Intelligent wave management method and system for overseas warehouse operation

Abstract

The invention discloses an overseas warehouse operation intelligent wave order management method and system, and the method comprises the steps: constructing a commodity incidence matrix, mining a frequent item set, determining the commodity correlation degree, carrying out the centralized picking of high-correlation commodities, reducing the round-trip times, shortening the walking distance, improving the picking efficiency, planning a picking path in combination with the warehouse layout and inventory information, and achieving the intelligent wave order management of the overseas warehouse operation. The method comprises the following steps: preferentially selecting short-distance commodities in the same area, further reducing the picking time, allocating priorities according to order emergency degrees and customer levels, ensuring that important orders are processed in time, improving customer satisfaction, dynamically adjusting the sequence in the picking process, avoiding invalid walking caused by stockout, enhancing path flexibility and adaptability, and collecting warehouse-in and warehouse-out information in real time. Inventory is updated immediately, data are ensured to be accurate and timely, labor intensity and operation time of picking personnel are reduced, labor cost is reduced, and storage equipment loss and maintenance cost are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of overseas warehouse operations, and particularly to an intelligent wave management method and system for overseas warehouse operations. Background Art

[0002] In the current field of logistics warehousing management, the efficiency and accuracy of overseas warehouse operations are crucial for improving customer satisfaction and reducing operating costs. However, there are many deficiencies in the traditional wave management method for overseas warehouse operations. First, in terms of order processing, the traditional method often simply batches orders according to the time sequence of orders, lacking in-depth analysis of the correlation between the goods in different orders, resulting in frequent back-and-forth movements of pickers in the warehouse, long walking distances, and low picking efficiency. Second, in setting the wave priority, the traditional method fails to fully consider the urgency of orders and customer levels, and cannot ensure that important orders can be processed in a timely manner.

[0003] In addition, the planning of the picking path is also a major problem in the traditional method. The traditional method often plans the path only according to the static layout of the warehouse, ignoring the real-time changes in inventory information, resulting in the need to re-plan the path due to out-of-stock of some goods during the picking process, increasing the picking time and cost. At the same time, the traditional inventory update method is not timely and accurate enough. It often adjusts the inventory quantity only after the picking is completed, and cannot reflect the inventory status of the warehouse in real time, affecting the processing efficiency of subsequent orders. Summary of the Invention

[0004] In view of this, the present invention proposes an intelligent wave management method and system for overseas warehouse operations, which can effectively solve the deficiencies in the prior art, such as the lack of in-depth analysis of the correlation between the goods in different orders, the failure to fully consider the urgency of orders and customer levels, the unreasonable planning of the picking path, and the inability to reflect the inventory status of the warehouse in real time.

[0005] The technical solution of the present invention is realized as follows:

[0006] An intelligent wave management method for overseas warehouse operations specifically includes:

[0007] Collect order information to be processed, and at the same time obtain the layout data of the warehouse;

[0008] By constructing a commodity correlation matrix, calculate the correlation between the goods in different orders, and mine the frequent item sets between the goods from the historical order data to determine the commodity correlation degree;

[0009] According to the urgency of the order and the customer level, assign a priority value to each wave;

[0010] Combine the warehouse layout and inventory information to plan the picking path;

[0011] According to the determined wave division, organize the pickers to carry out the picking operation, monitor the picking progress and inventory changes in real time, and handle abnormal situations;

[0012] Collect the inbound and outbound information of goods in real time, and update the inventory quantity when the goods are picked out or put into storage.

[0013] As a further optional solution of the intelligent wave management method for overseas warehouse operations, the method of constructing a commodity association matrix, calculating the association between commodities in different orders, and mining the frequent item sets between commodities from historical order data to determine the commodity association degree specifically includes:

[0014] Define an n×n commodity association matrix C according to the order information to be processed, where n is the total number of commodity types, and the matrix element C ij represents the initial association between commodity i and commodity j, and calculate the initial association between commodity i and commodity j according to the association calculation formula;

[0015] Set a support threshold, which is used to measure the frequency of the commodity combination appearing in the order;

[0016] According to the support threshold, mine the frequent item sets between commodities from the historical order data, and the frequent item sets represent the patterns of frequent co-occurrence between commodities;

[0017] Finally, determine the association degree between commodities according to the initial association between commodity i and commodity j and the frequent item sets;

[0018] Among them, the association calculation formula is specifically:

[0019]

[0020] In the formula, C ij represents the initial association between commodity i and commodity j, N ij represents the number of orders that contain both commodity i and commodity j, N total represents the total number of orders, N i and N j respectively represent the total number of orders that contain commodity i and commodity j.

[0021] As a further optional solution of the intelligent wave management method for overseas warehouse operations, the setting of the support threshold specifically includes:

[0022] Collect historical order data and count the frequency of each commodity appearing in all orders;

[0023] According to the scale of the warehouse, the number of commodity types, and the real-time requirement for order processing, preset an initial support threshold range;

[0024] Within this range, different support thresholds are gradually tested to find the final support threshold for data mining.

[0025] As a further optional solution of the intelligent wave management method for overseas warehouse operations, assigning a priority value to each wave according to the urgency of the order and the customer level specifically includes:

[0026] Dividing the orders into different urgency levels according to the delivery deadline of the order, the order creation time, or the emergency flag specified by the customer;

[0027] Assigning a corresponding numerical weight, denoted as Ek, to each urgency level, where k represents the urgency level;

[0028] Dividing the customers into different levels according to the customer's purchase history, consumption amount, loyalty, or customer type;

[0029] Assigning a corresponding numerical weight, denoted as Hl, to each customer level, where l represents the customer level;

[0030] For each wave, calculating the sum of the numerical weights Ek of the urgency levels of all orders included in this wave, denoted as Etotal;

[0031] Calculating the sum of the numerical weights Hl of the levels of the customers corresponding to all orders included in this wave, denoted as Htotal;

[0032] Calculating the priority value of the wave based on the sum of the numerical weights of the urgency level Etotal and the sum of the numerical weights of the level Htotal;

[0033] Assigning a priority to each wave according to the calculated priority value. The higher the priority value, the higher the urgency of this wave and the importance of the customer.

[0034] As a further optional solution of the intelligent wave management method for overseas warehouse operations, calculating the priority value of the wave based on the sum of the numerical weights of the urgency level Etotal and the sum of the numerical weights of the level Htotal, and the specific calculation formula is:

[0035]

[0036] In the formula, P is the priority value of the wave, Ne is the total number of orders in this wave, Nh is the total number of customers involved in this wave, γ and δ are adjustment coefficients used to adjust the influence degree of the urgency level and the customer level in the priority calculation; α and β are weight coefficients used to adjust the relative importance of the urgency level and the customer level in the priority calculation.

[0037] As a further optional solution to the intelligent wave management method for overseas warehouse operations, combining the warehouse layout and inventory information to plan the picking path specifically includes:

[0038] Obtain warehouse layout data, including shelf positions, aisle distributions, and the storage locations of goods in the warehouse;

[0039] Obtain real-time inventory information, including the current inventory quantities of each item;

[0040] Use Dijkstra's algorithm to plan the picking path based on the warehouse layout data and real-time inventory information.

[0041] As a further optional solution to the intelligent wave management method for overseas warehouse operations, using Dijkstra's algorithm to plan the picking path based on the warehouse layout data and real-time inventory information specifically includes:

[0042] Take the shelf positions in the warehouse as the vertices of the graph, the aisles as the edges, and determine the weights of the edges according to the actual distance or walking time between the shelves. Starting from the starting shelf, gradually select the unvisited vertex closest to the starting shelf in the current vertex set as the next visited vertex, and update the distances of the unvisited vertices adjacent to this vertex until all vertices are visited or the storage locations of all goods to be picked are reached, thus obtaining the optimal picking path.

[0043] An intelligent wave management system for overseas warehouse operations includes:

[0044] A data collection module for collecting order information to be processed and the layout data of the warehouse;

[0045] A relevance analysis module for constructing a commodity association matrix, calculating the relevance between commodities in different orders, and mining frequent item sets between commodities from historical order data to determine the commodity association degree;

[0046] A priority setting module for assigning a priority value to each wave according to the urgency of the order and the customer level;

[0047] A path planning module for planning the picking path by combining the warehouse layout data and inventory information;

[0048] A picking execution module for organizing pickers to perform picking operations according to the determined wave division, monitoring the picking progress and inventory changes in real time, and handling abnormal situations;

[0049] An inventory update module for collecting the inbound and outbound information of goods in real time and updating the inventory quantity when goods are picked out or put into storage.

[0050] A computing device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of any one of the above overseas warehouse operation intelligent wave management methods are implemented.

[0051] A computer-readable storage medium stores a computer program thereon. When the computer program is executed by a processor, the steps of any one of the above overseas warehouse operation intelligent wave management methods are implemented.

[0052] The beneficial effects of the present invention are as follows: By constructing a commodity association matrix and mining frequent itemsets to determine the commodity association degree, commodities with high association degrees can be concentrated in the same wave for picking, reducing the round-trip times of pickers in the warehouse, significantly shortening the walking distance, and improving the picking efficiency. Combining the warehouse layout and inventory information to plan the picking path and preferentially selecting commodities that are closer and in the same area for picking further reduces the picking time. According to the urgency of orders and customer levels, priority values are assigned to each wave to ensure that important orders can be processed in a timely manner and improve customer satisfaction. During the picking process, the picking order is dynamically adjusted according to the real-time changes in inventory to avoid ineffective walking caused by out-of-stock commodities, improving the flexibility and adaptability of the picking path. By real-time collecting the inbound and outbound information of commodities and immediately updating the inventory quantity when the commodities are picked out or put into storage, the accuracy and timeliness of inventory data are ensured. By improving the picking efficiency and order processing priority, the labor intensity and operation time of pickers are reduced, and the labor cost is lowered. By reducing ineffective walking and avoiding out-of-stock situations, the loss and maintenance cost of warehousing equipment are reduced. Brief Description of the Drawings

[0053] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0054] Figure 1 It is a schematic flow chart of an overseas warehouse operation intelligent wave management method of the present invention;

[0055] Figure 2 It is a schematic composition diagram of an overseas warehouse operation intelligent wave management system of the present invention;

[0056] Figure 3 It is a schematic composition diagram of a computing device of the present invention. Detailed Embodiments

[0057] The technical solutions in the embodiments of the present invention will be clearly and completely described below. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0058] Reference Figures 1 to 3 , an intelligent wave management method for overseas warehouse operations, specifically including:

[0059] Collect order information to be processed and simultaneously obtain the layout data of the warehouse;

[0060] By constructing a commodity association matrix, calculate the correlation between commodities in different orders, and mine the frequent item sets between commodities from historical order data to determine the commodity correlation degree;

[0061] According to the urgency of the order and the customer level, assign a priority value to each wave;

[0062] Combine the warehouse layout and inventory information to plan the picking path;

[0063] Organize pickers to perform picking operations according to the determined wave division, monitor the picking progress and inventory changes in real time, and handle abnormal situations;

[0064] Collect the inbound and outbound information of commodities in real time, and update the inventory quantity when the commodities are picked out or stored in the warehouse.

[0065] In this embodiment, by constructing a commodity association matrix and mining frequent item sets to determine the commodity correlation degree, commodities with high correlation can be concentrated in the same wave for picking, reducing the round-trip times of pickers in the warehouse, significantly shortening the walking distance, and improving the picking efficiency. Combining the warehouse layout and inventory information to plan the picking path, preferentially selecting commodities that are relatively close and in the same area for picking further reduces the picking time. According to the urgency of the order and the customer level, assign a priority value to each wave to ensure that important orders can be processed in a timely manner and improve customer satisfaction. During the picking process, dynamically adjust the picking order according to the real-time changes in inventory, avoiding ineffective walking caused by out-of-stock commodities, improving the flexibility and adaptability of the picking path. By collecting the inbound and outbound information of commodities in real time and immediately updating the inventory quantity when the commodities are picked out or stored in the warehouse, ensure the accuracy and timeliness of inventory data. By improving the picking efficiency and order processing priority, reduce the labor intensity and working time of pickers, and reduce the labor cost. By reducing ineffective walking and avoiding out-of-stock situations, reduce the loss and maintenance cost of warehousing equipment.

[0066] It should be noted that wave picking is carried out: according to the determined wave division, organize pickers to perform picking operations. During the picking process, monitor the picking progress and inventory changes in real time, and handle abnormal situations in a timely manner, such as out-of-stock of goods, picking errors, etc. If an abnormality occurs, automatically adjust the wave task or notify relevant personnel for handling;

[0067] Establish a real-time inventory update system. Install temperature and humidity sensors and weight sensing devices on the shelves to monitor environmental abnormalities. The electronic tags guide the picking path through lights, reducing the manual picking error rate. Collect the inbound and outbound information of goods in real time to ensure the accuracy and timeliness of inventory data. When goods are picked out, immediately update the inventory quantity. When new goods are put into storage, they can also be included in inventory management in a timely manner. Provide an alarm when the data does not match. In this way, during the wave picking process, pickers can obtain the latest inventory information and avoid picking interruptions or errors caused by insufficient inventory.

[0068] Preferably, by constructing a commodity association matrix, calculating the correlation between commodities in different orders, and mining the frequent item sets between commodities from historical order data to determine the commodity correlation degree, specifically including:

[0069] Define an n×n commodity association matrix C according to the order information to be processed, where n is the total number of commodity types, and the matrix element C ij represents the initial correlation between commodity i and commodity j, and calculate the initial correlation between commodity i and commodity j according to the correlation calculation formula;

[0070] Set a support threshold, and the support threshold is used to measure the frequency of the commodity combination appearing in the order;

[0071] According to the support threshold, mine the frequent item sets between commodities from historical order data, and the frequent item sets represent the patterns of frequent co-occurrence between commodities;

[0072] Finally, determine the correlation degree between commodities according to the initial correlation between commodity i and commodity j and the frequent item sets;

[0073] Among them, the specific correlation calculation formula is:

[0074]

[0075] In the formula, C ij represents the initial correlation between commodity i and commodity j, N ij represents the number of orders that contain both commodity i and commodity j, N total represents the total number of orders, N i and N j respectively represent the total number of orders containing commodity i and commodity j.

[0076] In this embodiment, by constructing a commodity association matrix, the association between different commodities can be clearly shown, providing an accurate data basis for the intelligent wave management of overseas warehouse operations. This association insight helps to understand which commodities are often purchased together, thereby optimizing wave division to ensure that associated commodities are processed in the same wave and improving picking efficiency. By using the frequent item sets of commodities mined from historical order data, a wave division strategy can be formulated more scientifically. Grouping frequently co-occurring commodity combinations into the same wave can significantly reduce the walking distance and picking time of pickers in the warehouse, improving the overall operation efficiency. By understanding the association between commodities, orders can be processed more flexibly. In the case of a large order volume or tight warehouse resources, the system can preferentially process order combinations with a high degree of association according to the commodity association degree, ensuring that important and urgent orders are processed in a timely manner and improving customer satisfaction. By quantifying the association degree between commodities through a calculation formula, the intelligent wave management system of overseas warehouse operations can divide waves more accurately according to the commodity association degree. Grouping commodities with a high degree of association into the same wave can effectively reduce the walking distance of pickers in the warehouse and improve picking efficiency because associated commodities are often stored in adjacent locations. The calculation formula is not only used to determine the commodity association degree but also can assist in assigning priorities to waves according to the urgency of orders and customer levels. By comprehensively considering various factors, it can ensure that important orders are processed first, improving customer satisfaction and order processing timeliness.

[0077] Preferably, the setting of the support threshold specifically includes:

[0078] Collect historical order data and count the frequency of each commodity appearing in all orders;

[0079] Preset an initial support threshold range according to the scale of the warehouse, the number of commodity types, and the real-time requirement of order processing;

[0080] Within this range, gradually test different support thresholds to find the final support threshold for data mining.

[0081] In this embodiment, by collecting historical order data and counting the frequency of each commodity appearing in all orders, a reliable data basis can be provided for setting the support threshold, which helps to ensure that the mined commodity association rules actually exist rather than occur accidentally, thereby improving the accuracy of data mining; presetting an initial support threshold range according to the scale of the warehouse, the number of commodity types, and the real-time requirements of order processing makes the setting of the support threshold more in line with the actual operation of the warehouse; gradually testing different support thresholds within the preset initial support threshold range can find the support threshold most suitable for the current warehouse operation situation, and this step-by-step testing method helps to avoid problems that may be brought about by blindly setting the support threshold, such as too many or too few mined rules, thereby optimizing the selection of the support threshold; allowing the support threshold to be dynamically adjusted according to changes in the warehouse operation situation. When the scale of the warehouse, the number of commodity types, or the real-time requirements of order processing change, the support threshold range can be reset and tested to ensure that it can always adapt to the new operation environment.

[0082] It should be noted that within this range, different support thresholds are gradually tested to find the final support threshold for data mining. The specific steps are as follows:

[0083] Mine frequent item sets that meet the current support threshold in the historical order data;

[0084] Evaluate the quantity and quality of the mined frequent item sets. If the number of frequent item sets is too small, it indicates that the support threshold is set too high, resulting in the omission of many potential association relationships. If the number of frequent item sets is too large and contains a large number of meaningless combinations, it indicates that the support threshold is set too low, introducing too much noise data;

[0085] According to the evaluation results, adjust the support threshold until a balance point is found, such that the number of mined frequent item sets is moderate and can accurately reflect the association relationships between commodities.

[0086] Preferably, a priority value is assigned to each wave according to the urgency of the order and the customer level, which specifically includes:

[0087] According to the delivery deadline of the order, the order creation time, or the emergency flag specified by the customer, the orders are divided into different urgency levels, for example: urgent, high, medium, low;

[0088] A corresponding numerical weight is assigned to each urgency level, denoted as Ek, where k represents the urgency level, and E1 < E2 < E3 < E4. For example: urgent corresponds to the numerical value 4, high corresponds to the numerical value 3, medium corresponds to the numerical value 2, and low corresponds to the numerical value 1;

[0089] Customers are classified into different levels according to their purchase history, consumption amount, loyalty, or customer type;

[0090] A corresponding numerical weight, denoted as Hl, is assigned to each customer level, where l represents the customer level, and H1 < H2 < H3 < H4. For example, VIP customers correspond to the numerical value 4, high-level customers correspond to the numerical value 3, ordinary customers correspond to the numerical value 2, and new customers correspond to the numerical value 1;

[0091] For each wave, the sum of the numerical weights Ek of the urgency levels of all orders included in that wave is calculated and denoted as Etotal;

[0092] The sum of the numerical weights Hl of the levels of the customers corresponding to all orders included in that wave is calculated and denoted as Htotal;

[0093] Based on the sum of the numerical weights of urgency Etotal and the sum of the numerical weights of levels Htotal, the priority value of the wave is calculated;

[0094] According to the calculated priority value, a priority is assigned to each wave. The higher the priority value, the higher the urgency level and the importance of the customers in that wave.

[0095] In this embodiment, by assigning different priorities to orders with different urgency levels, it is ensured that urgent orders can be processed first, reducing the order processing time. By assigning weights according to the customer level, orders of important customers can be responded to and processed faster, improving customer satisfaction; by calculating the priority value of each wave, warehouse resources such as manpower and equipment can be reasonably allocated to ensure the most effective use of resources. Waves with higher priority values can obtain resources first to ensure that the needs of critical orders and customers are met.

[0096] Preferably, the calculation of the priority value of the wave based on the sum of the numerical weights of urgency Etotal and the sum of the numerical weights of levels Htotal is specifically calculated using the following formula:

[0097]

[0098] In the formula, P is the priority value of the wave, Ne is the total number of orders in that wave, Nh is the total number of customers involved in that wave, γ and δ are adjustment coefficients used to adjust the influence of the urgency level and the customer level in the priority calculation; α And β is a weight coefficient used to adjust the relative importance of the urgency level and the customer level in the priority calculation.

[0099] In this embodiment, by introducing adjustment coefficients γ and δ, the influence degrees of the urgency level and customer level in the priority calculation can be flexibly adjusted, which enables dynamic adjustment of priorities according to actual requirements to adapt to different business scenarios; the calculation of the priority value P not only considers the urgency level of the order but also the importance of the customer. This comprehensive consideration method ensures that the priorities of each wave can be comprehensively evaluated, thus making more reasonable resource allocation decisions; by assigning a priority value to each wave, waves with higher priorities can be processed first to ensure that the needs of critical orders and customers are met, which helps improve the utilization efficiency of warehouse resources and reduce resource waste; the calculation of the priority value takes into account the customer level, enabling orders from important customers to be responded to and processed more quickly, which helps improve customer satisfaction.

[0100] It should be noted that where Ne is the total number of orders in this wave, and ik represents the urgency level of the k-th order;

[0101] where Nh is the total number of customers involved in this wave, and ls represents the level of the customer corresponding to the l-th order.

[0102] Preferably, combining the warehouse layout and inventory information to plan the picking path specifically includes:

[0103] Obtain warehouse layout data, including shelf positions, aisle distributions, and the storage positions of goods in the warehouse;

[0104] Obtain real-time inventory information, including the current inventory quantities of each commodity;

[0105] Use Dijkstra's algorithm to plan the picking path based on the warehouse layout data and real-time inventory information.

[0106] In this embodiment, Dijkstra's algorithm can ensure finding the shortest path from the starting point to the ending point in the warehouse layout. By applying this algorithm, the walking distance of the picker can be significantly reduced, and the picking efficiency can be improved. Combining real-time inventory information, the picking path can be dynamically adjusted according to the current inventory situation to prevent the picker from going to areas with out-of-stock or insufficient inventory, further saving time and labor; by optimizing the picking path, the picker can reach the target shelf faster, reducing the walking time in the warehouse, thereby improving the overall picking efficiency. Accurate path planning helps the picker find the target commodity faster, reducing the possibility of incorrect picking and improving picking accuracy; combining real-time inventory information can update the inventory status in real time to ensure that the picking path planning is based on the latest inventory data, enhancing the real-time and accuracy of warehouse management; by optimizing the picking path, warehouse resources such as manpower and equipment can be utilized more effectively, improving the overall operation efficiency of the warehouse.

[0107] Preferably, the Dijkstra algorithm is used to plan the picking path according to the warehouse layout data and real-time inventory information, which specifically includes:

[0108] Regarding the shelf positions in the warehouse as the vertices of a graph and the aisles as the edges, the weight of each edge is determined according to the actual distance or walking time between the shelves. Starting from the starting shelf, the unvisited vertex closest to the starting shelf in the current vertex set is gradually selected as the next vertex to be visited, and the distances of the unvisited vertices adjacent to this vertex are updated until all vertices are visited or the storage positions of all the goods to be picked are reached, thereby obtaining the optimal picking path.

[0109] In this embodiment, the Dijkstra algorithm can ensure that the shortest path from the starting shelf to the storage positions of all the goods to be picked is found. By regarding the shelf positions as the vertices of a graph, the aisles as the edges, and determining the weights of the edges according to the actual distance or walking time, the algorithm can calculate the optimal picking path, thereby reducing the walking distance and time of the pickers. By gradually selecting the unvisited vertex closest to the starting shelf in the current vertex set as the next vertex to be visited and updating the distances of the unvisited vertices adjacent to this vertex, the algorithm ensures the continuity and optimality of the path, avoiding repeated walking and detours. Combining with the real-time inventory information, the algorithm can dynamically adjust the picking path, preventing the pickers from going to areas with out-of-stock or insufficient inventory, reducing ineffective walking and waiting time, and enhancing the real-time performance and accuracy of warehouse management. Since the algorithm plans the optimal path, the pickers can visit the shelves more orderly, reducing the possibility of incorrect picking and improving the order accuracy, thus enhancing customer satisfaction.

[0110] An intelligent wave management system for overseas warehouse operations includes:

[0111] A data collection module for collecting order information to be processed and the warehouse layout data;

[0112] A relevance analysis module for constructing a commodity association matrix, calculating the relevance between commodities in different orders, and mining the frequent item sets between commodities from historical order data to determine the commodity association degree;

[0113] A priority setting module for assigning a priority value to each wave according to the urgency of the order and the customer level;

[0114] A path planning module for planning the picking path in combination with the warehouse layout data and inventory information;

[0115] A picking execution module for organizing pickers to perform picking operations according to the determined wave division, monitoring the picking progress and inventory changes in real time, and handling abnormal situations;

[0116] Inventory update module, which is used to collect the inbound and outbound information of goods in real time and update the inventory quantity when the goods are picked out or put into storage.

[0117] A computing device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of any one of the above overseas warehouse operation intelligent wave management methods.

[0118] A computer-readable storage medium stores a computer program. When the computer program is executed by a processor, it implements the steps of any one of the above overseas warehouse operation intelligent wave management methods.

[0119] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. An intelligent wave management method for overseas warehouse operations, characterized in that, Specifically include: Collect order information to be processed and simultaneously obtain the layout data of the warehouse; By constructing a commodity association matrix, calculate the correlation between commodities in different orders, and mine the frequent item sets between commodities from historical order data to determine the commodity correlation degree; According to the urgency of the order and the customer level, assign a priority value to each wave; Combine the warehouse layout and inventory information to plan the picking path; According to the determined wave division, organize pickers to perform picking operations, monitor the picking progress and inventory changes in real time, and handle abnormal situations; Collect the inbound and outbound information of commodities in real time, and update the inventory quantity when the commodities are picked out or put into storage.

2. The intelligent wave management method for overseas warehouse operations according to claim 1, wherein, The step of calculating the correlation between commodities in different orders by constructing a commodity association matrix, mining the frequent item sets between commodities from historical order data, and determining the commodity correlation degree specifically includes: Define an n×n commodity association matrix C according to the order information to be processed, where n is the total number of commodity types, and the matrix element C ij represents the initial association between commodity i and commodity j, and calculate the initial association between commodity i and commodity j according to the association calculation formula; Set a support threshold, which is used to measure the frequency of the commodity combination appearing in the order; According to the support threshold, mine the frequent item sets between commodities from historical order data, and the frequent item sets represent the patterns of frequent co-occurrence between commodities; According to the initial correlation between commodity i and commodity j and the frequent item sets, finally determine the correlation degree between commodities; Among them, the specific formula for the correlation is: where C ij represents the initial correlation between product i and product j, N ij represents the number of orders that contain both product i and product j, N total represents the total number of orders, N i and N j respectively represent the total number of orders containing product i and product j.

3. The intelligent wave management method for overseas warehouse operations according to claim 2, characterized in that The step of setting the support threshold specifically includes: Collect historical order data and count the frequency of each commodity appearing in all orders; According to the scale of the warehouse, the number of commodity types, and the real-time requirements of order processing, preset an initial support threshold range; Within this range, gradually test different support thresholds to find the final support threshold for data mining.

4. The intelligent wave management method for overseas warehouse operations according to claim 3, wherein, The step of assigning a priority value to each wave according to the urgency of the order and the customer level specifically includes: According to the delivery deadline of the order, the order creation time, or the emergency flag specified by the customer, divide the orders into different urgency levels; Assign a corresponding numerical weight to each urgency level, denoted as Ek, where k represents the urgency level; According to the customer's purchase history, consumption amount, loyalty, or customer type, divide the customers into different levels; Assign a corresponding numerical weight to each customer level, denoted as Hl, where l represents the customer level; For each wave, count the sum of the numerical weights Ek of the urgency levels of all orders included in this wave, denoted as Etotal; Count the sum of the numerical weights Hl of the levels of the customers corresponding to all orders included in this wave, denoted as Htotal; Calculate the priority value of the wave based on the sum of the numerical weights of the urgency level Etotal and the sum of the numerical weights of the level Htotal; According to the calculated priority value, assign a priority to each wave. The higher the priority value, the higher the urgency of the wave and the importance of the customer.

5. The intelligent wave management method for overseas warehouse operations according to claim 4, wherein, The specific formula for calculating the priority value of the wave based on the sum of the numerical weights of the urgency level Etotal and the sum of the numerical weights of the level Htotal is: In the formula, P is the priority value of the wave order, Ne is the total number of orders in this wave order, Nh is the total number of customers involved in this wave order, and γ and δ are adjustment coefficients used to adjust the influence degrees of the urgency level and the customer level in the priority calculation; α And β is the weight coefficient used to adjust the relative importance of the urgency level and the customer level in the priority calculation.

6. The intelligent wave management method for overseas warehouse operations according to claim 5, characterized in that The step of combining the warehouse layout and inventory information to plan the picking path specifically includes: Obtain warehouse layout data, including shelf positions, aisle distributions, and the storage locations of goods in the warehouse; Obtain real-time inventory information, including the current inventory quantities of each item; Use Dijkstra's algorithm to plan the picking path based on the warehouse layout data and real-time inventory information.

7. An intelligent wave management method for overseas warehouse operations according to claim 6, characterized in that, The step of using Dijkstra's algorithm to plan the picking path based on the warehouse layout data and real-time inventory information specifically includes: Taking the shelf positions in the warehouse as the vertices of a graph, the aisles as the edges, and the weights of the edges determined according to the actual distance or walking time between the shelves. Starting from the starting shelf, gradually select the unvisited vertex in the current vertex set that is closest to the starting shelf as the next visited vertex, and update the distances of the unvisited vertices adjacent to this vertex until all vertices are visited or the storage locations of all items to be picked are reached, thereby obtaining the optimal picking path.

8. An intelligent wave management system for overseas warehouse operations, characterized in that, It includes: A data collection module for collecting order information to be processed and the layout data of the warehouse; A correlation analysis module for constructing a commodity correlation matrix, calculating the correlation between commodities in different orders, and mining frequent item sets between commodities from historical order data to determine the commodity correlation degree; A priority setting module for assigning a priority value to each wave according to the urgency of the order and the customer level; A path planning module for planning the picking path by combining the warehouse layout data and inventory information; A picking execution module for organizing pickers to perform picking operations according to the determined wave division, monitoring the picking progress and inventory changes in real time, and handling abnormal situations; An inventory update module for collecting the inbound and outbound information of goods in real time and updating the inventory quantity when goods are picked out or put into storage.

9. A computing device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the overseas warehouse operation intelligent wave management method described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, A computer program is stored on the storage medium. When the computer program is executed by the processor, it implements the steps of the overseas warehouse operation intelligent wave management method described in any one of claims 1-7.

Images