Internet of Things enhanced logistics distribution efficiency improvement method and system

Abstract

The invention discloses an Internet of Things enhanced logistics distribution efficiency improvement method and system, and relates to the technical field of Internet of Things, and the method comprises the steps: collecting logistics multi-source data and logistics distribution multi-dimensional data, and carrying out the preprocessing; based on the preprocessed logistics distribution multi-dimensional data, using a machine learning algorithm to predict a future distribution demand, and generating a prediction result of a distribution task; calculating the priority of each distribution task based on the prediction result of the distribution task; combining the preprocessed logistics multi-source data with distribution task priorities, and calculating a path of each distribution task priority by using an intelligent path algorithm; according to the distribution task priority, the storage position of the goods in the warehouse is adjusted; according to the invention, through an intelligent path planning algorithm, the distribution path is optimized to ensure that the high-priority task can be preferentially and rapidly distributed, and the storage position of the goods in the warehouse is intelligently adjusted according to the priority of the task, so that the high-priority goods can be extracted more rapidly.

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things, and in particular to a method and system for improving logistics distribution efficiency enhanced by the Internet of Things. Background Art

[0002] In recent years, Internet of Things (IoT) technology has been widely used in the field of logistics and distribution, showing great potential in improving distribution efficiency, optimizing warehouse management, and reducing distribution costs. Current path algorithms are often calculated based on fixed environmental data, while ignoring the impact of task priorities and environmental changes on the path. This makes it impossible to fully guarantee the delivery efficiency of high-priority tasks.

[0003] Existing routing algorithms are typically simplistic and fail to fully consider task priorities, cargo characteristics, and real-time changing environmental data, resulting in inefficiency in dynamic and complex logistics environments. Traditional warehouse management relies on manual adjustments to cargo storage locations and lacks real-time response to changes in task priorities. As a result, high-priority tasks may be constrained by inefficient storage locations, thereby increasing cargo retrieval time and reducing overall delivery efficiency. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides an IoT-enhanced method for improving logistics distribution efficiency, which solves the problem that existing path and warehouse management fail to respond to changes in task priorities in real time.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: In a first aspect, the present invention provides an IoT-enhanced method for improving logistics distribution efficiency, comprising collecting multi-source logistics data and multi-dimensional logistics distribution data, and performing pre-processing; Based on the pre-processed multi-dimensional logistics and distribution data, machine learning algorithms are used to predict future distribution demand and generate prediction results for distribution tasks. Based on the predicted results of the delivery tasks, calculate the priority of each delivery task; Combine the pre-processed logistics multi-source data with the delivery task priority, and use the intelligent routing algorithm to calculate the path for each delivery task priority; Adjust the storage location of goods in the warehouse according to the priority of delivery tasks; Based on the priority routes of the delivery tasks and the storage locations of the goods in the warehouse, the goods for each delivery task are quickly located and retrieved through intelligent scheduling algorithms.

[0007] As a preferred solution of the method for improving logistics distribution efficiency enhanced by the Internet of Things of the present invention, the following steps are included: collecting multi-source logistics data and multi-dimensional logistics distribution data and pre-processing them: The multi-source logistics data includes traffic, weather, road conditions and the location of delivery vehicles, and the multi-dimensional logistics and delivery data includes collected order data, order type, customer type and cargo type; Perform data cleaning and data organization on the collected multi-source logistics data and multi-dimensional logistics distribution data.

[0008] As a preferred solution of the method for improving logistics distribution efficiency enhanced by the Internet of Things of the present invention, the following steps are included: based on the pre-processed multi-dimensional logistics distribution data, a machine learning algorithm is used to predict future distribution demand, and the prediction results of the distribution task are generated. By taking the multi-dimensional data of logistics distribution as feature input and using the gradient boosting decision tree algorithm for training, a GBDT model is constructed to predict future cargo distribution demand; The pre-processed multi-dimensional logistics distribution data is divided into a training set and a test set, and the training set is used to train the GBDT model; Input the test set into the trained GBDT model to predict the future order quantity and obtain the predicted result of the order quantity; The geographically weighted regression method is used to analyze the order demand intensity in different geographical locations. The demand is weighted according to the order type to obtain the demand distribution of order type in each region and the prediction results of the delivery task.

[0009] As a preferred solution of the method for improving logistics distribution efficiency enhanced by the Internet of Things of the present invention, the priority of each distribution task is calculated based on the prediction result of the distribution task, including the following steps: According to the delivery time requirement of each delivery task, the timeliness score of each delivery task is obtained by calculating the difference between the current time and the delivery time using the time difference calculation method; According to the cargo type of each delivery task, the priority assignment method is used to obtain the importance of the cargo type of each delivery task; Based on the customer type, we analyze the order quantity and customer category and use a weighted scoring method to obtain the priority score of each customer, the customer priority score, the importance of the cargo type and the timeliness score of the delivery task; According to the final priority score, the weight of the timeliness score, the weight of the cargo type score, and the weight of the customer type are adjusted to sort the priority score of each task and obtain the priority of each delivery task.

[0010] As a preferred solution of the method for improving logistics distribution efficiency enhanced by the Internet of Things of the present invention, the following steps are included: combining the pre-processed logistics multi-source data with the distribution task priority and using the intelligent path algorithm to calculate the path for each distribution task priority: According to the priority of each delivery task, a greedy algorithm is used to select the optimal path for the delivery vehicle and determine the current node and target node of the delivery vehicle; Based on the pre-processed logistics multi-source data and the optimal path of the delivery vehicle, the Bellman-Ford algorithm is used to calculate the actual distance of the shortest path from the current node of the delivery vehicle to the target node; The Euclidean distance heuristic method is used to calculate the distance from the current node of the delivery vehicle to the target node of the delivery vehicle, and the RRT path optimization algorithm is used to calculate the path of the delivery task priority.

[0011] As a preferred solution of the method for improving logistics distribution efficiency enhanced by the Internet of Things of the present invention, wherein: adjusting the storage location of goods in the warehouse according to the priority of the distribution task includes the following steps: By sorting the priority scores of each task, the delivery task with the highest priority is selected, and the shortest distance matching algorithm is used to match it with the goods in the warehouse to identify the goods that need to be delivered first; Use stacker cranes to locate and move goods, and move high-priority goods to the warehouse's outbound exit; Use a dynamic priority adjustment algorithm to determine real-time adjustments to cargo storage; Based on the adjusted cargo location and delivery task priority, the cargo storage locations of all high-priority tasks are adjusted to the parking points close to the delivery vehicles.

[0012] As a preferred solution of the method for improving logistics distribution efficiency enhanced by the Internet of Things of the present invention, the following steps are included: based on the priority path of the distribution task and the storage location of the goods in the warehouse, the goods for each distribution task are quickly located and retrieved through an intelligent scheduling algorithm: Based on the adjusted cargo location and delivery task priority path, the Dijkstra algorithm is used to calculate the shortest path from the current location of the delivery vehicle to the cargo storage location; Use automated equipment to locate the warehouse cargo based on the shortest path from the delivery vehicle's current location to the cargo storage location; By locating the priority path of the delivery task and the location of the goods in the warehouse, it is found that the goods of the high-priority tasks are picked up first; The located goods in the warehouse are transported from the storage location to the designated extraction area by conveyor belts.

[0013] In a second aspect, the present invention provides a method for improving logistics distribution efficiency enhanced by the Internet of Things, comprising: Data collection module collects multi-source logistics data and multi-dimensional logistics distribution data and performs pre-processing; The prediction module uses machine learning algorithms to predict future delivery demand based on pre-processed multi-dimensional logistics and delivery data, and generates prediction results for delivery tasks; The priority module calculates the priority of each delivery task based on the predicted results of the delivery task; The delivery task module combines pre-processed logistics multi-source data with delivery task priorities and uses an intelligent routing algorithm to calculate the path for each delivery task priority; The cargo adjustment module adjusts the storage location of cargo in the warehouse according to the priority of delivery tasks; The extraction module uses an intelligent scheduling algorithm to quickly locate and extract the goods for each delivery task based on the delivery task priority path and the storage location of the goods in the warehouse.

[0014] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the method for improving logistics distribution efficiency enhanced by the Internet of Things as described in the first aspect of the present invention is implemented.

[0015] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the method for improving logistics distribution efficiency enhanced by the Internet of Things as described in the first aspect of the present invention.

[0016] The beneficial effects of the present invention are as follows: by using the GBDT model to predict future distribution needs, it is possible to respond to changing market demands in a timely manner; based on the prediction results, the task priority is calculated; and the priority of the distribution task is dynamically adjusted in combination with timeliness, cargo type and customer demand; through the intelligent path planning algorithm, the distribution path is optimized to ensure that high-priority tasks can be delivered quickly and preferentially; the storage location of goods in the warehouse is also intelligently adjusted according to the task priority, so that high-priority goods can be retrieved more quickly; combined with path planning and cargo storage location, goods can be quickly retrieved through automated equipment, thereby improving overall distribution efficiency, achieving efficient and accurate logistics distribution, and improving response speed and resource utilization. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 This is a flow chart of the method for improving logistics distribution efficiency enhanced by the Internet of Things in Example 1.

[0019] Figure 2 This is a module diagram of the method for improving logistics distribution efficiency enhanced by the Internet of Things in Example 1. DETAILED DESCRIPTION

[0020] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0021] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0022] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0023] Example 1, with reference to Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides a method for improving logistics distribution efficiency enhanced by the Internet of Things, comprising the following steps: S1. Collect multi-source logistics data and multi-dimensional logistics distribution data and perform pre-processing.

[0024] S1.1. Logistics multi-source data includes traffic, weather, road conditions and the location of delivery vehicles. Logistics distribution multi-dimensional data includes collected order data, order type, customer type and cargo type.

[0025] Furthermore, by collecting multi-source logistics data in real time, using the traffic monitoring platform to obtain road condition information, using the meteorological API to obtain weather data, and the delivery vehicles transmitting location data through GPS or sensors, the multi-dimensional logistics distribution data is connected with order management, customer relationship management and warehouse management to obtain relevant information of each order, customer classification and the specific nature of the goods.

[0026] S1.2. Clean and organize the collected multi-source logistics data and multi-dimensional logistics distribution data.

[0027] Furthermore, the data is preprocessed, including removing redundant or incomplete information, filling missing values ​​and eliminating noise. For traffic data, invalid abnormal data is removed and various types of data are standardized. For order data, information in different formats will be processed uniformly to ensure data consistency.

[0028] S2. Based on the pre-processed multi-dimensional logistics and distribution data, use machine learning algorithms to predict future distribution needs and generate prediction results for distribution tasks.

[0029] S2.1. By using multi-dimensional logistics and delivery data as feature input and training with the gradient boosting decision tree algorithm, a GBDT model is constructed to predict future cargo delivery demand. Furthermore, we use historical order data, order type, customer type, and product type to establish the feature input of the GBDT model. The advantage of the GBDT model is that it can process high-dimensional nonlinear data and improve the prediction effect through iterative optimization of weak learners.

[0030] S2.2. The pre-processed multi-dimensional logistics distribution data is divided into a training set and a test set, and the training set is used to train the GBDT model.

[0031] Furthermore, the pre-processed multi-dimensional logistics distribution data is divided into a certain ratio of 80% training set and 20% test set. The training set is used to train the GBDT model to enable it to learn the patterns and trends in the data. The GBDT model training uses the gradient descent method to optimize the loss function, so that the GBDT model can gradually adjust the parameters and improve the prediction accuracy. At the same time, in order to prevent overfitting, cross-validation technology is used in the training process to ensure the stability of the model.

[0032] S2.3. Input the test set into the trained GBDT model to predict the future order quantity and obtain the predicted result of the order quantity. The expression is: ; in, is the forecast result of order quantity, is the order quantity, is the index of the order quantity, For the The weight of the order quantity prediction, For the The predicted order quantity.

[0033] Furthermore, the test set data is input into the trained GBDT model to predict the number of future orders. First, the model calculates the predicted value of each order, and then a weighted sum is taken based on the prediction weight of each order to obtain the prediction result of the entire order batch.

[0034] S2.4. Use the geographically weighted regression method to analyze the order demand intensity in different geographical locations, weight the demand based on the order type, obtain the demand distribution of order type in each region, and obtain the prediction results of the delivery task.

[0035] Furthermore, the order quantity prediction results are combined with the geographic location information of the orders as the input of the GWR model. A geographic weight is assigned to each order. The size of the weight depends on the distance between the order and the distribution center or warehouse. The closer the distance, the greater the weight. Based on historical order data, the order density of different regions at different times is analyzed, and high-demand areas are predicted. The priority division of delivery tasks is further refined based on the order type.

[0036] S3. Based on the prediction results of the delivery tasks, calculate the priority of each delivery task.

[0037] S3.1. Based on the delivery time requirement of each delivery task, the timeliness score of each delivery task is obtained by calculating the difference between the current time and the delivery time using the time difference calculation method.

[0038] Furthermore, based on the delivery time requirements of each distribution task, the time difference calculation method is used to determine the timeliness score of the task. First, the time difference between the current time and the delivery deadline of the task is calculated to measure the urgency of the task. If the delivery time of the task is close and the time difference is small, the timeliness score will be higher, indicating that the task needs to be prioritized. If the delivery time is far, the timeliness score will be lower. It can accurately assess the urgency of each task and provide data support for subsequent priority sorting. The timeliness score helps ensure that the most urgent tasks can be scheduled first, thereby improving the response speed of the logistics distribution system.

[0039] S3.2. Based on the cargo type of each delivery task, the priority assignment method is used to obtain the importance of the cargo type of each delivery task.

[0040] Furthermore, each task is assigned a corresponding priority score based on the type of cargo it carries, according to preset classification rules (such as perishables, high-value goods, and standard goods). High-priority cargo such as perishables or valuables will receive higher scores, ensuring that these items are delivered first.

[0041] S3.3. Based on the customer type, the order quantity and customer category are analyzed and the weighted scoring method is used to obtain the priority score of each customer. The customer priority score, the importance of the cargo type and the timeliness score of the delivery task are expressed as follows: ; in, Score the final priority, is the weight of timeliness score, Score timeliness. The weights used to score the cargo type, Importance of cargo type, is the weight of the customer type, Rate the customer type.

[0042] Furthermore, based on historical data of customer type (such as VIP customers, key customers, and ordinary customers) and order quantity, a customer priority score is calculated for each task. This score takes into account the customer's value and order quantity. VIP customers and key customers usually have higher priority.

[0043] S3.4. Based on the final priority score, the weight of the timeliness score, the weight of the cargo type score, and the weight of the customer type are adjusted to sort the priority score of each task and obtain the priority of each delivery task.

[0044] Furthermore, the weight of each factor is adjusted according to its importance. The timeliness score has the highest weight. Delivery time directly affects customer satisfaction and the urgency of the task. The score of the cargo type comes second, especially for perishables and valuables, which need to be given priority in delivery. Although the customer type score is important, compared with timeliness and cargo type, this weighted adjustment can accurately determine the priority based on the actual needs of the task. After the priority scores of all tasks are calculated, these scores are sorted to ensure that the tasks with the highest priority are processed first. The sorting process ensures that high-priority tasks are given priority in resource scheduling, thereby maximizing delivery efficiency.

[0045] S4. Combine the pre-processed logistics multi-source data with the delivery task priority, and use the intelligent path algorithm to calculate the path of each delivery task priority.

[0046] S4.1. Based on the priority of each delivery task, a greedy algorithm is used to select the optimal path for the delivery vehicle and determine the current node and target node of the delivery vehicle.

[0047] Furthermore, based on the priority of each delivery task, a greedy algorithm is used to select the optimal path for the delivery vehicle. The greedy algorithm selects the shortest path (i.e., the path from the current node to the target node) each time to quickly find an approximate optimal solution. The algorithm prioritizes the path planning of high-priority tasks to ensure that high-priority delivery tasks can be processed in the shortest time. Based on the priority of the task, the current node and target node of the delivery vehicle are determined to ensure that the path planning can respond to priority changes in real time. S4.2. Based on the pre-processed logistics multi-source data and the optimal path of the delivery vehicle, the Bellman-Ford algorithm is used to calculate the actual distance of the shortest path from the current node of the delivery vehicle to the target node.

[0048] Furthermore, after selecting the optimal route for the delivery vehicle, the Bellman-Ford algorithm is used to calculate the actual distance of the shortest path from the delivery vehicle's current node to the target node. The Bellman-Ford algorithm can effectively handle graphs with negatively weighted edges and can take into account a variety of practical situations, such as traffic congestion and road closures. It can ensure the accuracy and shortest nature of the path, thereby improving delivery efficiency and reducing costs. The Bellman-Ford algorithm gradually updates the distance value of each node and ultimately obtains the shortest path from the starting point to the target node.

[0049] S4.3. Use the Euclidean distance heuristic method to calculate the distance from the current node of the delivery vehicle to the target node of the delivery vehicle, and use the RRT path optimization algorithm to calculate the path of the delivery task priority. The expression is:

[0050] in, is the priority path of the delivery task, is the actual cost of the delivery vehicle from the current node to the target node, is the estimated distance between the current node and the target node of the delivery vehicle, is the actual distance from the current node to the target node of the delivery vehicle, For nodes, is the weight of the actual distance, is the weight of actual cost, is the weight of the estimated distance.

[0051] Furthermore, the Euclidean distance heuristic method is used to calculate the straight-line distance from the current node to the target node of the delivery vehicle as a reference for path estimation. This method provides a simple and fast heuristic estimation and uses the RRT (rapidly expanding random tree) path optimization algorithm to further calculate the optimal path of the delivery vehicle. The RRT algorithm quickly explores and optimizes the path of the delivery vehicle by expanding the tree structure in high-dimensional space, allowing the vehicle to avoid obstacles and choose the most appropriate route. By combining the heuristic method and the RRT algorithm, the calculation of the delivery path is optimized to ensure that the delivery task is completed in the shortest time.

[0052] S5. Adjust the storage location of goods in the warehouse according to the priority of the delivery task.

[0053] S5.1. Rank the priority scores of each task, select the highest-priority delivery task, and use the shortest distance matching algorithm to match it with the goods in the warehouse to identify the goods that need to be delivered first. Furthermore, delivery tasks are sorted according to their priority scores, and the highest priority tasks are assigned to the relevant goods in the warehouse. By using the shortest distance matching algorithm, the goods closest to the delivery port and meeting the task requirements are selected based on the current task priority and the goods storage location. This ensures that the goods required for high-priority tasks can be found quickly, avoiding unnecessary transportation and waiting time.

[0054] S5.2. Use the stacker crane to move the goods to the storage location and move high-priority goods to the warehouse's exit.

[0055] Furthermore, automated equipment such as stacker cranes can be used to relocate goods, automatically moving high-priority goods from deeper within the warehouse to closer to the delivery point, thus reducing the time required to retrieve them. Based on route planning and real-time demand, stacker cranes quickly and accurately move goods, ensuring that high-priority deliveries are completed in the shortest possible time. This significantly increases the level of automation in warehouse operations and reduces errors and delays caused by manual operations.

[0056] S5.3. Use the dynamic adjustment algorithm of priority to determine the real-time adjustment of cargo storage. Use the dynamic adjustment algorithm of priority to determine the real-time adjustment of cargo storage. The expression is: ; in, The adjusted cargo position is: For in time The location where the goods are arranged, For the time Goods that need to be moved, For goods The amount of goods moved to the warehouse door, is the distance between the goods and the warehouse door, is the weight of the distance between the goods and the warehouse door, For goods, For time.

[0057] Furthermore, through the dynamic adjustment algorithm of priority, the position of the goods is adjusted in real time according to the priority of each delivery task. According to the priority score of the delivery task, the distance that each item needs to be moved is calculated and moved to a new storage location. The standardized score ensures that the goods required for tasks with higher priority can be adjusted to a location closer to the delivery port, reducing the time consumption when subsequent tasks are retrieved. Through the dynamic adjustment algorithm, we can flexibly respond to changes in the priority of delivery tasks and ensure that the inventory location is always efficiently optimized.

[0058] S5.4. Based on the adjusted cargo locations and delivery task priorities, adjust the cargo storage locations of all high-priority tasks to the parking spots close to the delivery vehicles.

[0059] Furthermore, after the adjustment of the cargo storage location is completed, the cargo required for all high-priority tasks will be stored in a location closer to the delivery vehicle parking point based on the priority of each delivery task. This adjustment ensures that in the actual delivery process, high-priority cargo in the warehouse can be picked up and delivered to customers in the shortest time, further reducing the transportation distance between the delivery vehicle and the warehouse, ensuring that high-priority tasks can be responded to quickly, improving delivery efficiency, and can greatly improve the flexibility and real-time response capabilities of warehouse management, ensuring the efficient operation of the logistics distribution process.

[0060] S6. Based on the priority path of the delivery task and the storage location of the goods in the warehouse, the goods for each delivery task are quickly located and retrieved through an intelligent scheduling algorithm.

[0061] S6.1. Based on the adjusted cargo location and delivery task priority path, use the Dijkstra algorithm to calculate the shortest path from the current location of the delivery vehicle to the cargo storage location.

[0062] Furthermore, based on the adjusted cargo storage location and delivery task priority, the Dijkstra algorithm is used to calculate the shortest path from the current location of the delivery vehicle to the cargo storage location. The Dijkstra algorithm gradually expands nodes to find the shortest path and updates the actual distance of each node on the path to ensure that the calculated path is optimal, reduce the driving distance of the delivery vehicle in the warehouse, and improve the efficiency of task processing.

[0063] S6.2. Use automated equipment to locate the warehouse cargo location based on the shortest path from the delivery vehicle's current location to the cargo storage location.

[0064] Furthermore, once the shortest path from the delivery vehicle's current location to the cargo storage location is determined, automated equipment will be used to accurately locate the cargo within the warehouse. Based on the path planning information and the storage conditions of the cargo within the warehouse, the automated equipment can quickly identify the exact location of the cargo, ensuring that the cargo within the warehouse can be accurately located, thus avoiding delays and errors in the manual positioning process.

[0065] S6.3. By locating the priority path of the distribution task and the location of the goods in the warehouse, it is determined that the goods of the high-priority tasks are picked up first.

[0066] Furthermore, after locating the position of the goods in the warehouse, combined with the priority sorting of the distribution tasks, it ensures that high-priority tasks can extract goods first. Through the intelligent scheduling algorithm, the order of goods extraction is automatically adjusted according to the urgency of the task, and high-priority goods are extracted first, which optimizes the processing order of tasks and ensures that urgent orders or important customers' needs are responded to first, thereby improving customer satisfaction.

[0067] S6.4. Use conveyor belts to transport the located goods in the warehouse from the storage location to the designated extraction area Furthermore, after the goods are successfully located, they are transported from the storage location to the designated pickup area through automated transmission equipment such as conveyor belts. The conveyor belts are connected to warehouse management to achieve efficient cargo transportation, quickly delivering the goods to the delivery vehicles, reducing manual intervention and waiting time. This not only improves the efficiency of picking up goods, but also makes the logistics process within the warehouse more automated, optimizing the timeliness of the overall delivery process.

[0068] This embodiment also provides an IoT-enhanced method for improving logistics and distribution efficiency, comprising: a data acquisition module for collecting multi-source logistics data and multi-dimensional logistics and distribution data, and performing pre-processing; The prediction module uses machine learning algorithms to predict future delivery demand based on pre-processed multi-dimensional logistics and delivery data, and generates prediction results for delivery tasks; The priority module calculates the priority of each delivery task based on the predicted results of the delivery task; The delivery task module combines pre-processed logistics multi-source data with delivery task priorities and uses an intelligent routing algorithm to calculate the path for each delivery task priority; The cargo adjustment module adjusts the storage location of cargo in the warehouse according to the priority of delivery tasks; The extraction module uses an intelligent scheduling algorithm to quickly locate and extract the goods for each delivery task based on the delivery task priority path and the storage location of the goods in the warehouse.

[0069] This embodiment also provides a computer device, which is suitable for the method of improving logistics distribution efficiency enhanced by the Internet of Things, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the method of improving logistics distribution efficiency enhanced by the Internet of Things proposed in the above embodiment.

[0070] The computer device may be a terminal, comprising a processor, memory, a communication interface, a display, and an input device connected via a bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores operations and computer programs. The internal memory provides an environment for the operations and computer programs stored in the non-volatile storage media. The communication interface of the computer device is used to communicate with external terminals via wired or wireless communication. Wireless communication may be achieved via Wi-Fi, a carrier network, NFC (near-field communication), or other technologies. The display of the computer device may be a liquid crystal display or an electronic ink display. The input device may be a touchscreen overlay on the display, buttons, a trackball, or a touchpad on the computer device housing, or an external keyboard, touchpad, or mouse.

[0071] This embodiment also provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for improving logistics distribution efficiency enhanced by the Internet of Things as proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0072] In summary, the present invention predicts future distribution demand by using the GBDT model, which can respond to changing market demand in a timely manner. Based on the prediction results, the task priority is calculated, and the priority of the distribution task is dynamically adjusted in combination with timeliness, cargo type and customer demand. Through the intelligent path planning algorithm, the distribution path is optimized to ensure that high-priority tasks can be delivered quickly and preferentially. The storage location of goods in the warehouse is also intelligently adjusted according to the task priority, so that high-priority goods can be retrieved more quickly. Combined with path planning and cargo storage location, goods are quickly retrieved through automated equipment, which improves the overall distribution efficiency, realizes efficient and accurate logistics distribution, and improves response speed and resource utilization.

[0073] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for improving logistics distribution efficiency enhanced by the Internet of Things, characterized by: include, Collect multi-source logistics data and multi-dimensional logistics distribution data and perform pre-processing; Based on the pre-processed multi-dimensional logistics and distribution data, machine learning algorithms are used to predict future distribution demand and generate prediction results for distribution tasks. Based on the predicted results of the delivery tasks, calculate the priority of each delivery task; Combine the pre-processed logistics multi-source data with the delivery task priority, and use the intelligent routing algorithm to calculate the path for each delivery task priority; Adjust the storage location of goods in the warehouse according to the priority of delivery tasks; Based on the priority routes of the delivery tasks and the storage locations of the goods in the warehouse, the goods for each delivery task are quickly located and retrieved through intelligent scheduling algorithms.

2. The method for improving logistics distribution efficiency enhanced by the Internet of Things according to claim 1, characterized in that: Collecting multi-source logistics data and multi-dimensional logistics distribution data and pre-processing them includes the following steps: The multi-source logistics data includes traffic, weather, road conditions and the location of delivery vehicles, and the multi-dimensional logistics and delivery data includes collected order data, order type, customer type and cargo type; Perform data cleaning and data organization on the collected multi-source logistics data and multi-dimensional logistics distribution data.

3. The method for improving logistics distribution efficiency enhanced by the Internet of Things according to claim 2, characterized in that: Based on the pre-processed multi-dimensional logistics distribution data, the machine learning algorithm is used to predict the future distribution demand. The prediction results of the distribution task are generated in the following steps: By taking the multi-dimensional data of logistics distribution as feature input and using the gradient boosting decision tree algorithm for training, a GBDT model is constructed to predict future cargo distribution demand; The pre-processed multi-dimensional logistics distribution data is divided into a training set and a test set, and the training set is used to train the GBDT model; Input the test set into the trained GBDT model to predict the future order quantity and obtain the predicted result of the order quantity; The geographically weighted regression method is used to analyze the order demand intensity in different geographical locations. The demand is weighted according to the order type to obtain the demand distribution of order type in each region and the prediction results of the delivery task.

4. The method for improving logistics distribution efficiency enhanced by the Internet of Things according to claim 3, characterized in that: Based on the prediction results of the delivery tasks, calculating the priority of each delivery task includes the following steps: According to the delivery time requirement of each delivery task, the timeliness score of each delivery task is obtained by calculating the difference between the current time and the delivery time using the time difference calculation method; According to the cargo type of each delivery task, the priority assignment method is used to obtain the importance of the cargo type of each delivery task; Based on the customer type, we analyze the order quantity and customer category and use a weighted scoring method to obtain the priority score of each customer, the customer priority score, the importance of the cargo type and the timeliness score of the delivery task; According to the final priority score, the weight of the timeliness score, the weight of the cargo type score, and the weight of the customer type are adjusted to sort the priority score of each task and obtain the priority of each delivery task.

5. The method for improving logistics distribution efficiency enhanced by the Internet of Things according to claim 4, characterized in that: Combining the pre-processed logistics multi-source data with the delivery task priority, and using the intelligent path algorithm to calculate the path for each delivery task priority includes the following steps: According to the priority of each delivery task, a greedy algorithm is used to select the optimal path for the delivery vehicle and determine the current node and target node of the delivery vehicle; Based on the pre-processed logistics multi-source data and the optimal path of the delivery vehicle, the Bellman-Ford algorithm is used to calculate the actual distance of the shortest path from the current node of the delivery vehicle to the target node; The Euclidean distance heuristic method is used to calculate the distance from the current node of the delivery vehicle to the target node of the delivery vehicle, and the RRT path optimization algorithm is used to calculate the path of the delivery task priority.

6. The method for improving logistics distribution efficiency enhanced by the Internet of Things according to claim 5, characterized in that: According to the priority of the delivery task, adjusting the storage location of the goods in the warehouse includes the following steps: By sorting the priority scores of each task, the delivery task with the highest priority is selected, and the shortest distance matching algorithm is used to match it with the goods in the warehouse to identify the goods that need to be delivered first; Use stacker cranes to move goods to storage locations and move high-priority goods to the warehouse's exit; Use a dynamic priority adjustment algorithm to determine real-time adjustments to cargo storage; Based on the adjusted cargo location and delivery task priority, the cargo storage locations of all high-priority tasks are adjusted to the parking points close to the delivery vehicles.

7. The method for improving logistics distribution efficiency enhanced by the Internet of Things according to claim 6, characterized in that: Based on the priority path of the delivery task and the storage location of the goods in the warehouse, the intelligent scheduling algorithm is used to quickly locate and extract the goods for each delivery task. The following steps are included: Based on the adjusted cargo location and delivery task priority path, the Dijkstra algorithm is used to calculate the shortest path from the current location of the delivery vehicle to the cargo storage location; Use automated equipment to locate the warehouse cargo based on the shortest path from the delivery vehicle's current location to the cargo storage location; By locating the priority path of the delivery task and the location of the goods in the warehouse, it is found that the goods of the high-priority tasks are picked up first; The located goods in the warehouse are transported from the storage location to the designated extraction area by conveyor belts.

8. A method for improving logistics distribution efficiency enhanced by the Internet of Things, based on the method for improving logistics distribution efficiency enhanced by the Internet of Things according to any one of claims 1 to 7, characterized in that: include, Data collection module collects multi-source logistics data and multi-dimensional logistics distribution data and performs pre-processing; The prediction module uses machine learning algorithms to predict future delivery demand based on pre-processed multi-dimensional logistics and delivery data, and generates prediction results for delivery tasks; The priority module calculates the priority of each delivery task based on the predicted results of the delivery task; The delivery task module combines pre-processed logistics multi-source data with delivery task priorities and uses an intelligent routing algorithm to calculate the path for each delivery task priority; The cargo adjustment module adjusts the storage location of cargo in the warehouse according to the priority of delivery tasks; The extraction module uses an intelligent scheduling algorithm to quickly locate and extract the goods for each delivery task based on the delivery task priority path and the storage location of the goods in the warehouse.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for improving logistics distribution efficiency enhanced by the Internet of Things according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for improving logistics distribution efficiency enhanced by the Internet of Things according to any one of claims 1 to 7 are implemented.

Images