Short-distance order selection and real-time delivery response method and system

Abstract

The invention discloses a short-distance order selection and real-time delivery response method and system, and the system comprises an order receiving module, an order optimization module, a delivery path planning module, a deliveryman distribution module, a state monitoring and feedback module and an exception handling module, the order receiving module is used for receiving a delivery order submitted by a user through a mobile terminal or a webpage terminal, carrying out the preprocessing of order information, and transmitting the preprocessed order information to a server; the order optimization module is used for ordering and selecting orders through an optimization algorithm on the basis of geographic positions, delivery time requirements and commodity characteristics of the orders, the delivery path planning module is used for generating an optimal delivery path according to the selected orders and adjusting the delivery path in real time by utilizing a dynamic path optimization algorithm, and the deliveryman distribution module is used for distributing the deliveryman. According to the current state, the distance and the workload condition of the deliveryman, the order is allocated to the optimal deliveryman, so that the order selection and delivery efficiency is improved through an intelligent means, the delivery path is optimized, and the abnormal condition in the delivery process is responded in time.

Description

Technical Field

[0001] The present invention relates to the fields of computer technology and logistics distribution, and particularly to a method and system for near-distance order selection and real-time distribution response. Specifically, the present invention provides an intelligent solution for near-distance order selection and real-time distribution response by applying optimization algorithms, real-time data processing, and resource scheduling technologies, which is widely applied in systems such as instant delivery and logistics management. Background Art

[0002] With the rapid growth of e-commerce and instant delivery demands, the traditional order delivery mode can no longer meet the increasingly complex delivery requirements. Especially in urban near-distance delivery, there are problems such as long delivery times, unreasonable route planning, and uneven distribution of delivery staff resources. In addition, factors such as the urgency of orders, geographical locations, and delivery requirements often lead to low delivery efficiency. Most existing delivery systems rely on static routes and manual intervention, lacking flexible dynamic adjustment capabilities and unable to respond in real time to changing situations such as traffic conditions, order changes, or the status of delivery staff.

[0003] To solve the above problems, intelligent delivery systems have emerged. By introducing technologies such as order optimization algorithms, real-time route planning, intelligent allocation of delivery staff, and status monitoring, attempts are made to improve order processing efficiency and reduce delivery times. However, existing delivery systems still face many challenges, such as how to accurately select orders for priority delivery from complex order data, how to optimize routes according to real-time traffic conditions, and how to efficiently and reasonably allocate delivery staff resources.

[0004] Therefore, there is an urgent need for an integrated near-distance order selection and real-time distribution response system, which can, through intelligent means, achieve order optimization, route optimization, reasonable allocation of delivery staff, and real-time response to exceptions, thereby improving delivery efficiency, reducing delivery costs, and effectively coping with various problems that may occur during the delivery process. Summary of the Invention

[0005] The present invention provides a method and system for near-distance order selection and real-time distribution response, which improve order selection and delivery efficiency, optimize delivery routes, and timely respond to exceptions during the delivery process through the cooperation of multiple modules and intelligent means.

[0006] The present invention specifically includes the following:

[0007] 1. An order receiving module, which receives delivery orders submitted by users through mobile terminals or web terminals and preprocesses the order information. Specifically, it includes:

[0008] (1) User Information Parsing Unit: It uses natural language processing algorithms to parse the order information submitted by users, identify and extract the user's identity information, delivery address, contact information, delivery time requirements, special remarks, etc. Through technologies such as text segmentation, syntax analysis, and keyword recognition, it ensures the accuracy and integrity of the information, avoiding delivery problems caused by incorrect or missing user filling.

[0009] (2) Order Preprocessing Unit: It preprocesses the order information through set rules and data verification technologies, marks special requirements (such as delivery time, special requirements for goods, etc.), and gives prompts or automatically supplements incomplete or abnormal orders.

[0010] (3) Data Storage Unit: It stores the order data into the system database and provides data interfaces for subsequent modules, ensuring real-time update and efficient access of the data. In the database, the order data is stored in a structured manner for quick retrieval and processing.

[0011] 2. Order Optimization Module: Based on the geographical location, delivery time requirements, and product characteristics of the orders, it sorts and selects orders through optimization algorithms, specifically including:

[0012] (1) Geographical Location Analysis Unit: It analyzes the geographical location of the orders through Geographic Information System (GIS) algorithms, calculates the delivery radius of the orders and the geographical aggregation degree with other orders. In the case of multiple order requests, it judges which orders can be combined for delivery through distance calculation and an innovative weighted spatial clustering algorithm, thereby reducing the empty driving distance of the delivery staff. The formula is as follows:

[0013]

[0014] Among them, J represents the total weighted clustering error;

[0015] k represents the number of clusters, that is, the number of tasks for combined delivery;

[0016] x represents the geographical location vector of the order;

[0017] C i represents the i-th cluster (delivery group);

[0018] α, β, γ represent weight coefficients, satisfying α + β + γ = 1;

[0019] T(x) represents the time urgency of the order, and the larger the value, the higher the priority for processing;

[0020] V(x) represents the value of the order (product price), normalized to [0, 1];

[0021] R(x) represents the inverse value of the delivery radius;

[0022] d(x, μ i ) represents the distance from order x to the cluster center μ i ;

[0023] (2) Priority sorting unit, comprehensively sorts orders based on a multi-objective optimization algorithm. The optimization algorithm comprehensively considers multiple factors, including the urgency of delivery time, user ratings, commodity delivery priorities, etc., to generate an order priority list. The algorithm scores each order, weights each factor according to preset weights, and selects the optimal order through a sorting strategy.

[0024] (3) Order packing unit, when the delivery addresses of multiple adjacent orders are relatively close, the system will merge these orders into one delivery task through an order clustering algorithm (distance-based clustering algorithm). This packing unit will determine which orders can be merged based on the similarity of the orders and the compatibility of the delivery routes, thereby optimizing the delivery efficiency.

[0025] 3. Delivery route planning module, generates the optimal delivery route according to the selected orders, and uses a dynamic route optimization algorithm to adjust the delivery route in real time, specifically including:

[0026] (1) Dynamic traffic data collection unit, obtains real-time traffic information of the road through a real-time traffic data interface (road condition API or sensor data), including factors such as traffic flow, road closure, and accidents. These data can help the system dynamically adjust the route selection when planning the route, avoiding congestion and delays.

[0027] (2) Optimal route generation unit, generates the optimal delivery route by combining the A* algorithm with dynamic traffic data. The A* algorithm evaluates the shortest path from the starting point to the target point and adjusts the path selection in combination with the traffic conditions to reduce the delivery time and mileage. The algorithm will consider different path selections and real-time traffic flows and select the path with the minimum cost.

[0028] (3) Route dynamic adjustment unit, can monitor the traffic changes during the delivery process in real time. Once a traffic accident, congestion or other emergencies are detected, the system will re-evaluate the current route and make adjustments. The route adjustment algorithm ensures that the delivery efficiency is not affected by real-time monitoring and recalculating a new route.

[0029] 4. Delivery staff allocation module, allocates orders to the optimal delivery staff according to the current status, distance, and workload of the delivery staff, specifically including:

[0030] (1) Delivery staff status analysis unit, monitors the positions, working status (idle, busy), and delivery task loads of all delivery staff in real time. Based on this information, the system can effectively judge the workload of each delivery staff and make reasonable decisions for the next order allocation.

[0031] (2) Weight calculation unit, which calculates the matching degree between the delivery staff and the order through a resource allocation algorithm. The algorithm evaluates the weight of each delivery staff based on factors such as the distance between the current location of the delivery staff and the order location, the current workload of the delivery staff, and the historical performance of the delivery staff. The higher the weight of the delivery staff, the higher the priority of receiving orders.

[0032] (3) Allocation decision unit. After the weight calculation is completed, the system performs optimal delivery staff allocation based on the matching degree, path distance, and task urgency of the delivery staff. This process selects a suitable delivery staff to receive the order through decision algorithms (greedy algorithm, heuristic search algorithm) to ensure the timely and efficient completion of order delivery.

[0033] 5. Status monitoring and feedback module, which monitors the location of the delivery staff, delivery progress, and order status in real time and feeds back relevant information to the system, specifically including:

[0034] (1) GPS positioning unit, which connects to the GPS system to obtain the location and delivery progress of the delivery staff in real time. The system continuously tracks the routes of each delivery staff to ensure the transparency and real-time nature of the delivery process.

[0035] (2) Order progress tracking unit, which records the delivery status of each order, including the current delivery node of the order, picked up, in delivery, delivered, and its estimated arrival time. The data will be updated in real time and reports will be generated within the system for use by the back-end management.

[0036] (3) Data feedback unit. During the delivery process, the system will regularly feed back the status, progress, and expected arrival time of the delivery staff to the user. The user can view the real-time delivery information through the mobile application or web page to obtain a transparent order tracking experience.

[0037] 6. Exception handling module, which detects abnormal statuses during the order execution process and generates solutions through an adaptive exception handling algorithm, specifically including:

[0038] (1) Exception detection unit, which detects abnormal situations during the delivery process through classification algorithms (decision tree algorithm or support vector machine algorithm), such as delays, failure to deliver on time, lost orders, or user complaints. The system will identify each abnormal situation and automatically classify it.

[0039] (2) Exception analysis unit, which evaluates the causes of exceptions and provides potential solutions by analyzing historical data, delivery progress, and current status. The algorithm will combine real-time data and historical patterns to identify the root causes of exceptions and predict possible reasons.

[0040] (3) Abnormal response unit. When the system identifies an abnormality, the abnormal response unit will automatically trigger a response mechanism, send an alert to the system administrator and provide handling suggestions. When necessary, the system can also automatically adjust the delivery tasks, such as reassigning orders or adjusting the delivery route, to quickly resolve the problem and ensure the smooth completion of the order.

[0041] A method for near-distance order selection and real-time delivery response, comprising the following steps:

[0042] Step 1: Order reception. The system receives the order information submitted by the user through the order reception module, including the user's basic information, delivery address, contact information, delivery time requirements, commodity information, etc. After receiving the order, the system uses natural language processing (NLP) algorithms to parse the order data, extract valid information, and ensure the integrity and accuracy of the order through data verification technology. If the order has format errors or missing information, the system will prompt the user to modify or automatically supplement it according to preset rules to ensure the smooth progress of subsequent processing.

[0043] Step 2: Order optimization. The system uses a multi-objective optimization algorithm to sort all orders to be delivered. First, through geographic information system (GIS) technology, it analyzes the geographical locations of each order, calculates the delivery radius and priority of the order. The system combines the weighted spatial clustering algorithm according to factors such as urgency, distance, and order quantity to pack and merge multiple orders with similar geographical locations, reducing the empty driving distance of the delivery staff. At the same time, based on the optimization algorithm, each order is assigned a priority score to ensure that the delivery staff preferentially selects orders that are closer and have a higher degree of urgency, thereby improving the delivery efficiency.

[0044] Step 3: Delivery route planning. The system obtains the current road condition data through a dynamic traffic data interface (such as real-time traffic flow information), and combines the A algorithm to calculate the optimal route for the delivery task. The A algorithm evaluates the best delivery route based on the geographical locations of the order start and destination, as well as the real-time traffic conditions, ensuring that the delivery staff avoids congested or closed roads and improves the delivery efficiency. If the traffic conditions change during the delivery process, the system will use the path dynamic adjustment unit to update the route planning in real time and automatically adjust the route for the delivery staff to reduce delivery delays and ensure on-time delivery.

[0045] Step 4: Delivery staff assignment. The system monitors the location, working status, and workload of each delivery staff in real time. It evaluates the workload and task acceptance capacity of the delivery staff through algorithms. The matching degree of the delivery staff is weighted and scored by calculating factors such as the distance between their current location and the order location, idle status, and historical performance. Based on these weights, the system uses the greedy algorithm or heuristic search algorithm to assign the most suitable delivery staff for the order, ensuring a reasonable workload for the delivery staff and enabling them to complete tasks efficiently. In addition, the system also considers the experience, skills, and historical performance of the delivery staff to further optimize the delivery staff assignment strategy.

[0046] Step 5: Status monitoring and feedback step. The system continuously tracks the location information of the delivery staff and the delivery progress of the order through GPS and real-time monitoring technology, ensuring that the status of each order can be updated in real time and feedback to the user. The system monitors the driving path and progress of the delivery staff, and promptly discovers and reports any problems that may cause delays, such as traffic jams or accidents. Users can view real-time delivery information through the mobile application or online platform and obtain updates on the estimated arrival time. If there are any abnormalities in the delivery, the system can quickly identify and take measures to adjust through the status analysis module.

[0047] Step 6: Abnormality handling step. The system identifies various problems that may occur during the delivery process through abnormality detection algorithms, such as delays, failure to deliver on time, order loss, or user complaints. The system first detects abnormal events through classification algorithms (decision tree or support vector machine), then analyzes the root cause of the problem, evaluates the possible impacts and solutions. For the identified abnormalities, the system can automatically adjust the delivery path or reassign the delivery staff tasks to ensure that the problems are handled in a timely manner and avoid adverse impacts on other orders through intelligent scheduling. At the same time, the system will also push a detailed report of the abnormal situation to the administrator or user and provide corresponding handling suggestions to ensure the smooth progress of the delivery.

[0048] Beneficial effects

[0049] A method and system for near-distance order selection and real-time delivery response have the following beneficial effects:

[0050] Efficient order selection: By accurately parsing order information and applying optimization algorithms, the system can quickly identify and prioritize urgent or high-benefit orders, avoiding the low efficiency problems caused by random assignment in traditional methods.

[0051] Dynamic path optimization: Using a path planning algorithm based on real-time traffic data, it can adjust the optimal path in real time for delivery tasks, effectively avoiding congested sections and unexpected situations, significantly shortening the delivery time and reducing the delivery cost.

[0052] Reasonable resource allocation: Through intelligent scheduling algorithms, the system can comprehensively consider the location, load, and status of delivery personnel, reasonably allocate orders to the most suitable delivery personnel, avoid resource waste, and at the same time improve order completion efficiency.

[0053] Real-time status monitoring and user feedback: Using status monitoring technology, the system realizes the whole-process tracking of the delivery process and pushes the delivery progress information to users in real time, improving the user experience and service transparency.

[0054] Exception efficient handling: Through exception detection algorithms, the system can timely identify various abnormal situations in the delivery (such as delays or order losses), and quickly formulate adjustment plans, effectively reducing the negative impact of exceptions on delivery efficiency and user experience.

[0055] Improve overall logistics efficiency: Through the whole-link optimization of order selection, route planning, resource allocation, real-time monitoring, and exception handling, the system has significant effects in shortening delivery time, reducing operating costs, and improving customer satisfaction, providing a full-range intelligent solution for short-distance delivery scenarios. Description of the Drawings

[0056] Figure 1 is the flowchart of the order receiving module;

[0057] Figure 2 is the flowchart of the order optimization module;

[0058] Figure 3 is the flowchart of the delivery route planning module;

[0059] Figure 4 is the flowchart of the delivery personnel allocation module;

[0060] Figure 5 is the flowchart of the status monitoring and feedback module;

[0061] Figure 6 is the flowchart of the exception handling module;

[0062] Figure 7 is the flowchart of the method steps. Detailed Implementation Manner

[0063] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention:

[0064] The order receiving module receives the delivery orders submitted by users through the mobile terminal or the web terminal, and preprocesses the order information, specifically including:

[0065] (1) User Information Parsing Unit: It uses natural language processing algorithms to parse the order information submitted by users, identify and extract the user's identity information, delivery address, contact information, delivery time requirements, special remarks, etc. Through techniques such as text segmentation, syntax analysis, and keyword recognition, it ensures the accuracy and integrity of the information, avoiding delivery problems caused by incorrect or missing user filling.

[0066] (2) Order Preprocessing Unit: It preprocesses the order information through set rules and data verification techniques, marks special requirements (such as delivery time, special requirements for goods, etc.), and gives prompts or automatically supplements incomplete or abnormal orders.

[0067] (3) Data Storage Unit: It stores the order data in the system database and provides data interfaces for subsequent modules, ensuring real-time update and efficient access of the data. In the database, the order data is stored in a structured manner for quick retrieval and processing.

[0068] Order Optimization Module: Based on the geographical location, delivery time requirements, and commodity characteristics of the orders, it sorts and selects orders through optimization algorithms, specifically including:

[0069] (1) Geographical Location Analysis Unit: It analyzes the geographical location of the orders through Geographic Information System (GIS) algorithms, calculates the delivery radius of the orders and the geographical aggregation degree with other orders. In the case of multiple order requests, it determines which orders can be combined for delivery through distance calculation and an innovative weighted spatial clustering algorithm, thereby reducing the empty driving distance of the delivery staff. The formula is as follows:

[0070]

[0071] Among them, J represents the total weighted clustering error;

[0072] k represents the number of clusters, that is, the number of tasks for combined delivery;

[0073] x represents the geographical location vector of the order;

[0074] C i represents the i-th cluster (delivery group);

[0075] α, β, γ represent weight coefficients, satisfying α + β + γ = 1;

[0076] T(x) represents the time urgency of the order, and the larger the value, the higher the priority for processing;

[0077] V(x) represents the value (commodity price) of the order, normalized to [0, 1];

[0078] R(x) represents the inverse value of the delivery radius;

[0079] d(x, μ i ) represents the distance from order x to the cluster center μ i ;

[0080] (2) Priority sorting unit, which comprehensively sorts orders based on a multi-objective optimization algorithm. The optimization algorithm comprehensively considers multiple factors, including the urgency of delivery time, user ratings, commodity delivery priorities, etc., to generate an order priority list. The algorithm scores each order, weights each factor according to preset weights, and selects the optimal order through a sorting strategy.

[0081] (3) Order packing unit, when the delivery addresses of multiple adjacent orders are relatively close, the system will merge these orders into one delivery task through an order clustering algorithm (distance-based clustering algorithm). This packing unit will determine which orders can be merged based on the similarity of orders and the compatibility of delivery routes, thereby optimizing the delivery efficiency.

[0082] Delivery route planning module, which generates the optimal delivery route according to the selected orders and uses a dynamic path optimization algorithm to adjust the delivery route in real time, specifically including:

[0083] (1) Dynamic traffic data collection unit, which obtains real-time traffic information of the road through a real-time traffic data interface (road condition API or sensor data), including traffic flow, road closure, accidents, etc. These data can help the system dynamically adjust the route selection when planning the route to avoid congestion and delays.

[0084] (2) Optimal path generation unit, which generates the optimal delivery route through the A* algorithm combined with dynamic traffic data. The A* algorithm evaluates the shortest path from the starting point to the target point and adjusts the path selection in combination with the traffic conditions to reduce the delivery time and mileage. The algorithm will consider different path selections and real-time traffic flow and select the path with the minimum cost.

[0085] (3) Path dynamic adjustment unit, which can monitor the traffic changes during the delivery process in real time. Once a traffic accident, congestion or other emergencies are detected, the system will re-evaluate the current path and make adjustments. The path adjustment algorithm ensures that the delivery efficiency is not affected by real-time monitoring and recalculating a new route.

[0086] Deliveryman assignment module, which assigns orders to the optimal deliveryman according to the current status, distance and workload of the deliveryman, specifically including:

[0087] (1) Deliveryman status analysis unit, which monitors the positions, working status (idle, busy) and workload of delivery tasks of all deliverymen in real time. Based on this information, the system can effectively judge the workload of each deliveryman and make a reasonable decision for the next order assignment.

[0088] (2) Weight calculation unit, which calculates the matching degree between the deliveryman and the order through a resource allocation algorithm. The algorithm evaluates the weight of each deliveryman based on factors such as the distance between the deliveryman's current location and the order location, the deliveryman's current workload, and the deliveryman's historical performance. The higher the weight of the deliveryman, the higher the priority of receiving the order.

[0089] (3) Allocation decision unit. After the weight calculation is completed, the system performs optimal deliveryman allocation according to the matching degree, path distance, and task urgency of the deliveryman. This process selects a suitable deliveryman to receive the order through decision algorithms (greedy algorithm, heuristic search algorithm) to ensure the timely and efficient completion of the order delivery.

[0090] Status monitoring and feedback module, which monitors the deliveryman's location, delivery progress, and order status in real time and feeds back relevant information to the system, specifically including:

[0091] (1) GPS positioning unit, which connects to the GPS system to obtain the deliveryman's location and delivery progress in real time. The system continuously tracks the route of each deliveryman to ensure the transparency and real-time nature of the delivery process.

[0092] (2) Order progress tracking unit, which records the delivery status of each order, including the current delivery node of the order (picked up, in delivery, delivered) and its estimated arrival time. The data will be updated in real time and reports will be generated within the system for use by the back-end management.

[0093] (3) Data feedback unit. During the delivery process, the system will regularly feedback the deliveryman's status, progress, and expected arrival time to the user. The user can view the real-time delivery information through the mobile application or web page to obtain a transparent order tracking experience.

[0094] Abnormal handling module, which detects abnormal states during the order execution process and generates solutions through an adaptive abnormal handling algorithm, specifically including:

[0095] (1) Abnormal detection unit, which detects abnormal situations during the delivery process through classification algorithms (decision tree algorithm or support vector machine algorithm), such as delays, failure to arrive on time, lost orders, or user complaints. The system will identify each abnormal situation and automatically classify it.

[0096] (2) Abnormal analysis unit, which evaluates the causes of abnormalities and provides potential solutions by analyzing historical data, delivery progress, and current status. The algorithm combines real-time data and historical patterns to identify the root causes of abnormalities and predict possible causes.

[0097] (3) Abnormal response unit. When the system identifies an abnormality, the abnormal response unit will automatically trigger a response mechanism, send an alert to the system administrator and provide handling suggestions. When necessary, the system can also automatically adjust the delivery tasks, such as reassigning orders or adjusting the delivery route, to quickly resolve the problem and ensure the smooth completion of the order.

[0098] A method for near-distance order selection and real-time delivery response, comprising the following steps:

[0099] Step 1: Order reception. The system receives the order information submitted by the user through the order reception module, including the user's basic information, delivery address, contact information, delivery time requirements, commodity information, etc. After receiving the order, the system uses natural language processing (NLP) algorithms to parse the order data, extract valid information, and ensure the integrity and accuracy of the order through data verification technology. If the order has format errors or missing information, the system will prompt the user to modify or automatically supplement it according to preset rules to ensure the smooth progress of subsequent processing.

[0100] Step 2: Order optimization. The system uses a multi-objective optimization algorithm to sort all orders to be delivered. First, through geographic information system (GIS) technology, it analyzes the geographical locations of each order, calculates the delivery radius and priority of the order. The system combines the weighted spatial clustering algorithm according to factors such as urgency, distance, and order quantity to pack and merge multiple orders with similar geographical locations, reducing the empty driving distance of the delivery staff. At the same time, based on the optimization algorithm, a priority score is assigned to each order to ensure that the delivery staff gives priority to selecting orders that are closer and have a higher degree of urgency, thereby improving the delivery efficiency.

[0101] Step 3: Delivery route planning. The system obtains the current road condition data through a dynamic traffic data interface (such as real-time traffic flow information), and combines the A algorithm to calculate the optimal route for the delivery task. The A algorithm evaluates the best delivery route based on the geographical locations of the order's starting point and destination, as well as the real-time traffic conditions, ensuring that the delivery staff avoids congested or closed roads and improves the delivery efficiency. If the traffic conditions change during the delivery process, the system will use the path dynamic adjustment unit to update the route planning in real time and automatically adjust the route for the delivery staff to reduce delivery delays and ensure on-time delivery.

[0102] Step 4: Delivery staff assignment. The system monitors the location, working status, and workload of each delivery staff in real time. It evaluates the workload and task acceptance capacity of the delivery staff through algorithms. The matching degree of the delivery staff is weighted and scored by calculating factors such as the distance between their current location and the order location, idle status, and historical performance. Based on these weights, the system uses the greedy algorithm or heuristic search algorithm to assign the most suitable delivery staff for the order, ensuring a reasonable workload for the delivery staff and enabling them to complete tasks efficiently. In addition, the system also considers the experience, skills, and historical performance of the delivery staff to further optimize the delivery staff assignment strategy.

[0103] Step 5: Status monitoring and feedback step. The system continuously tracks the location information of the delivery staff and the delivery progress of the order through GPS and real-time monitoring technology, ensuring that the status of each order can be updated in real time and feedback to the user. The system monitors the driving path and progress of the delivery staff, promptly discovers and reports any problems that may cause delays, such as traffic jams or accidents. Users can view real-time delivery information and obtain updates on the estimated arrival time through the mobile application or online platform. If there are any abnormalities in the delivery, the system can quickly identify and take measures to adjust through the status analysis module.

[0104] Step 6: Abnormality handling step. The system identifies various problems that may occur during the delivery process through abnormality detection algorithms, such as delays, failure to deliver on time, order loss, or user complaints. The system first detects abnormal events through classification algorithms (decision trees or support vector machines), then analyzes the root cause of the problem, evaluates the possible impacts and solutions. For the identified abnormalities, the system can automatically adjust the delivery path or reassign the delivery staff tasks to ensure that the problems are handled in a timely manner and avoid adverse impacts on other orders through intelligent scheduling. At the same time, the system will also push a detailed report of the abnormal situation to the administrator or user and provide corresponding handling suggestions to ensure the smooth progress of the delivery.

Claims

1. A short-distance order selection and real-time delivery response system, characterized in that: Includes the following modules: The order receiving module is used to receive the delivery orders submitted by users through the mobile terminal or the web terminal and pre-process the order information; The order optimization module is used to sort and select orders through optimization algorithms based on the order's geographical location, delivery time requirements and product characteristics; The delivery route planning module is used to generate the optimal delivery route based on the selected orders and adjust the delivery route in real time using a dynamic route optimization algorithm; The deliveryman allocation module is used to allocate orders to the best deliveryman based on the deliveryman’s current status, distance, and workload; Status monitoring and feedback module, which is used to monitor the location of the delivery person, delivery progress and order status in real time, and feed back relevant information to the system; The exception handling module is used to detect abnormal conditions during order execution and generate solutions through adaptive exception handling algorithms.

2. The system according to claim 1, characterized in that The order receiving module comprises: User information parsing unit, used to extract user identity, address, contact information and remarks; The order pre-processing unit is used to mark the special requirements and delivery time periods in the order, and to prompt and supplement incomplete information; The data storage unit is used to store the parsed order information in the database and provide interface support for subsequent modules.

3. The system according to claim 1, characterized in that The order optimization module includes: The geographic location analysis unit is used to calculate the delivery radius and geographic concentration of orders, using an innovative weighted spatial clustering algorithm: Where J represents the sum of weighted clustering errors; k represents the number of clusters, that is, the number of tasks for combined delivery; x represents the geographic location vector of the order; C i represents the i-th cluster (delivery group); α, β, and γ represent weight coefficients, satisfying α+β+γ=1; T(x) indicates the time urgency of the order, and a larger value indicates that it needs to be processed first; V(x) represents the value of the order (product price), which is standardized to [0,1]; R(x) represents the inverse value of the delivery radius; d(x,μ i ) represents the order x to the cluster center μ i distance; Prioritization unit, used to comprehensively sort orders by order urgency, customer level and product characteristics based on a multi-objective optimization algorithm; The order packaging unit is used to merge and package orders that are close to each other, and provide packaging suggestions to the path planning module.

4. The system according to claim 1, characterized in that The delivery route planning module includes: Dynamic traffic data collection unit, used to obtain real-time traffic flow information; The optimal path generation unit is used to generate the delivery path by combining the A* algorithm with dynamic traffic data; The dynamic route adjustment unit is used to adjust the delivery route in real time according to traffic conditions or delivery personnel feedback, and recalculate the delivery time.

5. The system according to claim 1, characterized in that The delivery personnel allocation module includes: The deliveryman status analysis unit is used to monitor the deliveryman’s current location, work status, and idleness in real time; A weight calculation unit, used to calculate the matching weight between the delivery person and the order based on the resource allocation algorithm; The allocation decision unit is used to prioritize the distribution of delivery tasks according to the weights and notify the delivery personnel to confirm the receipt of the order.

6. The system according to claim 1, characterized in that The state monitoring and feedback module includes: GPS positioning unit, used to obtain the delivery person’s location in real time; The order progress tracking unit is used to record the delivery nodes and status of orders, including waiting for delivery, delivering, and completed; The data feedback unit is used to feed back the delivery data to the user end in real time and generate a delivery report for background analysis.

7. The system according to claim 1, characterized in that The exception handling module includes: Anomaly detection unit, which is used to identify anomalies in the delivery process through classification algorithms, including delivery delays, order loss, and user complaints; Anomaly analysis unit, used to analyze the causes of anomalies and predict possible solutions based on historical data; The exception response unit is used to push exception handling suggestions to administrators and can quickly handle them by reallocating orders or adjusting delivery routes.

8. A method for short-distance order selection and real-time delivery response, characterized in that: The following steps are involved: Step 1: Order receiving: receiving the order information submitted by the user through the order receiving module, parsing the user's remarks, pre-processing the order data, and storing the data in the order database; Step 2: Order optimization: The order optimization module uses a multi-objective optimization algorithm to comprehensively sort the orders according to their geographic location, urgency, and product characteristics, and packages adjacent orders when necessary; Step 3: Distribution route planning: Use the distribution route planning module, combined with the A* algorithm and real-time traffic data, to generate the optimal distribution route and dynamically adjust the route to avoid traffic congestion; Step 4: Delivery personnel allocation: Through the delivery personnel allocation module, the delivery personnel's idle status, distance and workload are analyzed in real time, and orders are allocated based on the weight calculation results; Step 5: Status monitoring and feedback: During the delivery process, the status monitoring and feedback module is used to track the location of the delivery person and the order status, and to feed back the relevant data to the user and the system background; Step 6: Exception handling: If a delivery exception is detected, the exception handling module will analyze the cause, generate a solution using an adaptive algorithm, and push processing suggestions to the administrator or the system to automatically perform adjustments.

Images