CN118628024B

CN118628024B - Logistics storage management method and system

Info

Publication number: CN118628024B
Application number: CN202411099643.6A
Authority: CN
Inventors: 吕伟亮; 倪李俊
Original assignee: Lemai Information Technology Hangzhou Co ltd
Current assignee: Lemai Information Technology Hangzhou Co ltd
Priority date: 2024-08-12
Filing date: 2024-08-12
Publication date: 2024-11-26
Anticipated expiration: 2044-08-12
Also published as: CN118628024A

Abstract

The present invention proposes a logistics warehousing management method and system, wherein the method comprises: obtaining historical inventory information, predicting demand inventory according to the historical inventory information, obtaining a reorder point according to the predicted demand inventory, and sending an alarm message to the management personnel when the actual inventory reaches or falls below the reorder point to remind them to place an order; after placing an order, obtaining a warehouse entry form of a logistics warehousing warehouse of daily necessities, predicting the sales of the goods in the warehouse entry form, and allocating storage space for goods with high sales volume according to the predicted sales of the goods; obtaining information on different goods being browsed, added to shopping carts, and purchased, obtaining the goods correlation according to the information, and allocating storage space for goods with a large correlation with goods with high sales volume according to the goods correlation; when the goods are shipped out, determining the order of shipping out of the goods according to the order picking time within a preset time interval.

Description

Logistics storage management method and system

Technical Field

The invention provides a logistics storage management method and system, and belongs to the technical field of intelligent storage.

Background

In recent years, with the vigorous development of global electronic commerce and the increasing market demand, the traditional warehouse management mode has difficulty in meeting the requirements of the modern logistics industry on high efficiency, low cost and high reliability. In addition, as technology advances, customers have a higher desire for speed, accuracy, and traceability of cargo handling. The conventional warehouse management method has the following problems that when goods are reordered, the goods are often determined according to the previous human experience, mistakes are easy to occur, market change cannot be met, when the goods are warehoused, the possible sales of the goods in the future cannot be considered, the goods stored in the innermost part are frequently put in the warehouse, resources are consumed when the goods are put in the warehouse, or the goods cannot be stored according to the association degree among the goods, and the goods are possibly irrelevant, but when a user purchases the goods, the user always purchases another goods due to the promotion of a platform or the purchase of the goods due to the order-making activity, or the conventional warehouse shipment processes the order according to the order-making time of the customer, so that the order processing speed is slow, and the overall average shipment time is influenced.

Disclosure of Invention

The invention provides a logistics warehouse management method and a logistics warehouse management system, which are used for solving the problems mentioned above:

The invention provides a logistics storage management method, which comprises the following steps:

Acquiring historical inventory information, predicting a demand inventory according to the historical inventory information, acquiring a re-ordering point according to the predicted demand inventory, and sending alarm information to a manager to remind the manager of ordering when the actual inventory reaches or falls below the re-ordering point;

after ordering, acquiring a warehouse entry list of a logistics warehouse of the daily necessities, predicting the sales condition of the goods of the warehouse entry list, and distributing goods positions for the goods with high sales volume according to the predicted sales condition of the goods;

Acquiring information of browsed, added shopping carts and purchased different cargoes, acquiring the association degree of the cargoes according to the information, and distributing cargo positions with large association degree with the cargoes with high sales volume according to the association degree of the cargoes;

and when the goods are delivered, determining the delivery sequence of the goods according to the order picking time in a preset time interval.

Further, obtaining historical inventory information, predicting a demand inventory according to the historical inventory information, obtaining a reorder point according to the predicted demand inventory, and sending alarm information to a manager to remind the manager of ordering when the actual inventory reaches or falls below the reorder point, wherein the method comprises the following steps:

Acquiring historical inventory information, the historical inventory information comprising: historical inventory data, promotional data for corresponding goods, and seasonal factors;

The acquired information is tidied and cleaned, and future inventory requirements are predicted through seasonal ARIMA;

the predicting future inventory requirements by seasonal ARIMA includes:

dividing the historical data into a training set and a verification set;

training an initial demand prediction model using training set data;

Predicting the data of the verification set by using the initial demand prediction model, modifying the model according to the prediction result to obtain a demand prediction model, and predicting the verification set by using the initial demand prediction model to obtain the predicted inventory demand quantity D _j;

Calculating a reorder point according to the predicted value, wherein the reorder point calculation model is as follows:

Wherein R is the re-ordering point of the goods, mu is the predicted average demand quantity of the goods, LT is the average delivery time, Z is the safety coefficient of the goods corresponding to the required service level, n is the number of predicted points, D _i is the actual stock demand quantity, and D _j is the predicted stock demand quantity;

And when the stock quantity of the goods reaches or falls below the re-ordering point, sending alarm information to the manager to remind the manager of ordering the goods.

Further, after ordering, obtaining a warehouse entry of a logistics warehouse of the daily necessities, predicting the sales condition of the goods of the warehouse entry, and distributing goods positions for the goods according to the predicted sales condition of the goods, including:

after ordering, acquiring a warehouse entry list, acquiring the types of goods in the warehouse entry list, and acquiring historical sales data, inventory data and seasonal variation data of each type of goods;

Predicting sales of each cargo according to the historical sales data, the inventory data and the seasonal variation data;

Sorting goods in a descending order according to the predicted sales volume;

ascending order of the goods places according to the goods choosing distance from the initial goods choosing point to the goods places;

sequentially distributing the cargoes ranked in the first 50% to the ordered cargo positions.

Further, acquiring information that different cargoes are browsed, added into shopping carts and purchased, acquiring a cargo association degree according to the information, and distributing cargo positions with large cargo association degree with high sales volume according to the cargo association degree, wherein the method comprises the following steps:

Acquiring information that different cargoes in the logistics warehouse are browsed, added into shopping carts and purchased, and calculating the association degree of the cargoes through a cargo association degree model;

The cargo association degree model is as follows:

Wherein I (I: j _t) is the degree of association between good I and good j at time t, x _i,x_j represents the specific actions of good I and good j, respectively, including purchasing, browsing and joining shopping carts, p (x _i,x_j, t) represents the probability of simultaneous occurrence of good I in state x _i and good j in state x _j at time t, p (x _i, t) represents the probability of independent occurrence of good I in state x _i at time t, and p (x _j, t) represents the probability of independent occurrence of good j in state x _j at time t;

acquiring the association degree of the goods with the predicted sales quantity of which the last 50% is arranged and the goods with the predicted sales quantity of which the first 50% is arranged;

sorting the predicted sales amount of the cargoes arranged at the front 50% from high to low, sorting the association degree of the cargoes arranged at the back 50% and the cargoes arranged at the front 50% according to the predicted sales amount, acquiring the cargoes arranged at the back 50% with the largest association degree with the cargoes arranged at the front 50%, distributing the cargoes to the idle cargoes closest to the cargoes arranged at the front 50%, and acquiring the cargoes with the largest association degree without the allocated cargoes when the cargoes with the largest association degree are distributed, and distributing the cargoes closest to the cargoes arranged at the front 50%.

Further, when goods are delivered, determining a goods delivery sequence according to order picking time within a preset time interval, including:

When a plurality of orders are received in a preset time interval, acquiring picking time of each order;

Shipping orders in a preset time interval according to the order picking time sequence from less to more;

and sending the carrying instruction to the goods picking equipment, wherein the goods picking equipment picks goods sequentially.

The invention provides a logistics warehouse management system, which comprises:

the ordering module is used for acquiring historical inventory information, predicting demand inventory according to the historical inventory information, acquiring a re-ordering point according to the predicted demand inventory, and sending alarm information to a manager to remind the manager of ordering when the actual inventory reaches or falls below the re-ordering point;

The sales allocation goods space module is used for acquiring a warehouse entry list of a logistics warehouse of the daily necessities after ordering, predicting the sales condition of goods of the warehouse entry list, and allocating goods space for the goods with high sales volume according to the predicted sales condition of the goods;

the association distribution cargo space module is used for acquiring information of different cargoes browsed, added into shopping carts and purchased, acquiring the association degree of the cargoes according to the information, and distributing cargo spaces with high association degree with the cargoes with high sales according to the association degree of the cargoes;

and the delivery module is used for determining the delivery sequence of the goods according to the order picking time in a preset time interval when the goods are delivered.

Further, the order module includes:

The history information acquisition module is used for acquiring history inventory information, and the history inventory information comprises: historical inventory data, promotional data for corresponding goods, and seasonal factors;

The prediction module is used for sorting and cleaning the acquired information and predicting future inventory requirements through seasonal ARIMA; the predicting future inventory requirements by seasonal ARIMA includes:

dividing the historical data into a training set and a verification set;

training an initial demand prediction model using training set data;

And the reminding order module is used for sending alarm information to the manager to remind the manager of ordering when the stock quantity of the goods reaches or is lower than the re-ordering point.

Further, the sales allocation cargo space module includes:

the system comprises a module for acquiring sales data of each kind of goods, a module for acquiring a warehouse entry list after ordering, acquiring the kind of the goods in the warehouse entry list, and acquiring historical sales data, inventory data and seasonal variation data of each kind of goods;

The forecast sales module is used for forecasting sales conditions of each cargo according to historical sales data, inventory data and seasonal change data;

the sales ordering module is used for ordering goods in a descending order according to the predicted sales amount;

the distance sorting module is used for sorting the goods places in ascending order according to the goods sorting distance from the initial goods sorting point to the goods places;

And the distribution module is used for sequentially distributing the cargoes which are ranked at the top 50% to the ranked cargo positions.

Further, the association allocation cargo space module includes:

The goods association degree calculating module is used for obtaining information that different goods in the logistics warehouse are browsed, added into shopping carts and purchased, and calculating the goods association degree through a goods association degree model;

The cargo association degree model is as follows:

Wherein I (I; j _t) is the degree of association between good I and good j at time t, x _i,x_j represents the specific actions of good I and good j, respectively, including purchasing, browsing and joining shopping carts, p (x _i,x_j, t) represents the probability of simultaneous occurrence of good I in state x _i and good j in state x _j at time t, p (x _i, t) represents the probability of independent occurrence of good I in state x _i at time t, and p (x _j, t) represents the probability of independent occurrence of good j in state x _j at time t;

The sales quantity association degree obtaining module is used for obtaining association degree of the goods with the predicted sales quantity of which the back 50% is arranged and the goods with the predicted sales quantity of which the front 50% is arranged;

The sorting and distributing cargo space module is used for sorting the predicted sales volume of the cargoes which are arranged in the front 50% from high to low, sorting the cargoes which are arranged in the rear 50% and the association degree of the cargoes which are arranged in the front 50% according to the predicted sales volume, obtaining the cargoes which are arranged in the rear 50% and have the largest association degree with the cargoes which are arranged in the front 50% and have the largest association degree with the cargoes, distributing the cargoes to the idle cargo space which is closest to the cargoes which are arranged in the front 50%, and obtaining the cargoes which are not distributed and have the largest association degree with the cargoes when the cargoes which are distributed with the largest association degree are distributed with the cargoes which are arranged in the front 50%.

Assume that there are two commodities: commodity i and commodity j, during a certain period of time t, the user may perform the following three operating states for both commodities: purchasing (B), browsing (V) and joining shopping carts (A),

In this scenario, all possible state combinations for commodity i and commodity j are as follows:

(X _i＝B,X_j =b): both commodity i and commodity j were purchased, (X _i＝B,X_j = V): commodity i is purchased, commodity j is viewed, (X _i＝B,X_j = a) commodity i is purchased, commodity j is added to the shopping cart, (X _i＝V,X_j = B) commodity i is viewed, commodity j is purchased, (X _i＝V,X_j = V) commodity i and commodity j are both viewed, (X _i＝V,X_j = a) commodity i is viewed, commodity j is added to the shopping cart, (X _i＝A,X_j = B) commodity i is added to the shopping cart, commodity j is purchased, (X _i＝A,X_j = V) commodity i is added to the shopping cart, commodity j is viewed, (X _i＝A,X_j = a) commodity i and commodity j are both added to the shopping cart, we need to calculate the probabilities P (X _i,X_j, t) for each state combination and the individual probabilities P (X _i, t) and P (X _j, t), and then calculate and sum these values into the formula.

Further, a logistics warehouse management system, the warehouse-out module includes:

The order picking time acquisition module is used for acquiring picking time of each order when a plurality of orders are received in a preset time interval;

the order picking time ordering module is used for carrying out shipment on orders in a preset time interval according to the order picking time from less to more;

and the sending instruction module is used for sending the carrying instruction to the goods picking equipment, and the goods picking equipment picks goods sequentially.

The invention has the beneficial effects that: inventory management optimization, accurate demand prediction and timely replenishment can significantly reduce the conditions of backorder or excess inventory, thereby reducing capital occupation and storage cost; the operation efficiency is improved, the moving time of staff in a warehouse can be reduced by optimizing goods space distribution and an intelligent goods picking strategy, the overall goods processing speed is accelerated, and the working efficiency is improved; the sales amount is increased, so that the full inventory and quick delivery of the hot-sold commodities and related commodities are ensured, the satisfaction degree of customers can be improved, the loss of sales opportunities is reduced, and the overall sales amount can be increased; the flexibility of responding to market demands, the quick response capability of the system, so that the warehouse can flexibly adapt to market demand changes, especially in the case of sales promotion peak (such as supply chain interruption); in general, the technical scheme greatly improves the intelligent level of inventory management by comprehensively utilizing the data analysis, the automation system and the intelligent algorithm, reduces the operation cost and improves the service quality of clients.

Drawings

FIG. 1 is a schematic diagram of a logistics warehouse management method according to the present invention;

Fig. 2 is a schematic diagram of a logistics warehouse management system according to the present invention.

Detailed Description

In order that the above-recited objects, features and advantages of the present application will be more clearly understood, a more particular description of the application will be rendered by reference to specific embodiments thereof which are illustrated in the appended drawings. It should be noted that, without conflict, the embodiments of the present application and features in the embodiments may be combined with each other.

In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, and the described embodiments are merely some, rather than all, embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.

The embodiment of the invention, 1. A logistics warehouse management method is characterized in that the method comprises the following steps:

The working principle and the effect of the technical scheme are as follows: the technical scheme combines historical inventory information, demand prediction, reorder point setting, sales prediction, goods positioning and order processing strategies to form a comprehensive inventory and logistics management system, historical inventory data analysis and demand prediction are based on past inventory data (such as past sales, seasonal fluctuation, market trend and the like), the system predicts future inventory demands by using a machine learning model, the reorder point is determined, and the system sets the reorder point according to the predicted demand inventory. When the actual stock level is reduced to the point or lower, the system automatically sends out alarm information to remind a manager to carry out replenishment; and (3) warehousing and sales prediction of the goods, when the goods arrive at the warehouse, acquiring warehousing information, and predicting future sales conditions of the goods. Such predictions may be based on historical sales data, market trends, promotional program information, and the like; goods allocation optimization, namely allocating good goods to be delivered out of a warehouse rapidly for goods with high sales prediction, and determining goods in consideration of the association degree (such as goods which are often purchased together) among the goods so as to optimize a picking path and improve picking efficiency; and (3) intelligent picking and delivery management, wherein in a set time interval, the system starts to process the orders with short picking time preferentially according to the picking time of each order, so that the overall delivery efficiency is improved. Inventory management optimization, accurate demand prediction and timely replenishment can significantly reduce the conditions of backorder or excess inventory, thereby reducing capital occupation and storage cost; the operation efficiency is improved, the moving time of staff in a warehouse can be reduced by optimizing goods space distribution and an intelligent goods picking strategy, the overall goods processing speed is accelerated, and the working efficiency is improved; the sales amount is increased, so that the full inventory and quick delivery of the hot-sold commodities and related commodities are ensured, the satisfaction degree of customers can be improved, the loss of sales opportunities is reduced, and the overall sales amount can be increased; the flexibility of responding to market demands, the quick response capability of the system, so that the warehouse can flexibly adapt to market demand changes, especially in the case of sales promotion peak (such as supply chain interruption); in general, the technical scheme greatly improves the intelligent level of inventory management by comprehensively utilizing the data analysis, the automation system and the intelligent algorithm, reduces the operation cost and improves the service quality of clients.

An embodiment of the present invention is a logistics storage management method, which is characterized in that historical inventory information is obtained, demand inventory is predicted according to the historical inventory information, a reorder point is obtained according to the predicted demand inventory, and when an actual inventory reaches or falls below the reorder point, alarm information is sent to a manager to remind the manager of ordering, including:

the predicting future inventory requirements by seasonal ARIMA includes:

dividing the historical data into a training set and a verification set;

training an initial demand prediction model using training set data;

The working principle and the effect of the technical scheme are as follows: according to the technical scheme, a seasonal ARIMA (AutoRegressive Integrated Moving Average, autoregressive integral moving average model) model is used for implementing inventory management and optimization, data collection and preprocessing are carried out, historical inventory data are collected firstly, and the collected data are tidied and cleaned by combining related promotion activity data and seasonal factors, so that noise and abnormal values are eliminated, and the data quality is ensured; model construction and training, namely dividing the cleaned data into a training set and a verification set, and training a seasonal ARIMA model by using the training set data, wherein the model can capture seasonal fluctuation and trend in the data and is suitable for predicting time sequence data with obvious periodic modes; the demand prediction and verification, wherein the trained model is utilized to predict a verification set so as to evaluate the accuracy and reliability of the model and predict the inventory demand value of each time point in the future; calculation of the re-order points are calculated according to the model predicted demand and parameters estimated from historical data (e.g., average demand mu, average delivery time, etc.), inventory monitoring and management, the system monitors real-time inventory levels, and once the inventory is below the calculated re-order points, alarm information is sent to the manager to prompt replenishment operations. The accuracy is improved, and the seasonal ARIMA model is utilized to more accurately predict the inventory requirement with periodicity and trend characteristics, so that the inventory management is more scientific and accurate; in response to market changes in time, the system can respond to market changes rapidly by monitoring real-time inventory and comparing with preset re-ordering points, and loss caused by stock shortage or excessive inventory is reduced; cost optimization, demand prediction in advance and inventory level optimization can obviously reduce storage cost and prevent funds from being excessively idle in excessive inventory; the service level is improved, and the proper inventory level is maintained to ensure that the requirements of customers can be met, so that the loss of sales opportunities caused by backorders is avoided, and the customer satisfaction degree and brand reputation are improved; risk management, namely adjusting a re-ordering point by setting a safety coefficient Z, and reflecting trade-off between the enterprise for the backorder risk and the inventory cost; a high safety factor means a higher stock level to avoid the risk of a backout, while a lower safety factor may reduce stock carrying costs but increase the risk of a backout; the selection of the proper Z value can be flexibly adjusted according to market demands and enterprise strategies.

According to one embodiment of the invention, a logistics storage management method, after ordering, obtains a warehouse entry list of a logistics storage warehouse of daily necessities, predicts the sales condition of goods of the warehouse entry list, and allocates goods positions for the goods according to the predicted sales condition of the goods, comprising:

Sorting goods in a descending order according to the predicted sales volume;

The working principle and the effect of the technical scheme are as follows: according to the technical scheme, the following main steps are executed by integrating historical sales data, inventory data and seasonal variation factors of warehoused goods: data arrangement and analysis, and obtaining a warehouse entry bill after ordering, and listing the types of goods in detail; collecting historical sales data, inventory data, and seasonal variation data for each type of cargo;

Sales prediction, using historical sales data, inventory conditions, and seasonal data, using statistical or machine learning models (e.g., time series prediction models) to predict future sales performance for each good; sorting goods, namely sorting the goods in a descending order according to the predicted sales quantity so as to determine which goods have higher expected sales quantity; sorting and distributing goods places, namely sorting the goods places in the warehouse in ascending order according to the goods choosing distance from the initial goods choosing point to the goods places so as to optimize the goods choosing route and reduce the moving distance of staff; the top 50% of the items in the forecast sales volume are distributed to the top 50% of the ordered items, with the aim of placing high sales volume items in a more convenient location for picking.

The picking efficiency is improved, the picking time and labor cost are reduced, and the working efficiency is improved by distributing the commodity with high sales volume to a position which is easier to reach; optimizing inventory management, accurate sales prediction can help to better manage inventory, avoid excessive inventory or backorder, reduce holding cost and improve fund turnover rate; customer satisfaction is improved, picking and distribution processes are quickened, customer orders can be responded more quickly, and customer satisfaction and service level are improved; the logistics cost is reduced, the goods space layout is optimized, and the transportation and carrying distance in the warehouse is reduced, so that the internal logistics cost is reduced; the market change is flexibly dealt with, and the goods sales prediction is carried out by considering seasonal change, so that the warehouse can adjust the inventory strategy according to seasonal fluctuation of market demands, and the market change such as holiday sales peak and the like can be better dealt with. In general, by efficiently combining sales prediction with physical layout optimization, this solution can significantly improve warehouse operating efficiency and response speed, making the whole supply chain more efficient and competitive.

According to one embodiment of the invention, a logistics storage management method obtains information that different cargoes are browsed, added into shopping carts and purchased, obtains the association degree of the cargoes according to the information, and distributes cargo positions for cargoes with high association degree with cargoes with high sales according to the association degree of the cargoes, wherein the logistics storage management method comprises the following steps:

the method comprises the steps of obtaining information that different cargoes in the logistics warehouse are browsed, added into a shopping cart and purchased, and calculating the association degree of the cargoes through a cargo association degree model, wherein the cargo association degree model is as follows:

The item association model includes various states or combinations of behaviors, each of which can be in a number of different states (e.g., purchase, browse, join shopping cart, etc.) at a given time t, summed to ensure that the algorithm can include all possible combinations of states for these items and calculate the association between them; comprehensively evaluating overall mutual information: mutual information is a measure of shared information between two variables, summing all possible state combinations means a comprehensive assessment of the amount of information of items i and j under all possible interactions, which provides a comprehensive view of how different states or behaviors affect each other as a whole in time t; calculating the degree of association of the whole, each state or behavior alone may not be sufficient to express the overall relationship between the goods. For example, considering the "purchase" behavior alone may ignore interactions of the "browse" or "join shopping cart" behaviors. Integrating all behavior patterns provides a more comprehensive correlation analysis.

Assume that there are two commodities: commodity i and commodity j, during a certain period of time t, the user may perform the following three operating states for both commodities: purchase (B), browse (V), and join shopping cart (a).

The technical scheme uses the cargo association degree model to optimize the layout of the cargoes in the warehouse, collects and analyzes data, collects behavior data of different cargoes in the warehouse, and comprises browsing, adding shopping carts and purchasing; calculating the relevancy of cargoes, applying a cargo relevancy model, measuring the relevancy of two cargoes by comparing the ratio of the behavior probability between the cargoes to the independent behavior probability, sorting the relevancy of the cargoes and distributing the cargo space, sorting the cargoes with predicted sales, and screening out the first 50% with higher sales and the last 50% with lower sales respectively; calculating the association degree between the front 50% of high sales goods and the rear 50% of goods; matching the goods with the highest sales ranking in the last 50% according to the association degree and sales, and carrying out cargo space distribution; the low sales volume goods with high association degree are distributed to the idle goods space close to the high sales volume goods, so that the distribution efficiency and the convenience of purchasing various goods by customers are improved; the goods picking efficiency is improved, and the goods with high relevance are placed at the positions close to each other, so that the moving distance during goods picking is reduced, and the goods picking efficiency is improved; optimizing warehouse space usage: the reasonable goods layout enables the hot goods to be more easily accessible, ensures the logic placement of the related goods, and effectively utilizes warehouse space; based on dynamic adjustment of data, the scheme allows the association degree and the position of goods to be updated and adjusted periodically, so that the strategy has the flexibility of dynamic adjustment to cope with the change of market and consumption behavior; in general, through intelligent analysis and strategic goods space arrangement, the technical scheme not only improves the efficiency of warehouse operation, but also can enhance the purchase experience of customers and increase sales, and is a warehouse management solution with improved comprehensive performance.

In one embodiment of the present invention, a logistic warehouse management method, when delivering goods, determines a goods delivery sequence according to order picking time within a preset time interval, includes:

And determining whether the goods delivery sequence is when the free picking equipment is not in the warehouse or is first served according to first come first served in the preset time interval according to the order picking time, and referring to the following time interval model when the free picking equipment is not in the warehouse.

T＝min(T_b+α·ln(1+N)+β·ln(1+M)，Tmax)

Where T is a preset time interval, T _b is a base time interval, which is a minimum time interval that the system should hold regardless of the number or size of orders, the base time interval can be set to be the average time that the AGV trolley processes an order, α is an adjustment factor related to the number of orders, N is the total number of orders currently pending, β is an adjustment factor related to the average number of goods of the orders, M is the average number of goods of all orders currently pending, and T _max is a preset maximum time interval.

The working principle and the effect of the technical scheme are as follows: according to the technical scheme, the order processing flow is optimized, so that the warehouse can process and ship orders more efficiently, order information is collected, information of each received order is collected by the system in a preset time interval, the picking time is calculated and ordered, the complete picking time required by each order is calculated, and the complete picking time is based on factors such as the positions and the quantity of commodities in the order and relevant picking paths; ordering the collected orders according to the time required by picking from less to more; order shipment optimization, in which orders with short pick times are preferentially processed according to the ordering of pick times. This means that orders requiring less time to prepare can be placed first, thereby improving overall shipping efficiency; The system automatically sends the order of pick to a pick device, such as an automated pick robot or a conventional picker; the picking device or person will perform the picking operation in accordance with the instructions of the system. The processing speed is improved, and the processing speed of the whole order is improved by optimizing the processing sequence of the orders, namely preferentially processing the orders with shorter picking time; improving customer satisfaction, faster order processing speed generally means that the customer can receive the goods faster, which directly improves customer satisfaction; the efficiency is improved, the clear order of picking reduces the purposeless movement of equipment and personnel in the warehouse, reduces the time waste and improves the overall efficiency of picking. The error rate is reduced, and the system automation instructions reduce errors caused by human factors, such as picking out goods or missing certain orders; Resource optimization, reasonable time ordering and machine scheduling allow more efficient use of warehouse resources, including employee time and use of mechanical equipment. The structured operation is promoted, the structured level of the operation is promoted by the unified and automatic processing flow, and the confusion and uncertainty in the operation are reduced. In a word, the technical scheme ensures that warehouse operation is more efficient and systematic by intelligently optimizing the order processing sequence, thereby remarkably improving the processing speed and the customer service quality and realizing higher operation efficiency and lower error rate; calculating a current time interval using the provided formula, wherein T _b is the lowest base time interval that the system should maintain when the order quantity is minimal, the parameter α controls the effect of the order quantity (N) on the interval, and β controls the effect of the average cargo quantity (M); ordering orders within this time interval from less to more according to the items of the load location information to generate a shipping order that minimizes the average shipping time in the event that the AGV cart resource is limited and cannot immediately respond to the user's request for order placement, significantly reducing the average shipping time of orders by ordering orders within this time interval from less to more according to the items of the load location information, since less of the load information is preferentially processed, they leave the system faster, resulting in a reduction in the number of orders waiting to be shipped and the average shipping time for all orders; the shorter operation can process more operations in unit time due to the fact that the operation is completed quickly, and therefore the throughput of the system can be improved; Reducing the cumulative delay of orders, the early completion of orders means that tasks that subsequently rely on those orders can begin early, shortening the cumulative delay in the order flow; improving the user experience, a system that sees a fast response would have a better experience for the user, which is especially important for applications that require interactive responses.

In one embodiment of the present invention, a logistics warehouse management system, the system comprises:

In one embodiment of the present invention, a logistics warehouse management system, the order module includes:

dividing the historical data into a training set and a verification set;

training an initial demand prediction model using training set data;

In one embodiment of the present invention, a logistics warehouse management system, the sales allocation cargo space module includes:

In one embodiment of the present invention, a logistics warehouse management system, the associated allocation cargo space module includes:

the module for calculating the relevancy of the goods is used for acquiring information that different goods in the logistics warehouse are browsed, added into a shopping cart and purchased, and calculating the relevancy of the goods through a relevancy model of the goods, wherein the relevancy model of the goods is as follows:

The working principle and the effect of the technical scheme are as follows: according to the technical scheme, the layout of the goods in the warehouse is optimized by using a goods association degree model, data are collected and analyzed, and behavior data of different goods in the warehouse are collected, including browsing, shopping cart adding and purchasing; calculating the relevancy of cargoes, applying a cargo relevancy model, measuring the relevancy of two cargoes by comparing the ratio of the behavior probability between the cargoes to the independent behavior probability, sorting the relevancy of the cargoes and distributing the cargo space, sorting the cargoes with predicted sales, and screening out the first 50% with higher sales and the last 50% with lower sales respectively; calculating the association degree between the front 50% of high sales goods and the rear 50% of goods; matching the goods with the highest sales ranking in the last 50% according to the association degree and sales, and carrying out cargo space distribution; the low sales volume goods with high association degree are distributed to the idle goods space close to the high sales volume goods, so that the distribution efficiency and the convenience of purchasing various goods by customers are improved; the goods picking efficiency is improved, and the goods with high relevance are placed at the positions close to each other, so that the moving distance during goods picking is reduced, and the goods picking efficiency is improved; optimizing warehouse space usage: the reasonable goods layout enables the hot goods to be more easily accessible, ensures the logic placement of the related goods, and effectively utilizes warehouse space; based on dynamic adjustment of data, the scheme allows the association degree and the position of goods to be updated and adjusted periodically, so that the strategy has the flexibility of dynamic adjustment to cope with the change of market and consumption behavior; in general, through intelligent analysis and strategic goods space arrangement, the technical scheme not only improves the efficiency of warehouse operation, but also can enhance the purchase experience of customers and increase sales, and is a warehouse management solution with improved comprehensive performance.

In one embodiment of the present invention, a logistics warehouse management system, the warehouse-out module includes:

T＝min(T_b+α·ln(1+N)+β·ln(1+M)，Tmax)

The working principle and the effect of the technical scheme are as follows: according to the technical scheme, the order processing flow is optimized, so that the warehouse can process and ship orders more efficiently, order information is collected, information of each received order is collected by the system in a preset time interval, the picking time is calculated and ordered, the complete picking time required by each order is calculated, and the complete picking time is based on factors such as the positions and the quantity of commodities in the order and relevant picking paths; ordering the collected orders according to the time required by picking from less to more; order shipment optimization, in which orders with short pick times are preferentially processed according to the ordering of pick times. This means that orders requiring less time to prepare can be placed first, thereby improving overall shipping efficiency; The system automatically sends the order of pick to a pick device, such as an automated pick robot or a conventional picker; the picking device or person will perform the picking operation in accordance with the instructions of the system. The processing speed is improved, and the processing speed of the whole order is improved by optimizing the processing sequence of the orders, namely preferentially processing the orders with shorter picking time; improving customer satisfaction, faster order processing speed generally means that the customer can receive the goods faster, which directly improves customer satisfaction; the efficiency is improved, the clear order of picking reduces the purposeless movement of equipment and personnel in the warehouse, reduces the time waste and improves the overall efficiency of picking. The error rate is reduced, and the system automation instructions reduce errors caused by human factors, such as picking out goods or missing certain orders; Resource optimization, reasonable time ordering and machine scheduling allow more efficient use of warehouse resources, including employee time and use of mechanical equipment. The structured operation is promoted, the structured level of the operation is promoted by the unified and automatic processing flow, and the confusion and uncertainty in the operation are reduced. In a word, the technical scheme ensures that warehouse operation is more efficient and systematic by intelligently optimizing the order processing sequence, thereby remarkably improving the processing speed and the customer service quality and realizing higher operation efficiency and lower error rate; calculating a current time interval using the provided formula, wherein Tb is the lowest base time interval that the system should maintain when the order quantity is minimal, the parameter α controls the effect of the order quantity (N) on the interval, and β controls the effect of the average cargo quantity (M); ordering orders within this time interval from less to more according to the items of the load location information to generate a shipping order that minimizes the average shipping time in the event that the AGV cart resource is limited and cannot immediately respond to the user's request for order placement, significantly reducing the average shipping time of orders by ordering orders within this time interval from less to more according to the items of the load location information, since less of the load information is preferentially processed, they leave the system faster, resulting in a reduction in the number of orders waiting to be shipped and the average shipping time for all orders; the shorter operation can process more operations in unit time due to the fact that the operation is completed quickly, and therefore the throughput of the system can be improved; Reducing the cumulative delay of orders, the early completion of orders means that tasks that subsequently rely on those orders can begin early, shortening the cumulative delay in the order flow; improving the user experience, a system that sees a fast response would have a better experience for the user, which is especially important for applications that require interactive responses.

It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.

Claims

1. A logistics warehouse management method, characterized in that the method comprises:

The method for acquiring the historical inventory information, predicting the demand inventory according to the historical inventory information, acquiring a re-ordering point according to the predicted demand inventory, and sending alarm information to a manager to remind the manager of ordering when the actual inventory reaches or falls below the re-ordering point comprises the following steps:

the predicting future inventory requirements by seasonal ARIMA includes:

dividing the historical data into a training set and a verification set;

training an initial demand prediction model using training set data;

predicting the verification set data by using the initial demand prediction model, and modifying the initial demand prediction model according to a prediction result to obtain a demand prediction model;

inputting current inventory information into the demand prediction model to obtain predicted inventory demand quantity D _j;

calculating a reorder point according to the predicted inventory requirement number, wherein the reorder point calculation model is as follows:

when the stock quantity of the goods reaches or is lower than the re-ordering point, sending alarm information to a manager to remind the manager of ordering the goods;

The method for acquiring information of different cargoes browsed, added into shopping carts and purchased, acquiring the association degree of the cargoes according to the information, and distributing cargo positions with large association degree with the cargoes with high sales according to the association degree of the cargoes comprises the following steps:

Different cargoes in the logistics warehouse are browsed, added into shopping carts and purchased information, the correlation degree of the cargoes is calculated through a correlation degree model of the cargoes,

The cargo association degree model is as follows:

sorting the predicted sales amount of the cargoes arranged at the front 50% from high to low, sorting the association degree of the cargoes arranged at the back 50% with the cargoes arranged at the front 50% with the predicted sales amount, obtaining the cargoes arranged at the back 50% with the largest association degree with the cargoes arranged at the front 50%, distributing the cargoes to the idle cargoes closest to the cargoes arranged at the front 50%, and when the cargoes with the largest association degree are distributed with the cargoes, obtaining the cargoes with the largest association degree without the distributed cargoes, and distributing the cargoes closest to the cargoes in the cargoes arranged at the front 50%;

2. The logistics storage management method of claim 1, wherein after ordering, obtaining a warehouse entry order of a logistics storage warehouse of daily necessities, predicting sales conditions of goods of the warehouse entry order, and distributing goods positions for the goods according to the predicted sales conditions of the goods, comprising:

Sorting goods in a descending order according to the predicted sales volume;

3. The logistic warehouse management method according to claim 1, wherein determining the order of shipment according to the order picking time at a preset time interval when shipment of the goods, comprises:

4. A logistics warehouse management system, the system comprising:

Wherein the order module comprises:

the prediction module is used for sorting and cleaning the acquired information and predicting future inventory requirements through seasonal ARIMA;

the predicting future inventory requirements by seasonal ARIMA includes:

dividing the historical data into a training set and a verification set;

training an initial demand prediction model using training set data;

Inputting current inventory information into the demand prediction model to obtain predicted inventory demand quantity Dj;

The reminding ordering module is used for sending alarm information to the manager to remind the manager of ordering when the stock quantity of the goods reaches or is lower than the re-ordering point;

wherein, the association allocation cargo space module comprises:

the module for calculating the relevancy of the goods is used for acquiring information that different goods in the logistics warehouse are browsed, added into the shopping cart and purchased, calculating the relevancy of the goods through the relevancy model of the goods,

The cargo association degree model is as follows:

The sorting and distributing cargo space module is used for sorting the predicted sales volume of the cargoes which are arranged at the front 50% from high to low, sorting the cargoes which are arranged at the back 50% and the association degree of the cargoes which are arranged at the front 50% according to the predicted sales volume, obtaining the cargoes which are arranged at the back 50% and have the largest association degree with the cargoes which are arranged at the front 50%, distributing the cargoes to the idle cargo space which is closest to the cargoes which are arranged at the front 50%, and obtaining the cargoes which are not distributed with the largest association degree and have the closest association degree with the cargoes which are arranged at the front 50% when the cargoes which have the largest association degree are distributed with the cargoes;

5. The logistics warehouse management system of claim 4, wherein the sales allocation site module comprises:

6. The logistics warehouse management system of claim 4, wherein the ex-warehouse module comprises: