Method and device for intelligent matching of delivery order and delivery rider, computer device and medium

Abstract

The application relates to a method and device for intelligent matching of a delivery order and a delivery rider, a computer device and a medium, which comprises the following steps: obtaining order information of a target delivery order, including a target delivery starting point; determining a delivery rider whose current position is within a preset distance range centered on the target delivery starting point as a candidate delivery rider, and obtaining a first rider set; screening the candidate delivery riders meeting preset direct matching conditions from the first rider set, and determining a target delivery rider therefrom; if there is no candidate delivery rider meeting the preset direct matching conditions in the first rider set, screening candidate delivery riders meeting preset recommendation conditions from the first rider set as a third rider set, pushing the target delivery order to each candidate delivery rider in the third rider set, and determining the target delivery rider according to order response information. The application can solve the problem of low system matching efficiency and success rate caused by single matching strategy and rigid matching process.

Description

Technical Field

[0001] This application relates to the field of ride-hailing order dispatch technology, and in particular to a method, apparatus, computer equipment and medium for intelligent matching of delivery orders and delivery riders. Background Technology

[0002] In the on-demand delivery sector, efficiently and accurately matching delivery orders with delivery riders is a core technical challenge for improving delivery efficiency and user experience. Currently, the mainstream order matching methods are mainly divided into two modes: "system-assigned orders" and "rider-bid orders."

[0003] The system-based order dispatch mode involves the system filtering available riders within a certain radius of the order's pickup address (i.e., delivery origin) and checking these riders' preset order-accepting conditions (such as maximum delivery distance, carrying capacity, and areas where they do not accept orders). Only riders who simultaneously meet both location and set conditions are given a forced order dispatch instruction. This mode has high dispatch efficiency; however, because the system rigidly filters riders' preset order-accepting conditions, if certain parameters of an order (such as delivery distance slightly exceeding the limit or product weight approaching a critical value) do not match the rider's settings, the system will directly abandon the order dispatch even if the order is actually suitable for the rider in terms of earnings and route convenience. This either-or matching logic leads to a large number of orders at the critical conditions not being automatically dispatched, causing orders to remain idle for extended periods, resulting in low matching success rates, and also causing riders to miss opportunities to adjust their order-accepting strategies to gain more earnings.

[0004] The rider-grabbing model involves publishing order information on a public platform, allowing riders to choose which orders to accept. This method fully respects the riders' autonomy, but when order density is low or the platform lacks appeal, it can easily lead to delayed order responses or even no orders being placed, thus affecting the success rate of order matching and delivery time. Summary of the Invention

[0005] In response to the above-mentioned deficiencies or disadvantages, this application provides a method, apparatus, computer equipment, and medium for intelligent matching of delivery orders and delivery riders.

[0006] This application provides a method for intelligent matching of delivery orders and delivery riders according to a first aspect. The method includes: obtaining order information of a target delivery order to be dispatched, the order information including a target delivery origin and a target delivery destination; identifying delivery riders whose current location is within a preset distance range centered on the target delivery origin as candidate delivery riders to obtain a first rider set; selecting candidate delivery riders from the first rider set who meet preset direct matching conditions to form a second rider set; determining the target delivery rider from the second rider set; and dispatching the target delivery order to the target delivery rider; if there are no candidate delivery riders in the first rider set who meet the preset direct matching conditions, selecting candidate delivery riders from the first rider set who meet preset recommendation conditions to form a third rider set; pushing the target delivery order to each candidate delivery rider in the third rider set; determining the target delivery rider based on the received order acceptance response information; and dispatching the target delivery order to the target delivery rider.

[0007] In some embodiments, the preset direct matching conditions include a first matching condition and a second matching condition; the first matching condition refers to the capacity status being idle; the second matching condition refers to the capacity status being order-carrying, and the delivery origin and target delivery origin of at least one accepted delivery order being the same, and the distance between the delivery destination and the target delivery destination being less than a first distance threshold; selecting candidate delivery riders who meet the preset direct matching conditions from the first rider set as the second rider set includes: detecting whether there are candidate delivery riders who meet the first matching conditions in the first rider set; if there are, including the candidate delivery riders who meet the first matching conditions as the second rider set; if not, detecting whether there are candidate delivery riders who meet the second matching conditions in the first rider set; if so, including the candidate delivery riders who meet the second matching conditions as the second rider set.

[0008] In some embodiments, the method further includes: if there are no candidate delivery riders in the first rider set that meet the second matching conditions, determining that there are no candidate delivery riders in the first rider set that meet the preset direct matching conditions.

[0009] In some embodiments, the preset recommendation criteria include a first recommendation criterion, a second recommendation criterion, and a third recommendation criterion; selecting candidate delivery riders from the first rider set who meet the preset recommendation criteria as the third rider set includes: detecting whether there are candidate delivery riders in the first rider set who meet the first recommendation criterion; the first recommendation criterion refers to the distance level to which the historical order-taking distance record and the delivery distance of the target delivery order belong; if there are, selecting candidate delivery riders who meet the first recommendation criterion as the third rider set; if not, selecting delivery orders from all delivery orders to be dispatched that meet the combination criteria with the target delivery order, and combining the selected delivery orders with the target delivery order. The target delivery order is considered as a delivery order combination. Based on the delivery order combination, it is checked whether there are candidate delivery riders in the first rider set who meet the second recommendation condition. The second recommendation condition is that the current capacity load does not exceed the preset load threshold, and the distance between the current location and the origin aggregation center determined by the delivery origin of each delivery order in the delivery order combination is less than the second distance threshold. If so, the candidate delivery riders who meet the second recommendation condition are included in the third rider set. If not, the candidate delivery riders in the first rider set who meet the third recommendation condition are included in the third rider set. The third recommendation condition is that the distance between the permanent residence area and the target delivery destination is less than the third distance threshold.

[0010] In some embodiments, pushing a target delivery order to each candidate delivery rider in a third rider set includes: if the third rider set is a candidate delivery rider that meets the second recommendation criteria, then pushing a combination of delivery orders to each candidate delivery rider that meets the second recommendation criteria; the combination criteria refer to the distance between the delivery origin and the target delivery origin being less than a fourth distance threshold, and the distance between the delivery destination and the target delivery destination being less than the fourth distance threshold.

[0011] In some embodiments, detecting whether there are candidate delivery riders in the first rider set who meet the first recommendation criteria includes: determining the delivery distance of the target delivery order based on the target delivery origin and the target delivery destination; comparing the delivery distance of the target delivery order with the distance range corresponding to a preset delivery distance level; determining the distance level to which the delivery distance of the target delivery order belongs based on the comparison result; obtaining the historical order-taking distance records of each candidate delivery rider in the first rider set; analyzing the preferred distance level of each candidate delivery rider based on the historical order-taking distance records of each candidate delivery rider; and determining that the candidate delivery rider meets the first recommendation criteria if the preferred distance level and the distance level to which the delivery distance of the target delivery order belongs are the same for any candidate delivery rider.

[0012] In some embodiments, the method further includes: if no order acceptance response is received from any candidate delivery rider in the third rider set within a preset time period, the matching is determined to have failed, and the target delivery order is sent to the order grabbing hall.

[0013] According to a second aspect, this application provides a smart matching device for delivery orders and delivery riders, the device comprising: The order information acquisition module is used to acquire the order information of the target delivery orders to be dispatched. The order information includes the target delivery origin and the target delivery destination. The candidate rider determination module is used to identify delivery riders whose current location is within a preset distance range centered on the target delivery origin as candidate delivery riders, thus obtaining the first set of riders; The direct matching module is used to select candidate delivery riders who meet the preset direct matching conditions from the first rider set as the second rider set, determine the target delivery rider from the second rider set, and dispatch the target delivery order to the target delivery rider. The order recommendation module is used to select candidate delivery riders who meet the preset direct matching conditions from the first rider set if there are no candidate delivery riders in the first rider set. This is then used as a third rider set. The target delivery order is pushed to each candidate delivery rider in the third rider set. Based on the received order acceptance response information, the target delivery rider is determined and the target delivery order is assigned to the target delivery rider.

[0014] According to a third aspect, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described intelligent matching methods for delivery orders and delivery riders.

[0015] According to a fourth aspect, this application provides a computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executed, implements any of the above-described intelligent matching methods for delivery orders and delivery riders.

[0016] This application introduces a two-stage, condition-driven collaborative working mechanism of direct matching and recommended matching, which can combine the advantages of order dispatch mode and order grabbing mode, and can intelligently switch matching strategies according to real-time situation, so as to solve the problem of low system matching efficiency and success rate caused by single matching strategy and rigid matching process.

[0017] Specifically, after acquiring the target delivery orders to be dispatched, the order dispatch system first filters candidate delivery riders within a preset distance range centered on the target delivery origin to obtain a first set of riders. Then, riders meeting preset direct matching criteria are identified from this first set to form a second set for direct order dispatch, ensuring efficient automatic matching under ideal conditions. When no riders meeting the direct matching criteria exist in the first set, the system does not abandon the matching process but instead switches its matching strategy, selecting riders meeting preset recommendation criteria from the first set to form a third set for proactive push notifications. Matching is completed by receiving order acceptance responses. This hierarchical mechanism, prioritizing direct matching and using recommended matching as a fallback, overcomes the matching bottleneck caused by rigid filtering based on preset rider criteria in traditional matching methods. While ensuring the efficiency of automatic order dispatch, it expands the potential range of accepting riders through proactive recommendations, allowing orders that might otherwise be filtered out due to individual parameter discrepancies to still be proactively accepted by riders. Ultimately, this improves order matching success rate, reduces order dwell time, increases rider earnings, and enhances the overall system efficiency. Attached Figure Description

[0018] Figure 1 A flowchart illustrating a method for intelligent matching of delivery orders and delivery riders in one or more embodiments of this application; Figure 2 This is a schematic diagram of the intelligent matching device for delivery orders and delivery riders in one or more embodiments of this application; Figure 3 This is a schematic diagram of the internal structure of a computer device according to one or more embodiments of this application. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings. It should be understood that the described embodiments are merely some embodiments of this application, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0020] In the following description, when referring to the accompanying drawings, the same numbers in different drawings denote the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0021] In the description of this application, it should be understood that the terms "first," "second," "third," etc., are used only to distinguish similar objects and are not necessarily used to describe a specific order or sequence, nor should they be construed as indicating or implying relative importance. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances. Furthermore, in the description of this application, unless otherwise stated, "multiple" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0022] To address the shortcomings or defects of related technologies, this application provides a method for intelligent matching of delivery orders and delivery riders. This method can integrate the advantages of order dispatching mode and order grabbing mode, and can intelligently switch matching strategies according to real-time conditions, so as to solve the problem of low system matching efficiency and success rate caused by a single matching strategy and rigid matching process.

[0023] In some embodiments, such as Figure 1 As shown, the method includes steps S110 to S140. The following will take the application of this method to the order scheduling system (hereinafter referred to as the system) of the delivery platform as an example to illustrate each step. The order scheduling system is the core of the delivery platform's calculation and scheduling. Specifically, it is an independent server or a server cluster, responsible for operations such as order information management, rider location tracking, matching condition judgment and order dispatch.

[0024] S110: Obtain the order information of the target delivery orders to be dispatched. The order information includes the target delivery origin and the target delivery destination.

[0025] A target delivery order refers to a delivery task published by a merchant through the merchant terminal and waiting to be assigned a delivery rider. The order information is the basic data for rider matching, which includes at least the target delivery origin (i.e., the geographical location of the merchant or the coordinates of the agreed pick-up location) and the target delivery destination (i.e., the coordinates of the delivery location specified by the customer). In addition, it may also include auxiliary attribute information such as order weight, delivery time requirements, and delivery price.

[0026] The order scheduling system can monitor order creation requests sent by merchant terminals in real time. When it receives an order creation request, it parses the geographical location information contained therein (which can be represented by latitude and longitude coordinates or geocoding), then extracts the target delivery origin and target delivery destination, and finally generates target delivery order data to be dispatched and stores it in the order queue to be matched.

[0027] S120: Identify delivery riders whose current location is within a preset distance range centered on the target delivery origin as candidate delivery riders, and obtain the first set of riders.

[0028] Delivery riders are transportation providers who are registered and active on the delivery platform. Their current location can be collected in real time through the positioning module of the rider's terminal (such as a smartphone) and reported to the order dispatch system.

[0029] The preset distance range refers to the initial screening radius set by the system (e.g., 3 kilometers), which can be pre-configured by the delivery platform's operators based on delivery efficiency and rider response time.

[0030] After receiving a target delivery order, the order dispatch system establishes a geofence with the coordinates of the target delivery origin as the center and a preset distance range as the radius. It then queries the rider location database for all delivery riders within the geofence's range and aggregates their identifiers (such as rider IDs) and real-time location information to form the first rider set.

[0031] The first rider pool is the pool of potential delivery capacity that meets the basic requirements for serving the target delivery orders in physical locations. It serves as the basic candidate set for all subsequent matching operations.

[0032] S130: Select candidate delivery riders who meet the preset direct matching conditions from the first rider set as the second rider set, determine the target delivery rider from the second rider set, and dispatch the target delivery order to the target delivery rider.

[0033] Preset direct matching conditions refer to the set of matching rules set by the system that allow for mandatory automatic order assignment to riders. For example, the rider's current delivery capacity status is idle (meaning the rider has not accepted other delivery orders), the rider's order acceptance settings are fully compatible with the current order attributes (such as the delivery distance does not exceed the rider's maximum order acceptance distance, the order weight is within the rider's carrying capacity, the order is not in the rider's set rejection area, etc.).

[0034] The second rider set refers to the candidate subset of the first rider set that is suitable for automatic order dispatch after being filtered by direct matching conditions.

[0035] A target delivery rider refers to a specific delivery person selected to undertake a target delivery order.

[0036] For example, the order dispatch system can iterate through each candidate delivery rider in the first rider set, obtain their current delivery capacity status (such as idle, carrying orders, offline, etc.) and preset order acceptance configuration parameters, and determine one by one whether they meet the preset direct matching conditions. If there are riders that meet the conditions, a unique target delivery rider is determined from them according to preset rules (such as nearest priority, highest rating priority, etc.), and a forced order dispatch instruction is sent to the target delivery rider's terminal. If an order acceptance confirmation message is received from the target delivery rider (such as the rider not refusing within the preset timeout period or the timeout period), the order matching is confirmed to be successful, the order status of the target delivery order is updated to assigned, and a binding relationship is established between the target delivery order and the target delivery rider.

[0037] In some embodiments, the method further includes: if there are no candidate delivery riders in the first rider set that meet the second matching conditions, determining that there are no candidate delivery riders in the first rider set that meet the preset direct matching conditions.

[0038] S140: If there are no candidate delivery riders in the first rider set who meet the preset direct matching conditions, select candidate delivery riders in the first rider set who meet the preset recommendation conditions as the third rider set, push the target delivery order to each candidate delivery rider in the third rider set, determine the target delivery rider based on the received order acceptance response information, and dispatch the target delivery order to the target delivery rider.

[0039] Preset recommendation criteria are used to identify riders who do not fully meet the mandatory order dispatch requirements but may be willing to actively accept orders based on factors such as order revenue, route convenience, or historical behavior. For example, preset recommendation criteria may include: the rider is currently carrying orders but the pickup location of the current order is the same as or close to the target delivery origin (i.e., has route potential); the rider has a historically high order acceptance rate within the distance range of the current order (i.e., matches the rider's order acceptance preferences); the rider's usual location is close to the target delivery destination (i.e., has the advantage of convenient return trips), etc. Unlike the rigid constraints of preset direct matching criteria, preset recommendation criteria allow for a certain degree of parameter discrepancy, but require riders to have the willingness and ability to actively choose.

[0040] The third rider set refers to the candidate subset of riders identified through preset recommendation criteria who are suitable for pushing target delivery orders.

[0041] Order acceptance response information refers to the order acceptance request data packet initiated by a candidate delivery rider in the third rider set through their terminal after receiving the system's order recommendation message. This data packet may include information such as rider ID, order ID, and response timestamp.

[0042] For example, when the order dispatch system confirms that no rider in the first rider set meets the preset direct matching conditions (i.e., the second rider set is empty), it triggers the recommendation matching process. In the recommendation matching process, the system uses the first rider set as a candidate pool, applies preset recommendation conditions for filtering, and aggregates the selected rider identifiers to form a third rider set.

[0043] The order dispatch system pushes order recommendation messages to the terminals of each candidate delivery rider in the third rider set. The push method can be a built-in push notification or an in-app message. The alert strength of the order recommendation message can be weaker than that of the forced order dispatch notification message. The order recommendation message can include basic information about the target delivery order (such as delivery origin, delivery destination, delivery price, estimated mileage, etc.) and an interactive entry point for "Accept Order Now" (such as a virtual button). Within a preset recommendation validity period (e.g., 30 seconds), the system listens for order acceptance responses from any rider in the third rider set. If one or more order acceptance responses are received within the validity period, the system determines the target delivery rider according to preset order-accepting rules (such as first-come, first-served or selection based on rider's comprehensive score), sends a successful order acceptance confirmation message to that rider, and dispatches the target delivery order to that rider.

[0044] In some embodiments, if no order acceptance response is received from any candidate delivery rider in the third rider set within a preset time period, the matching is deemed to have failed, and the target delivery order is sent to the order grabbing hall.

[0045] If no order acceptance response is received within the validity period, the system will transfer the target delivery order to the order-grabbing hall to enter a broader open competitive matching stage.

[0046] This embodiment introduces a two-stage, condition-driven collaborative working mechanism of direct matching and recommended matching, which can combine the advantages of order dispatch mode and order grabbing mode, and can intelligently switch matching strategies according to real-time situation to solve the problem of low system matching efficiency and success rate caused by single matching strategy and rigid matching process.

[0047] Specifically, after acquiring the target delivery orders to be dispatched, the order dispatch system first filters candidate delivery riders within a preset distance range centered on the target delivery origin to obtain a first set of riders. Then, riders meeting preset direct matching criteria are identified from this first set to form a second set for direct order dispatch, ensuring efficient automatic matching under ideal conditions. When no riders meeting the direct matching criteria exist in the first set, the system does not abandon the matching process but instead switches its matching strategy, selecting riders meeting preset recommendation criteria from the first set to form a third set for proactive push notifications. Matching is completed by receiving order acceptance responses. This hierarchical mechanism, prioritizing direct matching and using recommended matching as a fallback, overcomes the matching bottleneck caused by rigid filtering based on preset rider criteria in traditional matching methods. While ensuring the efficiency of automatic order dispatch, it expands the potential range of accepting riders through proactive recommendations, allowing orders that might otherwise be filtered out due to individual parameter discrepancies to still be proactively accepted by riders. Ultimately, this improves order matching success rate, reduces order dwell time, increases rider earnings, and enhances the overall system efficiency.

[0048] In some embodiments, the preset direct matching conditions include a first matching condition and a second matching condition. The first matching condition refers to a capacity status of being idle. The second matching condition refers to a capacity status of being on-call, where the delivery origin and target delivery origin of at least one accepted delivery order are the same, and the distance between the delivery destination and the target delivery destination is less than a first distance threshold. Here, capacity status means that the rider has currently accepted one or more delivery orders, i.e., the rider has currently bound at least one delivery order, and these delivery orders have not yet been completed. Idle status means that the candidate delivery rider does not currently have any ongoing or assigned but not started delivery tasks, i.e., their "accepted order count" is zero, and they are in a state where they can immediately accept new tasks. On-call status means that the candidate delivery rider has currently accepted at least one delivery order and has not yet completed it; these orders may be in different stages such as pending pickup, pickup in progress, or delivery. Accepted delivery orders refer to orders that have been successfully assigned to the rider through the system and accepted by the rider (or forcibly assigned by the system), but whose delivery service process (from pickup to completion) has not yet ended. The first distance threshold is a preset geographical distance threshold (e.g., 500 meters) used to quantify the proximity of the destinations of two delivery orders. When the straight-line distance between the destinations of two delivery orders is less than this threshold, the system considers them to be geographically close enough and can be regarded as on-the-way delivery.

[0049] Accordingly, candidate delivery riders who meet the preset direct matching conditions are selected from the first rider set to form the second rider set, including: Check if there are any candidate delivery riders in the first rider set who meet the first matching criteria; If they exist, the candidate delivery riders who meet the first matching criteria will be used as the second rider set; If not, check if there are any candidate delivery riders in the first rider set who meet the second matching conditions; If so, the candidate delivery riders who meet the second matching criteria will be included in the second rider set.

[0050] This embodiment further refines the preset direct matching conditions into two sub-conditions with clear priorities and different technical implications: the first matching condition and the second matching condition. This hierarchical design makes the direct matching process logically clear and more efficient in execution.

[0051] In this embodiment, the system first performs a first-level detection to find available delivery capacity, that is, it traverses the first set of riders and checks the real-time delivery capacity status of each candidate delivery rider. For example, it checks whether the "current number of accepted orders" of each rider is zero. If it is zero, the rider meets the first matching condition (the delivery capacity status is idle).

[0052] Once at least one available rider meeting the first matching criteria is detected in the first rider set, all detected available riders are selected and directly formed into the second rider set. Subsequent second-level checks will not be performed, thus enabling rapid utilization of available capacity.

[0053] If no available riders are found in the first rider set (i.e., all riders are currently carrying orders), a second layer of detection is performed to find available riders along the same route. The system checks each rider carrying orders one by one. For each rider carrying orders, it first obtains detailed information on all their accepted delivery orders. Then, it compares the delivery origin of the target delivery order with the delivery origin of each of the rider's accepted orders. If at least one accepted order has the same delivery origin as the target delivery origin (e.g., both pointing to the same shopping mall or restaurant), the origin matching condition is met. Simultaneously, the system calculates the straight-line distance between the destination of the target delivery order and the destination of the accepted orders (or those) with the same delivery origin. If this distance is less than a preset first distance threshold, the destination proximity condition is met. When a rider carrying orders meets both the "same origin" and "proximity destination" conditions, they are deemed to meet the second matching condition.

[0054] If, during the second-level detection, riders meeting the second matching criteria are found, these riders are selected to form a second rider set. If none are found, it is determined that there are no riders in the first rider set who meet the preset direct matching criteria, and the process proceeds to the recommended matching stage in S140.

[0055] This embodiment, based on a dual direct matching condition with strict priority, can unconditionally match idle capacity, completing order dispatch with minimal system overhead and communication latency, maximizing the instantaneous utilization efficiency of absolutely idle resources. When no idle riders are available, it searches for along-route capacity. The sub-conditions of "same origin" and "similar destination" ensure that new orders highly match the rider's existing tasks in terms of spatial path. This is equivalent to adding a along-route task for the rider without significantly increasing the rider's additional mileage (i.e., marginal cost), thereby improving the overall load rate and aggregated delivery efficiency of the system's capacity network. Furthermore, this embodiment employs a serial detection process of "checking idle capacity first, then checking along-route," which is logically simple and has low computational complexity, ensuring the system's rapid response capability under high concurrency requests. Simultaneously, this design avoids unnecessary complex along-route calculations when idle riders exist, optimizing the allocation of server computing resources.

[0056] In some embodiments, the preset recommendation criteria include a first recommendation criterion, a second recommendation criterion, and a third recommendation criterion; correspondingly, selecting candidate delivery riders who meet the preset recommendation criteria from the first rider set as the third rider set includes: (1) Detect whether there are candidate delivery riders in the first rider set who meet the first recommendation criteria.

[0057] The first recommendation criterion is that the historical order distance records and the delivery distance of the target delivery order match the distance level.

[0058] Historical order distance records refer to the set of delivery distance data of all delivery orders undertaken by each rider in the past period (such as the last 30 days) stored in the system. Historical order distance records can reflect the rider's preference for different distance orders in actual operation.

[0059] There are multiple distance levels. To simplify matching and preference analysis, the system can divide a continuous delivery distance range into several discrete levels. For example, it can be divided into: Level 1 (0-2 km), Level 2 (2-5 km), Level 3 (5-10 km), and Level 4 (>10 km). Based on the specific delivery distance of the target delivery order (calculated from the origin and destination), it can be assigned to one of the distance levels.

[0060] (2) If they exist, the candidate delivery riders who meet the first recommendation criteria will be used as the third rider set.

[0061] (3) If not, select delivery orders that meet the combination conditions with the target delivery order from all delivery orders to be dispatched, and combine the selected delivery orders and the target delivery order as a delivery order combination. Based on the delivery order combination, check whether there are candidate delivery riders in the first rider set that meet the second recommendation conditions.

[0062] The second recommended condition is that the current capacity load does not exceed the preset load threshold, and the distance between the current location and the origin aggregation center determined by the delivery origin of each delivery order based on the delivery order combination is less than the second distance threshold.

[0063] A delivery order bundle refers to logically binding a target delivery order with one or more other eligible, yet-to-be-assigned delivery orders to form a single order package that can be uniformly accepted and delivered.

[0064] Combination conditions refer to the rules used to filter which pending orders can be combined with the target delivery order to form a delivery order combination. For example, the distance between the delivery origin of the candidate order and the target delivery origin is less than a certain threshold (such as 1 kilometer), and the distance between its delivery destination and the target delivery destination is also less than a certain threshold, so as to ensure the geographical clustering of orders within the delivery order combination.

[0065] The origin cluster center of a delivery order combination is a geometric center point used to characterize the concentrated area of ​​all order origin locations in the delivery order combination. This center point can be obtained by calculating the arithmetic mean (mean of latitude and longitude) of the origin coordinates of all orders.

[0066] Current delivery capacity refers to the total number of delivery orders that riders have accepted but not yet completed at the current moment. This can be the number of orders or a weighted calculation based on the estimated delivery time of each order.

[0067] The preset load threshold is a critical value set by the system to determine whether a rider is still capable of accepting new orders (especially order combinations). For example, it can be set to "current number of accepted orders ≤ 3". This threshold can be globally fixed or dynamically adjusted according to rider level and time of day.

[0068] (4) If so, the candidate delivery riders who meet the second recommendation criteria will be used as the third rider set.

[0069] (5) If not, the candidate delivery riders in the first rider set who meet the third recommendation criteria shall be used as the third rider set.

[0070] The third recommended condition is that the distance between the permanent location and the target delivery destination is less than the third distance threshold.

[0071] The resident area refers to the typical geographical area where the rider habitually stays or is active, identified by analyzing the rider's historical location data (such as offline points, long-term stay points, and high-frequency areas). For example, the rider's residential community or the business district where the rider often waits for orders.

[0072] When direct matching fails, the system enters a refined, tiered recommendation and matching phase. This embodiment specifies the preset recommendation conditions into three sub-conditions with a clear progressive order: the first recommendation condition, the second recommendation condition, and the third recommendation condition. This design aims to maximize order acceptance by progressively exploring potential capacity through attractive strategies across different dimensions.

[0073] In this embodiment, the system first attempts to match the rider's individual habits in the most suitable way. That is, it calculates the actual delivery distance (which can be the distance corresponding to the delivery path between the delivery start coordinates and the delivery end coordinates) based on the origin and destination coordinates of the target delivery order, and determines the distance level of the target delivery order (for example, it belongs to the "2-5 km" level) by referring to the preset distance level range.

[0074] Next, the system retrieves the historical order-taking distance records of each candidate delivery rider in the first rider set. By analyzing the historical order-taking distance records of each candidate delivery rider (for example, by calculating the percentage of orders accepted at each distance level), the preferred distance level of each candidate delivery rider can be inferred (for example, a certain rider accepts the highest percentage of "2-5 km" orders).

[0075] For any rider, if the system infers that their preferred distance level is the same as the distance level of the target delivery order, then the rider is deemed to meet the first recommendation condition.

[0076] If there are riders who meet the first recommendation criteria, these riders will be directly included in the third rider set, and subsequent recommendation criteria will not be checked.

[0077] If no rider is matched in the first layer, the system will attempt to attract riders by offering higher earnings incentives. First, the system filters orders from the pool of all pending delivery orders that match the target delivery order's combination criteria. Then, it combines the filtered orders with the target delivery order into a delivery order combination and calculates the coordinates of the origin cluster center of all orders within this combination. Subsequently, the system checks the first set of riders for riders who meet the second recommendation criteria. The second recommendation criteria include two sub-conditions that must be met simultaneously: (1) Capacity conditions, that is, the rider’s current capacity load (such as the current number of orders carried) does not exceed the preset load threshold, indicating that the rider has the objective ability to accept orders.

[0078] (2) Spatial conditions, namely, the straight-line distance between the rider's current location and the starting point of the delivery order combination is less than the second distance threshold (e.g., 1.5 kilometers), which indicates that the rider can reach the centralized pickup point of the combination relatively quickly.

[0079] If riders who meet both of the above sub-conditions can be found, these riders will be grouped into a third rider set. The entire delivery order combination will be presented during the push notification, attracting riders with a higher total price.

[0080] If no match is found in the first two layers, the system executes a final fallback recommendation based on individual convenience. The system directly obtains the permanent location information of each rider in the first rider set. Then, it determines whether the distance between the destination of the target delivery order and the boundary (or center point) of each rider's permanent location is less than a third distance threshold (e.g., 100 meters). If so, it meets the third recommendation criteria. Finally, all riders who meet the third recommendation criteria are included in the third rider set.

[0081] This embodiment defines a strictly progressive three-tiered recommendation system: "Preference → Value → Convenience." First, the first tier, based on historical behavior and preference matching, ensures recommended orders align with riders' subjective desires, significantly improving the relevance of recommendations and riders' willingness to accept orders, while reducing interference from invalid push notifications. When personalized recommendations fail, the second tier intelligently constructs order packages, transforming individual orders into more economically attractive bundles for riders. This is combined with objective criteria of delivery capacity and space to ensure recommendations are given to riders capable of efficiently completing the bundle, resolving the issue of order backlogs due to insufficient attractiveness of individual orders and significantly improving the efficiency of high-density order processing. Finally, a fallback solution is provided to maximize the use of marginal opportunities: the third tier utilizes the correlation between the order's destination and the rider's usual location for recommendations. While this may offer weaker economic incentives for riders, the near-zero cost of convenient access remains highly attractive to certain riders (such as those finishing their shifts). This allows for the discovery of the final segment of "marginal delivery capacity" based on extreme convenience, further reducing the final order failure rate.

[0082] In some embodiments, if the third set of riders consists of candidate delivery riders who meet the first or third recommendation criteria, the target delivery order is pushed to each candidate delivery rider who meets the first or third recommendation criteria.

[0083] In some embodiments, pushing a target delivery order to each candidate delivery rider in a third rider set includes: if the third rider set consists of candidate delivery riders who meet a second recommendation criterion, then pushing a delivery order combination to each candidate delivery rider who meets the second recommendation criterion; the combination criterion refers to the distance between the delivery origin and the target delivery origin being less than a fourth distance threshold, and the distance between the delivery destination and the target delivery destination being less than the fourth distance threshold. The fourth distance threshold is a geographical distance threshold (e.g., it can be set to 800 meters) used to define the degree of aggregation within a delivery order combination. This threshold ensures that orders within a delivery order combination are not only close at the pickup point but also highly concentrated in the final delivery area, thereby guaranteeing that the combined orders have the efficient characteristic of completing multiple orders within a short distance for the rider.

[0084] Before entering the push notification stage, the system has already filtered out matching orders from the order pool based on combination conditions (using a fourth distance threshold), and these orders, together with the target delivery order, constitute a delivery order combination. In this embodiment, the system will again confirm the validity of this combination and the details of the orders within it.

[0085] Instead of simply encapsulating the single information of the target delivery order into a push message, the system generates an aggregated and specialized push message for the entire delivery order combination. This push message can include a combination identifier and combination summary information. The combination summary information can include the total number of orders within the combination, estimated total delivery revenue, the range of aggregated pickup points (or landmarks near the origin gathering center), and the aggregated delivery area, etc.

[0086] The system will send the push information of the entire delivery order combination to each candidate delivery rider in the third rider set simultaneously or quickly in sequence through message channels (such as APP push notifications and system messages).

[0087] Each rider will see a single order-grabbing entry on their terminal, representing the entire order combination. When a rider chooses to accept an order, it indicates their willingness and commitment to take on all orders within that delivery order combination. The order acceptance response received by the system also corresponds to acceptance of the entire combination.

[0088] This embodiment intelligently aggregates and uniformly pushes the dispersed value (unit price) and route information (origin and destination) of multiple orders that meet the combination conditions. This makes the two core attractive points of "high total price" and "concentrated route" immediately clear to riders, increasing their click-through rate and willingness to accept orders. Furthermore, by pushing and accepting orders based on delivery order combinations, the allocation negotiation of multiple orders can be completed at once, simplifying the potential for multiple rounds and multiple matching into a single efficient batch transaction. This not only reduces the system's communication overhead and state synchronization complexity but also ensures that the contract between the rider and the system (accepting all orders within the combination) is clear and unambiguous from the beginning, avoiding potential disputes over selective order acceptance and improving the certainty and efficiency of the process.

[0089] In some embodiments, detecting whether there are candidate delivery riders in the first rider set who meet the first recommendation criteria includes: determining the delivery distance of the target delivery order based on the target delivery origin and the target delivery destination; comparing the delivery distance of the target delivery order with the distance range corresponding to a preset delivery distance level; determining the distance level to which the delivery distance of the target delivery order belongs based on the comparison result; obtaining the historical order-taking distance records of each candidate delivery rider in the first rider set; analyzing the preferred distance level of each candidate delivery rider based on the historical order-taking distance records of each candidate delivery rider; and determining that the candidate delivery rider meets the first recommendation criteria if the preferred distance level and the distance level to which the delivery distance of the target delivery order belongs are the same for any candidate delivery rider.

[0090] Delivery distance refers to the estimated travel distance between the target delivery order's target delivery origin and target delivery destination.

[0091] The preferred distance level refers to the distance level to which a rider is most inclined to accept orders, derived from statistical analysis of a rider's historical behavioral data.

[0092] In this embodiment, the system calculates the precise delivery distance (in kilometers) of a target delivery order by calling geospatial calculation functions (such as the Haversine formula) or route planning services based on the coordinates (such as latitude and longitude) of the target delivery origin and destination. Next, the system compares the calculated delivery distance value with the distance intervals corresponding to each level in a preset delivery distance level table. Based on the comparison results, it determines which interval the delivery distance falls into and assigns the corresponding level identifier (such as "Level 2") to the distance level to which the target delivery order's delivery distance belongs. For example, a delivery distance of 3.5 kilometers falling into the [2,5) interval is labeled as "Level 2".

[0093] For each candidate delivery rider in the first rider set, the system retrieves the rider's historical order-taking distance records from their behavior database for a certain period or a preset number of completed delivery orders (e.g., the last 30 days or 100 orders). The system analyzes these historical order-taking distance records; specifically, it categorizes the delivery distance of each completed delivery order in the historical order-taking distance records into the corresponding distance level according to the same preset delivery distance level rules.

[0094] Then, the system calculates the number of orders or the percentage of orders received by each rider at each distance level. The system determines the distance level with the highest number of orders (or the highest percentage of orders received) as the rider's preferred distance level. For example, if a rider's order history shows that "Level 2" orders account for 60% of their total orders, then their preferred distance level is "Level 2".

[0095] For any candidate delivery rider, the system compares their preferred distance level with the distance level corresponding to the delivery distance of the target order. If the two levels are exactly the same, the candidate delivery rider is deemed to meet the first recommendation criterion. If the levels are different, the rider is deemed not to meet the criterion. The system iterates through the entire first set of riders, recording all riders that meet this matching rule.

[0096] This embodiment quantifies subjective preferences into calculable level matching. Specifically, by assigning distance levels to orders and establishing a preference distance level model for riders, the system can accurately and personally match orders with riders on the key dimension of delivery distance. This ensures that the orders pushed by the system closely match the riders' historical behavior patterns, greatly enhancing the personal relevance and attractiveness of the recommendations, thereby increasing the probability that riders will convert their viewing of the recommendations into order-grabbing behavior. Furthermore, traditional indiscriminate push notifications result in a large number of riders receiving orders they are not interested in, creating information harassment and wasting communication resources. This embodiment, through pre-emptive preference matching filtering, ensures that only riders whose historical data suggests they may be interested in orders at this distance are included in the push notification list. This significantly reduces the number of invalid push notifications, minimizes disruption to riders, and saves server message push bandwidth and processing overhead.

[0097] It should be noted that, regarding the steps included in the intelligent matching method for delivery orders and delivery riders provided in any of the above embodiments, unless explicitly stated herein, there is no strict order restriction on the execution of these steps; they can be executed in other orders. Furthermore, at least some of these steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps.

[0098] Based on the same inventive concept, this application also provides a smart matching device for delivery orders and delivery riders. In some embodiments, such as Figure 2 As shown, the intelligent matching device for delivery orders and delivery riders includes the following modules: The order information acquisition module 110 is used to acquire the order information of the target delivery orders to be dispatched. The order information includes the target delivery origin and the target delivery destination. The candidate rider determination module 120 is used to determine the delivery riders whose current location is within a preset distance range centered on the target delivery origin as candidate delivery riders, thereby obtaining the first set of riders; The direct matching module 130 is used to select candidate delivery riders who meet the preset direct matching conditions from the first rider set as the second rider set, determine the target delivery rider from the second rider set, and dispatch the target delivery order to the target delivery rider. The order recommendation module 140 is used to select candidate delivery riders who meet the preset direct matching conditions from the first rider set if there are no candidate delivery riders in the first rider set. Then, it selects candidate delivery riders who meet the preset recommendation conditions as the third rider set, pushes the target delivery order to each candidate delivery rider in the third rider set, determines the target delivery rider based on the received order acceptance response information, and dispatches the target delivery order to the target delivery rider.

[0099] In some embodiments, the preset direct matching conditions include a first matching condition and a second matching condition; the first matching condition refers to the capacity status being idle; the second matching condition refers to the capacity status being in a back-order status, and the delivery origin and target delivery origin of at least one accepted delivery order are the same and the distance between the delivery destination and the target delivery destination is less than a first distance threshold. The direct matching module 130 selects candidate delivery riders from the first rider set who meet the preset direct matching conditions as the second rider set. The operation includes: detecting whether there are candidate delivery riders in the first rider set who meet the first matching conditions; if there are, selecting the candidate delivery riders who meet the first matching conditions as the second rider set; if not, detecting whether there are candidate delivery riders in the first rider set who meet the second matching conditions; if so, selecting the candidate delivery riders who meet the second matching conditions as the second rider set.

[0100] In some embodiments, the direct matching module 130 is further configured to determine that there are no candidate delivery riders in the first rider set that meet the preset direct matching conditions if there are no candidate delivery riders in the first rider set that meet the second matching conditions.

[0101] In some embodiments, the preset recommendation criteria include a first recommendation criterion, a second recommendation criterion, and a third recommendation criterion; the operation of the order recommendation module 140 in selecting candidate delivery riders who meet the preset recommendation criteria from the first rider set as the third rider set includes: detecting whether there are candidate delivery riders who meet the first recommendation criteria in the first rider set; the first recommendation criterion refers to the distance level to which the historical order-taking distance record and the delivery distance of the target delivery order belong; if they exist, the candidate delivery riders who meet the first recommendation criteria are included in the third rider set; if they do not exist, delivery orders that meet the combination criteria with the target delivery order are selected from all delivery orders to be dispatched, and the selected orders are... The delivery orders and target delivery orders are combined into a delivery order set. Based on the delivery order set, it is checked whether there are candidate delivery riders in the first rider set who meet the second recommendation condition. The second recommendation condition is that the current capacity load does not exceed the preset load threshold, and the distance between the current location and the origin aggregation center determined by the delivery origin of each delivery order in the delivery order set is less than the second distance threshold. If so, the candidate delivery riders who meet the second recommendation condition are included in the third rider set. If not, the candidate delivery riders in the first rider set who meet the third recommendation condition are included in the third rider set. The third recommendation condition is that the distance between the permanent location and the target delivery destination is less than the third distance threshold.

[0102] In some embodiments, the operation of the order recommendation module 140 to push the target delivery order to each candidate delivery rider in the third rider set includes: if the third rider set is a candidate delivery rider that meets the second recommendation condition, then the delivery order combination is pushed to each candidate delivery rider that meets the second recommendation condition; the combination condition means that the distance between the delivery origin and the target delivery origin is less than a fourth distance threshold, and the distance between the delivery destination and the target delivery destination is less than the fourth distance threshold.

[0103] In some embodiments, the operation of the order recommendation module 140 in detecting whether there are candidate delivery riders in the first rider set that meet the first recommendation criteria includes: determining the delivery distance of the target delivery order based on the target delivery origin and the target delivery destination; comparing the delivery distance of the target delivery order with the distance range corresponding to a preset delivery distance level; determining the distance level to which the delivery distance of the target delivery order belongs based on the comparison result; obtaining the historical order-taking distance records of each candidate delivery rider in the first rider set; analyzing the preferred distance level of each candidate delivery rider based on the historical order-taking distance records of each candidate delivery rider; and determining that the candidate delivery rider meets the first recommendation criteria if the preferred distance level and the distance level to which the delivery distance of the target delivery order belongs are the same for any candidate delivery rider.

[0104] In some embodiments, the order recommendation module 140 is further configured to determine that the matching has failed if it does not receive an order acceptance response from any candidate delivery rider in the third rider set within a preset time period, and send the target delivery order to the order grabbing hall.

[0105] Specific limitations regarding the intelligent matching device for delivery orders and riders can be found in the limitations of the intelligent matching method for delivery orders and riders mentioned above, and will not be repeated here. Each module in the aforementioned intelligent matching device for delivery orders and riders can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0106] This application also provides a computer device. In some embodiments, the computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it can implement the intelligent matching method for delivery orders and delivery riders provided in any of the above embodiments.

[0107] In some embodiments, the internal structure diagram of a computer device may be as follows: Figure 3As shown, the computer device includes a processor, memory, and network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database stores data such as order information; the specific data stored may also be as defined in the above method embodiments. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for intelligent matching of delivery orders and delivery riders.

[0108] Those skilled in the art will understand that Figure 3 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0109] This application also provides a computer-readable storage medium, in some embodiments of which a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, it implements the intelligent matching method for delivery orders and delivery riders provided in any of the above embodiments.

[0110] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0111] Those skilled in the art will understand that implementing all or part of the processes in the above method embodiments can be accomplished by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), Synchlink, DRAM (SLDRAM), memory bus, direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0112] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0113] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for intelligently matching delivery orders and delivery riders, characterized in that, The method includes: Obtain the order information of the target delivery orders to be dispatched, wherein the order information includes the target delivery origin and the target delivery destination; The delivery riders whose current location is within a preset distance range centered on the target delivery origin are identified as candidate delivery riders, thus obtaining the first set of riders; From the first set of riders, select candidate delivery riders who meet the preset direct matching conditions to form a second set of riders. From the second set of riders, determine the target delivery rider and dispatch the target delivery order to the target delivery rider. If there are no candidate delivery riders in the first rider set who meet the preset direct matching conditions, select candidate delivery riders who meet the preset recommendation conditions from the first rider set to form a third rider set. Push the target delivery order to each candidate delivery rider in the third rider set. Determine the target delivery rider based on the received order acceptance response information and dispatch the target delivery order to the target delivery rider.

2. The method according to claim 1, characterized in that, The preset direct matching conditions include a first matching condition and a second matching condition; the first matching condition refers to the transportation capacity being in an idle state; the second matching condition refers to the transportation capacity being in a back-to-order state, and the delivery origin of at least one accepted delivery order is the same as the target delivery origin, and the distance between the delivery destination and the target delivery destination is less than a first distance threshold. The second rider set is composed of candidate delivery riders who meet the preset direct matching criteria selected from the first rider set, including: Detect whether there are any candidate delivery riders in the first rider set that meet the first matching conditions; If they exist, the candidate delivery riders who meet the first matching conditions will be included in the second rider set. If not, check if there are any candidate delivery riders in the first rider set that meet the second matching conditions; If so, the candidate delivery riders who meet the second matching conditions will be included in the second rider set.

3. The method according to claim 2, characterized in that, The method further includes: If there are no candidate delivery riders in the first rider set who meet the second matching conditions, it is determined that there are no candidate delivery riders in the first rider set who meet the preset direct matching conditions.

4. The method according to claim 1 or 2, characterized in that, The preset recommendation conditions include a first recommendation condition, a second recommendation condition, and a third recommendation condition; The third rider set is composed of candidate delivery riders who meet the preset recommendation criteria selected from the first rider set, including: Detect whether there are any candidate delivery riders in the first rider set that meet the first recommendation criteria; the first recommendation criteria refer to the matching of the distance level to which the historical order-taking distance record and the delivery distance of the target delivery order belong; If they exist, the candidate delivery riders who meet the first recommendation criteria will be included in the third rider set. If none exists, select delivery orders that meet the combination conditions with the target delivery order from all delivery orders to be dispatched, and combine the selected delivery orders and the target delivery order as a delivery order combination. Based on the delivery order combination, check whether there are candidate delivery riders in the first rider set that meet the second recommendation conditions. The second recommendation conditions refer to the current capacity load not exceeding a preset load threshold, and the distance between the current location and the origin aggregation center determined based on the delivery origin of each delivery order in the delivery order combination is less than a second distance threshold. If so, the candidate delivery riders who meet the second recommendation criteria will be used as the third rider set; If not, the candidate delivery riders in the first rider set who meet the third recommendation criteria are selected as the third rider set; the third recommendation criteria refer to the distance between the rider's permanent residence area and the target delivery destination being less than a third distance threshold.

5. The method according to claim 4, characterized in that, Pushing the target delivery order to each candidate delivery rider in the third rider set includes: If the third rider set is a candidate delivery rider that meets the second recommendation criteria, then the delivery order combination is pushed to each candidate delivery rider that meets the second recommendation criteria; the combination criteria refer to the distance between the delivery origin and the target delivery origin being less than a fourth distance threshold, and the distance between the delivery destination and the target delivery destination being less than the fourth distance threshold.

6. The method according to claim 4, characterized in that, Detecting whether there are candidate delivery riders in the first rider set that meet the first recommendation criteria includes: The delivery distance of the target delivery order is determined based on the target delivery origin and the target delivery destination. The delivery distance of the target delivery order is compared with the distance range corresponding to the preset delivery distance level. Based on the comparison result, the distance level to which the delivery distance of the target delivery order belongs is determined. Obtain the historical order-taking distance records of each candidate delivery rider in the first rider set, and analyze the preferred distance level of each candidate delivery rider based on the historical order-taking distance records of each candidate delivery rider; For any candidate delivery rider, if the preferred distance level and the delivery distance of the target delivery order belong to the same distance level, then the candidate delivery rider is determined to meet the first recommendation condition.

7. The method according to claim 1, characterized in that, The method further includes: If no order acceptance response is received from any candidate delivery rider in the third rider set within the preset time period, the matching is deemed to have failed, and the target delivery order is sent to the order grabbing hall.

8. A smart matching device for delivery orders and delivery riders, characterized in that, The device includes: The order information acquisition module is used to acquire the order information of the target delivery orders to be dispatched, including the target delivery origin and the target delivery destination; The candidate rider determination module is used to determine the delivery riders whose current location is within a preset distance range centered on the target delivery starting point as candidate delivery riders, thereby obtaining a first set of riders; The direct matching module is used to select candidate delivery riders who meet the preset direct matching conditions from the first rider set as a second rider set, determine the target delivery rider from the second rider set, and dispatch the target delivery order to the target delivery rider. The order recommendation module is used to select candidate delivery riders who meet the preset direct matching conditions from the first rider set if there are no candidate delivery riders in the first rider set. This is then used as a third rider set. The target delivery order is pushed to each candidate delivery rider in the third rider set. The target delivery rider is determined based on the received order acceptance response information, and the target delivery order is dispatched to the target delivery rider.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 7.

10. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method according to any one of claims 1 to 7.

Images