Commodity picking order generation method and system of supplier side

Abstract

The invention relates to a commodity picking order generation system and method of a supplier end, and relates to the technical field of commodity logistics management, and the system comprises a path optimization module which combines similar orders through an AI optimization algorithm, segments tasks, and selects a shortest picking path; the placement recommendation module calculates associated commodities by using collaborative filtering and a depth algorithm, and realizes aggregation placement and one-commodity multi-position shelf recommendation; the inventory optimization module adopts a multi-level model, comprehensively associates warehouse inventory and automatically triggers a deployment instruction; the goods allocation optimization module dynamically allocates goods allocation according to commodity characteristics, and arranges a goods picking sequence according to a shortest path; the data prediction module integrates multi-source data to predict order trends, and pre-picking orders are generated in advance, correspondingly, the invention further provides a commodity picking order generation method for realizing the system, corresponding electronic equipment and a computer readable storage medium, and an efficient and intelligent picking order generation solution is provided for suppliers.

Description

Technical Field

[0001] The present invention relates to the technical field of commodity logistics management, and more specifically, to a method and system for generating a commodity picking list at a supplier end. Background Art

[0002] Against the backdrop of the rapid development of the e-commerce industry, the generation of product picking lists on the supplier side faces many challenges. The traditional method of generating picking lists has many shortcomings. For example, order processing efficiency is low, unreasonable picking path planning leads to long picking time, product placement lacks scientific basis affecting picking speed, inaccurate inventory management leads to out-of-stock or backlogs, and it is impossible to prepare for picking in advance according to sales trends. These problems not only affect the supplier's operating efficiency, but also have a negative impact on the merchant's order processing and customer satisfaction.

[0003] Although there are some picking list generation systems on the market, their functions are relatively simple and cannot meet the comprehensive needs of suppliers in the ever-changing e-commerce environment. For example, some systems can only simply generate picking lists based on order information, without considering order similarity and storage location optimization, resulting in lengthy picking paths and low efficiency. Some systems also lack comprehensive consideration of the inventory of related warehouses in the supply chain network in terms of inventory management, and cannot achieve cross-warehouse allocation, which is prone to out-of-stock or backlogs in local warehouses. In addition, in terms of commodity placement, there is a lack of intelligent placement recommendations based on related commodity analysis and sales data, and commodities are placed arbitrarily, which increases the difficulty of picking. At the same time, the prediction of future order trends is not accurate enough, and pre-picking lists cannot be generated in advance, making it difficult for suppliers to respond quickly when facing promotional activities or seasonal sales peaks.

[0004] In summary, the existing technologies have problems such as low picking efficiency, unintelligent inventory allocation, lack of accurate prediction and reasonable layout, etc. Summary of the invention

[0005] In order to overcome the problems of low picking efficiency, unintelligent inventory allocation, lack of accurate prediction and reasonable layout in the prior art, the present invention designs a method and system for generating commodity picking lists on the supplier side that can effectively solve the above technical problems.

[0006] In order to solve the above technical problems, the technical solution of the present invention is as follows:

[0007] A system for generating a commodity picking list at a supplier end, comprising:

[0008] The route optimization module uses AI optimization algorithms to merge similar order data based on order similarity and location-related information, and evenly divides them into multiple picking tasks according to the number of pickers, selecting the shortest warehouse picking route;

[0009] The placement recommendation module is used to calculate related products through collaborative filtering algorithms and deep algorithms, and aggregate and place the related products; at the same time, based on daily hot sales data, promotional activities and seasonal factors, as well as robot or manual parallel fast picking routes, it generates a recommendation for multiple shelves for one product;

[0010] The inventory optimization module is used to adopt a multi-level inventory optimization model to automatically trigger cross-warehouse allocation instructions and integrate them into the picking list when generating a picking list based on the inventory status of each associated warehouse in the supply chain network;

[0011] The cargo location optimization module is used to use the cargo location optimization system to dynamically allocate cargo locations according to the sales frequency, volume and weight factors of the goods, and when generating the picking list, the cargo location information is combined to arrange the picking order according to the shortest path principle;

[0012] The data prediction module is used to integrate user reviews, product popularity and promotional activity data of the e-commerce platform and real-time logistics and transportation information, predict future order trends, and generate pre-picking orders in advance.

[0013] Preferably, the path optimization module includes:

[0014] An order merging unit, used to calculate order similarity based on the commodity type and quantity information in the order, and merge orders with similarity higher than a preset threshold;

[0015] The task division unit is used to divide the combined picking task into multiple subtasks evenly according to the number of pickers;

[0016] The route selection unit is used to select the warehouse picking route with the shortest total walking distance from multiple picking routes.

[0017] Preferably, the placement recommendation module includes:

[0018] A related product calculation unit, used to analyze customer purchase behavior through the collaborative filtering algorithm, find out frequently purchased product combinations, and then calculate related products using the deep algorithm;

[0019] A commodity placement unit is used to determine the storage area of ​​the associated commodities, and place the associated commodities on different shelves or different positions of the shelves in the same storage area according to commodity volume and weight rules;

[0020] The shelf recommendation unit is used to generate multiple shelf location recommendations for different products based on daily hot sales data, promotional activities and seasonal factors, combined with robot or manual parallel fast picking routes.

[0021] Preferably, the inventory optimization module includes:

[0022] Inventory monitoring unit, used to monitor the inventory quantity and in / out frequency of each commodity in the local warehouse in real time;

[0023] Inventory counting unit, used to regularly count the inventory of other related warehouses and synchronize the counted data with the local warehouse data to ensure the accuracy of inventory information of the entire supply chain network;

[0024] The allocation instruction triggering unit is used to determine whether cross-warehouse allocation is required based on inventory data and preset inventory policies. If necessary, the allocation instruction is automatically triggered and the allocation information is integrated into the picking list.

[0025] Preferably, the cargo space optimization module includes:

[0026] A commodity feature database unit for storing detailed information on commodity sales frequency, volume, weight and shelf life;

[0027] The storage location adjustment unit is used to dynamically adjust the storage locations of goods according to the data in the product feature database, combined with the warehouse layout and the location of the picking channel.

[0028] Preferably, the data prediction module includes:

[0029] Data integration unit, used to collect and integrate e-commerce platform user reviews, product popularity and promotion data, as well as obtain real-time logistics and transportation information;

[0030] An order prediction unit is used to analyze the integrated data to establish an order prediction model, and predict the order quantity, commodity type and demand trend in the future according to the order prediction model;

[0031] The pre-picking list generation unit is used to generate a pre-picking list in advance according to the prediction results, including the type, quantity and estimated picking time of the goods.

[0032] A method for generating a commodity picking list at a supplier end comprises the following steps:

[0033] Using AI optimization algorithms, similar order data is merged based on order similarity and location-related information, and evenly divided into multiple picking tasks based on the number of pickers, to select the shortest warehouse picking route;

[0034] Calculate related products through collaborative filtering algorithms and deep algorithms, and aggregate and display the related products; generate recommendations for multiple shelves for one product based on daily hot sales data, promotional activities, seasonal factors, and robot or manual parallel fast picking routes;

[0035] Adopting a multi-level inventory optimization model, when generating a picking list, the inventory status of each associated warehouse in the supply chain network is integrated, and cross-warehouse allocation instructions are automatically triggered and integrated into the picking list;

[0036] Use the cargo location optimization system to dynamically allocate cargo locations based on commodity sales frequency, volume and weight factors. When generating a picking list, combine the cargo location information and arrange the picking sequence according to the shortest path principle;

[0037] Integrate e-commerce platform user reviews, product popularity, promotional activity data and real-time logistics and transportation information to predict future order trends and generate pre-picking orders in advance.

[0038] An electronic device includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the steps of the above-mentioned method for generating a commodity picking list on the supplier side are implemented.

[0039] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned method for generating a commodity picking list at the supplier end are implemented.

[0040] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention significantly improves the efficiency and intelligence level of generating picking lists for goods on the supplier side by integrating multiple modules such as path optimization, placement recommendation, inventory optimization, cargo space optimization and data prediction. The path optimization and placement recommendation modules reduce the ineffective walking of pickers through AI algorithms and deep learning, realize the aggregate placement of related goods, greatly improve the picking efficiency, and can respond to orders quickly especially during peak hours. The intelligent allocation of the inventory optimization module ensures the reasonable distribution of inventory, avoids out-of-stocks, and reduces inventory costs. The accurate prediction of the data prediction module and the dynamic allocation of the cargo space optimization module enable suppliers to prepare in advance and reasonably layout goods, thereby improving the market response speed and warehouse operation efficiency, and realizing the intelligent management and optimization of the supply chain as a whole. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other implementation drawings can be derived based on the provided drawings without paying any creative work.

[0042] Figure 1 Generate a system structure diagram for a product picking list on the supplier side;

[0043] Figure 2 A step diagram of a method for generating a commodity picking list on the supplier side. DETAILED DESCRIPTION

[0044] The drawings are for illustrative purposes only and should not be construed as limiting the present patent;

[0045] In order to better illustrate the present embodiment, some parts in the drawings may be omitted, enlarged or reduced, and do not represent the size of the actual product;

[0046] It is understandable to those skilled in the art that some well-known structures and their descriptions may be omitted in the drawings.

[0047] The technical solution of the present invention is further described below in conjunction with the accompanying drawings and embodiments.

[0048] Example 1

[0049] A system for generating product picking lists on the supplier side, see Figure 1 ,include:

[0050] The route optimization module uses AI optimization algorithms to merge similar order data based on order similarity and location-related information, and evenly divides them into multiple picking tasks according to the number of pickers, selecting the shortest warehouse picking route;

[0051] The placement recommendation module is used to calculate related products through collaborative filtering algorithms and deep algorithms, and aggregate and place the related products; at the same time, based on daily hot sales data, promotional activities and seasonal factors, as well as robot or manual parallel fast picking routes, it generates a recommendation for multiple shelves for one product;

[0052] The inventory optimization module is used to adopt a multi-level inventory optimization model to automatically trigger cross-warehouse allocation instructions and integrate them into the picking list when generating a picking list based on the inventory status of each associated warehouse in the supply chain network;

[0053] The cargo location optimization module is used to use the cargo location optimization system to dynamically allocate cargo locations according to the sales frequency, volume and weight factors of the goods, and when generating the picking list, the cargo location information is combined to arrange the picking order according to the shortest path principle;

[0054] The data prediction module is used to integrate user reviews, product popularity and promotional activity data of the e-commerce platform and real-time logistics and transportation information, predict future order trends, and generate pre-picking orders in advance.

[0055] The path optimization module includes:

[0056] An order merging unit, used to calculate order similarity based on the commodity type and quantity information in the order, and merge orders with similarity higher than a preset threshold;

[0057] The task division unit is used to divide the combined picking task into multiple subtasks evenly according to the number of pickers;

[0058] The route selection unit is used to select the warehouse picking route with the shortest total walking distance from multiple picking routes.

[0059] The placement recommendation module includes:

[0060] A related product calculation unit, used to analyze customer purchase behavior through the collaborative filtering algorithm, find out frequently purchased product combinations, and then calculate related products using the deep algorithm;

[0061] A commodity placement unit is used to determine the storage area of ​​the associated commodities, and place the associated commodities on different shelves or different positions of the shelves in the same storage area according to commodity volume and weight rules;

[0062] The shelf recommendation unit is used to generate multiple shelf location recommendations for different products based on daily hot sales data, promotional activities and seasonal factors, combined with robot or manual parallel fast picking routes.

[0063] The inventory optimization module includes:

[0064] Inventory monitoring unit, used to monitor the inventory quantity and in / out frequency of each commodity in the local warehouse in real time;

[0065] Inventory counting unit, used to regularly count the inventory of other related warehouses and synchronize the counted data with the local warehouse data to ensure the accuracy of inventory information of the entire supply chain network;

[0066] The allocation instruction triggering unit is used to determine whether cross-warehouse allocation is required based on inventory data and preset inventory policies. If necessary, the allocation instruction is automatically triggered and the allocation information is integrated into the picking list.

[0067] The cargo space optimization module includes:

[0068] A commodity feature database unit for storing detailed information on commodity sales frequency, volume, weight and shelf life;

[0069] The storage location adjustment unit is used to dynamically adjust the storage locations of goods according to the data in the product feature database, combined with the warehouse layout and the location of the picking channel.

[0070] The data prediction module comprises:

[0071] Data integration unit, used to collect and integrate e-commerce platform user reviews, product popularity and promotion data, as well as obtain real-time logistics and transportation information;

[0072] An order prediction unit is used to analyze the integrated data to establish an order prediction model, and predict the order quantity, commodity type and demand trend in the future according to the order prediction model;

[0073] The pre-picking list generation unit is used to generate a pre-picking list in advance according to the prediction results, including the type, quantity and estimated picking time of the goods.

[0074] In the specific implementation, the order merging unit analyzes all orders of the day, and uses the similarity algorithm to calculate the order similarity based on the type and quantity information of the goods in the order. For example, Order A and Order B both contain Goods A and B, and the quantity is similar. The system determines that their similarity is higher than the preset threshold, and then merges the two orders into one picking task to reduce repeated walking and picking times; Task segmentation unit When there are 10 pickers in the warehouse on that day, the system will divide the merged picking task into 10 subtasks according to the number of pickers, and each picker is assigned to the corresponding task to ensure balanced task distribution and avoid excessive or insufficient workload for some personnel; The path selection unit generates multiple possible picking routes for each subtask based on the warehouse layout and shelf location information. Through the AI ​​optimization algorithm, it comprehensively considers factors such as route length, shelf spacing, and aisle congestion, and selects the warehouse picking route with the shortest total walking distance from many routes to provide the pickers with the best path guidance.

[0075] The related product calculation unit analyzes a large amount of customer purchase behavior data through collaborative filtering algorithms to find out the combination of products that are purchased frequently. For example, customers who buy mobile phones often buy accessories such as mobile phone cases and headphones at the same time. Then, the deep algorithm is used to further calculate related products to dig out deeper product associations, such as the association between mobile phones of different brands and compatible chargers. After the product placement unit determines the storage area for related products, it places them according to the rules of product volume and weight. For example, small and lightweight related products such as mobile phones and mobile phone cases are placed on different shelves in the same storage area, and mobile phone cases are placed on shelves close to mobile phone shelves. while heavier laptops are placed on the lower levels of the shelves with related products such as compatible radiators and mice to facilitate the handling of pickers; the shelf recommendation unit is based on daily popular sales data. For example, if the sales of a certain online celebrity snack have been high, the system combines promotional activities such as "buy one get one free" and "discounts for purchases over a certain amount" and seasonal factors, such as hot-selling cold drinks in summer and hot-selling warm products in winter, as well as robot or manual parallel fast picking routes to generate multiple shelf location recommendations for the online celebrity snack. It may be recommended to place it on a shelf close to the warehouse entrance with spacious picking aisles and easy to pass quickly to improve picking efficiency.

[0076] The inventory monitoring unit monitors the inventory quantity and in-and-out frequency of each commodity in the local warehouse in real time. Through sensors installed on the shelves and the warehouse management system, it obtains commodity inventory data in real time. For example, the current inventory of a certain commodity is 100 pieces, and the average daily in-and-out frequency is 20 times, etc., providing real-time basis for inventory management; the inventory counting unit regularly counts the inventory of other related warehouses, such as branch warehouses in the same city and warehouses in other places. The inventory counting cycle can be set to once a week or a month. After the inventory counting, the inventory counting data is synchronized with the local warehouse data to ensure the accuracy of the inventory information of the entire supply chain network and avoid inventory backlogs or out-of-stock problems caused by inconsistent data; the allocation instruction triggering unit determines whether cross-warehouse allocation is required based on inventory data and preset inventory strategies, such as safety inventory and replenishment cycle. For example, if the inventory of a certain commodity in the local warehouse is lower than the safety inventory, and other related warehouses have sufficient inventory, the system automatically triggers the allocation instruction, integrates the allocation information into the picking list, and indicates the type, quantity, source warehouse and other information of the allocated commodity, so that the picking personnel can handle the allocated commodity together when picking.

[0077] The commodity feature database unit establishes a commodity feature database to store detailed information such as commodity sales frequency, volume, weight and shelf life. For example, a certain beverage has a high sales frequency, a small volume, a light weight and a shelf life of 6 months, etc., to provide data support for storage location optimization; the storage location adjustment unit dynamically adjusts the commodity storage locations based on the data in the commodity feature database, combined with the warehouse layout and the location of the picking channel. For small and lightweight commodities with a high sales frequency, they are adjusted to a location close to the picking channel and easy to access on the shelf; and for commodities with large volume, heavy weight and low sales frequency, they are placed in a remote location in the warehouse and on the bottom shelf to make full use of the warehouse space and improve picking efficiency.

[0078] The data integration unit collects and integrates user reviews on the e-commerce platform, such as the rate of favorable reviews, reasons for negative reviews, etc., product popularity, views, collections, etc., promotional activity data, activity types, discount strength, etc., as well as real-time logistics and transportation information, transportation vehicle locations, estimated arrival times, etc., and connects with the e-commerce platform and logistics system through data interfaces to achieve real-time data transmission and integration. The order prediction unit analyzes the integrated data, uses statistical methods and machine learning algorithms to establish an order prediction model, and predicts the number of orders, product types and demand trends in the next week or month based on historical data and current trends. For example, it predicts that the order volume of a new electronic product will increase significantly in the early stage of its launch, and the product and related accessories will be the main ones. The pre-picking order generation unit generates a pre-picking order in advance based on the prediction results. The pre-picking order includes product types, quantities and estimated picking time. For example, if it is predicted that a large number of orders will include a best-selling clothing within a certain time period on a certain day, the system will generate a pre-picking order in advance, allowing the pickers to prepare in advance and pick the clothing and related matching products to the temporary storage area in advance, so that they can be shipped quickly when the order is officially placed, thereby improving customer satisfaction.

[0079] Example 2

[0080] A method for generating a product picking list on the supplier side, see Figure 2 , including the following steps:

[0081] Using AI optimization algorithms, similar order data is merged based on order similarity and location-related information, and evenly divided into multiple picking tasks based on the number of pickers, to select the shortest warehouse picking route;

[0082] Calculate related products through collaborative filtering algorithms and deep algorithms, and aggregate and display the related products; generate recommendations for multiple shelves for one product based on daily hot sales data, promotional activities, seasonal factors, and robot or manual parallel fast picking routes;

[0083] Adopting a multi-level inventory optimization model, when generating a picking list, the inventory status of each associated warehouse in the supply chain network is integrated, and cross-warehouse allocation instructions are automatically triggered and integrated into the picking list;

[0084] Use the cargo location optimization system to dynamically allocate cargo locations based on commodity sales frequency, volume and weight factors. When generating a picking list, combine the cargo location information and arrange the picking sequence according to the shortest path principle;

[0085] Integrate e-commerce platform user reviews, product popularity, promotional activity data and real-time logistics and transportation information to predict future order trends and generate pre-picking orders in advance.

[0086] An electronic device includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the steps of the above-mentioned method for generating a commodity picking list on the supplier side are implemented.

[0087] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned method for generating a commodity picking list at the supplier end are implemented.

[0088] Intelligent algorithms are used to merge similar orders based on order characteristics and shelf information, and orders are divided into several picking tasks based on the number of pickers. The shortest picking path in the warehouse is selected, and collaborative filtering and deep learning algorithms are used to identify and aggregate related products for easy placement. At the same time, based on sales data, promotional activities, seasonal demand, and automated or manual picking efficiency, multiple shelf location suggestions are provided for products, and a multi-level inventory management strategy is implemented. When making picking lists, the warehouse inventory status in the entire supply chain is considered, cross-warehouse allocation is automatically performed, and allocation information is included in the picking list. The shelf optimization system is used to dynamically allocate storage locations based on the sales activity, volume and weight of the products. When generating picking lists, the shelf information is combined to arrange the picking order according to the shortest path principle, integrate user feedback from e-commerce platforms, product popularity, promotional activity data and logistics information, predict order trends, and make pre-picking lists in advance.

[0089] An electronic device comprises a processor and a memory, wherein the memory stores a computer program executable by the processor, and when the program is executed, the steps of the above-mentioned method for generating a commodity picking list at the supplier end can be implemented.

[0090] A computer-readable storage medium stores a computer program, which, when executed on a processor, can implement the steps of the above-mentioned method for generating a commodity picking list at the supplier end.

[0091] The same or similar reference numerals correspond to the same or similar components;

[0092] The terms used in the drawings to describe positional relationships are only used for illustrative purposes and should not be construed as limiting this patent;

[0093] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not limitations on the implementation methods of the present invention. For ordinary technicians in the relevant field, other different forms of changes or modifications can be made on the basis of the above description. It is not necessary and impossible to list all the implementation methods here. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the claims of the present invention.

Claims

1. A system for generating a commodity picking list at a supplier end, characterized in that: include: The route optimization module uses AI optimization algorithms to merge similar order data based on order similarity and location-related information, and evenly divides them into multiple picking tasks according to the number of pickers, selecting the shortest warehouse picking route; The placement recommendation module is used to calculate related products through collaborative filtering algorithms and deep algorithms, and aggregate and place the related products; at the same time, based on daily hot sales data, promotional activities and seasonal factors, as well as robot or manual parallel fast picking routes, it generates a recommendation for multiple shelves for one product; The inventory optimization module is used to adopt a multi-level inventory optimization model to automatically trigger cross-warehouse allocation instructions and integrate them into the picking list when generating a picking list based on the inventory status of each associated warehouse in the supply chain network; The cargo location optimization module is used to use the cargo location optimization system to dynamically allocate cargo locations according to the sales frequency, volume and weight factors of the goods, and when generating the picking list, the cargo location information is combined to arrange the picking order according to the shortest path principle; The data prediction module is used to integrate user reviews, product popularity and promotional activity data of the e-commerce platform and real-time logistics and transportation information, predict future order trends, and generate pre-picking orders in advance.

2. A system for generating a product picking list at a supplier end according to claim 1, characterized in that: The path optimization module includes: An order merging unit, used to calculate order similarity based on the commodity type and quantity information in the order, and merge orders with similarity higher than a preset threshold; The task division unit is used to divide the combined picking task into multiple subtasks evenly according to the number of pickers; The route selection unit is used to select the warehouse picking route with the shortest total walking distance from multiple picking routes.

3. A system for generating a product picking list at a supplier end according to claim 1, characterized in that: The placement recommendation module includes: A related product calculation unit, used to analyze customer purchase behavior through the collaborative filtering algorithm, find out frequently purchased product combinations, and then calculate related products using the deep algorithm; A commodity placement unit is used to determine the storage area of ​​the associated commodities, and place the associated commodities on different shelves or different positions of the shelves in the same storage area according to commodity volume and weight rules; The shelf recommendation unit is used to generate multiple shelf location recommendations for different products based on daily hot sales data, promotional activities and seasonal factors, combined with robot or manual parallel fast picking routes.

4. A system for generating a product picking list at a supplier end according to claim 1, characterized in that: The inventory optimization module includes: Inventory monitoring unit, used to monitor the inventory quantity and in / out frequency of each commodity in the local warehouse in real time; Inventory counting unit, used to regularly count the inventory of other related warehouses and synchronize the counted data with the local warehouse data to ensure the accuracy of inventory information of the entire supply chain network; The allocation instruction triggering unit is used to determine whether cross-warehouse allocation is required based on inventory data and preset inventory policies. If necessary, the allocation instruction is automatically triggered and the allocation information is integrated into the picking list.

5. A system for generating a product picking list at a supplier end according to claim 1, characterized in that: The cargo space optimization module includes: A commodity feature database unit for storing detailed information on commodity sales frequency, volume, weight and shelf life; The storage location adjustment unit is used to dynamically adjust the storage locations of goods according to the data in the product feature database, combined with the warehouse layout and the location of the picking channel.

6. A system for generating a product picking list at a supplier end according to claim 1, characterized in that: The data prediction module comprises: Data integration unit, used to collect and integrate e-commerce platform user reviews, product popularity and promotion data, as well as obtain real-time logistics and transportation information; An order prediction unit is used to analyze the integrated data to establish an order prediction model, and predict the order quantity, commodity type and demand trend in the future according to the order prediction model; The pre-picking list generation unit is used to generate a pre-picking list in advance according to the prediction results, including the type, quantity and estimated picking time of the goods.

7. A method for generating a commodity picking list at a supplier end, used to implement a system for generating a commodity picking list at a supplier end according to any one of claims 1 to 6, characterized in that: The following steps are involved: Using AI optimization algorithms, similar order data is merged based on order similarity and location-related information, and evenly divided into multiple picking tasks based on the number of pickers, to select the shortest warehouse picking route; Calculate related products through collaborative filtering algorithms and deep algorithms, and aggregate and display the related products; generate recommendations for multiple shelves for one product based on daily hot sales data, promotional activities, seasonal factors, and robot or manual parallel fast picking routes; Adopting a multi-level inventory optimization model, when generating a picking list, the inventory status of each associated warehouse in the supply chain network is integrated, and cross-warehouse allocation instructions are automatically triggered and integrated into the picking list; Use the cargo location optimization system to dynamically allocate cargo locations based on commodity sales frequency, volume and weight factors. When generating a picking list, combine the cargo location information and arrange the picking sequence according to the shortest path principle; Integrate e-commerce platform user reviews, product popularity, promotional activity data and real-time logistics and transportation information to predict future order trends and generate pre-picking orders in advance.

8. An electronic device, characterized in that: The invention comprises a processor, a memory and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of a method for generating a commodity picking list at a supplier end as described in claim 7.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the steps of the method for generating a commodity picking list at the supplier end described in claim 7 are implemented.

Images