A real-time control method and system for logistics data changes

Abstract

The present invention proposes a real-time control method and system for logistics data changes, wherein the method includes: setting a route number for each route in the logistics route network, obtaining historical road use information and current road use information according to the route number; predicting road use information for future time periods according to the historical road use information and the current road use information, screening out route numbers with changed road use information, and obtaining the route of the driver who needs to change the route according to the route number with changed road use information; obtaining the transport cargo attributes of the driver who needs to change the route, and calculating the scores of all reachable routes according to the transport cargo attributes; selecting the changed route for the driver according to the scores of the reachable routes and the probabilistic decision-making mechanism. Through this method and the corresponding system, the route can be dynamically optimized according to the cargo attributes, the flexible response capability of the logistics network can be enhanced, excessive concentration on a certain optimal route can be avoided, and the risk of congestion can be reduced.

Description

Technical Field

[0001] The present invention proposes a real-time control method and system for logistics data changes, and relates to the field of logistics. Background Art

[0002] In today's rapidly developing global market, effective logistics management is a key factor in ensuring the smooth operation of the supply chain. With the prosperity of e-commerce and the increase in international trade, the logistics industry faces unprecedented challenges, especially in how to respond to changes in logistics data in real time. Therefore, it is crucial to develop a method for real-time regulation of logistics data changes.

[0003] However, the existing real-time control of logistics data changes notifies the driver to change the route when it is found that the route the driver is currently going to take is congested. However, the current congestion does not mean that the road will still be congested when the driver takes it. It cannot respond to road changes in real time, or all routes are selected according to one goal regardless of the attributes of the goods transported by the driver. Or when it is found that the road information of the original route has changed, the route is changed. At this time, the originally non-congested route will become congested due to the route change of a large number of vehicles. Summary of the invention

[0004] The present invention provides a method and system for real-time control of logistics data changes to solve the above-mentioned problems:

[0005] The present invention proposes a method for real-time control of logistics data changes, the method comprising:

[0006] Setting a route number for each route in the logistics route network, and obtaining historical road usage information and current road usage information according to the route number;

[0007] Predicting road usage information in a future time period based on the historical road usage information and the current road usage information, screening out route numbers for which the road usage information has changed, and obtaining a driver route that needs to be changed based on the route number for which the road usage information has changed;

[0008] Obtaining the transport cargo attributes of the driver who needs to change the route, and calculating the scores of all accessible routes according to the transport cargo attributes;

[0009] The altered route is chosen for the driver based on the scores of the achievable routes and a probabilistic decision-making mechanism.

[0010] Furthermore, a route number is set for each route in the logistics route network, and historical road use information and current road use information are obtained according to the route number, including:

[0011] Mapping all routes in the logistics route network, wherein the mapping indicates the starting point, the passing point and the end point of each route, and assigning a unique route number to each mapped route;

[0012] Obtaining historical road usage information of each numbered route, the historical road usage information including average vehicle speed and traffic density, storing the acquired historical road information in a database, and establishing an index and search optimization;

[0013] The road traffic conditions are monitored in real time through GPS tracking, traffic cameras and road surface sensors to obtain current road usage information, wherein the current road usage information includes average vehicle speed and traffic density.

[0014] Further, predicting the road usage information of a future time period based on the historical road usage information and the current road usage information, screening out the route numbers of the changed road usage information, and obtaining the driver route that needs to change the route based on the route numbers of the changed road usage information, including:

[0015] Predicting road usage information in a future time period based on the historical road usage information and the current road usage information through deep learning;

[0016] Unifying the formats of the data of historical road use information and the data of future road use information, wherein the formats include time format, speed unit and measurement unit of traffic density, and cleaning the data after the formats are unified;

[0017] Use JOIN query in SQL to match the historical road usage data and future road usage data of the routes in the logistics route network, and make comparisons and judgments based on the preset thresholds to filter out the route numbers whose road usage information will change in the future time period;

[0018] Get the route of the driver who needs to change the route according to the route number where the road use information has changed.

[0019] Furthermore, the transport cargo attributes of the driver who needs to change the route are obtained, and the scores of all accessible routes are calculated according to the transport cargo attributes, including:

[0020] Obtaining the attributes of the cargo transported by the driver who needs to change the route, wherein the cargo attributes include: general cargo, refrigerated cargo, fragile cargo, and dangerous cargo;

[0021] Map the logistics route network into a graph, and use the depth-first algorithm to enumerate all the accessible routes from the current location of the driver who needs to change the route to the destination;

[0022] The scores of all accessible routes are calculated by re-planning the route model.

[0023] Specifically, the re-route model is:

[0024]

[0025]

[0026] Where n is the number of sections in the reachable route, T i is the predicted time to pass through section i, L is the longest acceptable transportation time to pass through section i, R i is the flatness of road section i, C i is the average speed of section i, C max is the maximum average speed among the average speeds of all road sections, α(D), β(D), γ(D) and δ(D) are weight functions adjusted according to the cargo attribute D, P i is the traffic density of road section i, f(T i ) is a function of Ti, and M is the maximum traffic density among the traffic densities of all road sections.

[0027] Furthermore, a changed route is selected for the driver based on the score of the accessible route and the probabilistic decision-making mechanism, including:

[0028] The route with the highest score is selected as the optimal route, and the optimal route is denoted as j opt , the routes with the next highest scores are selected as candidate routes, and the candidate routes are denoted as j alt1 , j alt2 , …;

[0029] Calculate a selection probability for each route (including the optimal route and alternative routes). Specifically,

[0030] The probability of selecting the optimal route is:

[0031]

[0032] in, is the score of the optimal route, is the sum of the scores of all considered routes;

[0033] The probability of selecting an alternative route is:

[0034]

[0035] Among them, the value range of reduction_factor is (0,1);

[0036] Generate a random number r belonging to (0,1). If r is less than or equal to the probability of the optimal route being selected, then select the optimal route;

[0037] If r is greater than the probability of the optimal route being selected, the cumulative probability is used to check whether r falls within the selection probability range of a certain alternative route. If it falls within the selection probability range of a certain alternative route, the alternative route is selected.

[0038] The present invention proposes a real-time control system for logistics data changes, the system comprising:

[0039] An information acquisition module, used to set a route number for each route in the logistics route network, and acquire historical road use information and current road use information according to the route number;

[0040] A module for predicting and obtaining routes that need to be changed is used to predict the road usage information in a future time period based on the historical road usage information and the current road usage information, filter out route numbers whose road usage information has changed, and obtain the driver's route that needs to be changed based on the route numbers whose road usage information has changed;

[0041] A scoring calculation module is used to obtain the transport cargo attributes of the driver who needs to change the route, and calculate the scores of all accessible routes based on the transport cargo attributes;

[0042] The route change selection module is used to select a changed route for the driver based on the scores of the accessible routes and a probabilistic decision-making mechanism.

[0043] Furthermore, the information acquisition module includes:

[0044] A route mapping module, used to map all routes in the logistics route network, wherein the mapping indicates the starting point, the passing point and the end point of each route, and assigns a unique route number to each mapped route;

[0045] A module for obtaining historical road use information is used to obtain historical road use information of each numbered route, wherein the historical road use information includes average vehicle speed and traffic density, and the obtained historical road information is stored in a database to establish an index and search optimization;

[0046] The module for obtaining current road usage information is used to obtain current road usage information by real-time monitoring of road traffic conditions through GPS tracking, traffic cameras and road surface sensors. The current road usage information includes average vehicle speed and traffic density.

[0047] Furthermore, the module for predicting and obtaining routes that need to be changed includes:

[0048] A future road usage information prediction module, configured to predict the road usage information in a future time period based on the historical road usage information and the current road usage information through deep learning;

[0049] A format unification and cleaning module, used to unify the formats of the data of historical road use information and the data of future road use information, wherein the formats include time format, speed unit and measurement unit of traffic density, and clean the data after the formats are unified;

[0050] The screening module is used to use JOIN query in SQL to match the historical road usage data and future road usage data of the routes in the logistics route network, and compare and judge according to the preset threshold to screen out the route numbers whose road usage information will change in the future time period;

[0051] The module for obtaining the route of drivers who need to change the route is used to obtain the route of drivers who need to change the route according to the route number of the changed road use information.

[0052] Furthermore, the score calculation module includes:

[0053] A module for obtaining transport cargo attributes is used to obtain the transport cargo attributes of the driver who needs to change the route, and the cargo attributes include: general cargo, refrigerated cargo, fragile cargo and dangerous cargo;

[0054] The module for enumerating accessible routes is used to map the logistics route network into a graph and enumerate all accessible routes from the current location of the driver who needs to change the route to the destination through a depth-first algorithm;

[0055] The module for calculating the score of accessible routes is used to calculate the scores of all accessible routes by replanning the route model.

[0056] Specifically, the re-route model is:

[0057]

[0058]

[0059] Where n is the number of sections in the reachable route, T i is the predicted time to pass through section i, L is the longest acceptable transportation time to pass through section i, R i is the flatness of road section i, C i is the average speed of section i, C max is the maximum average speed among the average speeds of all road sections, α(D), β(D), γ(D) and δ(D) are weight functions adjusted according to the cargo attribute D, P i is the traffic density of road section i, f(T i ) is a function of Ti, and M is the maximum traffic density among the traffic densities of all road sections.

[0060] Further, the route change module includes:

[0061] The consideration route module is used to select the route with the highest score as the optimal route, and the optimal route is denoted as j opt , the routes with the next highest scores are selected as candidate routes, and the candidate routes are denoted as j alt1 , j alt2 , …;

[0062] The selection probability calculation module is used to calculate a selection probability for each route (including the optimal route and the alternative routes). Specifically,

[0063] The probability of selecting the optimal route is:

[0064]

[0065] in, is the score of the optimal route, is the sum of the scores of all considered routes,

[0066] The probability of selecting an alternative route is:

[0067]

[0068] Among them, the value range of reduction_factor is (0,1);

[0069] Based on the random number selection module, it is used to generate a random number r belonging to (0,1). If r is less than or equal to the selection probability of the optimal route, the optimal route is selected. If r is greater than the selection probability of the optimal route, the cumulative probability is used to check whether r falls within the selection probability range of a certain alternative route. If it falls within the selection probability range of a certain alternative route, the alternative route is selected.

[0070] The beneficial effects of the present invention are as follows: improving response efficiency, real-time monitoring and prediction of road usage, rapid response to necessary route adjustments, reducing waiting and delays, and improving overall transportation efficiency; optimizing resource allocation, precise route management and intelligent adjustment can help logistics companies better allocate transportation resources and reduce operating costs; the system can dynamically optimize routes according to different cargo attributes, and enhance the adaptability and flexible response capabilities of the logistics network to different situations; more punctual cargo arrival and high-quality services improve end-user satisfaction, which is conducive to the building of corporate reputation and the improvement of market competitiveness; through this comprehensive technical solution, smarter, more efficient and safer transportation management can be achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] Figure 1 A schematic diagram of a real-time control method for logistics data changes described in the present invention. DETAILED DESCRIPTION

[0072] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0073] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. The embodiments described are only a part of the embodiments of the present invention, rather than 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.

[0074] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0075] One embodiment of the present invention provides a method for real-time control of logistics data changes, the method comprising:

[0076] Setting a route number for each route in the logistics route network, and obtaining historical road usage information and current road usage information according to the route number;

[0077] Predicting road usage information in a future time period based on the historical road usage information and the current road usage information, screening out route numbers for which the road usage information has changed, and obtaining a driver route that needs to be changed based on the route number for which the road usage information has changed;

[0078] Obtaining the transport cargo attributes of the driver who needs to change the route, and calculating the scores of all accessible routes according to the transport cargo attributes;

[0079] The altered route is chosen for the driver based on the scores of the achievable routes and a probabilistic decision-making mechanism.

[0080] The working principle and effect of the above technical solution are as follows: set a specific number for each route in the logistics network, so that the tracking and information management of the route become systematic and standardized; through these numbers, the system can record and analyze the historical usage and current usage of each route; use historical road usage information and current road conditions to predict road usage in a certain time period in the future; identify those routes that will undergo changes by comparing the prediction results with preset thresholds; screen out the affected routes, score each optional route according to the properties of the goods transported by the driver (such as whether it is fragile, requires refrigeration, or is it dangerous goods, etc.), and use a probabilistic decision-making mechanism to select the most suitable new route for the driver. Improve response efficiency, monitor and predict road usage in real time, respond quickly to necessary route adjustments, reduce waiting and delays, and improve overall transportation efficiency; optimize resource allocation, precise route management and intelligent adjustments can help logistics companies better allocate transportation resources and reduce operating costs; the system can dynamically optimize routes according to different cargo attributes, and enhance the adaptability and flexible response capabilities of the logistics network to different situations; more punctual cargo arrival and high-quality services improve end-user satisfaction, which is conducive to the building of corporate reputation and the improvement of market competitiveness; through this comprehensive technical solution, smarter, more efficient and safer transportation management can be achieved.

[0081] One embodiment of the present invention is a method for real-time control of logistics data changes, which sets a route number for each route in a logistics route network, and obtains historical road use information and current road use information according to the route number, including:

[0082] Mapping all routes in the logistics route network, wherein the mapping indicates the starting point, the passing point and the end point of each route, and assigning a unique route number to each mapped route;

[0083] Obtaining historical road usage information of each numbered route, the historical road usage information including average vehicle speed and traffic density, storing the acquired historical road information in a database, and establishing an index and search optimization;

[0084] The road traffic conditions are monitored in real time through GPS tracking, traffic cameras and road surface sensors to obtain current road usage information, wherein the current road usage information includes average vehicle speed and traffic density.

[0085] The working principle and effect of the above technical solution are as follows: first, the entire logistics route network is mapped in detail to clarify the starting point, waypoint and end point of each route; after the mapping is completed, a unique number is assigned to each route for subsequent management, tracking and data analysis; according to the route number, the historical road usage information of each route is collected, which mainly includes the average vehicle speed and traffic density; these data are stored in the database, and an efficient indexing and search optimization mechanism is established to facilitate fast query and analysis; GPS tracking technology, traffic cameras, road surface sensors and other means are used to monitor road traffic conditions in real time. The real-time monitoring data also includes the average vehicle speed and traffic density, which reflect the current usage of the road. Improve logistics efficiency. Through detailed mapping and numbering of logistics route networks, logistics companies can have a clearer understanding of the entire transportation network, optimize transportation routes, and thus improve logistics efficiency. The collection and storage of historical road usage information provides logistics companies with rich data resources, which can be used to analyze the changing trends of road traffic conditions and provide support for logistics decision-making. The function of real-time monitoring of road traffic conditions enables logistics companies to adjust transportation plans in a timely manner according to actual conditions, avoid congested sections, and reduce transportation delays. Accurate logistics information and timely adjustment capabilities help improve the punctuality of transportation, thereby improving customer satisfaction. Through the analysis of historical data and real-time data, companies can predict and evaluate potential risks, such as traffic congestion, accident-prone sections, etc., and take corresponding risk management measures. In summary, this technical solution provides logistics companies with a comprehensive and efficient road traffic information management solution through the comprehensive use of route mapping, data collection, and real-time monitoring, which helps to improve logistics efficiency and customer satisfaction and reduce operational risks.

[0086] An embodiment of the present invention is a method for real-time control of logistics data changes, which predicts road usage information in a future time period based on the historical road usage information and the current road usage information, screens out route numbers where the road usage information has changed, and obtains the driver route that needs to change the route based on the route number where the road usage information has changed, including:

[0087] Predicting road usage information in a future time period based on the historical road usage information and the current road usage information through deep learning;

[0088] Unifying the formats of the data of historical road use information and the data of future road use information, wherein the formats include time format, speed unit and measurement unit of traffic density, and cleaning the data after the formats are unified;

[0089] Use JOIN query in SQL to match the historical road usage data and future road usage data of the routes in the logistics route network, and make comparisons and judgments based on the preset thresholds to filter out the route numbers whose road usage information will change in the future time period;

[0090] Get the route of the driver who needs to change the route according to the route number where the road use information has changed.

[0091] A threshold value can be set for the average vehicle speed (such as a speed change of more than 10%). When the current vehicle speed drops by more than this threshold compared with the historical vehicle speed, it is considered that the road condition has changed significantly. A threshold value for density change (such as an increase of 20%) is also set for traffic density to determine significant changes in traffic density.

[0092] In SQL, you can use JOIN query to match the historical data of a specific line number with the future forecast data, and compare and judge based on the set threshold. Specifically, the code is as follows:

[0093] SELECT

[0094] H.line_id,

[0095] H.avg_speed as historical_speed,

[0096] R.avg_speed as real_time_speed,

[0097] H.traffic_density as historical_density,

[0098] R.traffic_density as real_time_density

[0099] FROM

[0100] historical_data H

[0101] JOIN

[0102] real_time_dataRONH.line_id=R.line_id

[0103] WHERE

[0104] ABS(H.avg_speed-R.avg_speed) / H.avg_speed>0.1

[0105] ORABS(H.traffic_density-R.traffic_density)>20

[0106] The working principle and effect of the above technical solution are as follows: using deep learning technology, combining historical road use information and current road use information, constructing a prediction model to predict road use information in future time periods, which may include key indicators such as average vehicle speed and traffic density; in order to ensure data consistency and accuracy, the historical data and predicted future data are formatted in a unified manner, including time format, speed unit and measurement unit of traffic density; outliers are removed and missing values ​​are filled in the data cleaning process to ensure data quality; in the SQL database, JOIN queries are used to associate historical road use data of routes in the logistics route network with predicted future road use data; by setting preset thresholds, comparing historical data and predicted data, and screening out route numbers whose road use information may change in the future time period (such as significant changes in traffic conditions); based on the screened route numbers, identifying which drivers' routes may be affected and need to be adjusted; changing routes for these drivers to avoid potential traffic congestion or delays. Through deep learning technology, it is possible to accurately predict road usage information in future time periods, providing logistics companies with foresight into traffic conditions; the unification and cleaning of data formats ensures the accuracy and consistency of data, providing a reliable basis for subsequent data analysis and decision-making; through SQL queries and comparisons of preset thresholds, the system can automatically screen out routes that may be affected by traffic changes, providing intelligent decision-making support for timely adjustment of transportation routes; with improved efficiency and flexibility, logistics companies can flexibly adjust transportation plans based on predicted road usage information, avoid congested sections, and improve transportation efficiency; by reducing delays and congestion during transportation, fuel consumption and vehicle maintenance costs can be reduced, thereby saving costs for the company; accurate predictions and timely route adjustments help ensure that goods are delivered on time and improve customer satisfaction; through deep learning predictions, data format unification and cleaning, SQL data matching and comparison, and intelligent route adjustment decisions, this technical solution provides logistics companies with a comprehensive solution that can improve transportation efficiency, reduce costs, and improve customer satisfaction.

[0107] One embodiment of the present invention is a real-time control method for logistics data changes, which obtains the transport cargo attributes of a driver who needs to change the route, and calculates the scores of all accessible routes according to the transport cargo attributes, including:

[0108] Obtaining the attributes of the cargo transported by the driver who needs to change the route, wherein the cargo attributes include: general cargo, refrigerated cargo, fragile cargo, and dangerous cargo;

[0109] Map the logistics route network into a graph, and use the depth-first algorithm to enumerate all the accessible routes from the current location of the driver who needs to change the route to the destination;

[0110] The scores of all accessible routes are calculated by re-planning the route model.

[0111] Specifically, the re-route model is:

[0112]

[0113]

[0114] Where n is the number of sections in the reachable route, T i is the predicted time to pass through section i, L is the longest acceptable transportation time to pass through section i, R i is the flatness of road section i (1 means very flat, 10 means very bumpy), C i is the average speed of section i, C max is the maximum average speed among the average speeds of all road sections, α(D), β(D), γ(D) and δ(D) are weight functions adjusted according to the cargo attribute D, P i is the traffic density of road section i, f(T i ) is a function of Ti, M is the maximum traffic density among the traffic densities of all road sections, α(D), β(D), γ(D) and δ(D) are weight functions determined according to the cargo attribute D.

[0115] For example, the following weight function can be defined: for refrigerated goods (D=1), the speed weight α is expected to be higher because fast transportation is required. α(1)=0.6, β(1)=0.2, γ(1)=0.1, δ1=0.1 can be set (giving importance to the speed factor).

[0116] For fragile goods (D=2), we hope that the flatness weight β is higher to ensure the safety of the goods. We can set α(2)=0.2, β(2)=0.6, γ(2)=0.1, δ2=0.1 (paying more attention to the flatness of the road surface).

[0117] For dangerous goods (D = 3), we hope that the traffic density δ is higher to ensure the safety of the goods. We can set α(3) = 0.2, β(3) = 0.1, γ(3) = 0.1, and δ3 = 0.6 (focusing on traffic density). By adjusting the weights in this way, we can ensure that the scoring function can optimize the route selection according to the characteristics of different goods.

[0118] For goods that are very time-sensitive (D = 4), that is, we need to ensure that the goods arrive on time, and we hope that the time factor γ is higher to ensure that they arrive on time, we can set α(4) = 0.2, β(3) = 0.1, γ(3) = 0.6, δ3 = 0.1 (emphasis on the time factor). Through such weight adjustment, we can ensure that the scoring function can optimize the route selection according to the characteristics of different goods.

[0119] The working principle and effect of the above technical solution are as follows: the re-routing model takes into account multiple key factors affecting route selection, and adjusts the influence of each factor in the total score through a weight function. The weight functions α(D), β(D), γ(D), and δ(D) in the formula can be adjusted according to the cargo attribute D, which means that different priorities can be flexibly set for different types of cargo. For example, for refrigerated goods that need to be transported quickly, the weight of the time factor can be increased; for fragile goods, the road surface flatness is more important; the formula comprehensively considers the average speed (C i), cargo attributes (D), safety standards (reflected by flatness Ri and traffic density Pi) and the longest acceptable transportation time (L). This comprehensive evaluation method helps to select a transportation route that is both fast and safe; by adjusting weights and parameters, the formula can be easily adapted to different transportation needs and scenarios. This customizability makes the formula highly practical; the various parameters in the formula (such as congestion index, flatness, population density, etc.) can be obtained and updated through real-time data. This makes route selection more dynamic and accurate, and can make the best decision based on actual conditions.

[0120] One embodiment of the present invention is a real-time control method for logistics data changes, which selects a changed route for a driver based on the score of a reachable route and a probabilistic decision-making mechanism, including:

[0121] The route with the highest score is selected as the optimal route, and the optimal route is denoted as j opt , the routes with the next highest scores are selected as candidate routes, and the candidate routes are denoted as j alt1 , j alt2 , …;

[0122] Calculate a selection probability for each route (including the optimal route and alternative routes). Specifically,

[0123] The probability of selecting the optimal route is:

[0124]

[0125] in, is the score of the optimal route, is the sum of the scores of all considered routes;

[0126] The probability of selecting an alternative route is:

[0127]

[0128] Among them, the value range of reduction_factor is (0,1);

[0129] Generate a random number r belonging to (0,1). If r is less than or equal to the probability of the optimal route being selected, then select the optimal route;

[0130] If r is greater than the probability of the optimal route being selected, the cumulative probability is used to check whether r falls within the selection probability range of a certain alternative route. If it falls within the selection probability range of a certain alternative route, the alternative route is selected.

[0131] When a route needs to be selected, the system generates a random number r between 0 and 1. Then, the selection is made as follows:

[0132] If r is less than the selection probability of the optimal route, the optimal route is selected.

[0133] If r is greater than or equal to , check whether it falls within the selection probability range of some alternative route. This is usually done by summing the probabilities. For example, if is 0.6, is 0.2 (assuming reduction_factor is 1, just for illustration), is 0.1, then:

[0134] If r is between 0.6 and 0.8 (0.6+0.2), then jalt1 is selected.

[0135] If r is between 0.8 and 0.9 (0.6+0.2+0.1), choose jalt2.

[0136] If r is greater than 0.9, you may need to regenerate r or choose a different route that was not considered (depending on the implementation).

[0137] In this way, even if the optimal route is the highest in terms of score, there is a chance that an alternative route will be chosen due to randomness, thus helping to disperse the traffic and reduce the risk of congestion.

[0138] The working principle and effect of the above technical solution are as follows: Traditional route planning usually focuses on selecting the optimal route, while ignoring the congestion problem caused by all vehicles choosing the same route at the same time. By introducing probabilistic decision-making, the method breaks this deterministic selection mode, increases the flexibility and robustness of the system, and dynamically weighs the optimal and alternative routes. This method not only considers the optimal route, but also considers the alternative routes at the same time, and dynamically weighs their choices through probability. This dynamic selection mechanism helps to avoid excessive concentration on a certain optimal route, thereby reducing the risk of congestion; adjustable selection tendency, by introducing reduction_factor, the method allows the tendency to select alternative routes to be adjusted according to actual conditions. This flexibility enables the method to better adapt to different traffic conditions and needs; comprehensive consideration of multiple factors: In the original scoring formula, multiple aspects such as cost, risk, time and penalty factors have been comprehensively considered. By combining this scoring formula with the probabilistic selection mechanism, the method can more comprehensively evaluate the pros and cons of different routes and make more reasonable decisions. ; By introducing a probabilistic decision-making mechanism, dynamically weighing optimal and alternative routes, adjustable selection preferences, and comprehensively considering multiple factors, this method is expected to improve the efficiency and stability of the transportation system and reduce the occurrence of congestion in practical applications.

[0139] One embodiment of the present invention provides a real-time control system for logistics data changes, the system comprising:

[0140] An information acquisition module, used to set a route number for each route in the logistics route network, and acquire historical road use information and current road use information according to the route number;

[0141] A module for predicting and obtaining routes that need to be changed is used to predict the road usage information in a future time period based on the historical road usage information and the current road usage information, filter out route numbers whose road usage information has changed, and obtain the driver's route that needs to be changed based on the route numbers whose road usage information has changed;

[0142] A scoring calculation module is used to obtain the transport cargo attributes of the driver who needs to change the route, and calculate the scores of all accessible routes based on the transport cargo attributes;

[0143] The route change selection module is used to select a changed route for the driver based on the scores of the accessible routes and a probabilistic decision-making mechanism.

[0144] The working principle and effect of the above technical solution are as follows: set a specific number for each route in the logistics network, so that the tracking and information management of the route become systematic and standardized; through these numbers, the system can record and analyze the historical usage and current usage of each route; use historical road usage information and current road conditions to predict road usage in a certain time period in the future; identify those routes that will undergo changes by comparing the prediction results with preset thresholds; screen out the affected routes, score each optional route according to the properties of the goods transported by the driver (such as whether it is fragile, requires refrigeration, or is it dangerous goods, etc.), and use a probabilistic decision-making mechanism to select the most suitable new route for the driver. Improve response efficiency, monitor and predict road usage in real time, respond quickly to necessary route adjustments, reduce waiting and delays, and improve overall transportation efficiency; optimize resource allocation, precise route management and intelligent adjustments can help logistics companies better allocate transportation resources and reduce operating costs; the system can dynamically optimize routes according to different cargo attributes, and enhance the adaptability and flexible response capabilities of the logistics network to different situations; more punctual cargo arrival and high-quality services improve end-user satisfaction, which is conducive to the building of corporate reputation and the improvement of market competitiveness; through this comprehensive technical solution, smarter, more efficient and safer transportation management can be achieved.

[0145] In one embodiment of the present invention, a real-time control system for logistics data changes is provided, wherein the information acquisition module comprises:

[0146] A route mapping module, used to map all routes in the logistics route network, wherein the mapping indicates the starting point, the passing point and the end point of each route, and assigns a unique route number to each mapped route;

[0147] A module for obtaining historical road use information is used to obtain historical road use information of each numbered route, wherein the historical road use information includes average vehicle speed and traffic density, and the obtained historical road information is stored in a database to establish an index and search optimization;

[0148] The module for obtaining current road usage information is used to obtain current road usage information by real-time monitoring of road traffic conditions through GPS tracking, traffic cameras and road surface sensors. The current road usage information includes average vehicle speed and traffic density.

[0149] The working principle and effect of the above technical solution are as follows: first, the entire logistics route network is mapped in detail to clarify the starting point, waypoint and end point of each route; after the mapping is completed, a unique number is assigned to each route for subsequent management, tracking and data analysis; according to the route number, the historical road usage information of each route is collected, which mainly includes the average vehicle speed and traffic density; these data are stored in the database, and an efficient indexing and search optimization mechanism is established to facilitate fast query and analysis; GPS tracking technology, traffic cameras, road surface sensors and other means are used to monitor road traffic conditions in real time. The real-time monitoring data also includes the average vehicle speed and traffic density, which reflect the current usage of the road. Improve logistics efficiency. Through detailed mapping and numbering of logistics route networks, logistics companies can have a clearer understanding of the entire transportation network, optimize transportation routes, and thus improve logistics efficiency. The collection and storage of historical road usage information provides logistics companies with rich data resources, which can be used to analyze the changing trends of road traffic conditions and provide support for logistics decision-making. The function of real-time monitoring of road traffic conditions enables logistics companies to adjust transportation plans in a timely manner according to actual conditions, avoid congested sections, and reduce transportation delays. Accurate logistics information and timely adjustment capabilities help improve the punctuality of transportation, thereby improving customer satisfaction. Through the analysis of historical data and real-time data, companies can predict and evaluate potential risks, such as traffic congestion, accident-prone sections, etc., and take corresponding risk management measures. In summary, this technical solution provides logistics companies with a comprehensive and efficient road traffic information management solution through the comprehensive use of route mapping, data collection, and real-time monitoring, which helps to improve logistics efficiency and customer satisfaction and reduce operational risks.

[0150] In one embodiment of the present invention, a real-time control system for logistics data changes is provided, wherein the module for predicting and obtaining routes that need to be changed includes:

[0151] A future road usage information prediction module, configured to predict the road usage information in a future time period based on the historical road usage information and the current road usage information through deep learning;

[0152] A format unification and cleaning module, used to unify the formats of the data of historical road use information and the data of future road use information, wherein the formats include time format, speed unit and measurement unit of traffic density, and clean the data after the formats are unified;

[0153] The screening module is used to use JOIN query in SQL to match the historical road usage data and future road usage data of the routes in the logistics route network, and compare and judge according to the preset threshold to screen out the route numbers whose road usage information will change in the future time period;

[0154] The module for obtaining the route of drivers who need to change the route is used to obtain the route of drivers who need to change the route according to the route number of the changed road use information.

[0155] The working principle and effect of the above technical solution are as follows: using deep learning technology, combining historical road use information and current road use information, constructing a prediction model to predict road use information in future time periods, which may include key indicators such as average vehicle speed and traffic density; in order to ensure data consistency and accuracy, the historical data and predicted future data are formatted in a unified manner, including time format, speed unit and measurement unit of traffic density; outliers are removed and missing values ​​are filled in the data cleaning process to ensure data quality; in the SQL database, JOIN queries are used to associate historical road use data of routes in the logistics route network with predicted future road use data; by setting preset thresholds, comparing historical data and predicted data, and screening out route numbers whose road use information may change in the future time period (such as significant changes in traffic conditions); based on the screened route numbers, identifying which drivers' routes may be affected and need to be adjusted; changing routes for these drivers to avoid potential traffic congestion or delays. Through deep learning technology, it is possible to accurately predict road usage information in future time periods, providing logistics companies with foresight into traffic conditions; the unification and cleaning of data formats ensures the accuracy and consistency of data, providing a reliable basis for subsequent data analysis and decision-making; through SQL queries and comparisons of preset thresholds, the system can automatically screen out routes that may be affected by traffic changes, providing intelligent decision-making support for timely adjustment of transportation routes; with improved efficiency and flexibility, logistics companies can flexibly adjust transportation plans based on predicted road usage information, avoid congested sections, and improve transportation efficiency; by reducing delays and congestion during transportation, fuel consumption and vehicle maintenance costs can be reduced, thereby saving costs for the company; accurate predictions and timely route adjustments help ensure that goods are delivered on time and improve customer satisfaction; through deep learning predictions, data format unification and cleaning, SQL data matching and comparison, and intelligent route adjustment decisions, this technical solution provides logistics companies with a comprehensive solution that can improve transportation efficiency, reduce costs, and improve customer satisfaction.

[0156] In one embodiment of the present invention, a real-time control system for logistics data changes is provided, wherein the scoring calculation module comprises:

[0157] A module for obtaining transport cargo attributes is used to obtain the transport cargo attributes of the driver who needs to change the route, and the cargo attributes include: general cargo, refrigerated cargo, fragile cargo and dangerous cargo;

[0158] The module for enumerating accessible routes is used to map the logistics route network into a graph and enumerate all accessible routes from the current location of the driver who needs to change the route to the destination through a depth-first algorithm;

[0159] The module for calculating the score of accessible routes is used to calculate the scores of all accessible routes by replanning the route model.

[0160] Specifically, the re-route model is:

[0161]

[0162]

[0163] Where n is the number of sections in the reachable route, T i is the predicted time to pass through section i, L is the longest acceptable transportation time to pass through section i, R i is the flatness of road section i (1 means very flat, 10 means very bumpy), C i is the average speed of section i, C max is the maximum average speed among the average speeds of all road sections, ɑ(D), β(D), γ(D) and δ(D) are weight functions adjusted according to the cargo attribute D, P i is the traffic density of road section i, f(T i ) is a function of Ti, and M is the maximum traffic density among the traffic densities of all road sections. α(D), β(D), γ(D), and δ(D) are weight functions determined according to the cargo attribute D. For example, the following weight function can be defined: For refrigerated goods (D = 1), it is hoped that the speed weight α is higher because fast transportation is required. α(1) = 0.6, β(1) = 0.2, γ(1) = 0.1, δ(1) = 0.1 (focusing on the speed factor).

[0164] For fragile goods (D=2), we hope that the flatness weight β is higher to ensure the safety of the goods. We can set α(2)=0.2, β(2)=0.6, γ(2)=0.1, δ(2)=0.1 (emphasis on road surface flatness).

[0165] For dangerous goods (D = 3), we hope that the traffic density δ is higher to ensure the safety of the goods. We can set α(3) = 0.2, β(3) = 0.1, γ(3) = 0.1, and δ3 = 0.6 (focusing on traffic density). By adjusting the weights in this way, we can ensure that the scoring function can optimize the route selection according to the characteristics of different goods.

[0166] For goods that are very time-sensitive (D = 4), that is, we need to ensure that the goods arrive on time, and we hope that the time factor γ is higher to ensure that they arrive on time, we can set α(4) = 0.2, β(3) = 0.1, γ(3) = 0.6, δ3 = 0.1 (emphasis on the time factor). Through such weight adjustment, we can ensure that the scoring function can optimize the route selection according to the characteristics of different goods.

[0167] The working principle and effect of the above technical solution are as follows: the re-routing model takes into account multiple key factors affecting route selection, and adjusts the influence of each factor in the total score through a weight function. The weight functions α(D), β(D), γ(D), and δ(D) in the formula can be adjusted according to the cargo attribute D, which means that different priorities can be flexibly set for different types of cargo. For example, for refrigerated goods that need to be transported quickly, the weight of the time factor can be increased; for fragile goods, the road surface flatness is more important; the formula comprehensively considers the average speed (C i), cargo attributes (D), safety standards (reflected by flatness Ri and traffic density Pi) and the longest acceptable transportation time (L). This comprehensive evaluation method helps to select a transportation route that is both fast and safe; by adjusting weights and parameters, the formula can be easily adapted to different transportation needs and scenarios. This customizability makes the formula highly practical; the various parameters in the formula (such as congestion index, flatness, population density, etc.) can be obtained and updated through real-time data. This makes route selection more dynamic and accurate, and can make the best decision based on actual conditions.

[0168] In one embodiment of the present invention, a real-time control system for logistics data changes is provided, wherein the route selection and change module comprises:

[0169] The consideration route module is used to select the route with the highest score as the optimal route, and the optimal route is denoted as j opt , the routes with the next highest scores are selected as candidate routes, and the candidate routes are denoted as j alt1 , j alt2 , …;

[0170] The selection probability calculation module is used to calculate a selection probability for each route (including the optimal route and the alternative routes). Specifically,

[0171] The probability of selecting the optimal route is:

[0172]

[0173] in, is the score of the optimal route, is the sum of the scores of all considered routes,

[0174] The probability of selecting an alternative route is:

[0175]

[0176] Among them, the value range of reduction_factor is (0,1);

[0177] Based on the random number selection module, it is used to generate a random number r belonging to (0,1). If r is less than or equal to the selection probability of the optimal route, the optimal route is selected. If r is greater than the selection probability of the optimal route, the cumulative probability is used to check whether r falls within the selection probability range of a certain alternative route. If it falls within the selection probability range of a certain alternative route, the alternative route is selected.

[0178] When a route needs to be selected, the system generates a random number r between 0 and 1. Then, the selection is made as follows:

[0179] If r is less than the selection probability of the optimal route, the optimal route is selected.

[0180] If r is greater than or equal to, check if it falls within the selection probability range of some alternative route. This is usually done by summing the probabilities. For example, if P_j_opt is 0.6, P_j_alt1 is 0.2 (assuming reduction_factor is 1, just for illustration), and P_j_alt2 is 0.1, then:

[0181] If r is between 0.6 and 0.8 (0.6+0.2), then j_alt1 is selected.

[0182] If r is between 0.8 and 0.9 (0.6+0.2+0.1), then j_alt2 is selected.

[0183] If r is greater than 0.9, you may need to regenerate r or choose a different route that was not considered (depending on the implementation).

[0184] In this way, even if the optimal route is the highest in terms of score, there is a chance that an alternative route will be chosen due to randomness, thus helping to disperse the traffic and reduce the risk of congestion.

[0185] The working principle and effect of the above technical solution are as follows: Traditional route planning usually focuses on selecting the optimal route, while ignoring the congestion problem caused by all vehicles choosing the same route at the same time. By introducing probabilistic decision-making, the method breaks this deterministic selection mode, increases the flexibility and robustness of the system, and dynamically weighs the optimal and alternative routes. This method not only considers the optimal route, but also considers the alternative routes at the same time, and dynamically weighs their choices through probability. This dynamic selection mechanism helps to avoid excessive concentration on a certain optimal route, thereby reducing the risk of congestion; adjustable selection tendency, by introducing reduction_factor, the method allows the tendency to select alternative routes to be adjusted according to actual conditions. This flexibility enables the method to better adapt to different traffic conditions and needs; comprehensive consideration of multiple factors: In the original scoring formula, multiple aspects such as cost, risk, time and penalty factors have been comprehensively considered. By combining this scoring formula with the probabilistic selection mechanism, the method can more comprehensively evaluate the pros and cons of different routes and make more reasonable decisions. ; By introducing a probabilistic decision-making mechanism, dynamically weighing optimal and alternative routes, adjustable selection preferences, and comprehensively considering multiple factors, this method is expected to improve the efficiency and stability of the transportation system and reduce the occurrence of congestion in practical applications.

[0186] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A real-time control method for logistics data changes, characterized in that: The method comprises: Setting a route number for each route in the logistics route network, and obtaining historical road usage information and current road usage information according to the route number; Predicting road usage information in a future time period based on the historical road usage information and the current road usage information, screening out route numbers for which the road usage information has changed, and obtaining a driver route that needs to be changed based on the route number for which the road usage information has changed; Obtaining the transport cargo attributes of the driver who needs to change the route, and calculating the scores of all accessible routes according to the transport cargo attributes; Selecting a changed route for the driver based on the scores of the accessible routes and a probabilistic decision-making mechanism; The step of obtaining the transport cargo attributes of the driver who needs to change the route, and calculating the scores of all accessible routes according to the transport cargo attributes, includes: Obtaining the attributes of the cargo transported by the driver who needs to change the route, wherein the cargo attributes include: general cargo, refrigerated cargo, fragile cargo, and dangerous cargo; Map the logistics route network into a graph, and use the depth-first algorithm to enumerate all the accessible routes from the current location of the driver who needs to change the route to the destination; The scores of all accessible routes are calculated by re-planning the route model. Specifically, the re-route model is: Where n is the number of sections in the reachable route, T i is the predicted time to pass through section i, L is the longest acceptable transportation time to pass through section i, R i is the flatness of road section i, C i is the average speed of section i, C max is the maximum average speed among the average speeds of all road sections, α(D), β(D), γ(D) and δ(D) are weight functions adjusted according to the cargo attribute D, P i is the traffic density of road section i, f(T i ) is T i function, M is the maximum traffic density among the traffic densities of all road sections.

2. According to claim 1, a real-time control method for logistics data changes is characterized in that: A route number is set for each route in the logistics route network, and historical road use information and current road use information are obtained according to the route number, including: Mapping all routes in the logistics route network, wherein the mapping indicates the starting point, the passing point and the end point of each route, and assigning a unique route number to each mapped route; Obtaining historical road usage information of each numbered route, the historical road usage information including average vehicle speed and traffic density, storing the acquired historical road information in a database, and establishing an index and search optimization; The road traffic conditions are monitored in real time through GPS tracking, traffic cameras and road surface sensors to obtain current road usage information, wherein the current road usage information includes average vehicle speed and traffic density.

3. According to claim 1, a real-time control method for logistics data changes is characterized in that: Predicting road usage information in a future time period based on the historical road usage information and the current road usage information, screening out route numbers where the road usage information has changed, and obtaining a driver route that needs to change the route based on the route number where the road usage information has changed, including: Predicting road usage information in a future time period based on the historical road usage information and the current road usage information through deep learning; Unifying the formats of the data of historical road use information and the data of future road use information, wherein the formats include time format, speed unit and measurement unit of traffic density, and cleaning the data after the formats are unified; Use JOIN query in SQL to match the historical road usage data and future road usage data of the routes in the logistics route network, and make comparisons and judgments based on the preset thresholds to filter out the route numbers whose road usage information will change in the future time period; Get the route of the driver who needs to change the route according to the route number where the road use information has changed.

4. According to claim 1, a real-time control method for logistics data changes is characterized in that: The driver is selected to change the route based on the scores of the accessible routes and a probabilistic decision-making mechanism, including: The route with the highest score is selected as the optimal route, and the optimal route is denoted as j opt , the routes with the next highest scores are selected as candidate routes, and the candidate routes are denoted as j alt1 , j alt2 , …; A selection probability is calculated for each route, wherein each route includes an optimal route and an alternative route. Specifically, The probability of selecting the optimal route is: in, is the score of the optimal route, is the sum of the scores of all considered routes; The probability of selecting an alternative route is: Among them, the value range of reduction_factor is (0,1); Generate a random number r belonging to (0,1). If r is less than or equal to the probability of the optimal route being selected, then select the optimal route; If r is greater than the probability of the optimal route being selected, the cumulative probability is used to check whether r falls within the selection probability range of a certain alternative route. If it falls within the selection probability range of a certain alternative route, the alternative route is selected.

5. A real-time control system for logistics data changes, characterized in that: The system comprises: An information acquisition module, used to set a route number for each route in the logistics route network, and acquire historical road use information and current road use information according to the route number; A module for predicting and obtaining routes that need to be changed is used to predict the road usage information in a future time period based on the historical road usage information and the current road usage information, filter out route numbers whose road usage information has changed, and obtain the driver's route that needs to be changed based on the route numbers whose road usage information has changed; A scoring calculation module is used to obtain the transport cargo attributes of the driver who needs to change the route, and calculate the scores of all accessible routes based on the transport cargo attributes; A route change selection module, used for selecting a route change for the driver based on the scores of the accessible routes and a probabilistic decision-making mechanism; Wherein, the score calculation module includes: A module for obtaining transport cargo attributes is used to obtain the transport cargo attributes of the driver who needs to change the route, and the cargo attributes include: general cargo, refrigerated cargo, fragile cargo and dangerous cargo; The module for enumerating accessible routes is used to map the logistics route network into a graph and enumerate all accessible routes from the current location of the driver who needs to change the route to the destination through a depth-first algorithm; The module for calculating the score of accessible routes is used to calculate the scores of all accessible routes by replanning the route model. Specifically, the re-route model is: Where n is the number of sections in the reachable route, T i is the predicted time to pass through section i, L is the longest acceptable transportation time to pass through section i, R i is the flatness of road section i, C i is the average speed of section i, C max is the maximum average speed among the average speeds of all road sections, α(D), β(D), γ(D) and δ(D) are weight functions adjusted according to the cargo attribute D, P i is the traffic density of road section i, f(T i ) is T i function, M is the maximum traffic density among the traffic densities of all road sections.

6. A real-time control system for logistics data changes according to claim 5, characterized in that: The information acquisition module includes: A route mapping module, used to map all routes in the logistics route network, wherein the mapping indicates the starting point, the passing point and the end point of each route, and assigns a unique route number to each mapped route; A module for obtaining historical road use information is used to obtain historical road use information of each numbered route, wherein the historical road use information includes average vehicle speed and traffic density, and the obtained historical road information is stored in a database to establish an index and search optimization; The module for obtaining current road usage information is used to obtain current road usage information by real-time monitoring of road traffic conditions through GPS tracking, traffic cameras and road surface sensors. The current road usage information includes average vehicle speed and traffic density.

7. A real-time control system for logistics data changes according to claim 5, characterized in that: The module for predicting and obtaining routes that need to be changed includes: A future road usage information prediction module, configured to predict the road usage information in a future time period based on the historical road usage information and the current road usage information through deep learning; A format unification and cleaning module, used to unify the formats of the data of historical road use information and the data of future road use information, wherein the formats include time format, speed unit and measurement unit of traffic density, and clean the data after the formats are unified; The screening module is used to use JOIN query in SQL to match the historical road usage data and future road usage data of the routes in the logistics route network, and compare and judge according to the preset threshold to screen out the route numbers whose road usage information will change in the future time period; The module for obtaining the route of drivers who need to change the route is used to obtain the route of drivers who need to change the route according to the route number of the changed road use information.

8. A real-time control system for logistics data changes according to claim 5, characterized in that: The route change selection module includes: The consideration route module is used to select the route with the highest score as the optimal route, and the optimal route is denoted as j opt , the routes with the next highest scores are selected as candidate routes, and the candidate routes are denoted as j alt1 , j alt2 , …; The selection probability calculation module is used to calculate a selection probability for each route, wherein each route includes an optimal route and an alternative route. Specifically, The probability of selecting the optimal route is: in, is the score of the optimal route, is the sum of the scores of all considered routes, The probability of selecting an alternative route is: Among them, the value range of reduction_factor is (0,1); Based on the random number selection module, it is used to generate a random number r belonging to (0,1). If r is less than or equal to the selection probability of the optimal route, the optimal route is selected. If r is greater than the selection probability of the optimal route, the cumulative probability is used to check whether r falls within the selection probability range of a certain alternative route. If it falls within the selection probability range of a certain alternative route, the alternative route is selected.

Images