Transportation process management method and system based on Internet of Things

Abstract

The invention discloses a transportation process management method and system based on the Internet of Things, and relates to the technical field of logistics transportation, and the method comprises the steps: carrying out the analysis of the transportation historical data of goods through deep learning; predicting possible delay or problems, and collecting feedback information to optimize a prediction result; constructing a multi-objective optimization model, and solving an optimal solution through a Pareto optimization algorithm; and re-planning a path and optimizing a transportation strategy based on an optimized prediction result. According to the method, the overall efficiency of logistics transportation is greatly improved, the cargo transportation time is shortened, the transportation cost is reduced, and the logistics industry is promoted to develop in the greener and sustainable direction by considering environment and energy factors. According to the invention, the flexibility and adaptability of logistics transportation are enhanced, various emergencies can be responded quickly and accurately, and safe and on-time arrival of goods is ensured. By using the Internet of Things technology, real-time monitoring and management of the logistics transportation process are realized, and the accuracy and timeliness of decision making are improved.

Description

Technical Field

[0001] The present invention relates to the field of logistics and transportation technology, and specifically to a transportation process management method and system based on the Internet of Things. Background Art

[0002] In today's highly globalized and rapidly developing e-commerce environment, logistics and transportation have become a key component of the global economy. Logistics companies are under tremendous pressure to ensure that goods can reach their destination quickly, accurately and safely within the scheduled time. However, the logistics and transportation process is often affected by a variety of unpredictable factors, such as traffic jams, bad weather, equipment failures and other emergencies, which may cause delays or damage to goods. In addition, traditional logistics optimization methods are often oversimplified and only focus on a single goal, such as the shortest time or the lowest cost, while ignoring other important factors, such as environmental impact, energy consumption and cargo safety. This single-perspective approach is often difficult to meet multiple needs in the complex and changeable real-world transportation environment. Summary of the invention

[0003] In view of the above-mentioned problems, the present invention is proposed.

[0004] Therefore, the technical problem solved by the present invention is: how to effectively optimize logistics transportation routes and strategies while taking into account multiple factors to improve transportation efficiency, reduce costs, reduce environmental impact, save energy and ensure the safety of goods.

[0005] To solve the above technical problems, the present invention provides the following technical solutions: a transportation process management method based on the Internet of Things, which comprises the following steps: using deep learning to analyze the historical transportation data of goods; predicting possible delays or problems, and collecting feedback information to optimize the prediction results; constructing a multi-objective optimization model, and finding the optimal solution through the Pareto optimization algorithm; based on the optimized prediction results, re-planning the route and optimizing the transportation strategy.

[0006] As a preferred solution of the transportation process management method based on the Internet of Things described in the present invention, the transportation history data includes the departure time, arrival time, transportation route, traffic conditions, weather conditions, cargo type and cargo weight of the vehicle, and the collected status data is removed from missing values, abnormal values, and invalid data in the wrong format, and the original format data is converted into a format that meets the requirements of the mathematical model analysis to normalize the data, and key features or information are extracted from the captured original high-dimensional data and converted into low-dimensional features to complete data preprocessing.

[0007] As a preferred solution of the transportation process management method based on the Internet of Things described in the present invention, the prediction of possible delays or problems is to construct a logistics network diagram, for each node, collect its historical data and convert it into time series features, and construct a feature vector expression as follows:

[0008]

[0009] in, and are the departure and arrival times of the nodes at time t, R i,t is the transport route, C i,t is the traffic condition, W i,t For weather conditions, G i,t is the type of goods, M i,t The weight of the cargo.

[0010] Use graph neural networks to capture the relationships and dependencies between nodes in the logistics network and optimize the prediction results. The expression is:

[0011]

[0012] Among them, N(i) is the set of neighbors of node i, is the weight between node i and node j in layer l, The feature vector of the node in the l-1th layer of the graph neural network, B l is the weight matrix of the lth layer, σ is the activation function, X i,t Represents the original feature vector of the node at time t;

[0013]

[0014] Among them, Y i,t It is the prediction result after optimization.

[0015] According to the probability of problems corresponding to the collected historical data, preliminary thresholds are set respectively, and the optimized prediction results are compared with the corresponding thresholds. If the prediction result is greater than the threshold, it is predicted that the current node will be delayed or have problems at time t, and the prediction result is further compared with the actual feedback information.

[0016] As a preferred solution of the transportation process management method based on the Internet of Things described in the present invention, the comparison between the prediction results and the actual feedback information is to calculate the prediction accuracy, recall rate, precision rate and compare them with the target accuracy, recall rate and precision rate respectively.

[0017] If the target accuracy is greater than the predicted accuracy, further judgment is made. When the prediction is that delays or problems may occur, but the actual feedback information does not appear, the initial threshold is increased. When the prediction is that there will be no delays or problems, but they actually occur, the initial threshold is lowered. If the target recall rate is greater than the predicted recall rate, the initial threshold is lowered. If the target precision rate is greater than the predicted precision rate, the initial threshold is increased.

[0018] After the three preliminary threshold adjustments are completed, the weight is set for the difference between the target value and the predicted value to construct an updated threshold model to output the adjusted threshold, which is expressed as:

[0019] Δ=α×Δ accuracy +β×Δ recall +γ×Δ precision

[0020] α+β+γ=1

[0021] Among them, Δ is the adjustment threshold, Δ accuracy is the difference between the target accuracy and the predicted accuracy, α is the weight of the accuracy difference, Δ recall is the difference between the target recall rate and the predicted recall rate, β is the weight of the recall rate difference, Δ precision is the difference between the target accuracy and the predicted accuracy, and γ is the weight of the accuracy difference.

[0022] The new threshold adjusted for the first time is the sum of the adjusted threshold and the preliminary threshold. The previous new threshold is used as the preliminary threshold for the next time. This process is recorded as a complete threshold iteration. When the preset number of iterations is reached or the threshold of consecutive iterations remains unchanged, the threshold optimization is stopped, the final threshold is output, and the prediction result is optimized.

[0023] As a preferred solution of the transportation process management method based on the Internet of Things described in the present invention, the construction of the multi-objective optimization model takes time efficiency, cost efficiency, environmental impact, energy consumption and safety as research objects.

[0024] The multi-objective optimization model expression is:

[0025]

[0026] Among them, f1(x,u,v) is time efficiency, f2(x,u,v) is cost efficiency, f3(x,u,v) is environmental impact, f4(x,u,v) is energy consumption, f5(x,u,v) is safety, x is the characteristics of the goods, u is the choice of transportation method, and v is the choice of transportation route.

[0027] As a preferred solution of the transportation process management method based on the Internet of Things described in the present invention, the transportation history data affects the time efficiency, cost efficiency, environmental impact, energy consumption and safety in the multi-objective optimization model. When the vehicle departure time and arrival time thresholds increase, the time efficiency parameter in the multi-objective optimization model increases; when the transportation route threshold increases, the cost efficiency and energy consumption parameters increase; when the traffic condition threshold increases, the time efficiency parameter decreases and the energy consumption parameter increases; when the weather condition threshold increases, the time efficiency parameter decreases and the energy consumption and safety parameters increase; when the cargo type threshold increases, the cost efficiency parameter increases and the environmental impact parameter increases; when the cargo weight threshold increases, the energy consumption parameter increases and the time efficiency parameter decreases.

[0028] As a preferred solution of the transportation process management method based on the Internet of Things described in the present invention, the re-planning of the path optimization transportation strategy based on the optimization prediction result is the optimal solution of the multi-objective optimization model solved by the Pareto optimization algorithm and the constraint method, which is used as the optimal path.

[0029] The Pareto optimization algorithm is to construct a weighted objective function by allocating relevant weights for time efficiency, cost efficiency, environmental impact, energy consumption and safety in a multi-objective optimization model when there are no requirements or restrictions during the transportation process, and calculate the optimal solution to output the optimal path under normal circumstances.

[0030] The constraint method is to customize any one of the parameters of time efficiency, cost efficiency, environmental impact, energy consumption or safety during the transportation process. The highest priority of the current constraint is selected as the main constraint, and the other four are selected as secondary constraints. The constraint optimization model and the weighted secondary objective function expression are constructed as follows:

[0031] f1(x,u,v)≤T

[0032] F sub (x,u,v)=w2·f2(x,u,v)+w3·f3(x,u,v)+w4·f4(x,u,v)+w5.f5(x,y,v)

[0033] Where f1(x,u,v) is any one of the main constraints among time efficiency, cost efficiency, environmental impact, energy consumption or safety, T is a given custom requirement, and F sub (x,u,v) is the weighted secondary objective function, and w2, w3, w4, and w5 are the weights corresponding to the other four secondary objective functions.

[0034] By minimizing the weighted secondary objective function, the optimal solution is obtained and the corresponding optimal transportation path is output.

[0035] Another object of the present invention is to provide a transportation process management system based on the Internet of Things, which can dynamically adjust transportation routes and strategies by collecting and analyzing transportation data in real time and combining advanced multi-objective optimization algorithms, thereby solving the problem that existing methods are difficult to make accurate and efficient decisions when faced with complex and changeable transportation environments.

[0036] In order to solve the above technical problems, the present invention provides the following technical solutions: a transportation process management method based on the Internet of Things, comprising: a data processing module, a constraint determination module, a weight distribution module, an optimization solution module and a path output module;

[0037] The data processing module processes the input transportation data, including departure time, arrival time, transportation route, traffic conditions, weather conditions, cargo type and cargo weight.

[0038] The constraint determination module determines the primary constraints and secondary constraints according to the customized requirements during the transportation process.

[0039] The weight allocation module allocates corresponding weights to all data based on historical data.

[0040] The optimization solution module is used to solve the optimal solution of the weighted secondary objective function under given constraints.

[0041] The path output module outputs the optimal transportation path according to the optimal solution of the optimization model.

[0042] A computer device includes a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, the steps of the above-mentioned transportation process management method based on the Internet of Things are implemented.

[0043] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of a transportation process management method based on the Internet of Things as described above are implemented.

[0044] Beneficial effects of the present invention: The present invention not only greatly improves the overall efficiency of logistics transportation, shortens the transportation time of goods, and reduces transportation costs, but also promotes the development of the logistics industry in a more green and sustainable direction by considering environmental and energy factors. In addition, the present invention also enhances the flexibility and adaptability of logistics transportation, enabling it to respond quickly and accurately to various emergencies and ensure the safety and timely arrival of goods. By utilizing the Internet of Things technology, the present invention also realizes real-time monitoring and management of the logistics transportation process, greatly improving the accuracy and timeliness of decision-making, and providing logistics companies with a strong competitive advantage. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing 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. Among them:

[0046] Figure 1 An overall flow chart of a transportation process management method based on the Internet of Things provided by the first embodiment of the present invention;

[0047] Figure 2 A structural diagram of a transportation process management system based on the Internet of Things provided for the second embodiment of the present invention. DETAILED DESCRIPTION

[0048] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0049] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0050] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0051] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0052] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0053] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, such as: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0054] Example 1

[0055] Reference Figure 1 , is an embodiment of the present invention, and provides a transportation process management method based on the Internet of Things, characterized in that:

[0056] Use deep learning to analyze historical data on cargo transportation; predict possible delays or problems, and collect feedback information to optimize prediction results; build a multi-objective optimization model and use the Pareto optimization algorithm to find the optimal solution; re-plan routes and optimize transportation strategies based on optimized prediction results.

[0057] The transportation history data includes the vehicle's departure time, arrival time, transportation route, traffic conditions, weather conditions, cargo type and cargo weight. The collected status data will remove missing values, outliers, and invalid data in the wrong format, convert the original format data into a format that meets the requirements of the mathematical model analysis, normalize the data, extract key features or information from the captured original high-dimensional data, and convert them into low-dimensional features to complete data preprocessing.

[0058] The method of predicting possible delays or problems is to construct a logistics network diagram. For each node, its historical data is collected and converted into time series features. The feature vector expression is constructed as follows:

[0059]

[0060] in, and are the departure and arrival times of the nodes at time t, R i,t is the transport route, C i,t is the traffic condition, W i,t For weather conditions, Gi,t is the type of goods, M i,t is the weight of the cargo;

[0061] Use graph neural networks to capture the relationships and dependencies between nodes in the logistics network and optimize the prediction results. The expression is:

[0062]

[0063] Among them, N(i) is the set of neighbors of node i, is the weight between node i and node j in layer l, The feature vector of the node in the l-1th layer of the graph neural network, B l is the weight matrix of the lth layer, σ is the activation function, X i,t Represents the original feature vector of the node at time t;

[0064]

[0065] Among them, Y i,t is a vector whose length is equal to the number of possible causes of delays or problems. Each element represents the probability of the corresponding cause, which is also the prediction result after optimization;

[0066] According to the probability of problems corresponding to the collected historical data, preliminary thresholds are set respectively, and the optimized prediction results are compared with the corresponding thresholds. If the prediction result is greater than the threshold, it is predicted that the current node will be delayed or have problems at time t, and the prediction result is further compared with the actual feedback information.

[0067] Different thresholds are set for different situations based on the characteristics of historical data, such as vehicle departure time, arrival time, transportation route, traffic conditions, weather conditions, cargo type, and cargo weight.

[0068] Perform error analysis regularly, compare the prediction results with the actual feedback data, and compare the predicted accuracy, recall, and precision with the target accuracy, recall, and precision.

[0069] If the target accuracy is greater than the predicted accuracy, further judgment is made. When the prediction is that there may be delays or problems, but they do not actually occur, the initial threshold is increased. When the prediction is that there will be no delays or problems, but they actually occur, the initial threshold is lowered. If the target recall rate is greater than the predicted recall rate, the initial threshold is lowered. If the target precision rate is greater than the predicted precision rate, the initial threshold is increased. The weight is set for the difference between the target value and the predicted value. The threshold is adjusted by constructing an updated threshold model output. The expression is:

[0070] Δ=α×Δ accuracy +β×Δ recall +γ×Δprecision

[0071] α+β+γ=1

[0072] Among them, Δ is the adjustment threshold, Δ accuracy is the difference between the target accuracy and the predicted accuracy, α is the weight of the accuracy difference, Δ recall is the difference between the target recall rate and the predicted recall rate, β is the weight of the recall rate difference, Δ precision is the difference between the target accuracy and the predicted accuracy, and γ is the weight of the accuracy difference.

[0073] The new threshold adjusted for the first time is the sum of the adjusted threshold and the preliminary threshold. The previous new threshold is used as the preliminary threshold for the next time. This process is recorded as a complete threshold iteration. When the preset number of iterations is reached or the threshold of consecutive iterations remains unchanged, the threshold optimization is stopped, the final threshold is output, and the prediction result is optimized.

[0074] Logistics and transportation optimization needs to consider many factors, namely, time efficiency, cost efficiency, environmental impact, energy consumption and safety as research objects, and build a multi-objective optimization model;

[0075] Time efficiency refers to minimizing the total transportation time of goods from the starting point to the destination, cost efficiency refers to minimizing the total transportation cost, including fuel, labor, equipment depreciation, etc., environmental impact refers to minimizing CO2 emissions and other pollutants, energy consumption refers to minimizing the total energy consumption during transportation, and safety refers to minimizing the risk of damage or loss of goods.

[0076] The multi-objective optimization model expression is:

[0077]

[0078] Among them, f1(x,u,v) is time efficiency, f2(x,u,v) is cost efficiency, f3(x,u,v) is environmental impact, f4(x,u,v) is energy consumption, f5(x,u,v) is safety, x is the characteristics of the goods, u is the choice of transportation method, and v is the choice of transportation route.

[0079] f1(x,u,v) represents the total transportation time, x is the characteristics of the goods, such as quantity, size, weight, etc., u is the choice of transportation method, such as truck, train, plane, ship, etc., v is the choice of transportation path, such as a direct path from A to B, a path from A to B via C, etc.

[0080] f2(x,u,v) represents the total cost, x is the characteristics of the goods, which may affect the cost. For example, heavier goods may require higher freight rates, u is the choice of transportation mode, and different transportation modes have different costs, and v is the choice of transportation route. Different route lengths and difficulties may result in different costs.

[0081] f3(x,u,v) represents CO2 emissions, x is the characteristics of the goods, such as certain specific goods may require specific modes of transportation, which may have higher or lower CO2 emissions, u: the choice of transportation mode, each mode of transportation has its specific CO2 emissions, v is the choice of transportation route, a longer route may result in more CO2 emissions.

[0082] f4(x,u,v)) represents energy consumption, x is the characteristics of the goods, such as large goods may require more energy to transport, u is the choice of transportation mode, each mode of transportation has its own specific energy consumption, and v is the choice of transportation route. Longer or more difficult routes may result in more energy consumption.

[0083] f5(x,u,v) represents the risk of damage or loss of goods. x is the characteristics of the goods. For example, fragile or valuable goods may have higher risks. u is the choice of transportation method. Some transportation methods may be safer or more dangerous. v is the choice of transportation route. Some routes may have higher risks, such as passing through unstable areas.

[0084] Transportation history data affects time efficiency, cost efficiency, environmental impact, energy consumption, and safety in multi-objective optimization models.

[0085] When the vehicle departure time and arrival time thresholds increase, the time efficiency parameter in the multi-objective optimization model increases.

[0086] When the transport route threshold increases, the cost efficiency as well as the energy consumption parameters increase.

[0087] When the threshold of traffic conditions increases, the time efficiency parameter decreases and the energy consumption parameter increases.

[0088] When the threshold of weather conditions increases, the time efficiency parameter decreases, and the energy consumption and safety parameters increase.

[0089] When the threshold of goods types increases, the cost efficiency parameter increases and the environmental impact parameter increases.

[0090] When the threshold of cargo weight increases, the energy consumption parameter increases and the time efficiency parameter decreases.

[0091] If the thresholds of departure time and arrival time are increased, the time efficiency constraints in the multi-objective optimization model will be relaxed because there are more time windows to arrange transportation, but it may cause the cost efficiency constraints to become stricter due to possible increased storage costs or waiting costs.

[0092] If the threshold of the transport route is increased, the constraints on cost efficiency and energy consumption in the multi-objective optimization model will become more stringent because the selected route may be longer or more complex, but the constraints on safety may be relaxed because the selected route may avoid certain high-risk areas.

[0093] If the threshold of traffic conditions increases, the constraints of time efficiency and energy consumption in the multi-objective optimization model become more stringent because more traffic jams or accidents may be encountered.

[0094] If the threshold of weather conditions increases, the constraints of time efficiency, energy consumption, and safety in the multi-objective optimization model become more stringent because more severe weather conditions such as storms or snow may be encountered.

[0095] If the threshold of cargo types is increased, the constraints of cost efficiency and environmental impact in the multi-objective optimization model become more stringent, because more packaging and handling may be required, and some cargo may be harmful to the environment.

[0096] If the threshold of cargo weight is increased, the energy consumption constraint in the multi-objective optimization model becomes more stringent, because heavy cargo requires more energy to transport, and the time efficiency constraint may become more stringent, because heavy cargo may require longer loading and unloading time.

[0097] Based on the optimization prediction results, the re-planning of the route optimization transportation strategy is the optimal solution of the multi-objective optimization model solved by the Pareto optimization algorithm and the constraint method as the optimal path;

[0098] The Pareto optimization algorithm is to construct a weighted objective function by allocating relevant weights for time efficiency, cost efficiency, environmental impact, energy consumption and safety in the multi-objective optimization model when there are no requirements or restrictions in the transportation process, and calculate the optimal solution to output the optimal path under normal circumstances;

[0099] The constraint method is that when there are custom requirements for any one of time efficiency, cost efficiency, environmental impact, energy consumption or safety in the transportation process, the constraint with the highest execution priority is selected as the main constraint, and the other four are selected as secondary constraints. The constraint optimization model and the weighted secondary objective function expression are constructed as follows:

[0100] f1(x,u,v)≤T

[0101] F sub (x,u,v)=w2·f2(x,u,v)+w3·f3(x,u,v)+w4·f4(x,u,v)+w5.f5(x,u,v)

[0102] Where f1(x,u,v) is any one of the main constraints among time efficiency, cost efficiency, environmental impact, energy consumption or safety, T is a given custom requirement, and F sub (x,u,v) is the weighted secondary objective function, w2, w3, w4, w5 are the weights corresponding to the other four secondary objective functions;

[0103] By minimizing the weighted secondary objective function, the optimal solution is obtained and the corresponding optimal transportation path is output.

[0104] Output the best transportation path after constraint optimization, ensuring that the path not only achieves the best in terms of the main constraint objectives, but also meets the predetermined standards in terms of all secondary constraints.

[0105] When there are mandatory requirements for time during the transportation process, the time efficiency factor is used as the primary constraint, and the other four factors (cost efficiency, environmental impact, energy consumption, and safety) are used as secondary constraints. They are substituted into the weighted secondary objective function to calculate the optimal solution, that is, output the optimal transportation route, and so on.

[0106] Example 2

[0107] Reference Figure 2 , which is an embodiment of the present invention, provides a system for a transportation process management method based on the Internet of Things, characterized in that it includes a data processing module, a constraint determination module, a weight allocation module, an optimization solution module and a path output module.

[0108] The data processing module processes the input transportation data, including departure time, arrival time, transportation route, traffic conditions, weather conditions, cargo type and cargo weight.

[0109] The constraint determination module determines the primary and secondary constraints based on the customized requirements during the transportation process.

[0110] The weight allocation module assigns corresponding weights to all data based on historical data.

[0111] The optimization solution module is used to find the optimal solution of the weighted secondary objective function under given constraints.

[0112] The path output module outputs the optimal transportation path based on the optimal solution of the optimization model.

[0113] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program code.

[0114] The logic and / or steps represented in the flowchart or otherwise described herein, such as, can be considered as an ordered list of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by an instruction execution system, apparatus or device (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, apparatus or device and execute instructions), or in conjunction with such instruction execution systems, apparatuses or devices. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, apparatus or device, or in conjunction with such instruction execution systems, apparatuses or devices.

[0115] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, such as by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0116] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0117] Example 3

[0118] In this embodiment, in order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments. This embodiment experiments the existing traditional method and the method of this embodiment respectively.

[0119] In order to verify the effectiveness of the IoT-based transportation process management method in different scenarios, especially its responsiveness in the face of unpredictable transportation obstacles, a simulated city map was built, including multiple warehouses, distribution centers, and customer addresses, and a traffic network simulation, including roads, traffic signals, and traffic flow.

[0120] The transportation data for the past year was collected, including the vehicle’s departure time, arrival time, transportation route, traffic conditions, weather conditions, cargo type and cargo weight, and then the IoT devices were used to simulate the collected real-time traffic, weather and cargo status data.

[0121] Build a logistics network graph. For each node, collect its historical data and convert it into time series features. Use graph neural network to capture the relationships and dependencies between nodes in the logistics network and optimize the prediction results.

[0122] Construct a multi-objective optimization model, taking into account time efficiency, cost efficiency, environmental impact, energy consumption, and safety.

[0123] Use the constraint method for optimization. When there are custom requirements, select the current constraint with the highest execution priority as the primary constraint, and the other four as secondary constraints.

[0124] Take time efficiency as an example: set the weight of time efficiency to α.

[0125] f1(x,u,v)=α×(T end -T start )

[0126] Among them, T start and T end are the departure and arrival times of the node at time t, respectively.

[0127] Vehicle departure time: 08:00, arrival time: 10:00, transportation route: A->B->C, traffic conditions: smooth, weather conditions: sunny, cargo type: frozen food, cargo weight: 1000kg.

[0128] Feature vector of node A: [08:00, A->B, unobstructed, sunny, frozen food, 1000kg].

[0129] Collect relevant data for each path.

[0130] Path A: Time = 8 hours, cost = $100, environmental impact = 10 units.

[0131] Path B: Time = 10 hours, cost = $80, environmental impact = 8 units.

[0132] Path C: Time = 9 hours, cost = $90, environmental impact = 9 units.

[0133] Score of path A = 0.5*8+0.3*100+0.2*10=4+30+2=36

[0134] Score of Path B = 0.5*10+0.3*80+0.2*8=5+24+1.6=30.6

[0135] Score of path C = 0.5*9+0.3*90+0.2*9=4.5+27+1.8=33.3

[0136] According to the score, the path with the lowest score is selected. A lower score means a better path with shorter time, lower cost and less environmental impact. Therefore, path B is the best choice.

[0137] When faced with logistics and transportation optimization problems, specific hard requirements often arise. Certain goods may have clear delivery time windows, or certain routes may be restricted due to safety or environmental reasons. In this case, we need to ensure that these hard requirements are taken into account during the optimization process.

[0138] Filter out the paths that meet all hard requirements from all possible paths. If there is a hard requirement that the transportation time cannot exceed 9 hours, then all paths with a transportation time exceeding 9 hours will be immediately excluded.

[0139] Time efficiency w1=0.5, cost efficiency w2=0.5. Since time is a hard requirement, we increase the weight of time efficiency, w1_new=0.7, w2_new=0.3.

[0140] Using the adjusted weights, we calculate a score for each path, where path A has a shipping cost of $100 and path C has a shipping cost of $110

[0141] Score(A)=0.7×(9-8)+0.3×(120-100)=0.7+6=6.7

[0142] Score(C)=0.7×(9-9)+0.3×(120-110)=3

[0143] According to the above scores, path A has the highest score, so it is selected as the optimal path.

[0144] This approach ensures that hard requirements are met and provides a score for paths that meet these requirements, allowing us to select the optimal path.

[0145] Table 1 Data comparison table

[0146]

[0147]

[0148] It can be clearly seen from the above table that compared with traditional methods, the present invention has significant advantages in time efficiency, cost efficiency and energy consumption. In all scenarios, the time efficiency of the present invention saves 1-2 hours compared with traditional methods, which means that the goods can reach the destination faster. In addition, the cost efficiency of the present invention also saves 15-20 US dollars compared with traditional methods, which brings significant economic benefits to logistics companies. Finally, the energy consumption of the present invention is also 15-20 kWh less than that of traditional methods, which not only reduces operating costs but is also environmentally friendly.

[0149] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A transportation process management method based on the Internet of Things, characterized in that: include: Use deep learning to analyze historical data on cargo transportation; Predict possible delays or problems and collect feedback to optimize predictions; Construct a multi-objective optimization model and find the optimal solution through the Pareto optimization algorithm; Based on the optimization prediction results, re-plan the route and optimize the transportation strategy.

2. The method for transport process management based on the Internet of Things as claimed in claim 1, characterized in that: The transportation history data includes the vehicle's departure time, arrival time, transportation route, traffic conditions, weather conditions, cargo type and cargo weight. The collected status data will remove missing values, outliers, and invalid data in the wrong format, convert the original format data into a format that meets the requirements of the mathematical model analysis, normalize the data, extract key features or information from the captured original high-dimensional data, and convert them into low-dimensional features to complete data preprocessing.

3. A method for transport process management based on the Internet of Things as claimed in claim 2, characterized in that: The possible delays or problems in predicting the above are to construct a logistics network diagram. For each node, its historical data is collected and converted into time series features. The feature vector expression is constructed as follows: in, and are the departure and arrival times of the nodes at time t, R i,t is the transportation route, C i,t is the traffic condition, W i,t For weather conditions, G i,t is the type of goods, M i,t is the weight of the cargo; Use graph neural networks to capture the relationships and dependencies between nodes in the logistics network and optimize the prediction results. The expression is: Among them, N(i) is the set of neighbors of node i, is the weight between node i and node j in layer l, The feature vector of the node in the l-1th layer of the graph neural network, B l is the weight matrix of the lth layer, σ is the activation function, X i,t Represents the original feature vector of the node at time t; Among them, Y i,t is the prediction result after optimization; According to the probability of problems corresponding to the collected historical data, preliminary thresholds are set respectively, and the optimized prediction results are compared with the corresponding thresholds. If the prediction result is greater than the threshold, it is predicted that the current node will be delayed or have problems at time t, and the prediction result is further compared with the actual feedback information.

4. A method for transport process management based on the Internet of Things as claimed in claim 3, characterized in that: The comparison between the prediction result and the actual feedback information is to calculate the accuracy, recall rate and precision of the prediction and compare them with the target accuracy, recall rate and precision respectively; If the target accuracy is greater than the predicted accuracy, further judgment is made. When the prediction is that there may be delays or problems, but the actual feedback information does not appear, the initial threshold is increased. When the prediction is that there will be no delays or problems, but they actually occur, the initial threshold is lowered. If the target recall rate is greater than the predicted recall rate, the initial threshold is lowered. If the target precision rate is greater than the predicted precision rate, the initial threshold is increased. After the three preliminary threshold adjustments are completed, the weight is set for the difference between the target value and the predicted value to construct an updated threshold model to output the adjusted threshold, which is expressed as: Δ=Δ×a accuracy +β×α recall +γ×Δ precision α+β+γ=1 Among them, Δ is the adjustment threshold, Δ accuracy is the difference between the target accuracy and the predicted accuracy, α is the weight of the accuracy difference, Δ recall is the difference between the target recall rate and the predicted recall rate, β is the weight of the recall rate difference, Δ precision is the difference between the target accuracy and the predicted accuracy, and γ is the weight of the accuracy difference; The new threshold adjusted for the first time is the sum of the adjusted threshold and the preliminary threshold. The previous new threshold is used as the preliminary threshold for the next time. This process is recorded as a complete threshold iteration. When the preset number of iterations is reached or the threshold of consecutive iterations remains unchanged, the threshold optimization is stopped, the final threshold is output, and the prediction result is optimized.

5. A method for transport process management based on the Internet of Things as claimed in claim 4, characterized in that The multi-objective optimization model is constructed to take time efficiency, cost efficiency, environmental impact, energy consumption and safety as research objects; The multi-objective optimization model expression is: Among them, f1(x,u,v) is time efficiency, f2(x,u,v) is cost efficiency, f3(x,u,v) is environmental impact, f4(x,u,v) is energy consumption, f5(x,u,v) is safety, x is the characteristics of the goods, u is the choice of transportation method, and v is the choice of transportation route.

6. A method for transport process management based on the Internet of Things as claimed in claim 5, characterized in that: The transportation history data affects the time efficiency, cost efficiency, environmental impact, energy consumption and safety in the multi-objective optimization model. When the vehicle departure time and arrival time thresholds increase, the time efficiency parameter in the multi-objective optimization model increases. When the transportation route threshold increases, the cost efficiency and energy consumption parameters increase. When the traffic condition threshold increases, the time efficiency parameter decreases and the energy consumption parameter increases. When the weather condition threshold increases, the time efficiency parameter decreases and the energy consumption and safety parameters increase. When the cargo type threshold increases, the cost efficiency parameter increases and the environmental impact parameter increases. When the cargo weight threshold increases, the energy consumption parameter increases and the time efficiency parameter decreases.

7. A method for transport process management based on the Internet of Things as claimed in claim 6, characterized in that: The re-planning of the route optimization transportation strategy based on the optimization prediction result is the optimal solution of the multi-objective optimization model solved by the Pareto optimization algorithm and the constraint method as the optimal path; The Pareto optimization algorithm is to construct a weighted objective function by allocating relevant weights for time efficiency, cost efficiency, environmental impact, energy consumption and safety in a multi-objective optimization model when there are no requirements or restrictions during transportation, and calculate the optimal solution to output the optimal path under normal circumstances; The constraint method is to customize any one of the parameters of time efficiency, cost efficiency, environmental impact, energy consumption or safety during the transportation process. The highest priority of the current constraint is selected as the main constraint, and the other four are selected as secondary constraints. The constraint optimization model and the weighted secondary objective function expression are constructed as follows: f1(x,u,v)≤T F sub (x,u,v)=w2·f2(x,u,v)+w3·f3(x,u,v)+w4·f4(x,u,v)+w5.f5(x,y,v) Where f1(x,u,v) is any one of the main constraints among time efficiency, cost efficiency, environmental impact, energy consumption or safety, T is a given custom requirement, and F sub (x,u,v) is the weighted secondary objective function, w2, w3, w4, w5 are the weights corresponding to the other four secondary objective functions; By minimizing the weighted secondary objective function, the optimal solution is obtained and the corresponding optimal transportation path is output.

8. A system using a transportation process management method based on the Internet of Things as claimed in any one of claims 1 to 7, characterized in that: It includes a data processing module, a constraint determination module, a weight distribution module, an optimization solution module and a path output module; The data processing module processes the input transportation data, including departure time, arrival time, transportation route, traffic conditions, weather conditions, cargo type and cargo weight; The constraint determination module determines the primary constraints and secondary constraints according to the customized requirements during the transportation process; The weight allocation module allocates corresponding weights to all data according to historical data; The optimization solution module is to solve the optimal solution of the weighted secondary objective function under given constraints; The path output module outputs the optimal transportation path according to the optimal solution of the optimization model.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of a transportation process management method based on the Internet of Things described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a transportation process management method based on the Internet of Things described in any one of claims 1 to 7 are implemented.

Images