A logistics supply chain digitalization collaborative management system and method

Abstract

This invention relates to the field of logistics supply chain and discloses a digital and intelligent collaborative management system and method for logistics supply chain. The system includes collecting order submission time, delivery area information, warehouse inventory levels, vehicle location, and remaining vehicle loading space to form order demand change data; identifying the changing trends of order demand across different delivery areas based on the order demand change data, and constructing an order demand diffusion relationship structure; jointly calculating the inventory consumption of each delivery area based on the order demand diffusion relationship structure, and selecting a set of supply warehouses based on warehouse inventory levels; generating transportation task combinations for the supply warehouse set, combined with the current vehicle location and remaining vehicle loading space; monitoring changes in order demand along the demand propagation path based on the transportation task combinations, recalculating unexecuted transportation task combinations to form updated transportation task combinations. This invention has the advantages of improving operational efficiency and responsiveness.

Description

Technical Field

[0001] This invention relates to the field of logistics supply chain, specifically to a digital and intelligent collaborative management system and method for logistics supply chain. Background Technology

[0002] With the continuous improvement of informatization and digitalization in the logistics industry, enterprises are increasingly using information systems to manage orders, inventory, and transportation to improve the overall efficiency of the supply chain. In the existing logistics supply chain management model, order management systems, warehouse management systems, and transportation management systems typically manage order demand, inventory status, and transportation vehicle resources respectively. The degree of data sharing and collaboration between these systems is relatively limited, leading to supply chain scheduling decisions often relying on manual coordination. In actual delivery, order demand data, inventory data, and vehicle resource data are often scattered across different systems, and the data update frequency and scheduling cycle differ. When order demand changes after the transportation plan is generated, existing systems often struggle to adjust vehicle loading structures or transportation routes in a timely manner. Meanwhile, inventory systems primarily rely on inventory thresholds for early warning, lacking a collaborative mechanism based on multi-source logistics data to comprehensively analyze changes in order demand and adjust warehouse supply and transportation plans accordingly. This results in situations where some warehouses experience inventory backlogs while some delivery tasks are delayed. Therefore, the ability of existing technologies to comprehensively analyze changes in order demand and collaboratively adjust warehouse inventory resources and transportation loading plans in a multi-source logistics data environment still needs improvement. Summary of the Invention

[0003] To address the shortcomings of existing technologies, this invention provides a digital and intelligent collaborative management system and method for logistics supply chains, which has the advantages of improving operational efficiency and responsiveness, and solves the problems mentioned in the background technology.

[0004] To achieve the aforementioned goals of improving operational efficiency and responsiveness, this invention provides the following technical solution: a digital and intelligent collaborative management method for logistics supply chains, comprising the following steps: Collect order submission time, delivery area information, warehouse inventory quantity, vehicle location, and remaining vehicle loading space; and statistically analyze the order quantity based on the delivery area to generate order demand change data for each delivery area. Identify the changing trends of order demand across different delivery areas based on order demand change data, and construct an order demand diffusion relationship structure by combining the transportation distance relationship between delivery areas; Based on the order demand diffusion relationship structure, the inventory consumption of each distribution area is jointly calculated to determine the warehouse nodes that can cover the demand propagation path, and the set of supply warehouses is selected according to the warehouse inventory quantity. For the set of supply warehouses, the system selects transportation vehicles that can cover multiple demand propagation paths simultaneously, based on the current location of the vehicles and their remaining loading space. It then generates transportation task combinations based on the order demand quantity, warehouse inventory quantity, and vehicle loading capacity. Based on the monitoring of changes in order demand along the demand propagation path using transportation task combinations, as order demand continues to expand along the demand propagation path, transportation task combinations that have not yet been executed are recalculated to form updated transportation task combinations.

[0005] Preferably, the process for generating order demand change data for each delivery area is as follows: The order management system obtains real-time information on order submission time, delivery area, and order quantity, and timestamps the order data. The system synchronously reads the inventory quantity, inventory update frequency, and historical inbound and outbound records of each warehouse from the warehouse management system, and associates and identifies them according to the service relationship between the warehouse and the distribution area. The vehicle positioning terminal is used to collect the real-time geographical location, current transportation status and remaining loading space of the transport vehicle, and is uniformly identified with the vehicle number; Order data is aggregated and statistically analyzed according to delivery area, and the order quantity is segmented and summarized in a preset time window to generate an order demand statistical sequence for the corresponding time scale. The order demand statistics sequence is structured and linked with warehouse inventory information and vehicle operation information according to time index. Abnormal order data filtering and missing data completion are performed to generate order demand change data for each delivery area.

[0006] Preferably, the process of identifying the changing trends of order demand across different delivery areas based on order demand change data is as follows: Time series analysis was performed on the order demand change data of each delivery area to calculate the order demand growth rate, fluctuation range and peak demand location; By using a sliding time window, the correlation between changes in order demand in adjacent delivery areas is calculated to identify the spatial synchronicity and lag relationship of changes in order demand. Based on historical order data, statistical analysis is conducted on the demand change patterns of each delivery area to predict the order demand trend of each area in the future. By integrating and analyzing the estimated demand change trends with current real-time order demand change data, we can identify the direction of demand growth and potential demand shift areas. Based on the direction of demand growth, changes in demand intensity, and the correlation between regions, demand propagation characteristic data is generated to describe the changing trends of order demand across different delivery areas.

[0007] Preferably, the process of constructing the order demand diffusion relationship structure is as follows: Obtain geographical distances, travel times, and historical transportation routes between each delivery area to construct a spatial relationship matrix between delivery areas; By mapping demand propagation characteristic data to a spatial relationship matrix of delivery areas, potential demand diffusion paths can be identified through the direction of demand growth and regional correlation. The intensity of demand propagation is weighted according to the demand diffusion path and the transportation distance between regions to generate a demand diffusion weight value. Establish a regional demand propagation graph structure by using delivery areas as nodes and demand diffusion weights as edge weights; The path selection and propagation intensity correction of the regional demand propagation map structure are performed to generate an order demand diffusion relationship structure that can describe the spatial diffusion relationship of order demand.

[0008] Preferably, the process of determining the warehouse nodes that can cover the demand propagation path is as follows: Match the demand propagation paths in the order demand diffusion relationship structure with the warehouse service coverage area to identify the candidate warehouse nodes corresponding to each demand propagation path; Based on the order demand volume and demand diffusion weight of each delivery area, the order demand along the demand propagation path is calculated using a weighted cumulative method. By combining historical warehouse outbound rates and inventory update cycles, the rate of warehouse inventory depletion can be predicted. The demand volume along the demand propagation path and the warehouse inventory consumption forecast results are jointly calculated to determine the coverage capability of each warehouse node on the demand propagation path. Select warehouse nodes that can meet the order requirements of the demand propagation path within a preset time range, and use them as a candidate warehouse node set to cover the demand propagation path.

[0009] Preferably, the process of selecting a set of supply warehouses based on warehouse inventory quantity is as follows: Obtain the real-time inventory quantity and inventory safety threshold of each warehouse in the candidate warehouse node set; Compare and calculate the warehouse inventory quantity with the order demand along the demand propagation path to identify the inventory adequacy level; The supply capacity of each warehouse node is scored by combining the warehouse's historical shipping efficiency and order processing capabilities. By comprehensively evaluating inventory adequacy and supply capacity scores, warehouse nodes that meet the supply requirements of the demand propagation path are selected. The selected warehouse nodes are prioritized to form a set of supply warehouses for executing order delivery tasks.

[0010] Preferably, the process of selecting transport vehicles that can simultaneously cover multiple demand propagation paths is as follows: Obtain the real-time location, operating status, and remaining loading space of transport vehicles, and establish a vehicle resource information table; Based on the location of each warehouse node in the supply warehouse set, the transportation distance between the warehouse node and the vehicle's current location, and the estimated arrival time, the accessibility of the vehicle to each supply warehouse node is calculated. The vehicle loading matching degree is assessed by combining the remaining loading space of the vehicle with the order demand volume of the demand propagation path undertaken by the supply warehouse set; Calculate the route coverage capability of vehicles that can start from the supply warehouse set and simultaneously meet the delivery needs of multiple demand propagation paths; Select transport vehicles with high route coverage and sufficient loading capacity to form a candidate transport vehicle set.

[0011] Preferably, the process of generating transportation task combinations is as follows: The supply warehouse set, the candidate transportation vehicle set, and the demand propagation path are processed together. The transportation distance between the warehouse, vehicle, and delivery area is calculated based on the location of the supply warehouse node, the current location of the vehicle, and the delivery area involved in the demand propagation path. Based on the order demand quantity and warehouse inventory quantity, the supply allocation is calculated for orders along each demand propagation path; The order loading quantity is optimized and allocated based on the vehicle's loading capacity and operating route. Based on the calculated transportation distance and delivery area location, determine the transportation route of the vehicle from the warehouse to multiple delivery areas; The warehouse supply allocation results, vehicle loading plans, and transportation routes are combined to generate a transportation task combination for executing the delivery task.

[0012] Preferably, the process of forming the updated transport task combination is as follows: We continuously collect data on new orders and update data on changes in order demand in each delivery area in real time. The updated order demand change data is remapped to the order demand diffusion relationship structure to identify demand changes along the demand propagation path. When the order demand on the demand propagation path exceeds the preset growth threshold, the status of the transportation task combination that has not yet been executed is marked according to the warehouse supply allocation results, vehicle loading plan and transportation route information in the transportation task combination. Based on the new order demand, changes in warehouse inventory, and vehicle operating status, the warehouse supply allocation results, vehicle loading plans, and transportation routes are recalculated and adjusted. The adjusted warehouse supply allocation results, vehicle loading plans, and transportation routes are recombined to generate an updated transportation task combination.

[0013] A digital collaborative management system for logistics supply chain includes: Demand Acquisition Module: Collects order information, warehouse inventory information, and vehicle location information, and calculates the number of orders by delivery area, generating order demand change data; Diffusion building module: Identifies regional demand change trends based on order demand change data, and constructs an order demand diffusion relationship structure based on regional transportation distance; Warehouse determination module: Calculates inventory consumption based on the order demand diffusion relationship structure, determines warehouse nodes, and filters the set of supply warehouses; Task generation module: Filters transport vehicles based on the set of supply warehouses, vehicle locations, and vehicle loading capacity, and generates transport task combinations; Task Update Module: Monitors changes in order demand along the demand propagation path and recalculates the transportation task combination when demand expands.

[0014] Compared with existing technologies, the present invention provides a digital and intelligent collaborative management system and method for logistics supply chains, which has the following beneficial effects: This invention unifies the collection and analysis of multi-source logistics data, including order submission time, delivery area information, warehouse inventory, vehicle location, and remaining vehicle loading space, to generate order demand change data for each delivery area. Based on this, it identifies order demand change trends between different delivery areas and constructs an order demand diffusion relationship structure by combining the transportation distance relationships between areas. This allows for a comprehensive assessment of order demand changes and potential propagation across different areas. Furthermore, by jointly calculating inventory consumption in each delivery area based on the order demand diffusion relationship structure, it identifies warehouse nodes that can cover the demand propagation path and filters the set of supply warehouses based on warehouse inventory. This enables warehouse supply decisions to be coordinated based on demand change trends and inventory status. Simultaneously, it combines vehicle current location and remaining vehicle loading space... This system filters transport vehicles capable of simultaneously covering multiple demand propagation paths and generates transport task combinations based on order demand quantity, warehouse inventory quantity, and vehicle loading capacity. This establishes a coordinated relationship between transport resource utilization and delivery task allocation. During the execution of transport tasks, changes in order demand along the demand propagation path are continuously monitored. As order demand continues to expand along the demand propagation path, unexecuted transport task combinations are recalculated to form updated transport task combinations. This enables transport scheduling to be dynamically adjusted according to demand changes. Under multi-source logistics data conditions, it achieves collaborative linkage between order demand change analysis, warehouse supply decisions, and transport task allocation, thereby helping to improve the coordinated utilization of inventory and transport resources and enhance the flexibility and overall operational efficiency of logistics distribution scheduling when order demand changes. Attached Figure Description

[0015] Figure 1 This is a schematic diagram of the method of the present invention; Figure 2 This is a schematic diagram of the structure of the present invention. Detailed Implementation

[0016] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0017] Example 1: Please refer to Figure 1 As shown in the embodiment of the present invention, a digital collaborative management method for logistics supply chain includes the following steps: S1: Collect order submission time, delivery area information, warehouse inventory quantity, vehicle location, and remaining vehicle loading space. Calculate the number of orders based on the delivery area to generate order demand change data for each delivery area.

[0018] The process of generating order demand change data for each delivery area in S1 is as follows: The system obtains real-time information on order submission time, delivery area, and quantity from the order management system and timestamps the order data. It also establishes a data interface with the order management system to acquire new order data in real time, including submission time, delivery area, and quantity. Upon receiving the order data, the system timestamps each order record and uniquely identifies it by order number, forming an order data set containing both time and delivery area information. This provides foundational data for analyzing changes in order demand. The system synchronously reads the inventory quantity, inventory update frequency, and historical inbound and outbound records of each warehouse from the warehouse management system, and associates and identifies them according to the service relationship between the warehouse and the distribution area. By establishing a data synchronization interface with the warehouse management system, the system obtains the inventory quantity and historical inbound and outbound records of each warehouse, and associates and identifies the warehouse information with the corresponding distribution area according to the pre-established service relationship table between warehouse and distribution area. For example, one warehouse can correspond to multiple distribution areas, thus forming a mapping relationship between warehouse and distribution area, providing a data foundation for analyzing the relationship between distribution area demand and warehouse inventory. The real-time geographical location, current transportation status, and remaining loading space of the transport vehicles are collected using vehicle positioning terminals and uniformly identified with the vehicle number. Each transport vehicle is equipped with a vehicle positioning terminal, which obtains the real-time geographical location of the vehicle through the positioning system and uploads it to the logistics management platform through the communication network. At the same time, the current operating status and remaining loading space of the vehicle are collected and uniformly identified with the vehicle number to form a vehicle resource information table, which reflects the current dispatchable status and transportation capacity of the vehicle. Order data is aggregated and statistically analyzed by delivery area, and the order quantity is segmented and summarized by preset time windows to generate an order demand statistical sequence for the corresponding time scale. Order data is also classified and statistically analyzed by the delivery area to which the order belongs, and preset time windows are set, such as 15 minutes or 30 minutes. The order quantity within each time window is summarized and statistically analyzed to form order demand data for different time periods. By statistically analyzing continuous time windows, an order demand statistical sequence for each delivery area over time is obtained to reflect the changing trend of order demand. The order demand statistics sequence is structured and linked with warehouse inventory information and vehicle operation information according to time index. Abnormal order data filtering and missing data completion are performed to generate order demand change data for each delivery area. Based on the time index, the order demand statistics sequence is linked and integrated with warehouse inventory information and vehicle operation information to form a unified data record. At the same time, the data is preprocessed, including filtering abnormal order data and completing missing order data, to generate order demand change data that can reflect the order demand changes in each delivery area, providing basic data support for demand change analysis and logistics scheduling.

[0019] S2: Identify the changing trends of order demand across different delivery areas based on order demand change data, and construct an order demand diffusion relationship structure by combining the transportation distance relationship between delivery areas.

[0020] The process in S2 for identifying the changing trends of order demand across different delivery areas based on order demand change data is as follows: Time series analysis is performed on the order demand change data of each delivery area to calculate the order demand growth rate, fluctuation range, and peak demand position. The order demand change data of each delivery area is arranged in chronological order, and a preset time interval is used as the statistical period. The order quantity of adjacent time periods is compared and calculated to obtain the order demand growth rate. At the same time, the range of change of order quantity in each time period is calculated to determine the demand fluctuation range. The peak demand position is determined by identifying the time period with the highest order quantity, so as to obtain the basic trend characteristics of order demand change over time in each delivery area. By using a sliding time window, correlation calculations are performed on changes in order demand in adjacent delivery areas to identify the spatial synchronicity and lag relationship of changes in order demand. Order demand data in adjacent delivery areas are segmented using a preset time window, and the changes in order demand in each area within the same time window are compared and analyzed using correlation calculation methods. When multiple areas show similar demand changes in close time periods, they are determined to have high demand synchronicity. If the demand change in one area has a certain time delay relative to another area, its lag relationship is recorded to identify the spatial correlation characteristics of order demand between different delivery areas. Based on historical order data, statistical analysis is performed on the demand change patterns of each delivery area to predict the order demand trend of each area in the future. By accessing the historical order database, statistical analysis is performed on the changes in the number of orders in each delivery area in different time periods, such as statistical analysis of historical peak periods, periodic demand changes, and demand growth. Combined with current order demand change data, the order demand change trend of each delivery area in the future is predicted, thereby obtaining the possible demand growth or decline trend in each area. By integrating and analyzing the estimated demand change trend with the current real-time order demand change data, we can identify the direction of demand growth and potential demand transfer areas. By comprehensively analyzing the demand change trend with the real-time order demand change data, we can identify areas with faster order demand growth and determine whether order demand is expanding from a certain delivery area to adjacent areas, thereby determining the direction of order demand growth and the range of areas where demand transfer may occur. Based on the direction of demand growth, changes in demand intensity, and the correlation between regions, demand propagation characteristic data describing the changing trends of order demand across different delivery areas is generated. By comprehensively considering the direction of demand growth, the magnitude of demand changes, and the spatial correlation between regions, the changes in order demand across each delivery area are structured and organized to form demand propagation characteristic data. This data is used to describe the changing trends and propagation relationships of order demand across different delivery areas, providing basic data support for constructing the structure of order demand diffusion relationships.

[0021] The process of constructing the order demand diffusion relationship structure in S2 is as follows: The system acquires geographical distances, travel times, and historical transportation route information between delivery areas to construct a spatial relationship matrix between these areas. It also obtains geographical distances between central nodes of each delivery area by calling the geographic information system within the logistics platform, and uses a map navigation interface to obtain average travel times between areas. Furthermore, it extracts frequently used transportation route information from historical transportation records. Based on this data, the spatial correlation between areas is calculated, and a spatial relationship matrix is ​​established using delivery areas as row and column indices. Matrix elements represent distance or travel time relationships between different delivery areas, providing fundamental spatial data for identifying demand diffusion paths. Demand propagation characteristic data is mapped to a spatial relationship matrix of delivery areas. Potential demand diffusion paths are identified by demand growth direction and regional correlation. The demand propagation characteristic data is matched with the spatial relationship matrix of delivery areas. Based on the demand growth direction and the spatial correlation between adjacent areas, the areas with obvious demand growth are expanded for analysis. When the demand in a certain delivery area grows rapidly and the adjacent areas have strong spatial correlation, the area is marked as a potential demand diffusion path, thereby identifying the spatial propagation direction of order demand that may spread from one area to the surrounding areas. The intensity of demand propagation is weighted based on the demand diffusion path and the transportation distance between regions to generate a demand diffusion weight value. The intensity of the identified demand diffusion path is calculated by taking into account the demand growth rate, the transportation distance between regions, and the historical order flow. The demand propagation capacity of each path is weighted. Generally, the greater the demand growth rate and the closer the regional distance, the higher the propagation weight of the corresponding path. The demand diffusion weight value between each delivery area is obtained through the above calculation and is used to quantify the intensity of order demand propagation between different regions. A regional demand propagation graph structure is established by using delivery areas as nodes and demand diffusion weight values ​​as edge weights. Each delivery area is abstracted as a node in the graph structure, and the demand diffusion weight values ​​are used as the weights of the edges connecting the nodes, thereby establishing a regional demand propagation graph structure. This graph structure can intuitively represent the demand propagation relationship and propagation intensity between different delivery areas, providing a structured data foundation for logistics scheduling and transportation route planning. The regional demand propagation map structure is subjected to path filtering and propagation intensity correction to generate an order demand diffusion relationship structure that can describe the spatial diffusion relationship of order demand. The established regional demand propagation map structure is further processed, such as filtering the main demand propagation paths with high propagation weights and removing abnormal or noisy paths. At the same time, the propagation weights of each path are dynamically corrected in combination with real-time changes in order demand, thereby forming a stable order demand diffusion relationship structure that can reflect the spatial diffusion relationship of order demand, providing a basis for warehouse selection and transportation task generation.

[0022] S3: Based on the order demand diffusion relationship structure, jointly calculate the inventory consumption of each delivery area, determine the warehouse nodes that can cover the demand propagation path, and filter the set of supply warehouses according to the warehouse inventory quantity.

[0023] The process of determining the warehouse nodes that can cover the demand propagation path in S3 is as follows: The system matches the demand propagation paths in the order demand diffusion relationship structure with the warehouse service coverage area to identify candidate warehouse nodes corresponding to each demand propagation path. It reads the demand propagation paths recorded in the order demand diffusion relationship structure and calls the warehouse service area configuration table in the logistics system to obtain the delivery area range that each warehouse can serve. By matching the delivery areas involved in the demand propagation path with the warehouse service area, it filters out warehouse nodes that can provide supply to the delivery areas on the path, thereby identifying candidate warehouse nodes corresponding to each demand propagation path and providing a basis for warehouse capacity assessment. Based on the order demand volume and demand diffusion weight of each delivery area, the order demand along the demand propagation path is weighted and accumulated. The order demand volume corresponding to each delivery area along the demand propagation path is extracted, and combined with the demand diffusion weight between areas, the demand of each area is weighted. For example, areas with higher demand diffusion weights are assigned higher demand impact values, and the order demand of each area is accumulated and calculated according to the order of the demand propagation path to obtain the comprehensive demand volume along the demand propagation path, which is used to represent the overall order demand scale of the path within a certain time range. By combining historical outbound rates and inventory update cycles, the speed of warehouse inventory consumption is predicted. Historical outbound records of each warehouse are read from the warehouse management system, and the average outbound volume per unit time is calculated. At the same time, warehouse inventory update cycle information, such as replenishment cycle or inventory refresh time, is obtained. By combining historical outbound rates and inventory update cycles, the speed of warehouse inventory consumption in the future is predicted, thereby assessing the inventory changes of the warehouse under continuous supply conditions. The demand along the demand propagation path is jointly calculated with the warehouse inventory consumption forecast to determine the coverage capacity of each warehouse node for the demand propagation path. The comprehensive demand along the demand propagation path is compared and analyzed with the warehouse inventory consumption forecast. By calculating the degree of matching between the inventory that the warehouse can provide and the demand along the demand propagation path, it is determined whether each warehouse node has the supply capacity to cover the demand propagation path, thereby determining the support capacity of different warehouses for each demand propagation path. Warehouse nodes that can meet the order requirements of the demand propagation path within a preset time range are selected as a set of candidate warehouse nodes covering the demand propagation path. Based on warehouse inventory, inventory consumption forecast results, and comprehensive demand of the demand propagation path, warehouse nodes that can continuously provide goods and meet order requirements within a preset time range are selected. The warehouse nodes that meet the conditions are then aggregated to form a set of candidate warehouse nodes covering the demand propagation path, providing a warehousing resource foundation for the selection of transport vehicles and the generation of transport task combinations.

[0024] The process of selecting a set of supply warehouses based on warehouse inventory quantity in S3 is as follows: The system obtains the real-time inventory quantity and inventory safety threshold of each warehouse in the candidate warehouse node set; it obtains the real-time inventory quantity of each warehouse in the candidate warehouse node set through the data interface of the warehouse management system, and reads the inventory safety threshold preset by the system. The inventory safety threshold is used to represent the minimum inventory quantity required for the warehouse to maintain normal operation. By sorting the real-time inventory data, a warehouse inventory information table containing warehouse number, inventory quantity and inventory safety threshold is formed, providing a data basis for judging supply capacity. The inventory level of each warehouse is compared with the order demand along the demand propagation path to identify the inventory adequacy. The real-time inventory level of each warehouse is compared with the order demand along the demand propagation path. For example, the ratio between inventory level and demand or the remaining inventory level is calculated. When the inventory level of a warehouse is significantly higher than the demand level, the inventory adequacy level is determined to be high. If the inventory level is close to the demand level, the inventory adequacy level is determined to be medium. The inventory guarantee capacity of each warehouse under the current demand conditions is evaluated through the above methods. The supply capacity of each warehouse node is scored by combining the warehouse's historical shipping efficiency and order processing capacity; historical shipping records of the warehouse are read, such as the average shipping volume and order processing time per unit time, and the order processing capacity of the warehouse during peak periods is statistically analyzed. The supply capacity of the warehouse is scored based on the above data, for example, by calculating a comprehensive score based on shipping efficiency, order processing speed and inventory turnover, which is used to reflect the supply efficiency of the warehouse in actual delivery tasks. The inventory adequacy and supply capacity scores are comprehensively evaluated to screen warehouse nodes that meet the supply requirements of the demand propagation path. The inventory adequacy and supply capacity scores are comprehensively evaluated, for example, by using a weighted calculation method to obtain the comprehensive supply capacity value of the warehouse, and a screening threshold is set. Based on the comprehensive supply capacity value, warehouse nodes that can meet the order requirements of the demand propagation path are screened out, thereby determining the warehouse resources with supply capacity. The selected warehouse nodes are prioritized to form a set of supply warehouses for executing order delivery tasks. The selected warehouse nodes are sorted according to their comprehensive supply capacity value. At the same time, the transportation distance or delivery time between the warehouse and the demand area can be used for auxiliary sorting. After priority sorting, the warehouse nodes with priority supply are determined to form a set of supply warehouses for executing order delivery tasks, providing a warehousing resource foundation for transportation vehicle scheduling and transportation task combination generation.

[0025] S4: For the set of supply warehouses, combined with the current location of the vehicles and the remaining loading space of the vehicles, the transport vehicles that can cover multiple demand propagation paths at the same time are screened, and transport task combinations are generated based on the order demand quantity, warehouse inventory quantity and vehicle loading capacity.

[0026] The process of selecting transport vehicles that can simultaneously cover multiple demand propagation paths in S4 is as follows: The system acquires the real-time location, operating status, and remaining loading space of transport vehicles and establishes a vehicle resource information table. It obtains the real-time geographical location, current operating status, and remaining loading space of transport vehicles through vehicle positioning terminals and vehicle management systems, and uploads the above data to the logistics management platform. The collected vehicle information is uniformly organized according to vehicle number to form a vehicle resource information table containing vehicle location, vehicle status, and loading capacity, which reflects the current vehicle resource situation that can participate in delivery tasks. Based on the location of each warehouse node in the supply warehouse set, the transportation distance between the vehicle and its current location, and the estimated arrival time, the accessibility of the vehicle to each supply warehouse node is calculated. The geographical location of each warehouse node in the supply warehouse set is obtained, and combined with the current location of the vehicle, the transportation distance and estimated arrival time of the vehicle to each warehouse node are calculated through the map navigation interface. If the vehicle can reach the corresponding warehouse node within a preset time range, it is determined that the vehicle has accessibility to the warehouse, thereby filtering out vehicles that can participate in the warehouse pickup task. The vehicle loading matching degree is evaluated by combining the vehicle's remaining loading space with the order demand volume of the demand propagation path undertaken by the supply warehouse set. The vehicle's remaining loading space is compared and analyzed with the order demand volume of the demand propagation path corresponding to the supply warehouse set. For example, the matching ratio between the vehicle's load capacity and the demand volume is calculated. When the vehicle's remaining loading space can meet all or part of the order demand, the vehicle is determined to have a high loading matching degree, thereby identifying vehicles suitable for undertaking delivery tasks. The route coverage capability is calculated for vehicles that can depart from the supply warehouse set and simultaneously meet the delivery needs of multiple demand propagation paths. Based on the delivery area location involved in the demand propagation path, the delivery routes that the vehicle may take after departing from the supply warehouse are analyzed, and the number of demand propagation paths that the vehicle can cover in one transportation process is counted. When the vehicle's transportation route can pass through multiple demand areas in sequence, it is determined that it has a high route coverage capability, which is used to measure the vehicle's ability to complete multi-area delivery in one transportation task. Select transport vehicles with high route coverage and sufficient loading capacity to form a candidate transport vehicle set; based on vehicle accessibility, loading matching degree and route coverage, comprehensively screen vehicles, eliminate vehicles with insufficient loading capacity or unable to arrive at the warehouse in time, and summarize the vehicles that meet the conditions to form a candidate transport vehicle set, providing schedulable vehicle resources for the generation of transport task combinations.

[0027] The process of generating transport task combinations in S4 is as follows: The system jointly processes the set of supply warehouses, the set of candidate transport vehicles, and the demand propagation path; it reads the information of the set of supply warehouses, the set of candidate transport vehicles, and the demand propagation path, and organizes the three types of data in a unified manner. The set of supply warehouses includes warehouse location and inventory information, the set of candidate transport vehicles includes vehicle location and loading capacity information, and the demand propagation path includes the delivery areas involved and the order demand. By establishing a unified data structure, the above information is associated to provide basic data for transportation task calculation. Based on the location of the supply warehouse node, the current location of the vehicle, and the delivery area involved in the demand propagation path, the transportation distance between the warehouse, vehicle, and delivery area is calculated; the geographical coordinates of the supply warehouse node, the current location of the transport vehicle, and the center location of the delivery area are obtained, and the transportation distance and estimated travel time between the warehouse and the delivery area and between the vehicle and the warehouse are calculated through the map navigation interface, thereby obtaining the transportation distance data between the warehouse, vehicle, and delivery area, which is used to evaluate the path cost of different transportation options; Based on the order demand and warehouse inventory, the supply allocation is calculated for orders along each demand propagation path. Based on the order demand corresponding to the demand propagation path and the inventory of each supply warehouse, the supply allocation is calculated for orders. For example, when the order demand on a certain demand propagation path is large, multiple warehouses can share the supply task. When a warehouse has sufficient inventory and is close by, it will be given priority to supply orders in the corresponding area, thus forming a preliminary warehouse supply allocation plan. The loading quantity of orders is optimized and allocated by combining vehicle loading capacity and vehicle operation routes; based on the loading capacity of candidate transport vehicles, the loading matching calculation of orders allocated to the warehouse is performed, and the loading quantity of orders is optimized and adjusted by combining the order of delivery areas that the vehicle may pass through. For example, orders from multiple delivery areas on the same transportation route are loaded together to improve vehicle loading rate and reduce the number of transportation trips, thereby forming a vehicle loading plan. Based on the calculated transportation distance and delivery area location, the transportation route of the vehicle from the warehouse to multiple delivery areas is determined; the vehicle transportation route is planned by combining the current location of the vehicle, the location of the warehouse and the location of the delivery area, and the transportation route of the vehicle from the warehouse to multiple delivery areas is determined by the route optimization method, so that the vehicle transportation distance is relatively short and can cover multiple order demand areas, thereby improving delivery efficiency. The warehouse supply allocation results, vehicle loading plans, and transportation routes are combined to generate a transportation task combination for executing delivery tasks. The warehouse supply allocation plan, vehicle loading plan, and vehicle transportation routes are integrated to form a transportation task combination that includes warehouse pickup information, vehicle loading quantity, and delivery route. This task combination is then sent to the logistics scheduling system for executing order delivery tasks.

[0028] S5: Based on the monitoring of changes in order demand along the demand propagation path, when the order demand continues to expand along the demand propagation path, the unexecuted transportation task combinations are recalculated to form updated transportation task combinations.

[0029] The process of creating an updated transport task combination in S5 is as follows: Continuously collect new order data and update order demand change data for each delivery area in real time; obtain new order data in real time through the order management system, including order submission time, delivery area of ​​the order, and order quantity information, and merge and update the new order data with the original order data. Then, perform statistics on the order data according to the delivery area and summarize the order quantity within a preset time window, thereby updating the order demand change data for each delivery area in real time to reflect the dynamic changes in current order demand. The updated order demand change data is remapped to the order demand diffusion relationship structure to identify demand changes along the demand propagation path. The updated order demand change data is matched with the order demand diffusion relationship structure. Based on the delivery areas involved in the demand propagation path, the order demand changes in each area are recalculated, and it is analyzed whether there is a significant increase or expansion in order demand along the demand propagation path, thereby identifying demand changes along the demand propagation path. When order demand on a demand propagation path exceeds a preset growth threshold, the system marks the status of unexecuted transport task combinations based on warehouse supply allocation results, vehicle loading plans, and transport route information within the transport task combination. An order demand growth threshold is set; for example, when order demand on a certain demand propagation path increases by more than a set percentage within a preset time range, it is determined that the demand on that path has changed significantly. At this time, the system reads the warehouse supply allocation results, vehicle loading plans, and transport route information from the current transport task combination and marks the status of transport tasks that have not yet started or been completed, so that subsequent adjustments can be made. Based on the new order demand quantity, warehouse inventory changes and vehicle operation status, the warehouse supply allocation results, vehicle loading plan and transportation route are recalculated and adjusted; the updated order demand quantity is obtained, and the warehouse inventory change information in the warehouse management system and the vehicle operation status information in the vehicle positioning system are read. Based on the above data, the warehouse supply allocation plan, vehicle loading quantity and vehicle transportation route are recalculated to form a new delivery plan. The adjusted warehouse supply allocation results, vehicle loading plans, and transportation routes are recombined to generate updated transportation task combinations. The recalculated warehouse supply allocation scheme, vehicle loading plans, and transportation routes are then integrated to form new transportation task combinations. The updated transportation tasks are then sent to the logistics scheduling system to replace the original unexecuted transportation tasks, thereby achieving dynamic response to changes in order demand.

[0030] Example 2: Please refer to Figure 2 As shown, a digital collaborative management system for logistics supply chains includes: Demand Acquisition Module: Collects order information, warehouse inventory information, and vehicle location information, and calculates the number of orders by delivery area, generating order demand change data; Diffusion building module: Identifies regional demand change trends based on order demand change data, and constructs an order demand diffusion relationship structure based on regional transportation distance; Warehouse determination module: Calculates inventory consumption based on the order demand diffusion relationship structure, determines warehouse nodes, and filters the set of supply warehouses; Task generation module: Filters transport vehicles based on the set of supply warehouses, vehicle locations, and vehicle loading capacity, and generates transport task combinations; Task Update Module: Monitors changes in order demand along the demand propagation path and recalculates the transportation task combination when demand expands.

[0031] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus.

[0032] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A digital collaborative management method for logistics supply chain, characterized in that, Includes the following steps: Collect order submission time, delivery area information, warehouse inventory quantity, vehicle location, and remaining vehicle loading space; and statistically analyze the order quantity based on the delivery area to generate order demand change data for each delivery area. Identify the changing trends of order demand across different delivery areas based on order demand change data, and construct an order demand diffusion relationship structure by combining the transportation distance relationship between delivery areas; Based on the order demand diffusion relationship structure, the inventory consumption of each distribution area is jointly calculated to determine the warehouse nodes that can cover the demand propagation path, and the set of supply warehouses is selected according to the warehouse inventory quantity. For the set of supply warehouses, the system selects transportation vehicles that can cover multiple demand propagation paths simultaneously, based on the current location of the vehicles and their remaining loading space. It then generates transportation task combinations based on the order demand quantity, warehouse inventory quantity, and vehicle loading capacity. Based on the monitoring of changes in order demand along the demand propagation path using transportation task combinations, as order demand continues to expand along the demand propagation path, transportation task combinations that have not yet been executed are recalculated to form updated transportation task combinations.

2. The intelligent collaborative management method for logistics supply chain according to claim 1, characterized in that, The process of generating order demand change data for each delivery area is as follows: The order management system obtains real-time information on order submission time, delivery area, and order quantity, and timestamps the order data. The system synchronously reads the inventory quantity, inventory update frequency, and historical inbound and outbound records of each warehouse from the warehouse management system, and associates and identifies them according to the service relationship between the warehouse and the distribution area. The vehicle positioning terminal is used to collect the real-time geographical location, current transportation status and remaining loading space of the transport vehicle, and is uniformly identified with the vehicle number; Order data is aggregated and statistically analyzed according to delivery area, and the order quantity is segmented and summarized in a preset time window to generate an order demand statistical sequence for the corresponding time scale. The order demand statistics sequence is structured and linked with warehouse inventory information and vehicle operation information according to time index. Abnormal order data filtering and missing data completion are performed to generate order demand change data for each delivery area.

3. The intelligent collaborative management method for logistics supply chain according to claim 2, characterized in that, The process of identifying trends in order demand across different delivery areas based on order demand change data is as follows: Time series analysis was performed on the order demand change data of each delivery area to calculate the order demand growth rate, fluctuation range and peak demand location; By using a sliding time window, the correlation between changes in order demand in adjacent delivery areas is calculated to identify the spatial synchronicity and lag relationship of changes in order demand. Based on historical order data, statistical analysis is conducted on the demand change patterns of each delivery area to predict the order demand trend of each area in the future. By integrating and analyzing the estimated demand change trends with current real-time order demand change data, we can identify the direction of demand growth and potential demand shift areas. Based on the direction of demand growth, changes in demand intensity, and the correlation between regions, demand propagation characteristic data is generated to describe the changing trends of order demand across different delivery areas.

4. The intelligent collaborative management method for logistics supply chain according to claim 3, characterized in that, The process of constructing the order demand diffusion relationship structure is as follows: Obtain geographical distances, travel times, and historical transportation routes between each delivery area to construct a spatial relationship matrix between delivery areas; By mapping demand propagation characteristic data to a spatial relationship matrix of delivery areas, potential demand diffusion paths can be identified through the direction of demand growth and regional correlation. The intensity of demand propagation is weighted according to the demand diffusion path and the transportation distance between regions to generate a demand diffusion weight value. Establish a regional demand propagation graph structure by using delivery areas as nodes and demand diffusion weights as edge weights; The path selection and propagation intensity correction of the regional demand propagation map structure are performed to generate an order demand diffusion relationship structure that can describe the spatial diffusion relationship of order demand.

5. The intelligent collaborative management method for logistics supply chain according to claim 4, characterized in that, The process of determining the warehouse nodes that can cover the demand propagation path is as follows: Match the demand propagation paths in the order demand diffusion relationship structure with the warehouse service coverage area to identify the candidate warehouse nodes corresponding to each demand propagation path; Based on the order demand volume and demand diffusion weight of each delivery area, the order demand along the demand propagation path is calculated using a weighted cumulative method. By combining historical warehouse outbound rates and inventory update cycles, the rate of warehouse inventory depletion can be predicted. The demand volume along the demand propagation path and the warehouse inventory consumption forecast results are jointly calculated to determine the coverage capability of each warehouse node on the demand propagation path. Select warehouse nodes that can meet the order requirements of the demand propagation path within a preset time range, and use them as a candidate warehouse node set to cover the demand propagation path.

6. The intelligent collaborative management method for logistics supply chain according to claim 5, characterized in that, The process of selecting a set of supply warehouses based on warehouse inventory quantity is as follows: Obtain the real-time inventory quantity and inventory safety threshold of each warehouse in the candidate warehouse node set; Compare and calculate the warehouse inventory quantity with the order demand along the demand propagation path to identify the inventory adequacy level; The supply capacity of each warehouse node is scored by combining the warehouse's historical shipping efficiency and order processing capabilities. By comprehensively evaluating inventory adequacy and supply capacity scores, warehouse nodes that meet the supply requirements of the demand propagation path are selected. The selected warehouse nodes are prioritized to form a set of supply warehouses for executing order delivery tasks.

7. The intelligent collaborative management method for logistics supply chain according to claim 6, characterized in that, The process of selecting transport vehicles that can simultaneously cover multiple demand propagation paths is as follows: Obtain the real-time location, operating status, and remaining loading space of transport vehicles, and establish a vehicle resource information table; Based on the location of each warehouse node in the supply warehouse set, the transportation distance between the warehouse node and the vehicle's current location, and the estimated arrival time, the accessibility of the vehicle to each supply warehouse node is calculated. The vehicle loading matching degree is assessed by combining the remaining loading space of the vehicle with the order demand volume of the demand propagation path undertaken by the supply warehouse set; Calculate the route coverage capability of vehicles that can start from the supply warehouse set and simultaneously meet the delivery needs of multiple demand propagation paths; Select transport vehicles with high route coverage and sufficient loading capacity to form a candidate transport vehicle set.

8. The intelligent collaborative management method for logistics supply chain according to claim 7, characterized in that, The process of generating a transportation task combination is as follows: The supply warehouse set, the candidate transportation vehicle set, and the demand propagation path are processed together. The transportation distance between the warehouse, vehicle, and delivery area is calculated based on the location of the supply warehouse node, the current location of the vehicle, and the delivery area involved in the demand propagation path. Based on the order demand quantity and warehouse inventory quantity, the supply allocation is calculated for orders along each demand propagation path; The order loading quantity is optimized and allocated based on the vehicle's loading capacity and operating route. Based on the calculated transportation distance and delivery area location, determine the transportation route of the vehicle from the warehouse to multiple delivery areas; The warehouse supply allocation results, vehicle loading plans, and transportation routes are combined to generate a transportation task combination for executing the delivery task.

9. The intelligent collaborative management method for logistics supply chain according to claim 8, characterized in that, The process of forming the updated transport task combination is as follows: We continuously collect data on new orders and update data on changes in order demand in each delivery area in real time. The updated order demand change data is remapped to the order demand diffusion relationship structure to identify demand changes along the demand propagation path. When the order demand on the demand propagation path exceeds the preset growth threshold, the status of the transportation task combination that has not yet been executed is marked according to the warehouse supply allocation results, vehicle loading plan and transportation route information in the transportation task combination. Based on the new order demand, changes in warehouse inventory, and vehicle operating status, the warehouse supply allocation results, vehicle loading plans, and transportation routes are recalculated and adjusted. The adjusted warehouse supply allocation results, vehicle loading plans, and transportation routes are recombined to generate an updated transportation task combination.

10. A digital collaborative management system for logistics supply chains, applied to the method described in any one of claims 1-9, characterized in that, include: Demand Acquisition Module: Collects order information, warehouse inventory information, and vehicle location information, and calculates the number of orders by delivery area, generating order demand change data; Diffusion building module: Identifies regional demand change trends based on order demand change data, and constructs an order demand diffusion relationship structure based on regional transportation distance; Warehouse determination module: Calculates inventory consumption based on the order demand diffusion relationship structure, determines warehouse nodes, and filters the set of supply warehouses; Task generation module: Filters transport vehicles based on the set of supply warehouses, vehicle locations, and vehicle loading capacity, and generates transport task combinations; Task Update Module: Monitors changes in order demand along the demand propagation path and recalculates the transportation task combination when demand expands.

Images