Intelligent logistics path optimization method and system
By collecting and processing environmental data in real time in the logistics route optimization system, and using deep neural networks and reinforcement learning algorithms to dynamically adjust route planning, the problems of limited computing resources and poor real-time performance in traditional logistics route planning are solved. This achieves efficient logistics route optimization, reduces costs and time, and improves the system's adaptability and robustness.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- JIANGSU NETIN TECH CO LTD
- Filing Date
- 2026-02-02
- Publication Date
- 2026-05-08
AI Technical Summary
Traditional logistics route planning faces problems such as limited computing resources, poor real-time performance, and insufficient adaptability to dynamic traffic environments. How to make full use of edge computing resources to rationally plan logistics routes remains a technical challenge that urgently needs to be solved.
By collecting environmental data in real time in the intelligent logistics route optimization system, performing data cleaning, noise reduction and normalization, building a route optimization model using deep neural networks and reinforcement learning algorithms, dynamically adjusting the route planning strategy in conjunction with edge computing nodes, and storing the route optimization results on the edge server to achieve task reuse.
It achieves maximum reduction in logistics delivery time, fuel consumption and cost, improves the real-time performance of route planning and the overall operating efficiency of the system, enhances the robustness and adaptability of the system, and adapts to the needs of different logistics scenarios and dynamic traffic environments.
Smart Images
Figure CN121998537A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of logistics optimization technology, and in particular to an intelligent logistics route optimization method and system based on edge computing. Background Technology
[0002] With the rapid development of e-commerce and modern logistics, the demand for logistics transportation has surged. However, traditional logistics route planning often faces problems such as limited computing resources, poor real-time performance, and insufficient adaptability to dynamic traffic environments. The development of edge computing technology, deploying computing power near logistics nodes, can reduce cloud computing pressure while improving the efficiency and real-time performance of logistics route optimization. However, how to fully utilize edge computing resources and rationally plan logistics routes remains a pressing technical challenge. Summary of the Invention
[0003] To address the aforementioned technical problems, this invention proposes an intelligent logistics route optimization method and system based on edge computing, which minimizes delivery time, fuel consumption, and logistics costs.
[0004] In the first embodiment of the invention, an adaptive production parameter optimization method is proposed. The method includes: real-time collection of current logistics environment data by a first intelligent sensing component installed in an intelligent logistics route optimization system; preprocessing the real-time collected environmental data by removing noise from the environmental data through data cleaning, denoising, and normalization; constructing a delivery route optimization model based on historical environmental data and a deep neural network; predicting and analyzing the preprocessed environmental data through the delivery route optimization model to predict the distribution of future route demand; and dynamically adjusting the route planning strategy based on edge computing nodes using a reinforcement learning algorithm.
[0005] Optionally, the method further includes: storing commonly used path optimization results and corresponding environmental features on an edge server, and constructing a task reuse table.
[0006] Optionally, the method further includes: continuously optimizing the delivery route optimization model based on real-time feedback data.
[0007] Optionally, the first intelligent sensing component includes multiple sensors, GPS, and edge nodes.
[0008] Optionally, the environmental data includes the geographical location information of the transportation vehicle, cargo information, traffic information, and edge server information.
[0009] Optionally, the step of removing noise from the data through data cleaning, denoising, and normalization includes: cleaning the real-time collected data to remove invalid data and outliers to obtain cleaned data; denoising the cleaned data to eliminate interference to obtain denoised data; and normalizing the denoised data to standardize the data to a preset range to obtain normalized data.
[0010] Optionally, the step of constructing a delivery route optimization model based on historical environmental data and a deep neural network, and using the delivery route optimization model to predict and analyze the preprocessed environmental data to predict the distribution of future route demand includes: collecting historical environmental data and real-time environmental data; extracting key features using a feature selection algorithm and inputting them into the delivery route optimization model; adopting an incremental learning strategy to update parameters in real time and improve prediction accuracy; and using the delivery route optimization model to predict and analyze the input historical environmental data and real-time environmental data to predict the distribution of future route demand.
[0011] A second embodiment of the present invention proposes an adaptive production parameter optimization system, the system comprising: a data acquisition module for real-time acquisition of current logistics environment data via a first intelligent sensing component installed in the system; a data processing module for preprocessing the real-time acquired environmental data by removing noise from the environmental data through data cleaning, denoising, and normalization; a path prediction module for constructing a delivery path optimization model based on historical environmental data and a deep neural network, and predicting and analyzing the preprocessed environmental data through the delivery path optimization model to predict the distribution of future path demand; and a path optimization module for dynamically adjusting path planning strategies based on edge computing nodes using reinforcement learning algorithms.
[0012] Optionally, the system further includes: a coordination and reuse module, which stores commonly used path optimization results and corresponding environmental characteristics on the edge server and constructs a task reuse table.
[0013] Optionally, the system further includes a feedback module for continuously optimizing the delivery route optimization model based on real-time feedback data.
[0014] The intelligent logistics route optimization method and system provided by this invention can fully utilize the distributed computing capabilities of edge computing to design and implement an intelligent logistics route optimization mechanism, effectively reducing the time cost and computing resource consumption of logistics delivery, while improving the real-time performance of route planning and the overall operating efficiency of the system. The method of this invention has high flexibility and adaptability, capable of adapting to the route optimization needs of different logistics scenarios and dynamic traffic environments, maximizing the reduction of delivery time, fuel consumption, and logistics costs, while enhancing the robustness and adaptability of the system. Attached Figure Description
[0015] Figure 1 This is a flowchart illustrating an embodiment of an intelligent logistics route optimization method according to the present invention.
[0016] Figure 2 This is a flowchart illustrating another embodiment of the intelligent logistics route optimization method of the present invention.
[0017] Figure 3 This is a flowchart illustrating another embodiment of the intelligent logistics route optimization method of the present invention.
[0018] Figure 4 This is a flowchart illustrating another embodiment of the intelligent logistics route optimization method of the present invention.
[0019] Figure 5 This is a schematic diagram of the structure of an intelligent logistics route optimization system according to the present invention. Detailed Implementation
[0020] The technical solutions of the embodiments of the invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the invention, and not all of them. Based on the embodiments of the invention, all other embodiments obtained by those skilled in the art without inventive effort are within the scope of protection of the invention.
[0021] Please refer to Figure 1 As shown, this invention proposes an intelligent logistics route optimization method, which includes the following steps: Step S10: Real-time data collection of the current logistics environment is performed by the first intelligent sensing component installed in the intelligent logistics route optimization system.
[0022] The first intelligent sensing component includes multiple sensors, GPS, and edge nodes. The environmental data includes weather data, road condition data, vehicle geographic location information, cargo information, traffic information, and edge server information. Specifically, weather data includes collected weather changes such as temperature, humidity, air pressure, precipitation, and wind speed; intersection data includes real-time road condition information, including traffic congestion, road construction, and traffic accidents; geographic location information includes data on the vehicle's location; and cargo information includes cargo type and its specific requirements (such as cold chain requirements and weight).
[0023] Step S20: Preprocess the real-time collected environmental data by removing noise from the environmental data through data cleaning, denoising, and normalization.
[0024] In one embodiment of the present invention, please refer to Figure 2As shown, the steps of removing noise from the data through data cleaning, denoising, and normalization include: Step S21: Perform data cleaning on the real-time collected data to remove invalid data and outliers, and obtain cleaned data; Step S22: Denoise the cleaned data to eliminate interference and obtain denoised data; Step S23: Normalize the denoised data to standardize it to a preset range and obtain normalized data.
[0025] This invention ensures the quality and consistency of the model input data by performing data cleaning, noise reduction, and normalization on the real-time collected data.
[0026] Step S30: Based on historical environmental data and a deep neural network, a delivery route optimization model is constructed. The preprocessed environmental data is then predicted and analyzed using the delivery route optimization model to predict the distribution of future route demand.
[0027] This invention utilizes environmental data, such as historical delivery data and traffic information, and employs deep learning models (such as time series prediction models based on LSTM or Transformer) to predict the distribution of future delivery route demand, serving as the initial input for route optimization.
[0028] This invention continuously trains the model using historical data, gradually improving the accuracy of parameter effect predictions. Once the model training is complete, the system predicts and analyzes the real-time collected data.
[0029] In one embodiment of the present invention, please refer to Figure 3 As shown, step S30 specifically includes the following methods: Step S31: Collect historical and real-time environmental data, and extract key features using a feature selection algorithm to input into the delivery route optimization model.
[0030] This invention collects historical and real-time environmental data, including temperature, pressure, humidity, vehicle geographic location, cargo distribution, and traffic congestion information. Key features are then selected using a feature selection algorithm (such as LASSO) and input into the delivery route optimization model.
[0031] Step S32: An incremental learning strategy is adopted to update parameters in real time and improve prediction accuracy.
[0032] CNNs are used to extract local patterns, LSTMs to capture time-series dependencies, and the output layer uses regression to predict the distribution of future delivery route demand, serving as the initial input for route optimization. The model employs an incremental learning strategy to update parameters in real time, improving prediction accuracy. Step S33: Use the delivery route optimization model to predict and analyze the input historical and real-time environmental data to predict the distribution of future route demand.
[0033] Step S40: Based on edge computing nodes, dynamically adjust the path planning strategy using a reinforcement learning algorithm.
[0034] This invention is based on edge computing nodes and employs reinforcement learning algorithms (such as DDPG or A3C) to dynamically adjust path planning strategies. Each edge node is responsible for computing tasks within its coverage area, and cross-regional collaborative optimization is achieved using a distributed computing framework.
[0035] In one embodiment of the present invention, please refer to Figure 4 As shown, the method further includes: Step S50: Store commonly used path optimization results and corresponding environmental characteristics on the edge server, and build a task reuse table.
[0036] On the edge server, frequently used path optimization results and their corresponding environmental characteristics are stored to build a task reuse table. When a new task arrives, existing results are quickly matched and reused, reducing computational resource consumption and optimization time.
[0037] Step S60: Continuously optimize the delivery route optimization model based on real-time feedback data.
[0038] During the delivery process, changes in the route environment are monitored in real time. The route planning scheme is dynamically adjusted through the rapid response of edge computing nodes, and the model is continuously optimized using feedback data.
[0039] This invention proposes an intelligent logistics route optimization method and system. This invention fully utilizes the distributed computing capabilities of edge computing to design and implement an intelligent logistics route optimization mechanism, effectively reducing the time cost and computing resource consumption of logistics delivery, while improving the real-time performance of route planning and the overall operating efficiency of the system. The method of this invention has high flexibility and adaptability, capable of adapting to the route optimization needs of different logistics scenarios and dynamic traffic environments, maximizing the reduction of delivery time, fuel consumption, and logistics costs, while enhancing the robustness and adaptability of the system.
[0040] This invention also provides an intelligent logistics route optimization system, please refer to... Figure 5As shown, the system includes a data acquisition module 100, a data processing module 200, a route prediction module 300, and a route optimization module 400. The data acquisition module 100 is used to collect current logistics environment data in real time through a first intelligent sensing component installed in the system. The data processing module 200 is used to preprocess the real-time collected environmental data by cleaning, denoising, and normalizing the environmental data to remove noise. The route prediction module 300 is used to construct a delivery route optimization model based on historical environmental data and a deep neural network. The delivery route optimization model is used to predict and analyze the preprocessed environmental data to predict the distribution of future route demand. The route optimization module 400 is used to dynamically adjust the route planning strategy based on edge computing nodes and a reinforcement learning algorithm.
[0041] The intelligent logistics route optimization system described in this invention fully utilizes the distributed computing capabilities of edge computing to design and implement an intelligent logistics route optimization mechanism. This effectively reduces the time cost and computational resource consumption of logistics delivery, while improving the real-time performance of route planning and the overall operational efficiency of the system. The method of this invention has high flexibility and adaptability, capable of adapting to the route optimization needs of different logistics scenarios and dynamic traffic environments, minimizing delivery time, fuel consumption, and logistics costs, while enhancing the robustness and adaptability of the system.
[0042] In one embodiment of the present invention, the system further includes a coordination and reuse module for storing commonly used path optimization results and corresponding environmental features on an edge server and constructing a task reuse table.
[0043] On the edge server, frequently used path optimization results and their corresponding environmental characteristics are stored to build a task reuse table. When a new task arrives, existing results are quickly matched and reused, reducing computational resource consumption and optimization time.
[0044] In one embodiment of the present invention, the system further includes a feedback module for continuously optimizing the delivery route optimization model based on real-time feedback data.
[0045] During the delivery process, changes in the route environment are monitored in real time. The route planning scheme is dynamically adjusted through the rapid response of edge computing nodes, and the model is continuously optimized using feedback data.
[0046] In the embodiments provided in this application, it should be understood that the disclosed system can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of modules described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical or other forms.
[0047] The modules described above as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0048] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.
[0049] The above embodiments are only used to illustrate the technical solutions of the invention, and are not intended to limit it. Although the invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the invention.
Claims
1. A method for optimizing intelligent logistics routes, characterized in that, The method includes: The first intelligent sensing component installed in the intelligent logistics route optimization system collects current logistics environment data in real time. The environmental data collected in real time is preprocessed by removing noise from the environmental data through data cleaning, denoising and normalization. Based on historical environmental data and a deep neural network, a delivery route optimization model is constructed. The delivery route optimization model is then used to predict and analyze the preprocessed environmental data to predict the distribution of future route demand. Based on edge computing nodes, the path planning strategy is dynamically adjusted through reinforcement learning algorithms.
2. The intelligent logistics route optimization method according to claim 1, characterized in that, The method further includes: Store commonly used path optimization results and corresponding environmental characteristics on edge servers to build a task reuse table.
3. The intelligent logistics route optimization method according to claim 1, characterized in that, The method further includes: The delivery route optimization model is continuously improved based on real-time feedback data.
4. The intelligent logistics route optimization method according to claim 1, characterized in that, The first intelligent sensing component includes multiple sensors, GPS, and edge nodes.
5. The intelligent logistics route optimization method according to claim 1, characterized in that, The environmental data includes the geographical location information of the transportation vehicle, cargo information, traffic information, and edge server information.
6. The intelligent logistics route optimization method according to claim 1, characterized in that, The steps of removing noise from the data through data cleaning, denoising, and normalization include: The real-time collected data is cleaned to remove invalid data and outliers, resulting in cleaned data. The cleaned data is then denoised to eliminate interference, resulting in denoised data. The denoised data is normalized to bring it to a preset range, resulting in normalized data.
7. The intelligent logistics route optimization method according to claim 1, characterized in that, The steps of constructing a delivery route optimization model based on historical environmental data and a deep neural network, and using the delivery route optimization model to predict and analyze the preprocessed environmental data to predict the distribution of future route demand include: Collect historical and real-time environmental data, and extract key features using a feature selection algorithm to input them into the delivery route optimization model; An incremental learning strategy is adopted to update parameters in real time, thereby improving prediction accuracy; By using a delivery route optimization model to predict and analyze historical and real-time environmental data, the distribution of future route demand can be forecasted.
8. The intelligent logistics route optimization method according to claim 1, characterized in that, The steps of constructing a delivery route optimization model based on historical environmental data and a deep neural network, and using the delivery route optimization model to predict and analyze the preprocessed environmental data to predict the distribution of future route demand include: Collect historical and real-time environmental data, and extract key features using a feature selection algorithm to input them into the delivery route optimization model; An incremental learning strategy is adopted to update parameters in real time, thereby improving prediction accuracy; By using a delivery route optimization model to predict and analyze historical and real-time environmental data, the distribution of future route demand can be forecasted.
9. The adaptive production parameter optimization system according to claim 1, characterized in that, The system also includes: The coordination and reuse module stores commonly used path optimization results and corresponding environmental characteristics on the edge server, and builds a task reuse table.
10. The adaptive production parameter optimization system according to claim 1, characterized in that, The system also includes: The feedback module is used to continuously optimize the delivery route optimization model based on real-time feedback data.