Warehousing information prediction method and device, equipment and storage medium

Abstract

The embodiment of the invention discloses a warehousing information prediction method and device, equipment and a storage medium. The method comprises the following steps: acquiring current actual warehouse information of a target warehouse at current time and target planned warehouse information of the target warehouse at target time; obtaining a target warehousing task of which the reservation warehousing time of the target warehouse is the target time; based on the target warehousing task, determining target warehousing article information of the target warehouse at the target time; based on a target prediction model, the current actual warehouse information, the target plan warehouse information and the target warehouse-in article information, determining target prediction warehouse-in information of the target warehouse at the target time; wherein the target prediction model is determined in advance based on the current actual warehouse information, the historical plan warehouse information, the historical warehousing article information and the historical actual warehousing information of the warehouse at the historical time. Through the technical scheme of the embodiment of the invention, the accuracy of warehousing information prediction can be improved, so that the productivity utilization rate and the warehousing efficiency are improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to computer technology, and in particular to a method, device, equipment and storage medium for predicting incoming inventory information. Background Art

[0002] With the rapid development of computer technology, item owners, such as merchants, can pre-deliver items to platform warehouses based on business needs, so that items can be delivered to consumers faster and improve consumer experience.

[0003] At present, the future incoming goods volume is usually predicted based on the scheduled incoming goods time and scheduled incoming goods volume filled in by the party to which the goods belong, so as to optimize and integrate the incoming goods plan and the incoming goods time efficiency based on the predicted incoming goods volume, and arrange the production capacity in advance.

[0004] However, in the process of implementing the present invention, the inventors found that there are at least the following problems in the prior art:

[0005] The existing warehousing forecasting method is highly dependent on the scheduled warehousing time and the scheduled warehousing quantity filled in by the party to whom the items belong. However, the filled-in scheduled warehousing time and the scheduled warehousing quantity may be filled in incorrectly, and the item delivery process cannot fully guarantee the timeliness, so the accuracy of the filled-in scheduled warehousing time cannot be guaranteed, resulting in inaccurate predicted warehousing quantity, which in turn causes unreasonable production capacity allocation, reduces production capacity utilization, and reduces warehousing efficiency. Summary of the invention

[0006] The embodiments of the present invention provide a method, device, equipment and storage medium for predicting warehousing information to improve the accuracy of warehousing information prediction, thereby improving production capacity utilization and warehousing efficiency.

[0007] In a first aspect, an embodiment of the present invention provides a method for predicting incoming inventory information, comprising:

[0008] Get the current actual warehouse information of the target warehouse at the current time and the target planned warehouse information at the target time;

[0009] Obtain a target warehousing task whose scheduled warehousing time of the target warehouse is the target time;

[0010] Based on the target warehousing task, determine the target warehousing item information of the target warehouse at the target time;

[0011] Determine the target forecasted warehouse entry information of the target warehouse at the target time based on the target forecast model, the current actual warehouse information, the target planned warehouse information and the target warehouse entry information;

[0012] The target prediction model is determined in advance based on the current actual warehouse information, historical planned warehouse information, historical warehouse item information and historical actual warehouse item information of the warehouse at historical time.

[0013] In a second aspect, an embodiment of the present invention further provides a storage information prediction device, comprising:

[0014] The warehouse information acquisition module is used to obtain the current actual warehouse information of the target warehouse at the current time and the target planned warehouse information at the target time;

[0015] A warehousing task acquisition module, used to acquire a target warehousing task whose scheduled warehousing time of the target warehouse is the target time;

[0016] An entry item information determination module, configured to determine target entry item information of the target warehouse at the target time based on the target entry task;

[0017] A storage information prediction module, used to determine the target predicted storage information of the target warehouse at the target time based on the target prediction model, the current actual warehouse information, the target planned warehouse information and the target storage item information;

[0018] The target prediction model is determined in advance based on the current actual warehouse information, historical planned warehouse information, historical warehouse item information and historical actual warehouse item information of the warehouse at historical time.

[0019] In a third aspect, an embodiment of the present invention further provides an electronic device, the electronic device comprising:

[0020] one or more processors;

[0021] A memory for storing one or more programs;

[0022] When the one or more programs are executed by the one or more processors, the one or more processors implement the inventory information prediction method provided by any embodiment of the present invention.

[0023] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the inventory information prediction method provided by any embodiment of the present invention.

[0024] One embodiment of the above invention has the following advantages or beneficial effects:

[0025] By determining in advance a target prediction model based on the current actual warehouse information, historical planned warehouse information, historical incoming item information and historical actual incoming item information of the warehouse at historical times, the target prediction model can be used to determine the target predicted incoming inventory information of the target warehouse at the target time based on the current actual warehouse information of the target warehouse at the current time, the target planned warehouse information at the target time and the target incoming item information at the target time. By considering the planned warehouse information at the planning layer, the incoming item information at the fulfillment layer and the actual warehouse information at the execution layer, the incoming inventory information at future times can be more accurately predicted, thereby improving the accuracy of the incoming inventory information prediction and thereby improving the capacity utilization and incoming inventory efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0027] Figure 1 It is a flow chart of a method for predicting warehousing information provided by an embodiment of the present invention;

[0028] Figure 2 is a flow chart of another method for predicting warehousing information provided by an embodiment of the present invention;

[0029] Figure 3 It is a flowchart of another method for predicting warehousing information provided by an embodiment of the present invention;

[0030] Figure 4 It is a structural schematic diagram of a storage information prediction device provided by an embodiment of the present invention;

[0031] Figure 5 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0032] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0033] Figure 1This is a flowchart of a method for predicting incoming warehouse information provided by an embodiment of the present invention. This embodiment is applicable to the case of predicting incoming warehouse information in the future. The method can be executed by an incoming warehouse information prediction device, which can be implemented by software and / or hardware and integrated into an electronic device. Figure 1 As shown, the method specifically comprises the following steps:

[0034] S110. Obtain the current actual warehouse information of the target warehouse at the current time and the target planned warehouse information at the target time.

[0035] Among them, the target warehouse may refer to the warehouse for which the incoming warehouse information needs to be predicted at present. Any warehouse may be used as the target warehouse. Time may refer to the date for calculating the incoming warehouse information with the granularity of day. For example, the current time may refer to the current day. The target time may refer to the future time after the current time. For example, a certain day in the future may be determined as the target time. The current actual warehouse information may refer to the actual warehouse information of the target warehouse at the execution layer. For example, the current actual warehouse information may include but is not limited to: the current actual in-stock information and / or the current actual out-of-stock information. It should be noted that the current actual in-stock information may be the actual inventory information obtained after deducting the current actual out-of-stock information.

[0036] Among them, the current actual in-stock information may include but is not limited to: at least one of the current actual in-stock quantity, the current actual in-stock volume and the current actual in-stock weight. The current actual in-stock quantity, the current actual in-stock volume and the current actual in-stock weight may refer to the total quantity, total volume and total weight of all in-stock items in the target warehouse respectively. The current actual outbound information may include but is not limited to: at least one of the current actual outbound task quantity, the current actual outbound quantity, the current actual outbound volume and the current actual outbound weight. Among them, the actual outbound task may refer to the task of moving items out of the target warehouse. For example. The actual outbound task may refer to the actual outbound order. The current actual outbound quantity, the current actual outbound volume and the current actual outbound weight may refer to the total quantity, total volume and total weight of all outbound items in the target warehouse respectively.

[0037] The target planned warehouse information may refer to the planned warehouse information of the target warehouse at the planning level. For example, the target planned warehouse information may include but is not limited to: at least one of the target planned incoming goods quantity, the target planned outgoing goods quantity and the target planned in-stock goods quantity. It should be noted that the target planned in-stock goods quantity may not include the target planned incoming goods quantity and the target planned outgoing goods quantity.

[0038] Specifically, the current actual warehouse information of the target warehouse at the current time can be obtained from the inventory management system, such as the current actual inventory quantity, the current actual inventory volume, the current actual inventory weight, the current actual outbound task quantity, the current actual outbound quantity, the current actual outbound volume, and the current actual outbound weight. The target planned warehouse information at the target time can be obtained from the purchase, sales, and inventory plan pre-specified for the target warehouse, such as the target planned inbound quantity, the target planned outbound quantity, and the target planned inbound quantity. It should be noted that the more information dimensions obtained, the more accurate the predicted inbound information.

[0039] S120: Obtain a target warehousing task whose scheduled warehousing time of the target warehouse is the target time.

[0040] Among them, the warehousing task may refer to the warehousing task of the item issued by the owner of the item (such as a merchant) to the target warehouse. For example, the warehousing task may refer to a purchase order. The warehousing task may include detailed information on the items planned to be put into the warehouse. As shown in Table 1, the warehousing task may include: the item attribute information such as the item code, item volume, item weight, whether it is a new product, and whether special management is required for each item planned to be put into the warehouse. Among them, special management may refer to shelf life management or serial number management. Some high-value items require serial number management, and one-number-one-item management is achieved through serial numbers. The scheduled warehousing time may refer to the time when the items in the warehousing task scheduled in advance by the owner of the item are delivered to the target warehouse.

[0041] Table 1 Example of warehousing task

[0042]

[0043] Specifically, after the item owner issues the warehousing task, the corresponding scheduled warehousing time is configured for each warehousing task, and the scheduled task is generated and issued to the target warehouse. The scheduled warehousing time corresponding to each warehousing task of the target warehouse can be obtained through the scheduled task, and the warehousing task with the scheduled warehousing time as the target time is determined as the target warehousing task.

[0044] S130: Based on the target warehousing task, determine the target warehousing item information of the target warehouse at the target time.

[0045] Among them, the target warehouse items may refer to the warehouse items included in the target warehouse tasks. The target warehouse item information may include but is not limited to: the total number of target warehouse item types, the total number of target warehouse items, the total volume of target warehouse items, the total weight of target warehouse items, target warehouse new product information, target warehouse special management item information and at least one of the target warehouse task quantity. Among them, the target warehouse new product information may include but is not limited to: the total number of target warehouse new product types and / or the proportion of target warehouse new product types. The target warehouse special management item information may include but is not limited to: the total number of target warehouse special management item types and / or the proportion of target warehouse special management item types.

[0046] Specifically, statistical analysis is performed on all existing target warehousing tasks to determine the target warehousing item information of the target warehouse at the target time. For example, the number of target warehousing tasks can be counted. The number of types of warehousing items in all target warehousing tasks can be added together to obtain the total number of target warehousing item types. The number of warehousing items in all target warehousing tasks can be added together to obtain the total number of target warehousing items. The volume of warehousing items in all target warehousing tasks can be added together to obtain the total volume of target warehousing items. The weight of warehousing items in all target warehousing tasks can be added together to obtain the total weight of target warehousing items.

[0047] Exemplarily, the total number of target incoming new product categories at the target warehouse at the target time can be determined based on the incoming items that are new products in each target incoming task. The ratio between the total number of target incoming new product categories and the total number of target incoming item categories can be determined as the target incoming new product category ratio. The total number of target incoming special management item categories at the target warehouse at the target time can be determined based on the incoming items that require special management in each target incoming task. The ratio between the total number of target incoming special management item categories and the total number of target incoming item categories can be determined as the target incoming special management item category ratio.

[0048] It should be noted that by collecting statistics on target new product information and target special management item information, we can pay attention to the special attributes of the items and consider the impact of the special attributes on the incoming information, thereby further improving the accuracy of the incoming information prediction.

[0049] S140: Determine the target forecasted warehousing information of the target warehouse at the target time based on the target forecast model, the current actual warehouse information, the target planned warehouse information and the target warehousing item information.

[0050] Among them, the target predicted warehousing information may include but is not limited to: at least one of the target predicted warehousing quantity, the target predicted warehousing volume, the target predicted warehousing weight and the target predicted warehousing duration. Among them, the target predicted warehousing quantity may include but is not limited to: the target predicted total warehousing quantity and / or the target predicted warehousing peak quantity. The target predicted warehousing peak quantity may refer to the warehousing quantity corresponding to the preset duration when the warehousing task is divided by the preset duration and the predicted warehousing quantity is the largest. The target predicted warehousing duration may include but is not limited to: at least one of the task queuing duration, the task acceptance duration and the task shelving duration. The warehousing process after the item arrives at the warehouse is: check-in, acceptance and shelving. The task queuing duration may be the time between the check-in time of the warehousing task and the time when the first item in the warehousing task is started to be accepted. The task acceptance duration may refer to the time between the time when the first item in the warehousing task is started to be accepted and the time when the last item is completed. The task shelving duration may refer to the time between the time when the last item in the warehousing task is completed to be put on the shelf. In this embodiment, when there are multiple target warehousing tasks, the predicted target predicted warehousing time may refer to the average of the predicted warehousing time, such as the average task queuing time, the average task acceptance time and the average task listing time.

[0051] Among them, the target prediction model may be a model for predicting incoming warehouse information. The target prediction model may refer to an objective function model or a target network model. The target prediction model is determined in advance based on the current actual warehouse information, historical planned warehouse information, historical incoming goods information and historical actual incoming warehouse information of the warehouse at historical time. Among them, the current actual warehouse information at historical time may refer to the current actual warehouse information when predicting the incoming warehouse information at historical time. For example, the current actual warehouse information at historical time may include the current actual in-stock information and / or the current actual out-of-stock information at historical time. The historical planned warehouse information may refer to the planned warehouse information of the warehouse at historical time. The historical planned warehouse information may include but is not limited to at least one of the historical planned incoming goods quantity, the historical planned out-of-stock goods quantity and the historical planned in-stock goods quantity. The historical incoming goods information may be determined in advance based on the historical incoming warehouse task whose scheduled warehousing time is historical time. For example, historical warehouse-in information includes: at least one of the total number of historical warehouse-in item types, the total number of historical warehouse-in items, the total volume of historical warehouse-in items, the total weight of historical warehouse-in items, historical warehouse-in new product information, historical warehouse-in special management item information, and the number of historical warehouse-in tasks. Historical actual warehouse-in information may refer to the actual warehouse-in information of the warehouse at a historical time. For example, historical actual warehouse-in information includes: at least one of the historical actual warehouse-in quantity, the historical actual warehouse-in volume, the historical actual warehouse-in weight, and the historical actual warehouse-in duration. It should be noted that the parameters in the historical data used to determine the target prediction model are the same as the parameters in the current data obtained during the actual prediction, except that the parameter values ​​are different.

[0052] Specifically, by utilizing the target prediction model, based on the current actual warehouse information of the execution layer, the target planned warehouse information of the planning layer, and the target incoming item information of the fulfillment layer, the target predicted incoming warehousing information of the target warehouse at the target time can be determined more accurately. For example, the target predicted incoming warehousing quantity, target predicted incoming warehousing volume, target predicted incoming warehousing weight, and target predicted incoming warehousing time can be predicted, so that the production capacity can be arranged more reasonably, that is, reasonable warehousing resources can be allocated to the target collectors, such as warehousing operators, warehouse storage locations and storage capacity, etc., thereby improving the capacity utilization rate and warehouse operation efficiency.

[0053] The technical solution of this embodiment determines in advance a target prediction model based on the current actual warehouse information, historical planned warehouse information, historical incoming item information and historical actual incoming item information of the warehouse at historical times, thereby utilizing the target prediction model to determine the target predicted incoming item information of the target warehouse at the target time based on the current actual warehouse information of the target warehouse at the current time, the target planned warehouse information at the target time and the target incoming item information at the target time, thereby more accurately predicting the incoming item information of the future time by considering the planned warehouse information at the planning layer, the incoming item information at the fulfillment layer and the actual warehouse information at the execution layer, thereby improving the accuracy of the incoming item prediction and thereby improving the capacity utilization and incoming item efficiency.

[0054] Figure 2 This is a flowchart of another method for predicting incoming inventory information provided by an embodiment of the present invention. Based on the above embodiments, this embodiment describes in detail the process of determining the target prediction model, and on this basis, further optimizes the process of predicting incoming inventory information. The explanations of the terms that are the same or corresponding to the above embodiments are not repeated here.

[0055] See also Figure 2 Another method for predicting incoming inventory information provided in this embodiment specifically includes the following steps:

[0056] S210, taking the current actual warehouse information, historical planned warehouse information and historical warehouse item information of the warehouse at historical time as independent variables, taking the historical actual warehouse item information as the dependent variable for function fitting, and determining the objective function model between the dependent variable and each independent variable.

[0057] Specifically, the correlation between the independent variable and the dependent variable can be determined by function fitting based on historical data, so as to analyze the influence of the planned warehouse information at the planning layer, the incoming goods information at the fulfillment layer, and the actual warehouse information at the execution layer on the incoming goods information prediction. For example, the independent variables may include: the current actual inventory quantity x1, the current actual inventory volume x2, the current actual inventory weight x3, the current actual outbound task quantity x4, the current actual outbound quantity x5, the current actual outbound volume x6, the current actual outbound weight x7, the historical planned inbound quantity x8, the historical planned outbound quantity x9, the historical planned inbound quantity x10, the historical incoming task quantity x11, the historical total number of incoming goods types x12, the historical total number of incoming goods x13, the historical total volume of incoming goods x14, the historical total weight of incoming goods x15, the historical proportion of new incoming goods types x16, and the historical proportion of special management items types x17. The dependent variables may include: the actual total volume of goods entering the warehouse in history y1 (equivalent to the predicted total volume of goods entering the warehouse), the actual peak volume of goods entering the warehouse in history y2 (equivalent to the predicted peak volume of goods entering the warehouse), the task queuing time y3, the task acceptance time y4 and the task listing time y5. When there are multiple dependent variables, the functional change relationship between each dependent variable and all independent variables can be determined. For example, linear fitting is performed on the independent variables and the dependent variables, and the obtained linear fitting function is used as the objective function model, such as Y(y1, y2, ..., y5) = ax1 + bx2 + ... + lx17, where a, b, ..., l are the influence weight values ​​corresponding to the 17 independent variables, respectively. The weight value is a value between 0 and 1. The larger the weight value, the higher the correlation of the independent variable to the dependent variable and the greater the influence.

[0058] S220. Obtain the current actual warehouse information of the target warehouse at the current time and the target planned warehouse information at the target time.

[0059] S230: Obtain a target warehousing task whose scheduled warehousing time of the target warehouse is the target time.

[0060] S240: Based on the target warehousing task, determine the target warehousing item information of the target warehouse at the target time.

[0061] S250. Based on the objective function model, the target predicted warehouse entry information of the target warehouse at the target time is determined according to the current actual warehouse information, the target planned warehouse information and the target warehouse entry information.

[0062] Specifically, based on the changing relationship between each dependent variable and all independent variables in the objective function model, the current actual warehouse information, target planned warehouse information and target incoming item information can be substituted into the objective function model as independent variable values ​​for weighted calculation. The obtained dependent variable value is the predicted target predicted incoming inventory information, so that the incoming inventory information can be accurately predicted through the objective function model, thereby improving the accuracy of the incoming inventory information prediction.

[0063] It should be noted that if multiple target forecasted warehousing information needs to be predicted, that is, if there are multiple dependent variables, each dependent variable can correspond to an objective function model, and all independent variable values ​​are input into the objective function model corresponding to the dependent variable for weighted calculation, and the obtained dependent variable value is determined as the corresponding target forecasted warehousing information. For example, the value of the predicted total warehousing volume y1 is 32,000 pieces, the value of the predicted peak warehousing volume y2 is 4,000 pieces, and the values ​​of the task queuing time y3, task acceptance time y4, and task shelf time y5 are 45 minutes, 28 minutes, and 32 minutes, respectively.

[0064] The technical solution of this embodiment is to use the current actual warehouse information, historical planned warehouse information and historical incoming item information of the warehouse in historical time as independent variables, and the historical actual incoming item information as the dependent variable to perform function fitting, and determine the target function model between the dependent variable and each independent variable. Then, by utilizing the change relationship between each dependent variable and all independent variables in the target prediction model, the current actual warehouse information, the target planned warehouse information and the target incoming item information are used as independent variable values ​​to perform dependent variable calculation, so that the incoming and outgoing warehouse information can be accurately predicted, thereby improving the accuracy of the incoming warehouse information prediction.

[0065] Figure 3 A flowchart of another method for predicting incoming inventory information is provided for one embodiment of the present invention. Based on the above embodiments, this embodiment describes in detail the process of determining the target prediction model, and on this basis, further optimizes the process of predicting incoming inventory information. The explanations of the terms that are the same or corresponding to the above embodiments are not repeated here.

[0066] See also Figure 3 Another method for predicting incoming inventory information provided in this embodiment specifically includes the following steps:

[0067] S310: Based on the current actual warehouse information, historical planned warehouse information, historical warehouse item information and historical actual warehouse item information of the warehouse at historical time, the prediction network model is trained to obtain a trained target prediction network model.

[0068] The prediction network model may be a pre-set neural network model for predicting storage information. The architecture of the prediction network model may be any regression network model architecture. The target prediction network model may refer to the prediction network model obtained after training.

[0069] Specifically, historical data can be used as sample data to train the prediction network model. For example, the current actual warehouse information, historical planned warehouse information, and historical warehouse item information of the warehouse at historical time are used as sample input data, and the corresponding historical actual warehouse information is used as sample label data to train the prediction network model, so that the changing relationship between the independent variable and the dependent variable can be autonomously learned. The model training process can be: input the current actual warehouse information, historical planned warehouse information, and historical warehouse item information of the warehouse at historical time into the prediction network model to predict the warehouse information, and obtain the historical predicted warehouse information at historical time based on the output of the prediction network model. The training error is determined based on the historical predicted warehouse information and the historical actual warehouse information, and the training error is back-propagated to the prediction network model, and the model parameters in the prediction network model are adjusted until the preset convergence condition is reached, such as when the number of iterations is equal to the preset number, or the training error changes tend to be stable, it is determined that the training of the prediction network model is completed, and the target prediction network model is obtained.

[0070] It should be noted that if it is necessary to predict multiple inventory entry information, a prediction network model with a single output end can be set for each predicted inventory entry information, so that different prediction network models can be used to output different predicted inventory entry information; or a prediction network model with multiple output ends can be set for all predicted inventory entry information, so that the prediction network model can output all predicted inventory entry information at the same time, thereby further improving the prediction efficiency.

[0071] S320. Obtain the current actual warehouse information of the target warehouse at the current time and the target planned warehouse information at the target time.

[0072] S330: Obtain a target warehousing task whose scheduled warehousing time of the target warehouse is the target time.

[0073] S340: Based on the target warehousing task, determine the target warehousing item information of the target warehouse at the target time.

[0074] S350: Input the current actual warehouse information, the target planned warehouse information and the target warehouse-entry item information into the target prediction network model to predict the warehouse-entry information.

[0075] Specifically, the current actual warehouse information, target planned warehouse information and target incoming item information can be input into the trained target prediction network model. The target prediction network model can predict the incoming information based on the input data, determine the target predicted incoming information and output it.

[0076] S360. Obtain target forecast warehousing information of the target warehouse at the target time according to the output of the target forecast network model.

[0077] Specifically, the target prediction network model can directly output the target predicted warehousing information of the target warehouse at the target time, so that the target prediction network model can be used to predict the warehousing information more accurately and quickly, thereby improving the accuracy and efficiency of the warehousing information prediction.

[0078] The technical solution of this embodiment is to train the prediction network model based on the current actual warehouse information, historical planned warehouse information, historical warehouse item information and historical actual warehouse item information of the warehouse at historical time, and obtain the trained target prediction network model. During the actual prediction, the current actual warehouse information, the target planned warehouse information and the target warehouse item information are input into the target prediction network model to predict the warehouse item information, and based on the output of the target prediction network model, the target predicted warehouse item information at the target time is obtained, so that the target prediction network model can be used to improve the accuracy and efficiency of the warehouse item information prediction.

[0079] The following is an embodiment of the inventory information prediction device provided in an embodiment of the present invention. The device and the inventory information prediction methods of the above-mentioned embodiments belong to the same inventive concept. For details not described in detail in the embodiment of the inventory information prediction device, please refer to the embodiment of the above-mentioned inventory information prediction method.

[0080] Figure 4 This is a schematic diagram of the structure of a storage information prediction device provided by an embodiment of the present invention. This embodiment is applicable to the case of predicting the storage information of a warehouse in the future. Figure 4 As shown, the device specifically includes: a warehouse information acquisition module 410, a warehousing task acquisition module 420, a warehousing item information determination module 430 and a warehousing information prediction module 440.

[0081] Among them, the warehouse information acquisition module 410 is used to obtain the current actual warehouse information of the target warehouse at the current time and the target planned warehouse information at the target time; the warehousing task acquisition module 420 is used to obtain the target warehousing task with the scheduled warehousing time of the target warehouse being the target time; the warehousing item information determination module 430 is used to determine the target warehousing item information of the target warehouse at the target time based on the target warehousing task; the warehousing information prediction module 440 is used to determine the target predicted warehousing information of the target warehouse at the target time based on the target prediction model, the current actual warehouse information, the target planned warehouse information and the target warehousing item information; wherein the target prediction model is determined in advance based on the current actual warehouse information, historical planned warehouse information, historical warehousing item information and historical actual warehousing information of the warehouse at historical time.

[0082] The technical solution of this embodiment determines in advance a target prediction model based on the current actual warehouse information, historical planned warehouse information, historical incoming item information and historical actual incoming item information of the warehouse at historical times, thereby utilizing the target prediction model to determine the target predicted incoming item information of the target warehouse at the target time based on the current actual warehouse information of the target warehouse at the current time, the target planned warehouse information at the target time and the target incoming item information at the target time, thereby more accurately predicting the incoming item information of the future time by considering the planned warehouse information at the planning layer, the incoming item information at the fulfillment layer and the actual warehouse information at the execution layer, thereby improving the accuracy of the incoming item prediction and thereby improving the capacity utilization and incoming item efficiency.

[0083] Optionally, the target predicted warehousing information includes: at least one of a target predicted warehousing quantity, a target predicted warehousing volume, a target predicted warehousing weight and a target predicted warehousing duration;

[0084] Among them, the target predicted inbound cargo volume includes: the target predicted total inbound cargo volume and / or the target predicted inbound peak cargo volume; the target predicted inbound time includes: at least one of the task queuing time, the task acceptance time and the task listing time.

[0085] Optionally, the device further comprises:

[0086] The target prediction model determination module is used to use the current actual warehouse information, historical planned warehouse information and historical warehouse item information of the warehouse in historical time as independent variables, and the historical actual warehouse item information as the dependent variable to perform function fitting, and determine the target function model between the dependent variable and each independent variable;

[0087] The inventory information prediction module 440 is specifically used to: determine the target predicted inventory information of the target warehouse at the target time based on the objective function model, according to the current actual warehouse information, the target planned warehouse information and the target inventory item information.

[0088] Optionally, the device further comprises:

[0089] The target prediction model determination module is used to train the prediction network model based on the current actual warehouse information, historical planned warehouse information, historical warehouse item information and historical actual warehouse information of the warehouse at historical time to obtain the trained target prediction network model;

[0090] The incoming warehouse information prediction module 440 is specifically used to: input the current actual warehouse information, the target planned warehouse information and the target incoming item information into the target prediction network model to predict the incoming warehouse information; and obtain the target predicted incoming warehouse information at the target time according to the output of the target prediction network model.

[0091] Optionally, the target warehouse item information includes at least one of: the total number of target warehouse item types, the total number of target warehouse items, the total volume of target warehouse items, the total weight of target warehouse items, target warehouse new item information, target warehouse special management item information and the target warehouse task quantity;

[0092] Among them, the target new product information includes: the total number of target new product types and / or the proportion of target new product types; the target special management item information includes: the total number of target special management item types and / or the proportion of target special management item types.

[0093] Optionally, the warehoused item information determination module 430 is specifically configured to:

[0094] Based on the incoming items that are new products in each of the target warehousing tasks, the total number of target incoming new items of the target warehouse at the target time is determined; and the ratio between the total number of target incoming new items and the total number of target incoming item types is determined as the target incoming new item ratio.

[0095] Optionally, the current actual warehouse information includes: current actual in-stock information and / or current actual out-stock information; wherein the current actual in-stock information includes at least one of the current actual in-stock quantity, the current actual in-stock volume and the current actual in-stock weight; the current actual out-stock information includes at least one of the current actual out-stock task quantity, the current actual out-stock quantity, the current actual out-stock volume and the current actual out-stock weight;

[0096] The target planned warehouse information includes at least one of a target planned incoming cargo quantity, a target planned outgoing cargo quantity and a target planned in-stock cargo quantity.

[0097] The storage information prediction device provided in the embodiment of the present invention can execute the storage information prediction method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the storage information prediction method.

[0098] It is worth noting that in the embodiment of the above-mentioned inventory information prediction device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0099] Figure 5 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Figure 5 A block diagram of an exemplary electronic device 12 suitable for use in implementing embodiments of the present invention is shown. Figure 5 The electronic device 12 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0100] like Figure 5 As shown, the electronic device 12 is in the form of a general purpose computing device. The components of the electronic device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that connects various system components (including the system memory 28 and the processing unit 16).

[0101] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0102] The electronic device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device 12, including volatile and non-volatile media, removable and non-removable media.

[0103] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The electronic device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Figure 5 not shown, usually called a "hard drive"). Although Figure 5 Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The system memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.

[0104] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. Program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0105] The electronic device 12 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, etc.), may communicate with one or more devices that enable a user to interact with the electronic device 12, and / or may communicate with any device that enables the electronic device 12 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed via an input / output (I / O) interface 22. Furthermore, the electronic device 12 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with other modules of the electronic device 12 via a bus 18. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0106] The processing unit 16 executes various functional applications and data processing by running the program stored in the system memory 28, for example, implementing a method for predicting warehousing information provided in the embodiment of the present invention, the method comprising:

[0107] Acquire translation sample pair data, the translation sample pair data including a first source text corresponding to a source language and a first target text corresponding to a target language;

[0108] Get the current actual warehouse information of the target warehouse at the current time and the target planned warehouse information at the target time;

[0109] Obtain a target warehousing task whose scheduled warehousing time of the target warehouse is the target time;

[0110] Based on the target warehousing task, determine the target warehousing item information of the target warehouse at the target time;

[0111] Determine the target forecasted warehouse entry information of the target warehouse at the target time based on the target forecast model, the current actual warehouse information, the target planned warehouse information and the target warehouse entry information;

[0112] The target prediction model is determined in advance based on the current actual warehouse information, historical planned warehouse information, historical warehouse item information and historical actual warehouse item information of the warehouse at historical time.

[0113] Of course, those skilled in the art can understand that the processor can also implement the technical solution of the inventory information prediction method provided by any embodiment of the present invention.

[0114] This embodiment provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the steps of the method for predicting inventory information provided in any embodiment of the present invention are implemented. The method includes:

[0115] Get the current actual warehouse information of the target warehouse at the current time and the target planned warehouse information at the target time;

[0116] Obtain a target warehousing task whose scheduled warehousing time of the target warehouse is the target time;

[0117] Based on the target warehousing task, determine the target warehousing item information of the target warehouse at the target time;

[0118] Determine the target forecasted warehouse entry information of the target warehouse at the target time based on the target forecast model, the current actual warehouse information, the target planned warehouse information and the target warehouse entry information;

[0119] The target prediction model is determined in advance based on the current actual warehouse information, historical planned warehouse information, historical warehouse item information and historical actual warehouse item information of the warehouse at historical time.

[0120] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0121] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0122] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0123] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0124] It should be understood by those skilled in the art that the modules or steps of the present invention described above can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, optionally, they can be implemented by a program code executable by a computer device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0125] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for predicting incoming inventory information, characterized in that: include: Get the current actual warehouse information of the target warehouse at the current time and the target planned warehouse information at the target time; Obtain a target warehousing task whose scheduled warehousing time of the target warehouse is the target time; Based on the target warehousing task, determine the target warehousing item information of the target warehouse at the target time; Determine the target forecasted warehouse entry information of the target warehouse at the target time based on the target forecast model, the current actual warehouse information, the target planned warehouse information and the target warehouse entry information; The target prediction model is determined in advance based on the current actual warehouse information, historical planned warehouse information, historical warehouse item information and historical actual warehouse item information of the warehouse at historical time.

2. The method according to claim 1, characterized in that The target predicted warehousing information includes: at least one of the target predicted warehousing quantity, the target predicted warehousing volume, the target predicted warehousing weight and the target predicted warehousing duration; Among them, the target predicted inbound cargo volume includes: the target predicted total inbound cargo volume and / or the target predicted inbound peak cargo volume; the target predicted inbound time includes: at least one of the task queuing time, the task acceptance time and the task listing time.

3. The method according to claim 1, characterized in that Based on the current actual warehouse information, historical planned warehouse information, historical incoming goods information and historical actual incoming goods information of the warehouse at historical time, the target prediction model is determined, including: The current actual warehouse information, historical planned warehouse information and historical warehouse item information of the warehouse in historical time are used as independent variables, and the historical actual warehouse item information is used as the dependent variable to perform function fitting, and determine the objective function model between the dependent variable and each independent variable; The determining, based on the target prediction model, the current actual warehouse information, the target planned warehouse information and the target warehoused item information, the target predicted warehouse entry information at the target time includes: Based on the objective function model, the target predicted warehouse information at the target time is determined according to the current actual warehouse information, the target planned warehouse information and the target warehoused item information.

4. The method according to claim 1, characterized in that: Based on the current actual warehouse information, historical planned warehouse information, historical incoming goods information and historical actual incoming goods information of the warehouse at historical time, the target prediction model is determined, including: Based on the current actual warehouse information, historical planned warehouse information, historical warehouse item information and historical actual warehouse information of the warehouse at historical time, the prediction network model is trained to obtain the trained target prediction network model; The determining, based on the target prediction method, the current actual warehouse information, the target planned warehouse information and the target warehoused item information, the target predicted warehouse entry information at the target time includes: Inputting the current actual warehouse information, the target planned warehouse information and the target warehouse-entry item information into the target prediction network model to predict the warehouse-entry information; According to the output of the target prediction network model, the target prediction warehousing information of the target warehouse at the target time is obtained.

5. The method according to claim 1, characterized in that: The target warehouse item information includes: at least one of: the total number of target warehouse item types, the total number of target warehouse items, the total volume of target warehouse items, the total weight of target warehouse items, target warehouse new item information, target warehouse special management item information and the target warehouse task quantity; Among them, the target new product information includes: the total number of target new product types and / or the proportion of target new product types; the target special management item information includes: the total number of target special management item types and / or the proportion of target special management item types.

6. The method according to claim 5, characterized in that The determining, based on the target warehousing task, target warehousing item information of the target warehouse at the target time includes: Based on the incoming items that are new products in each of the target incoming warehousing tasks, determine the total number of target incoming new products of the target warehouse at the target time; The ratio between the total number of target new product categories entering the warehouse and the total number of target item categories entering the warehouse is determined as the target new product category ratio.

7. The method according to any one of claims 1 to 6, characterized in that: The current actual warehouse information includes: current actual in-stock information and / or current actual out-stock information; wherein the current actual in-stock information includes at least one of the current actual in-stock quantity, the current actual in-stock volume and the current actual in-stock weight; the current actual out-stock information includes at least one of the current actual out-stock task quantity, the current actual out-stock quantity, the current actual out-stock volume and the current actual out-stock weight; The target planned warehouse information includes at least one of a target planned incoming cargo quantity, a target planned outgoing cargo quantity and a target planned in-stock cargo quantity.

8. A storage information prediction device, characterized in that: include: The warehouse information acquisition module is used to obtain the current actual warehouse information of the target warehouse at the current time and the target planned warehouse information at the target time; A warehousing task acquisition module, used to acquire a target warehousing task whose scheduled warehousing time of the target warehouse is the target time; An entry item information determination module, configured to determine target entry item information of the target warehouse at the target time based on the target entry task; A storage information prediction module, used to determine the target predicted storage information of the target warehouse at the target time based on the target prediction model, the current actual warehouse information, the target planned warehouse information and the target storage item information; The target prediction model is determined in advance based on the current actual warehouse information, historical planned warehouse information, historical warehouse item information and historical actual warehouse item information of the warehouse at historical time.

9. An electronic device, characterized in that: The electronic device comprises: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the inventory information prediction method as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for predicting inventory information as described in any one of claims 1 to 7 is implemented.

Images