Supply chain monitoring and optimizing method and system

Abstract

The invention relates to the technical field of supply chain management, and particularly discloses a supply chain monitoring and optimizing method and system, and the method comprises the steps: obtaining the real-time Internet of Things data of a to-be-delivered package set and a transport vehicle set in a warehouse; constructing a dynamic bipartite graph based on real-time Internet of Things data; based on the matching degree of the spatial index and / or the temporal index, defining the matching weight of the edge connected with the vertex; operating a dynamic matching algorithm, and generating a distribution scheme about the parcel and the vehicle according to the matching weight; converting the distribution scheme into a scheduling instruction of a warehouse operation management system; according to the method, dynamic matching of the parcels and the vehicles is realized by acquiring the real-time Internet of Things data, constructing the dynamic bipartite graph, operating the dynamic matching algorithm and generating the distribution scheme of the parcels and the vehicles, the distribution efficiency of the parcels and the vehicles can be effectively improved, the utilization rate of vehicle resources is improved, and effective cooperation of warehouse operation and transportation links is realized; and on-time delivery of orders can be effectively ensured.

Description

Technical Field

[0001] The present application relates to the technical field of supply chain management, and more specifically, to a supply chain monitoring and optimization method and system. Background Art

[0002] For large-scale commodity distribution companies, the core business is to receive, store and distribute massive quantities of goods from numerous suppliers to retailers and end customers. Their orders are high-frequency and small-batch, which requires extremely high response speed and flexibility of the supply chain.

[0003] To meet the challenges, enterprises have built a complex supply chain network that includes multiple regional distribution centers and urban distribution warehouses. To improve operational efficiency and visualization, enterprises deploy IoT devices at key nodes of the supply chain. The storage center uses sensors to monitor the storage location, automation equipment and personnel status in real time; all vehicles in the transportation link are equipped with on-board IoT terminals to collect and transmit data such as vehicle location, speed, and cargo volume to the central data platform in real time.

[0004] Although IoT devices are widely deployed, in the high-frequency and small-batch order model, the efficiency of matching packages and vehicles is low, warehouse operations and transportation links are closely related but difficult to coordinate, and local problems are easily transmitted to the overall process. Therefore, in complex distribution supply chain scenarios, integrating and utilizing warehouse operations and transportation vehicle IoT data to achieve real-time perception and coordinated scheduling to improve resource utilization efficiency and ensure on-time delivery of orders is a technical problem that needs to be solved urgently.

[0005] There is currently no effective technical solution to the above problems. Summary of the invention

[0006] The purpose of this application is to provide a supply chain monitoring and optimization method and system to achieve dynamic matching of packages and vehicles, effectively improve the allocation efficiency of packages and vehicles and the utilization rate of vehicle resources, and achieve effective coordination between warehouse operations and transportation links.

[0007] In a first aspect, the present application provides a supply chain monitoring and optimization method, which is applied in a warehouse operation management system, and the method comprises the following steps: S1. Obtain real-time IoT data of the collection of packages to be shipped and the collection of transport vehicles in the warehouse; S2. Constructing a dynamic bipartite graph based on the real-time IoT data, wherein a vertex set on one side of the dynamic bipartite graph represents the set of packages to be sent, and a vertex set on the other side represents the set of transport vehicles; S3, defining the matching weight of the edge connecting the vertices corresponding to the set of packages to be shipped and the vertices corresponding to the set of transport vehicles based on the matching degree of the spatial index and / or the temporal index; S4. Run the dynamic matching algorithm, and generate an allocation plan for packages and vehicles according to the matching weights, where the allocation plan is used to guide the warehouse loading operation and vehicle scheduling; S5. Convert the allocation plan into a scheduling instruction of the warehouse operation management system.

[0008] The supply chain monitoring and optimization method of the present application obtains real-time Internet of Things data, constructs a dynamic bipartite graph and runs a dynamic matching algorithm to generate an allocation plan for packages and vehicles, realizes the dynamic matching of packages and vehicles, can effectively improve the allocation efficiency of packages and vehicles, and improve the utilization rate of vehicle resources, realizes the effective coordination of warehouse operations and transportation links, and can effectively ensure the on-time delivery of orders.

[0009] In the described supply chain monitoring and optimization method, the real-time Internet of Things data includes the destination, volume, weight, time limit requirements of the package, and the location, speed, remaining available space, and estimated arrival time of the vehicle.

[0010] The above specific data items provide basic information for constructing a dynamic bipartite graph reflecting the potential matching relationship between packages and vehicles. Based on these data, the matching weights of the edges connecting the package vertices and the vehicle vertices can be defined.

[0011] In the described supply chain monitoring and optimization method, step S1 includes: S11. Scan the labels on the packages to collect the unique identification codes of each package in the set of packages to be shipped, and use the GPS positioning module to collect the location information of each vehicle in the set of transport vehicles; S12. Upload the collected unique identification codes and vehicle location information to the cloud data center for cleaning, conversion and integration by the cloud data center to form a set of packages to be shipped including the destination, volume, weight, and time limit requirements of the packages, and a set of transport vehicles including the vehicle location, speed, remaining available space, and estimated arrival time.

[0012] In this example, through the cleaning, conversion and integration processing of the cloud data center, the original identification and location data are enriched and structured, forming a set of packages to be shipped and a set of transport vehicles containing all necessary attributes. Thereby, it provides an accurate and complete real-time data basis for subsequent construction of a dynamic bipartite graph and matching calculation, and improves the effectiveness of the entire supply chain monitoring and optimization method.

[0013] In the described supply chain monitoring and optimization method, the spatiality indicators include one or more of the matching degree between the destination of the package and the predetermined route of the vehicle, the matching degree between the volume of the package and the remaining available space of the vehicle, and the distance between the current location of the vehicle and the warehouse where the package is located, and the temporality indicators include the matching degree between the time limit requirements of the package order and the estimated delivery time of the vehicle.

[0014] The described supply chain monitoring and optimization method, wherein step S3 includes: S31. Obtain the destination coordinates of each package in the set of packages to be dispatched, obtain multiple route coordinate points on the predetermined route of each vehicle in the set of transport vehicles, calculate the minimum geographical distance between each of the destination coordinates and the multiple route coordinate points of each vehicle, and obtain a distance set; S32. According to the distance set, use the Gaussian function to calculate the spatial matching degree between the destination of each package and the vehicle's predetermined route; S33. Obtain the latest delivery time of each package in the set of packages to be dispatched, calculate the estimated delivery time of each vehicle in the set of transport vehicles for each package, calculate the time margin between the latest delivery time and the estimated delivery time, and obtain a time margin set; S34. According to the time margin set, use the sigmoid function to calculate the time matching degree between each package and each vehicle; S35. According to the spatial matching degree and the time matching degree, perform weighted fusion calculation to obtain the matching weight between each package and each vehicle.

[0015] The described supply chain monitoring and optimization method, wherein step S35 includes: S351. According to the preset weight coefficient of the spatial matching degree and the preset weight coefficient of the time matching degree, use the weighted average method to fuse the spatial matching degree and the time matching degree to obtain an initial matching weight; S352. Obtain the vehicle type preference parameter, and the vehicle type preference parameter indicates the priority of different vehicle types; S353. According to the vehicle type preference parameter, adjust the initial matching weight to obtain the final matching weight.

[0016] The described supply chain monitoring and optimization method, wherein step S4 includes: S41. Obtain the warehouse loading resource limit information in the warehouse operation management system; S42. Obtain the vehicle driving route information in the vehicle scheduling system, and the vehicle driving route information includes multiple unloading points of the vehicle and the time window requirements of each unloading point; S43. Use the warehouse loading resource limit information and the vehicle driving route information as constraint conditions, and combine the matching weight, and use the dynamic matching algorithm to generate an initial allocation plan for each package; S44. According to the initial allocation plan, evaluate the matching degree between the arrival time of the vehicle at each unloading point and the time window requirement. If there is an unloading point that does not meet the time window requirement, adjust the matching relationship between the packages and the vehicles in the initial allocation plan, reallocate the packages that cause the time window not to be met to other vehicles that meet the time window requirement, and generate an adjusted allocation plan; S45. According to the adjusted allocation plan, evaluate the utilization rate of the warehouse loading resources. If the utilization rate of the warehouse loading resources is lower than the preset threshold, adjust the matching relationship between the packages and the vehicles in the adjusted allocation plan, reallocate the packages allocated to the vehicles with low resource utilization rate to the vehicles with high resource utilization rate, and generate a final allocation plan.

[0017] In the described supply chain monitoring and optimization method, the warehouse loading resource limit information includes the number of loading platforms and the number of loading personnel. Step S43 includes: S431. According to the matching weights, configure multiple alternative vehicles for each package, sort the multiple alternative vehicles according to the matching weights, and generate a set of alternative transportation plans based on the sorted alternative vehicles; S432. For each alternative transportation plan in the set of alternative transportation plans, based on the number of loading platforms and the number of loading personnel, evaluate the loading efficiency of the alternative transportation plan in the warehouse by using a pre-constructed loading efficiency evaluation model, and obtain a loading efficiency evaluation result; S433. For each alternative transportation plan, based on the multiple unloading points of the vehicle and the time window requirements of each unloading point, evaluate the degree of meeting the time window of the alternative transportation plan during the transportation process by using a pre-constructed time window satisfaction degree evaluation model, and obtain a time window satisfaction degree evaluation result; S435. According to the loading efficiency evaluation result and the time window satisfaction degree evaluation result, use the weighted average method to calculate the comprehensive score of each alternative transportation plan, and take the alternative transportation plan with the highest comprehensive score as the initial allocation plan for the corresponding package.

[0018] In the described supply chain monitoring and optimization method, step S5 includes: S51. Analyze the allocation plan, and extract the unique identification code of the package to be loaded and the corresponding vehicle identification information; S52. According to the unique identification code of the package, obtain the physical attribute information of the package from the warehouse operation management system; S53. According to the vehicle identification information, obtain the loading layout information of the vehicle from the warehouse operation management system; S54. Generate a loading sequence instruction according to the physical attribute information of the package and the loading layout information of the vehicle; S55. Convert the loading sequence instruction into a scheduling instruction executable by the warehouse operation management system.

[0019] In a second aspect, the present application also provides a supply chain monitoring and optimization system applied in a warehouse operation management system. The system includes: A data acquisition module for acquiring real-time Internet of Things data of the set of packages to be shipped and the set of transport vehicles inside the warehouse; A bipartite graph construction module for constructing a dynamic bipartite graph based on the real-time Internet of Things data. One vertex set of the dynamic bipartite graph represents the set of packages to be shipped, and the other vertex set represents the set of transport vehicles; A weight definition module for defining the matching weight of the edges connecting the vertices corresponding to the set of packages to be shipped and the vertices corresponding to the set of transport vehicles based on the matching degree of spatial metrics and / or temporal metrics; A matching algorithm module for running a dynamic matching algorithm and generating an allocation plan for packages and vehicles according to the matching weight. The allocation plan is used to guide the warehouse loading operation and vehicle scheduling; An instruction sending module for converting the allocation plan into a scheduling instruction of the warehouse operation management system.

[0020] The supply chain monitoring and optimization system of the present application realizes the dynamic matching of packages and vehicles, can effectively improve the allocation efficiency of packages and vehicles, and improve the utilization rate of vehicle resources, realizes the effective coordination of warehouse operations and transportation links, and can effectively ensure the timely delivery of orders.

[0021] As can be seen from the above, the present application provides a supply chain monitoring and optimization method and system. Among them, the supply chain monitoring and optimization method of the present application acquires real-time Internet of Things data, constructs a dynamic bipartite graph and runs a dynamic matching algorithm to generate an allocation plan for packages and vehicles, realizes the dynamic matching of packages and vehicles, can effectively improve the allocation efficiency of packages and vehicles, and improve the utilization rate of vehicle resources, realizes the effective coordination of warehouse operations and transportation links, and can effectively ensure the timely delivery of orders. Description of the Drawings

[0022] Figure 1 It is a flowchart of the supply chain monitoring and optimization method provided by an embodiment of the present application.

[0023] Figure 2 It is a schematic diagram of the dynamic bipartite graph constructed in step S2.

[0024] Figure 3 It is a schematic modular structure diagram of the supply chain monitoring and optimization system provided by an embodiment of the present application.

[0025] Reference Numerals: 201, data acquisition module; 202, bipartite graph construction module; 203, weight definition module; 204, matching algorithm module; 205, instruction sending module. Detailed Implementation Manner

[0026] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Usually, the components of the embodiments of the present application described and shown in the accompanying drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application to be protected, but only represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0027] It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of the present application, the terms "first", "second", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0028] In a first aspect, please refer to Figure 1 - Figure 2 , some embodiments of the present application provide a supply chain monitoring and optimization method, which is applied to a warehouse operation management system. The method includes the following steps: S1. Obtain real-time Internet of Things data of the set of packages to be shipped and the set of transport vehicles inside the warehouse; S2. Based on the real-time Internet of Things data, construct a dynamic bipartite graph. One vertex set of the dynamic bipartite graph represents the set of packages to be shipped, and the other vertex set represents the set of transport vehicles; S3. Define the matching weights of the edges connecting the vertices corresponding to the set of packages to be shipped and the vertices corresponding to the set of transport vehicles based on the matching degree of spatial indicators and / or temporal indicators; S4. Run a dynamic matching algorithm, and generate an allocation plan for packages and vehicles according to the matching weights. The allocation plan is used to guide warehouse loading operations and vehicle scheduling; S5. Convert the allocation plan into a scheduling instruction of the warehouse operation management system.

[0029] Specifically, the supply chain monitoring and optimization method of the embodiments of the present application solves the problems of efficient matching of packages and vehicles and coordination of warehouse loading and vehicle scheduling by integrating and utilizing real-time Internet of Things data.

[0030] More specifically, step S1 obtains the real-time Internet of Things data of the packages to be dispatched and the transport vehicles, provides the current status information of the system, and supports subsequent dynamic decision-making. The real-time Internet of Things data can be collected by devices such as sensors and vehicle-mounted terminals and transmitted to the data processing platform through the network.

[0031] More specifically, step S2 constructs a dynamic bipartite graph based on the real-time data, abstracts the matching relationship between packages and vehicles into a graph structure, and provides a model for algorithm processing. As Figure 2 shown, one side of the vertices of the dynamic bipartite graph represents packages, and the other side represents vehicles. There are undetermined edges between the package vertices and the vehicle vertices. Steps S3 - S4 are equivalent to determining the edges connecting the package vertices and the vehicle vertices to represent that the packages connected by the edges are transported by the corresponding vehicles. Among them, Figure 2 shows the edges connecting one of the packages (package 1).

[0032] More specifically, step S3 calculates the matching degree between packages and vehicles according to spatial indicators and temporal indicators, and defines the matching weights of the edges connecting package vertices and vehicle vertices to quantify the suitability of the matching, providing an evaluation criterion for the matching algorithm. The spatial indicators can involve the matching degrees of location, volume, etc., and the temporal indicators can involve the matching degree between the time limit requirements and the estimated delivery time.

[0033] More specifically, step S4 runs a dynamic matching algorithm, uses the matching weights calculated in step S3, and calculates the specific allocation plan for packages and vehicles. This plan guides the warehouse for package loading and the vehicle for transportation scheduling. The dynamic matching algorithm can adjust the matching results according to the changes in real-time data.

[0034] More specifically, step S5 converts the allocation plan generated in step S4 into scheduling instructions that can be recognized and executed by the warehouse operation management system, realizing the implementation of the optimization plan in actual operations. The scheduling instructions can include information such as the loading order of packages and the designated vehicles.

[0035] More specifically, when the supply chain monitoring and optimization method of the embodiment of the present application solves the technical problem of efficiently matching packages and vehicles using real-time data and coordinating warehouse loading and vehicle scheduling, its working principle is as follows: First, obtain the real-time Internet of Things data of the packages to be dispatched and the transport vehicles in the warehouse through step S1. These data reflect the current status of the packages (e.g., picked, waiting to be loaded) and the current status of the vehicles (e.g., location, available capacity). Thus, the system obtains the real-time information required for decision-making.

[0036] Next, in step S2, a dynamic bipartite graph is constructed based on the acquired real-time data. One side of the nodes in the graph represents the parcels to be dispatched, and the other side represents the transport vehicles. This graph structure intuitively represents the potential transport relationships between parcels and vehicles, laying a model foundation for subsequent matching calculations.

[0037] Then, in step S3, according to the predefined spatial and temporal metrics, the matching degree between each parcel to be dispatched and each transport vehicle is calculated, and this matching degree is defined as the weight of the corresponding edge in the bipartite graph. For example, if the destination of the parcel is close to the driving route of the vehicle, or the time limit requirement of the parcel matches the estimated arrival time of the vehicle, the corresponding matching weight is higher. Thus, the quality of the matching between the parcel and the vehicle is quantified.

[0038] Subsequently, in step S4, a dynamic matching algorithm is run. This algorithm takes the matching weights calculated in step S3 as input, considers possible constraints (such as vehicle capacity limitations), and calculates an optimal or near-optimal parcel-vehicle allocation plan. This plan clarifies which parcels should be transported by which vehicle and the possible loading order, etc. Thus, a plan guiding the actual operation is generated.

[0039] Finally, in step S5, the allocation plan generated in step S4 is converted into scheduling instructions that can be understood and executed by the warehouse operation management system. These instructions are sent to the warehouse operation management system to guide warehouse personnel or automated equipment in the loading operation of parcels, and are synchronized to the vehicle scheduling system to guide the scheduling and transportation of vehicles. Thus, the optimization plan is implemented at the actual operation level, improving the collaborative efficiency of warehouse loading and vehicle scheduling.

[0040] The supply chain monitoring and optimization method of the embodiment of the present application acquires real-time Internet of Things data, constructs a dynamic bipartite graph and runs a dynamic matching algorithm to generate a parcel-vehicle allocation plan, realizes the dynamic matching of parcels and vehicles, can effectively improve the allocation efficiency of parcels and vehicles, and improve the utilization rate of vehicle resources, realizes the effective collaboration between the warehouse operation and the transportation link, and can effectively ensure the on-time delivery of orders.

[0041] In some preferred embodiments, the real-time Internet of Things data includes various information such as the destination, volume, weight, time limit requirement of the parcel, and the location, speed, remaining available space, estimated arrival time of the vehicle.

[0042] Specifically, the destination information of the package is used to determine the geographical location of package delivery for spatial matching with the vehicle's predetermined route. The volume and weight information of the package is used to evaluate the impact of the package on the vehicle's loading space occupancy and load-bearing, and is associated with the remaining available space and load-bearing capacity of the vehicle. The time requirement of the package sets the latest delivery time of the package, which is used to compare with the vehicle's estimated arrival time to evaluate the time matching degree. The position and speed of the vehicle are used to track the vehicle status in real time, calculate the distance between the vehicle and the warehouse or package location, and estimate the arrival time. The remaining available space information of the vehicle indicates the space capacity currently available for loading packages in the vehicle. The vehicle's estimated arrival time information is the time estimated to reach a specific location based on the vehicle's current status and route.

[0043] More specifically, these specific data items above provide the basic information for constructing a dynamic bipartite graph reflecting the potential matching relationship between packages and vehicles. Based on these data, the matching weights of the edges connecting the package vertices and vehicle vertices can be defined. For example, the matching weights are calculated using indicators such as the spatial proximity between the package destination and the vehicle's predetermined route, the matching degree between the package volume and weight and the vehicle's remaining space, and the time margin between the package time requirement and the vehicle's estimated arrival time.

[0044] More specifically, in addition, when running the dynamic matching algorithm, these data items can be used as inputs and constraints. For example, considering the remaining available space limit of the vehicle and the time requirement of the package, a more reasonable and effective package-vehicle allocation plan can be generated, improving the warehouse loading efficiency and transportation and delivery timeliness.

[0045] In some preferred embodiments, step S1 includes: S11. Scan the label on the package to collect the unique identification code of each package in the set of packages to be dispatched, and use the GPS positioning module to collect the position information of each vehicle in the set of transport vehicles; S12. Upload the collected unique identification code and vehicle position information to the cloud data center for cleaning, transformation and integration by the cloud data center to form a set of packages to be dispatched including the destination, volume, weight, and time requirement of the package, and a set of transport vehicles including the vehicle position, speed, remaining available space, and estimated arrival time.

[0046] Specifically, the label on the package is preferably an RFID label.

[0047] More specifically, scanning the RFID label on the package to collect the unique identification code provides the basis for uniquely identifying each package to be dispatched. Using the GPS positioning module to collect the vehicle position information provides the basic data of the vehicle's real-time spatial position. Thus, the initial data collection of these two key resources, packages and vehicles, is realized.

[0048] More specifically, the unique identification codes and vehicle location information collected are uploaded to the cloud data center so that the data can be processed centrally. Cleaning in the cloud data center can remove errors or redundant data in the collection process and improve data quality.

[0049] More specifically, the cloud data center converts the cleaned data to unify the original data from different sources and formats. The cloud data center integrates the converted data by associating the collected basic identification and location information with the existing package attributes (such as destination, volume, weight, timeliness requirements) and vehicle attributes (such as speed, remaining available space, and estimated arrival time) in the system to form a structured and complete set of packages to be shipped and a set of transportation vehicles. This integration process ensures the accuracy and completeness of the data required for the subsequent construction of the dynamic bipartite graph and the calculation of matching weights, and also reduces the storage and analysis pressure of local data.

[0050] More specifically, through the cleaning, conversion and integration processing of the cloud data center, the original collected data is enriched and structured, forming a set of packages to be shipped and a set of transportation vehicles with all necessary attributes. This provides an accurate and complete real-time data foundation for the subsequent construction of a dynamic bipartite graph and matching calculations, improving the effectiveness of the entire supply chain monitoring and optimization method.

[0051] In some preferred embodiments, the spatial indicators include one or more of the degree of match between the destination of the package and the scheduled route of the vehicle, the degree of match between the volume of the package and the remaining available space of the vehicle, and the distance between the current position of the vehicle and the warehouse where the package is located. The temporal indicators include the degree of match between the timeliness requirements of the package order and the estimated delivery time of the vehicle.

[0052] Specifically, the definition of the above indicators enables the calculation of matching weights to reflect the actual spatial and temporal constraints between packages and vehicles. Specifically, for the problem of allocating packages and transport vehicles in warehouse operation management systems, the traditional method is vague in the content of spatial and temporal indicators when defining the matching weights of packages and vehicles, resulting in the allocation plan failing to fully consider constraints such as actual loading space, transportation routes and delivery timeliness, affecting operation efficiency and delivery punctuality. The supply chain monitoring and optimization method of the embodiment of the present application solves this problem by clearly defining spatial indicators and temporal indicators. Among them, the degree of matching between the destination of the package and the scheduled route of the vehicle is used to evaluate the degree of convenience of the vehicle route for the delivery of the package, the degree of matching between the volume of the package and the remaining available space of the vehicle is used to evaluate whether the vehicle has the ability to load the package, the distance between the current position of the vehicle and the warehouse where the package is located is used to evaluate the convenience of the vehicle to arrive at the warehouse, and the degree of matching between the timeliness requirements of the package order and the estimated delivery time of the vehicle is used to evaluate whether the vehicle can complete the delivery task within the specified time.

[0053] More specifically, by calculating the matching degree of these specific indicators, a matching weight that more accurately reflects the actual compatibility between the package and the vehicle can be generated. Thus, the subsequent dynamic matching algorithm can generate an allocation plan based on these more accurate weights, which can better consider the loading space limitations, optimize the transportation route selection, and ensure the timely delivery of packages, improving the efficiency and effectiveness of warehouse loading operations and vehicle scheduling.

[0054] In some preferred embodiments, step S3 includes: S31. Obtain the destination coordinates of each package in the set of packages to be dispatched, obtain multiple route coordinate points on the predetermined route of each vehicle in the set of transportation vehicles, calculate the minimum geographical distance between each destination coordinate and the multiple route coordinate points of each vehicle, and obtain a distance set; S32. According to the distance set, use the Gaussian function to calculate the spatial matching degree between the destination of each package and the predetermined route of the vehicle; S33. Obtain the latest delivery time of each package in the set of packages to be dispatched, calculate the estimated delivery time of each vehicle for each package, calculate the time margin between the latest delivery time and the estimated delivery time, and obtain a time margin set; S34. According to the time margin set, use the sigmoid function to calculate the time matching degree between each package and each vehicle; S35. According to the spatial matching degree and the time matching degree, calculate the matching weight between each package and each vehicle by weighted fusion.

[0055] Specifically, the matching weight defined in the above steps is the basis for the subsequent dynamic matching algorithm to generate an allocation plan.

[0056] More specifically, step S31 obtains the package destination coordinates and the coordinate points on the vehicle's predetermined route, preparing data for spatial matching calculation. This process mainly calculates the minimum geographical distance between the package destination and the vehicle route points, thereby quantifying the spatial proximity.

[0057] More specifically, step S32 uses the Gaussian function to calculate the spatial matching degree based on the minimum geographical distance, quantifying the proximity of geographical locations as a numerical value. The smaller the distance, the higher the spatial matching degree.

[0058] More specifically, step S33 obtains the latest delivery time of the package and the estimated delivery time of the vehicle for the package, calculates the time margin, preparing data for time matching calculation, thereby quantifying the time feasibility.

[0059] More specifically, step S34 uses the sigmoid function to calculate the time matching degree based on the time margin, quantifying the satisfaction degree of the time window as a numerical value. The larger the time margin, the higher the time matching degree.

[0060] More specifically, in step S35, the calculated spatial matching degree and temporal matching degree are weighted and fused to obtain the final matching weight.

[0061] More specifically, this matching weight comprehensively reflects the spatial proximity between the package destination and the vehicle route, as well as the temporal matching degree between the package timeliness requirement and the vehicle delivery capacity, providing a quantitative basis for the subsequent dynamic matching algorithm, solving the problem of how to specifically quantify and fuse spatial and temporal indicators, improving the accuracy of the matching weight, and thus optimizing the package and vehicle allocation scheme. Through these specific steps, the method provides an operable and quantifiable method to calculate the matching weight, providing reliable input for the subsequent dynamic matching algorithm, thereby supporting the generation of a more reasonable package and vehicle allocation scheme.

[0062] More specifically, in step S35, the matching weight can be simply calculated based on the following formula: matching weight = α * spatial matching degree + β * temporal matching degree; where α and β are the weight coefficients of the spatial matching degree and the temporal matching degree respectively, and the sum of the two is preferably 1, and α and β can be set according to actual usage requirements, such as 0.8 and 0.2.

[0063] In some preferred embodiments, step S35 includes: S351. According to the preset weight coefficient of the spatial matching degree and the preset weight coefficient of the temporal matching degree, the spatial matching degree and the temporal matching degree are fused by the weighted average method to obtain an initial matching weight; S352. Obtain the vehicle type preference parameter, and the vehicle type preference parameter indicates the priority of different vehicle types; S353. Adjust the initial matching weight according to the vehicle type preference parameter to obtain the final matching weight.

[0064] Specifically, the above processing process first calculates the weighted average value of the spatial matching degree between the package destination and the vehicle's predetermined route and the temporal matching degree between the package order timeliness requirement and the vehicle's estimated delivery time according to the preset weight coefficient of the spatial matching degree and the preset weight coefficient of the temporal matching degree, thereby obtaining the initial matching weight of the package and the vehicle. Subsequently, the initial matching weight is adjusted according to the obtained vehicle type preference parameter. Thus, the final matching weight not only considers the geographical location and time fit between the package and the vehicle, but also incorporates the suitability or importance of the vehicle type for the transportation task.

[0065] More specifically, the vehicle type preference parameter sets the priorities of different vehicle types (such as cold chain vehicles, ordinary trucks, small vehicles, large vehicles) in the matching process. The vehicle type preference parameter can be a numerical value, and the larger the value, the higher the priority of the vehicle type in matching a specific package.

[0066] More specifically, the process of adjusting the initial matching weight can be multiplying the initial matching weight by the corresponding vehicle type preference parameter, or adjusting it using other functional relationships.

[0067] More specifically, the final matching weight can comprehensively reflect the spatial proximity, time matching degree, and vehicle type preference, and is used for the subsequent dynamic matching algorithm.

[0068] More specifically, the technical contribution: By introducing the vehicle type preference parameter, it is possible to better utilize the advantages of different types of vehicles. For example, preferentially using cold chain vehicles to transport fresh products, or preferentially using small vehicles for last-mile delivery, thereby improving transportation efficiency and reducing transportation costs. In this embodiment, the process of obtaining the vehicle type preference parameter in step S352 can be obtaining the vehicle type preference parameters of each vehicle according to the package type. This adjustment makes the final matching weight more comprehensively reflect the matching degree between the package and the vehicle, comprehensively considering spatial, time, and vehicle type factors, provides a more accurate input for the subsequent dynamic matching algorithm, helps to generate a more reasonable and efficient package-vehicle allocation plan, and thus improves the utilization efficiency of different types of transportation resources.

[0069] In some preferred embodiments, step S4 includes: S41. Obtain the warehouse loading resource limit information in the warehouse operation management system; S42. Obtain the vehicle driving route information in the vehicle scheduling system, where the vehicle driving route information includes multiple unloading points of the vehicle and the time window requirements for each unloading point; S43. Use the warehouse loading resource limit information and the vehicle driving route information as constraint conditions, and combine with the matching weight to generate an initial allocation plan for each package using the dynamic matching algorithm; S44. According to the initial allocation plan, evaluate the matching degree between the arrival time of the vehicle at each unloading point and the time window requirements. If there are unloading points that do not meet the time window requirements, adjust the matching relationship between the package and the vehicle in the initial allocation plan, and re-allocate the packages that cause the time window not to be met to other vehicles that meet the time window requirements to generate an adjusted allocation plan; S45. According to the adjusted allocation plan, evaluate the utilization rate of warehouse loading resources. If the utilization rate of warehouse loading resources is lower than the preset threshold, then adjust the matching relationship between packages and vehicles in the adjusted allocation plan, and reallocate the packages assigned to the vehicles with low resource utilization rates to other vehicles with high resource utilization rates to improve the utilization rate of warehouse loading resources and generate the final allocation plan.

[0070] Specifically, step S41 obtains the physical resource limitations for the warehouse to perform loading operations, such as the number of loading platforms and the number of loading personnel.

[0071] More specifically, step S42 obtains the time constraints that must be satisfied during the vehicle transportation process, including the unloading points and the corresponding time window requirements.

[0072] More specifically, step S43 combines the actual operation limitations with the matching weights, runs the dynamic matching algorithm, generates a preliminary package and vehicle allocation plan, and incorporates the actual operation limitations into the matching process. The initial allocation plan includes which vehicle should transport each package and the vehicle loading sequence and quantity.

[0073] More specifically, step S44 performs time window verification and adjustment on the initial allocation plan. Evaluate whether the preset time window requirements can be met at each unloading point when the vehicle transports according to the initial plan. If there are non - compliant situations, then adjust the matching relationship between packages and vehicles, and reallocate the packages that cause time window conflicts to other vehicles that can meet the time window to ensure the transportation timeliness.

[0074] More specifically, step S45 conducts warehouse resource utilization rate evaluation and optimization on the adjusted allocation plan, evaluates the utilization efficiency of warehouse loading resources when implementing the current allocation plan. If the resource utilization rate is lower than the preset level, then further adjust the matching relationship between packages and vehicles, transfer the packages assigned to the vehicles with lower resource utilization rates to the vehicles with higher resource utilization rates, and improve the overall utilization efficiency of warehouse loading resources.

[0075] More specifically, the above processing method optimizes the allocation of packages and vehicles by introducing actual operation constraints. First, resource limit information such as the number of loading platforms and the number of personnel is obtained from the warehouse operation management system. At the same time, the driving route information of the vehicles, including each unloading point and its corresponding time window requirements, is obtained from the vehicle scheduling system. These resource limitations and time window requirements are used as constraints and, together with the matching weights of packages and vehicles calculated based on spatial and temporal metrics, are input into the dynamic matching algorithm to generate a preliminary package allocation plan. This initial plan specifies which vehicle transports each package and the loading order and quantity of the vehicles. Next, a time window compliance check is performed on this initial plan. For each vehicle involved in the plan, the estimated arrival time at each unloading point is calculated and compared with the preset time window requirements. If it is found that a vehicle cannot meet the time window requirements at a certain unloading point, the packages causing the time window conflict are identified and removed from the current vehicle, and an attempt is made to reallocate them to other vehicles that can meet the time window constraints, thereby generating an allocation plan adjusted for the time window. Finally, an evaluation of the utilization rate of warehouse loading resources is performed on the adjusted allocation plan. The utilization of resources such as warehouse loading platforms and personnel is calculated when implementing this plan. If the overall resource utilization rate is lower than the preset efficiency threshold, indicating that there is room for optimizing the resource allocation, the matching relationship between packages and vehicles is further adjusted. For example, the packages allocated to vehicles with lower resource utilization rates are transferred to vehicles with higher resource utilization rates to make more full use of warehouse resources, and finally an allocation plan for guiding actual loading and scheduling is generated. Through the introduction, verification, and optimization of layer-by-layer constraints, this plan can generate an allocation plan that comprehensively considers matching degree, warehouse operation capabilities, and transportation time limit constraints, and solves the resource limitation and time limit guarantee problems in actual operations.

[0076] In some preferred embodiments, the warehouse loading resource limit information includes the number of loading platforms and the number of loading personnel, and step S43 includes: S431. According to the matching weights, configure multiple alternative vehicles for each package, sort the multiple alternative vehicles according to the matching weights, and generate a set of alternative transportation plans based on the sorted alternative vehicles; S432. For each alternative transportation plan in the set of alternative transportation plans, based on the number of loading platforms and the number of loading personnel, evaluate the loading efficiency of the alternative transportation plan in the warehouse using a pre-constructed loading efficiency evaluation model to obtain a loading efficiency evaluation result; S433. For each alternative transportation plan, based on the multiple unloading points of the vehicle and the time window requirements of each unloading point, evaluate the degree of compliance with the time window of the alternative transportation plan during transportation using a pre-constructed time window compliance evaluation model to obtain a time window compliance evaluation result; S435. According to the evaluation results of the loading efficiency and the satisfaction degree of the time window, the weighted average method is used to calculate the comprehensive score of each alternative transportation plan, and the alternative transportation plan with the highest comprehensive score is used as the initial allocation plan for the corresponding package.

[0077] Specifically, the above processing method is used to solve the problem that the requirements of the warehouse loading efficiency and the vehicle transportation time window cannot be effectively balanced when generating the initial allocation plan. First, multiple alternative vehicles are generated for each package according to the matching weights in reverse order, and an alternative transportation plan set is formed based on these alternative vehicles. This provides a variety of possible combinations of package and vehicle allocations, laying a foundation for subsequent evaluation and selection. Then, for each plan in the alternative transportation plan set, using the pre-constructed loading efficiency evaluation model, combined with the number of loading platforms and the number of loading personnel in the warehouse, the loading efficiency of this plan in the warehouse is evaluated. This quantifies the utilization of warehouse resources by the plan.

[0078] At the same time, for each alternative transportation plan, using the pre-constructed time window satisfaction degree evaluation model, combined with the unloading points and time window requirements of the vehicle, the degree to which this plan meets the time window requirements during transportation is evaluated. This quantifies the feasibility and timeliness of the plan in the transportation link. Finally, the obtained evaluation results of the loading efficiency and the satisfaction degree of the time window are used to calculate the comprehensive score of each alternative transportation plan by the weighted average method. This provides a mechanism to balance the two potentially conflicting goals of warehouse loading efficiency and vehicle time window satisfaction. Finally, the alternative transportation plan with the highest comprehensive score is selected as the initial allocation plan for the corresponding package. Through the process of generation, evaluation, and selection, this method can generate an initial allocation plan that balances the warehouse loading efficiency and the vehicle time window satisfaction, thus solving the problem of insufficient balance in the existing methods.

[0079] In some preferred embodiments, step S5 includes: S51. Analyze the allocation plan, extract the unique identification code of the package to be loaded and the corresponding vehicle identification information; S52. According to the unique identification code of the package, obtain the physical attribute information of the package from the warehouse operation management system; S53. According to the vehicle identification information, obtain the loading layout information of the vehicle from the warehouse operation management system; S54. Generate a loading sequence instruction according to the physical attribute information of the package and the loading layout information of the vehicle; S55. Convert the loading sequence instruction into a scheduling instruction executable by the warehouse operation management system.

[0080] Specifically, the above processing method refines step S5 and solves the problem that when generating the scheduling instruction only based on the allocation plan, the loading constraints and operation details are not considered.

[0081] More specifically, step S51 receives the allocation plan and extracts the unique identification code of the package to be loaded and the corresponding vehicle identification information from it. Step S52 obtains the physical attribute information of the package from the warehouse operation management system according to the extracted unique package identification code. The physical attribute information may include the size, weight, and stacking requirements of the package. Step S53 obtains the loading layout information of each vehicle from the warehouse operation management system according to the extracted vehicle identification information. The loading layout information may include the available loading space and load-bearing limit of the vehicle. Then, step S54 generates a loading sequence instruction according to the package physical attribute information and the vehicle loading layout information. The loading sequence instruction indicates that, considering the load-bearing limit and available loading space of the vehicle, the loading position of each package in the vehicle is determined. Finally, step S55 converts the loading sequence instruction into a data structure in a format that can be recognized and executed by the warehouse operation management system.

[0082] More specifically, in step S54, the loading sequence instruction is used to guide warehouse personnel or automated equipment to load the packages into the vehicle in a determined order, and considering the size, weight, stacking requirements of the packages, as well as the load-bearing limit and available space of the vehicle, determines the loading position of each package in the vehicle. For example, packages with a high weight or packages with stacking requirements are placed at the bottom.

[0083] More specifically, the allocation plan is refined into loading instructions that consider physical constraints and operation sequences, ensuring the execution of the allocation plan at the warehouse end and improving loading efficiency and loading accuracy.

[0084] In some preferred embodiments, the physical attribute information includes the size, weight, and stacking requirements of the package; the loading layout information includes the available loading space and load-bearing limit of the vehicle; the loading sequence instruction indicates that, considering the load-bearing limit and available loading space of the vehicle, the specific loading position of each package in the vehicle is determined. If the package has stacking requirements, stackable packages are preferentially placed at the bottom, and packages with a large weight are placed at the bottom.

[0085] Specifically, the physical attribute information includes the size, weight, and stacking requirements of the package, which are obtained by scanning or input and are used to describe the physical characteristics of the package. The loading layout information includes the available loading space and load-bearing limit of the vehicle, which are obtained through the warehouse operation management system or preset parameters and are used to describe the physical constraints of the vehicle. The generation of the loading sequence instruction involves a decision-making process that determines the position where each package should be placed inside the vehicle and the loading order according to the physical attributes of the package and the loading layout of the vehicle.

[0086] More specifically, the decision logic takes into account the overall load-bearing limit of the vehicle and the load-bearing capacity of different areas to ensure that the total weight of the loaded packages does not exceed the limit. At the same time, the decision logic considers the three-dimensional available space inside the vehicle and plans the placement positions of the packages to maximize space utilization. In addition, the decision logic follows specific loading rules. For example, for packages marked as stackable, the system will prioritize arranging them in lower positions so that other packages can be stacked on top of them. For heavier packages, the system will also prioritize arranging them at the bottom of the vehicle or near the center of gravity of the vehicle to improve transportation stability. The combination of these rules and information enables the generated loading sequence instructions to guide the actual loading operation and ensure the safety and efficiency of loading.

[0087] More specifically, specifically, after receiving the allocation plan of packages and vehicles, the system parses the plan and extracts the package identifiers to be loaded and the corresponding vehicle identifiers. Using the package identifiers, the system queries and obtains the physical attribute data such as the size, weight, and stacking requirements of each package to be loaded from the warehouse database. Using the vehicle identifiers, the system obtains the three-dimensional model of the available loading space of the corresponding vehicle and the loading layout data such as the load-bearing limit of each area from the warehouse operation management system. Subsequently, the system runs a loading planning algorithm based on the obtained package physical attribute information and vehicle loading layout information. The algorithm aims to maximize space utilization and comply with the load-bearing limit, while considering the stacking requirements and weight distribution rules of the packages. The algorithm iteratively finds suitable loading positions for each package inside the vehicle and determines the optimal loading sequence. For example, the algorithm will evaluate whether placing a package in a certain position will cause local or overall overweight, whether it will exceed the available space range, and whether it complies with the stacking rules (such as placing stackable packages below and heavy packages below). By evaluating the feasibility and advantages and disadvantages of placing different packages in different positions, the algorithm finally generates a detailed loading sequence instruction. The instruction clearly indicates which specific position in the vehicle each package should be loaded into and the loading order between the packages. Thus, this technical solution solves the problem of how to convert an abstract allocation plan into specific loading operation instructions that can be understood and executed by warehouse operators, improving the accuracy and efficiency of loading operations.

[0088] In a second aspect, please refer to Figure 3 , some embodiments of the present application further provide a supply chain monitoring and optimization system, which is applied in a warehouse operation management system. The system includes: A data acquisition module 201, configured to acquire real-time Internet of Things data of the set of packages to be shipped and the set of transport vehicles inside the warehouse; A bipartite graph construction module 202, configured to construct a dynamic bipartite graph based on the real-time Internet of Things data. One vertex set of the dynamic bipartite graph represents the set of packages to be shipped, and the other vertex set represents the set of transport vehicles; A weight definition module 203 is configured to define a matching weight of an edge connecting a vertex corresponding to a set of parcels to be sent and a vertex corresponding to a set of transport vehicles based on the matching degree of spatial indicators and / or temporal indicators; A matching algorithm module 204 is configured to run a dynamic matching algorithm and generate an allocation plan for parcels and vehicles according to the matching weight, and the allocation plan is used to guide warehouse loading operations and vehicle scheduling; An instruction sending module 205 is configured to convert the allocation plan into a scheduling instruction of a warehouse operation management system.

[0089] The supply chain monitoring and optimization system according to the embodiment of the present application obtains real-time Internet of Things data, constructs a dynamic bipartite graph and runs a dynamic matching algorithm to generate an allocation plan for parcels and vehicles, realizes the dynamic matching of parcels and vehicles, can effectively improve the allocation efficiency of parcels and vehicles, and improves the utilization rate of vehicle resources, realizes the effective coordination of warehouse operations and transportation links, and can effectively ensure the timely delivery of orders.

[0090] In addition, the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0091] Furthermore, the functional modules in various embodiments of the present application may be integrated together to form an independent part, or each module may exist alone, or two or more modules may be integrated to form an independent part.

[0092] In this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations.

[0093] The above are only the embodiments of the present application and are not intended to limit the protection scope of the present application. For those skilled in the art, the present application may have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A supply chain monitoring and optimization method, applied in a warehouse operation management system, characterized in that The method includes the following steps: S1. Obtain the real-time Internet of Things data of the set of packages to be shipped inside the warehouse and the set of transport vehicles; S2. Based on the real-time Internet of Things data, construct a dynamic bipartite graph, where one vertex set of the dynamic bipartite graph represents the set of packages to be shipped, and the other vertex set represents the set of transport vehicles; S3. Define the matching weights of the edges connecting the vertices corresponding to the set of packages to be shipped and the vertices corresponding to the set of transport vehicles based on the matching degree of spatial indicators and / or temporal indicators; S4. Run a dynamic matching algorithm, and generate an allocation plan for packages and vehicles according to the matching weights, where the allocation plan is used to guide the warehouse loading operation and vehicle scheduling; S5. Convert the allocation plan into a scheduling instruction of the warehouse operation management system.

2. The supply chain monitoring and optimization method according to claim 1, wherein The real-time Internet of Things data includes the destination, volume, weight, time limit requirement of the package, and the location, speed, remaining available space, and estimated arrival time of the vehicle.

3. The supply chain monitoring and optimization method according to claim 2, characterized in that, Step S1 includes: S11. Scan the labels on the packages to collect the unique identification codes of each package in the set of packages to be shipped, and use the GPS positioning module to collect the location information of each vehicle in the set of transport vehicles; S12. Upload the collected unique identification codes and vehicle location information to the cloud data center, so as to use the cloud data center for cleaning, conversion, and integration to form a set of packages to be shipped including the destination, volume, weight, and time limit requirement of the package, and a set of transport vehicles including the vehicle location, speed, remaining available space, and estimated arrival time.

4. A supply chain monitoring and optimization method according to claim 1, characterized in that, The spatial indicators include one or more of the matching degree between the destination of the package and the predetermined route of the vehicle, the matching degree between the volume of the package and the remaining available space of the vehicle, and the distance between the current location of the vehicle and the warehouse where the package is located. The temporal indicators include the matching degree between the time limit requirement of the package order and the estimated delivery time of the vehicle.

5. A supply chain monitoring and optimization method according to claim 1 or 4, characterized in that, Step S3 includes: S31. Obtain the destination coordinates of each package in the set of packages to be shipped, obtain multiple route coordinate points on the predetermined route of each vehicle in the set of transport vehicles, calculate the minimum geographical distance between each destination coordinate and the multiple route coordinate points of each vehicle, and obtain a distance set; S32. According to the distance set, use the Gaussian function to calculate the spatial matching degree between the destination of each package and the predetermined route of the vehicle; S33. Obtain the latest delivery time of each package in the set of packages to be shipped, calculate the estimated delivery time of each vehicle in the set of transport vehicles for each package, calculate the time margin between the latest delivery time and the estimated delivery time, and obtain a time margin set; S34. According to the time margin set, use the sigmoid function to calculate the temporal matching degree between each package and each vehicle; S35. According to the spatial matching degree and the temporal matching degree, calculate the matching weight between each package and each vehicle by weighted fusion.

6. The supply chain monitoring and optimization method according to claim 5, characterized in that, Step S35 includes: S351. According to the preset weight coefficient of the spatial matching degree and the preset weight coefficient of the temporal matching degree, use the weighted average method to fuse the spatial matching degree and the temporal matching degree to obtain the initial matching weight; S352. Obtain vehicle type preference parameters, where the vehicle type preference parameters indicate the priorities of different vehicle types; S353. Adjust the initial matching weights according to the vehicle type preference parameters to obtain the final matching weights.

7. A supply chain monitoring and optimization method according to claim 1, characterized in that Step S4 includes: S41. Obtain the warehouse loading resource limit information in the warehouse operation management system; S42. Obtain the vehicle driving route information in the vehicle scheduling system, where the vehicle driving route information includes multiple unloading points of the vehicle and the time window requirements for each unloading point; S43. Use the warehouse loading resource limit information and the vehicle driving route information as constraint conditions, and combine with the matching weights to generate an initial allocation plan for each package using a dynamic matching algorithm; S44. According to the initial allocation plan, evaluate the matching degree between the arrival time of the vehicle at each unloading point and the time window requirements. If there are unloading points that do not meet the time window requirements, adjust the matching relationship between the packages and the vehicles in the initial allocation plan, and reallocate the packages that cause the time window not to be met to other vehicles that meet the time window requirements to generate an adjusted allocation plan; S45. According to the adjusted allocation plan, evaluate the utilization rate of the warehouse loading resources. If the utilization rate of the warehouse loading resources is lower than the preset threshold, adjust the matching relationship between the packages and the vehicles in the adjusted allocation plan, and reallocate the packages allocated to the vehicles with low resource utilization rate to the vehicles with high resource utilization rate to generate the final allocation plan.

8. A supply chain monitoring and optimization method according to claim 7, characterized in that The warehouse loading resource limit information includes the number of loading platforms and the number of loading personnel. Step S43 includes: S431. According to the matching weights, configure multiple alternative vehicles for each package, sort the multiple alternative vehicles according to the matching weights, and generate a set of alternative transportation plans based on the sorted alternative vehicles; S432. For each alternative transportation plan in the set of alternative transportation plans, evaluate the loading efficiency of the alternative transportation plan in the warehouse based on the number of loading platforms and the number of loading personnel using a pre-constructed loading efficiency evaluation model to obtain the loading efficiency evaluation result; S433. For each alternative transportation plan, evaluate the degree of time window satisfaction of the alternative transportation plan during the transportation process based on the multiple unloading points of the vehicle and the time window requirements for each unloading point using a pre-constructed time window satisfaction evaluation model to obtain the time window satisfaction evaluation result; S435. According to the loading efficiency evaluation result and the time window satisfaction evaluation result, use the weighted average method to calculate the comprehensive score of each alternative transportation plan, and use the alternative transportation plan with the highest comprehensive score as the initial allocation plan for the corresponding package.

9. A supply chain monitoring and optimization method according to claim 1, characterized in that Step S5 includes: S51. Analyze the allocation plan, and extract the unique identification code of the package to be loaded and the corresponding vehicle identification information; S52. According to the unique identification code of the package, obtain the physical attribute information of the package from the warehouse operation management system; S53. According to the vehicle identification information, obtain the loading layout information of the vehicle from the warehouse operation management system; S54. Generate a loading sequence instruction according to the physical attribute information of the package and the loading layout information of the vehicle; S55. Convert the loading sequence instruction into a scheduling instruction executable by the warehouse operation management system.

10. A supply chain monitoring and optimization system, which is applied to a warehouse operation management system, is characterized in that The system includes: A data acquisition module for acquiring real-time Internet of Things data of the set of packages to be shipped and the set of transport vehicles inside the warehouse; A bipartite graph construction module for constructing a dynamic bipartite graph based on the real-time Internet of Things data, where one vertex set of the dynamic bipartite graph represents the set of packages to be shipped, and the other vertex set represents the set of transport vehicles; A weight definition module for defining the matching weight of the edge connecting the vertex corresponding to the set of packages to be shipped and the vertex corresponding to the set of transport vehicles based on the matching degree of spatial indicators and / or temporal indicators; A matching algorithm module for running a dynamic matching algorithm and generating an allocation plan for packages and vehicles according to the matching weight, where the allocation plan is used to guide the warehouse loading operation and vehicle scheduling; An instruction sending module for converting the allocation plan into a scheduling instruction of the warehouse operation management system.

Images