Cold chain transportation resource allocation method, device, equipment and medium

Abstract

The invention provides a cold chain transportation resource allocation method and device, equipment and a medium. According to the method, a real-time state table is generated based on real-time data, including position, temperature change and road condition information, of a cold-chain vehicle, temperature control risk points are recognized through the temperature change in the table, and a risk distribution diagram is generated in combination with the position and the road condition. And creating a thermodynamic diagram through the distribution data of the to-be-supplied goods points, and performing overlay analysis on the thermodynamic diagram and the road condition information to determine the boundary of the logistics bottleneck region. And optimizing the original circulation path of the cold-chain vehicle according to the risk distribution diagram and the logistics bottleneck boundary range by adopting a genetic algorithm to obtain an optimized path scheme. And updating a cold-chain transportation resource allocation scheme according to the optimized path, and scheduling the cold-chain vehicles, the goods supply points and the refrigeration houses according to the cold-chain transportation resource allocation scheme. According to the method provided by the invention, the safety and efficiency of cold-chain logistics in a dynamic environment can be improved.

Description

Technical Field

[0001] This application relates to the field of logistics. Specifically, it relates to a cold chain transportation resource allocation method, device, equipment and medium. Background Art

[0002] As a key area in modern supply chain management, cold chain logistics is directly related to the safety and efficiency of industries such as food and medicine, and its importance is self-evident. With the deepening of global trade and the surging demand of consumers for high-quality temperature-controlled products, how to optimize resource allocation and improve transportation efficiency has become the core proposition for the development of the industry. Cold chain transportation not only needs to ensure the temperature stability of goods throughout the process, but also has to cope with complex logistics networks and dynamically changing market demands, which makes the accuracy and real-time nature of resource allocation the key indicators for measuring the system's capabilities.

[0003] However, current cold chain transportation solutions generally have limitations. Traditional methods mostly rely on static planning and manual experience, and it is difficult to adapt to real-time road conditions changes, fluctuations in the status of cold chain vehicles, and dynamic adjustments in the demands of supply points to be served. This rigid scheduling method often leads to resource waste, an overly large distribution radius, and even the inability to timely identify temperature control risks due to information lag, thus affecting the quality of goods and delivery timeliness. Against this background, the core challenges faced by cold chain transportation resource allocation have gradually emerged. First, it is difficult to obtain and integrate real-time information on the positions, temperature changes, and road conditions of cold chain vehicles, resulting in a lack of dynamic basis for scheduling decisions. Second, the spatio-temporal heterogeneity of the distribution of supply points to be served makes it difficult to accurately identify potential risk points and logistics bottlenecks, increasing the possibility of temperature control failure. Finally, the existing dynamic adjustment capabilities of route planning and time arrangement are insufficient, and it is difficult to achieve an optimal solution in a complex network. These technical factors have not been effectively resolved, resulting in unique technical problems for cold chain logistics in terms of efficiency and reliability.

[0004] Therefore, this application provides a cold chain transportation resource allocation method, device, equipment and medium to solve one of the above technical problems. Summary of the Invention

[0005] The purpose of this application is to provide a cold chain transportation resource allocation method, device, equipment and medium, which can solve at least one of the above-mentioned technical problems. The specific solutions are as follows:

[0006] According to the specific embodiments of this application, in the first aspect, this application provides a cold chain transportation resource allocation method, including:

[0007] Generate a real-time status table including location coordinates, temperature values, and road condition levels based on the real-time location, temperature changes, and road condition information of cold chain vehicles; identify temperature control risk points based on the change data of the temperature values in the real-time status table, and integrate the temperature control risk points, the location coordinates, and the road condition levels to generate a risk distribution map; generate a heat map based on the distribution data of the to-be-supplied delivery points, superimpose the heat map on the road condition information to obtain a superimposed map, and determine the boundary range of the logistics bottleneck area based on the superimposed map; wherein, the boundary range of the logistics bottleneck area represents key points or key areas that lead to a decrease in logistics efficiency, delays, and even a decline in service quality; optimize the original transfer path of the cold chain vehicle using a genetic algorithm according to the boundary ranges of the risk distribution map and the logistics bottleneck area boundary range to obtain an optimized original transfer path; update the cold chain transportation resource allocation plan according to the optimized original transfer path, and execute the scheduling for the cold chain vehicle, the to-be-supplied delivery points, and the cold storage according to the updated cold chain transportation resource allocation plan.

[0008] In one implementation manner, the updating the cold chain transportation resource allocation plan according to the optimized original transfer path includes: updating the delivery schedule of the cold chain vehicle according to the optimized original transfer path; matching the location data of the cold storage with the optimized original transfer path, and re-dividing the service ranges of different cold storages using the K-means clustering algorithm according to the matching result; iteratively optimizing the optimized original transfer path using the simulated annealing algorithm with reference to the updated delivery schedule, and outputting a transfer path that meets the global optimum; taking the re-divided cold storage service ranges, the transfer path that meets the global optimum, and the updated delivery schedule as the updated cold chain transportation resource allocation plan.

[0009] In one implementation manner, the updating the delivery schedule of the cold chain vehicle according to the optimized original transfer path includes: extracting the timestamp sequence of path nodes in the optimized original transfer path, and extracting the demand peak period in the distribution heat map; adjusting the timestamp order of different path nodes in the timestamp sequence using the time window constraint algorithm with reference to the demand peak period to obtain an adjusted timestamp sequence; updating the delivery schedule of the cold chain vehicle according to the adjusted timestamp sequence.

[0010] In one implementation manner, determining the boundary range of the logistics bottleneck area according to the superimposed map includes: for the superimposed map, using a density clustering algorithm to determine a target area where the density of the to-be-supplied cargo points and the road condition complexity are both higher than a preset threshold; determining a set of potential logistics bottleneck points within the target area, and for each potential logistics bottleneck point, calculating the number of to-be-supplied cargo points and the average road condition level within the influence range of the potential logistics bottleneck point to generate a bottleneck influence factor; sorting different potential logistics bottleneck points according to the values of the bottleneck influence factors, and intercepting a specified number of potential logistics bottleneck points as key logistics bottleneck points; through a geographic boundary detection algorithm, determining the influence range of each key logistics bottleneck point, and determining the corresponding boundary coordinate set for each influence range; and constructing the boundary range of the logistics bottleneck area according to all the boundary coordinates in all the boundary coordinate sets.

[0011] According to a specific implementation manner of the present application, in a second aspect, the present application provides a cold chain transportation resource allocation device, including:

[0012] A generation unit, configured to generate a real-time status table including position coordinates, temperature values, and road condition levels according to the real-time position, temperature change, and road condition information of cold chain vehicles; and configured to identify temperature control risk points according to the change data of the temperature values in the real-time status table, and integrate the temperature control risk points, the position coordinates, and the road condition levels to generate a risk distribution map; a processing unit, configured to generate a heat map according to the distribution data of to-be-supplied cargo points, superimpose the heat map on the road condition information to obtain a superimposed map, and determine the boundary range of the logistics bottleneck area according to the superimposed map; wherein the boundary range of the logistics bottleneck area represents key points or key areas that cause a decrease in logistics efficiency, delays, or even a decline in service quality; and configured to optimize the original transfer path of the cold chain vehicles by using a genetic algorithm according to the boundary ranges of the risk distribution map and the boundary range of the logistics bottleneck area respectively, to obtain an optimized original transfer path; an execution unit, configured to update the cold chain transportation resource allocation plan according to the optimized original transfer path, and execute the scheduling for the cold chain vehicles, the to-be-supplied cargo points, and the cold storage according to the updated cold chain transportation resource allocation plan.

[0013] In one implementation, the execution unit updates the cold chain transportation resource allocation plan according to the optimized original transfer path in the following manner: update the delivery schedule of the cold chain vehicles according to the optimized original transfer path; match the location data of the cold storage with the optimized original transfer path, and re-divide the service scope of different cold storages by using the K-means clustering algorithm according to the matching result; refer to the updated delivery schedule, and iteratively optimize the optimized original transfer path by using the simulated annealing algorithm to output a transfer path that meets the global optimum; use the re-divided service scope of the cold storage, the transfer path that meets the global optimum, and the updated delivery schedule as the updated cold chain transportation resource allocation plan.

[0014] In one implementation, the execution unit updates the delivery schedule of the cold chain vehicles according to the optimized original transfer path in the following manner: extract the timestamp sequence of the path nodes from the optimized original transfer path, and extract the demand peak period from the distribution heat map; use the time window constraint algorithm to adjust the timestamp order of different path nodes in the timestamp sequence according to the demand peak period to obtain the adjusted timestamp sequence; update the delivery schedule of the cold chain vehicles according to the adjusted timestamp sequence.

[0015] In one implementation, the processing unit determines the boundary range of the logistics bottleneck area according to the superimposed map in the following manner: for the superimposed map, use the density clustering algorithm to determine the target area where the density of the supply points to be supplied and the road condition complexity are both higher than the preset threshold; determine the set of potential logistics bottleneck points in the target area, and for each potential logistics bottleneck point, calculate the number of supply points to be supplied and the average road condition level within the influence range of the potential logistics bottleneck point to generate a bottleneck influence factor; sort different potential logistics bottleneck points according to the value of the bottleneck influence factor to intercept a specified number of potential logistics bottleneck points as key logistics bottleneck points; use the geographic boundary detection algorithm to determine the influence range of each key logistics bottleneck point and determine the boundary coordinate set corresponding to each influence range; construct the boundary range of the logistics bottleneck area according to all the boundary coordinates in all the boundary coordinate sets.

[0016] According to the specific implementation manners of the present application, in a third aspect, the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory, and the processor executes the computer program to implement the method described in any one of the first aspect.

[0017] According to the specific embodiments of the present application, in a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program / instructions are stored, and when the computer program / instructions are executed by a processor, the method described in any one of the first aspects is implemented.

[0018] Compared with the prior art, the above solution of the embodiments of the present application has at least the following beneficial effects:

[0019] The present application provides a cold chain transportation resource allocation method. By integrating the real-time location, temperature changes, and road conditions of cold chain vehicles, a real-time status table is generated. This method can dynamically reflect the actual situation of cold chain vehicles during transportation, providing a reliable basis for subsequent analysis. Based on the temperature change data in this status table, temperature control risk points are identified, and a risk distribution map is generated by combining the location coordinates and road condition levels, which helps to timely discover and handle problems that may affect the safety of goods, thus ensuring the safety and efficiency of cold chain logistics. At the same time, a heat map is generated according to the distribution of the supply points to be supplied and superimposed with the road condition information to determine the boundary range of the logistics bottleneck area, enabling logistics enterprises to optimize resource allocation targeted, reducing delays and service quality degradation caused by information lag, and improving the overall operation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 Shows a flowchart of a cold chain transportation resource allocation method;

[0021] Figure 2 Shows a flowchart of a method for updating a cold chain transportation resource allocation plan;

[0022] Figure 3 Shows a flowchart of a method for updating the delivery schedule of cold chain vehicles;

[0023] Figure 4 Shows a flowchart of a method for determining the boundary range of a logistics bottleneck area;

[0024] Figure 5 Shows a unit block diagram of a cold chain transportation resource allocation device according to an embodiment of the present application;

[0025] Figure 6 Is a block diagram of an electronic device for cold chain transportation resource allocation shown according to an exemplary embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0026] To make the objectives, technical solutions, and advantages of this application clearer, the following will further describe this application in detail with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all of them. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of this application.

[0027] The terms used in the embodiments of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. The singular forms "a", "the", and "said" used in the embodiments of this application and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise. "Multiple" generally includes at least two.

[0028] It should be understood that the term "and / or" used herein is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " herein generally represents an "or" relationship between the associated objects before and after.

[0029] It should be understood that although terms such as first, second, and third may be used in the embodiments of this application for description, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, without departing from the scope of the embodiments of this application, the first can also be called the second, and similarly, the second can also be called the first.

[0030] Depending on the context, the words "if" and "when" as used herein can be interpreted as "when...", "when...", "in response to determining", or "in response to detecting". Similarly, depending on the context, the phrase "if determined" or "if detecting (stated condition or event)" can be interpreted as "when determined", "in response to determining", "when detecting (stated condition or event)", or "in response to detecting (stated condition or event)".

[0031] It should also be noted that the term "comprising", "including", or any other variant thereof is intended to cover non-exclusive inclusion, so that a commodity or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or elements inherent to such commodity or device. Without further limitation, the element defined by the statement "including one..." does not exclude the existence of another identical element in the commodity or device including the said element.

[0032] It should be particularly noted that the symbols and / or numbers in the specification, if not marked in the accompanying drawing descriptions, are not drawing reference numerals.

[0033] The optional embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0034] For the embodiments provided by the present application, namely, the embodiments of a cold chain transportation resource allocation method.

[0035] Below in conjunction with Figure 1 The embodiments of the present application will be described in detail.

[0036] Figure 1 The flowchart of a cold chain transportation resource allocation method is shown, as Figure 1 shown, including steps S101 to S105.

[0037] Step S101, generate a real-time status table including position coordinates, temperature values, and road condition levels according to the real-time position, temperature changes, and road condition information of cold chain vehicles.

[0038] Step S102, identify temperature control risk points according to the change data of temperature values in the real-time status table, and integrate the temperature control risk points, position coordinates, and road condition levels to generate a risk distribution map.

[0039] Step S103, generate a heat map according to the distribution data of the to-be-supplied delivery points, overlay the heat map with the road condition information to obtain an overlay map, and determine the boundary range of the logistics bottleneck area according to the overlay map.

[0040] Among them, the boundary range of the logistics bottleneck area represents the key points or key areas that lead to a decrease in logistics efficiency, delays, and even a decline in service quality.

[0041] Step S104, optimize the original transfer path of cold chain vehicles by using a genetic algorithm according to the boundary ranges of the risk distribution map and the boundary range of the logistics bottleneck area, and obtain the optimized original transfer path.

[0042] Step S105, update the cold chain transportation resource allocation plan according to the optimized original transfer path, and execute the scheduling for cold chain vehicles, to-be-supplied delivery points, and cold storages according to the updated cold chain transportation resource allocation plan.

[0043] The cold chain transportation resource allocation method provided by this application can dynamically reflect the actual conditions of cold chain vehicles during transportation, providing a reliable basis for subsequent analysis. Based on the temperature change data in this status table, temperature control risk points are identified, and a risk distribution map is generated by combining location coordinates and road condition levels, which helps to timely discover and handle problems that may affect the safety of goods, thus ensuring the safety and efficiency of cold chain logistics. At the same time, a heat map is generated according to the distribution of the delivery points to be supplied and superimposed with the road condition information to determine the boundary range of the logistics bottleneck area, enabling logistics enterprises to optimize resource allocation targeted, reducing delays and service quality degradation caused by information lag, and improving the overall operation efficiency.

[0044] In some embodiments, the real-time status table in step S101 can be generated in the following manner.

[0045] Exemplarily, the location coordinates and temperature values are collected by sensors, the road condition level is obtained from the traffic data interface, and they are integrated into a unified data set containing real-time status to obtain an initial status table. The data integration method is adopted to fuse the sensor data and traffic information, and a dynamic update record is generated for the cold chain vehicle status of each vehicle to obtain an updated real-time table. If the location coordinates change, the road condition level is extracted from the traffic information according to the new location, and the real-time status is judged in combination with the temperature value to obtain an adjusted status table. Whether the temperature value is abnormal is judged through a preset threshold. If it is abnormal, the cold chain vehicle status is marked as to be processed, and the dynamic update record is updated to obtain an abnormal annotation table. The change trend in the dynamic update record is obtained, and the time series analysis algorithm is used to analyze the fluctuations of the location coordinates and temperature values to obtain a status change table. For the road condition level and temperature value in the status change table, it is judged whether the cold chain vehicle status is stable. If it is not stable, it is recalibrated through the sensor data to obtain a calibrated status table. According to the calibrated status table, the location coordinates, temperature value, and road condition level are integrated to generate a real-time status table containing all attributes.

[0046] In some specific embodiments, the real-time position of the cold-chain vehicle collects longitude and latitude coordinates (such as 116.404°E, 39.915°N) at a frequency of once per second through an in-vehicle GPS module. The data is transmitted to the cloud server through a 4G module, and the Kalman filtering algorithm is used to eliminate the positioning drift error of ±3 meters. The temperature sensor (such as the DS18B20 model) records the values in the range of -25°C to 15°C in the carriage at 30-second intervals. When the detected temperature exceeds the preset threshold (such as a fluctuation of ±2°C), the alarm mechanism is triggered, and the abnormal data is preferentially uploaded through the ZigBee protocol. The road condition information is obtained through the Amap traffic API interface. The road sections are divided into granularities of 500 meters and the congestion levels (1-5 levels) are marked. The Dijkstra algorithm is used to calculate the optimal path in combination with the historical path data, and the weight coefficients are dynamically adjusted (such as the congestion coefficient α = 0.7 and the temperature control coefficient β = 0.3). In the data integration stage, the Flink stream processing framework is adopted, and the window function is set to a 10-second sliding window. The position coordinates (WGS84 coordinate system), temperature values (retaining 1 decimal place), and road condition levels (integer type) are associated and matched to generate a real-time status table containing fields such as the cold-chain vehicle ID, timestamp (Unix millisecond level), longitude, latitude, temperature, and road conditions, and it is pushed to the monitoring system through the Kafka message queue.

[0047] Further, as some embodiments, when it is detected that the temperature of a certain cold-chain vehicle is higher than -18°C for three consecutive cycles and it is in a level-4 congested road section, a three-level emergency response can be automatically triggered, the path re-planning module is called, and the dispatching center is notified.

[0048] In some embodiments, the risk distribution map in step S102 can be generated in the following manner.

[0049] Exemplarily, the temperature change data can be obtained through the real-time status table. If the temperature value exceeds the preset threshold, an anomaly detection algorithm is used to identify the temperature control risk points to obtain a set of temperature control risk points. According to the set of temperature control risk points, in combination with the position of the cold-chain vehicle and the road condition level, a risk distribution map is generated through a clustering algorithm to determine the preliminary high-risk area. The coordinate set is extracted from the preliminary high-risk area, and the time series analysis algorithm is used to analyze the fluctuations of the temperature change and the road condition level to obtain a fluctuation feature table. According to the fluctuation feature table, if the temperature control risk exceeds the stable range, the risk distribution map is updated through the position coordinates of the cold-chain vehicle to obtain the adjusted high-risk area. The adjusted high-risk area is obtained, and the road condition levels within the coordinate set are classified to obtain a classified risk table. Through the classified risk table, in combination with the temperature change data in the real-time status table, it is judged whether the temperature control risk persists to obtain a persistent risk table. According to the persistent risk table, dynamic monitoring records are generated for the coordinate set within the high-risk area, and the final risk area coordinates are determined for the risk distribution map.

[0050] In some embodiments, after generating the heat map, the spatial superposition analysis of the customer distribution density data in the heat map and the road condition information is performed through Geographic Information System (GIS) technology. First, the two sets of data need to be converted into a unified geographic coordinate system, such as the WGS84 coordinate system, to ensure the consistency and accuracy of the data. Then, using GIS software or a custom algorithm, the data of the two layers are merged and processed within the same geographic area. In this process, different weight parameters can be set according to actual needs to emphasize the importance of customer density or road condition. For example, a comprehensive scoring function based on customer demand density and road condition level can be set, which takes into account high-density customer areas and traffic congestion conditions, so as to generate a superimposed map of comprehensive evaluation.

[0051] In some embodiments, when using the genetic algorithm to optimize the original transfer path of the cold chain vehicle, first, an initial population is constructed based on the data of the risk distribution map and the boundary range of the logistics bottleneck area. Each individual represents a possible transfer path, and its gene encoding includes the position coordinates and order of each node on the path. In the initialization stage, a certain number (such as 100) of initial solutions are randomly generated as the basis of the population. On this basis, the performance of each individual is evaluated through a fitness function, which comprehensively considers factors such as path length, temperature control coefficient, and real-time road condition information. For example, the fitness can be defined as the sum of the total driving distance plus the weighted sum of the temperature fluctuation penalty term and the congestion level weight.

[0052] Among them, excellent individuals are selected according to the fitness value to enter the next generation, and crossover and mutation operations are used to generate new solutions. The crossover operation usually adopts partially mapped crossover (PMX) or order crossover (OX) to ensure the validity of the offspring path; mutation is achieved by swapping the positions of two nodes, etc., and the mutation probability is generally set to a small value (such as 0.1). After multiple rounds of iteration (such as 50 times), with the gradual improvement of the fitness, the transfer path finally converges to a global optimal solution or a solution close to the optimal solution.

[0053] In some specific embodiments, temperature data is extracted from the real-time status table, and the sliding window mechanism is used to calculate the temperature change rate at a time interval of 5 minutes. When the temperature change rate exceeds ±0.5 °C / minute, it is marked as an abnormal point. The Isolation Forest algorithm is used to detect the abnormal points, and the abnormal score threshold is set to 0.7 to identify the temperature control risk points. Combining the cold chain vehicle position information, the risk points are mapped into the geographic coordinate system, and the K-means clustering algorithm is used to divide the risk points into regions. The number of clusters is set to 3 to generate a risk distribution map.

[0054] Further, in some embodiments, the central point coordinates of a high-risk area (such as 116.408°E, 39.912°N) can be extracted, and the area radius (such as 500 meters) can be calculated. At the same time, road condition information within the area is obtained through the Amap Traffic API, the congestion level (1-5 levels) is marked, and the average congestion coefficient within the area (such as 0.6) is calculated in combination with historical data. The coordinate set of the high-risk area is associated with the road condition information to generate a risk area report, which is pushed to the dispatching center through the Kafka message queue to provide data support for subsequent decision-making.

[0055] In some embodiments, the cold chain transportation resource allocation plan can be updated in the following manner.

[0056] Figure 2 A method flowchart for updating the cold chain transportation resource allocation plan is shown, as Figure 2 shown, including the following steps S201 to step S204.

[0057] Step S201, update the delivery schedule of the cold chain vehicles according to the optimized original transfer path.

[0058] Step S202, match the location data of the cold storage with the optimized original transfer path, and re-divide the service scope of different cold storages according to the matching result using the K-means clustering algorithm.

[0059] Step S203, refer to the updated delivery schedule, and use the simulated annealing algorithm to iteratively optimize the optimized original transfer path to output a transfer path that meets the global optimum.

[0060] Step S204, take the re-divided service scope of the cold storage, the transfer path that meets the global optimum, and the updated delivery schedule as the updated cold chain transportation resource allocation plan.

[0061] In the embodiments of the present application, when updating the cold chain transportation resource allocation plan according to the optimized original transfer path, not only the delivery schedule of the cold chain vehicles is adjusted, but also the service scope of the cold storage is re-divided, and then the simulated annealing algorithm is used for iterative optimization to finally obtain a transfer path that meets the global optimum.

[0062] In some embodiments, the delivery schedule of the cold chain vehicles can be updated in the following manner.

[0063] Figure 3 A method flowchart for updating the delivery schedule of the cold chain vehicles is shown, as Figure 3 shown, including the following steps S301 to step S303.

[0064] Step S301: Extract the timestamp sequence of path nodes from the optimized original transfer path, and extract the demand peak period from the distribution heat map.

[0065] Step S302: Use the time window constraint algorithm to adjust the timestamp order of different path nodes in the timestamp sequence with reference to the demand peak period, and obtain the adjusted timestamp sequence.

[0066] Step S303: Update the delivery schedule of the cold chain vehicles according to the adjusted timestamp sequence.

[0067] In the embodiments of the present application, in order to further optimize the delivery process, the timestamp sequence of path nodes is extracted from the optimized original transfer path, and combined with the demand peak period in the distribution heat map of the to-be-supplied points, the time window constraint algorithm is used to adjust the timestamp order of different path nodes, and then the delivery schedule of the cold chain vehicles is updated. This approach effectively alleviates traffic pressure, reduces waiting time, improves delivery efficiency and service quality, and can smoothly deliver goods especially during peak periods, greatly enhancing the experience of the to-be-supplied points.

[0068] In some embodiments, obtain the timestamp sequence corresponding to the path nodes from the optimized original transfer path, and use a sorting method to arrange them in chronological order to obtain an ordered set of timestamps. Generate a heat map through the distribution data of the to-be-supplied points, extract the distribution characteristics of the demand peak period, and determine the time range of the peak period. For the timestamp sequence and the demand peak period, use the time window constraint algorithm to adjust the node times in the timestamp sequence to obtain a preliminary delivery schedule. Obtain the preliminary delivery schedule. If the node time exceeds the time window corresponding to the demand peak period, reallocate the time through the constraint algorithm to generate the adjusted delivery schedule. According to the adjusted delivery schedule, combined with the path nodes in the optimized path, calculate the delivery time of each node to obtain a delivery time sequence synchronized with the path. Based on the delivery time sequence and the distribution characteristics of the to-be-supplied points in the heat map, determine whether there are time conflicts. If there are, use the priority sorting method to adjust the delivery times of the conflict nodes to generate the final delivery schedule.

[0069] As some feasible embodiments, during the process of adjusting the timestamp order of different path nodes in the timestamp sequence, the adjustment strategies include the peak avoidance principle, the principle of giving priority to supplying goods with high inventory levels, and / or the principle of minimizing the global completion time of cold chain vehicles. The adjusted timestamp sequence is a timestamp sequence that is more in line with the optimal scheduling. Under ideal conditions, it can minimize the overall receiving time of the to-be-supplied points and make the delivery completion time of the cold chain vehicles as early as possible.

[0070] In some specific embodiments, a timestamp sequence of path nodes can be extracted from the optimized original transfer path. For example, the timestamp of node A (116.408°E, 39.914°N) is 08:30, the timestamp of node B (116.412°E, 39.916°N) is 08:35, and the timestamp of node C (116.415°E, 39.918°N) is 08:40. Combining with the peak demand periods in the heat map of the distribution of points to be supplied, for example, the peak demand in area X (116.410°E, 39.915°N to 116.414°E, 39.919°N) is from 08:45 to 09:15, and the peak demand in area Y (116.405°E, 39.917°N to 116.409°E, 39.921°N) is from 09:00 to 09:30. Through the time window constraint algorithm, the timestamps of the path nodes are matched with the peak demand periods. For example, the arrival time of node C is adjusted to 08:45 to meet the peak demand in area X, and at the same time, the arrival time of node D (116.407°E, 39.920°N) is adjusted to 09:00 to meet the peak demand in area Y. Finally, a delivery schedule synchronized with the path is generated. For example, the delivery time from node A to node B is from 08:30 to 08:35, the delivery time from node B to node C is from 08:35 to 08:45, the delivery time from node C to node D is from 08:45 to 09:00, and the delivery time from node D to node E (116.410°E, 39.922°N) is from 09:00 to 09:15.

[0071] In some embodiments, the service scopes of different cold storages can be re-divided in the following manner.

[0072] Exemplarily, coordinate information is extracted through the cold storage locations, and preliminary matching is performed by combining the node data in the optimized original transfer path to obtain the corresponding relationship between the cold storages and the path nodes. The delivery radius is obtained from the matching result. For the boundary range of the bottleneck area, the K-means clustering algorithm is used to divide the service scope, and the adjusted site selection coordinates are output. According to the adjusted site selection coordinates, the distribution characteristics of the covered area are calculated to determine the service scope boundary of each cold storage. The overlapping part of the covered area and the node data is obtained. If the overlapping part exceeds the boundary range, the node allocation is adjusted through priority sorting to obtain an optimized matching scheme. For the optimized matching scheme, the distance distribution from the cold storage to the nodes is calculated in combination with the delivery radius to determine whether there are out-of-range nodes. The out-of-range nodes are extracted from the distance distribution, and the site selection coordinates are adjusted by the coordinate offset method to obtain the final cold storage location distribution. Through the final cold storage location distribution, a service scope division scheme synchronized with the optimized original transfer path is generated in combination with the covered area.

[0073] In some specific embodiments, the longitude and latitude coordinates of the current cold storage can be obtained through the cold storage location data. For example, Cold Storage 1 (116.400°E, 39.910°N), Cold Storage 2 (116.420°E, 39.920°N), and Cold Storage 3 (116.430°E, 39.930°N). Combining with the distribution nodes in the optimized original transfer path, such as Node A (116.408°E, 39.914°N), Node B (116.412°E, 39.916°N), and Node C (116.415°E, 39.918°N), calculate the Euclidean distance between each cold storage and the distribution nodes to form a distance matrix. For the distribution radius limit, for example, setting the maximum distribution radius to 5 kilometers, filter out the nodes beyond the range. For example, the distance between Node C and Cold Storage 1 is 5.2 kilometers, and mark it as a bottleneck area. Using the K-means clustering algorithm, with the cold storage location as the initial clustering center, set the number of clusters to 3, iteratively calculate the distance from each node to the clustering center, and reassign the node attribution. For example, adjust Node C from the service range of Cold Storage 1 to Cold Storage 2. The optimized cold storage service range covers Node A, Node B, and Node C. Output the adjusted cold storage location coordinates, such as Cold Storage 1 (116.405°E, 39.912°N), Cold Storage 2 (116.418°E, 39.918°N), and Cold Storage 3 (116.432°E, 39.928°N), and generate the polygon boundary of the coverage area. For example, the coverage range of Cold Storage 1 is from 116.400°E to 116.410°E, 39.908°N to 39.916°N; the coverage range of Cold Storage 2 is from 116.415°E to 116.425°E, 39.915°N to 39.925°N; the coverage range of Cold Storage 3 is from 116.428°E to 116.435°E, 39.925°N to 39.935°N. Visualize the adjusted cold storage service range through a geographic information system to ensure the maximization of distribution efficiency.

[0074] In some embodiments, the transfer path that meets the global optimum can be obtained in the following manner.

[0075] Exemplarily, dynamic update records can be obtained through a real-time status table. Combining with the coordinate adjustment data of the cold storage location, an initial optimized original transfer path and schedule distribution are generated. Extract the temperature change and road condition information from the dynamic update records. For the fluctuations of this information, use the simulated annealing algorithm to iteratively optimize the optimized original transfer path to obtain the iteratively optimized transfer path.

[0076] In addition, in some embodiments, the flow path and the delivery schedule can be further optimized. For example, for the updated combined delivery schedule, it is determined whether there is a time period that does not match the temperature change. If so, the cold storage location is reallocated by coordinate adjustment to further optimize the flow path. If not, this step is directly skipped. On this basis, considering the fluctuation characteristics of the road condition information, the arrival time of each node in the flow path is further calculated to determine the delivery schedule that meets the global optimum under the current factors. Through the delivery schedule that is globally optimal under the current factors, combined with the real-time status in the dynamic update record, the priority order of the flow path is adjusted to generate a flow path synchronized with the temperature change, so as to extract the key nodes of information fluctuation in the adjusted flow path, and the cold storage location is slightly adjusted by the coordinate offset method to obtain the final flow path and delivery schedule. According to the final path and delivery schedule, combined with the real-time status and road condition information, a flow plan consistent with the global optimum goal is generated.

[0077] In some specific embodiments, the coordinate data of the current cold storage is extracted from the real-time status table, such as Cold Storage A (118.500°E, 32.080°N), Cold Storage B (118.520°E, 32.090°N), and Cold Storage C (z118.530°E, 32.100°N). At the same time, the real-time location information of the delivery nodes is obtained, including Node X (118.505°E, 32.085°N), Node Y (118.510°E, 32.088°N), and Node Z (118.515°E, 32.092°N). Combining the data collected by the temperature sensor, such as the real-time temperature of Node X is -18.5°C, Node Y is -19.2°C, and Node Z is -17.8°C, and the traffic congestion index returned by the road condition API (Node X is 0.7, Node Y is 0.5, and Node Z is 0.9), a target function is constructed, comprehensively considering the transportation time, temperature fluctuation, and path cost. The simulated annealing algorithm is used, with the initial temperature set to 1000, the cooling coefficient to 0.95, and the number of iterations to 500. Each time an iteration is performed, the delivery order of two nodes is randomly exchanged, and the change in the value of the target function is calculated. For example, in one iteration, the delivery order of Node Y and Node Z is swapped, and the value of the target function drops from the initial 1200 to 1150, and this exchange is accepted. After multiple iterations, it converges to the optimal solution, and the globally optimal path output is Cold Storage A → Node X → Node Y → Cold Storage B → Node Z, with a total transportation time of 2.3 hours and the temperature fluctuation controlled within ±1°C. At the same time, a schedule is generated, with the delivery time of Node X being 08:00 - 08:30, Node Y being 09:00 - 09:30, and Node Z being 10:00 - 10:45, ensuring that the delivery of each node is completed within the time window.

[0078] In some other embodiments, the final optimization result can be written into a database and used to trigger the path visualization module of the geographic information system to display the path avoidance plan for temperature-sensitive areas and the real-time road condition adaptation result.

[0079] Exemplarily, the following method can be adopted to determine the boundary range of the logistics bottleneck area.

[0080] Figure 4 Fig. shows a flowchart of a method for determining the boundary range of a logistics bottleneck area, as Figure 4 shown, including steps S401 to S405.

[0081] Step S401: For the superimposed map, use the density clustering algorithm to determine the target area where the density of the supply points to be supplied and the road condition complexity are both higher than the preset threshold.

[0082] Step S402: Determine the set of potential logistics bottleneck points within the target area, and for each potential logistics bottleneck point, calculate the number of supply points to be supplied within the influence range of the potential logistics bottleneck point and the average road condition level to generate a bottleneck influence factor.

[0083] Step S403: Sort the different potential logistics bottleneck points according to the value of the bottleneck influence factor, and intercept a specified number of potential logistics bottleneck points as key logistics bottleneck points.

[0084] Step S404: Through the geographic boundary detection algorithm, determine the influence range of each key logistics bottleneck point, and determine the set of boundary coordinates corresponding to each influence range.

[0085] Step S405: Construct the boundary range of the logistics bottleneck area according to all the boundary coordinates in all the boundary coordinate sets.

[0086] In the embodiments of the present application, the boundary range of the logistics bottleneck area can be used on the one hand to update and optimize the original circulation path of the cold chain vehicles, and on the other hand, it can also combine the road condition data and the density of supply points to be supplied within the boundary to calculate the comprehensive congestion index of each bottleneck area for quantifying the logistics pressure.

[0087] In some specific embodiments, delivery address data for the past 30 days is extracted from a database of orders for points to be supplied. A geocoding service is used to convert the addresses into longitude and latitude coordinates (e.g., 116.404°E, 39.915°N). A kernel density estimation algorithm is used to generate a heat map of the distribution of points to be supplied, with a bandwidth parameter set to 0.02 and a grid resolution of 100 meters x 100 meters. Areas in the heat map with a density exceeding a threshold of 0.8 are spatially overlaid with real-time traffic data (e.g., the road congestion level provided by the AutoNavi API). The DBSCAN clustering algorithm is then used to density-cluster the overlaid data points, with a neighborhood radius ε set to 300 meters and a minimum sample size (MinPts) set to 15, to identify logistics bottleneck areas. The convex hull boundary coordinates of the clustering results (e.g., polygon vertex set 116.402°E, 39.918°N to 116.406°E, 39.920°N) are extracted and combined with the real-time traffic congestion index (e.g., 1.2) and the historical average speed (e.g., 20 km / h) to calculate the regional comprehensive congestion coefficient (e.g., 0.75). The bottleneck area boundary, congestion index, and associated order volume of the supply point (e.g., 500 orders per day) are integrated into structured data and transmitted to the route optimization engine via the REST interface to trigger the generation of a dynamic scheduling strategy.

[0088] The present application also provides an apparatus embodiment that is consistent with the above embodiment, which is used to implement the method steps of the above embodiment. The explanation based on the same name meaning is the same as the above embodiment, and has the same technical effect as the above embodiment, and will not be repeated here.

[0089] like Figure 5 As shown, the present application provides a cold chain transportation resource allocation device 500, comprising:

[0090] A generating unit 501 is configured to generate a real-time status table including position coordinates, temperature values, and road condition levels based on the real-time position, temperature changes, and road condition information of a cold chain vehicle. And it is also configured to identify temperature control risk points based on the change data of the temperature values in the real-time status table, and integrate the temperature control risk points, position coordinates, and road condition levels to generate a risk distribution map. A processing unit 502 is configured to generate a heat map based on the distribution data of the to-be-supplied delivery points, superimpose the heat map on the road condition information to obtain a superimposed map, and determine the boundary range of the logistics bottleneck area according to the superimposed map. Wherein, the boundary range of the logistics bottleneck area represents the key points or key areas that cause the reduction of logistics efficiency, delays, and even the decline of service quality. And it is also configured to optimize the original transfer path of the cold chain vehicle by using a genetic algorithm according to the boundary ranges of the risk distribution map and the logistics bottleneck area respectively, to obtain an optimized original transfer path. An execution unit 503 is configured to update the cold chain transportation resource allocation plan according to the optimized original transfer path, and execute the scheduling for cold chain vehicles, to-be-supplied delivery points, and cold storage according to the updated cold chain transportation resource allocation plan.

[0091] In one implementation, the execution unit 503 updates the cold chain transportation resource allocation plan according to the optimized original transfer path in the following way: update the delivery schedule of the cold chain vehicle according to the optimized original transfer path. Match the location data of the cold storage with the optimized original transfer path, and re-divide the service scope of different cold storages according to the matching result by using the K-means clustering algorithm. Refer to the updated delivery schedule, and use the simulated annealing algorithm to iteratively optimize the optimized original transfer path to output a transfer path that meets the global optimum. Take the re-divided service scope of the cold storage, the transfer path that meets the global optimum, and the updated delivery schedule as the updated cold chain transportation resource allocation plan.

[0092] In one implementation, the execution unit 503 updates the delivery schedule of the cold chain vehicle according to the optimized original transfer path in the following way: extract the time stamp sequence of path nodes from the optimized original transfer path, and extract the peak demand period from the distribution heat map. Use the time window constraint algorithm to adjust the time stamp order of different path nodes in the time stamp sequence with reference to the peak demand period to obtain an adjusted time stamp sequence. Update the delivery schedule of the cold chain vehicle according to the adjusted time stamp sequence.

[0093] In one implementation, the processing unit 502 determines the boundary range of the logistics bottleneck area according to the superimposed map in the following manner: for the superimposed map, a density clustering algorithm is used to determine the target area where the density of the supply points to be supplied and the road condition complexity are both higher than the preset threshold. A set of potential logistics bottleneck points is determined within the target area, and for each potential logistics bottleneck point, the number of supply points to be supplied within the influence range of the potential logistics bottleneck point and the average road condition level are calculated to generate a bottleneck influence factor. Different potential logistics bottleneck points are sorted according to the values of the bottleneck influence factors, and a specified number of potential logistics bottleneck points are intercepted as key logistics bottleneck points. Through a geographical boundary detection algorithm, the influence range of each key logistics bottleneck point is determined, and the boundary coordinate set corresponding to each influence range is determined. According to all the boundary coordinates in all the boundary coordinate sets, the boundary range of the logistics bottleneck area is constructed.

[0094] Regarding the device in the above embodiments, the specific manners in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0095] Figure 6 It is a block diagram of an electronic device 600 for cold chain transportation resource allocation shown according to an exemplary embodiment.

[0096] As Figure 6 shown, an implementation of the present application provides an electronic device 600. Among them, the electronic device 600 includes a memory 601, a processor 602, and an input / output (I / O) interface 603. Among them, the memory 601 is used to store instructions. The processor 602 is used to call the instructions stored in the memory 601 to execute the cold chain transportation resource allocation method of the embodiments of the present application. Among them, the processor 602 is respectively connected to the memory 601 and the I / O interface 603, and can be connected, for example, through a bus system and / or other forms of connection mechanisms (not shown). The memory 601 can be used to store programs and data, including the programs of the cold chain transportation resource allocation method involved in the embodiments of the present application, and the processor 602 executes various functional applications and data processing of the electronic device 600 by running the programs stored in the memory 601.

[0097] In the embodiments of the present application, the processor 602 may be implemented in at least one hardware form of a digital signal processor (DSP), a field programmable gate array (FPGA), or a programmable logic array (PLA). The processor 602 may be a central processing unit (CPU) or a combination of one or more of other forms of processing units with data processing capabilities and / or instruction execution capabilities.

[0098] The memory 601 in the embodiments of the present application may include one or more computer program products, and the computer program products may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory. The non-volatile memory may include, for example, read-only memory (ROM), flash memory, a hard disk drive (HDD), or a solid state drive (SSD).

[0099] In the embodiments of the present application, the I / O interface 603 can be used to receive input instructions (such as digital or character information, and key signal inputs related to user settings and function controls of the electronic device 600), and can also output various information to the outside (such as images or sounds). In the embodiments of the present application, the I / O interface 603 may include one or more of a physical keyboard, function keys (such as volume control keys, power on / off keys, etc.), a mouse, a joystick, a trackball, a microphone, a speaker, and a touch panel.

[0100] In some embodiments, the present application provides a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, perform any of the methods described above.

[0101] In some embodiments, the present application provides a computer program product including a computer program that, when executed by a processor, performs any of the methods described above.

[0102] Although the operations are depicted in the drawings in a particular order, it should not be construed as requiring that the operations be performed in the particular order shown or in a sequential order, or that all of the operations shown be performed to achieve the desired result. In certain environments, multitasking and parallel processing may be advantageous.

[0103] The methods, apparatuses, devices, and storage media of this application can be accomplished using standard programming techniques, implementing various method steps using rule-based logic or other logic. It should also be noted that the terms "apparatus" and "module" as used herein and in the claims are intended to include implementations using one or more lines of software code and / or hardware implementations and / or devices for receiving input.

[0104] Any of the steps, operations, or procedures described herein can be performed or implemented using one or more hardware or software modules alone or in combination with other devices. In one embodiment, the software module is implemented using a computer program product that includes a computer-readable medium containing computer program code that can be executed by a computer processor to perform any or all of the described steps, operations, or procedures.

[0105] For purposes of illustration and description, the foregoing description of the implementation of this application has been given. The foregoing description is not exhaustive nor is it intended to limit this application to the exact form disclosed, and various variations and modifications are possible in light of the above teachings, or various variations and modifications may be derived from the practice of this application. These embodiments were chosen and described in order to illustrate the principles of this application and its practical application, so that those skilled in the art can utilize this application in various embodiments and various modifications suitable for the particular purposes contemplated.

[0106] Regarding the apparatus in the above embodiments, the specific manner in which each module performs the operations has been described in detail in the embodiments related to the method, and will not be elaborated here.

[0107] It can be further understood that, unless otherwise specified, "connection" includes direct connection between two elements without other components therebetween, and also includes indirect connection between two elements with other elements therebetween.

[0108] It can be further understood that although the operations are depicted in the drawings in a particular order in the embodiments of this application, it should not be construed as requiring that the operations be performed in the particular order shown or in a sequential order, or that all of the operations shown be performed to achieve the desired result. In certain environments, multitasking and parallel processing may be advantageous.

[0109] Other embodiments of the present application will be readily contemplated by those skilled in the art upon considering the specification and practicing the invention disclosed herein. The present application is intended to cover any variations, uses, or adaptations of the present application, which follow the general principles of the present application and include known common general knowledge or conventional technical means in the field of the present application not disclosed herein. The specification and examples are only illustrative, and the true scope and spirit of the present application are pointed out by the following claims.

[0110] It should be understood that the present application is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present application is only limited by the appended claims.

[0111] The above embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present application.

Claims

1. A cold chain transportation resource allocation method, characterized in that, Including: Generate a real-time status table containing location coordinates, temperature values, and road condition levels based on the real-time location, temperature changes, and road condition information of cold chain vehicles; Identify temperature control risk points based on the change data of the temperature values in the real-time status table, and integrate the temperature control risk points, the location coordinates, and the road condition levels to generate a risk distribution map; Generate a heat map based on the distribution data of the supply points to be delivered, overlay the heat map with the road condition information to obtain an overlay map, and determine the boundary range of the logistics bottleneck area according to the overlay map; wherein, the boundary range of the logistics bottleneck area represents the key points or key areas that cause a decrease in logistics efficiency, delays, and even a decline in service quality; Optimize the original transfer path of the cold chain vehicle using a genetic algorithm according to the boundary ranges of the risk distribution map and the boundary range of the logistics bottleneck area respectively, to obtain an optimized original transfer path; Update the cold chain transportation resource allocation plan according to the optimized original transfer path, and execute the scheduling for the cold chain vehicle, the supply points to be delivered, and the cold storage according to the updated cold chain transportation resource allocation plan.

2. The method according to claim 1, wherein The step of updating the cold chain transportation resource allocation plan according to the optimized original transfer path includes: Update the delivery schedule of the cold chain vehicle according to the optimized original transfer path; Match the location data of the cold storage with the optimized original transfer path, and re-divide the service scope of different cold storages using the K-means clustering algorithm according to the matching result; Iteratively optimize the optimized original transfer path using the simulated annealing algorithm with reference to the updated delivery schedule, and output a transfer path that meets the global optimum; Use the re-divided service scope of the cold storage, the transfer path that meets the global optimum, and the updated delivery schedule as the updated cold chain transportation resource allocation plan.

3. The method according to claim 2, wherein The step of updating the delivery schedule of the cold chain vehicle according to the optimized original transfer path includes: Extract the time stamp sequence of the path nodes in the optimized original transfer path, and extract the demand peak period in the distribution heat map; Use the time window constraint algorithm to adjust the time stamp order of different path nodes in the time stamp sequence with reference to the demand peak period to obtain an adjusted time stamp sequence; Update the delivery schedule of the cold chain vehicle according to the adjusted time stamp sequence.

4. The method according to claim 1, wherein The step of determining the boundary range of the logistics bottleneck area according to the overlay map includes: For the overlay map, use the density clustering algorithm to determine the target area where the density of the supply points to be delivered and the road condition complexity are both higher than the preset threshold; Determine a set of potential logistics bottleneck points in the target area, and for each potential logistics bottleneck point, calculate the number of supply points to be delivered and the average road condition level within the influence range of the potential logistics bottleneck point to generate a bottleneck influence factor; Sort different potential logistics bottleneck points according to the values of the bottleneck influence factor, and intercept a specified number of potential logistics bottleneck points as key logistics bottleneck points; By using a geographical boundary detection algorithm, determine the influence range of each of the key logistics bottleneck points, and determine the set of boundary coordinates corresponding to each of the influence ranges; Based on all the boundary coordinates in all the sets of boundary coordinates, construct the boundary range of the logistics bottleneck area.

5. A cold chain transportation resource allocation device, characterized in that, Including: A generating unit, configured to generate a real-time status table including position coordinates, temperature values, and road condition levels according to the real-time position, temperature change, and road condition information of the cold chain vehicles; And configured to identify temperature control risk points according to the change data of the temperature values in the real-time status table, and integrate the temperature control risk points, the position coordinates, and the road condition levels to generate a risk distribution map; A processing unit, configured to generate a heat map according to the distribution data of the supply points to be supplied, superimpose the heat map on the road condition information to obtain a superimposed map, and determine the boundary range of the logistics bottleneck area according to the superimposed map; wherein, the boundary range of the logistics bottleneck area represents key points or key areas that cause a decrease in logistics efficiency, delays, and even a decline in service quality; and configured to optimize the original transfer path of the cold chain vehicles by using a genetic algorithm according to the boundary ranges of the risk distribution map and the boundary range of the logistics bottleneck area respectively, to obtain an optimized original transfer path; An execution unit, configured to update the cold chain transportation resource allocation plan according to the optimized original transfer path, and execute the scheduling for the cold chain vehicles, the supply points to be supplied, and the cold storage according to the updated cold chain transportation resource allocation plan.

6. The device according to claim 5, characterized in that The execution unit updates the cold chain transportation resource allocation plan according to the optimized original transfer path in the following manner: Update the delivery schedule of the cold chain vehicles according to the optimized original transfer path; Match the location data of the cold storage with the optimized original transfer path, and re-divide the service ranges of different cold storages according to the matching results by using the K-means clustering algorithm; Iteratively optimize the optimized original transfer path by using the simulated annealing algorithm with reference to the updated delivery schedule, and output a transfer path that meets the global optimum; Take the re-divided service ranges of the cold storage, the transfer path that meets the global optimum, and the updated delivery schedule as the updated cold chain transportation resource allocation plan.

7. The device according to claim 6, characterized in that, The execution unit updates the delivery schedule of the cold chain vehicles according to the optimized original transfer path in the following manner: Extract the time stamp sequence of the path nodes in the optimized original transfer path, and extract the demand peak period in the distribution heat map; Adjust the time stamp order of different path nodes in the time stamp sequence by using a time window constraint algorithm with reference to the demand peak period, to obtain an adjusted time stamp sequence; Update the delivery schedule of the cold chain vehicles according to the adjusted time stamp sequence.

8. The device according to claim 5, characterized in that The processing unit determines the boundary range of the logistics bottleneck area according to the superimposed map in the following manner: For the superimposed map, use a density clustering algorithm to determine a target area where the density of the supply points to be supplied and the road condition complexity are both higher than a preset threshold; Determine a set of potential logistics bottleneck points within the target area, and for each potential logistics bottleneck point, calculate the number of supply points to be served and the average road condition level within the influence range of the potential logistics bottleneck point to generate a bottleneck influence factor; Sort different potential logistics bottleneck points according to the values of the bottleneck influence factors, and intercept a specified number of the potential logistics bottleneck points as key logistics bottleneck points; Through a geographical boundary detection algorithm, determine the influence range of each key logistics bottleneck point, and determine the set of boundary coordinates corresponding to each influence range; Construct the boundary range of the logistics bottleneck area according to all the boundary coordinates in all the sets of boundary coordinates; 9. An electronic device, comprising a memory, a processor, and a computer program stored on the memory, characterized in that, The processor executes the computer program to implement the method according to any one of claims 1-4; 10. A computer-readable storage medium having a computer program / instructions stored thereon, characterized in that, When the computer program / instructions are executed by the processor, the method according to any one of claims 1-4 is implemented.

Images