A logistics optimization method and system based on intelligent algorithm

Abstract

The application discloses a logistics optimization method and system based on an intelligent algorithm, relates to the technical field of logistics and supply chain management, and comprises the following steps: S1, acquiring dynamic traffic event information and real-time traffic flow distribution data of a logistics distribution network; the dynamic traffic event information comprises a traffic accident position, a road control range and a time constraint condition. The application reversely generates traffic diffusion model parameters based on the dynamic traffic event information, converts the chain effect of the event on the surrounding road network into quantifiable dynamic indexes, combines real-time traffic flow data and congestion intensity evaluation, provides multi-dimensional risk evaluation basis for distribution path planning, accurately identifies key road sections affected by the event, avoids high-risk road sections through dynamic fusion of diffusion parameters and weight evaluation, significantly improves the timeliness of distribution and the balance of global resource allocation of the logistics network, sensitively responds to road network resource fluctuations in a high-dynamic traffic scene, and reduces local congestion risks.

Description

Technical Field

[0001] This invention relates to the field of logistics and supply chain management technology, specifically to a logistics optimization method and system based on intelligent algorithms. Background Technology

[0002] In the modern logistics industry, intelligent algorithms such as Dijkstra's algorithm and genetic algorithms are widely used in route planning and vehicle scheduling, significantly reducing operating costs and improving delivery efficiency. However, while existing algorithms are effective in static environments, they fall short in dealing with dynamic traffic events, becoming a bottleneck for improving logistics and delivery efficiency. Dynamic traffic events not only directly cause traffic congestion or disruptions but also have a cascading impact on surrounding traffic flow. Ideally, the algorithm should quickly assess this impact and replan the route. However, existing technologies have the following shortcomings. First, the response speed is insufficient, with delays in route replanning, and they rely on static or historical data, exhibiting poor dynamic perception capabilities. Second, their ability to assess the scope of event impact is limited, failing to fully consider the cascading effects on surrounding areas, and they lack sufficient integration of multi-source data. Finally, the route optimization objective is singular, lacking flexibility. Faced with sudden events, they simply adjust the route without comprehensively considering other objectives. These problems restrict the development of the logistics industry, urgently requiring the design of intelligent algorithms that can quickly and comprehensively assess the impact of dynamic traffic events and accurately plan routes. Summary of the Invention

[0003] To address the shortcomings of existing technologies, this invention provides a logistics optimization method and system based on intelligent algorithms. This solves the problems of slow response speed, incomplete impact assessment, and single optimization objective in existing technologies when intelligent algorithms are used to deal with dynamic traffic events in the logistics and distribution process, which limit the efficiency of logistics and distribution.

[0004] To achieve the above objectives, the present invention provides a logistics optimization method based on intelligent algorithms, comprising the following steps: S1. Obtain dynamic traffic incident information and real-time traffic flow distribution data of the logistics and distribution network. Dynamic traffic incident information includes the location of traffic accidents, the scope of road control, and time constraints. S2. Generate traffic diffusion model parameters for the affected area based on dynamic traffic event information. The traffic diffusion model parameters are used to characterize the degree of cascading impact of the event on the surrounding road network. S3. Dynamically monitor the potential congestion risk of each delivery route based on traffic diffusion model parameters and real-time traffic flow distribution data, and generate congestion intensity indicators. S4. Evaluate the time cost weight of each delivery route based on traffic diffusion model parameters and congestion intensity index; S5. Combine time cost weights with real-time traffic flow distribution data to generate the optimal route selection weights for candidate delivery routes; S6. Filter global delivery routes based on the optimal route selection weight and trigger navigation instructions for delivery vehicles to complete route adjustment.

[0005] Furthermore, obtain dynamic traffic event information and real-time traffic flow distribution data of the logistics and distribution network, including: The location of traffic accidents and the scope of road control are collected through the urban traffic monitoring system. The location of traffic accidents includes latitude and longitude coordinates and lane occupancy. Real-time traffic flow distribution data is obtained based on the vehicle-to-everything (V2X) platform. The real-time traffic flow distribution data includes the average vehicle speed and vehicle density of each road segment. Traffic accident locations are linked to real-time traffic flow distribution data and stored as dynamic traffic event information. The linked storage results are dynamically refreshed according to the real-time update cycle.

[0006] Furthermore, based on dynamic traffic incident information, traffic diffusion model parameters for the affected area are generated, including: Based on the location of a traffic accident, the topological features of adjacent road segments within the affected area are extracted. These topological features include the connection angles and differences in traffic capacity between adjacent road segments. The diffusion coefficient and propagation delay time of each road segment affected by the event are calculated based on the topological characteristics. The diffusion coefficient and propagation delay time are generated by preset diffusion rules. Diffusion coefficient = (Traffic capacity of adjacent road segments / Traffic capacity of accident road segments) × (1 - Connection angle / 180°); The connection angle is the angle between the adjacent road segment and the accident road segment, where 0° ≤ angle ≤ 180°; Propagation delay time = (Length of adjacent road segment / Max(Average vehicle speed of the accident road segment, V design × 20%)) × Diffusion coefficient × (1 + Vehicle density of adjacent road segment / Design vehicle density of adjacent road segment) Wherein, V is the average vehicle speed corresponding to the design capacity of the accident section; the Max function is used to limit the lower limit of the average vehicle speed of the accident section to 20% of the design speed to avoid the denominator approaching zero and causing calculation overflow; the vehicle density of adjacent road sections / the design vehicle density of adjacent road sections is used to quantify the impact of traffic flow status of adjacent road sections on the delay time.

[0007] The diffusion coefficient and propagation delay time are mapped to traffic diffusion model parameters, and the traffic diffusion model parameters are associated and stored in the latitude and longitude coordinates of the corresponding traffic accident location.

[0008] Furthermore, based on traffic diffusion model parameters and real-time traffic flow distribution data, the potential congestion risk of each delivery route is dynamically monitored, and congestion intensity indicators are generated, including: Based on the diffusion coefficient and propagation delay time in the traffic diffusion model parameters, the key road segments affected by the event in each delivery route are located. Based on the vehicle density statistics in real-time traffic flow distribution data, the real-time vehicle flow change rate of key road sections is calculated, and the dynamic congestion threshold of key road sections is calculated by combining the diffusion coefficient in the traffic diffusion model parameters. The first congestion factor is generated based on the ratio of the difference between the real-time vehicle flow change rate and the dynamic congestion threshold. The second congestion factor is generated based on the diffusion coefficient, the propagation delay time, and the historical average propagation delay time of the area. The calculation formula is: Second congestion factor = diffusion coefficient / [(propagation delay time / T0) + 1], where T0 is the historical average propagation delay time of the same type of road segment in the area, the statistical period is the past 30 days, and 1 is added to the denominator to avoid meaningless values ​​when the propagation delay time is 0. If the first congestion factor exceeds the preset alarm threshold, the first congestion factor is directly used as the congestion intensity index; if it does not exceed the threshold, the congestion intensity index is generated according to the mapping relationship between the second congestion factor and the road segment type, and the congestion intensity index is associated with the latitude and longitude coordinates of the corresponding key road segment.

[0009] Furthermore, key road sections are determined by reverse derivation from the latitude and longitude coordinates of the traffic accident locations.

[0010] Furthermore, the time cost weights of each delivery route are evaluated based on traffic diffusion model parameters and congestion intensity indicators, including: The initial time cost weights for each delivery route are generated based on the diffusion coefficient and propagation delay time in the traffic diffusion model parameters. The initial time cost weights are a linear combination of the diffusion coefficient and propagation delay time. The initial time cost weight is adjusted according to the type of congestion intensity index. If the congestion intensity index is the first congestion factor, it is adjusted by increasing the difference proportionally; if it is the second congestion factor, it is adjusted by the preset coefficient of the road segment type. The adjusted initial time cost weights are normalized to time cost weights and then bound to the latitude and longitude coordinates of the delivery route for storage.

[0011] Furthermore, the optimal route selection weights for candidate delivery routes are generated by combining time cost weights with real-time traffic flow distribution data, including: Candidate delivery routes are divided into segments based on the average vehicle speed in real-time traffic flow distribution data, and an initial route selection weight coefficient is set for each type of segment. The initial route selection weights for candidate delivery routes are calculated based on time cost weights and vehicle density in real-time traffic flow distribution data. The initial route selection weight is dynamically adjusted based on the initial route selection weight coefficient corresponding to the road segment type to generate the optimal route selection weight, and the optimal route selection weight is associated with the latitude and longitude coordinates of the candidate delivery route.

[0012] Furthermore, the candidate delivery routes are divided into high-traffic, medium-traffic, and low-traffic segments; the initial route selection weight is the inverse product of the time cost weight and the vehicle density.

[0013] Furthermore, the global delivery routes are filtered based on the optimal path selection weight, and navigation instructions for delivery vehicles are triggered to complete the route adjustment, including: The global delivery routes are prioritized based on the optimal route selection weight. The priority grouping rule is that routes with an optimal route selection weight higher than the preset congestion fluctuation threshold are classified as high priority groups, and the rest are classified as low priority groups. The ratio of high-priority and low-priority routes is dynamically adjusted based on vehicle density in real-time traffic flow distribution data. If the vehicle density exceeds the preset congestion fluctuation threshold, the number of routes in the high-priority group is reduced. The navigation instructions for delivery vehicles are triggered based on the adjusted route grouping results. The navigation instructions include the latitude and longitude coordinates and driving direction of the high-priority group routes to complete the route adjustment.

[0014] This invention also provides a logistics optimization system based on intelligent algorithms, applied to the above-described logistics optimization method based on intelligent algorithms, comprising: Traffic data acquisition module: Acquires dynamic traffic incident information and real-time traffic flow distribution data of the logistics and distribution network. Dynamic traffic incident information includes the location of traffic accidents, the scope of road control, and time constraints. The diffusion parameter generation module generates traffic diffusion model parameters for the affected area based on dynamic traffic event information. These parameters characterize the degree of cascading impact of the event on the surrounding road network. Potential risk monitoring module: Dynamically monitors the potential congestion risk of each delivery route based on traffic diffusion model parameters and real-time traffic flow distribution data, and generates congestion intensity indicators; Time-weighted evaluation module: Evaluates the time cost weight of each delivery route based on traffic diffusion model parameters and congestion intensity indicators; Optimal weight generation module: Combines time cost weight with real-time traffic flow distribution data to generate the optimal route selection weight for candidate delivery routes; Route adjustment execution module: Filters global delivery routes based on the optimal route selection weight and triggers navigation instructions for delivery vehicles to complete the route adjustment.

[0015] Beneficial effects

[0016] This invention generates traffic diffusion model parameters based on dynamic traffic event information, transforming the cascading impact of events on the surrounding road network into quantifiable dynamic indicators. Combined with real-time traffic flow data and congestion intensity assessment, it provides multi-dimensional risk evaluation for delivery route planning. It accurately identifies key road segments affected by events and avoids high-risk segments through the dynamic fusion of diffusion parameters and weight assessments, significantly improving delivery timeliness and the overall resource allocation balance of the logistics network. In highly dynamic traffic scenarios, it can sensitively respond to fluctuations in road network resources and reduce the risk of localized congestion. Simultaneously, driven by diffusion model parameters and congestion intensity indicators, it achieves coordinated optimization of static time consumption and dynamic congestion status in delivery route selection through hierarchical calculation and dynamic adjustment of time cost weights. During the route selection stage, priority grouping is performed based on the optimal route weight, and the route ratio is dynamically adjusted in conjunction with real-time traffic flow, reducing route adjustment delays and improving the utilization rate of high-capacity road segments. It can adapt to dynamic changes in road network resources, fundamentally solving the problem of global resource waste and delivery delays caused by incomplete traffic event information. It demonstrates strong practicality and adaptability in complex urban traffic environments. Attached Figure Description

[0017] Figure 1 This is a schematic diagram of the system structure of the present invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] This invention provides a logistics optimization method and system based on intelligent algorithms. Its core lies in achieving intelligent optimization of logistics delivery routes by combining dynamic traffic event information with real-time traffic flow distribution data. The following will be illustrated in conjunction with the appendix. Figure 1 The schematic diagram of the module structure and specific application scenarios shown in the figure describe the specific implementation of the present invention in detail.

[0020] First, the overall operation flow of this invention is introduced. The system includes a traffic data acquisition module, a diffusion parameter generation module, a potential risk monitoring module, a time weight evaluation module, an optimal weight generation module, and a route adjustment execution module. These modules work together to complete the entire process from data acquisition to route optimization. Taking a specific logistics delivery task as an example, suppose a logistics company needs to deliver a batch of goods from city A to city B. The delivery process involves multiple road segments, which may be affected by dynamic traffic events such as traffic accidents or road closures. The system operation process is as follows.

[0021] In the traffic data acquisition module, the system obtains dynamic traffic event information and real-time traffic flow distribution data from the logistics and distribution network through the urban traffic monitoring system and the vehicle-to-everything (V2X) platform. Specifically, the urban traffic monitoring system is responsible for collecting information on the location of traffic accidents and the scope of road control. The location of a traffic accident includes its latitude and longitude coordinates and lane occupancy, while the scope of road control includes the specific control area and time constraints. Simultaneously, the V2X platform acquires real-time traffic flow distribution data for each road segment through onboard sensors and communication equipment. This data mainly includes the average vehicle speed and vehicle density of each road segment. To ensure the real-time nature of the data, the system sets an update cycle based on the impact level of the dynamic traffic event: for example, the update cycle for traffic accident events is 1 minute, and the update cycle for road control events is 5 minutes. This information is dynamically refreshed and stored periodically. The update cycle is set based on the scope of the event's impact: if the impact area exceeds three road segments, the update cycle is shortened to 1 minute; otherwise, it is 5 minutes. For example, at a certain moment, the system detects a traffic accident on a road segment, located at 30.5 degrees North latitude and 120.3 degrees East longitude, and the accident results in the occupancy of two lanes. Meanwhile, real-time traffic flow data for this section of road showed that the average vehicle speed decreased to 20 km / h, and the vehicle density increased to 80 vehicles per kilometer. This information was integrated into dynamic traffic event information and used as the basis for subsequent calculations.

[0022] Next, the diffusion parameter generation module generates traffic diffusion model parameters for the affected area based on dynamic traffic event information. Specifically, the system first extracts the topological features of adjacent road segments around the accident location. These features include the connection angles and capacity differences between adjacent road segments. For example, the system analysis found that the connection angles between the accident road segment and its three adjacent road segments are 45 degrees, 90 degrees, and 135 degrees, respectively, and the capacity of these three road segments is 1000 vehicles per hour, 1200 vehicles per hour, and 800 vehicles per hour, respectively. Based on these topological features, the system further calculates the diffusion coefficient and propagation delay time of each road segment affected by the event. The diffusion coefficient is used to quantify the degree of impact of the traffic accident on surrounding road segments, while the propagation delay time represents the time required for the impact to spread.

[0023] The diffusion coefficient and propagation delay time are generated using preset diffusion rules: Diffusion coefficient = (traffic capacity of adjacent road segments / traffic capacity of accident road segments) × (1 - connection angle / 180°). The connection angle is the angle between the adjacent road segment and the accident road segment, where 0° ≤ angle ≤ 180°; Propagation delay time = (Length of adjacent road segment / Max(Average vehicle speed of the accident road segment, V design × 20%)) × Diffusion coefficient × (1 + Vehicle density of adjacent road segment / Design vehicle density of adjacent road segment) Here, V represents the average vehicle speed corresponding to the design capacity of the accident section; the Max function is used to limit the lower limit of the average vehicle speed of the accident section to 20% of the design speed to avoid the denominator approaching zero and causing calculation overflow; the vehicle density of adjacent road sections / the design vehicle density of adjacent road sections is used to quantify the impact of traffic flow status on the delay time of adjacent road sections. Finally, these two are mapped to traffic diffusion model parameters. For example, for the aforementioned adjacent road sections, the system calculates that the diffusion coefficient of the first road section is 0.7, and the propagation delay time is 5 minutes; the diffusion coefficient of the second road section is 0.6, and the propagation delay time is 8 minutes; the diffusion coefficient of the third road section is 0.3, and the propagation delay time is 10 minutes. These parameters are associated and stored in the latitude and longitude coordinates of the corresponding traffic accident location for subsequent use.

[0024] Subsequently, the potential risk monitoring module dynamically monitors the potential congestion risk of each delivery route based on the traffic diffusion model parameters and real-time traffic flow distribution data, and generates a congestion intensity index.

[0025] Specifically, the system first locates the critical road segments affected by the event on each delivery route based on the diffusion coefficient and propagation delay time parameters in the traffic diffusion model. For example, the system analysis found that the aforementioned traffic accident had a significant impact on three critical road segments in route A.

[0026] Next, the system calculates the real-time vehicle flow rate change rate of key road segments based on vehicle density statistics from real-time traffic flow distribution data, and combines this with the diffusion coefficient from the traffic diffusion model parameters to calculate the dynamic congestion threshold for the key road segments. For example, for the first key road segment, the system detects the real-time vehicle flow rate change rate. To calculate the dynamic congestion threshold based on an increase of 8 vehicles per minute and the diffusion coefficient, the following criteria are used: To add 5 vehicles per minute.

[0027] At this point, the first congestion factor = (ΔQ−Q) th ) / Q th = (8-5) / 5 = 0.6. If the preset alarm threshold is 0.5, then this factor exceeds the threshold and is directly used as the congestion intensity indicator.

[0028] Then, the system adjusts the real-time vehicle traffic flow rate. With dynamic congestion threshold The difference ratio generates the first congestion factor: .when When the factor is positive, it indicates that the threshold has been exceeded; when When the factor is negative, it indicates that the threshold has not been exceeded. A second congestion factor is generated based on the ratio of the diffusion coefficient to the propagation delay time: Second congestion factor = diffusion coefficient / [(propagation delay time / T0) + 1]. The denominator + 1 avoids meaningless values ​​when the delay time is 0. Here, T0 is the historical average propagation delay time of the area.

[0029] For example, with a diffusion coefficient of 0.5 and a propagation delay of 8 minutes, assuming the historical average propagation delay time for this region... Minutes; based on the propagation delay time statistics of similar road sections in the area over the past 30 days, the second congestion factor is calculated as follows: 0.5 / [(8 / 5) + 1] = 0.5 / (1.6 + 1) = 0.5 / 2.6 ≈ 0.192. If the first congestion factor exceeds the preset alarm threshold, it is directly used as the congestion intensity index; otherwise, the congestion intensity index is generated based on the mapping relationship between the second congestion factor and the road section type. For example, for the first critical road section mentioned above, the first congestion factor is 0.71, exceeding the preset alarm threshold of 0.6. Therefore, the system uses it as the congestion intensity index and associates it with the latitude and longitude coordinates of the corresponding critical road section.

[0030] In the time-weighted evaluation module, the system assesses the time cost weight of each delivery route based on traffic diffusion model parameters and congestion intensity indicators. Specifically, the system first generates an initial time cost weight for each delivery route based on the diffusion coefficient and propagation delay time in the traffic diffusion model parameters. For example, for route A, the system calculates the initial time cost weight as a linear combination of the diffusion coefficient and propagation delay time, i.e., 0.7×5 + 0.5×8 + 0.3×10 = 10.5. Then, the system adjusts the initial time cost weight according to the type of congestion intensity indicator. If the congestion intensity indicator is the first congestion factor, it is adjusted by increasing the difference proportionally; if it is the second congestion factor, it is adjusted according to a preset coefficient for the road segment type. For example, for route A above, since the first congestion factor is 0.71, the system adjusts the initial time cost weight by increasing the difference proportionally, ultimately obtaining an adjusted time cost weight of 12.3. Finally, the system normalizes the adjusted initial time cost weight into a time cost weight and stores it bound to the latitude and longitude coordinates of the delivery route.

[0031] In the optimal weight generation module, the system combines time cost weight and real-time traffic flow distribution data to generate optimal route selection weights for candidate delivery routes. Specifically, the system first divides the candidate delivery routes into segments based on the average vehicle speed in the real-time traffic flow distribution data and sets an initial route selection weight coefficient for each segment type. For example, the system divides route A into high-flow, medium-flow, and low-flow segments, and sets initial route selection weight coefficients of 0.8, 0.6, and 0.4 for the three segments, respectively. Next, the system calculates the initial route selection weights for candidate delivery routes based on the time cost weight and the vehicle density in the real-time traffic flow distribution data. For example, for route A, the system calculates the initial route selection weight as the product of the time cost weight and the reciprocal of the relative vehicle density. Assuming the real-time vehicle density of this segment is 80 vehicles / km and the maximum vehicle density is 100 vehicles / km, then the relative vehicle density... That is, 12.3 × (1 / 0.8) = 15.375. Then, the system dynamically adjusts the initial path selection weights according to the initial path selection weight coefficient corresponding to the road segment type, generating the optimal path selection weights and associating them with the latitude and longitude coordinates of the candidate delivery routes. For example, for the high-traffic segment in route A, the system adjusts the initial path selection weights according to the initial path selection weight coefficient of 0.8, ultimately obtaining an optimal path selection weight of 15.375 × 0.8 = 12.3.

[0032] Finally, in the route adjustment execution module, the system filters global delivery routes based on the optimal route selection weight and triggers navigation commands for delivery vehicles to complete the route adjustment. Specifically, the system first prioritizes global delivery routes based on the optimal route selection weight. The priority grouping rule is to classify routes with optimal route selection weights higher than a preset congestion fluctuation threshold into a high-priority group, and the rest into a low-priority group. For example, the system sets a preset congestion fluctuation threshold of 0.1 based on historical congestion data statistics: this value is the minimum weight of high-traffic-efficiency routes in the past 3 months. For route A, since its optimal route selection weight is 12.3, which is higher than the threshold, it is classified into a high-priority group. If historical data shows that the threshold deviates from the actual congestion fluctuation by more than 10%, the threshold is automatically updated. Next, the system dynamically adjusts the ratio of high-priority and low-priority routes based on vehicle density in real-time traffic flow distribution data. For example, when vehicle density exceeds the preset congestion fluctuation threshold, the system reduces the number of routes in the high-priority group. Finally, the system triggers navigation commands for delivery vehicles based on the adjusted route grouping results. The navigation commands include the latitude and longitude coordinates and driving direction of the high-priority group routes to complete the route adjustment. For example, the system sends navigation instructions to the delivery vehicle, directing it to travel along route A, specifically starting from 30.5 degrees north latitude and 120.3 degrees east longitude, and proceeding along the high-priority road segment to the destination.

[0033] Furthermore, this invention introduces a novel intelligent algorithm formula for calculating the optimal path selection weight, as follows: ;

[0034] in, Indicates the weight of the optimal path selection; Indicates the first Time cost weight of segment path; Indicates the first Congestion intensity index of the route segment; Indicates the first Vehicle density of the route segment; For the first Maximum vehicle density of the route segment; This refers to relative vehicle density. and These are the weighting coefficients for time cost and congestion intensity, respectively, and they satisfy... The application of this formula is as follows: Assume path A contains three segments with time cost weights of 12.3, 10.5, and 8.7, congestion intensity indices of 0.71, 0.5, and 0.3, and vehicle densities of 80, 100, and 120, respectively. The maximum vehicle density of the three segments is... The weighting coefficients are 100, 150, and 200, respectively, set according to road design standards. and The values ​​are set to 0.6 and 0.4 respectively. According to the formula, the first segment is: Second paragraph: Third paragraph:

[0035] After calculation, the final result is: The optimal path selection weight for path A is 28.19. This formula comprehensively considers time cost, congestion intensity, and vehicle density to achieve a comprehensive evaluation of candidate paths, ensuring the scientific and efficient nature of path selection.

[0036] In summary, this invention acquires dynamic traffic event information and real-time traffic flow distribution data through a traffic data acquisition module, generates traffic diffusion model parameters through a diffusion parameter generation module, generates congestion intensity indicators through a potential risk monitoring module, evaluates time cost weights through a time weight assessment module, generates optimal route selection weights through an optimal weight generation module, and completes route adjustment through a route adjustment execution module. The entire process is logically clear and technically comprehensive, effectively improving the timeliness of logistics delivery and the balance of resource allocation, making it particularly suitable for logistics optimization tasks in complex urban traffic environments.

[0037] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0038] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A logistics optimization method based on intelligent algorithms, characterized in that, The steps include the following: S1. Obtain dynamic traffic incident information and real-time traffic flow distribution data of the logistics and distribution network. Dynamic traffic incident information includes the location of traffic accidents, the scope of road control, and time constraints. S2. Generate traffic diffusion model parameters for the affected area based on dynamic traffic event information. The traffic diffusion model parameters are used to characterize the degree of cascading impact of the event on the surrounding road network. S3. Dynamically monitor the potential congestion risk of each delivery route based on traffic diffusion model parameters and real-time traffic flow distribution data, and generate congestion intensity indicators. S4. Evaluate the time cost weight of each delivery route based on traffic diffusion model parameters and congestion intensity index; S5. Combine time cost weights with real-time traffic flow distribution data to generate the optimal route selection weights for candidate delivery routes; S6. Filter global delivery routes based on the optimal route selection weight and trigger navigation instructions for delivery vehicles to complete route adjustment.

2. The logistics optimization method based on intelligent algorithms according to claim 1, characterized in that, Obtain dynamic traffic event information and real-time traffic flow distribution data for the logistics and distribution network, including: The location of traffic accidents and the scope of road control are collected through the urban traffic monitoring system. The location of traffic accidents includes latitude and longitude coordinates and lane occupancy. Real-time traffic flow distribution data is obtained based on the vehicle-to-everything (V2X) platform. The real-time traffic flow distribution data includes the average vehicle speed and vehicle density of each road segment. Traffic accident locations are linked to real-time traffic flow distribution data and stored as dynamic traffic event information. The linked storage results are dynamically refreshed according to the real-time update cycle.

3. The logistics optimization method based on intelligent algorithms according to claim 1, characterized in that, Based on dynamic traffic incident information, traffic diffusion model parameters for the affected area are generated, including: Based on the location of a traffic accident, the topological features of adjacent road segments within the affected area are extracted. These topological features include the connection angles and differences in traffic capacity between adjacent road segments. The diffusion coefficient and propagation delay time of each road segment affected by the event are calculated based on the topological characteristics. The diffusion coefficient and propagation delay time are generated by preset diffusion rules. Diffusion coefficient = (Traffic capacity of adjacent road segments / Traffic capacity of accident road segments) × (1 - Connection angle / 180°); The connection angle is the angle between the adjacent road segment and the accident road segment, where 0° ≤ angle ≤ 180°; Propagation delay time = (Length of adjacent road segment / Max(Average vehicle speed of the accident road segment, V design × 20%)) × Diffusion coefficient × (1 + Vehicle density of adjacent road segment / Design vehicle density of adjacent road segment) Wherein, V is the average vehicle speed corresponding to the design capacity of the accident section; the Max function is used to limit the lower limit of the average vehicle speed of the accident section to 20% of the design speed to avoid the denominator approaching zero and causing calculation overflow; the vehicle density of adjacent road sections / the design vehicle density of adjacent road sections is used to quantify the impact of traffic flow status of adjacent road sections on the delay time. The diffusion coefficient and propagation delay time are mapped to traffic diffusion model parameters, and the traffic diffusion model parameters are associated and stored in the latitude and longitude coordinates of the corresponding traffic accident location.

4. The logistics optimization method based on intelligent algorithms according to claim 1, characterized in that, Based on traffic diffusion model parameters and real-time traffic flow distribution data, the potential congestion risk of each delivery route is dynamically monitored, and congestion intensity indicators are generated, including: Based on the diffusion coefficient and propagation delay time in the traffic diffusion model parameters, the key road segments affected by the event in each delivery route are located. Based on the vehicle density statistics in real-time traffic flow distribution data, the real-time vehicle flow change rate of key road sections is calculated, and the dynamic congestion threshold of key road sections is calculated by combining the diffusion coefficient in the traffic diffusion model parameters. The first congestion factor is generated based on the ratio of the difference between the real-time vehicle flow rate and the dynamic congestion threshold. The second congestion factor is generated based on the diffusion coefficient, propagation delay time, and the historical average propagation delay time of the area. The calculation formula is: Second congestion factor = Diffusion coefficient / [(Propagation delay time / T0) + 1]. Where T0 is the historical average propagation delay time of similar road sections in this area, the statistical period is the past 30 days, and 1 is added to the denominator to avoid meaningless values ​​when the propagation delay time is 0; If the first congestion factor exceeds the preset alarm threshold, the first congestion factor is directly used as the congestion intensity index; if it does not exceed the threshold, the congestion intensity index is generated according to the mapping relationship between the second congestion factor and the road segment type, and the congestion intensity index is associated with the latitude and longitude coordinates of the corresponding key road segment.

5. The logistics optimization method based on intelligent algorithms according to claim 4, characterized in that, Key road sections are determined by reverse derivation from the latitude and longitude coordinates of the traffic accident locations.

6. The logistics optimization method based on intelligent algorithms according to claim 1, characterized in that, The time cost weights of each delivery route are evaluated based on traffic diffusion model parameters and congestion intensity indices, including: The initial time cost weights for each delivery route are generated based on the diffusion coefficient and propagation delay time in the traffic diffusion model parameters. The initial time cost weights are a linear combination of the diffusion coefficient and propagation delay time. The initial time cost weight is adjusted according to the type of congestion intensity index. If the congestion intensity index is the first congestion factor, it is adjusted by increasing the difference proportionally; if it is the second congestion factor, it is adjusted by the preset coefficient of the road segment type. The adjusted initial time cost weights are normalized to time cost weights and then bound to the latitude and longitude coordinates of the delivery route for storage.

7. The logistics optimization method based on intelligent algorithms according to claim 1, characterized in that, The optimal route selection weights for candidate delivery routes are generated by combining time cost weights with real-time traffic flow distribution data, including: Candidate delivery routes are divided into segments based on the average vehicle speed in real-time traffic flow distribution data, and an initial route selection weight coefficient is set for each type of segment. The initial route selection weights for candidate delivery routes are calculated based on time cost weights and vehicle density in real-time traffic flow distribution data. The initial route selection weight is dynamically adjusted based on the initial route selection weight coefficient corresponding to the road segment type to generate the optimal route selection weight, and the optimal route selection weight is associated with the latitude and longitude coordinates of the candidate delivery route.

8. The logistics optimization method based on intelligent algorithms according to claim 7, characterized in that, Candidate delivery routes are divided into high-traffic, medium-traffic, and low-traffic segments; the initial route selection weight is the inverse product of time cost weight and vehicle density.

9. The logistics optimization method based on intelligent algorithms according to claim 1, characterized in that, The system filters global delivery routes based on optimal route selection weights and triggers navigation commands for delivery vehicles to adjust routes, including: The global delivery routes are prioritized based on the optimal route selection weight. The priority grouping rule is that routes with an optimal route selection weight higher than the preset congestion fluctuation threshold are classified as high priority groups, and the rest are classified as low priority groups. The ratio of high-priority and low-priority routes is dynamically adjusted based on vehicle density in real-time traffic flow distribution data. If the vehicle density exceeds the preset congestion fluctuation threshold, the number of routes in the high-priority group is reduced. Based on the adjusted route grouping results, navigation instructions are triggered for delivery vehicles. These instructions include the latitude and longitude coordinates and driving direction of the high-priority group routes to complete the route adjustment.

10. A logistics optimization system based on intelligent algorithms, characterized in that, include: Traffic data acquisition module: Acquires dynamic traffic incident information and real-time traffic flow distribution data of the logistics and distribution network. Dynamic traffic incident information includes the location of traffic accidents, the scope of road control, and time constraints. The diffusion parameter generation module generates traffic diffusion model parameters for the affected area based on dynamic traffic event information. These parameters characterize the degree of cascading impact of the event on the surrounding road network. Potential risk monitoring module: Dynamically monitors the potential congestion risk of each delivery route based on traffic diffusion model parameters and real-time traffic flow distribution data, and generates congestion intensity indicators; Time-weighted evaluation module: Evaluates the time cost weight of each delivery route based on traffic diffusion model parameters and congestion intensity indicators; Optimal weight generation module: Combines time cost weight with real-time traffic flow distribution data to generate the optimal route selection weight for candidate delivery routes; Route adjustment execution module: Filters global delivery routes based on the optimal route selection weight and triggers navigation instructions for delivery vehicles to complete the route adjustment.

Images