Logistics dynamic optimization method and platform based on Internet of Things
By using IoT technology to obtain real-time information for logistics capacity assessment and route optimization, the problem of low resource utilization in logistics management has been solved, achieving the optimization of logistics capacity and dynamic adjustment of routes, thereby improving delivery efficiency and resource utilization.
Patent Information
- Application Number
- CN202410927380.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-11
- Publication Date
- 2024-11-08
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Existing logistics management technologies cannot optimize the allocation of logistics capacity and dynamically adjust routes based on real-time information, resulting in low resource utilization and low delivery efficiency.
By using IoT-based logistics dynamic optimization methods and platforms, customer demand information is obtained, and intelligent route matching is performed in conjunction with the delivery route generation module. The IoT is used to obtain information on station warehousing and vehicle idle status for logistics capacity assessment. Route optimization is performed by combining route delivery time and cost, and real-time vehicle location and traffic condition information are obtained for dynamic adjustment.
It achieves optimal allocation of logistics capacity and dynamic adjustment of routes, improving resource utilization and delivery efficiency, and saving logistics costs.
Smart Images

Figure CN118917768A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of logistics management technology, and specifically to a logistics dynamic optimization method and platform based on the Internet of Things. Background Art
[0002] With the rapid development of globalization and e-commerce, the logistics industry is facing unprecedented challenges and opportunities. As an important part of supply chain management, the efficiency and effectiveness of logistics management directly affect the operation of enterprises and customer satisfaction. Traditional logistics management technologies mainly include warehousing management, transportation management and distribution management, which have indeed improved the overall level of the logistics industry in the past few decades. However, with the diversification and personalization of market demand and the rapid development of information technology, the existing logistics management technologies have gradually exposed some shortcomings.
[0003] Traditional logistics and distribution route planning mainly relies on manual experience and simple algorithms. Although it has achieved a certain degree of automation and informatization, there is still much room for improvement in intelligent and refined management. The planning of distribution routes is often limited to static geographic information, ignoring the impact of real-time traffic conditions and cargo characteristics; the scheduling of logistics resources lacks real-time data support, making it difficult to achieve the optimal configuration of logistics capacity, resulting in low resource utilization. Summary of the invention
[0004] The present application provides a logistics dynamic optimization method and platform based on the Internet of Things, which solves the technical problem that the existing technology is unable to achieve the optimal configuration of logistics capacity according to real-time information and dynamically adjust the route, resulting in low resource utilization and low distribution efficiency. It achieves the technical effect of obtaining real-time information for logistics capacity evaluation and route optimization, generating the optimal distribution route and dynamically adjusting it, improving resource utilization and distribution efficiency, and saving logistics costs.
[0005] In view of the above problems, on the one hand, the present application provides a logistics dynamic optimization method based on the Internet of Things, the method comprising: obtaining customer demand information, the customer demand information including product information and transportation demand information; based on the customer demand information, in combination with the distribution route generation module, performing intelligent route matching to obtain multiple alternative distribution routes; based on the Internet of Things, obtaining the site storage information and vehicle idle status information of multiple alternative distribution routes, performing logistics capacity evaluation, and obtaining logistics capacity evaluation results; using the logistics capacity evaluation results, combining the route distribution time and the route distribution cost to perform route optimization, and obtain the best distribution route; based on the best distribution route, performing material distribution, and during the transportation process, based on the Internet of Things technology, obtaining vehicle location information and traffic condition information in real time; performing route status evaluation through the vehicle location information and traffic condition information, and dynamically adjusting the route based on the route status evaluation results.
[0006] On the other hand, the present application also provides a logistics dynamic optimization platform based on the Internet of Things, and the platform includes: a demand information acquisition module, the customer demand information acquisition module is used to obtain customer demand information, and the customer demand information includes product information and transportation demand information; a route intelligent matching module, the route intelligent matching module is used to perform route intelligent matching based on the customer demand information, combined with the distribution route generation module, to obtain multiple alternative distribution routes; a logistics capacity evaluation module, the logistics capacity evaluation module is used to obtain the site storage information and vehicle idle status information of multiple alternative distribution routes based on the Internet of Things, perform logistics capacity evaluation, and obtain logistics capacity evaluation results; a route optimization module, the route optimization module is used to use the logistics capacity evaluation results, combine the route distribution time and the route distribution cost to perform route optimization, and obtain the best distribution route; a material distribution module, the material distribution module is used to perform material distribution based on the best distribution route, and during the transportation process, based on the Internet of Things technology, obtain vehicle location information and traffic status information in real time; a route dynamic adjustment module, the route dynamic adjustment module is used to evaluate the route status through the vehicle location information and traffic status information, and dynamically adjust the route based on the route status evaluation result.
[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:
[0008] Obtain customer demand information, which includes product information and transportation demand information. This step provides basic data for subsequent route planning and logistics capacity evaluation. According to the customer demand information, combined with the distribution route generation module, intelligent route matching is performed to obtain multiple alternative distribution routes. This step provides a selection basis for subsequent path optimization. Based on the Internet of Things, the site storage information and vehicle idle status information of multiple alternative distribution routes are obtained, and the logistics capacity evaluation is performed to obtain the logistics capacity evaluation results. This process ensures the feasibility and timeliness of the distribution route and provides key data for route optimization. Using the logistics capacity evaluation results, combined with the route distribution time and route distribution cost, the route is optimized to obtain the best distribution route. This process generates the optimal route and improves the distribution efficiency. Material distribution is carried out based on the best distribution route, and during the transportation process, the vehicle location information and traffic status information are obtained in real time based on the Internet of Things technology; the route status is evaluated through the vehicle location information and traffic status information, and the route is dynamically adjusted based on the route status evaluation results. This process collects real-time information to timely discover problems and dynamically adjust the distribution plan, thereby improving the ability to respond to emergencies.
[0009] To sum up, this application realizes the optimization and dynamic management of logistics distribution routes through intelligent data analysis and real-time monitoring, thereby improving distribution efficiency and resource utilization and saving logistics costs.
[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS
[0011] Figure 1 A flow chart of a logistics dynamic optimization method based on the Internet of Things provided in an embodiment of the present application.
[0012] Figure 2 A schematic diagram of a process for obtaining multiple alternative delivery routes in a logistics dynamic optimization method based on the Internet of Things provided in an embodiment of the present application.
[0013] Figure 3 A schematic diagram of the process of obtaining logistics capacity evaluation results in the logistics dynamic optimization method based on the Internet of Things provided in an embodiment of the present application.
[0014] Figure 4 A schematic diagram of the process of route optimization in the logistics dynamic optimization method based on the Internet of Things provided in an embodiment of the present application.
[0015] Figure 5 A schematic diagram of the structure of the logistics dynamic optimization platform based on the Internet of Things provided in an embodiment of the present application.
[0016] Explanation of the reference numerals: demand information acquisition module 10 , route intelligent matching module 20 , logistics capacity evaluation module 30 , route optimization module 40 , material distribution module 50 , route dynamic adjustment module 60 . DETAILED DESCRIPTION
[0017] The embodiments of the present application provide a logistics dynamic optimization method and platform based on the Internet of Things, thereby solving the technical problem that the prior art lacks a real-time information feedback mechanism, making it difficult to achieve optimal configuration of logistics capacity based on real-time information and to dynamically adjust routes, resulting in low resource utilization and low distribution efficiency. Logistics capacity evaluation and route optimization are performed based on real-time information, and the optimal distribution route is automatically generated and dynamically adjusted, thereby improving resource utilization and distribution efficiency and saving logistics costs.
[0018] Embodiment 1, as Figure 1 As shown, the embodiment of the present application provides a logistics dynamic optimization method based on the Internet of Things, and the method includes:
[0019] Step S1: Obtain customer demand information, which includes product information and transportation demand information.
[0020] Specifically, customer demand information refers to the specific requirements of customers for logistics services, including product information and transportation demand information. Product information refers to the detailed information of the goods that customers need to deliver, including the type, size, weight, quantity, and whether the goods are fragile or require special handling. Transportation demand information refers to the specific requirements of customers for the transportation of goods, including the expected delivery time, delivery starting and destination points, delivery frequency, transportation method preferences, and other special requirements.
[0021] Logistics companies communicate with customers through electronic order systems, online customer service platforms, telephone consultations or face-to-face meetings to collect and confirm customers' product information and transportation demand information. For example, an e-commerce customer may need to ship a batch of electronic products from a warehouse in Shanghai to a retail store in Guangzhou. He will enter the quantity of goods in the order system: 500 smartphones; size: the size of each packaging box; weight: the weight of each mobile phone plus the packaging, and the urgency of the transportation time requirement: it needs to be delivered within 48 hours. In order to ensure the accuracy and completeness of the information, logistics companies can also use special customer demand management software to record and organize this information. This type of software usually has data entry, storage, query and analysis functions, which can help logistics companies efficiently handle a large amount of customer demand information. For example, using a CRM (customer relationship management) system, the product information and transportation demand information provided by the customer are entered into the system, and the system will automatically classify and archive this information to facilitate subsequent route planning and resource scheduling.
[0022] The customer demand information obtained in step S1 will be used for subsequent logistics planning and capacity allocation to help formulate distribution plans and select the most appropriate logistics solutions.
[0023] Step S2: Based on the customer demand information, combined with the delivery route generation module, intelligent route matching is performed to obtain multiple alternative delivery routes.
[0024] Specifically, the delivery route generation module is a software tool that integrates algorithms to generate possible delivery routes based on input customer demand information, traffic conditions, storage locations, etc. Route intelligent matching refers to the use of the delivery route generation module to automatically analyze and compare various possible delivery routes and generate multiple alternative delivery routes. Alternative delivery routes are the output results of the delivery route generation module, that is, possible delivery route options that meet customer needs and logistics conditions.
[0025] First, obtain the customer demand information collected in step S1. Then, build a distribution route generation module, which usually contains a series of preset algorithms, such as the shortest path algorithm, the minimum cost flow algorithm, the genetic algorithm, etc. These algorithms can perform complex calculations and analyses based on multi-dimensional information such as geographic information, real-time traffic conditions, and historical transportation data. Then input the customer demand information into the distribution route generation module for intelligent route matching, and automatically generate multiple alternative distribution routes. Step S2 improves the efficiency of route planning through the above process, and provides scientific and accurate distribution route options for subsequent logistics capacity evaluation and route optimization.
[0026] Furthermore, if Figure 2 As shown, step S2 of the embodiment of the present application also includes:
[0027] Step S21: Obtain logistics site information, including site distribution locations and site traffic information.
[0028] Step S22: construct a delivery route generation module according to the site distribution locations and site traffic information.
[0029] Step S23: extracting the delivery starting point and the delivery destination point based on the transportation demand information of the customer demand information.
[0030] Step S24: using the delivery route generation module to perform intelligent matching of delivery routes based on the delivery starting point and the delivery target point, and generate multiple alternative delivery routes.
[0031] Specifically, logistics site information refers to the geographical location, capacity, function and traffic condition information related to each site in the logistics network, including site distribution location and site traffic information. Site distribution location describes the specific coordinates of the logistics site on the map; site traffic information includes the road conditions in and out of the site, traffic flow, whether it is prone to congestion, etc. Use map services, traffic information APIs or the internal databases of logistics companies to obtain logistics site information. For example, you can access the API of Baidu Maps or Google Maps to automatically obtain the longitude and latitude coordinates of each logistics warehouse and distribution center, and update the surrounding road conditions in real time through traffic information services.
[0032] According to the collected logistics site information, especially the site distribution location and site traffic information, select the appropriate path planning algorithm to build the distribution route generation module, such as Dijkstra algorithm, traveling salesman problem (TSP) solving algorithm, genetic algorithm, ant colony algorithm, etc. For example, choose Dijkstra algorithm to find the shortest path between two points, and combine genetic algorithm to deal with the problem of multi-point distribution, that is, to reasonably arrange the visit order of each site under the premise of ensuring the shortest total path.
[0033] The distribution starting point and distribution target point refer to the starting point and final destination of the goods distribution, respectively. Extract the transportation demand information from the customer demand information to determine the distribution starting point and distribution target point. This information directly determines the starting and ending points of the distribution route. Input the distribution starting point and distribution target point into the distribution route generation module, perform intelligent matching of distribution routes, and generate multiple alternative distribution routes.
[0034] Step S2 ensures, through the above sub-steps, that the delivery route generation module can efficiently and intelligently generate multiple alternative delivery routes based on the latest logistics site information and customer transportation needs.
[0035] Step S3: Based on the Internet of Things, the site storage information and vehicle idle status information of multiple alternative delivery routes are obtained, and the logistics capacity evaluation is performed to obtain the logistics capacity evaluation results.
[0036] Specifically, the Internet of Things refers to various physical devices connected via the Internet that can collect and exchange data. Site storage information includes warehouse inventory levels, storage space availability, cargo types and quantities, etc. Vehicle idle status information refers to the availability of vehicles in the logistics fleet, including whether they are idle, location, and expected idle time. Logistics capacity assessment is a comprehensive evaluation of the current transportation capacity and storage capacity of the logistics system to determine whether it can meet distribution needs.
[0037] Through IoT devices, such as sensors and GPS trackers, site storage information and vehicle idle status information are collected. For example, sensors in warehouses can monitor inventory levels, while GPS trackers on vehicles can provide the location and status of vehicles. Use data analysis tools and algorithms to evaluate the collected data to determine the delivery capacity of the logistics network within a specific time, including calculating available storage space, loading and unloading capacity, and the idle time and location of vehicles, etc., and output logistics capacity evaluation results, which will be used for subsequent route optimization and distribution decisions. The logistics capacity evaluation results refer to the conclusions drawn after a comprehensive analysis of the delivery capacity of the logistics network within a specific time.
[0038] Step S3 uses the Internet of Things technology to achieve real-time monitoring and management of internal resources of the logistics system, and through the evaluation of logistics capacity, ensures the effective evaluation and reasonable allocation of logistics capacity, thereby improving the efficiency and reliability of the entire distribution process.
[0039] Furthermore, step S3 of the embodiment of the present application also includes:
[0040] Step S31: extracting the corresponding logistics sites in the multiple alternative delivery routes respectively to obtain multiple site sets.
[0041] Step S32: For the multiple site sets, based on the Internet of Things technology, site information is extracted respectively to obtain site storage information and vehicle idle status information of each site, and mapped with corresponding alternative routes to obtain site storage information and vehicle idle status information of multiple alternative delivery routes.
[0042] Step S33: Based on the site storage information and vehicle idle status information of the multiple alternative delivery routes, the logistics capacity of each route is evaluated to obtain a logistics capacity evaluation result.
[0043] Specifically, logistics sites refer to individual sites on a distribution route, such as warehouses, distribution centers, or transfer stations. A site set refers to the collection of all logistics sites included in each alternative distribution route. The logistics sites involved are identified and extracted from each alternative distribution route to form multiple site sets. Each alternative distribution route corresponds to a site set. For example, if a route passes through 3 warehouses and 2 distribution centers, a site set containing these sites is created.
[0044] Mapping refers to associating site information with specific alternative routes for targeted analysis and evaluation. Use IoT technology to extract detailed information about sites within each site set. Specifically, it uses RFID technology, sensors, cameras and other equipment to collect storage information and vehicle status information for each site. For example, the storage environment of cold chain goods can be understood through temperature sensors in the warehouse, and the real-time location and status of the vehicle can be obtained through the GPS device on the vehicle. Then, the extracted site information is mapped with the corresponding alternative routes, that is, a data set containing detailed information about all sites is established for each alternative route. For example, the data set for route A may contain information such as the inventory of site 1, the vehicle availability of site 2, and the cargo processing speed of site 3. Finally, the logistics capacity of each alternative route is evaluated based on these detailed information to obtain the logistics capacity evaluation results.
[0045] Preferably, Figure 3 As shown, step S33 of the embodiment of the present application also includes:
[0046] Step S33 - 1 : Based on the multiple alternative delivery routes, select a first alternative route.
[0047] Step S33-2: construct the first alternative route and extract multiple first logistics sites.
[0048] Step S33-3: For the multiple first logistics sites, the remaining storage volume is calculated and the idle vehicles are counted respectively, and the sites are classified into levels according to the capacity evaluation standard to obtain multiple remaining storage levels and multiple vehicle capacity levels.
[0049] Step S33-4: taking the minimum value of the multiple remaining storage levels and the multiple vehicle capacity levels as the logistics capacity evaluation result of the first alternative route.
[0050] Specifically, the first alternative route refers to the route that is first selected for detailed logistics capacity evaluation among multiple alternative distribution routes. Any one of the multiple alternative distribution routes is selected as the object of the current evaluation, which is called the first alternative route. This first alternative route is constructed, and all logistics sites on the route are extracted to obtain multiple first logistics sites, where the first logistics site refers to the logistics site in the first alternative route. For example, a route from Beijing to Shanghai is selected as the first alternative route. This route may include sites such as the distribution center in Beijing, the transfer station in Jinan, and the receiving warehouse in Shanghai. These sites are all called first logistics sites.
[0051] Data is collected in real time through IoT devices, and then the remaining storage volume and idle vehicle statistics are calculated for multiple first logistics sites through data analysis software. The remaining storage volume refers to the size of the space available for new goods to be stored in the site. Idle vehicle statistics refer to the number of vehicles currently available for transportation. Then, according to the pre-set capacity evaluation standards, the remaining storage volume and vehicle capacity of each site are graded to obtain multiple remaining storage levels and multiple vehicle capacity levels. The capacity evaluation standard is a set of standards or indicator systems for evaluating the transportation capacity of logistics sites and vehicles, which are pre-customized according to actual distribution needs. For example, the remaining storage volume can be divided into three levels: high, medium, and low, and the vehicle capacity can be divided into three levels: strong, medium, and weak. The remaining storage level and vehicle capacity level are the grading results obtained after quantitative evaluation of the remaining storage volume and vehicle idle status of the site. For example, it is calculated that in the above route from Beijing to Shanghai, the remaining storage capacity of the Beijing distribution center is 1,000 cubic meters, there are 5 idle vehicles in the Jinan transfer station, and the remaining storage capacity of the Shanghai receiving warehouse is 500 cubic meters. After classification, the result is that the remaining storage level of the Beijing distribution center is high, the vehicle capacity level of the Jinan transfer station is medium, and the remaining storage level of the Shanghai receiving warehouse is low.
[0052] The obtained multiple remaining storage levels and multiple vehicle capacity levels are compared respectively, and the minimum value of the multiple remaining storage levels and multiple vehicle capacity levels is used as the logistics capacity evaluation result of the first alternative route. For example, if the storage level of the Shanghai receiving warehouse is the lowest on this route, then the logistics capacity evaluation result of the entire route is low.
[0053] Then, select another alternative delivery route from the multiple alternative delivery routes obtained in step S2 and repeat the above operation to perform logistics capacity evaluation and obtain the corresponding logistics capacity evaluation result. The above operation is repeated until the logistics capacity evaluation of each alternative delivery route is completed and multiple logistics capacity evaluation results are obtained. This provides a reference for subsequent route optimization.
[0054] Step S4: using the logistics capacity evaluation result, combining the route delivery time and route delivery cost to perform route optimization, and obtain the best delivery route.
[0055] Specifically, route delivery time refers to the estimated time from the delivery starting point to the destination, including transportation time, loading and unloading time, etc. Route delivery cost refers to the total cost of executing a specific delivery route, including transportation cost, storage cost, operating cost, etc. Route optimization refers to selecting the best delivery route among multiple alternative routes through certain algorithms and standards to achieve the shortest time, lowest cost or other established goals.
[0056] Collect and analyze the delivery time and delivery cost of each alternative delivery route. These data can be obtained through historical records, real-time monitoring systems, cost accounting systems, etc. Combined with the logistics capacity evaluation results obtained in step S3, each alternative route is comprehensively evaluated. Use route optimization algorithms, such as genetic algorithms, particle swarm optimization algorithms, simulated annealing algorithms, etc. to determine the best delivery route. These algorithms can find near-optimal solutions under complex constraints. Finally, an optimal delivery route that comprehensively considers delivery time, delivery cost, and logistics capacity evaluation results is obtained, and the subsequent actual delivery process is known to help logistics companies improve delivery efficiency and reduce delivery costs.
[0057] Furthermore, step S4 of the embodiment of the present application also includes:
[0058] Step S41: based on the product information of the customer demand information, obtain the required logistics capacity.
[0059] Step S42: screening the plurality of alternative delivery routes based on the required logistics capacity and the logistics capacity evaluation result to obtain a plurality of available delivery routes.
[0060] Specifically, the required logistics capacity refers to the logistics transportation capacity and warehousing processing capacity required to complete these orders based on the customer's order requirements. The available delivery routes are the routes that can meet customer needs after considering the actual logistics capacity and are selected from multiple alternative delivery routes.
[0061] Based on the product information of the customer demand information, the overall logistics capacity required to complete these orders is calculated. For example, if a customer needs to deliver a batch of electronic products weighing 5 tons and a volume of 20 cubic meters, the system will calculate the size and number of transport vehicles required, as well as the storage space of the warehouse based on the characteristics of these products. According to the calculated required logistics capacity, combined with the logistics capacity evaluation results obtained in the previous step S3, multiple alternative delivery routes are screened by comparing the storage capacity, transportation capacity and required logistics capacity of each station on each route. Routes that cannot meet the current delivery needs are excluded, and multiple available delivery routes are finally obtained. This process screens alternative delivery routes through in-depth analysis of customer needs and combined with the logistics capacity evaluation results to ensure that the selected routes can meet the specific needs of customers.
[0062] Furthermore, if Figure 4 As shown, step S4 of the embodiment of the present application also includes:
[0063] Step S43: Taking the route delivery time and route delivery cost as optimization parameters, a route optimization function is constructed.
[0064] Step S44: Obtaining a route optimization target based on the transportation demand information of the customer demand information.
[0065] Step S45: According to the route optimization target, the weight coefficient of the route optimization function is adjusted to obtain an updated optimization function.
[0066] Step S46: Based on the updated optimization function, route fitness is calculated for multiple available delivery routes, and the available delivery route with the largest fitness is selected as the optimal delivery route.
[0067] Specifically, optimization parameters refer to the key factors considered when optimizing routes, specifically the route delivery time and route delivery cost. The route optimization function is a mathematical model that defines how to evaluate and compare the pros and cons of different routes based on optimization parameters. The route optimization goal is the goal you want to achieve when selecting a delivery route, such as minimizing costs, maximizing customer satisfaction, etc. The weight coefficient is a numerical value used to represent the importance of each optimization parameter in the route optimization function. Route fitness is calculated by the route optimization function and reflects the quality of a route relative to the optimization goal.
[0068] First, we take the route delivery time and route delivery cost as key optimization parameters and construct a route optimization function. This function may be linear or nonlinear, depending on the specific optimization algorithm. For example, using the linear weighted sum method, the optimization function can be expressed as:
[0069] F (x) =ω1 T+ω 2 T
[0070] Among them, T represents the delivery time, C represents the delivery cost, ω 1 is the weight coefficient corresponding to the delivery time and ω 2 It is the weight coefficient corresponding to the delivery cost.
[0071] According to the transportation demand information of customer demand information, the goal of route optimization is determined, including minimizing delivery costs and meeting customer time requirements to the greatest extent. According to the determined optimization goal, the weight coefficient of the route optimization function is adjusted. For example, if the customer requires delivery to be completed in the shortest time, the weight of the delivery time is increased, that is, ω is increased. 1 , when the customer requires delivery at the lowest cost, the weight of the delivery cost is increased, that is, ω 2 . The weights can be determined by common methods such as subjective weighting method, analytic hierarchy process (AHP), and entropy method. For example, the weights can be initially determined by subjective weighting method, then verified and corrected by analytic hierarchy process, and finally objectively verified by entropy method. Based on the updated optimization function, the fitness of multiple available delivery routes is calculated. The route with the largest fitness is selected as the best delivery route. This route will be the choice that best meets the optimization goal.
[0072] Step S4 constructs and adjusts the route optimization function, calculates the route fitness, and selects the route with the highest fitness as the optimal delivery route, ensuring that the logistics distribution plan can meet the customer's transportation needs to the greatest extent.
[0073] Step S5: Distribute materials based on the optimal distribution route, and obtain vehicle location information and traffic status information in real time based on the Internet of Things technology during transportation.
[0074] Specifically, vehicle location information refers to the exact geographic location of a logistics transport vehicle at a certain moment, which is usually obtained through the Global Positioning System (GPS) or other vehicle-mounted positioning devices. Traffic condition information refers to real-time road traffic conditions, including congestion levels, accidents, construction areas, weather conditions, etc. This information can be collected through various channels such as traffic monitoring systems, social media, and traffic broadcasts.
[0075] According to the best delivery route determined in step S4, the goods are delivered, including loading the goods from the starting warehouse, transporting them according to the predetermined route, and unloading them when they reach the destination. During the entire transportation process, the location information and traffic condition information of the vehicle are monitored and obtained in real time using the Internet of Things technology. This includes but is not limited to real-time monitoring of the location and movement status of the vehicle through the GPS tracker installed on the vehicle; using the traffic information API or real-time monitoring system to obtain the traffic conditions during the vehicle's travel, such as congestion, road construction, etc. The real-time vehicle location and traffic condition information is fed back to the logistics management system for dynamic monitoring and adjustment.
[0076] Step S5 uses the Internet of Things technology to monitor the entire material distribution process in real time, so as to respond to emergencies in a timely manner and improve the efficiency and safety of material distribution.
[0077] Step S6: Evaluate the route status using the vehicle location information and traffic condition information, and dynamically adjust the route based on the route status evaluation result.
[0078] Specifically, route status evaluation refers to evaluating the feasibility and efficiency of the current delivery route based on vehicle location information and traffic condition information. Route dynamic adjustment refers to making immediate modifications to the original delivery route based on the evaluation results to avoid unfavorable factors and improve delivery efficiency. The vehicle location information and traffic condition information obtained in real time in step S5 are analyzed to evaluate the congestion level, estimated arrival time, safety risks, etc. of the current delivery route. Based on the evaluation results, the dynamic adjustment of the route is automatically performed, including selecting an alternative route, adjusting the vehicle speed, and rearranging the delivery order.
[0079] Step S6 can respond to changes in road conditions in real time through route status evaluation, optimize delivery routes, reduce delays, improve delivery efficiency, and ensure that goods are delivered safely and on time.
[0080] Furthermore, step S6 of the embodiment of the present application also includes:
[0081] Step S61: training a traffic prediction model based on the historical traffic condition information of the route.
[0082] Step S62: performing route status evaluation based on the traffic prediction model in combination with the vehicle location information and vehicle travel speed, and obtaining a route status evaluation result.
[0083] Step S63: Dynamically adjust the route based on the route status evaluation result.
[0084] Specifically, route historical traffic condition information refers to data such as traffic flow, congestion, and accident records on a specific route over a period of time in the past. A traffic prediction model is an algorithmic model that uses historical data to predict future traffic conditions. It can be a simple statistical model or a complex machine learning model, such as time series analysis, regression analysis, and neural networks. Vehicle speed refers to the real-time speed of a vehicle while it is traveling, which is usually obtained through an on-board GPS device or the vehicle's own speed sensor.
[0085] Use machine learning frameworks such as TensorFlow and Scikit-learn to build an initial machine learning model, collect and analyze a large amount of historical route traffic status information, and use this as a basis for training a traffic prediction model. This model will learn the patterns and trends in historical data and be able to predict future traffic conditions. Input real-time vehicle location information and vehicle driving speed into the trained traffic prediction model, evaluate the current route status, and obtain route evaluation results. Then, based on the results of the route status evaluation, propose and implement strategies for dynamic route adjustment, including changing the driving route, adjusting the driving speed, and advancing or delaying the departure time.
[0086] The above steps use historical data to train the traffic prediction model, combine it with real-time vehicle information to evaluate the route status, and dynamically adjust the route accordingly to improve the efficiency and reliability of logistics distribution.
[0087] In summary, the logistics dynamic optimization method based on the Internet of Things provided in the embodiments of the present application has the following technical effects:
[0088] Obtain customer demand information, which includes product information and transportation demand information. This step provides basic data for subsequent route planning and logistics capacity evaluation. Obtain logistics site information, build a distribution route generation module, and use the distribution route generation module to perform intelligent route matching based on the transportation demand information of customer demand information to generate multiple alternative distribution routes. This step provides a selection basis for subsequent path optimization. Based on the Internet of Things, obtain site storage information and vehicle idle status information of multiple alternative distribution routes, perform logistics capacity evaluation, and obtain logistics capacity evaluation results. This process ensures the feasibility and timeliness of the distribution route and provides key data for route optimization. Using the logistics capacity evaluation results, combined with the route distribution time and route distribution cost, as well as the transportation demand information of the customer demand information, construct and update the route optimization function, perform route optimization, and obtain the best distribution route. This process generates the optimal route that can meet the customer's transportation needs to the greatest extent, thereby improving distribution efficiency. Material distribution is carried out based on the optimal distribution route, and during the transportation process, vehicle location information and traffic condition information are obtained in real time based on the Internet of Things technology; a traffic prediction model is trained, and a route status evaluation is performed based on the traffic prediction model in combination with vehicle location information and vehicle driving speed, and a route status evaluation result is obtained, and the route is dynamically adjusted based on the route status evaluation result. This process improves the ability to respond to emergencies by collecting real-time information to timely discover problems and dynamically adjust distribution plans.
[0089] As described above, the embodiments of the present application deeply mine customer demand information, construct a distribution route generation module, a route optimization function, and a training traffic prediction model to realize intelligent data analysis, automatically generate a scientific and reliable optimal distribution route, and combine the Internet of Things technology to monitor the distribution process in real time, and dynamically adjust the distribution route according to real-time vehicle information and traffic conditions information, thereby improving the distribution efficiency and resource utilization of the logistics distribution process and saving logistics costs.
[0090] Embodiment 2, as Figure 5 As shown, the embodiment of the present application provides a logistics dynamic optimization platform based on the Internet of Things, and the platform includes:
[0091] The demand information acquisition module 10 is used to acquire customer demand information, and the customer demand information includes product information and transportation demand information.
[0092] The route intelligent matching module 20 is used to perform route intelligent matching based on the customer demand information in combination with the delivery route generation module to obtain multiple alternative delivery routes.
[0093] The logistics capacity evaluation module 30 is used to obtain the site storage information and vehicle idle status information of multiple alternative delivery routes based on the Internet of Things, perform logistics capacity evaluation, and obtain logistics capacity evaluation results.
[0094] The route optimization module 40 is used to use the logistics capacity evaluation result, combine the route delivery time and the route delivery cost to perform route optimization, and obtain the best delivery route.
[0095] The material distribution module 50 is used to distribute materials based on the optimal distribution route, and during the transportation process, based on the Internet of Things technology, to obtain vehicle location information and traffic status information in real time.
[0096] The route dynamic adjustment module 60 is used to evaluate the route status through the vehicle position information and traffic condition information, and to dynamically adjust the route based on the route status evaluation result.
[0097] Furthermore, the route intelligent matching module 20 of the embodiment of the present application is also used to perform the following steps:
[0098] Obtain logistics site information, including site distribution location and site traffic information.
[0099] A delivery route generation module is constructed based on the site distribution locations and site traffic information.
[0100] Based on the transportation demand information of the customer demand information, the delivery starting point and the delivery destination point are extracted.
[0101] The delivery route generation module is used to perform intelligent matching of delivery routes based on the delivery starting point and delivery target point to generate multiple alternative delivery routes.
[0102] Furthermore, the logistics capacity evaluation module 30 of the embodiment of the present application is also used to perform the following steps:
[0103] The corresponding logistics sites in the multiple alternative delivery routes are extracted respectively to obtain multiple site sets.
[0104] For the multiple site sets, based on the Internet of Things technology, site information is extracted respectively to obtain site storage information and vehicle idle status information of each site, and mapped with corresponding alternative routes to obtain site storage information and vehicle idle status information of multiple alternative delivery routes.
[0105] Based on the site storage information and vehicle idle status information of the multiple alternative delivery routes, a logistics capacity evaluation is performed on each route to obtain a logistics capacity evaluation result.
[0106] Preferably, the logistics capacity evaluation module 30 of the embodiment of the present application is also used to perform the following steps:
[0107] Based on the plurality of alternative delivery routes, a first alternative route is selected.
[0108] Construct the first alternative route and extract multiple first logistics sites.
[0109] For the multiple first logistics sites, remaining storage volume calculation and idle vehicle statistics are performed respectively, and levels are divided according to the capacity evaluation standard to obtain multiple remaining storage levels and multiple vehicle capacity levels.
[0110] The minimum value of the multiple remaining storage levels and the multiple vehicle capacity levels is used as the logistics capacity evaluation result of the first alternative route.
[0111] Furthermore, the route optimization module 40 of the embodiment of the present application is also used to perform the following steps:
[0112] Based on the product information of the customer demand information, the required logistics capacity is obtained.
[0113] The plurality of alternative delivery routes are screened according to the required logistics capacity and in combination with the logistics capacity evaluation result to obtain a plurality of available delivery routes.
[0114] Furthermore, the route optimization module 40 of the embodiment of the present application is also used to perform the following steps:
[0115] The route delivery time and route delivery cost are used as optimization parameters to construct a route optimization function.
[0116] Based on the transportation demand information of the customer demand information, a route optimization target is obtained.
[0117] According to the route optimization objective, the weight coefficient of the route optimization function is adjusted to obtain an updated optimization function.
[0118] Based on the updated optimization function, route fitness is calculated for multiple available delivery routes, and the available delivery route with the largest fitness is selected as the optimal delivery route.
[0119] Furthermore, the route dynamic adjustment module 60 of the embodiment of the present application is also used to perform the following steps:
[0120] Train the traffic prediction model based on the historical traffic condition information of the route.
[0121] According to the traffic prediction model, combined with the vehicle position information and the vehicle driving speed, a route status assessment is performed to obtain a route status assessment result.
[0122] The route is dynamically adjusted based on the route status evaluation results.
[0123] Through the above detailed description of the logistics dynamic optimization method based on the Internet of Things in this specification, those skilled in the art can clearly understand the logistics dynamic optimization platform based on the Internet of Things in this embodiment. For the platform disclosed in Example 2, since it corresponds to the method disclosed in Example 1, it has corresponding functional modules and beneficial effects. For relevant details, please refer to the method part description.
[0124] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A logistics dynamic optimization method based on the Internet of Things, characterized in that: The method comprises: Acquiring customer demand information, wherein the customer demand information includes product information and transportation demand information; According to the customer demand information, combined with the delivery route generation module, intelligent route matching is performed to obtain multiple alternative delivery routes; Based on the Internet of Things, the site storage information and vehicle idle status information of multiple alternative delivery routes are obtained to evaluate the logistics capacity and obtain the logistics capacity evaluation results; Using the logistics capacity evaluation results, combined with the route delivery time and route delivery cost, route optimization is performed to obtain the best delivery route; Distribute materials based on the optimal distribution route, and obtain vehicle location information and traffic condition information in real time based on the Internet of Things technology during transportation; The route status is evaluated through the vehicle position information and traffic condition information, and the route is dynamically adjusted based on the route status evaluation result.
2. The method for dynamic optimization of logistics based on the Internet of Things according to claim 1, wherein, according to the customer demand information, a distribution route generation module is combined to perform intelligent route matching to obtain multiple alternative distribution routes, including: Obtain logistics site information, including site distribution location and site traffic information; Constructing a delivery route generation module according to the site distribution locations and site traffic information; Extracting the delivery starting point and the delivery destination point based on the transportation demand information of the customer demand information; The delivery route generation module is used to perform intelligent matching of delivery routes based on the delivery starting point and delivery target point to generate multiple alternative delivery routes.
3. The method for dynamic optimization of logistics based on the Internet of Things as claimed in claim 1, based on the Internet of Things, obtains the site storage information and vehicle idle status information of multiple alternative delivery routes, performs logistics capacity evaluation, and obtains logistics capacity evaluation results, including: Respectively extracting corresponding logistics sites in the plurality of alternative delivery routes to obtain a plurality of site sets; For the multiple site sets, based on the Internet of Things technology, site information is extracted respectively to obtain site storage information and vehicle idle status information of each site, and mapped with corresponding alternative routes to obtain site storage information and vehicle idle status information of multiple alternative delivery routes; Based on the site storage information and vehicle idle status information of the multiple alternative delivery routes, a logistics capacity evaluation is performed on each route to obtain a logistics capacity evaluation result.
4. The method for dynamic optimization of logistics based on the Internet of Things as claimed in claim 3, characterized in that: Based on the site storage information and vehicle idle status information of the multiple alternative delivery routes, the logistics capacity of each route is evaluated respectively to obtain the logistics capacity evaluation results, including: Based on the multiple alternative delivery routes, selecting a first alternative route; Constructing the first alternative route and extracting a plurality of first logistics sites; For the multiple first logistics sites, respectively, remaining storage volume calculation and idle vehicle statistics are performed, and levels are divided according to the transportation capacity evaluation standard to obtain multiple remaining storage levels and multiple vehicle transportation capacity levels; The minimum value of the multiple remaining storage levels and the multiple vehicle capacity levels is used as the logistics capacity evaluation result of the first alternative route.
5. The method for dynamic optimization of logistics based on the Internet of Things as claimed in claim 1, characterized in that: The logistics capacity evaluation results are used to optimize the route by combining the route delivery time and route delivery cost to obtain the best delivery route, including: Based on the product information of the customer demand information, obtain the required logistics capacity; The plurality of alternative delivery routes are screened according to the required logistics capacity and in combination with the logistics capacity evaluation result to obtain a plurality of available delivery routes.
6. The method for dynamic optimization of logistics based on the Internet of Things as claimed in claim 5, characterized in that: The logistics capacity evaluation results are used to optimize the route by combining the route delivery time and route delivery cost to obtain the best delivery route, including: Taking the route delivery time and route delivery cost as optimization parameters, constructing a route optimization function; Based on the transportation demand information of the customer demand information, obtaining a route optimization target; According to the route optimization objective, adjusting the weight coefficient of the route optimization function to obtain an updated optimization function; Based on the updated optimization function, route fitness is calculated for multiple available delivery routes, and the available delivery route with the largest fitness is selected as the optimal delivery route.
7. The method for dynamic optimization of logistics based on the Internet of Things as claimed in claim 1, characterized in that: The route status is evaluated by using the vehicle position information and traffic condition information, and the route is dynamically adjusted based on the route status evaluation result, including: Train traffic prediction models based on historical route traffic information; According to the traffic prediction model, combined with the vehicle location information and the vehicle driving speed, a route status assessment is performed to obtain a route status assessment result; The route is dynamically adjusted based on the route status evaluation results.
8. The logistics dynamic optimization platform based on the Internet of Things is characterized by: The platform includes: A demand information acquisition module, wherein the customer demand information acquisition module is used to acquire customer demand information, wherein the customer demand information includes product information and transportation demand information; A route intelligent matching module, which is used to perform route intelligent matching based on the customer demand information and in combination with the delivery route generation module to obtain multiple alternative delivery routes; A logistics capacity evaluation module, which is used to obtain the site storage information and vehicle idle status information of multiple alternative delivery routes based on the Internet of Things, conduct logistics capacity evaluation, and obtain logistics capacity evaluation results; A route optimization module, which is used to optimize the route by using the logistics capacity evaluation result, combining the route delivery time and the route delivery cost, to obtain the best delivery route; A material distribution module, which is used to distribute materials based on the optimal distribution route and obtain vehicle location information and traffic status information in real time during transportation based on the Internet of Things technology; A route dynamic adjustment module is used to evaluate the route status through the vehicle position information and traffic condition information, and to dynamically adjust the route based on the route status evaluation result.
Citation Information
Cited By
Fruit and vegetable logistics supply chain management system based on aging analysis
CN119809486A
Logistics transportation whole course visualization system and method
CN119809496A
Logistics supply digital management system and method based on cloud platform
CN119850071A
Logistics distribution management method and device, equipment and medium
CN119887027A
