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

Abstract

The application provides a cold chain transportation resource allocation method, device, equipment and medium. The method generates a real-time state table based on real-time data of a cold chain vehicle, including position, temperature change and road condition information, identifies temperature control risk points using the temperature change in the table, and generates a risk distribution map in combination with the position and road condition. A heat map is created by distribution data of to-be-supplied goods points, which is superimposed and analyzed with road condition information to determine the boundary of a logistics bottleneck area. A genetic algorithm is used to optimize the original flow path of the cold chain vehicle according to the risk distribution map and the boundary range of the logistics bottleneck, and an optimized path scheme is obtained. The cold chain transportation resource allocation scheme is updated according to the optimized path, and the scheduling of the cold chain vehicle, the to-be-supplied goods point and the cold storage is performed accordingly. The method provided by the application can improve the safety and efficiency of cold chain logistics in a dynamic environment.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of logistics, in particular to a cold chain transportation resource allocation method, device, equipment and medium. BACKGROUND

[0002] As a key field of modern supply chain management, cold chain logistics is directly related to the safety and efficiency of food, medicine and other industries, and its importance is self-evident. With the deepening of global trade and the surge in demand for high-quality temperature-controlled products, how to optimize resource allocation and improve transportation efficiency has become the core proposition of industry development. Cold chain transportation not only needs to ensure the temperature stability of goods throughout the journey, but also needs to cope with complex logistics networks and dynamic market demand, which makes the accuracy and real-time nature of resource allocation a key indicator of system capability.

[0003] However, current cold chain transportation solutions have limitations. Traditional methods rely heavily on static planning and manual experience, making it difficult to adapt to real-time road conditions, fluctuations in cold chain vehicle status, and dynamic adjustments to the needs of the supply points. This rigid scheduling often leads to resource waste, excessive distribution radius, and even failure to identify temperature control risks in a timely manner due to information lag, thereby affecting the quality of goods and delivery timeliness. In this context, the core challenges of cold chain transportation resource allocation have gradually emerged. First, real-time acquisition and integration of cold chain vehicle location, temperature changes and road conditions are difficult, leading to a lack of dynamic basis for scheduling decisions. Second, the spatio-temporal heterogeneity of supply points makes it difficult to accurately identify potential risk points and logistics bottlenecks, increasing the likelihood of temperature control failure. Finally, the dynamic adjustment capability of existing path planning and time scheduling is insufficient, making it difficult to achieve optimal solutions in complex networks. These technical factors have not been effectively addressed, resulting in unique technical challenges in efficiency and reliability for cold chain logistics.

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

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

[0006] According to the specific embodiment of the present application, in a first aspect, the present application provides a cold chain transportation resource allocation method, comprising:

[0007] According to the real-time position, temperature change and road condition information of the cold chain vehicle, a real-time state table containing position coordinates, temperature values and road condition levels is generated; temperature control risk point identification is performed according to the change data of the temperature values in the real-time state table, and the temperature control risk points, the position coordinates and the road condition levels are integrated to generate a risk distribution map; a heat map is generated according to the distribution data of the to-be-supplied goods points, the heat map is superimposed with the road condition information to obtain a superimposed map, and a logistics bottleneck area boundary range is determined according to the superimposed map; wherein the logistics bottleneck area boundary range represents a key point or a key area that causes a decrease in logistics efficiency, delay or even a decrease in service quality; the original circulation path of the cold chain vehicle is optimized by using a genetic algorithm according to the boundary ranges of the risk distribution map and the logistics bottleneck area boundary range respectively, to obtain an optimized original circulation path; the cold chain transportation resource allocation scheme is updated according to the optimized original circulation path, and the scheduling of the cold chain vehicle, the to-be-supplied goods points and the cold storage is performed according to the updated cold chain transportation resource allocation scheme.

[0008] In an embodiment, updating the cold chain transportation resource allocation scheme according to the optimized original circulation path comprises: updating a delivery schedule of the cold chain vehicle according to the optimized original circulation path; matching position data of the cold storage with the optimized original circulation path, and re-dividing service ranges of different cold storages according to the matching result by using a K-means clustering algorithm; iteratively optimizing the optimized original circulation path by using a simulated annealing algorithm with reference to the updated delivery schedule, and outputting a circulation path satisfying global optimization; taking the re-divided cold storage service ranges, the circulation path satisfying global optimization and the updated delivery schedule as the updated cold chain transportation resource allocation scheme.

[0009] In an embodiment, updating the delivery schedule of the cold chain vehicle according to the optimized original circulation path comprises: extracting a time stamp sequence of path nodes in the optimized original circulation path, and extracting a demand peak period in a distribution heat map; adjusting the time stamp order of different path nodes in the time stamp sequence with reference to the demand peak period by using a time window constraint algorithm, to obtain an adjusted time stamp sequence; and updating the delivery schedule of the cold chain vehicle according to the adjusted time stamp sequence.

[0010] In an implementation, the determining the boundary range of the logistics bottleneck area according to the superimposed map comprises: determining a target area in which the to-be-supplied goods points and the road conditions have a density and a complexity higher than a preset threshold by using a density clustering algorithm for the superimposed map; determining a set of potential logistics bottleneck points in the target area, and calculating, for each potential logistics bottleneck point, a number of to-be-supplied goods points and an average road condition level in an influence range of the potential logistics bottleneck point to generate a bottleneck influence factor; sorting different potential logistics bottleneck points according to values of the bottleneck influence factors to intercept a specified number of the potential logistics bottleneck points as key logistics bottleneck points; determining an influence range of each key logistics bottleneck point and a boundary coordinate set corresponding to each influence range by using a geographic boundary detection algorithm; and constructing the boundary range of the logistics bottleneck area according to all boundary coordinates in all boundary coordinate sets.

[0011] According to the specific implementation of the present application, the second aspect, the present application provides a cold chain transportation resource deployment device, comprising:

[0012] A generating unit is configured to generate a real-time state table containing position coordinates, temperature values, and road condition levels according to real-time positions, temperature changes, and road condition information of cold chain vehicles, and to identify temperature control risk points according to change data of the temperature values in the real-time state table, and to integrate the temperature control risk points, the position coordinates, and the road condition levels to generate a risk distribution map; a processing unit is configured to generate a heat map according to distribution data of to-be-supplied goods points, to obtain a superimposed map by superimposing the heat map and road condition information, and to determine a boundary range of a 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, delay, or even a decrease in service quality; and to optimize an original flow path of the cold chain vehicles by using a genetic algorithm according to respective boundary ranges of the risk distribution map and the boundary range of the logistics bottleneck area to obtain an optimized original flow path; and an executing unit is configured to update a cold chain transportation resource deployment scheme according to the optimized original flow path, and to perform scheduling for the cold chain vehicles, the to-be-supplied goods points, and cold storage according to the updated cold chain transportation resource deployment scheme.

[0013] In an implementation, the execution unit updates the cold-chain vehicle delivery schedule according to the optimized original circulation path in the following manner: the cold-chain vehicle delivery schedule is updated according to the optimized original circulation path; the locations of the cold storage facilities are matched with the optimized original circulation path, and the service ranges of different cold storage facilities are re-divided according to the matching results by using a K-means clustering algorithm; the optimized original circulation path is iteratively optimized by using a simulated annealing algorithm with reference to the updated delivery schedule, and a circulation path meeting global optimization is output; the re-divided cold storage facility service ranges, the circulation path meeting global optimization, and the updated delivery schedule are taken as the updated cold-chain transportation resource allocation scheme.

[0014] In an implementation, the execution unit updates the cold-chain vehicle delivery schedule according to the optimized original circulation path in the following manner: the time stamp sequence of the path nodes in the optimized original circulation path is extracted, and the demand peak period is extracted in a distribution heat map; the time stamp sequence of different path nodes is adjusted with reference to the demand peak period by using a time window constraint algorithm, and an adjusted time stamp sequence is obtained; the cold-chain vehicle delivery schedule is updated according to the adjusted time stamp sequence.

[0015] In an 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, a density clustering algorithm is used to determine a target area in which the to-be-supplied delivery point density and road condition complexity are higher than preset thresholds; a set of potential logistics bottleneck points is determined in the target area, and for each potential logistics bottleneck point, the number of to-be-supplied delivery points and the average road condition level in the influence range of the potential logistics bottleneck point 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 the potential logistics bottleneck points are intercepted as key logistics bottleneck points; the influence range of each key logistics bottleneck point is determined by a geographic boundary detection algorithm, and a boundary coordinate set corresponding to each influence range is determined; and the boundary range of the logistics bottleneck area is constructed according to all boundary coordinates in all boundary coordinate sets.

[0016] According to the specific embodiments of the present application, in a third aspect, the present application provides an electronic device, comprising a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to implement the method of 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 having stored thereon computer programs / instructions which, when executed by a processor, implement the method of any one of the first aspect.

[0018] Compared with the prior art, the above scheme 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, which generates a real-time state table by integrating real-time position, temperature change and road condition information of cold chain vehicles. This method can dynamically reflect the actual status of cold chain vehicles during transportation, providing a reliable basis for subsequent analysis. Based on the temperature change data in this state table, risk points are identified, and combined with position coordinates and road condition levels, a risk distribution map is generated, which helps to discover and handle possible safety problems in time, thereby ensuring the safety and efficiency of cold chain logistics. At the same time, a heat map is generated according to the distribution of the to-be-supplied cargo points and superimposed with road condition information to determine the boundary range of the logistics bottleneck area, so that logistics enterprises can optimize resource allocation, reduce delays and service quality degradation caused by information lag, and improve overall operational efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0020] Figure 1 A flowchart of a cold chain transportation resource allocation method is shown;

[0021] Figure 2 A flowchart of a method for updating a cold chain transportation resource allocation scheme is shown;

[0022] Figure 3 A flowchart of a method for updating a cold chain vehicle distribution schedule is shown;

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

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

[0025] Figure 6 An electronic device block diagram for cold chain transportation resource allocation according to an exemplary embodiment is shown. DETAILED DESCRIPTION

[0026] In order to make the purposes, technical solutions and advantages of the present application clearer, the following further describes the present application with reference to the accompanying drawings. Obviously, the described embodiments are only some of the embodiments of the present application but not all of them. Based on the embodiments in the present application, any other embodiments obtained by those ordinarily skilled in the art without creative effort should fall into the scope of the present application.

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

[0028] It should be understood that the term "and / or" used herein only describes an association relationship of associated objects, which means that there can be three relationships, for example, A and / or B can mean that A exists alone, A and B exist together, and B exists alone. In addition, the character " / " herein generally represents an "or" relationship between the front and rear associated objects.

[0029] It should be understood that although the terms first, second, third, etc. can be used in the embodiments of the present application to describe, these descriptions should not be limited to these terms. These terms are only used to distinguish the description. For example, without departing from the scope of the embodiments of the present 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 word "if" as used herein can be interpreted to mean "when" or "upon" or "in response to determining" or "in response to detecting". Similarly, depending on the context, the phrase "if it is determined" or "if (a stated condition or event) is detected" can be interpreted to mean "when it is determined" or "in response to determining" or "when (a stated condition or event) is detected" or "in response to detecting (a stated condition or event)".

[0031] It should also be noted that the terms "comprising", "containing", or any other variant thereof are intended to cover non-exclusive inclusion, so that the product or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such product or device. Without more limitations, the element defined by the phrase "comprising a" does not exclude the presence of another identical element in the product or device comprising the element.

[0032] It should be particularly noted that the symbols and / or numbers present in the specification, if not marked in the description, are not the figure marks.

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

[0034] The embodiments provided by the present application are the embodiments of a cold chain transportation resource allocation method.

[0035] The embodiments provided by the present application are the embodiments of a cold chain transportation resource allocation method. Figure 1 The embodiments provided by the present application are the embodiments of a cold chain transportation resource allocation method.

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

[0037] Step S101, according to the real-time position, temperature change and road condition information of the cold chain vehicle, a real-time state table containing position coordinates, temperature values and road condition levels is generated.

[0038] Step S102, according to the change data of the temperature value in the real-time state table, the temperature control risk point is identified, and the temperature control risk point, position coordinates and road condition level are integrated to generate a risk distribution map.

[0039] Step S103, according to the distribution data of the to-be-supplied goods points, a heat map is generated, the heat map is superimposed with the road condition information to obtain a superimposed map, and the boundary range of the logistics bottleneck area is determined according to the superimposed map.

[0040] Among them, the boundary range of the logistics bottleneck area represents the key points or key areas that cause the reduction of logistics efficiency, delay or even the decline of service quality.

[0041] Step S104, according to the boundary range of the risk distribution map and the boundary range of the logistics bottleneck area respectively, the original circulation path of the cold chain vehicle is optimized by using a genetic algorithm to obtain an optimized original circulation path.

[0042] Step S105, according to the optimized original circulation path, the cold chain transportation resource allocation scheme is updated, and according to the updated cold chain transportation resource allocation scheme, the scheduling for the cold chain vehicle, the to-be-supplied goods points and the cold storage is executed.

[0043] The cold chain transportation resource allocation method provided by the application can dynamically reflect the actual status of the cold chain vehicle in the transportation process, and provide a reliable basis for subsequent analysis. Based on the temperature change data in the state table, the temperature control risk points are identified, and the risk distribution map is generated in combination with the position coordinates and road condition levels, which helps to discover and handle the problems that may affect the safety of goods in time, thereby ensuring the safety and efficiency of the cold chain logistics. At the same time, the heat map is generated according to the distribution of the to-be-supplied goods points, and the logistics bottleneck area boundary range is determined by superimposing the road condition information, so that the logistics enterprise can optimize the resource allocation, reduce the delay and service quality decline caused by information lag, and improve the overall operation efficiency.

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

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

[0046] In some embodiments, the real-time position of the cold chain vehicle is collected by the on-board GPS module at a frequency of 1 per second (e.g., 116.404 °E, 39.915 °N), and the data is transmitted to the cloud server through the 4G module. The Kalman filtering algorithm is used to eliminate the positioning drift error of ±3 meters. The temperature sensor (e.g., DS18B20 model) records the value of the temperature in the vehicle cabin at an interval of 30 seconds, and when the temperature exceeds the preset threshold (e.g., ±2 °C fluctuation), the alarm mechanism is triggered, and the abnormal data is uploaded preferentially through the ZigBee protocol. The traffic information is obtained through the Gaode traffic API interface, and the road section is divided into 500 meters and marked with congestion levels (1-5 levels). The Dijkstra algorithm is used to calculate the optimal path based on the historical path data, and the weight coefficient is dynamically adjusted (e.g., congestion coefficient a = 0.7, temperature control coefficient b = 0.3). In the data integration stage, the Flink stream processing framework is used, and the window function is set to a 10-second sliding window. The position coordinates (WGS84 coordinate system), temperature values (1 decimal place), and road conditions are associated and matched to generate a real-time state table containing cold chain vehicle ID, timestamp (Unix millisecond level), longitude, latitude, temperature, road condition, etc. The table is pushed to the monitoring system through the Kafka message queue.

[0047] Further, as some embodiments, when a certain cold chain vehicle is detected to have a temperature higher than -18 °C for 3 consecutive periods and is in a 4-level congestion road section, a level 3 emergency response is automatically triggered, and the path re-planning module is called and the dispatch center is notified.

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

[0049] For example, temperature change data can be obtained from the real-time state table, and if the temperature value exceeds the preset threshold, an abnormal detection algorithm is used to identify temperature control risk points to obtain a set of temperature control risk points. According to the set of temperature control risk points, the cold chain vehicle position and the road condition level are combined to generate a risk distribution map by a clustering algorithm to determine a preliminary high-risk area. From the preliminary high-risk area, a set of coordinates is extracted, and a time series analysis algorithm is used to analyze the temperature change and the fluctuation of 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 by the cold chain vehicle position coordinates to obtain an adjusted high-risk area. The adjusted high-risk area is obtained, and the road condition level in the coordinate set is processed to obtain a graded risk table. Through the graded risk table, the temperature change data in the real-time state table is combined to determine whether the temperature control risk is continuous to obtain a persistence risk table. According to the persistence risk table, a dynamic monitoring record is generated for the coordinate set in the high-risk area to determine the final risk area coordinates based on the risk distribution map.

[0050] In some embodiments, after generating the heat map, the customer distribution density data in the heat map is spatially overlaid with road condition information through geographic information system (GIS) technology. First, both sets of data need to be converted to a unified geographic coordinate system, such as the WGS84 coordinate system, to ensure consistency and accuracy of the data. Then, using GIS software or custom algorithms, the data of the two layers is combined 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 conditions. 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, thereby generating a comprehensive evaluation overlay map.

[0051] In some embodiments, when using a genetic algorithm to optimize the original flow path of the cold chain vehicle, an initial population is first constructed based on the risk distribution map and the data of the boundary range of the logistics bottleneck area. Each individual represents a possible flow path, and its gene code 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 by the fitness function, which takes into account factors such as path length, temperature control coefficient, and real-time road condition information. For example, the fitness can be defined as the total driving distance plus the temperature fluctuation penalty term and the weighted sum of congestion level weights.

[0052] Among them, according to the fitness value, excellent individuals are selected into the next generation, and new solutions are generated by crossover and mutation operations. Crossover operation usually uses partial mapping crossover (PMX) or sequential crossover (OX) to ensure the effectiveness of the offspring path; mutation is achieved by exchanging the positions of two nodes, and the mutation probability is generally set to a small value (such as 0.1). After multiple iterations (such as 50 times), as the fitness gradually improves, the final convergence is to a global optimal solution or a flow path close to the optimal solution.

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

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

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

[0056] Figure 2 A method flow chart for updating the cold chain transportation resource allocation scheme is shown in FIG. 8, which includes the following steps S201 to S204. Figure 2

[0057] Step S201, updating the delivery schedule of the cold chain vehicle according to the optimized original flow path.

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

[0059] Step S203, referring to the updated delivery schedule, iteratively optimizing the optimized original flow path by using the simulated annealing algorithm, and outputting the flow path satisfying the global optimum.

[0060] Step S204, taking the re-divided cold storage service range, the flow path satisfying the global optimum, and the updated delivery schedule as the updated cold chain transportation resource allocation scheme.

[0061] In the embodiments of the present application, when updating the cold chain transportation resource allocation scheme according to the optimized original flow path, not only the delivery schedule of the cold chain vehicle is adjusted, but also the service range of the cold storage is re-divided, and then the simulated annealing algorithm is used for iterative optimization, and finally the flow path satisfying the global optimum is obtained.

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

[0063] Figure 3 A method flow chart for updating the delivery schedule of the cold chain vehicle is shown in FIG. 9, which includes the following steps S301 to S303. Figure 3

[0064] ​​Step S301, extracting the time stamp sequence of the path nodes in the optimized original flow path, and extracting the demand peak period in the distribution heat map.

[0065] Step S302, adjusting the time stamp order of different path nodes in the time stamp sequence by referring to the demand peak period by using the time window constraint algorithm, to obtain an adjusted time stamp sequence.

[0066] Step S303, updating the delivery schedule of the cold chain vehicle according to the adjusted time stamp sequence.

[0067] In the embodiments of the present application, in order to further optimize the delivery process, the time stamp sequence of the path nodes in the optimized original flow path is extracted, and the demand peak period in the distribution heat map of the to-be-supplied goods point is combined, and the time stamp order of different path nodes is adjusted by using the time window constraint algorithm, and then the delivery schedule of the cold chain vehicle is updated. This method effectively relieves traffic pressure, reduces waiting time, improves delivery efficiency and service quality, especially in peak period, and can also smoothly carry out goods delivery, greatly enhancing the experience of the to-be-supplied goods point.

[0068] In some embodiments, the time stamp sequence corresponding to the path nodes is obtained from the optimized original flow path, and the sorting method is used to arrange in time sequence to obtain an ordered time stamp set. The heat map is generated by the distribution data of the to-be-supplied goods point, the distribution characteristics of the demand peak period are extracted, and the time range of the peak period is determined. For the time stamp sequence and the demand peak period, the time window constraint algorithm is used to adjust the node time in the time stamp sequence to obtain a preliminary delivery schedule. If the node time exceeds the time window corresponding to the demand peak period, the time is redistributed by the constraint algorithm to generate an adjusted delivery schedule. According to the adjusted delivery schedule, combined with the path nodes in the optimized path, the delivery time of each node is calculated to obtain a delivery time sequence synchronized with the path. By the delivery time sequence and the distribution characteristics of the to-be-supplied goods point in the heat map, it is judged whether there is a time conflict, if there is, the delivery time of the conflict node is adjusted by using the priority sorting method to generate a final delivery schedule.

[0069] As some feasible embodiments, in the process of adjusting the time stamp order of different path nodes in the time stamp sequence, the adjustment strategy includes the peak avoidance principle, the high inventory supply priority principle, and / or the minimum global completion time principle of the cold chain vehicle. The adjusted time stamp sequence is a time stamp sequence that is more in line with the scheduling optimization, and under ideal conditions, it can make the overall receipt time of the to-be-supplied goods point shortest and the delivery completion time of the cold chain vehicle as early as possible.

[0070] In some embodiments, the time stamp sequence of the path nodes can be extracted from the optimized original flow path, for example, the time stamp of node A (116.408°E, 39.914°N) is 08:30, the time stamp of node B (116.412°E, 39.916°N) is 08:35, and the time stamp of node C (116.415°E, 39.918°N) is 08:40. Combined with the demand peak period in the distribution heat map of the supply point, for example, the area X (116.410°E, 39.915°N to 116.414°E, 39.919°N) is in demand peak from 08:45 to 09:15, and the area Y (116.405°E, 39.917°N to 116.409°E, 39.921°N) is in demand peak from 09:00 to 09:30. By time window constraint algorithm, the time stamp of the path node is matched with the demand peak period, for example, the arrival time of node C is adjusted to 08:45 to meet the peak demand of area X, and the arrival time of node D (116.407°E, 39.920°N) is adjusted to 09:00 to meet the peak demand of area Y. Finally, a distribution schedule synchronized with the path is generated, for example, the distribution time from node A to node B is 08:30 to 08:35, the distribution time from node B to node C is 08:35 to 08:45, the distribution time from node C to node D is 08:45 to 09:00, and the distribution time from node D to node E (116.410°E, 39.922°N) is 09:00 to 09:15.

[0071] In some embodiments, the service range of different cold stores can be re-divided in the following way.

[0072] For example, by extracting coordinate information from the cold store location, preliminary matching is performed in combination with node data in the optimized original flow path to obtain the correspondence between the cold store and the path node. The distribution radius is obtained from the matching result, and the K-means clustering algorithm is used to divide the service range for the boundary range of the bottleneck area, and the adjusted site coordinates are output. According to the adjusted site coordinates, the distribution characteristics of the covered area are calculated to determine the service range boundary of each cold store. The overlapping part of the covered area and the node data is obtained, and 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 store to the node is calculated in combination with the distribution radius to determine whether there are out-of-range nodes. The out-of-range nodes are extracted from the distance distribution, and the site coordinates are adjusted using the coordinate offset method to obtain the final cold store location distribution. Through the final cold store location distribution, a service range division scheme synchronized with the optimized original flow path is generated in combination with the covered area.

[0073] In some embodiments, the current coordinates of the cold storage locations, such as 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), can be obtained from the cold storage location data, and combined with the distribution nodes in the optimized original flow 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), to calculate the Euclidean distance between each cold storage and distribution node, forming a distance matrix. For distribution radius restrictions, such as setting the maximum distribution radius to 5 kilometers, filter out nodes that exceed the range, such as node C, which is 5.2 kilometers away from cold storage 1, and mark it as a bottleneck area. Using the K-means clustering algorithm, taking the cold storage location as the initial clustering center, setting the number of clusters to 3, iteratively calculating the distance of each node to the cluster center, and reassigning the node ownership, such as adjusting 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 a polygon boundary covering the area, such as the coverage range of cold storage 1 is 116.400°E to 116.410°E, 39.908°N to 39.916°N, the coverage range of cold storage 2 is 116.415°E to 116.425°E, 39.915°N to 39.925°N, and the coverage range of cold storage 3 is 116.428°E to 116.435°E, 39.925°N to 39.935°N. Visualize the adjusted cold storage service range through geographic information system to maximize distribution efficiency.

[0074] In some embodiments, the flow path that satisfies the global optimum can be obtained as follows.

[0075] In some embodiments, the dynamic update record can be obtained through the real-time state table, combined with the coordinate adjustment data of the cold storage location, to generate the initial optimized original flow path and time table distribution. Extract temperature changes and road conditions from the dynamic update record, and use the simulated annealing algorithm to iteratively optimize the optimized original flow path for fluctuations in these information, to obtain the iteratively optimized flow path.

[0076] In addition, in some embodiments, further optimization can also be made to the circulation path and the delivery schedule. For example, for the updated combined delivery schedule, it is determined whether there is a time period that does not match the temperature change, and if there is, the cold storage site is re-allocated through coordinate adjustment to further optimize the circulation path. If not, this step is directly skipped. On this basis, for the fluctuation characteristics of the road condition information, the arrival time of each node in the circulation path is further calculated to determine the delivery schedule that meets the global optimization under the current factors. Through the global optimal delivery schedule under the current factors, combined with the real-time state in the dynamic update record, the priority order of the circulation path is adjusted to generate a circulation path that synchronizes with the temperature change, so as to extract the key nodes of information fluctuation in the adjusted circulation path, and fine-tune the cold storage site using the coordinate offset method to obtain the final circulation path and delivery schedule. According to the final path and delivery schedule, combined with the real-time state and road condition information, a circulation scheme consistent with the global optimal target is generated.

[0077] In some specific embodiments, the coordinate data of the current cold storage is extracted from the real-time state 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 (118.530°E, 32.100°N), and the real-time position 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). Combined with the data collected by the temperature sensor, such as the real-time temperature of node X being -18.5°C, node Y being -19.2°C, and node Z being -17.8°C, and the traffic congestion index returned by the road condition API (node X being 0.7, node Y being 0.5, and node Z being 0.9), a target function is constructed, which comprehensively considers transportation time, temperature fluctuation, and path cost. The simulated annealing algorithm is used, the initial temperature is set to 1000, the cooling coefficient is 0.95, the iteration number is 500 times, the delivery order of two nodes is randomly exchanged in each iteration, and the change of the target function value is calculated. For example, in one iteration, the delivery order of node Y and node Z is exchanged, the target function value decreases from the initial 1200 to 1150, and the exchange is accepted. After multiple iterations, the optimal solution is converged, and the global optimal path is output as cold storage A→node X→node Y→cold storage B→node Z, the total transportation time is 2.3 hours, and the temperature fluctuation is controlled within ±1°C. At the same time, the time schedule is generated, the delivery time of node X is 08:00-08:30, the delivery time of node Y is 09:00-09:30, and the delivery time of node Z is 10:00-10:45, ensuring that each node completes the delivery within the time window.

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

[0079] In an example, the boundary range of the logistics bottleneck area can be determined in the following manner.

[0080] Figure 4 A method flowchart for determining the boundary range of the logistics bottleneck area is shown in FIG. 4. Figure 4 As shown, the method includes steps S401 to S405.

[0081] In step S401, a density clustering algorithm is used to determine a target area in which the density of the to-be-supplied delivery points and the road condition complexity are both higher than a preset threshold, for the superimposed map.

[0082] In step S402, a set of potential logistics bottleneck points is determined in the target area, and for each potential logistics bottleneck point, the number of to-be-supplied delivery points and the average road condition level in the influence range of the potential logistics bottleneck point are calculated to generate a bottleneck influence factor.

[0083] In step S403, different potential logistics bottleneck points are sorted according to the value of the bottleneck influence factor, and a specified number of potential logistics bottleneck points are selected as key logistics bottleneck points.

[0084] In step S404, a geographic boundary detection algorithm is used to determine the influence range of each key logistics bottleneck point and determine the boundary coordinate set corresponding to each influence range.

[0085] In step S405, the boundary range of the logistics bottleneck area is constructed 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 to update the original flow path of the optimized cold chain vehicle, and on the other hand, the road condition data and the density of the to-be-supplied delivery points in the boundary can be combined to calculate a comprehensive congestion index of each bottleneck area, which can be used to quantify the logistics pressure.

[0087] In some embodiments, the delivery address data of the past 30 days is extracted from the to-be-supplied point order database, the address is converted into latitude and longitude coordinates (such as 116.404 °E, 39.915 °N) using a geocoding service, a kernel density estimation algorithm is used to generate a to-be-supplied point distribution heat map, the bandwidth parameter is set to 0.02, and the grid resolution is 100 m x 100 m. For the area in the heat map with a density exceeding a threshold value of 0.8, spatial superposition analysis is performed with real-time traffic data (such as road congestion levels provided by the Gaode API), a DBSCAN clustering algorithm is used to perform density clustering on the superimposed data points, the neighborhood radius ε is set to 300 m, and the minimum sample size MinPts is set to 15, and a logistics bottleneck area is identified. The convex hull boundary coordinates (such as the polygon vertex set 116.402 °E, 39.918 °N to 116.406 °E, 39.920 °N) of the clustering result are extracted, the congestion index (such as 1.2) of the real-time traffic and the historical average travel speed (such as 20 km / h) are combined, and the regional comprehensive congestion coefficient (such as 0.75) is calculated. The bottleneck area boundary, the congestion index, and the associated to-be-supplied point order quantity (such as 500 orders per day) are integrated into structured data, transmitted to the path optimization engine through a REST interface, and trigger the generation of a dynamic scheduling strategy.

[0088] The application also provides a device embodiment that continues the above-mentioned embodiment, is used to implement the method steps of the above-mentioned embodiment, has the same name meaning as the above-mentioned embodiment, has the same technical effect as the above-mentioned embodiment, and will not be described here.

[0089] As shown in Figure 5 The application provides a cold chain transportation resource allocation device 500, which comprises:

[0090] The generation unit 501 is configured to generate a real-time state table containing position coordinates, temperature values and road condition levels according to the real-time position, temperature change and road condition information of the cold chain vehicle. The generation unit 501 is further configured to identify temperature control risk points according to the change data of the temperature values in the real-time state table, and integrate the temperature control risk points, position coordinates and road condition levels to generate a risk distribution map. The processing unit 502 is configured to generate a heat map according to the distribution data of the to-be-supplied goods points, superimpose the heat map on the road condition information to obtain a superimposed map, and determine a logistics bottleneck area boundary range according to the superimposed map. The logistics bottleneck area boundary range represents a key point or a key area that causes a decrease in logistics efficiency, delay or even a decrease in service quality. The processing unit 502 is further configured to optimize the original circulation path of the cold chain vehicle according to the boundary range of the risk distribution map and the boundary range of the logistics bottleneck area boundary range respectively, and obtain an optimized original circulation path by using a genetic algorithm. The execution unit 503 is configured to update the cold chain transportation resource allocation scheme according to the optimized original circulation path, and perform scheduling on the cold chain vehicle, the to-be-supplied goods points and the cold storage according to the updated cold chain transportation resource allocation scheme.

[0091] In an embodiment, the execution unit 503 updates the cold chain transportation resource allocation scheme according to the optimized original circulation path in the following manner: updating the delivery schedule of the cold chain vehicle according to the optimized original circulation path; matching the position data of the cold storage with the optimized original circulation path, and re-dividing the service ranges of different cold storages according to the matching result by using a K-means clustering algorithm; referring to the updated delivery schedule, iteratively optimizing the optimized original circulation path by using a simulated annealing algorithm, and outputting a circulation path satisfying global optimization; and taking the re-divided service ranges of the cold storages, the circulation path satisfying global optimization and the updated delivery schedule as the updated cold chain transportation resource allocation scheme.

[0092] In an embodiment, the execution unit 503 updates the delivery schedule of the cold chain vehicle according to the optimized original circulation path in the following manner: extracting a time stamp sequence of path nodes in the optimized original circulation path, and extracting a demand peak period in the distribution heat map. Referring to the demand peak period, the execution unit 503 adjusts the time stamp order of different path nodes in the time stamp sequence by using a time window constraint algorithm, and obtains an adjusted time stamp sequence. The execution unit 503 updates 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 based on the overlay map as follows: For the overlay map, a density clustering algorithm is used to determine target areas where both the density of supply points and the road condition complexity are higher than a preset threshold. Within the target area, a set of potential logistics bottleneck points is determined, and for each potential bottleneck point, the number of supply points and the average road condition level within its influence range 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 selected as key logistics bottleneck points. A geographic boundary detection algorithm is used to determine the influence range of each key logistics bottleneck point, and the corresponding set of boundary coordinates for each influence range is determined. Based on all boundary coordinates in the complete set of boundary coordinates, the boundary range of the logistics bottleneck area is constructed.

[0094] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

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

[0096] like Figure 6 As shown, one embodiment of this application provides an electronic device 600. The electronic device 600 includes a memory 601, a processor 602, and an input / output (I / O) interface 603. The memory 601 stores instructions. The processor 602 is used to execute the cold chain transportation resource allocation method of this application embodiment by calling the instructions stored in the memory 601. The processor 602 is connected to both the memory 601 and the I / O interface 603, for example, via 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 program for the cold chain transportation resource allocation method involved in the embodiments of this application. The processor 602 executes various functional applications and data processing of the electronic device 600 by running the program stored in the memory 601.

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

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

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

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

[0102] Although the operations in the diagrams are described in a particular, sequential order, this should not be understood as a requirement that these operations be performed in the order described, nor that all illustrated operations be performed, to achieve desirable results. In certain circumstances, multitasking and parallel processing can be advantageous.

[0103] The methods, devices, apparatuses, and storage media of the present application can be implemented using standard programming techniques, with rules-based logic or other logic that can be implemented in software, hardware, or both. It should be noted that the words "component" and "module," as used herein and in the claims, can refer to one or more hardware or software elements.

[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, a software module is implemented using a computer program product comprising a computer-readable medium containing computer program code, which can be executed by a computer processor for performing any or all of the steps, operations, or procedures described.

[0105] The foregoing description of the present application has been presented for the purposes of illustration and description. It is not intended to be exhaustive or to limit the application to the precise form disclosed. Various modifications and variations are possible in light of the above teachings or can be acquired from practice of the application. Other embodiments can be apparent to those skilled in the art and can be derived from the description without departing from the spirit of the application. The embodiments were chosen and described in order to best explain the principles of the application and its practical application, and to thereby enable others skilled in the art to best utilize the application in various embodiments and various modifications as are suited to the particular use contemplated.

[0106] With respect to the devices in the above-described embodiments, the specific manner in which the various modules perform operations has been described in detail in the embodiments related to the methods, and will not be described in detail here.

[0107] It is further understood that "connected" can include the presence of one or more intervening components, or be connected without intervening components.

[0108] It is further understood that, although the operations in the diagrams are described in a particular, sequential order, this should not be understood as a requirement that these operations be performed in the order described, nor that all illustrated operations be performed, to achieve desirable results. In certain circumstances, multitasking and parallel processing can be advantageous.

[0109] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the field of this application that are not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

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

[0111] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A cold chain transportation resource allocation method, characterized in that, The application comprises the following steps: According to the real-time position, temperature change and road condition information of the cold chain vehicle, a real-time state table containing position coordinates, temperature values and road condition levels is generated; According to the change data of the temperature values in the real-time state table, a temperature control risk point is identified, and the temperature control risk point, the position coordinates and the road condition level are integrated to generate a risk distribution map; A heat map is generated according to the distribution data of the to-be-supplied goods points, the heat map is superimposed with the road condition information to obtain a superimposed map, and a logistics bottleneck area boundary range is determined according to the superimposed map; wherein the logistics bottleneck area boundary range represents a key point or a key area that causes a decrease in logistics efficiency and a decrease in service quality; According to the boundary range of the risk distribution map and the logistics bottleneck area boundary range respectively, a genetic algorithm is used to optimize the original flow path of the cold chain vehicle to obtain an optimized original flow path; According to the optimized original flow path, the cold chain transportation resource allocation scheme is updated, and the scheduling of the cold chain vehicle, the to-be-supplied goods points and the cold storage is performed according to the updated cold chain transportation resource allocation scheme; The determination of the logistics bottleneck area boundary range according to the superimposed map comprises the following steps: For the superimposed map, a density clustering algorithm is used to determine a target area in which the to-be-supplied goods point density and the road condition complexity are higher than a preset threshold; A set of potential logistics bottleneck points is determined in the target area, and for each potential logistics bottleneck point, the number of to-be-supplied goods points and the average road condition level in the influence range of the potential logistics bottleneck point are calculated to generate a bottleneck influence factor; According to the value of the bottleneck influence factor, different potential logistics bottleneck points are sorted to select a specified number of potential logistics bottleneck points as key logistics bottleneck points; Through a geographic boundary detection algorithm, the influence range of each key logistics bottleneck point is determined, and a boundary coordinate set corresponding to each influence range is determined; According to all boundary coordinates in all boundary coordinate sets, the logistics bottleneck area boundary range is constructed.

2. The method of claim 1, wherein, The updating of the cold chain transportation resource allocation scheme according to the optimized original flow path comprises the following steps: According to the optimized original flow path, the delivery schedule of the cold chain vehicle is updated; The position data of the cold storage is matched with the optimized original flow path, and the service range of different cold storages is re-divided according to the matching result by using a K-means clustering algorithm; Referring to the updated delivery schedule, a simulated annealing algorithm is used to iteratively optimize the optimized original flow path to output a flow path that meets the global optimum; The re-divided cold storage service range, the flow path that meets the global optimum and the updated delivery schedule are used as the updated cold chain transportation resource allocation scheme.

3. The method of claim 2, wherein, The updating of the delivery schedule of the cold chain vehicle according to the optimized original flow path comprises the following steps: In the optimized original flow path, the time stamp sequence of the path node is extracted, and the demand peak period is extracted in the distribution heat map; The time window constraint algorithm refers to the demand peak period, adjusts the timestamp sequence of different path nodes in the timestamp sequence, and obtains an adjusted timestamp sequence; According to the adjusted timestamp sequence, update the delivery schedule of the cold chain vehicle.

4. A cold chain transportation resource allocation apparatus, characterized in that, Comprise: The generating unit is configured to generate a real-time state table containing position coordinates, temperature values and road conditions according to real-time position, temperature change and road condition information of the cold chain vehicle; And for temperature control risk point identification according to the change data of the temperature value in the real-time state table, and data integration of the temperature control risk point, the position coordinates and the road condition level to generate a risk distribution map; The processing unit is configured to generate a heat map according to the distribution data of the to-be-supplied goods point, superimpose the heat map and 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 point or key area that causes the reduction of logistics efficiency and the decline of service quality; and for optimizing the original circulation path of the cold chain vehicle according to the boundary range of the risk distribution map and the logistics bottleneck area respectively, an optimized original circulation path is obtained; The execution unit is configured to update the cold chain transportation resource allocation scheme according to the optimized original circulation path, and perform scheduling for the cold chain vehicle, the to-be-supplied goods point and the cold storage according to the updated cold chain transportation resource allocation scheme; The processing unit determines the boundary range of the logistics bottleneck area according to the superimposed map in the following way: For the superimposed map, a density clustering algorithm is used to determine a target area where the density of the to-be-supplied goods point and the road condition complexity are higher than a preset threshold; A set of potential logistics bottleneck points is determined in the target area, and for each potential logistics bottleneck point, the number of to-be-supplied goods points and the average road condition level in the influence range of the potential logistics bottleneck point are calculated to generate a bottleneck influence factor; According to the value of the bottleneck influence factor, different potential logistics bottleneck points are sorted to extract a specified number of potential logistics bottleneck points as key logistics bottleneck points; By a geographic 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 boundary coordinates in all boundary coordinate sets, the boundary range of the logistics bottleneck area is constructed.

5. The apparatus of claim 4, wherein, The execution unit updates the cold chain transportation resource allocation scheme according to the optimized original circulation path in the following way: According to the optimized original circulation path, update the delivery schedule of the cold chain vehicle; Match the position data of the cold storage with the optimized original circulation path, and redivide the service range of different cold storages according to the matching result by using a K-means clustering algorithm; According to the updated delivery schedule, the optimized original circulation path is iteratively optimized by using a simulated annealing algorithm, and a circulation path meeting the global optimum is output. The re-divided cold storage service range, the global optimal flow path and the updated distribution schedule are taken as an updated cold chain transportation resource allocation scheme.

6. The apparatus of claim 5, wherein, The execution unit updates the distribution schedule of the cold chain vehicle according to the optimized original flow path in the following manner: The time stamp sequence of the path node in the optimized original flow path is extracted, and the demand peak period in the distribution heat map is extracted; A time window constraint algorithm is used to refer to the demand peak period to adjust the time stamp sequence of different path nodes in the time stamp sequence to obtain an adjusted time stamp sequence; The distribution schedule of the cold chain vehicle is updated according to the adjusted time stamp sequence.

7. An electronic device comprising a memory, a processor, and a computer program stored on the memory, wherein the computer program comprises instructions that, when executed by the processor, cause the electronic device to perform the method of any one of claims 1-6. The processor executes the computer program to implement the method of any one of claims 1-3.

8. A computer readable storage medium having stored thereon computer programs / instructions, characterized in that, The computer program / instruction is executed by the processor to implement the method of any one of claims 1-3.

Images