CN120725571A - Warehouse configuration method and its device, equipment and medium - Google Patents

Abstract

The present application relates to a warehouse configuration method and its device, equipment, and medium in the field of e-commerce technology, the method comprising: monitoring the current inventory of goods in each inventory node in a warehouse service cluster, and predicting the expected total outbound shipment of the goods corresponding to each inventory node within an expected time period in the future; judging whether the current inventory of goods in each inventory node meets the expected total outbound shipment, if so, determining it as an allocable node and determining its corresponding allocable inventory, otherwise determining it as a node to be replenished and determining its corresponding inventory to be replenished; for the inventory to be replenished of the node to be replenished, formulating an allocation plan based on each allocable node and its corresponding allocable inventory, and formulating a procurement plan based on the pre-allocated supply source corresponding to the node to be replenished; selecting one of the allocation plan and the procurement plan as a replenishment plan, and executing the replenishment plan to replenish the inventory to be replenished within an expected time period in the future. The present application provides an automated and robust commodity supply service.

Description

Warehouse configuration method and device, equipment and medium thereof

Technical Field

The present application relates to the field of electronic commerce technologies, and in particular, to a warehouse configuration method, and a corresponding apparatus, computer device, and computer readable storage medium thereof.

Background

With the rapid development of electronic commerce and supply chain management, the intelligent demand for warehouse resource allocation is increasingly urgent. The traditional warehouse management is dependent on manual experience or a semi-automatic system, and has the defects of lag in updating inventory information, insufficient dynamic adjustment capability and the like. For example, past inventory management has focused on simple recording and monitoring of current inventory amounts, and lacks the ability to accurately predict future out-of-stock trends, which makes warehouse backlashes often passive in the face of sudden order peaks or market demand fluctuations, and makes it impossible to adjust inventory strategies in time. When the inventory is insufficient among the inventory nodes, the inventory can not be quickly and scientifically determined from which nodes and the specific allocation quantity can not be easily and scientifically allocated, so that the time and the precision of the planning of the replenishment plan are not enough, and the efficiency and the benefit of the whole warehouse operation are affected. Meanwhile, for nodes needing to purchase and restock, the traditional purchasing plan also lacks effective comparison and trade-off with other inventory allocation schemes, and the restock cost and time are difficult to optimize on the whole, so that the flexibility and competitiveness of the warehousing service are limited to a certain extent.

In view of the shortcomings of the conventional technology, the inventor conducts research in the related field for a long time, and develops a new way for solving the problem in the field of electronic commerce.

Disclosure of Invention

It is therefore a primary objective of the present application to solve at least one of the above problems and provide a warehouse configuration method, and a corresponding apparatus, computer device, and computer program product.

In order to meet the purposes of the application, the application adopts the following technical scheme:

one of the objects of the present application is to provide a warehouse allocation method, comprising the following steps:

Monitoring the current inventory quantity of the commodity in each inventory node in the warehouse service cluster, and predicting the expected inventory total quantity of the commodity corresponding to each inventory node in the future expected duration;

Judging whether the current stock quantity of the commodity in each stock node meets the expected total quantity of the stock delivery, if yes, determining the commodity to be supplemented as an adjustable node and determining the corresponding adjustable stock quantity, otherwise, determining the commodity to be supplemented as a node to be supplemented and determining the corresponding stock quantity to be supplemented;

Aiming at the stock quantity to be supplemented of the nodes to be supplemented, setting an allocation plan based on each adjustable node and the corresponding adjustable stock quantity thereof, and setting a purchasing plan based on a pre-allocation supply source corresponding to the nodes to be supplemented;

And preferably, one of the allocation plan and the purchase plan is used as a replenishment plan, and the replenishment plan is executed to replenish the stock quantity of the node to be replenished within the expected future time period.

On the other hand, the warehouse configuration device provided by adapting to one of the purposes of the application comprises a monitoring prediction module, a replenishment judgment module, a plan determining module and an inventory replenishment module, wherein the monitoring prediction module is used for monitoring the current inventory of commodities in all inventory nodes in a warehouse service cluster and predicting the corresponding expected total amount of the commodities in all inventory nodes in future expected time, the replenishment judgment module is used for judging whether the current inventory of the commodities in each inventory node meets the expected total amount of the commodities, if yes, the plan determining module is used for determining the current inventory of the commodities as an adjustable inventory node and determining the corresponding adjustable inventory of the commodities, otherwise, the plan determining module is used for determining the node to be replenished and determining the corresponding inventory to be replenished, and the plan determining module is used for setting a plan for the node to be replenished based on all the adjustable inventory nodes and the corresponding adjustable inventory to be replenished, setting a plan based on the corresponding pre-allocated supply source inventory of the nodes to be replenished, and the inventory replenishment module is used for optimizing one of the plan to be taken as the purchase plan to be the expected total amount to be replenished in the future inventory nodes.

In yet another aspect, a computer device adapted to one of the objects of the present application comprises a central processor and a memory, said central processor being adapted to invoke the steps of running a computer program stored in said memory to perform the warehouse configuration method according to the present application.

In yet another aspect, a computer program product is provided adapted to another object of the application, comprising a computer program/instruction which, when executed by a processor, carries out the steps of the method described in any of the embodiments of the application.

The technical scheme of the application has various advantages, including but not limited to the following aspects:

The application monitors the current inventory quantity of commodities of each inventory node in real time and utilizes the prediction to obtain the expected inventory quantity in the future expected duration, so that the inventory management is not limited to the simple record and monitoring of the current inventory, but has the prospective, the inventory consumption trend of each node can be known in advance, thereby providing a powerful basis for the subsequent inventory strategy adjustment, and the warehouse can timely and actively take measures according to the pre-prediction and analysis when the peak of the sudden order or the market demand fluctuates, so as to avoid being in a passive situation.

Secondly, through the accurate comparison of the current stock quantity and the expected total quantity of the warehouse-out, each inventory node can be accurately divided into the categories of the adjustable stock or the to-be-restocked, and the corresponding adjustable stock quantity and to-be-restocked stock quantity are determined. Compared with the traditional mode that the allocation sources and the amount are difficult to quickly and accurately allocate when the inventory is insufficient, the efficiency and the accuracy of allocation decisions are greatly improved, the preparation of the replenishment plan is quicker and more reasonable, the overall efficiency of the warehousing operation is effectively improved, the time waste and the resource loss caused by untimely or unreasonable allocation of replenishment are reduced, and the benefit of the warehousing operation is further enhanced.

In addition, based on the allocation plan established by each adjustable node and the adjustable inventory quantity thereof, the optimization allocation of the internal inventory resources is fully considered, and the existing inventory resources can be utilized to the greatest extent. And taking a strategy of purchasing replenishment from the outside into consideration based on a purchasing plan formulated by a pre-configured supply source corresponding to the node to be replenished. By optimizing the two, the goods supplementing cost and time can be comprehensively weighed on the whole, the selected goods supplementing plan is ensured to be in most line with the cost benefit principle and time limit requirement, the goods supplementing cost can be optimized, goods supplementing can be completed in reserved goods supplementing time, the flexibility and competitiveness of the warehouse service are obviously improved, the intelligent requirements of electronic commerce and supply chain management on warehouse resource allocation in the rapid development process are better met, and powerful guarantee is provided for efficient and flexible development of warehouse operation.

Drawings

The foregoing and/or additional aspects and advantages of the application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:

FIG. 1 is a network architecture of an exemplary e-commerce platform of the present application;

FIG. 2 is a flow chart of an exemplary embodiment of a warehouse configuration method of the present application;

FIG. 3 is a schematic block diagram of a warehouse configuration device of the present application;

fig. 4 is a schematic structural diagram of a computer device according to the present application.

Detailed Description

Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative only and are not to be construed as limiting the application.

As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless expressly stated otherwise, as understood by those skilled in the art. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. The term "and/or" as used herein includes all or any element and all combination of one or more of the associated listed items.

It will be understood by those skilled in the art that all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs unless defined otherwise. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.

In the network architecture shown in fig. 1, the e-commerce platform 82 is deployed in the internet to provide corresponding services to its users, and the merchant user's device 80 and the consumer user's device 81 of the e-commerce platform 82 are similarly connected to the internet to use the services provided by the e-commerce platform.

The exemplary e-commerce platform 82 provides matching of supply and demand for products and/or services to the public by means of an internet infrastructure, in the e-commerce platform 82, the products and/or services are provided as merchandise information, and for simplicity of description, the concept of merchandise, products, etc. is used in the present application to refer to the products and/or services in the e-commerce platform 82, and specifically may be physical products, digital products, tickets, service subscriptions, other off-line fulfillment services, etc.

In reality, each entity of the parties can access the identity of the user to the e-commerce platform 82, and the purpose of participating in the business activity realized by the e-commerce platform 82 is realized by using various online services provided by the e-commerce platform 82. These entities may be natural persons, legal persons, social organizations, etc. The e-commerce platform 82 corresponds to both merchant and consumer entities in commerce, and there are two broad categories of merchant users and consumer users, respectively. The online service can be used in the e-commerce platform 82 by the identity of the merchant user, while the online service can be used in the e-commerce platform 82 by the identity of the consumer, including the real or potential consumer, of the merchant user. In actual business activities, the same entity can perform activities on the identity of a merchant user and the identity of a consumer user, so that the user can flexibly understand the activities.

The infrastructure for deploying the e-commerce platform 82 mainly comprises a background architecture and front-end equipment, wherein the background architecture runs various online services through a service cluster, including middleware or front-end services facing a platform side, services facing a consumer, services facing a merchant and the like to enrich and perfect service functions of the services, and the front-end equipment mainly comprises terminal equipment used by a user as a client to access the e-commerce platform 82, including but not limited to various mobile terminals, personal computers, point-of-sale equipment and the like. For example, a merchant user can enter commodity information for his online store through his terminal device 80 or generate his commodity information by using an interface opened by the e-commerce platform, and a consumer user can access a webpage of the online store implemented by the e-commerce platform 82 through his terminal device 81, trigger a shopping process by a shopping key provided on the webpage, and invoke various online services provided by the e-commerce platform 82 in the shopping process, thereby achieving the purpose of ordering shopping.

In some embodiments, the e-commerce platform 82 may be implemented by a processing facility including a processor and memory that stores a set of instructions that, when executed, cause the e-commerce platform 82 to perform e-commerce and support functions in accordance with the present application. The processing facility may be part of a server, client, network infrastructure, mobile computing platform, cloud computing platform, fixed computing platform, or other computing platform, and provide electronic components of the merchant platform 82, merchant devices, payment gateways, application developers, marketing channels, transport providers, client devices, point-of-sale devices, and the like.

The e-commerce platform 82 may be implemented as online services such as cloud computing services, software as a service (SaaS), infrastructure as a service (IaaS), platform as a service (PaaS), desktop as a service (DaaS), hosted software as a service, mobile backend as a service (MBaaS), information technology management as a service (ITMaaS), and the like. In some embodiments, the various features of the e-commerce platform 82 may be implemented to be adapted to operate on a variety of platforms and operating systems, e.g., for an online store, the administrator user may enjoy the same or similar functionality, whether in the various embodiments iOS, android, homonyOS, web pages, etc.

The e-commerce platform 82 may implement its respective independent station for each merchant to run its respective online store, providing the merchant with a respective instance of the commerce management engine for the merchant to establish, maintain, and run one or more of its online stores in one or more independent stations. The business management engine instance can be used for content management, task automation and data management of one or more online stores, and various specific business processes of the online stores can be configured through interfaces or built-in components and the like to support the realization of business activities. The independent station is an infrastructure of the e-commerce platform 82 with cross-border service functionality, and merchants can maintain their online stores more centrally and autonomously based on the independent station. The stand-alone stations typically have merchant-specific domain names and memory space, with relative independence between the different stand-alone stations, and the e-commerce platform 82 may provide standardized or personalized technical support for a vast array of stand-alone stations, so that merchant users may customize their own adaptive commerce management engine instances and use such commerce management engine instances to maintain one or more online stores owned by them.

The online store may implement background configuration and maintenance by the merchant user logging in his business management engine instance with an administrator identity, which, in support of various online services provided by the infrastructure of the e-commerce platform 82, may configure various functions in his online store, consult various data, etc., e.g., the merchant user may manage various aspects of his online store, such as viewing recent activities of the online store, updating online store inventory, managing orders, recent access activities, total order activities, etc., the merchant user may also view more detailed information about businesses and visitors to the merchant's online store, such as displaying sales summaries of the merchant's overall business, specific sales and participation data of the active sales marketing channel, etc., by acquiring reports or metrics.

The e-commerce platform 82 may provide a communications facility and associated merchant interface for providing electronic communications and marketing, such as utilizing an electronic message aggregation facility to collect and analyze communications interactions between merchants, consumers, merchant devices, customer devices, point-of-sale devices, etc., to aggregate and analyze communications, such as for increasing the potential to provide product sales, etc. For example, a consumer may have problems with the product, which may create a dialogue between the consumer and the merchant (or an automated processor-based proxy on behalf of the merchant), where the communication facility is responsible for interacting and providing the merchant with an analysis of how to increase sales probabilities.

In some embodiments, an application program suitable for being installed to a terminal device may be provided to serve access requirements of different users, so that various users can access the e-commerce platform 82 in the terminal device through running the application program, for example, a merchant background module of an online store in the e-commerce platform 82, and in the process of implementing the business activity through the functions, the e-commerce platform 82 may implement various functions related to supporting implementation of the business activity as middleware or online service and open corresponding interfaces, and then implant a tool kit corresponding to the interface access function into the application program to implement function expansion and task implementation. The commerce management engine may include a series of basic functions and expose those functions through APIs to online service and/or application calls that use the corresponding functions by remotely calling the corresponding APIs.

Under the support of the various components of the commerce management engine instance, the e-commerce platform 82 may provide online shopping functionality, enabling merchants to establish contact with customers in a flexible and transparent manner, consumer users may purchase items online, create merchandise orders, provide delivery addresses for the items in the merchandise orders, and complete payment confirmation of the merchandise orders. The merchant may then review and fulfill or cancel the order.

The warehouse configuration method of the application can be programmed into a computer program product and deployed in a client or a server for operation, for example, in the exemplary application scenario of the application, the warehouse configuration method can be deployed in a server of an e-commerce customer service platform, so that the method can be executed by accessing an interface opened after the computer program product is operated, and performing man-machine interaction with a process of the computer program product through a graphical user interface.

Referring to fig. 2, in an exemplary embodiment of the warehouse configuration method of the present application, the method includes the following steps:

Step S1100, monitoring the current stock quantity of the commodity in each stock node in the storage service cluster, and predicting the expected total quantity of the commodity out of the stock node corresponding to the commodity in the expected future time length;

the server continuously monitors the current inventory quantity of commodities in all inventory nodes in the warehouse service cluster in real time, and acquires the latest inventory state of all nodes through a real-time data acquisition interface. Inventory nodes refer to warehouses or distribution centers distributed in different geographic locations, and each node independently maintains inventory data of its jurisdictional commodity. The server establishes long connection with each node database through the message middleware, and captures inventory change events by adopting a publish-subscribe mode, for example, when a warehouse finishes commodity ex-warehouse operation or commodity warehouse operation, the inventory update message is immediately pushed to the server. The current stock quantity takes the commodity unique identification code as an index, and is stored in the distributed cache according to the dimension of the warehouse, so that the data consistency under high concurrent access is ensured.

The future expected duration refers to a period of time from the current time to a future prediction, such as a future week, month or quarter, and the specific duration may be determined by one skilled in the art based on actual business requirements and/or prediction accuracy requirements. The expected total amount of inventory refers to the sum of the number of inventory items expected to be in inventory in a single inventory node for the expected duration of the future.

First, for each inventory node, a recent inventory sequence formed by the actual inventory records of the inventory node in the recent past (e.g., the past week or month) is analyzed. For products with complex sales fluctuation, a deep learning model such as LSTM (long short time memory network) is used for prediction to form a sequence to be corrected in future within expected duration.

Secondly, comprehensively considering sales environment influence factors possibly faced by the region where the inventory node is located in the prediction period. These factors include weather type (e.g., rain and snow), promotional event type, price fluctuation of competitors, holiday type, etc. In order to effectively model the influence of the factors on sales volume, the weather type, the promotion type and the holiday type are usually converted into structural data features by adopting technologies such as single-heat coding, and the price of the bid product is normalized to construct a feature sequence of the sales environment, wherein the feature sequence comprises characteristics of the sales environment corresponding to each day in the expected future time length, namely, a feature representation corresponding to each factor.

And finally, fusing the obtained sequence to be corrected with the sales environment characteristic sequence. And (3) weighting and adjusting the to-be-corrected ex-warehouse quantity and the environmental characteristics through weights provided by a pre-trained algorithm model (such as a random forest regression model), and calculating to obtain the daily expected ex-warehouse quantity which is more in line with market dynamics. And accumulating all expected ex-warehouse amounts to obtain the expected total ex-warehouse amount of the node in the target time period. Therefore, the inherent sales trend of the commodity is tightly combined with the external dynamic market environment, the accuracy of future demand prediction is remarkably improved, and a solid data base is provided for reasonable allocation of inventory resources.

Step 1200, judging whether the current stock quantity of the commodity in each stock node meets the expected total quantity of the stock, if yes, determining the commodity to be supplemented as an adjustable node and determining the corresponding adjustable stock quantity, otherwise, determining the commodity to be supplemented as a node and determining the corresponding stock quantity to be supplemented;

for each inventory node and its stored commodity, the calculated expected total inventory is compared with the inventory it is currently actually holding. Automatically classifying the nodes based on the comparison result:

If the current stock quantity of a certain node is greater than or equal to the expected total quantity of the warehouse, the certain node is classified as an adjustable node. The node's adjustable inventory is calculated as the difference of its current inventory minus the total expected inventory. This means that the node has an inventory margin, which can be used to support other nodes.

Otherwise, if the current stock quantity of a certain node is smaller than the expected total quantity of the warehouse-out, classifying the node as the node to be restocked. The stock quantity to be replenished of the node is calculated as the difference of the expected total stock quantity minus the current stock quantity. This identifies the risk that the node will have an inventory shortage in the future.

Therefore, by dynamically evaluating and classifying the inventory of all the nodes, specific nodes with resource surplus (adjustable) and resource shortage (to-be-restocked) in the cluster and inventory gaps or surplus thereof are clearly and rapidly distinguished, and a clear target and a quantitative basis are provided for the next step of formulating a precise inventory restocking strategy.

Step 1300, aiming at the stock quantity to be compensated of the nodes to be compensated, setting up an allocation plan based on each adjustable node and the corresponding adjustable stock quantity thereof, and setting up a purchase plan based on a pre-allocated supply source corresponding to the nodes to be compensated;

and (3) aiming at the to-be-restocked node and the to-be-restocked stock quantity thereof, which are identified as the to-be-restocked node, two sets of complementary restocking schemes are established in parallel to cope with the shortage demand, namely an internal allocation scheme and an external purchasing scheme.

And (3) setting an allocation plan, namely analyzing all the adjustable nodes and the adjustable inventory thereof. Meanwhile, feasible transportation scheme information between the nodes and the nodes to be restocked is collected. Each shipping scheme contains core parameters of shipping price quote (unit commodity shipping cost), shipping duration (time required from shipment to shipment), and minimum shipping volume (minimum commodity demand for a single shipment).

Based on the node relation and the transportation scheme information, a node transportation topological graph is constructed (nodes represent inventory points, and feasible transportation schemes represent connecting edges). By means of preset prescreening rules (for example, the required transportation duration does not exceed the expected future duration, the minimum shipping amount does not exceed the available amount of the adjustable node) and cost-first optimization strategies (such as a greedy algorithm for preferably selecting a low-price transportation scheme), a feasible adjustment path (possibly involving direct or multi-stage transit) from the adjustable node to the node to be restocked is searched in the topological graph. And finally determining the nodes involved in the allocation, the allocation amount, the allocation path, the estimated total allocation cost and the total time consumption born by the nodes, and forming a complete allocation plan.

And (3) making a purchase plan, namely utilizing the supplier resources (pre-configured supply sources) pre-configured by the nodes to be restocked. The supply scheme of each supplier for the commodity is inquired, and the supply scheme comprises supply quotation (including commodity cost, logistics fee and the like), supply duration (total time from ordering to warehousing) and minimum booking quantity (single purchase minimum quantity).

The suppliers are preferably favored, and the key constraints to be considered include that the supply time length is required to meet the aging requirement of the expected time length in the future, and that the minimum order quantity is not more than the stock quantity to be replenished. After the provider qualified by the coarse screening is respectively used as an alternative provider, the historical performance data (such as commodity loss rate and order timing rate) of the provider can be combined for grading and sorting, or reinforcement learning algorithms such as epsilon-greedy and the like are applied for intelligent selection, so that the target provider is determined. Based on the supply quotation, the supply duration and the stock quantity to be supplemented of the target supplier, the total purchase cost and the total time consumption are calculated, and a purchase plan is formed. Therefore, the internal inventory resource potential and the external supply chain capacity of the warehouse service cluster can be fully utilized, and efficient solution reserves with balanced cost and aging are provided for different resource shortage conditions.

Step S1400, selecting one of the allocation plan and the purchase plan as a replenishment plan, and executing the replenishment plan to replenish the stock quantity of the nodes to be replenished within the expected future time period.

After the two sets of candidate schemes of allocation and purchase are generated, the optimal scheme needs to be evaluated and selected for execution, execution progress is monitored in the whole process, and the completion of the replenishment of the inventory of the nodes to be replenished within the expected time length in the future is ensured.

Firstly, two key indexes of an allocation plan and a purchase plan are respectively evaluated, namely the estimated total implementation cost and the risk probability of delay in the execution process (obtained by applying pre-trained deep learning risk assessment model analysis plan details). And comprehensively considering the cost and the risk, and calculating the recommended execution score of each plan in a weighted scoring mode. And selecting the plan with the highest recommended execution score as the finally implemented replenishment plan.

Next, the selected replenishment program is disassembled into key milestone events (e.g., pick up approval, shipment of goods, in-transit monitoring, in-transit verification) that must be completed sequentially, and an event execution sequence is established accordingly, with an expected completion time point (completion time sequence) being set for each event in the sequence. In the process of planning execution, each time a predetermined event completion time point is reached, the progress states of all events to be completed (constituting an event sub-sequence) before the time point are automatically checked. And (3) evaluating the actual completion condition of the subsequence in real time, and combining historical data and real-time information (such as abnormal weather, traffic interruption and the like), and predicting the risk of delay of the follow-up event occurrence plan by applying an algorithm model. And immediately calculating the remaining available replenishment time (future remaining duration) according to the consumed time and updating the original future expected duration to the future remaining duration once the plan delay risk is judged to exceed the preset warning threshold. The triggering process is then restarted, starting again from the first step of the exemplary embodiment, and based on the latest inventory status and market environment, re-planning and executing the optimal restocking scheme to ensure that the inventory restocking objectives of the nodes to be restocked are eventually completed on time. Therefore, an execution guarantee mechanism integrating optimization, fine process monitoring and intelligent dynamic adjustment is realized, uncertainty of a supply chain environment is effectively overcome, delay and cost risks are reduced to the greatest extent, and high reliability and timeliness of inventory replenishment tasks in complex and changeable environments are ensured.

It will be appreciated from the above embodiments that the present application has various advantages over the prior art, including at least:

The application monitors the current inventory quantity of commodities of each inventory node in real time and utilizes the prediction to obtain the expected inventory quantity in the future expected duration, so that the inventory management is not limited to the simple record and monitoring of the current inventory, but has the prospective, the inventory consumption trend of each node can be known in advance, thereby providing a powerful basis for the subsequent inventory strategy adjustment, and the warehouse can timely and actively take measures according to the pre-prediction and analysis when the peak of the sudden order or the market demand fluctuates, so as to avoid being in a passive situation.

Secondly, through the accurate comparison of the current stock quantity and the expected total quantity of the warehouse-out, each inventory node can be accurately divided into the categories of the adjustable stock or the to-be-restocked, and the corresponding adjustable stock quantity and to-be-restocked stock quantity are determined. Compared with the traditional mode that the allocation sources and the amount are difficult to quickly and accurately allocate when the inventory is insufficient, the efficiency and the accuracy of allocation decisions are greatly improved, the preparation of the replenishment plan is quicker and more reasonable, the overall efficiency of the warehousing operation is effectively improved, the time waste and the resource loss caused by untimely or unreasonable allocation of replenishment are reduced, and the benefit of the warehousing operation is further enhanced.

In addition, based on the allocation plan established by each adjustable node and the adjustable inventory quantity thereof, the optimization allocation of the internal inventory resources is fully considered, and the existing inventory resources can be utilized to the greatest extent. And taking a strategy of purchasing replenishment from the outside into consideration based on a purchasing plan formulated by a pre-configured supply source corresponding to the node to be replenished. By optimizing the two, the goods supplementing cost and time can be comprehensively weighed on the whole, the selected goods supplementing plan is ensured to be in most line with the cost benefit principle and time limit requirement, the goods supplementing cost can be optimized, goods supplementing can be completed in reserved goods supplementing time, the flexibility and competitiveness of the warehouse service are obviously improved, the intelligent requirements of electronic commerce and supply chain management on warehouse resource allocation in the rapid development process are better met, and powerful guarantee is provided for efficient and flexible development of warehouse operation.

In a further embodiment, step S1100, predicting the expected total amount of the commodity to be delivered out corresponding to each inventory node in the future expected duration includes the following steps:

Step S1110, for each inventory node, estimating a to-be-corrected ex-warehouse sequence based on a recent ex-warehouse sequence corresponding to the commodity in the inventory node, wherein the to-be-corrected ex-warehouse sequence comprises daily to-be-corrected ex-warehouse quantity in a future expected duration, and the recent ex-warehouse sequence comprises daily actual ex-warehouse quantity in the recent duration;

The recent delivery sequence is a sequence formed by collecting the actual delivery of the commodity at the stock node every day in a period of time from the current moment to the past in a backward pushing way and arranging the commodity from the beginning to the end, and the sequence is used for reflecting the sales trend and fluctuation characteristics of the commodity in a short period. This period of time may be the past week, month or 90 days, and the specific duration may be determined by one skilled in the art based on actual business requirements and/or prediction accuracy requirements.

The prediction of the sequence to be corrected is a process of predicting daily delivery in the expected future time period by performing time sequence analysis on the recent delivery. In particular, various timing prediction methods may be employed. In one embodiment, for items whose daily sales trends are relatively smooth, such as for some daily items, there is no significant increase or decrease in sales over a period of time, nor is there a strong periodic fluctuation. Therefore, a moving average method is applied, the average value obtained by dividing the sum of the multi-day delivery volume before the day by the sum of the days is calculated for each future day after the current moment, the average value is estimated to be the delivery volume of the day, the delivery volume is used as the delivery volume to be corrected, and the delivery volumes are respectively used as the delivery volumes to be corrected and are arranged according to the time sequence order to form the delivery sequence to be corrected. The number of days in the calculation process herein may be set by those skilled in the art as desired, for example, 7 days or 3 days, etc. In another embodiment, for the commodity with relatively complex sales trend or frequent fluctuation, a deep learning algorithm is applied, specifically, a time sequence prediction model trained to a convergence state in advance is called, a near-term ex-warehouse sequence is taken as input, future daily ex-warehouse quantity after the current moment is output, and then the ex-warehouse quantity is respectively taken as the ex-warehouse quantity to be corrected, and the ex-warehouse sequence to be corrected is formed by arranging according to the time sequence. The time sequence prediction model may be LSTM (long and short time memory network), ARIMA (differential integration moving average autoregressive model), AR (autoregressive model), MA (moving average model), ARMA model (autoregressive moving average model), or the like. One skilled in the art can flexibly adapt the training of the time series prediction model based on the model reasoning results disclosed herein.

In a further embodiment, after the above sequence to be corrected is obtained, the sequence may be corrected according to the lowest prediction threshold and the highest prediction threshold, so that the highest amount of the sequence to be corrected must not exceed the highest prediction threshold, and the lowest amount must not exceed the lowest threshold. The lowest predictive threshold and the highest predictive threshold may be obtained by statistically analyzing a plurality of years of outbound records of the item in the inventory node.

Step S1120, correcting the to-be-corrected ex-warehouse sequence based on the environment characteristic sequence corresponding to the commodity to obtain an expected ex-warehouse sequence, wherein the environment characteristic sequence comprises the daily sales environment characteristics in the expected future time length;

The sales environment characteristics comprise characteristic representations of the commodity in the region where the inventory node is located, wherein the characteristic representations correspond to the weather type, the promotion type, the bid price and the holiday type of the current day, the corresponding types of text description are converted into corresponding vector representations by adopting single-hot codes for the characteristic representations of the weather type, the promotion type and the holiday type, and the bid price is converted into corresponding numerical representations by adopting a normalization algorithm for the characteristic representations of the bid price. It will be appreciated that if no promotional event is held on the day and not a holiday, then the corresponding promotional type, holiday type, and holiday type of characteristic representations are each represented as vectors of all zeros.

It can be understood that, for the daily to-be-corrected delivery amount in the to-be-corrected delivery sequence, the sales environment features of the day in the environment feature sequence are taken out, and the expected delivery amount of the day is obtained by carrying out weighted fusion on the to-be-corrected delivery amount and the sales environment features, and an exemplary formula is as follows:

Wherein, the For the expected volume of delivery of the day,The amount to be corrected for the day is Trend, price, weather, holiday of the promotion type, bid price, weather type, holiday type. Alpha ₁,α₂,α₃,α₄,α₅ is the weight of the corresponding term, which is provided by a random forest regression model trained in advance to a converged state, and one skilled in the art can flexibly implement training of the model based on the model reasoning results disclosed herein.

And step S1130, accumulating all expected ex-warehouse quantities in the expected ex-warehouse sequence to obtain the expected ex-warehouse total quantity.

And calculating the sum of all expected warehouse-out amounts in the expected warehouse-out sequence, and taking the calculated sum value as the expected warehouse-out total amount.

In the embodiment, the to-be-corrected ex-warehouse sequence is deduced from the recent ex-warehouse sequence, and is corrected based on the environment feature sequence corresponding to the commodity, so that the expected total ex-warehouse quantity is finally obtained, and the future ex-warehouse quantity of the commodity is predicted more accurately. In the process, the recent ex-warehouse trend of the commodity and various influencing factors of future sales environment, such as weather, sales promotion, price of the competitive commodity and the like, can be comprehensively considered, can effectively cope with different commodity characteristics and complex and changeable market environments, and provides reliable basis for subsequent warehouse configuration decisions, so that the inventory is more reasonably arranged, stock backlog or backlog risk caused by inaccurate prediction is reduced, and warehouse operation efficiency and economic benefit are improved.

In a further embodiment, step S1300, preparing an allocation plan based on each of the adjustable nodes and their corresponding adjustable inventory amounts, includes the steps of:

Step 1310, obtaining transportation information among different nodes in each adjustable node and the nodes to be restocked according to the commodity, wherein the transportation information comprises at least one set of transportation scheme, and the transportation scheme comprises a transportation quotation, a minimum shipping capacity and a transportation duration;

For commodities, transportation information between each adjustable node and each node to be restocked needs to be collected. In general, a transportation scheme with lower transportation quotation is transported between different nodes, and the transportation time length of the opposite transportation scheme is higher, for example, for a certain two nodes, an air transportation scheme is possible, the transportation quotation is relatively higher, but the transportation time length can be short, and commodity allocation can be completed in a short time, while the transportation quotation of a sea transportation scheme is low, but the transportation time length is longer. Meanwhile, the schemes such as railway transportation or highway transportation and the like can exist, and each scheme has different quotation and duration characteristics. The server may call an API provided by the third party carrier via a pre-configured physical interface or retrieve shipping information between nodes from a local shipping scheme database.

The shipping price quote refers to the shipping cost charged by the logistics carrier for unit goods, including base shipping cost, fuel additional cost, etc., the minimum shipping volume refers to the minimum commodity quantity requirement for a single shipment, and the shipping duration refers to the time required for shipping from one node to another node for receipt, including loading and unloading time, time in transit, transit waiting time, etc.

For the updating mechanism of the transportation information in the local transportation scheme database, an event-driven mode is adopted, and when a logistics service merchant adjusts the transportation price or opens a new route, the synchronous updating of the transportation information database of the logistics management system is triggered through a message queue.

Step S1320, according to the adjustable stock quantity of each adjustable node, the stock quantity to be compensated of the to-be-compensated node, and each transportation information, making an adjustment plan to complement the stock quantity to be compensated of the to-be-compensated node within the future expected duration.

In one embodiment, firstly, a node transportation topological graph is constructed, each adjustable node and a node to be restocked are respectively used as nodes in the graph, when a transportation scheme between the nodes is obtained, the transportation scheme is built into an edge between the two nodes, and each transportation scheme is correspondingly built into an edge.

And then, screening out the smallest single-side lifting capacity from all sides connected with the node to be replenished in the node transportation topological graph, wherein the smallest single-side lifting capacity is not more than the adjustable stock quantity of the adjustable nodes connected with the side, the transportation duration of the side is not more than the expected duration in the future, and if a plurality of sides exist between the corresponding adjustable nodes and the node to be replenished, selecting one side with the lowest transportation quotation as the target side, otherwise, directly taking the single side as the target side. So far, the adjustable nodes which meet the demand of the minimum delivery and the corresponding target edges are determined, the adjustable nodes are respectively used as direct nodes, on the basis, whether the sum of the adjustable inventory amounts of the direct nodes is smaller than the inventory amount to be supplemented is judged, if not, a greedy strategy with low delivery quotation priority is further adopted, the delivery amount of the delivery to the node to be supplemented is determined from the adjustable inventory amounts of each direct node, so that the stock amount to be supplemented is fully achieved, and of course, the delivery amount of each direct node must exceed the minimum delivery amount of the target edges of the node. Then, according to the transfer amount of each direct node and the transport quotation of the target edge of the direct node, calculating the transfer cost of each direct node, marking the transport time length of the target edge of each direct node as the transfer time of the node, calculating the sum of the transfer costs, the sum of the transfer time and the sum of the transfer amounts of all direct nodes, obtaining the corresponding transfer total cost, the transfer total time and the transfer total amount, recording the transfer amount, the transfer time of each direct node, If the sum of the adjustable stock quantity is smaller than the stock quantity to be supplemented, the difference quantity obtained by subtracting the sum of the adjustable stock quantity from the stock quantity to be supplemented is calculated, the adjustable stock quantity of the adjustable node connected with any direct node is screened out from all sides connected with the single side, the minimum transport quantity of the single side is not more than the minimum transport quantity of the adjustable node connected with the single side, the sum of the transport time length of the single side and the transport time length of the target side connected with the direct node of the single side is not more than the future expected time length, and further, if a plurality of sides are arranged between the corresponding adjustable node and the direct node, one side with the lowest transport price is selected as the target side, otherwise, the single side with the lowest transport price is directly taken as the target side. So far, the adjustable nodes are respectively used as differential compensating nodes, on the basis, whether the sum of the adjustable stock amounts of the differential compensating nodes is smaller than the differential amount is judged, if not, a greedy strategy with low traffic quotation priority is further adopted, the adjustment amount of the direct node is determined from the adjustable stock amounts of each differential compensating node, so that the differential amount is full, and of course, the adjustment amount of each differential compensating node must exceed the minimum lifting traffic amount of the target side of the node. And then, according to the transfer quantity of each differential node and the transport quotation of the target edge of the differential node, calculating the transfer cost of each differential node, marking the transport time length of the target edge of each differential node as the transfer time of the node, calculating the sum of the transfer costs of all differential nodes and direct nodes, the sum of the transfer time and the sum of the transfer quantities, obtaining the corresponding transfer total cost, the transfer total time and the transfer total quantity, and recording the transfer quantity, the transfer time and the transfer cost of each differential node and the direct node, and the transfer total cost, the transfer total time and the transfer total quantity to form a transfer plan.

Furthermore, for the case where the sum of the adjustable inventory amounts of these differential compensation nodes is less than the differential amount, determination of the final allocation plan may be flexibly accomplished by one skilled in the art in light of the above disclosure.

In this embodiment, when the allocation plan is formulated, the transportation information between each adjustable node and the node to be repaired, including key factors such as the transportation quotation, the minimum shipping capacity, the transportation time length, and the like, is fully considered, a node transportation topological graph is constructed, and the optimal allocation path and allocation amount are determined according to a series of screening and optimizing strategies. The method ensures the feasibility of the allocation plan, can timely complement the inventory of the nodes to be restocked in the expected time length in the future, also gives consideration to cost effectiveness, reduces the allocation total cost as much as possible through a greedy strategy with low transport quotation priority and other methods, realizes the efficient allocation of resources, improves the collaborative operation efficiency among the inventory nodes in the warehouse service cluster, and enhances the flexibility and the response speed of the whole warehouse management.

In a further embodiment, step S1300, of preparing a purchase plan based on the pre-configured supply source corresponding to the node to be restocked, includes the following steps:

Step S1301, obtaining supply information of each supplier in the pre-configured supply source to the commodity, where the supply information includes at least one set of supply scheme, and the supply scheme includes a supply quotation, a supply duration and a minimum booking quantity;

For commodities, supply sources pre-equipped for the nodes to be restocked need to be collected, which means that a set of suppliers establishing long-term cooperation relationship with the nodes to be restocked can be stored in a database of a supplier system, and each supplier corresponds to a unique supplier identifier. The provisioning information includes at least one set of provisioning schemes, each consisting of three core elements of a provisioning quote, a provisioning duration, and a minimum subscription amount.

The offer price refers to the price the provider charges for the unit commodity, including commodity cost price, tax, and logistic surcharge. The supply duration refers to the average total time from the ordering of the unit commodity to the delivery of the unit commodity to the node to be restocked, and comprises the production period, the stock time and the logistics transportation time. The minimum order quantity refers to the minimum commodity quantity requirement of a single purchase. The latest supply information is obtained in real time through a provider API interface or an EDI data exchange platform, and is stored in a database in a JSON format for quick retrieval.

And step S1302, making a purchase plan according to the stock quantity to be compensated of the node to be compensated and the supply information so as to complement the stock quantity to be compensated of the node to be compensated within the expected future time length.

In one embodiment, first, suppliers whose supply duration does not exceed the expected duration in the future are screened out from the supply source, and the timeliness of replenishment is ensured. For suppliers meeting the preset ageing requirements, further confirming whether the minimum booking quantity exceeds the stock quantity to be replenished or not, excluding the exceeding of the corresponding suppliers, and then taking the rest of suppliers as alternative suppliers respectively. In one embodiment, the supply information of each candidate provider is obtained from the database, including the loss rate and the time scheduling rate, and then, for each candidate provider, the loss rate, the time scheduling rate and the transport quotation corresponding to the candidate provider are calculated, multiplied by the weights of the candidate providers respectively, and then summed to obtain the supply score, and the candidate provider with the highest supply score is preferably selected as the target provider. In another embodiment, the target provider is preferred from the alternative providers using a reinforcement algorithm based on exploration and utilization balance, including but not limited to any one of an E-greedy algorithm, an upper confidence algorithm, a Topson sampling algorithm.

Calculating the total purchase cost according to the supply quotation and the inventory waiting for the target supplier, calculating the total purchase time according to the supply time and the inventory waiting for the target supplier, taking the inventory waiting for the replenishment as the supply quantity of the target supplier, recording the supply quantity of the target supplier, and forming a purchase plan.

In this embodiment, by acquiring the supply information of each supplier in the supply source, including the supply quotation, the supply duration and the minimum booking amount, a comprehensive and accurate data base is provided for the purchase plan formulation. When the purchasing plan is formulated, screening and optimizing are carried out according to the stock quantity to be supplemented and the supply information of the nodes to be supplemented, so that the feasibility and the high efficiency of the purchasing plan are ensured. Therefore, timeliness of replenishment can be effectively guaranteed, selection of suppliers is optimized, purchasing cost and time consumption are reduced, purchasing management efficiency and benefit of warehousing operation are improved, and stability and competitiveness of a warehousing service cluster in a supply chain are enhanced.

In a further embodiment, after the step S1300 of preparing an allocation plan based on each of the adjustable nodes and their corresponding adjustable inventory amounts, the method includes the steps of:

Step S2300, when the difference between the current stock quantity and the expected stock quantity of the commodity in the stock node meets a preset condition, determining the corresponding diapause stock quantity of the commodity in the stock node;

And calculating the difference obtained by subtracting the expected total inventory from the current inventory of the stock node. If the stock node participates in the allocation plan to provide the corresponding allocation quantity, and the difference quantity exceeds the preset threshold, the difference quantity is directly used as the diapause out-of-stock quantity, and if the stock node participates in the allocation plan to provide the corresponding allocation quantity, the difference value obtained by subtracting the allocation quantity from the difference quantity exceeds the preset threshold, the difference value is used as the diapause out-of-stock quantity. When the amount of diapause out of stock exceeds a preset threshold, a promotional program is formulated based on the amount of diapause out of stock in order to reduce the amount of diapause out of stock for the commodity in the stock node. The preset threshold may be set by those skilled in the art as required by the service.

And step S2310, a promotion plan is formulated based on the diapause sales volume.

For creating a promotion plan, in one embodiment, first, a plurality of historical promotion activities are recalled roughly from all the historical promotion activities held in the sales area corresponding to the stock node based on the exploration and balance-based reinforcement algorithm, and further, according to the promotion duration of each promotion activity and the total sales amount in the promotion duration, i.e. the sales amount sold more than usual due to the holding of the promotion activity, the promotion activities whose promotion duration is in the expected future duration and the total sales amount exceeds the amount of sales to be sold out are screened out as target promotion activities, and discount rates corresponding to the target promotion activities are determined, for example, the target promotion activities are purchased one by one, and then the discount rates are 50%. And then acquiring the price of the bid corresponding to the commodity, multiplying the price of the bid by the discount rate corresponding to the target sales promotion, and obtaining the sales promotion price of the commodity. And recording the sales promotion price of the commodity and forming a sales promotion plan by the target sales promotion.

In another embodiment, considering that the commodity is easier to sell in the sales area of the node to be restocked, firstly, the total amount of sales increase and the excessive sales promotion of the node to be restocked in the expected future time period are acquired, the sales promotion activity with the optimal sales promotion effect can be optimized from all the historical sales promotion activities held in the sales region corresponding to the node to be restocked as the excess sales promotion activity, so that the sales increase total corresponding to the excess sales promotion activity held in the expected future time period is quantized. And then, determining all inventory nodes with the stock out quantity in the warehouse service cluster, carrying out full split on the total increment amount by the inventory nodes with the low stock out quantity, determining a plurality of inventory nodes with lower corresponding values and the allocation quantity thereof, wherein the sum of the allocation quantities is smaller than or equal to the total increment amount, and further determining the sales promotion plan of the inventory nodes with the low stock out quantity to participate in the allocation plan. For easy understanding, the inventory nodes meeting the preset conditions and the corresponding stock quantity of the stock nodes after the stock nodes are sold are corresponding to { 120:66, 66:20:30 }, the total quantity of the stock nodes to be restocked in the expected future is corresponding to {200}, and the corresponding lower inventory nodes and the corresponding allocation quantities of the stock nodes are determined to be corresponding to { 16:66, 20:30 }.

In this embodiment, when the difference between the current inventory amount and the expected inventory amount of the commodity in the inventory node meets a preset condition, the diapause inventory amount is determined in time, and a targeted promotion plan is formulated accordingly. Therefore, the method is beneficial to actively coping with the problem of commodity diapause, avoids excessive stock backlog to occupy storage space and capital cost, stimulates market demands by reasonably determining sales promotion activities and sales promotion prices, quickens commodity turnover, improves the mobility of stock and the use efficiency of capital, is beneficial to maintaining commodity and market competitiveness sold as soon as possible, reduces commodity devaluation or diapause loss possibly caused by long-term diapause, further optimizes storage resource allocation, and improves the overall benefit of storage operation.

In a further embodiment, step S1400 of executing the restocking plan to restock the stock quantity of the restocking node within the future expected duration includes the steps of:

step S1410, constructing an event execution sequence for completing the replenishment in the future expected duration according to the replenishment plan, and a completion time sequence configured corresponding to each event in the sequence;

And when an event execution sequence required to be executed for completing replenishment in the future expected duration is constructed, decomposing the discretization operation units based on the replenishment plan and establishing a time sequence dependency relationship. The event execution sequence is composed of a plurality of events arranged according to the execution sequence, and each event corresponds to a key operation node in the replenishment flow, such as generating a pick-up order, confirming a carrier order, picking up and delivering the warehouse, tracking transportation in transit, checking and accepting the warehouse and the like. Each time node in the completion time sequence is strictly matched with the planned completion time of the corresponding event in the event execution sequence, and the time is generated by distributing the total time length of the replenishment to each operation link according to the conventional completion time of the event. For example, for a replenishment program selected as a transfer program, the event sequence may include initiating an application for a transfer warehouse audit (+1 hour), a logistics vehicle dispatch (+3 hours), a commodity shipment (+6 hours), a land transportation (+24 hours), a commodity warehouse (+30 hours), and a time node sequence corresponding to [1,3,6,24,30] hours

Step S1420, determining a completion progress of an event sub-sequence corresponding to the order of the completion time nodes in the event execution sequence each time a completion time node in the completion time sequence is reached, and evaluating a planned delay risk corresponding to the completion progress, wherein the event sub-sequence comprises an event corresponding to the completion time node in the event execution sequence and all the previous events;

And when the preset completion time node is reached, evaluating the event subsequence progress by comparing the planned state with the actual state. The event sub-sequence contains the current time node corresponding event and all events that should be completed before it, e.g. when a "land" node is detected, the sub-sequence contains all events from application to land. The completion progress quantification adopts double indexes of event completion rate and time consumption rate, wherein the event completion rate is the proportion of the number of successfully executed events to the total number of events in the subsequence, and the time consumption rate is the proportion of the current consumed time to the total time length of the subsequence plan. The planned delay risk is calculated by applying a delay probability model trained to a convergence state in advance, and input parameters comprise current completion progress, average delay time of historical similar events and external environment factors (such as weather early warning and traffic control). The delay risk assessment model can be realized by a logistic regression classifier, a random forest or a neural network, and the training can be flexibly performed by a person skilled in the art.

And step S1430, when the plan delay risk exceeds a preset threshold, determining the future residual duration in the future expected duration according to the current time node, resetting the future expected duration to be the future residual duration, and returning to the step of monitoring the current inventory quantity of the commodities in each inventory node in the inventory service cluster to start to be executed.

Triggering the early warning mechanism when the delay risk value exceeds a preset threshold value (such as 0.7). And after the early warning is triggered, dynamically adjusting future expected duration parameters. The future remaining time length calculation uses the original total time length minus the elapsed time, for example, a delay occurs after 15 days of the original 30-day plan execution, and the future expected time length is reset to 15 days. And then, re-executing the whole flow to re-formulate a new replenishment plan, and continuing incomplete replenishment to ensure timely completion of replenishment of the inventory to be replenished of the nodes to be replenished.

In this embodiment, during the process of executing the replenishment program, the event execution sequence and the corresponding completion time sequence required for completing replenishment within the expected time length in the future are constructed, so as to achieve the fine management and timing control of the replenishment flow. Meanwhile, each time the completion time node is reached, the completion progress of the event subsequence is evaluated, and the planned delay risk is evaluated in real time by combining a pre-trained risk evaluation model, once the delay risk exceeds a preset threshold, the response can be quickly made, the future expected duration can be dynamically adjusted, and the process is re-executed. The dynamic monitoring and adjusting mechanism greatly enhances the flexibility and reliability of the replenishment plan, effectively reduces the uncertainty in the replenishment process, ensures that the inventory of the nodes to be replenished can be replenished on time, ensures the continuity and stability of the warehousing service, and improves the customer satisfaction and the service quality of the warehousing operation.

In a further embodiment, step S1400, which is preferably one of the allocation plan and the purchase plan as a restocking plan, includes the steps of:

step S1401, evaluating the total cost of the replenishment and the plan delay risk of the allocation plan and the purchase plan respectively, and determining recommended execution scores corresponding to the plans;

The total cost of restocking of the allocation plan is the allocation total cost, and the total cost of restocking of the purchase plan is the purchase total cost. And (3) applying a risk assessment model trained to a convergence state in advance, taking an allocation plan and a purchase plan as input respectively, and reasoning out plan delay risks. The risk assessment model may be a deep learning model used for two classification tasks in the NLP field, and in the training process, the loss value between the predicted and inferred plan delay risk and the actually marked plan delay risk is reduced to be smaller than a preset threshold value, so that a convergence state is achieved, and the ability of accurately assessing the probability of generating the plan delay based on all contents in the plan is learned. Training of risk assessment models can be flexibly performed by those skilled in the art based on the disclosure herein.

For each plan, the total cost of restocking and the plan delay risk of the plan are multiplied by the weights of the plan and added to obtain a recommended execution score, and the weights can be set by a person skilled in the art according to requirements.

Step S1402, screening out the plan with the highest recommended execution score from the allocation plan and the purchase plan as a replenishment plan.

And selecting a plan with the highest recommended execution score from the allocation plan and the purchasing plan, and taking the plan as a replenishment plan so as to obtain the optimal replenishment effect.

In this embodiment, when screening the replenishment program, the total cost of replenishment and the delay risk of the allocation program and the purchase program are respectively evaluated, the recommended execution score corresponding to each program is calculated, and finally the optimal replenishment program is screened according to the score. The method comprehensively balances two key factors of cost and risk, avoids unilateral performance possibly brought by decision making according to the cost or the risk, ensures that the selected replenishment plan has more advantages in cost effectiveness and execution reliability, can better adapt to different business scenes and market conditions, improves the scientificity and rationality of storage configuration decisions, realizes the minimization of storage operation cost and the optimization of replenishment effect, and creates greater economic value and competitive advantage.

Referring to fig. 3, a warehouse allocation device provided by adapting to one of the purposes of the present application is a functional implementation of a warehouse allocation method of the present application, and the device on the other hand, adapting to one of the purposes of the present application, includes a monitoring prediction module 1100, a replenishment judgment module 1200, a plan determination module 1300, and an inventory replenishment module 1400, where the monitoring prediction module 1100 is configured to monitor a current inventory of goods in each inventory node in a warehouse service cluster, and predict an expected total amount of the goods in each inventory node corresponding to a future expected duration, the replenishment judgment module 1200 is configured to judge whether the current inventory of the goods in each inventory node meets the expected total amount, and if yes, determine an adjustable inventory node and determine a corresponding inventory to be replenished, and if no, determine a corresponding inventory to be replenished node, and determine a corresponding inventory to be replenished node, the plan determination module 1300 is configured to determine the inventory to be replenished node, based on the monitoring of each adjustable node and the corresponding inventory to the current inventory node, and predict the expected total amount of the goods in each inventory node corresponding to the future expected inventory node, and perform a purchase plan from the future inventory node as a preferred inventory replenishment plan.

In a further embodiment, the monitoring prediction module 1100 includes a sequence prediction submodule, configured to infer, for each inventory node, a to-be-corrected ex-warehouse sequence based on a recent ex-warehouse sequence corresponding to a commodity in the inventory node, where the to-be-corrected ex-warehouse sequence includes a to-be-corrected ex-warehouse amount per day in a future expected duration, and the recent ex-warehouse sequence includes an actual ex-warehouse amount per day in the future expected duration, a sequence correction submodule, configured to correct, for each inventory-warehouse-to-be-corrected sequence based on an environmental feature sequence corresponding to the commodity, to obtain an expected ex-warehouse sequence, where the environmental feature sequence includes a sales environmental feature per day in the future expected duration, and a total amount determination submodule, configured to accumulate each expected ex-warehouse amount in the expected ex-warehouse sequence to obtain an expected total amount of the expected ex-warehouse.

In a further embodiment, the plan determining module 1300 includes a transportation information obtaining sub-module configured to obtain, for the commodity, transportation information between each of the adjustable nodes and different nodes in the nodes to be restocked, where the transportation information includes at least one set of transportation schemes including a transportation offer, a minimum shipping capacity, and a transportation duration, and a first planning sub-module configured to make a plan for restocking the nodes to be restocked in the future expected duration according to an adjustable stock quantity of each of the adjustable nodes, a stock quantity to be restocked in the nodes to be restocked, and each of the transportation information.

In a further embodiment, the plan determining module 1300 includes a supply information obtaining sub-module configured to obtain supply information of the commodity by each supplier in the pre-configured supply source, where the supply information includes at least one set of supply schemes, and the supply schemes include a supply price, a supply duration, and a minimum order quantity, and a second plan making sub-module configured to make up a purchase plan according to a stock quantity to be filled of the node to be filled and each supply information, so as to fill the stock quantity to be filled of the node to be filled in the future expected duration.

In a further embodiment, the plan determining module 1300 further includes a delivery determining sub-module configured to determine a diapire delivery amount corresponding to the commodity in the inventory node when a difference between a current inventory amount of the commodity in the inventory node and an expected delivery total amount satisfies a preset condition, and a plan updating sub-module configured to formulate a promotion plan based on the diapire delivery amount.

In a further embodiment, the stock completion module 1400 includes a sequence determining sub-module configured to construct an event execution sequence to be executed for completing replenishment in the future expected duration according to a replenishment plan, and a completion time sequence configured for each event in the sequence, a node judging sub-module configured to determine a completion progress of an event sub-sequence corresponding to a sequence of completion time nodes in the event execution sequence each time a completion time node in the completion time sequence is reached, evaluate a plan delay risk corresponding to the completion progress, the event sub-sequence including an event corresponding to the completion time node in the event execution sequence and all events preceding the event, and a restocking sub-module configured to determine a future remaining duration in the future expected duration according to a current time node when the plan delay risk exceeds a preset threshold, reset the future expected duration to the future remaining duration, and return the step of current stock of the commodity in each stock node in the monitoring storage service cluster to begin execution.

In a further embodiment, the stock completion module 1400 includes a scoring evaluation sub-module configured to evaluate total cost of replenishment and risk of delay of the allocation plan and the purchase plan, respectively, and determine recommended execution scores corresponding to the respective plans, and a plan screening sub-module configured to screen a plan with the highest recommended execution score from the allocation plan and the purchase plan as a replenishment plan.

In order to solve the technical problems, the embodiment of the application also provides computer equipment. As shown in fig. 4, the internal structure of the computer device is schematically shown. The computer device includes a processor, a computer readable storage medium, a memory, and a network interface connected by a system bus. The computer readable storage medium of the computer device stores an operating system, a database and computer readable instructions, the database can store a control information sequence, and the computer readable instructions can enable the processor to realize a warehouse configuration method when the computer readable instructions are executed by the processor. The processor of the computer device is used to provide computing and control capabilities, supporting the operation of the entire computer device. The memory of the computer device may have stored therein computer readable instructions that, when executed by the processor, cause the processor to perform the warehouse configuration method of the present application. The network interface of the computer device is for communicating with a terminal connection. It will be appreciated by persons skilled in the art that the architecture shown in fig. 4 is merely a block diagram of some of the architecture relevant to the present inventive arrangements and is not limiting as to the computer device to which the present inventive arrangements are applicable, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.

The processor in this embodiment is configured to execute specific functions of each module and its sub-module in fig. 3, and the memory stores program codes and various data required for executing the above modules or sub-modules. The network interface is used for data transmission between the user terminal or the server. The memory in this embodiment stores the program codes and data required for executing all the modules/sub-modules in the warehouse configuration device of the present application, and the server can call the program codes and data of the server to execute the functions of all the sub-modules.

The present application also provides a storage medium storing computer readable instructions that, when executed by one or more processors, cause the one or more processors to perform the steps of the warehouse configuration method of any of the embodiments of the present application.

Those skilled in the art will appreciate that all or part of the processes implementing the methods of the above embodiments of the present application may be implemented by a computer program for instructing relevant hardware, where the computer program may be stored on a computer readable storage medium, where the program, when executed, may include processes implementing the embodiments of the methods described above. The storage medium may be a computer readable storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a random access Memory (Random Access Memory, RAM).

In summary, the present application provides an automated and robust commodity provision service.

Those of skill in the art will appreciate that the various operations, methods, steps in the flow, acts, schemes, and alternatives discussed in the present application may be alternated, altered, combined, or eliminated. Further, other steps, means, or steps in a process having various operations, methods, or procedures discussed herein may be alternated, altered, rearranged, disassembled, combined, or eliminated. Further, various operations, methods, steps, means, or arrangements of procedures found in the prior art with the open source of the present application may be alternated, altered, rearranged, split, combined, or eliminated.

The foregoing is only a partial embodiment of the present application, and it should be noted that it will be apparent to those skilled in the art that modifications and adaptations can be made without departing from the principles of the present application, and such modifications and adaptations are intended to be comprehended within the scope of the present application.

Claims (10)

1. The warehouse configuration method is characterized by comprising the following steps:

Monitoring the current inventory quantity of the commodity in each inventory node in the warehouse service cluster, and predicting the expected inventory total quantity of the commodity corresponding to each inventory node in the future expected duration;

Judging whether the current stock quantity of the commodity in each stock node meets the expected total quantity of the stock delivery, if yes, determining the commodity to be supplemented as an adjustable node and determining the corresponding adjustable stock quantity, otherwise, determining the commodity to be supplemented as a node to be supplemented and determining the corresponding stock quantity to be supplemented;

Aiming at the stock quantity to be supplemented of the nodes to be supplemented, setting an allocation plan based on each adjustable node and the corresponding adjustable stock quantity thereof, and setting a purchasing plan based on a pre-allocation supply source corresponding to the nodes to be supplemented;

And preferably, one of the allocation plan and the purchase plan is used as a replenishment plan, and the replenishment plan is executed to replenish the stock quantity of the node to be replenished within the expected future time period.

2. The warehouse allocation method as claimed in claim 1, wherein predicting the expected total amount of the commodity to be delivered to the warehouse at each of the inventory nodes for the expected future time period includes the steps of:

For each inventory node, estimating a to-be-corrected ex-warehouse sequence based on a recent ex-warehouse sequence corresponding to commodities in the inventory node, wherein the to-be-corrected ex-warehouse sequence comprises to-be-corrected ex-warehouse quantity per day in a future expected duration, and the recent ex-warehouse sequence comprises actual ex-warehouse quantity per day in the recent duration;

Correcting the to-be-corrected ex-warehouse sequence based on the environment characteristic sequence corresponding to the commodity to obtain an expected ex-warehouse sequence, wherein the environment characteristic sequence comprises the sales environment characteristics of each day in the future expected duration;

And accumulating each expected ex-warehouse quantity in the expected ex-warehouse sequence to obtain the expected total ex-warehouse quantity.

3. The warehouse allocation method as claimed in claim 1, wherein the scheduling of allocation based on each of the adjustable nodes and its corresponding adjustable inventory comprises the steps of:

For the commodity, acquiring transportation information between each adjustable node and different nodes in the nodes to be restocked, wherein the transportation information comprises at least one set of transportation scheme, and the transportation scheme comprises a transportation quotation, a minimum shipping capacity and a transportation duration;

And according to the adjustable stock quantity of each adjustable node, the stock quantity to be supplemented of the node to be supplemented and the transportation information, setting an adjustment plan so as to supplement the stock quantity to be supplemented of the node to be supplemented within the expected future time length.

4. The warehouse allocation method according to claim 1, wherein the step of making a purchase plan based on the pre-allocated supply sources corresponding to the nodes to be restocked comprises the steps of:

Obtaining supply information of each supplier in a pre-configured supply source for the commodity, wherein the supply information comprises at least one set of supply scheme, and the supply scheme comprises supply quotation, supply duration and minimum booking quantity;

and according to the stock quantity to be supplemented of the node to be supplemented and the supply information, making a purchase plan so as to supplement the stock quantity to be supplemented of the node to be supplemented within the expected future time.

5. The warehouse allocation method as claimed in claim 1, wherein after creating an allocation plan based on each of the adjustable nodes and its corresponding adjustable inventory, comprising the steps of:

When the difference between the current inventory quantity and the expected inventory quantity of the commodity in the inventory node meets a preset condition, determining the corresponding diapause inventory quantity of the commodity in the inventory node;

And making a promotion plan based on the diapause quantity.

6. The warehouse allocation method according to claim 1, wherein executing the restocking plan to restock the stock quantity of the node to be restocked for the future expected duration comprises the steps of:

constructing an event execution sequence which is needed to be executed for completing replenishment in the future expected duration according to a replenishment plan, and a completion time sequence which is configured corresponding to each event in the sequence;

Each time a completion time node in the completion time sequence is reached, determining the completion progress of an event sub-sequence corresponding to the order of the completion time nodes in the event execution sequence, and evaluating the plan delay risk corresponding to the completion progress, wherein the event sub-sequence comprises an event corresponding to the completion time node and all the events before the event corresponding to the completion time node in the event execution sequence;

And when the plan delay risk exceeds a preset threshold, determining the future residual duration in the future expected duration according to the current time node, resetting the future expected duration to the future residual duration, and returning to the current inventory of the commodities in all inventory nodes in the monitoring and warehousing service cluster to start execution.

7. The warehouse allocation method according to claim 1, wherein one of the allocation plan and the purchase plan is preferable as a restocking plan, comprising the steps of:

respectively evaluating the total cost of the replenishment and the plan delay risk of the allocation plan and the purchasing plan, and determining recommended execution scores corresponding to the plans;

And screening a plan with the highest recommended execution score from the allocation plan and the purchasing plan as a replenishment plan.

8. A warehouse deployment device, comprising:

The monitoring prediction module is used for monitoring the current inventory quantity of the commodity in each inventory node in the warehouse service cluster and predicting the expected total quantity of the commodity out of the warehouse corresponding to each inventory node in the future expected duration;

The replenishment judging module is used for judging whether the current stock quantity of the commodity in each stock node meets the expected total quantity of delivery, if yes, determining the commodity to be replenished as an adjustable node and determining the corresponding adjustable stock quantity, otherwise, determining the commodity to be replenished as a node and determining the corresponding stock quantity to be replenished;

The plan determining module is used for setting up an allocation plan based on each adjustable node and the corresponding adjustable stock quantity aiming at the stock quantity to be compensated of the node to be compensated, and setting up a purchase plan based on a pre-allocated supply source corresponding to the node to be compensated;

And the stock completing module is used for optimizing one of the allocation plan and the purchase plan as a replenishment plan, and executing the replenishment plan to complete the stock to be replenished of the nodes to be replenished within the expected future time.

9. A computer device comprising a central processor and a memory, characterized in that the central processor is arranged to invoke a computer program stored in the memory for performing the steps of the method according to any of claims 1 to 7.

10. A computer-readable storage medium, characterized in that it stores in the form of computer-readable instructions a computer program implemented according to the method of any one of claims 1 to 7, which, when invoked by a computer, performs the steps comprised by the corresponding method.