Remote logistics management method and system based on cloud big data management and control

Abstract

The invention relates to the technical field of logistics management and control of cloud computing, and particularly discloses a remote logistics management method and system based on cloud big data management and control, and the method comprises the steps: obtaining multi-source data in a logistics transportation process in real time through a data collection module, including the information of road conditions, weather, warehouse states and the like; the real-time data and historical data are compared and analyzed through a data comparison and analysis module, and the optimal logistics transportation path is determined; monitoring the real-time data based on the selected path through a path risk assessment module, assessing the risk existing in the current logistics transportation, and dividing the risk into a high risk or a low risk according to the assessment result; different countermeasures are taken according to the risk levels, that is, the current transportation process continues to be executed for low-risk paths, and for high-risk paths, risk factors are analyzed, and alternative schemes are implemented; according to the invention, functions of real-time data acquisition, intelligent path planning and dynamic risk assessment are integrated, and efficient management of logistics transportation is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of cloud computing logistics control, and in particular to a remote logistics management method and system based on cloud big data control. Background Art

[0002] With the acceleration of global economic integration and the rapid development of e-commerce, modern logistics industry is facing unprecedented opportunities and challenges. On the one hand, consumers have higher and higher requirements for the speed of goods delivery and service quality. On the other hand, factors such as complex traffic environment, changeable weather conditions and uncertainty in warehouse management have also brought many problems to logistics and transportation. Traditional logistics management models often rely on manual experience for route planning and risk assessment. This method is not only inefficient, but also difficult to adapt to the growing logistics needs.

[0003] On the technical level, although information technology has developed rapidly in recent years, its application in the logistics industry is still in its infancy; most logistics companies still use relatively traditional information management systems, which are unable to achieve real-time data collection and analysis, resulting in slow response to emergencies and inability to adjust transportation plans in a timely manner, thus affecting the overall efficiency and safety of logistics;

[0004] There is a lack of a method that can collect multi-source data in the logistics transportation process in real time and process it through big data analysis technology, so as to dynamically adjust the transportation route, assess risks and take corresponding measures. Summary of the invention

[0005] The purpose of the present invention is to provide a remote logistics management method and system based on cloud big data control to solve the above-mentioned problems.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] The remote logistics management method based on cloud big data control includes the following steps:

[0008] S1: Obtain real-time multi-source data during logistics transportation, including road condition data, weather data, and warehouse status data;

[0009] S2: Compare and analyze real-time multi-source data with historical multi-source data to identify the best logistics transportation path;

[0010] Wherein, the optimal path represents the first selected path in the logistics transportation process;

[0011] S3: Based on the optimal transportation route, real-time multi-source data is monitored to assess the risks of current logistics and transportation, and the risks are divided into high risk and low risk according to the assessment results;

[0012] S4: Based on the low-risk logistics and transportation process, continue to execute the current logistics and transportation process;

[0013] S5: Based on the high-risk logistics and transportation process, analyze the specific risk factors and implement alternative plans based on the specific risk factors.

[0014] As a further solution of the present invention: the road condition data, weather data and warehouse status data specifically include:

[0015] Traffic data includes: traffic flow and real-time vehicle speed;

[0016] Weather data includes: precipitation and wind speed;

[0017] Warehouse data includes: inventory.

[0018] As a further solution of the present invention: the comparative analysis of real-time multi-source data and historical multi-source data to identify the best logistics transportation path specifically includes:

[0019] Obtain real-time multi-source data and historical multi-source data for each path respectively, calculate the score of each path through comparative analysis and combining with the path score function, and obtain the minimum path score as the optimal path for logistics transportation;

[0020] The calculation expression of the path score function is:

[0021]

[0022] Where, X c Indicates the value of real-time multi-source data, X h represents the value of the historical average multi-source data, λ represents the preset balance parameter, S(z) represents the score of the zth path, i represents the number of parameters in the multi-source data, z represents the number of paths, σ i represents the variance corresponding to each parameter i, and n represents the maximum number of parameters.

[0023] As a further solution of the present invention: Based on the optimal transportation path, monitoring the real-time multi-source data, analyzing the real-time multi-source data, and calculating the risk score of the logistics transportation path specifically include:

[0024] Using the Bayesian network model, the risk probability in the logistics transportation process is calculated based on real-time input of multi-source data;

[0025] Calculate the probability of logistics transportation routes based on the risk probability during logistics transportation;

[0026] The calculation expression of the probability of the logistics transportation path is:

[0027]

[0028] Where X represents real-time multi-source data, P(Risk|X) represents the probability that the logistics transportation path is at risk given the real-time multi-source data X, P(X|Risk) represents the joint probability distribution of real-time multi-source data under high-risk conditions, P(Risk) represents the preset prior risk probability, and P(X) represents the marginal probability of real-time multi-source data X.

[0029] As a further solution of the present invention: the calculation expression of the joint probability distribution is:

[0030]

[0031] In the formula, j represents the number of feature data in multi-source data, m represents the maximum number of feature data, and X j represents the jth feature data in multi-source data, Pa(X j ) represents the parent node set of the jth feature, P(X j |Risk,Pa(X j )) represents the conditional probability of the i-th feature given the risk and the parent node.

[0032] As a further solution of the present invention: the Bayesian network model, the specific training process includes:

[0033] In the logistics and transportation risk assessment model of the present invention, the defined variables include:

[0034] Real-time traffic flow, real-time vehicle speed, real-time precipitation, real-time wind speed, real-time inventory and the final target variable risk;

[0035] Through causal analysis, a directed acyclic graph is constructed to show the relationship between variables;

[0036] Obtain real-time and historical multi-source data;

[0037] Real-time multi-source data and historical multi-source data are organized into a format for Bayesian network analysis, and the Bayesian network model is trained using maximum likelihood estimation.

[0038] As a further solution of the present invention: the assessment of the risks existing in the current logistics and transportation specifically includes:

[0039] Determine whether the probability of risk in the logistics transportation route is greater than or equal to the preset threshold. If so, it is recorded as high risk, otherwise it is recorded as low risk.

[0040] As a further solution of the present invention: Based on the high-risk logistics transportation process, the specific risk-causing factors are analyzed, including:

[0041] If real-time multi-source data exceeds the preset safety threshold, the system automatically marks the factor as a high-risk factor and records it;

[0042] The system compares and analyzes real-time data with historical data, calculates the difference between current traffic flow and historical average flow, and evaluates potential transportation threats based on weather conditions.

[0043] As a further solution of the present invention: the alternative solution is implemented according to the specific factors, specifically including:

[0044] For high risks identified, the system will immediately formulate response strategies, including adjusting the transportation route, the driver reducing the speed and increasing the driving distance;

[0045] During the transportation process, the system will dynamically update the driver's travel arrangements;

[0046] During the implementation of alternative plans, the system updates the risk status of drivers and dispatchers in real time through the cloud platform to ensure that they are aware of the latest environmental changes and response measures. Specific real-time updates include the push of real-time vehicle speed, wind speed, road conditions and other information;

[0047] All high-risk events and their handling measures will be recorded in detail in the system to form a risk analysis report, which will include high-risk identification time, influencing factors and handling measures.

[0048] Remote logistics management system based on cloud big data control, including:

[0049] A data acquisition module, which is used to obtain real-time multi-source data during logistics transportation, including: road condition data, weather data and warehouse status data;

[0050] A data comparison and analysis module, which is used to compare and analyze real-time multi-source data with historical multi-source data to identify the best logistics transportation path;

[0051] A path risk assessment module, which monitors real-time multi-source data based on the optimal transportation path, assesses the risks of current logistics transportation, and divides the risks into high risk and low risk according to the assessment results;

[0052] A low-risk path execution module, wherein the low-risk path execution module continues to execute the current logistics transportation process based on the low-risk logistics transportation process;

[0053] The high-risk path processing module analyzes specific risk-causing factors based on the high-risk logistics transportation process and implements alternative plans based on the specific risk-causing factors.

[0054] Beneficial effects of the present invention:

[0055] (1) The present invention realizes comprehensive monitoring and risk assessment of the logistics and transportation process by integrating real-time multi-source data collection and analysis. Traditional logistics and transportation often rely on fixed timetables and route planning, and lack sensitivity to real-time changes. This can easily lead to transportation delays or even safety accidents when encountering unforeseen traffic jams, bad weather, or warehouse inventory shortages. However, the present invention can capture these changes in the first place through cloud-based big data management and control technology, and quickly identify the optimal transportation route through comparative analysis of real-time data and historical data. In particular, when the system detects high-risk factors, it can quickly adjust the transportation plan and take measures such as changing routes and adjusting vehicle speeds to avoid risks. This immediate response mechanism greatly improves the safety of logistics and transportation, reduces transportation delays and cargo damage caused by emergencies, and also reduces the possibility of accidents, ensuring that goods are delivered to customers on time and in good quality.

[0056] (2) The present invention optimizes the selection of logistics transportation routes through intelligent algorithms, thereby effectively improving transportation efficiency and helping companies achieve cost savings. Traditional logistics transportation is often rigid in route planning, and once a route is selected, it is difficult to change, which may lead to low transportation efficiency and even additional cost expenditures when facing traffic jams or other force majeure factors. The present invention uses advanced data analysis technology, combined with real-time road conditions, weather forecasts, warehouse inventory status and other information, to dynamically adjust transportation plans and select the most economical and efficient transportation route. For example, when it is predicted that a certain section of road will be seriously congested, the system can plan alternative routes in advance, avoiding unnecessary waiting time, thereby speeding up the turnover of goods. In addition, by accurately controlling various factors in the transportation process, it can also reduce fuel waste and other resource losses caused by unreasonable transportation, thereby reducing operating costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] The present invention will be further described below in conjunction with the accompanying drawings.

[0058] Figure 1 It is a flowchart of the specific steps of the remote logistics management method based on cloud big data control of the present invention;

[0059] Figure 2 It is a flowchart of the remote logistics management system based on cloud big data control of the present invention. DETAILED DESCRIPTION

[0060] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0061] See also Figure 1 As shown, the present invention is a remote logistics management method based on cloud big data management and control, comprising the following steps:

[0062] S1: Obtain real-time multi-source data during logistics transportation, including road condition data, weather data, and warehouse status data;

[0063] S2: Compare and analyze real-time multi-source data with historical multi-source data to identify the best logistics transportation path;

[0064] Wherein, the optimal path represents the first selected path in the logistics transportation process;

[0065] S3: Based on the optimal transportation route, real-time multi-source data is monitored to assess the risks of current logistics and transportation, and the risks are divided into high risk and low risk according to the assessment results;

[0066] S4: Based on the low-risk logistics and transportation process, continue to execute the current logistics and transportation process;

[0067] S5: Based on the high-risk logistics and transportation process, analyze the specific risk factors and implement alternative plans based on the specific risk factors.

[0068] In S1, real-time multi-source data is obtained during the logistics transportation process, including road condition data, weather data, and warehouse status data. Specifically, it includes:

[0069] The acquisition and processing of road condition data includes: continuously monitoring and recording the vehicle's location and speed through the GPS positioning system installed on the transport vehicle, and uploading the data to the cloud through the 5G network.

[0070] At the same time, the system integrates external navigation services (such as public transportation platform API) to obtain real-time urban traffic data, including traffic conditions on major roads, traffic control information, etc.

[0071] The cloud system cleans the received road condition data, removes invalid data (such as position deviation data, duplicate data, etc.), and then performs data fusion, formats the navigation data and vehicle GPS data in a unified manner, and calculates information such as congested sections, average vehicle speed, and traffic anomalies.

[0072] Weather data acquisition and processing include: the system periodically calls the API interface of the meteorological data platform to obtain real-time weather information in different regions.

[0073] At the same time, through geographic location matching, weather data is associated with the vehicle's transportation location to ensure that the weather information obtained accurately corresponds to the current transportation area.

[0074] After being cleaned and classified, the weather data is input into the system for analysis.

[0075] Warehouse status data acquisition and processing include: directly accessing real-time inventory status through the warehouse management system, and sensors deployed in the warehouse (temperature, humidity, space monitoring, etc.) transmit environmental and space data to the cloud in real time.

[0076] Such data will be initially processed by the edge computing gateway before being uploaded to the central data platform, ensuring transmission efficiency and reducing the burden of original data transmission.

[0077] The system cleans and integrates warehouse data.

[0078] Among them, the road condition data includes: traffic flow and real-time vehicle speed;

[0079] Weather data includes: precipitation and wind speed;

[0080] Warehouse data includes: inventory.

[0081] In S2, real-time multi-source data is compared and analyzed with historical multi-source data to identify the best logistics transportation path, including:

[0082] Get real-time traffic flow c : Indicates the number of vehicles on the current road, which directly affects the transportation time;

[0083] Get real-time vehicle speed V c : Indicates the current speed of the transport vehicle, which affects the efficiency of logistics transportation;

[0084] Get real-time precipitation P c : Indicates real-time precipitation, affecting road conditions;

[0085] Get real-time wind speed W c : Affects the stability and speed of the vehicle;

[0086] Get real-time inventory C c : Reflects the actual inventory situation in the warehouse and affects the feasibility of logistics and transportation;

[0087] Get the historical average traffic flow T h : Indicates the average flow rate of the road section in history, which serves as a reference for comparing the current flow rate;

[0088] Get the historical average vehicle speed V h : Indicates the average speed of the road section in history, which is used to evaluate the rationality of the current speed;

[0089] Get the historical average precipitation P h : represents the historical precipitation in the area, used to assess the long-term impact of weather on transportation;

[0090] Get the historical average wind speed W h : Indicates the impact of wind on vehicle driving;

[0091] Get the historical average inventory C h : Indicates inventory status;

[0092] Obtain real-time multi-source data and historical multi-source data for each path respectively, calculate the score of each path through comparative analysis and combining with the path score function, and obtain the minimum path score as the optimal path for logistics transportation;

[0093] The calculation expression of the path score function is:

[0094]

[0095] Where, X c Indicates the value of real-time multi-source data, X h represents the value of the historical average multi-source data, λ represents the preset balance parameter, S(z) represents the score of the zth path, i represents the number of parameters in the multi-source data, z represents the number of paths, σ i represents the variance corresponding to each parameter i, and n represents the maximum number of parameters;

[0096] It should be noted that the score of each path is calculated, and each path score reflects the safety and timeliness of logistics transportation, and the minimum path score corresponds to the best logistics transportation path.

[0097] In S3, based on the optimal transportation path, real-time multi-source data is monitored to assess the risks of current logistics and transportation. Based on the assessment results, the risks are divided into high risk and low risk. Specifically, they include:

[0098] Constructing a Bayesian network model for evaluating the risks of logistics and transportation, specifically including: in the logistics and transportation risk assessment model of the present invention, defining variables including: real-time traffic flow, real-time vehicle speed, real-time precipitation, real-time wind speed, real-time inventory and final target variable risk;

[0099] It should be noted that: since real-time traffic flow directly affects the speed of vehicles, and precipitation and wind speed will jointly affect road safety and vehicle stability, ultimately leading to changes in risk, a directed acyclic graph is constructed through causal analysis to show the relationship between variables.

[0100] Acquire real-time and historical multi-source data. All collected data must be cleaned and preprocessed to remove noise and missing values ​​to ensure data quality and reliability.

[0101] Organize real-time multi-source data and historical multi-source data into a format for Bayesian network analysis, and use maximum likelihood estimation to train the Bayesian network model;

[0102] Using the trained Bayesian network model, the risk probability in the logistics transportation process is calculated based on real-time input of multi-source data;

[0103] According to the risk probability in the logistics transportation process, the probability of the logistics transportation path is calculated, and the calculation expression is:

[0104]

[0105] Where X represents real-time multi-source data, P(Risk|X) represents the probability that the logistics transportation path is at risk given the real-time multi-source data X, P(X|Risk) represents the joint probability distribution of real-time multi-source data under high-risk conditions, P(Risk) represents the preset prior risk probability, and P(X) represents the marginal probability of real-time multi-source data X;

[0106] Among them, the calculation expression of the joint probability distribution is:

[0107]

[0108] In the formula, j represents the number of feature data in multi-source data, m represents the maximum number of feature data, and X j represents the jth feature data in multi-source data, Pa(X j ) represents the parent node set of the jth feature, P(X j |Risk,Pa(X j )) represents the conditional probability of the i-th feature given the risk and parent node;

[0109] The calculated probability P(Risk|X) of risk in the logistics transportation path is compared with the preset threshold;

[0110] If the probability P(Risk|X) of a risk in a logistics transportation path is greater than or equal to the preset threshold, it means that there is a risk in the logistics transportation of the corresponding path, which is recorded as high risk;

[0111] If the probability P(Risk|X) of a risk in a logistics transportation path is less than the preset threshold, it means that the logistics transportation of the corresponding path has a low risk, which is recorded as low risk;

[0112] It should be noted that: since the selected optimal logistics transportation route may be subject to emergencies, corresponding risks will arise. It is necessary to monitor multi-source data in real time and make timely adjustments to the logistics transportation route and logistics transportation.

[0113] In S4, based on the low-risk logistics and transportation process, the current logistics and transportation process is continued, specifically including:

[0114] Based on the low-risk logistics transportation process, the system will monitor multi-source data in real time to ensure that the transportation status remains within a safe range;

[0115] At this point, the road condition data, weather data, and warehouse data are all normal, indicating that material transportation can proceed smoothly;

[0116] Therefore, the transport vehicles will continue to travel along the established routes, and the system will continue to collect and analyze data in order to promptly identify potential risks and make corresponding adjustments.

[0117] In S5, based on the high-risk logistics and transportation process, the specific risk factors are analyzed. According to the specific risk factors, the implementation of alternative solutions includes:

[0118] During the logistics and transportation process, the system monitors multi-source data in real time to identify high-risk factors;

[0119] When real-time multi-source data exceeds the preset safety threshold, the system automatically marks the factor as a high-risk factor and records it;

[0120] The system compares and analyzes real-time data with historical data, calculates the difference between current traffic flow and historical average flow, and evaluates potential transportation threats based on weather conditions;

[0121] For high risks identified, the system will immediately formulate response strategies, including adjusting the transportation route, the driver reducing the speed and increasing the driving distance;

[0122] During the transportation process, the system will dynamically update the driver's travel arrangements;

[0123] During the implementation of alternative plans, the system updates the risk status of drivers and dispatchers in real time through the cloud platform to ensure that they are aware of the latest environmental changes and response measures. Specific real-time updates include the push of real-time vehicle speed, wind speed, road conditions and other information;

[0124] All high-risk events and their treatment measures will be recorded in detail in the system to form a risk analysis report;

[0125] The report will provide a basis for subsequent risk management and logistics planning, including high-risk identification time, influencing factors, treatment measures and effect evaluation.

[0126] See also Figure 2 As shown in the figure, the remote logistics management system based on cloud big data control includes:

[0127] A data acquisition module, which is used to obtain real-time multi-source data during logistics transportation, including: road condition data, weather data and warehouse status data;

[0128] A data comparison and analysis module, which is used to compare and analyze real-time multi-source data with historical multi-source data to identify the best logistics transportation path;

[0129] A path risk assessment module, which monitors real-time multi-source data based on the optimal transportation path, assesses the risks of current logistics transportation, and divides the risks into high risk and low risk according to the assessment results;

[0130] A low-risk path execution module, wherein the low-risk path execution module continues to execute the current logistics transportation process based on the low-risk logistics transportation process;

[0131] The high-risk path processing module analyzes specific risk-causing factors based on the high-risk logistics transportation process and implements alternative plans based on the specific risk-causing factors.

[0132] The working principle of the present invention is to optimize the logistics transportation path and evaluate the transportation risk by acquiring, analyzing and processing multi-source data in the logistics transportation process in real time, so as to improve the safety and efficiency of logistics transportation. The technical solution first obtains real-time data including road conditions, weather and warehouse status through the data acquisition module. These data are collected through the GPS positioning system installed on the transportation vehicle, the external navigation service API, the warehouse management system and the internal sensor and uploaded to the cloud through the 5G network. Subsequently, in the data comparison and analysis module, the system compares and analyzes the multi-source data collected in real time with the historical data, and determines the optimal logistics transportation path by calculating the path score function. Then, based on the selected optimal path, the path risk assessment module uses the Bayesian network model to monitor the real-time multi-source data, evaluate the possible risks in the logistics transportation process, and divide it into high risk or low risk according to the risk assessment results. For low-risk paths, the system continues to execute the current logistics transportation process through the low-risk path execution module; for high-risk paths, the high-risk path processing module analyzes the specific causes of the risk, and formulates and implements corresponding alternative plans based on the analysis results, such as adjusting the transportation route or changing the driver's operating method. During the whole process, the system updates the risk status of drivers and dispatchers in real time, and records all high-risk events and their treatment measures, providing a reference for future risk management and logistics planning. In addition, the present invention also provides corresponding remote logistics management system hardware architecture support to ensure the effective implementation of the above method.

[0133] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0134] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0135] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0136] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0137] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A remote logistics management method based on cloud big data control, characterized in that: The following steps are involved: S1: Obtain real-time multi-source data during logistics transportation, including road condition data, weather data, and warehouse status data; S2: Compare and analyze real-time multi-source data with historical multi-source data to identify the best logistics transportation path; Wherein, the optimal path represents the first selected path in the logistics transportation process; S3: Based on the optimal transportation route, real-time multi-source data is monitored to assess the risks of current logistics and transportation, and the risks are divided into high risk and low risk according to the assessment results; S4: Based on the low-risk logistics and transportation process, continue to execute the current logistics and transportation process; S5: Based on the high-risk logistics and transportation process, analyze the specific risk factors and implement alternative plans based on the specific risk factors.

2. The remote logistics management method based on cloud big data control according to claim 1 is characterized in that: The road condition data, weather data and warehouse status data specifically include: Traffic data includes: traffic flow and real-time vehicle speed; Weather data includes: precipitation and wind speed; Warehouse data includes: inventory.

3. The remote logistics management method based on cloud big data control according to claim 1 is characterized in that: The comparative analysis of real-time multi-source data and historical multi-source data to identify the best logistics transportation path specifically includes: Obtain real-time multi-source data and historical multi-source data for each path respectively, calculate the score of each path through comparative analysis and combining with the path score function, and obtain the minimum path score as the optimal path for logistics transportation; The calculation expression of the path score function is: In the formula, X c Indicates the value of real-time multi-source data, X h represents the value of the historical average multi-source data, λ represents the preset balance parameter, S(z) represents the score of the zth path, i represents the number of parameters in the multi-source data, z represents the number of paths, σ i represents the variance corresponding to each parameter i, and n represents the maximum number of parameters.

4. The remote logistics management method based on cloud big data control according to claim 1 is characterized in that: The monitoring of real-time multi-source data based on the optimal transportation path, the analysis of real-time multi-source data, and the calculation of the risk score of the logistics transportation path specifically include: Using the Bayesian network model, the risk probability in the logistics transportation process is calculated based on real-time input of multi-source data; Calculate the probability of logistics transportation routes based on the risk probability during logistics transportation; Among them, the calculation expression of the probability of the logistics transportation path is: Where X represents real-time multi-source data, P(Risk|X) represents the probability that the logistics transportation path is at risk given the real-time multi-source data X, P(X|Risk) represents the joint probability distribution of real-time multi-source data under high-risk conditions, P(Risk) represents the preset prior risk probability, and P(X) represents the marginal probability of real-time multi-source data X.

5. The remote logistics management method based on cloud big data control according to claim 4 is characterized in that: The calculation expression of the joint probability distribution is: In the formula, j represents the number of feature data in the multi-source data, m represents the maximum number of feature data, and X j represents the jth feature data in multi-source data, Pa(X j ) represents the parent node set of the jth feature, P(X j |Risk,Pa(X j )) represents the conditional probability of the i-th feature given the risk and the parent node.

6. The remote logistics management method based on cloud big data control according to claim 4 is characterized in that: The Bayesian network model, the specific training process includes: In the logistics and transportation risk assessment model of the present invention, the defined variables include: Real-time traffic flow, real-time vehicle speed, real-time precipitation, real-time wind speed, real-time inventory and the final target variable risk; Through causal analysis, a directed acyclic graph is constructed to show the relationship between variables; Obtain real-time and historical multi-source data; Real-time multi-source data and historical multi-source data are organized into a format for Bayesian network analysis, and the Bayesian network model is trained using maximum likelihood estimation.

7. The remote logistics management method based on cloud big data control according to claim 1 is characterized in that: The assessment of the risks in current logistics and transportation specifically includes: Determine whether the probability of risk in the logistics transportation route is greater than or equal to the preset threshold. If so, it is recorded as high risk, otherwise it is recorded as low risk.

8. The remote logistics management method based on cloud big data control according to claim 1 is characterized in that: Based on the high-risk logistics and transportation process, analyze the specific risk factors, including: If real-time multi-source data exceeds the preset safety threshold, the system automatically marks the factor as a high-risk factor and records it; The system compares and analyzes real-time data with historical data, calculates the difference between current traffic flow and historical average flow, and evaluates potential transportation threats based on weather conditions.

9. The remote logistics management method based on cloud big data control according to claim 1 is characterized in that: The implementation of alternative plans based on specific factors includes: For high risks identified, the system will immediately formulate response strategies, including adjusting the transportation route, the driver reducing the speed and increasing the driving distance; During the transportation process, the system will dynamically update the driver's travel arrangements; During the implementation of alternative plans, the system updates the risk status of drivers and dispatchers in real time through the cloud platform to ensure that they are aware of the latest environmental changes and response measures. Specific real-time updates include the push of real-time vehicle speed, wind speed, road conditions and other information; All high-risk events and their handling measures will be recorded in detail in the system to form a risk analysis report, which will include high-risk identification time, influencing factors and handling measures.

10. A remote logistics management system based on cloud big data control, characterized in that: A remote logistics management method based on cloud big data control as claimed in any one of claims 1 to 9, comprising: A data acquisition module, which is used to obtain real-time multi-source data during logistics transportation, including: road condition data, weather data and warehouse status data; A data comparison and analysis module, which is used to compare and analyze real-time multi-source data with historical multi-source data to identify the best logistics transportation path; A path risk assessment module, which monitors real-time multi-source data based on the optimal transportation path, assesses the risks of current logistics transportation, and divides the risks into high risk and low risk according to the assessment results; A low-risk path execution module, wherein the low-risk path execution module continues to execute the current logistics transportation process based on the low-risk logistics transportation process; The high-risk path processing module analyzes specific risk-causing factors based on the high-risk logistics transportation process and implements alternative plans based on the specific risk-causing factors.

Images