CN113537850A - Storage optimization method and device, computer equipment and storage medium - Google Patents
Storage optimization method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN113537850A CN113537850A CN202010288397.4A CN202010288397A CN113537850A CN 113537850 A CN113537850 A CN 113537850A CN 202010288397 A CN202010288397 A CN 202010288397A CN 113537850 A CN113537850 A CN 113537850A
- Authority
- CN
- China
- Prior art keywords
- shipment
- warehouse
- long
- optimization
- stock
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000005457 optimization Methods 0.000 title claims abstract description 164
- 238000000034 method Methods 0.000 title claims abstract description 78
- 238000003860 storage Methods 0.000 title claims abstract description 72
- 238000004458 analytical method Methods 0.000 claims abstract description 8
- 238000012549 training Methods 0.000 claims description 41
- 238000012545 processing Methods 0.000 claims description 38
- 238000006243 chemical reaction Methods 0.000 claims description 27
- 238000004140 cleaning Methods 0.000 claims description 24
- 238000004590 computer program Methods 0.000 claims description 23
- 238000012216 screening Methods 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 8
- 238000009826 distribution Methods 0.000 claims description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000004519 manufacturing process Methods 0.000 description 6
- 238000012384 transportation and delivery Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 238000003066 decision tree Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
Abstract
The application relates to a storage optimization method, a storage optimization device, computer equipment and a storage medium. The method comprises the steps of obtaining a warehousing optimization request; searching historical shipment records of each warehouse storage in the warehouse corresponding to the warehousing optimization request, and acquiring shipment characteristic data corresponding to the historical shipment records; determining a long-tail stock in the stock according to the historical shipment records; acquiring a first shipment expected result according to shipment characteristic data corresponding to the long-tail stock; and performing warehousing optimization on the long-tailed warehouse inventory in the warehouse corresponding to the warehousing optimization request according to the first shipment expected result. This application confirms the long-tailed stock in the stock article through the historical shipment record in warehouse, then carries out special analysis to the long-tailed stock article to carry out the storage optimization with this, can carry out effective management to the stock article in the warehouse, more effectively with storage setting and shipment demand phase-match.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a storage optimization method and apparatus, a computer device, and a storage medium.
Background
With the development of industrial internet technology, C2M (Customer-to-Manufacturer) technology appeared, and C2M is a new business model of industrial internet e-commerce, also called "short-circuit economy". C2M specifically refers to the reverse mode of production in modern manufacturing driven by the user. The C2M mode is based on the Internet, big data and artificial intelligence, and an industrial customization mode for finally producing personalized products by using a huge computer system to exchange data at any time through the automation, customization, energy conservation and flexibility of a production line, setting suppliers and production procedures according to the requirements of product orders of customers and finally producing personalized products. The spread of C2M has led to changes in OTD (Order On-time delivery rate) and production methods, with large fluctuations and short-cycle orders becoming constant. And some long periods, small freight volume and large resource occupation quantity of various commodities (such as some high-value automobile after-sales parts).
In the conventional technology, historical sales data of the commodities are generally summarized, and then future sales of the commodities are predicted through a historical mean method, so that warehousing setting of a local warehouse is performed.
However, the existing method for setting the warehouse by the historical mean method is not suitable for long-tail warehouse products with small shipment volume, and the warehouse products in the warehouse cannot be effectively managed.
Disclosure of Invention
In view of the above, there is a need to provide a warehouse optimization method, apparatus, computer device and storage medium capable of more effectively managing the warehouse inventory in the warehouse.
A method of storage optimization, the method comprising:
acquiring a storage optimization request;
searching historical shipment records of each warehouse storage in the warehouse corresponding to the warehousing optimization request, and acquiring shipment characteristic data corresponding to the historical shipment records;
determining a long-tail stock in the stock according to the historical shipment records;
acquiring a first shipment expected result according to shipment characteristic data corresponding to the long-tail stock;
and performing warehousing optimization on the long-tailed warehouse inventory in the warehouse corresponding to the warehousing optimization request according to the first shipment expected result.
In one embodiment, after determining the long-tail stock in the stock according to the historical shipment records, the method further includes: analyzing shipment characteristic data corresponding to the stock products except the long-tail stock product by combining a weighted sliding average method with LGB prediction to obtain a second shipment expected result; and performing warehousing optimization on the warehouse storage except the long-tail warehouse storage in the warehouse corresponding to the warehousing optimization request according to the second shipment expected result.
In one embodiment, the searching for the historical shipment records of the inventory items in the warehouse corresponding to the warehouse optimization request, and the obtaining the shipment characteristic data corresponding to the historical shipment records includes: searching historical shipment records of each warehouse storage in the warehouse corresponding to the warehouse optimization request; carrying out data cleaning and data conversion processing on the shipment data in the historical shipment records; and carrying out characteristic engineering processing on the shipment data subjected to the data cleaning and data conversion processing to obtain shipment characteristic data.
In one embodiment, the performing feature engineering processing on the data cleaning and data conversion processing to obtain shipment feature data includes: carrying out characteristic engineering processing on the data cleaning and data conversion processing to obtain engineering characteristic data; and carrying out characteristic screening on the engineering characteristic data through the time sequence stability to obtain shipment characteristic data.
In one embodiment, before analyzing the shipment characteristic data corresponding to the stock other than the long-tailed stock by combining the weighted moving average method with LGB prediction to obtain a second shipment expected result, the method further includes:
Acquiring shipment record training data;
extracting shipment characteristic data corresponding to the shipment record training data;
taking shipment characteristic data corresponding to the shipment record training data as training parameters, taking the average absolute percentage error of a second shipment expected result as a model optimization target parameter, training an initial prediction model through Bayesian optimization parameter search, and obtaining a shipment quantity prediction model, wherein the initial prediction model is constructed based on a weighted sliding average method and LGB prediction;
the analyzing the shipment characteristic data corresponding to the stock products except the long-tail stock product by combining a weighted moving average method with LGB prediction to obtain a second shipment expected result comprises the following steps: and inputting the shipment characteristic data corresponding to the stock products except the long-tail stock product into the shipment quantity prediction model to obtain a second shipment expected result.
In one embodiment, the obtaining a first shipment expected result according to the shipment characteristic data corresponding to the long-tailed stock item includes: when the shipment data corresponding to the long-tail stock is lower than or equal to a preset shipment threshold, acquiring the stock type corresponding to the long-tail stock, and acquiring a first shipment expected result corresponding to the long-tail stock according to the stock type; when the shipment data corresponding to the long-tail stock is higher than a preset shipment threshold, obtaining a smooth average value of the shipment corresponding to the long-tail stock, and obtaining a first shipment expected result corresponding to the long-tail stock according to Poisson distribution corresponding to the smooth average value.
A storage optimization device, the device comprising:
the request acquisition module is used for acquiring a warehousing optimization request;
the characteristic data acquisition module is used for searching the historical shipment records of the warehouse stocks in the warehouse corresponding to the warehouse optimization request and acquiring the shipment characteristic data corresponding to the historical shipment records;
the long-tail screening module is used for determining long-tail stock in the stock according to the historical shipment records;
the first analysis module is used for acquiring a first expected shipment result according to shipment characteristic data corresponding to the long-tailed stock;
and the first optimization module is used for carrying out warehousing optimization on the long-tailed warehouse inventory in the warehouse corresponding to the warehousing optimization request according to the first shipment expected result.
In one embodiment, the system further comprises a second optimization module, configured to: analyzing shipment characteristic data corresponding to the stock products except the long-tail stock product by combining a weighted moving average method with LGB (LightGBM) prediction to obtain a second shipment expected result; and performing warehousing optimization on the warehouse storage except the long-tail warehouse storage in the warehouse corresponding to the warehousing optimization request according to the second shipment expected result.
A computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
acquiring a storage optimization request;
searching historical shipment records of each warehouse storage in the warehouse corresponding to the warehousing optimization request, and acquiring shipment characteristic data corresponding to the historical shipment records;
determining a long-tail stock in the stock according to the historical shipment records;
acquiring a first shipment expected result according to shipment characteristic data corresponding to the long-tail stock;
and performing warehousing optimization on the long-tailed warehouse inventory in the warehouse corresponding to the warehousing optimization request according to the first shipment expected result.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
acquiring a storage optimization request;
searching historical shipment records of each warehouse storage in the warehouse corresponding to the warehousing optimization request, and acquiring shipment characteristic data corresponding to the historical shipment records;
determining a long-tail stock in the stock according to the historical shipment records;
acquiring a first shipment expected result according to shipment characteristic data corresponding to the long-tail stock;
And performing warehousing optimization on the long-tailed warehouse inventory in the warehouse corresponding to the warehousing optimization request according to the first shipment expected result.
The storage optimization method, the storage optimization device, the computer equipment and the storage medium acquire a storage optimization request; searching historical shipment records of each warehouse storage in the warehouse corresponding to the warehousing optimization request, and acquiring shipment characteristic data corresponding to the historical shipment records; determining a long-tail stock in the stock according to the historical shipment records; acquiring a first shipment expected result according to shipment characteristic data corresponding to the long-tail stock; and performing warehousing optimization on the long-tailed warehouse inventory in the warehouse corresponding to the warehousing optimization request according to the first shipment expected result. According to the method and the system, the long-tail warehouse stocks in the warehouse stocks are determined through the historical shipment records of the warehouse, then the long-tail warehouse stocks are specially analyzed, the warehouse optimization is carried out according to the long-tail warehouse stocks, and the warehouse stocks in the warehouse can be effectively managed.
Drawings
FIG. 1 is a diagram of an exemplary embodiment of a warehouse optimization method;
FIG. 2 is a flow diagram illustrating a warehouse optimization method according to one embodiment;
FIG. 3 is a flow chart illustrating a warehousing optimization method according to another embodiment;
FIG. 4 is a schematic illustration of a sub-flow chart of step 203 of FIG. 3 in one embodiment;
FIG. 5 is a block diagram of a warehousing optimization device in one embodiment;
FIG. 6 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The warehousing optimization method provided by the application can be applied to the application environment shown in fig. 1. Wherein the terminal 102 communicates with the warehouse optimization server 104 via a network. When a user wants to optimize the warehouse storage structure of a certain warehouse, a warehouse optimization request can be sent to the warehouse optimization server 104 through the terminal 102, the warehouse optimization request carries the identity information corresponding to the warehouse, and the warehouse optimization server 104 acquires the warehouse optimization request from the terminal 102; searching historical shipment records of each warehouse storage corresponding to the warehouse optimization request, and acquiring shipment characteristic data corresponding to the historical shipment records; determining a long-tail stock in the stock according to the historical shipment records; analyzing shipment characteristic data corresponding to the stock of the long-tail stock through a preset long-tail shipment prediction algorithm to obtain a first shipment expected result; and performing warehousing optimization on the long tail warehouse inventory in the warehouse corresponding to the warehousing optimization request according to the first shipment expected result. The terminal 102 may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the warehousing optimization server 104 may be implemented by an independent server or a server cluster composed of a plurality of servers.
In one embodiment, as shown in fig. 2, a warehousing optimization method is provided, which is described by taking the example that the method is applied to the warehousing optimization server 104 in fig. 1, and includes the following steps:
And the warehousing optimization request carries target warehouse information corresponding to warehousing optimization. The target warehouse may specifically refer to a warehouse or a cluster of warehouses responsible for supplying inventory to the same region.
Specifically, the inventory of the inventory in the warehouse is closely related to the sales condition of the commodity at the location of the warehouse, and when a user wants to perform structural optimization on the inventory of the inventory in a certain warehouse to ensure that the inventory of the warehouse can conform to the actual delivery volume, the user can send a corresponding warehousing optimization request to the warehousing optimization server 104 through the terminal 102 to request the warehousing optimization server to perform quantitative analysis on each inventory in the target warehouse to ensure that the warehousing setting is matched with the delivery requirement. In one embodiment, the warehousing optimization request may further include a period setting of warehousing optimization, specifically including a long period, a medium period, and a short period, where in different optimization periods, a model used for optimizing warehousing of the warehouse, input data of the model, and an obtained optimization result are different.
Where inventory items may be sorted in the form of SKUs (Stock Keeping units), which are unique identifiers for each product and service, the use of the value of the SKU rooted in the data management enables companies to track inventory conditions of systems such as warehouses and retail stores or products. And the warehouse optimization request corresponding to the warehouse is the target warehouse for warehouse optimization, and if the warehouse goods in the warehouse are sold out, the warehouse goods can be taken out of the warehouse and transferred to the hand of the warehouse goods buyer. At this time, the warehouse will generate the corresponding warehouse inventory shipment record. And for the stock without the shipment record, the filling-in process can be directly carried out. The shipment characteristic data specifically includes shipment quantity, shipment time, destination location of shipment transportation, shipment frequency of different time periods in the history record, and the like.
Specifically, after receiving the warehousing optimization request, the warehousing optimization server 104 may parse the warehousing optimization request to determine the warehouse corresponding to the warehousing optimization request, and then directly search the inventory shipment record corresponding to the warehouse. In one embodiment, the shipment records correspond to the cycle setting direction of warehousing optimization, the time spans of the extracted shipment records are different for different cycles, and the time spans of the corresponding shipment records are longer for longer warehousing optimization cycles. When the historical shipment records of the inventory are obtained, in order to more effectively set the optimization of the warehousing, corresponding shipment characteristic data can be extracted from the historical shipment records, and the corresponding inventory optimization setting result is obtained through the analysis of the shipment characteristic data.
And step 205, determining the long-tail stock in the stock according to the historical shipment records.
The long-tail stock is stock with long-tail effect. From the perspective of human demand, most of the demand will be concentrated on the head, which is called a epidemic, while the demand distributed on the tail is personalized, scattered and small-amount demand. This part of the differentiated, small demand will form a long "tail" on the demand curve, which is the long tail. The long-tail stock generally has lower shipment volume and frequency. In one embodiment, the inventory of the warehouse may be specifically automobile after-sales parts, and for automobile after-sales parts of the same brand, skus in the warehouse may be as many as ten thousands, while most skus are delivered with a year delivery rate of less than 10 and a month delivery rate of less than 1, and these skus may be regarded as long-tail inventory.
Specifically, the warehousing optimization server 104 may determine which of the inventory items are long-tailed inventory items with lower shipment frequency and shipment volume according to the historical shipment records. And then, specially analyzing the long-tail stock, estimating the future shipment volume of the long-tail stock, and further optimizing the storage structure in the target warehouse.
And step 207, acquiring a first expected shipment result according to shipment characteristic data corresponding to the stock of the long-tail stock.
The first shipment expected result is specifically a result obtained by predicting future shipment conditions of each long-tailed stock in the warehouse according to the warehousing optimization request. If the shipment of inventory a in the next 1 month is expected to be 1, and the shipment of inventory B in the next month is expected to be 3.
Specifically, the warehousing optimization server may analyze the historical shipment records of the target warehouse to perform detailed analysis on future shipment conditions of the long-tail warehouse stocks in the target warehouse, so as to optimize the stock of each long-tail warehouse stock in the target warehouse.
And step 209, performing warehousing optimization on the long tail warehouse inventory in the warehouse corresponding to the warehousing optimization request according to the first shipment expected result.
Specifically, the first expected shipment result refers to the future shipment volume of each stock in the target warehouse, and the warehouse optimization of the long-tail stock in the warehouse corresponding to the warehouse optimization request is performed according to the first expected shipment result. Through the optimization of storage, can effectively reduce the volume of goods in transit, improve the production efficiency of long-tailed stock article factory then.
The warehousing optimization method comprises the steps of obtaining a warehousing optimization request; searching historical shipment records of each warehouse storage corresponding to the warehouse optimization request, and acquiring shipment characteristic data corresponding to the historical shipment records; determining a long-tail stock in the stock according to the historical shipment records; acquiring a first shipment expected result according to shipment characteristic data corresponding to the long-tail stock; and performing warehousing optimization on the long tail warehouse inventory in the warehouse corresponding to the warehousing optimization request according to the first shipment expected result. According to the method and the system, the long-tail warehouse stocks in the warehouse stocks are determined through the historical shipment records of the warehouse, then the long-tail warehouse stocks are specially analyzed, the warehouse optimization is carried out according to the long-tail warehouse stocks, and the warehouse stocks in the warehouse can be effectively managed.
In one embodiment, as shown in fig. 3, after step 209, the method further includes:
and step 302, analyzing shipment characteristic data corresponding to the stock products except the long-tail stock product by combining a weighted sliding average method with LGB prediction to obtain a second shipment expected result.
And step 304, performing warehousing optimization on the warehouse storage except the long-tail warehouse storage in the warehouse corresponding to the warehousing optimization request according to the second shipment expected result.
The weighted moving average method is to give different weights according to the influence degree of data in different time in the same moving segment on the predicted value, and then to carry out average moving to predict the future value. Unlike the simple moving average method, the weighted moving average method treats the data in the moving period equally when calculating the average value, but treats each data in the moving period differently according to the characteristic that the more recent data has a greater influence on the predicted value. More weight is given to the recent data and less weight is given to the distant data, thus making up for the deficiency of the simple moving average method. LGB prediction is performed through a LigthGBM, the LigthGBM is a new member in a boosting set model, the LigthGBM is an efficient implementation for GBDT like XGboost, in principle, the LigthGBM is similar to the XGboost, and negative gradients of loss functions are used as residual error approximate values of the current decision tree to fit the new decision tree. The LGB prediction in this application may be a rolling prediction algorithm set according to the expected time of the required shipment, in one embodiment, the LGB prediction may be rolled for 28 days, and the shipment volume of the inventory is estimated during this time.
In particular, since the inventory in the warehouse has a significant portion of non-long tail inventory in addition to long tail inventory, the expected shipment of this portion of inventory over a future period of time can be estimated by a weighted moving average method in combination with LGB prediction. In one embodiment, a prediction model may be constructed based on a weighted moving average method in combination with LGB prediction, and then the second shipment expected result may be predicted by inputting the obtained shipment characteristic data into the prediction model, which is implemented by combining a linear regression model with an LGB model and a prophet model. In this embodiment, the shipment characteristic data corresponding to the stock items other than the long-tailed stock item is analyzed to obtain the second shipment expected result, and then the stock items other than the long-tailed stock item in the warehouse are optimized, so that the stock structure of the stock items in the warehouse can be further optimized, and the warehousing setting can be more effectively matched with the shipment requirement.
As shown in FIG. 4, in one embodiment, step 203 comprises:
And step 403, performing data cleaning and data conversion processing on the shipment data in the historical shipment records.
And 405, performing characteristic engineering processing on the shipment data subjected to the data cleaning and data conversion processing to obtain shipment characteristic data.
The data cleaning specifically refers to removing invalid data in the historical shipment record data, for example, some data in the historical shipment record data are irrelevant to future shipment prediction and can be directly taken out through data cleaning. And the data conversion means that data conversion is performed on null values and meaningless data in the historical shipment data, when the stock in the warehouse contains a large number of long-tail stock, the shipment quantity of a certain stock in a certain period of time is possibly 0, and at this time, data conversion is performed, and the shipment data corresponding to the stock can be subjected to 0 filling processing. The feature engineering processing is to extract features included in the shipment data, and then the warehousing optimization server 104 can directly perform subsequent prediction according to the features. The feature engineering may specifically include processing procedures such as box-cox transformation, extraction of sliding window timing statistics, feature crossing, and the like.
Specifically, the warehousing optimization server 104 may directly obtain the historical shipment records of the inventory items in the warehouse corresponding to the user warehousing optimization request, perform corresponding data cleaning and data conversion processing on the shipment data in the historical shipment records to ensure the validity of the data, and further process the shipment data through the feature engineering to extract shipment feature data, which is included in the shipment features and can be used for future shipment prediction, of the inventory items. In the embodiment, the shipment characteristic data is obtained by processing the historical shipment records, such as data cleaning, data conversion, characteristic engineering and the like, and the effectiveness of the shipment characteristic data can be effectively ensured, so that the prediction accuracy of the subsequent shipment prediction process is improved.
In one embodiment, step 405 includes: carrying out characteristic engineering processing on the data cleaning and data conversion processing to obtain engineering characteristic data; and carrying out characteristic screening on the engineering characteristic data through the time sequence stability to obtain shipment characteristic data.
The time stability is that the fitted curve of the characteristics obtained by the sample time sequence is required to continue along the existing form inertially in a future period; if the data is not stable, the shape of the sample fitting curve does not have the characteristic of inertia continuation. And screening the engineering characteristic data based on the time sequence stability means that the engineering characteristic data with the time sequence stability is reserved and is used as the shipment characteristic data. In addition, the feature screening can be performed by a recursive feature elimination mode, or the importance of the obtained shipment features can be sorted by a method based on tree model splitting times and splitting gain sorting. In this embodiment, shipment characteristic data is obtained by processing such as feature screening, and the validity of shipment characteristic data used for shipment volume analysis can be effectively ensured, so that the prediction accuracy of the subsequent shipment prediction process is improved.
In one embodiment, before step 302, the method further includes: acquiring shipment record training data;
extracting shipment characteristic data corresponding to the shipment record training data; taking shipment characteristic data corresponding to shipment record training data as training parameters, taking the average absolute percentage error of the second shipment expected result as a model optimization target parameter, training an initial prediction model through Bayesian optimization parameter search, and obtaining a shipment quantity prediction model, wherein the initial prediction model is constructed based on a weighted sliding average method and LGB prediction; step 302 includes: and inputting the shipment characteristic data corresponding to the stock products except the long-tail stock product into a shipment quantity prediction model to obtain a second shipment expected result.
The shipment record training data may specifically be historical shipment data within a period of time before the current forecast date. For training the predictive model. This portion of the data still needs to be processed by data cleansing and data conversion. The training parameters may specifically include training set data, test set data, and verification set data, and specifically, the data after data cleaning and data conversion may be processed by a time-series hierarchical and random sampling method to obtain available training data, which is divided into training set data, test set data, and verification set data. After the training data are obtained, taking shipment characteristic data corresponding to the shipment record training data as training parameters, taking the average absolute percentage error of the second shipment expected result as a model optimization target parameter, and training the initial prediction model through Bayesian optimization parameter search to obtain a shipment quantity prediction model. And the initial prediction model is constructed based on a weighted moving average method combined with LGB prediction. When the second expected shipment result needs to be estimated, shipment characteristic data corresponding to the stock products except the long-tail stock product can be directly input into the shipment quantity prediction model, and the corresponding second expected shipment result can be directly obtained. In the embodiment, the historical shipment records corresponding to the warehouses
In one embodiment, the shipment characteristic data includes shipment volume data, and step 207 includes: when the shipment data corresponding to the long-tail stock is lower than or equal to a preset shipment threshold, acquiring the stock type corresponding to the long-tail stock, and acquiring a first shipment expected result corresponding to the long-tail stock according to the stock type; when the shipment data corresponding to the long-tail stock is higher than a preset shipment threshold, obtaining a smooth average value of the shipment corresponding to the long-tail stock, and obtaining a first shipment expected result corresponding to the long-tail stock according to Poisson distribution corresponding to the smooth average value.
The preset shipment threshold may be a very small value, such as 0 or 1, and when the shipment data corresponding to the long-tailed inventory is lower than or equal to the preset shipment threshold, it may be determined that the long-tailed sales data corresponding to the long-tailed inventory is too low, and at this time, the corresponding inventory index may be directly allocated to the long-tailed inventory according to the category of the long-tailed inventory. And when the shipment data corresponding to the long-tail stock is higher than the preset shipment threshold, the corresponding sales data can be determined to be further estimated, at this time, a smooth average value of the shipment quantity corresponding to the long-tail stock can be obtained, and a first shipment expected result corresponding to the long-tail stock is obtained according to the poisson distribution corresponding to the smooth average value. In another embodiment, the subsequent shipment estimation can be performed by SAA (Sample Average Approximation) method based on the shipment smooth Average. In the embodiment, according to the actual shipment condition of the long-tail stock, different shipment volume estimations are carried out on different types of long-tail stock, and the accuracy of the shipment volume estimation process can be effectively ensured.
It should be understood that although the various steps in the flow charts of fig. 2-4 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-4 may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed in turn or alternately with other steps or at least some of the other steps.
In one embodiment, as shown in fig. 5, there is provided a storage optimization apparatus, including: a request obtaining module 501, a feature data obtaining module 503, a long tail screening module 505, a first analyzing module 507 and a first optimizing module 509, wherein:
a request obtaining module 501, configured to obtain a warehousing optimization request.
The characteristic data obtaining module 503 is configured to search a historical shipment record of each inventory in the warehouse corresponding to the warehouse optimization request, and obtain shipment characteristic data corresponding to the historical shipment record.
And the long-tail screening module 505 is configured to determine a long-tail stock in the stock according to the historical shipment records.
And the first analysis module 507 is used for acquiring a first expected shipment result according to shipment characteristic data corresponding to the long-tailed stock.
The first optimizing module 509 is configured to perform warehousing optimization on the long-tailed warehouse inventory in the warehouse corresponding to the warehousing optimization request according to the first shipment expected result.
In one embodiment, the system further comprises a second optimization module, configured to: analyzing shipment characteristic data corresponding to stock products except the long-tail stock product by combining a weighted sliding average method with LGB prediction to obtain a second shipment expected result; and performing warehousing optimization on the warehouse storage except the long-tail warehouse storage in the warehouse corresponding to the warehousing optimization request according to the second shipment expected result.
In one embodiment, the feature data obtaining module 503 is configured to: searching historical shipment records of each warehouse storage in the warehouse corresponding to the warehouse optimization request; carrying out data cleaning and data conversion processing on shipment data in the historical shipment records; and carrying out characteristic engineering processing on the shipment data subjected to the data cleaning and data conversion processing to obtain shipment characteristic data.
In one embodiment, the feature data obtaining module 503 is further configured to: carrying out characteristic engineering processing on the data cleaning and data conversion processing to obtain engineering characteristic data; and carrying out characteristic screening on the engineering characteristic data through the time sequence stability to obtain shipment characteristic data.
In one embodiment, the method further comprises a model training module for: acquiring shipment record training data; extracting shipment characteristic data corresponding to the shipment record training data; and taking shipment characteristic data corresponding to the shipment record training data as training parameters, taking the average absolute percentage error of the second shipment expected result as a model optimization target parameter, training the initial prediction model through Bayesian optimization parameter search, and obtaining a shipment quantity prediction model, wherein the initial prediction model is constructed based on a weighted sliding average method and LGB prediction. The second optimization module is specifically configured to: and inputting the shipment characteristic data corresponding to the stock products except the long-tail stock product into a shipment quantity prediction model to obtain a second shipment expected result.
In one embodiment, the first analysis module is specifically configured to: when the shipment data corresponding to the long-tail stock is lower than or equal to a preset shipment threshold, acquiring the stock type corresponding to the long-tail stock, and acquiring a first shipment expected result corresponding to the long-tail stock according to the stock type; when the shipment data corresponding to the long-tail stock is higher than a preset shipment threshold, obtaining a smooth average value of the shipment corresponding to the long-tail stock, and obtaining a first shipment expected result corresponding to the long-tail stock according to Poisson distribution corresponding to the smooth average value.
For specific limitations of the warehousing optimization device, reference may be made to the above limitations of the warehousing optimization method, which are not described in detail herein. All or part of each module in the storage optimization device can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 6. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing warehousing optimization data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of bin optimization.
Those skilled in the art will appreciate that the architecture shown in fig. 6 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:
acquiring a storage optimization request;
searching historical shipment records of each warehouse storage corresponding to the warehouse optimization request, and acquiring shipment characteristic data corresponding to the historical shipment records;
determining a long-tail stock in the stock according to the historical shipment records;
acquiring a first shipment expected result according to shipment characteristic data corresponding to the long-tail stock;
and performing warehousing optimization on the long tail warehouse inventory in the warehouse corresponding to the warehousing optimization request according to the first shipment expected result.
In one embodiment, the processor, when executing the computer program, further performs the steps of: analyzing shipment characteristic data corresponding to stock products except the long-tail stock product by combining a weighted sliding average method with LGB prediction to obtain a second shipment expected result; and performing warehousing optimization on the warehouse storage except the long-tail warehouse storage in the warehouse corresponding to the warehousing optimization request according to the second shipment expected result.
In one embodiment, the processor, when executing the computer program, further performs the steps of: searching historical shipment records of each warehouse storage in the warehouse corresponding to the warehouse optimization request; carrying out data cleaning and data conversion processing on shipment data in the historical shipment records; and carrying out characteristic engineering processing on the shipment data subjected to the data cleaning and data conversion processing to obtain shipment characteristic data.
In one embodiment, the processor, when executing the computer program, further performs the steps of: carrying out characteristic engineering processing on the data cleaning and data conversion processing to obtain engineering characteristic data; and carrying out characteristic screening on the engineering characteristic data through the time sequence stability to obtain shipment characteristic data.
In one embodiment, the processor, when executing the computer program, further performs the steps of: acquiring shipment record training data; extracting shipment characteristic data corresponding to the shipment record training data; and taking shipment characteristic data corresponding to the shipment record training data as training parameters, taking the average absolute percentage error of the second shipment expected result as a model optimization target parameter, training the initial prediction model through Bayesian optimization parameter search, and obtaining a shipment quantity prediction model, wherein the initial prediction model is constructed based on a weighted sliding average method and LGB prediction.
In one embodiment, the processor, when executing the computer program, further performs the steps of: when the shipment data corresponding to the long-tail stock is lower than or equal to a preset shipment threshold, acquiring the stock type corresponding to the long-tail stock, and acquiring a first shipment expected result corresponding to the long-tail stock according to the stock type; when the shipment data corresponding to the long-tail stock is higher than a preset shipment threshold, obtaining a smooth average value of the shipment corresponding to the long-tail stock, and obtaining a first shipment expected result corresponding to the long-tail stock according to Poisson distribution corresponding to the smooth average value.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring a storage optimization request;
searching historical shipment records of each warehouse storage corresponding to the warehouse optimization request, and acquiring shipment characteristic data corresponding to the historical shipment records;
determining a long-tail stock in the stock according to the historical shipment records;
acquiring a first shipment expected result according to shipment characteristic data corresponding to the long-tail stock;
and performing warehousing optimization on the long tail warehouse inventory in the warehouse corresponding to the warehousing optimization request according to the first shipment expected result.
In one embodiment, the computer program when executed by the processor further performs the steps of: analyzing shipment characteristic data corresponding to stock products except the long-tail stock product by combining a weighted sliding average method with LGB prediction to obtain a second shipment expected result; and performing warehousing optimization on the warehouse storage except the long-tail warehouse storage in the warehouse corresponding to the warehousing optimization request according to the second shipment expected result.
In one embodiment, the computer program when executed by the processor further performs the steps of: searching historical shipment records of each warehouse storage in the warehouse corresponding to the warehouse optimization request; carrying out data cleaning and data conversion processing on shipment data in the historical shipment records; and carrying out characteristic engineering processing on the shipment data subjected to the data cleaning and data conversion processing to obtain shipment characteristic data.
In one embodiment, the computer program when executed by the processor further performs the steps of: carrying out characteristic engineering processing on the data cleaning and data conversion processing to obtain engineering characteristic data; and carrying out characteristic screening on the engineering characteristic data through the time sequence stability to obtain shipment characteristic data.
In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring shipment record training data; extracting shipment characteristic data corresponding to the shipment record training data; and taking shipment characteristic data corresponding to the shipment record training data as training parameters, taking the average absolute percentage error of the second shipment expected result as a model optimization target parameter, training the initial prediction model through Bayesian optimization parameter search, and obtaining a shipment quantity prediction model, wherein the initial prediction model is constructed based on a weighted sliding average method and LGB prediction.
In one embodiment, the computer program when executed by the processor further performs the steps of: when the shipment data corresponding to the long-tail stock is lower than or equal to a preset shipment threshold, acquiring the stock type corresponding to the long-tail stock, and acquiring a first shipment expected result corresponding to the long-tail stock according to the stock type; when the shipment data corresponding to the long-tail stock is higher than a preset shipment threshold, obtaining a smooth average value of the shipment corresponding to the long-tail stock, and obtaining a first shipment expected result corresponding to the long-tail stock according to Poisson distribution corresponding to the smooth average value.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware related to instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above examples only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A method of storage optimization, the method comprising:
acquiring a storage optimization request;
searching historical shipment records of each warehouse storage in the warehouse corresponding to the warehousing optimization request, and acquiring shipment characteristic data corresponding to the historical shipment records;
determining a long-tail stock in the stock according to the historical shipment records;
acquiring a first shipment expected result according to shipment characteristic data corresponding to the long-tail stock;
And performing warehousing optimization on the long-tailed warehouse inventory in the warehouse corresponding to the warehousing optimization request according to the first shipment expected result.
2. The method of claim 1, wherein after determining the long tail of the inventory items from the historical shipment records, further comprising:
analyzing shipment characteristic data corresponding to the stock products except the long-tail stock product by combining a weighted sliding average method with LGB prediction to obtain a second shipment expected result;
and performing warehousing optimization on the warehouse storage except the long-tail warehouse storage in the warehouse corresponding to the warehousing optimization request according to the second shipment expected result.
3. The method according to claim 2, wherein the searching for the historical shipment record of each inventory item in the warehouse corresponding to the warehousing optimization request, and the obtaining shipment characteristic data corresponding to the historical shipment record comprises:
searching historical shipment records of each warehouse storage in the warehouse corresponding to the warehouse optimization request;
carrying out data cleaning and data conversion processing on the shipment data in the historical shipment records;
and carrying out characteristic engineering processing on the shipment data subjected to the data cleaning and data conversion processing to obtain shipment characteristic data.
4. The method of claim 3, wherein the performing feature engineering on the data cleansing and data conversion process to obtain shipment feature data comprises:
carrying out characteristic engineering processing on the data cleaning and data conversion processing to obtain engineering characteristic data;
and carrying out characteristic screening on the engineering characteristic data through the time sequence stability to obtain shipment characteristic data.
5. The method according to claim 4, wherein before analyzing shipment characteristic data corresponding to inventory other than the long-tailed inventory by combining the weighted moving average method with LGB prediction to obtain a second shipment expected result, the method further comprises:
acquiring shipment record training data;
extracting shipment characteristic data corresponding to the shipment record training data;
taking shipment characteristic data corresponding to the shipment record training data as training parameters, taking the average absolute percentage error of a second shipment expected result as a model optimization target parameter, training an initial prediction model through Bayesian optimization parameter search, and obtaining a shipment quantity prediction model, wherein the initial prediction model is constructed based on a weighted sliding average method and LGB prediction;
The analyzing the shipment characteristic data corresponding to the stock products except the long-tail stock product by combining a weighted moving average method with LGB prediction to obtain a second shipment expected result comprises the following steps:
and inputting the shipment characteristic data corresponding to the stock products except the long-tail stock product into the shipment quantity prediction model to obtain a second shipment expected result.
6. The method of claim 1, wherein the shipment characteristic data comprises shipment volume data, and the obtaining a first shipment expected result according to the shipment characteristic data corresponding to the long-tailed stock comprises:
when the shipment data corresponding to the long-tail stock is lower than or equal to a preset shipment threshold, acquiring the stock type corresponding to the long-tail stock, and acquiring a first shipment expected result corresponding to the long-tail stock according to the stock type;
when the shipment data corresponding to the long-tail stock is higher than a preset shipment threshold, obtaining a smooth average value of the shipment corresponding to the long-tail stock, and obtaining a first shipment expected result corresponding to the long-tail stock according to Poisson distribution corresponding to the smooth average value.
7. A storage optimization device, the device comprising:
The request acquisition module is used for acquiring a warehousing optimization request;
the characteristic data acquisition module is used for searching the historical shipment records of the warehouse stocks in the warehouse corresponding to the warehouse optimization request and acquiring the shipment characteristic data corresponding to the historical shipment records;
the long-tail screening module is used for determining long-tail stock in the stock according to the historical shipment records;
the first analysis module is used for acquiring a first expected shipment result according to shipment characteristic data corresponding to the long-tailed stock;
and the first optimization module is used for carrying out warehousing optimization on the long-tailed warehouse inventory in the warehouse corresponding to the warehousing optimization request according to the first shipment expected result.
8. The apparatus of claim 7, further comprising a second optimization module to:
analyzing shipment characteristic data corresponding to the stock products except the long-tail stock product by combining a weighted sliding average method with LGB prediction to obtain a second shipment expected result; and performing warehousing optimization on the warehouse storage except the long-tail warehouse storage in the warehouse corresponding to the warehousing optimization request according to the second shipment expected result.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 6 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010288397.4A CN113537850A (en) | 2020-04-14 | 2020-04-14 | Storage optimization method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010288397.4A CN113537850A (en) | 2020-04-14 | 2020-04-14 | Storage optimization method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113537850A true CN113537850A (en) | 2021-10-22 |
Family
ID=78088055
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010288397.4A Pending CN113537850A (en) | 2020-04-14 | 2020-04-14 | Storage optimization method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113537850A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115187176A (en) * | 2022-09-07 | 2022-10-14 | 国连科技(浙江)有限公司 | Cargo transfer method and device for optimizing cargo storage space |
| CN115965140A (en) * | 2022-12-27 | 2023-04-14 | 北京航天智造科技发展有限公司 | Inventory optimal planning method, system, equipment and storage medium |
| CN116703301A (en) * | 2023-06-15 | 2023-09-05 | 山东盛太锆业资源有限公司 | Zirconia waste material management and control method based on information of multiple recovery warehouses |
| TWI826043B (en) * | 2022-10-12 | 2023-12-11 | 緯創資通股份有限公司 | Method and electronic apparatus for predictive value decision and non-transitory computer readable storage medium thereof |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1386234A (en) * | 2000-08-30 | 2002-12-18 | 本田技研工业株式会社 | Demand forecasting method in parts inventory control |
| CN108389013A (en) * | 2017-02-03 | 2018-08-10 | 北京京东尚科信息技术有限公司 | Storage data method for dynamically processing and device |
| US20180285902A1 (en) * | 2017-03-31 | 2018-10-04 | Walmart Apollo, Llc | System and method for data-driven insight into stocking out-of-stock shelves |
| CN110298613A (en) * | 2019-05-31 | 2019-10-01 | 江苏苏宁物流有限公司 | Processing method and system that commodity sort efficiency are improved in a kind of storage field |
| CN110363454A (en) * | 2018-04-09 | 2019-10-22 | 杉数科技(北京)有限公司 | For determining the method and device of commodity replenishment quantity |
| CN110400103A (en) * | 2019-05-08 | 2019-11-01 | 深圳壹账通智能科技有限公司 | Replenishment quantity determines method, apparatus, computer installation and storage medium |
| CN110751497A (en) * | 2018-07-23 | 2020-02-04 | 北京京东尚科信息技术有限公司 | Commodity replenishment method and device |
-
2020
- 2020-04-14 CN CN202010288397.4A patent/CN113537850A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1386234A (en) * | 2000-08-30 | 2002-12-18 | 本田技研工业株式会社 | Demand forecasting method in parts inventory control |
| CN108389013A (en) * | 2017-02-03 | 2018-08-10 | 北京京东尚科信息技术有限公司 | Storage data method for dynamically processing and device |
| US20180285902A1 (en) * | 2017-03-31 | 2018-10-04 | Walmart Apollo, Llc | System and method for data-driven insight into stocking out-of-stock shelves |
| CN110363454A (en) * | 2018-04-09 | 2019-10-22 | 杉数科技(北京)有限公司 | For determining the method and device of commodity replenishment quantity |
| CN110751497A (en) * | 2018-07-23 | 2020-02-04 | 北京京东尚科信息技术有限公司 | Commodity replenishment method and device |
| CN110400103A (en) * | 2019-05-08 | 2019-11-01 | 深圳壹账通智能科技有限公司 | Replenishment quantity determines method, apparatus, computer installation and storage medium |
| CN110298613A (en) * | 2019-05-31 | 2019-10-01 | 江苏苏宁物流有限公司 | Processing method and system that commodity sort efficiency are improved in a kind of storage field |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115187176A (en) * | 2022-09-07 | 2022-10-14 | 国连科技(浙江)有限公司 | Cargo transfer method and device for optimizing cargo storage space |
| TWI826043B (en) * | 2022-10-12 | 2023-12-11 | 緯創資通股份有限公司 | Method and electronic apparatus for predictive value decision and non-transitory computer readable storage medium thereof |
| CN115965140A (en) * | 2022-12-27 | 2023-04-14 | 北京航天智造科技发展有限公司 | Inventory optimal planning method, system, equipment and storage medium |
| CN116703301A (en) * | 2023-06-15 | 2023-09-05 | 山东盛太锆业资源有限公司 | Zirconia waste material management and control method based on information of multiple recovery warehouses |
| CN116703301B (en) * | 2023-06-15 | 2023-12-08 | 山东盛太锆业资源有限公司 | Zirconia waste material management and control method based on information of multiple recovery warehouses |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113537850A (en) | Storage optimization method and device, computer equipment and storage medium | |
| US10504120B2 (en) | Determining a temporary transaction limit | |
| Epp et al. | A discrete-time queueing network approach to performance evaluation of autonomous vehicle storage and retrieval systems | |
| CN111080398B (en) | Commodity recommendation method, commodity recommendation device, computer equipment and storage medium | |
| CN109961198B (en) | Associated information generation method and device | |
| Siregar et al. | Forecasting of raw material needed for plastic products based in income data using ARIMA method | |
| CN108665156B (en) | Supply chain selection evaluation method based on Markov chain under block chain | |
| CN108182633B (en) | Loan data processing method, loan data processing device, loan data processing program, and computer device and storage medium | |
| CN114663198A (en) | Product recommendation method, device and equipment based on user portrait and storage medium | |
| CN108628882A (en) | Method and system for prejudging problem | |
| CN115202847A (en) | Task scheduling method and device | |
| CN110516123A (en) | Data query time-consuming appraisal procedure, device, computer equipment and storage medium | |
| CN113850439A (en) | Energy consumption prediction method, device, equipment and storage medium for rail transit station equipment | |
| CN116827950A (en) | Cloud resource processing method, device, equipment and storage medium | |
| CN113743971A (en) | Data processing method and device | |
| KR102340179B1 (en) | Method for providing machine learning based picking location inventory replenishment service using demand forecasting | |
| CN115423555A (en) | Commodity recommendation method and device, electronic equipment and storage medium | |
| CN114925919A (en) | Service resource processing method and device, computer equipment and storage medium | |
| CN114840759A (en) | Recommendation method and device and computer readable storage medium | |
| CN113344604A (en) | User subdivision method based on user behavior data and flow calculation | |
| CN111915347A (en) | Method, device and system for effectively storing and applying promotion purchase price | |
| CN112884391A (en) | Receiving and dispatching piece planning method and device, electronic equipment and storage medium | |
| CN112906723A (en) | Feature selection method and device | |
| CN113837783A (en) | Time series model parameter optimization method and device and computer equipment | |
| CN116187895B (en) | Intelligent warehouse cargo flow planning method, system and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |