiency. The aforementioned technological limitations may ultimately lead to multiple problems, including wasted rider resources, high order delay rates for consumers, poor platform delivery experience, and conflicts in collaboration between merchants and riders. Therefore, there is an urgent need for a delivery system capable of adapting to peak order volumes during extreme weather conditions and implementing unconventional intelligent scheduling to solve these technical challenges. Summary of the Invention

[0003] I. Purpose of the Invention: Addressing the pain points of existing technologies in delivery scenarios with surges in orders due to extreme weather, this invention provides a solution for such scenarios. The high-efficiency intelligent order dispatch system for food delivery in a single scenario with unconventional scheduling takes into account rider load, merchant food preparation status and order timeliness through a two-layer order dispatch architecture and dynamic scheduling strategy, thereby optimizing overall delivery efficiency, improving order on-time rate and reducing multi-party collaboration costs.

[0004] II. Technical Solution The efficient and intelligent food delivery dispatch system of this invention, which utilizes unconventional scheduling in special weather-related order surge scenarios, includes a basic dispatch module, an order surge mode trigger module, an order surge scheduling module, and an auxiliary support module. These modules work collaboratively to form a complete technical solution of "basic dispatch + special order surge scheduling," as detailed below: The basic order dispatch module is the core foundation of the system, executing three main order dispatch logics to adapt to delivery needs in non-peak order scenarios: Scenario 1: When all riders are in an empty order state, the straight-line distance or actual delivery route distance between the rider and the pickup address is calculated using GPS location data, and the riders are sorted from closest to furthest, with priority given to assigning the order to the rider closest to them; Scenario 2: When some riders have no orders and the rest have orders, the system filters the list of riders with no orders and prioritizes assigning new orders to riders with no orders to avoid further overloading of already loaded riders; Scenario 3: When all riders have orders, the route planning algorithm calculates the overlap (smoothness coefficient) between the rider's current delivery route and the new order's pickup-delivery route, and prioritizes assigning the order to the rider with the highest smoothness coefficient.

[0005] The order surge trigger module is the core trigger mechanism of the system, which realizes the order surge through real-time data monitoring. Automatic start and stop of single mode: Data collection: Real-time acquisition of three core data points: average number of orders held by riders in the region (collected through rider's mobile app), special weather warnings from third-party weather platforms (accessed via API), and regional order growth rate within one hour (statistics from the platform's backend). Triggering conditions: When all three data points are met simultaneously, such as "average number of orders held by riders ≥ 3 + special weather warning issued + order growth rate ≥ 50%", the special weather order surge mode will be automatically activated. Exit conditions: The system checks the trigger conditions every 30 minutes. When "the rider's average number of orders is less than 3", "the order growth rate is less than 30%", or "the special weather warning is lifted", the system will automatically exit the order surge mode and restore the basic order dispatch logic.

[0006] The order surge scheduling module is a core innovative module of the system. Upon triggering, it executes four specific scheduling strategies, suitable for... Special requirements for scenarios with overwhelming order volume: Strategy 1: Extended Order Delivery Time. The system will automatically extend the preset delivery time for newly generated orders in this area by 30%-50%, and will push a notification to consumers via the user's app explaining the time adjustment and the reason for the adjustment (e.g., "Due to a surge in orders caused by special weather conditions, delivery time may be slightly longer"). (Please understand that the extension has been delayed.) Strategy 2: Reconstruct the order dispatch weighting model. Set the merchant's real-time food preparation status as the core reference factor for order dispatch, with a weighting of ≥60%; orders manually marked as "prepared" by the merchant's app are considered as actually prepared, and orders not marked as "prepared" will not be included in the order dispatch pool for the time being; Strategy 3: Dynamic adjustment of order dispatch interval. The order dispatch interval will be adjusted from 3 minutes / order under normal weather conditions to 10-15 minutes / order. The interval will be dynamically adapted based on real-time data: when the average food preparation time of merchants is ≥20% longer than usual, it will be adjusted to 15 minutes; when the order growth rate decreases and food preparation efficiency recovers, it will be reverted to 10 minutes. Strategy 4: Rider Matching Optimization. Each time an order is dispatched, the system simultaneously filters two types of suitable riders: "newly online riders with empty orders" and "riders on the way whose current delivery destination is ≤2 kilometers from the target merchant's pick-up address". The system then combines the rider's current number of orders (≤4 orders) and the route proximity factor to comprehensively allocate target orders.

[0007] The auxiliary support module is a supporting mechanism for the system, used to ensure the effective execution of the order surge scheduling module. Remove penalties for slow food preparation by merchants: Remove existing platform rules that penalize merchants for food preparation delays to prevent merchants from engaging in fake food preparation behavior under pressure and ensure that the food preparation status data obtained by the system is true and valid; Order delivery time extended a second time: If the target merchant fails to prepare the food for an extended period, exceeding 50% of the extended delivery time, the system will automatically extend the delivery time again. Extend the order's delivery time by 20% and continue matching suitable riders until the order is fully assigned. Beneficial effects

[0008] Optimize rider resource allocation: Avoid overloading riders with orders and unnecessary waiting times, improve rider resource utilization efficiency, and reduce... Delivery rider pressure; Improve order on-time delivery rate: Reduce the risk of chain-reaction delays, prioritize the on-time delivery of the majority of orders, and significantly improve the consumer delivery experience; Improve multi-party collaboration: Dispatch orders based on real food production data to reduce collaboration conflicts between merchants, platforms, and riders, and optimize the three-party collaboration model; Enhance scenario adaptability: By dynamically adjusting the mechanism to adapt to the uncertainty of peak order scenarios, the platform can achieve the goal of "small steps, fast pace, and overall rapid cycle" in delivery optimization, thereby improving the overall delivery scheduling competitiveness of the platform. Attached Figure Description

[0009] Figure 1 This is a schematic diagram of the module architecture of the order dispatch system of the present invention. The basic order dispatch module is the core, and it is associated with the order surge mode triggering, order surge scheduling and auxiliary support modules, showing the hierarchical relationship and interaction logic of each module.

[0010] Figure 2 This is a schematic diagram of the closed-loop process of the order surge mode of the present invention. Starting with the collection of indicators such as order volume and system load, and after judging the trigger / exit conditions, the full process control of the order surge mode is realized from "activation-running-termination".

[0011] Figure 3 This is a schematic diagram of the execution flow of the order surge scheduling module of the present invention. It clarifies the four core steps and logic of scheduling in the order of "time extension → weight reconstruction → interval adjustment → rider matching".

[0012] Figure 4 This diagram illustrates the comparison of order weighting between the present invention and existing order dispatch platforms. The weighting percentages of both platforms are listed based on four dimensions, including food preparation status, highlighting the technological advantages of the present invention through the comparison of differences and effects.

[0013] Figure 5 The accompanying diagram in the abstract of the instruction manual shows the automatic dispatching and order configuration interface, including parameters such as dispatching switch, mode selection, and order threshold, demonstrating the core operation mode.

[0014] Figure 6 This is a schematic diagram of the forced dispatch parameter configuration logic of the present invention, covering the order rejection process, forced strategy, trigger threshold, rider matching priority, etc., clarifying the relationship and setting purpose of each parameter.

Claims

1. An efficient intelligent delivery dispatching system for take-out under abnormal scheduling in a special weather burst order scenario, characterized in that, The application comprises a basic order dispatching module, an order surge triggering module, an order surge scheduling module and an auxiliary guarantee module, and the modules cooperatively realize the following functions: The basic order dispatching module executes the following order dispatching logic: a. When all riders are in an empty order state, orders are assigned to riders according to the priority of the distance between the rider and the pickup address; b. When some riders are in an empty order state and the rest of the riders have orders, orders are preferentially assigned to the riders in an empty order state; c. When all riders have orders, orders are preferentially assigned to riders in a relatively straight direction of delivery; The order surge triggering module monitors three core data in real time: the average number of orders held by riders in the region, special weather warning information from a third-party weather platform, and the order growth rate in a unit time. When the following conditions are met: "the average number of orders held by riders ≥ a preset threshold + special weather warning has been issued + the order growth rate ≥ a preset increase", the special weather order surge mode is automatically triggered; The order surge scheduling module executes the following scheduling strategy after being triggered: a. The preset delivery time of newly generated orders in the region is extended by 30%-50%; b. The order dispatching weight model is reconstructed, and the real-time meal status of the merchant is set as a core reference factor. Only when the merchant confirms the real meal through the terminal, the order is included in the order dispatching candidate pool; c. The automatic order dispatching interval is adjusted to 10-15 minutes per time, and the interval time is dynamically adapted according to the real-time order quantity growth rate and the average meal efficiency of the merchant; d. Each time an order is dispatched, "newly online empty order riders" and "in-transit riders whose current delivery endpoint and target merchant pickup address distance ≤ a preset distance" are synchronously screened, and orders are assigned according to the current load state of the riders; The auxiliary guarantee module cancels the related punishment mechanism generated by the merchant due to slow meal, and eliminates false meal behavior.

2. The special weather order surge scenario unconventional scheduling efficient intelligent delivery dispatching system of claim 1, wherein: The special weather includes heavy rain, heavy snow, high temperature, and cold wave, and the weather warning information is obtained in real time through a third-party weather platform interface.

3. The special weather order surge scenario unconventional scheduling efficient intelligent delivery dispatching system of claim 1, wherein: The "preset threshold" in the order surge triggering condition is 3 orders, the "unit time" is 1 hour, and the "preset increase" is 50%. The above parameters can be dynamically adjusted according to platform operation data.

4. The special weather order surge scenario unconventional scheduling efficient intelligent delivery dispatching system of claim 1, wherein: The dynamic adaptation rule of the order dispatching interval is: when the average meal time of the merchant is detected to be longer than that on ordinary days by ≥20%, the order dispatching interval is adjusted to 15 minutes; when the order growth rate decreases and the meal efficiency of the merchant rebounds, the order dispatching interval is adjusted back to 10 minutes.

5. The special weather order surge scenario unconventional scheduling efficient intelligent delivery dispatching system of claim 1, wherein: The "preset distance" is 2 kilometers, and the adaptation standard of the current load state of the rider is "the number of orders held ≤4".

6. The special weather order surge scenario outside regular scheduling efficient intelligent delivery dispatching system of take-out according to claim 1, characterized in that: If the target merchant has not been meal for a long time, and more than 50% of the extended delivery time, the system automatically extends the order time again, the extension ratio is 20%, and the matching suitable rider is continued until the order is assigned.

Images