Logistics planning and management system based on the Internet of Things

Through the logistics planning and management system based on the Internet of Things, real-time monitoring and dynamic optimization of the logistics network, the problems of low efficiency and low reliability in traditional systems in dealing with emergencies are solved, and the efficiency and reliability of logistics and transportation management are improved.

CN118569446BActive Publication Date: 2024-11-26JIANGSU JD-LINK INT LOGISTICS CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411037142.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-31
Publication Date
2024-11-26
Estimated Expiration
2044-07-31

AI Technical Summary

Technical Problem

Traditional logistics planning and management systems are inefficient and reliable in dealing with emergencies, making it difficult to quickly respond to uncertain factors such as traffic congestion and weather changes, resulting in insufficient efficiency and reliability of logistics and transportation management.

Method used

Adopting a logistics planning and management system based on the Internet of Things, the logistics and transportation network acquisition module, sub-network establishment module, transportation resource acquisition module, disturbance anti-enablement prediction module and transportation network optimization module are used to monitor and dynamically optimize the logistics network to generate transportation network optimization The plan is to improve the efficiency and reliability of logistics planning management.

Benefits of technology

Real-time response and dynamic optimization of emergencies are achieved, the efficiency and reliability of logistics planning and management are improved, and the logistics system can operate efficiently when facing uncertain factors.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118569446B_ABST
    Figure CN118569446B_ABST
Patent Text Reader

Abstract

The present invention discloses a logistics planning and management system based on the Internet of Things, which relates to the field of logistics management technology, including: obtaining the logistics transportation network of a first enterprise; establishing a first transportation sub-network between a first logistics node and a second logistics node according to the logistics transportation network and transportation attribute tags; collecting transportation resources for the first logistics node through an Internet of Things monitoring platform, and generating first reserve transportation resource information; establishing an anti-disturbance prediction auxiliary factor, combining the first reserve transportation resource information to predict the anti-disturbance capability, and generating a first anti-disturbance performance index; if the first anti-disturbance performance index is less than a preset anti-disturbance index, optimizing the transportation network, generating a first transportation network optimization plan, and performing logistics planning and management on the first transportation sub-network. The present invention solves the technical problems of low efficiency and low reliability of logistics planning and management in the prior art, and achieves the technical effect of improving the efficiency and reliability of logistics planning and management.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of logistics management, and in particular to a logistics planning and management system based on the Internet of Things. Background Art

[0002] With the rapid development of globalization and information technology, the logistics industry has become an important engine for economic growth. In particular, with the rise of e-commerce and the diversification of consumer demand, the logistics industry faces unprecedented challenges and opportunities. However, with the continuous expansion of logistics networks and the increasing complexity of logistics activities, traditional logistics planning and management systems have gradually revealed their limitations, especially in responding to emergencies, improving transportation efficiency and optimizing resource allocation.

[0003] Traditional logistics planning and management systems often rely on manual operations and offline data, which leads to delayed information updates and untimely decision-making. In the process of logistics transportation, various uncertainties such as traffic congestion, weather changes, equipment failures, etc. may have a serious impact on logistics transportation, and traditional logistics management systems often find it difficult to respond to these changes quickly, resulting in low efficiency and low reliability of logistics planning and management. Summary of the invention

[0004] The present application provides a logistics planning and management system based on the Internet of Things, which is used to solve the technical problems of low efficiency and low reliability of logistics planning and management, which are difficult to solve by existing technologies in logistics transportation due to unexpected factors.

[0005] In view of the above problems, this application provides a logistics planning and management system based on the Internet of Things.

[0006] The present application provides a logistics planning and management system based on the Internet of Things, the system comprising:

[0007] A logistics and transportation network acquisition module is used to acquire the logistics and transportation network of the first enterprise, wherein the logistics and transportation network includes multiple logistics nodes, and any logistics node has a transportation attribute mark; a sub-network establishment module is used to establish a first transportation sub-network between the first logistics node and the second logistics node according to the logistics and transportation network and the transportation attribute mark, wherein the first transportation sub-network includes multiple transportation routes and multiple transportation attributes; a transportation resource collection module is used to collect transportation resources for the first logistics node through the Internet of Things monitoring platform to generate first reserve transportation resource information; an anti-disturbance capability prediction module is used to use the Internet of Things monitoring platform to establish an anti-disturbance prediction auxiliary factor, and predict the anti-disturbance capability of the first transportation sub-network in combination with the first reserve transportation resource information to generate a first anti-disturbance performance index; a transportation network optimization module is used to optimize the first transportation sub-network if the first anti-disturbance performance index is less than a preset anti-disturbance index, and generate a first transportation network optimization plan; a logistics planning and management module is used to perform logistics planning and management on the first transportation sub-network based on the first transportation network optimization plan.

[0008] The technical solution provided in this application has at least the following technical effects or advantages:

[0009] The present application obtains the logistics and transportation network of the first enterprise, wherein the logistics and transportation network includes multiple logistics nodes, and any logistics node has a transportation attribute mark; according to the logistics and transportation network and the transportation attribute mark, a first transportation sub-network between the first logistics node and the second logistics node is established, wherein the first transportation sub-network includes multiple transportation paths and multiple transportation attributes; the transportation resources of the first logistics node are collected through the Internet of Things monitoring platform to generate the first reserve transportation resource information; the anti-disturbance prediction auxiliary factor is established by using the Internet of Things monitoring platform, and the anti-disturbance ability of the first transportation sub-network is predicted in combination with the first reserve transportation resource information to generate the first anti-disturbance performance index; if the first anti-disturbance performance index is less than the preset anti-disturbance index, the transportation network of the first transportation sub-network is optimized to generate the first transportation network optimization plan; based on the first transportation network optimization plan, the logistics planning and management of the first transportation sub-network is performed. The present invention solves the technical problems that the prior art is difficult to solve the impact of sudden factors on logistics and transportation, and there is low efficiency and low reliability of logistics planning and management. Through the functions of real-time monitoring, dynamic optimization, intelligent prediction and decision support, the technical effect of improving the efficiency and reliability of logistics planning and management is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in 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 creative work.

[0011] Figure 1 A schematic diagram of the structure of a logistics planning and management system based on the Internet of Things provided in an embodiment of the present application;

[0012] Figure 2 A flow chart of a logistics planning and management method based on the Internet of Things provided in an embodiment of the present application.

[0013] Explanation of the accompanying drawings: logistics and transportation network acquisition module 11, sub-network establishment module 12, transportation resource acquisition module 13, anti-disturbance capability prediction module 14, transportation network optimization module 15, logistics planning and management module 16. DETAILED DESCRIPTION

[0014] This application provides a logistics planning and management system based on the Internet of Things, aiming to solve the technical problems that the existing technology is difficult to solve the impact of sudden factors on logistics and transportation, and the low efficiency and reliability of logistics planning and management. Through real-time monitoring, dynamic optimization, intelligent prediction and decision support and other functions, the technical effect of improving the efficiency and reliability of logistics planning and management is achieved.

[0015] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0016] It should be noted that any variations of the terms "include" and "have" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or inherent to these processes, methods, products or devices.

[0017] Embodiment 1

[0018] like Figure 1 As shown, this application provides a logistics planning and management system based on the Internet of Things, which is used to perform the following Figure 2 The logistics planning and management method based on the Internet of Things shown in the figure comprises:

[0019] The logistics and transportation network acquisition module 11 is used to acquire the logistics and transportation network of the first enterprise, wherein the logistics and transportation network includes a plurality of logistics nodes, and any logistics node has a transportation attribute mark.

[0020] In the embodiment of the present application, the logistics and transportation network acquisition module accesses the internal database of the first enterprise to retrieve relevant data of the logistics and transportation network, which includes information such as the location and type of the logistics nodes.

[0021] The logistics and transportation network includes multiple logistics nodes, each of which has its own unique identification and detailed information within the acquisition range of the logistics and transportation network acquisition module. This information includes but is not limited to the node's geographical location, processing capacity, storage capacity, etc. At the same time, each logistics node is marked with a transportation attribute, which describes the node's transportation method, such as road, shipping, etc.

[0022] Finally, the logistics and transportation network acquisition module integrates the data obtained from the internal database of the first enterprise to form the logistics and transportation network of the first enterprise.

[0023] The sub-network establishing module 12 is used to establish a first transportation sub-network between the first logistics node and the second logistics node according to the logistics transportation network and the transportation attribute mark, wherein the first transportation sub-network includes multiple transportation routes and multiple transportation attributes.

[0024] In an embodiment of the present application, the sub-network establishment module receives the logistics and transportation network provided by the logistics and transportation network acquisition module, and the logistics and transportation network includes information such as the location, type, and function of multiple logistics nodes.

[0025] When establishing the first transport sub-network, the user first determines the first logistics node and the second logistics node. Then, the sub-network establishment module obtains the transport path between the first logistics node and the second logistics node from the logistics transport network according to the determined first logistics node and the second logistics node, and determines the transport attributes of each node according to the logistics nodes passed in the transport path. Finally, the obtained transport path and transport attributes are integrated to complete the establishment of the first transport sub-network.

[0026] The transportation resource collection module 13 is used to collect transportation resources for the first logistics node through the Internet of Things monitoring platform to generate first reserve transportation resource information.

[0027] In the embodiment of the present application, the Internet of Things monitoring platform integrates multiple sensors, RFID devices, GPS, etc. to collect various types of information of logistics nodes in real time.

[0028] The transportation resource collection module collects the transportation resource information of the first logistics node in real time through the Internet of Things monitoring platform, including but not limited to vehicle information, cargo information, warehousing information, etc.

[0029] Vehicle information includes vehicle quantity, type, location, etc. Cargo information includes cargo type, quantity, location, etc. Warehouse information includes warehouse capacity, etc.

[0030] Finally, the collected information is processed through data cleaning and format conversion to generate the first reserve transportation resource information.

[0031] The anti-disturbance capability prediction module 14 is used to use the Internet of Things monitoring platform to establish an anti-disturbance prediction auxiliary factor, combine the first reserve transportation resource information to predict the anti-disturbance capability of the first transportation sub-network, and generate a first anti-disturbance performance indicator.

[0032] In the embodiment of the present application, the anti-disturbance capability prediction module obtains various data from the IoT monitoring platform, including historical transportation records, road condition data, weather data, etc. Historical transportation records include transportation routes, time, cargo types, etc. Road condition data include traffic conditions, road closure information, etc. Weather data include temperature, rainfall, wind speed, etc.

[0033] Key factors affecting the stability of the logistics network are extracted from the collected data, such as weather severity, traffic congestion index, equipment failure rate, etc. These factors are quantified into specific anti-disturbance prediction auxiliary factors. For example, weather severity is represented by quantitative indicators such as rainfall and wind force level, and traffic congestion index is represented by indicators such as real-time traffic flow and average vehicle speed.

[0034] Combine the anti-disturbance prediction auxiliary factors with the first reserve transportation resource information, such as the number, type, type and quantity of vehicles, for a comprehensive evaluation. The anti-disturbance capability prediction module has a series of preset rules and thresholds built in to evaluate the impact of different anti-disturbance prediction auxiliary factors on the anti-disturbance capability of the logistics network. For example, when the severity of the weather exceeds a certain threshold, the transportation efficiency will drop significantly; when the traffic congestion index exceeds a certain threshold, the transportation time will increase significantly. By analyzing these rules and thresholds, combined with the first reserve transportation resource information, the anti-disturbance capability of the first transportation subnetwork under different disturbance conditions is predicted. Based on the prediction results, specific first anti-disturbance performance indicators are generated, such as disturbance recovery time, degree of decline in transportation efficiency, resource allocation efficiency, etc.

[0035] The transportation network optimization module 15 is used to optimize the first transportation subnetwork and generate a first transportation network optimization plan if the first anti-disturbance performance index is less than a preset anti-disturbance index.

[0036] In the embodiment of the present application, when the first anti-disturbance performance index is less than the preset anti-disturbance index, the first transport sub-network is optimized for transport network optimization. The preset anti-disturbance index is a standard value set by the logistics enterprise according to actual needs, which is used to determine whether the anti-disturbance capability of the current logistics network reaches the expected level.

[0037] When optimizing the transportation network, data mining tools and statistical analysis software are used to identify key issues where the first anti-disturbance performance index is less than the preset anti-disturbance index, such as congested transportation paths and low utilization of transportation tools. Based on the identified issues, the first transportation subnetwork is optimized through path optimization algorithms, such as Dijkstra algorithm and A* algorithm. Linear programming models such as IBM ILOG CPLEX and Gurobi are used to optimize the scheduling of transportation tools and resources, ensure reasonable allocation of resources, and minimize transportation costs and time.

[0038] Specifically, when obtaining real-time data from the IoT monitoring platform and finding that the anti-interference performance index of a transportation subnetwork is lower than the preset index, using data mining tools to analyze the data, it is found that the main problem is that a certain transportation route is often congested. The shortest path algorithm is used to replan the transportation route and select an alternative route with less congestion.

[0039] Real-time data was obtained from the IoT monitoring platform, and it was found that the anti-interference performance index of a certain transport sub-network was lower than the preset value. Using data analysis tools to analyze the data, it was found that the main problem was the unreasonable scheduling of transport vehicles, resulting in low utilization of some vehicles. Linear programming was used to optimize vehicle scheduling and balance vehicle utilization.

[0040] Through the above process, the first transportation network optimization plan is generated.

[0041] The logistics planning management module 16 is used to perform logistics planning management on the first transportation sub-network based on the first transportation network optimization solution.

[0042] In the embodiment of the present application, the logistics planning management module performs logistics planning management on the first transportation subnetwork according to the generated first transportation network optimization plan. The first transportation network optimization plan includes a re-planned transportation route, an optimized resource scheduling plan, and the like.

[0043] Logistics management is carried out according to the re-planned transportation routes and optimized resource scheduling plans to ensure the efficient operation of the logistics system and the improvement of its anti-disturbance capabilities.

[0044] Furthermore, the anti-disturbance capability prediction module 14 in the system provided in the embodiment of the application is also used for:

[0045] The Internet of Things monitoring platform is used to obtain a sample data set of historical transportation records of the first transportation subnetwork, wherein any piece of historical transportation record sample data includes a transportation route road condition record, a transportation weather record, and a transportation cargo scale record; based on the historical transportation record sample data set, a variation analysis of the transportation route road condition, transportation weather, and transportation cargo scale is performed, and a road condition variation index, a weather variation index, and a cargo scale variation index are output; the anti-disturbance prediction auxiliary factor is generated using the road condition variation index, the weather variation index, and the cargo scale variation index.

[0046] In the embodiment of the present application, a historical transport record sample data set of the first transport subnetwork is extracted from the historical monitoring data of the Internet of Things monitoring platform. The historical transport record sample data set includes transport path road condition records, transport weather records, and transport goods scale records.

[0047] Next, extract the road condition records of all transportation routes from the historical transportation record sample data set. Select key road condition indicators such as congestion index and average travel time. Calculate the standard deviation and mean of each road condition indicator. Use the coefficient of variation formula to obtain the road condition variation index by dividing the standard deviation of the road condition indicator by the mean. For example, assuming that the mean value of the congestion index is 5 and the standard deviation is 1.5, the coefficient of variation is 30%.

[0048] Extract weather records for all transportation periods from the historical transportation record sample data set, such as temperature, precipitation, etc. Calculate the standard deviation and mean value for each weather indicator. Also use the coefficient of variation formula to calculate the weather variation index. For example, assuming that the average temperature is 20°C and the standard deviation is 5°C, the coefficient of variation is 25%.

[0049] Extract the cargo size records of all transport tasks, such as weight, volume, etc., from the historical transport record sample data set. Calculate the standard deviation and mean value for each cargo size indicator. Use the coefficient of variation formula to calculate the cargo size variation indicator. For example, assuming that the average value of cargo weight is 100 kg and the standard deviation is 20 kg, the coefficient of variation is 20%.

[0050] According to the actual situation, technical experts set different weights for the road condition variation index, weather variation index and cargo scale variation index. For example, the weight of the road condition variation index is 0.4, the weight of the weather variation index is 0.3, and the weight of the cargo scale variation index is 0.3.

[0051] Using the weighted average method, the three variation indicators are weighted and summed according to their weights to obtain the value of the anti-disturbance prediction auxiliary factor. The calculation formula is:

[0052] Anti-disturbance prediction auxiliary factor = (road condition variation index × road condition weight) + (weather variation index × weather weight) + (cargo scale variation index × cargo scale weight).

[0053] For example, assuming that the road condition variation index is 30%, the weather variation index is 25%, and the cargo size variation index is 20%, the anti-disturbance prediction auxiliary factor = (30% × 0.4) + (25% × 0.3) + (20% × 0.3) = 12% + 7.5% + 6% = 25.5%.

[0054] Furthermore, the anti-disturbance capability prediction module 14 is also used for:

[0055] Set a road condition disturbance step size constraint, a weather disturbance step size constraint and a scale disturbance step size constraint; perform disturbance identification on the road condition record of the transport path according to the road condition disturbance step size constraint to generate the road condition variation index; perform disturbance identification on the transport weather record according to the weather disturbance step size constraint to generate the weather variation index; perform disturbance identification on the transport goods scale record according to the scale disturbance step size constraint to generate the goods scale variation index.

[0056] In the embodiment of the present application, when setting the road condition disturbance step length constraint, weather disturbance step length constraint and scale disturbance step length constraint, the technical experts set the constraints based on the needs. For the road condition disturbance step length constraint, taking the congestion index as an example, the disturbance step length constraint is set to ±5%. That is, when the congestion index changes by more than 5% compared with the previous record, it is considered that the road condition has changed significantly. For the weather disturbance step length constraint, taking the temperature as an example, the disturbance step length constraint is set to ±3°C. That is, when the temperature changes by more than 3°C compared with the previous record, it is considered that the weather has changed significantly. For the scale disturbance step length constraint, taking the weight of the goods as an example, the disturbance step length constraint is set to ±10kg. That is, when the weight of the goods changes by more than 10kg compared with the previous record, it is considered that the scale of the goods has changed significantly.

[0057] When perturbation identification is performed on the transport path road condition records according to the road condition perturbation step size constraint, the historical transport path road condition records are traversed. The congestion index of the current record is compared with the congestion index of the previous record. If the change exceeds ±5%, it is marked as a road condition disturbance event and the number of disturbances is recorded. According to the number of disturbances obtained, the road condition variation index is calculated. Specifically, when there are 15 days in a month with a congestion index change of more than 5%, the generated road condition variation index is 15 / 30=0.5.

[0058] When perturbation identification is performed on transport weather records according to the weather perturbation step constraint, the historical transport weather records are traversed. The temperature of the current record is compared with the temperature of the previous record. If the change exceeds ±3°C, it is marked as a weather perturbation event and the number of disturbances is recorded. Based on the number of disturbances obtained, the weather variation index is calculated. Specifically, there are 20 days in a month where the temperature changes exceed 33°C, and the generated weather variation index is 20 / 30=0.67.

[0059] When perturbation identification is performed on the transport cargo scale record according to the scale perturbation step constraint, the historical transport cargo scale records are traversed. Compare the cargo weight of the current record with the cargo weight of the previous record. If the change exceeds ±10kg, it is marked as a scale perturbation event and the number of disturbances is recorded. Based on the number of disturbances obtained, the cargo scale variation index is calculated. Specifically, within a month, there are 10 transport tasks with cargo weight changes exceeding 10kg, and the generated cargo scale variation index is 10 / 30=0.33.

[0060] Furthermore, the anti-disturbance capability prediction module 14 is also used for:

[0061] The Internet of Things monitoring platform is used to call a historical logistics anomaly database; based on the historical logistics anomaly database, the association between road condition anomalies, weather anomalies and scale anomalies is identified to obtain road condition anomaly association coefficients, weather anomaly association coefficients and scale anomaly association coefficients; the road condition variation index, the weather variation index and the goods scale variation index are weightedly calculated using the road condition anomaly association coefficients, the weather anomaly association coefficients and the scale anomaly association coefficients to generate the anti-disturbance prediction auxiliary factor.

[0062] In the embodiment of the present application, the interface or API of the Internet of Things monitoring platform is used to connect and call the historical logistics anomaly database. The historical logistics anomaly database contains records of logistics anomalies that occurred in the past, including abnormal road conditions, abnormal weather, and abnormal scale.

[0063] When identifying the association of abnormal road conditions, use the Apriori algorithm or association rule mining technology to identify the association between abnormal road conditions and other factors, such as peak hours and specific transportation routes. Use support and confidence to calculate the association coefficient of abnormal road conditions. Assuming that during the peak period, the support of abnormal road conditions on a certain path is 0.4 and the confidence is 0.8, the abnormal road condition association coefficient is defined as the weighted average of these two values, where the support and confidence have the same weight, then the abnormal road condition association coefficient = 0.4 × 0.5 + 0.8 × 0.5 = 0.6.

[0064] When identifying the association of weather anomalies, use the Pearson correlation coefficient or regression analysis to identify the association between weather anomalies and other factors, such as seasonal changes and geographical locations. The calculated correlation coefficient is used as the correlation coefficient of weather anomalies. Assuming that the Pearson correlation coefficient between temperature changes and weather anomalies is 0.7, the weather anomaly correlation coefficient is 0.7.

[0065] When identifying the association of scale anomalies, use data mining tools, such as Python's Scikit-learn library, to analyze the association between scale anomaly data and transportation type and cargo type. Based on the analysis results, use the correlation coefficient to calculate the correlation coefficient of scale anomalies. For example, when the calculated correlation coefficient between a certain type of cargo and scale anomalies is 0.5, the scale anomaly correlation coefficient is 0.5.

[0066] Next, the road condition variation index, weather variation index and cargo scale variation index are weightedly calculated using the road condition abnormality correlation coefficient, weather abnormality correlation coefficient and scale abnormality correlation coefficient to obtain the anti-disturbance prediction auxiliary factor.

[0067] Specifically, the anti-disturbance prediction auxiliary factor = (road condition variation index × road condition anomaly correlation coefficient) + (weather variation index × weather anomaly correlation coefficient) + (cargo scale variation index × scale anomaly correlation coefficient).

[0068] Furthermore, the anti-disturbance capability prediction module 14 is also used for:

[0069] A first fused transport route topology is constructed based on multiple transport paths and multiple transport attributes of the first transport subnetwork; transport tool spaces and transport personnel spaces with different transport attributes are extracted based on the first reserve transport resource information, and the extracted spaces are rendered to the first fused transport route topology to generate a first rendered route topology; based on the first rendered route topology, an anti-disturbance capability is predicted using an anti-disturbance prediction model to generate the first anti-disturbance performance indicator.

[0070] In an embodiment of the present application, when constructing the first fused transport route topology according to the transport path and transport attributes of the first transport subnetwork, the transport path and nodes are first visualized using GIS software to create a basic transport network topology. Use a graph data structure tool such as NetworkX to build a detailed transport route topology, including nodes and edges. The nodes represent warehouses, distribution centers, etc. The edges represent transport paths. At the same time, the transport attributes are integrated into the route topology through colors, labels, or icons to form a first fused transport route topology.

[0071] Through database query technology, such as SQL, the available space, quantity, and working capacity of transportation tools and transportation personnel are extracted from the first reserve transportation resource information. Using visualization rendering technology, the extracted transportation resource information, such as the type and quantity of transportation tools, and the location of transportation personnel, is rendered on the first fused transportation route topology in the form of icons, marks, or colors to form a first rendered route topology.

[0072] The first rendering line topology is used to predict the anti-disturbance capability through the anti-disturbance prediction model. When making a prediction, key features are first extracted from the first rendering line topology, such as the stability of the transportation tool, the professional ability of the transportation personnel, the historical disturbance data of the path, etc., and these key features are used as input features of the anti-disturbance prediction model. The anti-disturbance prediction model is obtained by training the support vector machine based on historical data and known disturbance events. The prepared input features are input into the anti-disturbance prediction model to generate a first anti-disturbance performance index. The first anti-disturbance performance index includes the predicted probability of the disturbance event, the scope of influence, the recovery time, etc.

[0073] Furthermore, the anti-disturbance capability prediction module 14 is also used for:

[0074] Construct an anti-disturbance sample library, wherein the anti-disturbance sample library includes multiple logistics rendering topology samples and corresponding multiple anti-disturbance performance index samples; call the anti-disturbance sample library through the anti-disturbance prediction model, calculate the similarity between the multiple logistics rendering topology samples and the first rendering line topology, and obtain the anti-disturbance performance index sample corresponding to the logistics rendering topology sample with the greatest similarity as the first anti-disturbance performance indicator.

[0075] In an embodiment of the present application, multiple logistics rendering topology samples are obtained from historical logistics data. These samples include various transportation routes, resource configurations, environmental conditions, and disturbance events. At the same time, for each logistics rendering topology sample, its performance in the face of a disturbance event is obtained, and the corresponding anti-disturbance performance indicators are marked, such as the average probability of occurrence of the disturbance event, the scope of influence, and the recovery time. Next, key features are extracted from the logistics rendering topology samples, such as path length, type of transport vehicle, number of transport personnel, environmental factors, etc. The processed logistics rendering topology samples and the corresponding anti-disturbance performance indicator samples are organized into an anti-disturbance sample library.

[0076] Load the trained anti-disturbance prediction model. Extract key features from the first rendering line topology, which reflect key information such as the topological structure, transportation resource configuration, and environmental conditions of the logistics network. Use the similarity calculation algorithm in the anti-disturbance prediction model, such as cosine similarity and Euclidean distance, to calculate the similarity between the features of the first rendering line topology and the logistics rendering topology samples in the anti-disturbance sample library. Find the logistics rendering topology sample with the greatest similarity to the first rendering line topology. This logistics rendering topology sample is closest to the first rendering line topology in terms of topological structure, resource configuration, etc.

[0077] The anti-interference performance index sample corresponding to the logistics rendering topology sample with the greatest similarity is taken as the first anti-interference performance index.

[0078] Furthermore, the transportation network optimization module 15 is also used for:

[0079] Taking the preset anti-disturbance index as the optimization target, the transformation resource consumption space as the constraint condition, and the transportation path, transportation attributes and transportation resources as the optimization variables, the transportation network is optimized to generate the first transportation network optimization plan.

[0080] In the embodiment of the present application, the preset anti-disturbance index is a pre-set index that needs to be achieved after optimization. When optimizing the transportation network, warehouses, transportation tools, etc. will be added. These methods will consume resources. At this time, the resource consumption space is established as the cost control range for optimization constraints, that is, the resources consumed when optimizing the transportation network cannot exceed the range of the resource consumption space. The resource consumption space is a space pre-set by the enterprise based on its own situation.

[0081] After determining the optimization objectives and constraints, the transportation network is optimized with transportation routes, transportation attributes and transportation resources as optimization variables. When optimizing, a mathematical optimization model is established based on the optimization objectives and constraints. The model includes objective functions and constraints. The objective function reflects the anti-disturbance index, and the constraints reflect the resource consumption space. In the model, transportation routes, transportation attributes and transportation resources will be used as decision variables, and the objective function will be optimized by adjusting the values ​​of these variables.

[0082] Use appropriate optimization algorithms, such as genetic algorithms, simulated annealing algorithms, particle swarm optimization algorithms, etc. to solve the optimization model. These algorithms find the decision variable values ​​that make the objective function optimal while satisfying the constraints. During the solution process, multiple iterations and adjustments are performed to find the optimal solution or a near-optimal solution.

[0083] According to the solution of the optimization model, a first transportation network optimization plan is generated, which includes optimized transportation routes, transportation attributes and transportation resource configuration.

[0084] Furthermore, the logistics transportation network acquisition module 11 is also used for:

[0085] According to the preset transportation attributes, a first transportation network with a first transportation attribute, a second transportation network with a second transportation attribute, and a third transportation network with a third transportation attribute are obtained; with repeated logistics nodes as connection factors, the first transportation network, the second transportation network, and the third transportation network are fused and connected to generate the logistics transportation network.

[0086] In the embodiment of the present application, the preset transport attributes are divided into three types: sea transport, land transport and air transport. Sea transport is used as the first transport network. Land transport is used as the second transport network, and air transport is used as the third transport network. The transport networks corresponding to different transport attributes are obtained from the internal database of the enterprise. That is, the first transport network, the second transport network and the third transport network are obtained.

[0087] Next, based on the acquired first transportation network, second transportation network and third transportation network, data analysis technology, such as RFID, is used to identify repeated logistics nodes in different transportation networks, such as warehouses, transshipment centers, etc. The repeated logistics nodes are used as connection factors to integrate and connect the first transportation network, the second transportation network and the third transportation network to generate a logistics transportation network.

[0088] In the embodiments of the present application, in summary, the embodiments of the present application have at least the following technical effects:

[0089] The present application obtains the logistics and transportation network of the first enterprise, wherein the logistics and transportation network includes multiple logistics nodes, and any logistics node has a transportation attribute mark; according to the logistics and transportation network and the transportation attribute mark, a first transportation sub-network between the first logistics node and the second logistics node is established, wherein the first transportation sub-network includes multiple transportation paths and multiple transportation attributes; the transportation resources of the first logistics node are collected through the Internet of Things monitoring platform to generate the first reserve transportation resource information; the anti-disturbance prediction auxiliary factor is established by using the Internet of Things monitoring platform, and the anti-disturbance ability of the first transportation sub-network is predicted in combination with the first reserve transportation resource information to generate the first anti-disturbance performance index; if the first anti-disturbance performance index is less than the preset anti-disturbance index, the transportation network of the first transportation sub-network is optimized to generate the first transportation network optimization plan; based on the first transportation network optimization plan, the logistics planning and management of the first transportation sub-network is performed. The present invention solves the technical problems that the prior art is difficult to solve the impact of sudden factors on logistics and transportation, and there is low efficiency and low reliability of logistics planning and management. Through the functions of real-time monitoring, dynamic optimization, intelligent prediction and decision support, the technical effect of improving the efficiency and reliability of logistics planning and management is achieved.

[0090] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order and continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0091] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0092] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. Logistics planning and management system based on the Internet of Things, It is characterized in that The system comprises: A logistics and transportation network acquisition module, used to acquire the logistics and transportation network of the first enterprise, wherein the logistics and transportation network includes a plurality of logistics nodes, and any logistics node has a transportation attribute tag; A subnetwork establishment module, used to establish a first transportation subnetwork between a first logistics node and a second logistics node according to the logistics transportation network and the transportation attribute mark, wherein the first transportation subnetwork includes multiple transportation paths and multiple transportation attributes; A transportation resource collection module, used to collect transportation resources from the first logistics node through the Internet of Things monitoring platform to generate first reserve transportation resource information; an anti-disturbance capability prediction module, configured to establish an anti-disturbance prediction auxiliary factor by using the Internet of Things monitoring platform, predict the anti-disturbance capability of the first transport subnetwork in combination with the first reserve transport resource information, and generate a first anti-disturbance performance indicator; A transportation network optimization module, configured to optimize the first transportation subnetwork and generate a first transportation network optimization plan if the first anti-disturbance performance index is less than a preset anti-disturbance index; A logistics planning and management module, used for performing logistics planning and management on the first transportation sub-network based on the first transportation network optimization solution; Wherein, the anti-disturbance capability prediction module is also used for: Using the Internet of Things monitoring platform to obtain a sample data set of historical transportation records of the first transportation subnetwork, wherein any sample data of historical transportation records includes a transportation route road condition record, a transportation weather record, and a transportation goods scale record; Based on the historical transport record sample data set, a variation analysis of the transport path road condition, transport weather and transport cargo scale is performed, and a road condition variation index, a weather variation index and a cargo scale variation index are output; generating the anti-disturbance prediction auxiliary factor by using the road condition variation index, the weather variation index and the cargo scale variation index; Wherein, the anti-disturbance capability prediction module is also used for: constructing a first fused transportation route topology according to the plurality of transportation paths and the plurality of transportation attributes of the first transportation subnetwork; Extracting transport tool spaces and transport personnel spaces with different transport attributes according to the first reserve transport resource information, and rendering them to the first fused transport route topology to generate a first rendered route topology; Based on the first rendering line topology, an anti-disturbance capability prediction is performed using an anti-disturbance prediction model to generate the first anti-disturbance performance index; Wherein, the anti-disturbance capability prediction module is also used for: Constructing an anti-disturbance sample library, wherein the anti-disturbance sample library includes a plurality of logistics rendering topology samples and a corresponding plurality of anti-disturbance performance index samples; The anti-disturbance sample library is called through the anti-disturbance prediction model, similarity calculation is performed on the multiple logistics rendering topology samples and the first rendering line topology, and the anti-disturbance performance index sample corresponding to the logistics rendering topology sample with the greatest similarity is obtained as the first anti-disturbance performance index.

2. The logistics planning and management system based on the Internet of Things as claimed in claim 1, It is characterized in that The anti-disturbance capability prediction module is also used for: Set the road condition disturbance step size constraints, weather disturbance step size constraints and scale disturbance step size constraints; Performing disturbance identification on the road condition record of the transportation path according to the road condition disturbance step size constraint to generate the road condition variation index; Performing disturbance identification on the transport weather record according to the weather disturbance step size constraint to generate the weather variation index; The transported goods scale record is subjected to disturbance identification according to the scale disturbance step size constraint to generate the goods scale variation index.

3. The logistics planning and management system based on the Internet of Things as claimed in claim 2, It is characterized in that The anti-disturbance capability prediction module is also used for: Using the Internet of Things monitoring platform to call the historical logistics anomaly database; Based on the historical logistics anomaly database, the association between abnormal road conditions, abnormal weather conditions and abnormal scale is identified to obtain an abnormal road condition association coefficient, an abnormal weather association coefficient and an abnormal scale association coefficient; The road condition variation index, the weather variation index and the goods scale variation index are weightedly calculated using the road condition abnormality correlation coefficient, the weather abnormality correlation coefficient and the scale abnormality correlation coefficient to generate the anti-disturbance prediction auxiliary factor.

4. The logistics planning and management system based on the Internet of Things as claimed in claim 1, It is characterized in that The transportation network optimization module is also used to: Taking the preset anti-disturbance index as the optimization target, the transformation resource consumption space as the constraint condition, and the transportation path, transportation attributes and transportation resources as the optimization variables, the transportation network is optimized to generate the first transportation network optimization plan.

5. The logistics planning and management system based on the Internet of Things as claimed in claim 1, It is characterized in that The logistics transportation network acquisition module is also used for: According to the preset transportation attributes, a first transportation network of a first transportation attribute, a second transportation network of a second transportation attribute, and a third transportation network of a third transportation attribute are obtained; The first transportation network, the second transportation network and the third transportation network are fused and connected with repeated logistics nodes as connection factors to generate the logistics transportation network.