Efficient feeding intelligent warehouse management method and device based on Internet of Things

Abstract

The invention discloses an efficient feeding intelligent warehouse management method and device based on the Internet of Things. The efficient feeding intelligent warehouse management method based on the Internet of Things comprises the following steps: acquiring data elements, and preprocessing the data elements; constructing a demand prediction model through a Fourier algorithm, an autoregression algorithm and a parallel movement method; determining a feeding sequence and a scheduling plan according to the demand prediction result; the inventory remaining amount is obtained, and a multi-level inventory early warning mechanism is set according to the inventory remaining amount; order emergency degrees are obtained, order priorities are determined according to the order emergency degrees, and order sequences are reordered; adjusting the scheduling plan according to the reordered order sequence; and the AGV and the robot are used for feeding according to the scheduling plan. Through the Fourier algorithm, the autoregression algorithm and the parallel movement method, the order demand in a period of time in the future is predicted, the effect of improving the feeding efficiency is achieved, and the problem of low feeding efficiency in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things, and in particular to an efficient material feeding intelligent warehousing management method and device based on the Internet of Things. Background Art

[0002] With the rapid development of Internet of Things technology, its application in the field of efficient material feeding and intelligent warehousing management is becoming more and more extensive. This project aims to develop a demand forecasting model and order urgency model, and realize the automation, intelligence and efficiency of the material feeding process through accurate positioning and intelligent scheduling of materials in the warehouse, thereby improving the efficiency of warehousing operations, reducing operating costs, and creating greater value for enterprises.

[0003] The existing efficient material feeding intelligent warehousing management method is achieved by attaching RFID tags to materials for RFID identification and tracking of material location, automatic update of inventory status, and adding intelligent robots to intelligent handling of material information.

[0004] For example, a warehouse management method and device announced in the invention patent with announcement number: CN108074058B includes: determining multiple management modules required for warehouse management through Android plug-in, determining the target management module based on user input, collecting identification code data of the item to be scanned through an identification code scanning device, receiving and identifying the collected identification code data through a two-way binding method of view and data, providing the identified identification code data to the target management module, and transmitting the identified identification code data to the corresponding module in the server in a responsive manner.

[0005] For example, the patent application with publication number: CN110046864A discloses a positioning system and a smart warehousing method for an intelligent warehousing system, which includes: a positioning tag and an RFID receiver set on a forklift and an RFID tag set on the goods. The RFID receiver can obtain the goods information stored in the RFID tag by making contact with the RFID tag. The storage location of the goods can be obtained by using the depth-first rule when the goods are stacked, the time when the RFID receiver loses contact with the RFID tag, and the position of the positioning tag. In addition, when the storage location of other goods is moved due to the removal of goods, the updated location information of the goods can be obtained according to the height-first priority and depth-second priority rule when stacking and the goods information read by the RFID receiver.

[0006] However, in the process of implementing the technical solution of the invention in the embodiments of the present application, the present application found that the above technology has at least the following technical problems:

[0007] In the prior art, robots are used to identify and transport materials and the space required for the materials is planned, but it does not consider whether insufficient inventory will cause delays in the feeding operation during the feeding process, resulting in low feeding efficiency. Summary of the invention

[0008] The embodiments of the present application solve the problem of low feeding efficiency in the prior art by providing an efficient feeding intelligent warehousing management method and device based on the Internet of Things, thereby achieving efficient feeding.

[0009] The embodiment of the present application provides an efficient feeding intelligent warehousing management method based on the Internet of Things, comprising the following steps: obtaining data elements and preprocessing the data elements; constructing a demand forecasting model based on the preprocessed data elements through Fourier algorithm, autoregressive algorithm and parallel movement method; obtaining demand forecasting results based on the demand forecasting model; determining the feeding sequence and scheduling plan based on the demand forecasting results; obtaining the predicted inventory remaining amount and setting a multi-level inventory early warning mechanism based on the predicted inventory remaining amount; obtaining the order urgency, determining the order priority according to the order urgency and reordering the order sequence; adjusting the scheduling plan according to the reordered order sequence; and using AGV carts and robots to feed according to the scheduling plan.

[0010] Furthermore, the data elements are preprocessed, and the preprocessing steps include: data cleaning, data noise reduction, data integration, feature extraction, and data normalization based on the collected data to obtain preprocessed data elements; the data elements include: order urgency, order demand, order profit, latest delivery date, cycle length of historical feed speed, and coefficient of seasonal factors.

[0011] Furthermore, the efficient material feeding intelligent warehousing management method based on the Internet of Things is characterized in that the demand forecasting model includes a demand quantity forecasting model, and the step of establishing the demand quantity forecasting model includes: using a multi-model fusion method to establish multiple time series forecasting models according to the preprocessed data elements; receiving input data of the forecast time period, inputting it into multiple time series models to predict the demand quantity of the required forecast time period, and using the demand quantity of the forecast time period as output data; comparing the output data with the actual data, and saving the time series forecasting model with the smallest error as the demand quantity forecasting model; and analyzing and learning according to the demand quantity forecasting model to predict the forecast demand and supply trends in a future period.

[0012] Furthermore, the principle of the demand forecasting model is as follows: according to the periodicity, the Fourier series part is decomposed into the sum of a series of sine functions and cosine functions to capture the periodic changes of the data; according to the autoregressive part, the autocorrelation of the time series is captured; according to the moving average part, the random fluctuations in the smoothed data are obtained, and the average value of the calculated specific time steps in the past is used as the estimated value of the predicted demand; the influence of the coefficient change of the seasonal factor on the feeding speed is obtained; the predicted demand is obtained according to the autocorrelation of the time series, the estimated value of the predicted demand, and the influence of the coefficient change of the seasonal factor on the feeding speed.

[0013] Further, the demand forecasting model includes an order urgency forecasting model, and an order urgency forecasting model is established:

[0014]

[0015] In the formula, i represents the order number, y i represents the predicted value of the order urgency of order i, α is the weight of the delivery time interval corresponding to the order urgency calculation, T i is the latest delivery date for order i, T C is the current time, β is the weight of the order demand corresponding to the order urgency calculation, Q i is the demand for order i, Q max is the maximum order demand that the current production system can handle, γ is the weight of the order profit corresponding to the order urgency calculation, P i is the profit of order i, P avg is the average profit of all current orders.

[0016] Furthermore, the efficient feeding intelligent warehousing management method based on the Internet of Things is characterized in that the setting of a multi-level inventory warning mechanism includes: setting a multi-level inventory warning mechanism, including a first-level warning, a second-level warning and a third-level warning, which correspond to different degrees of inventory reduction: when the predicted inventory remaining amount is within a first limited range, no warning is issued; when the predicted inventory remaining amount is within a second limited range, a first-level warning is issued; when the predicted inventory remaining amount is within a third limited range, a second-level warning is issued; when the predicted inventory remaining amount is within a fourth limited range, a third-level warning is issued.

[0017] Furthermore, the calculation formula for the predicted inventory remaining quantity is set as:

[0018]

[0019] In the formula, i represents the order number, A represents the inventory capacity, and Q i is the demand for order i, M i represents the predicted inventory remaining for order i, ω represents the influence of demand on the feeding speed, b is a constant term used to adjust the basic feeding speed, VST+1 Represents the predicted feed rate at the future time step T+1.

[0020] Furthermore, the step of determining order priority includes: automatically calculating a time interval based on order information; the time interval is the time interval from the submission date required by the order to the current date; sorting according to the length of the time interval, the longer the time interval, the lower the order urgency, the shorter the time interval, the higher the order urgency, and the same time intervals have the same order urgency; sorting the orders according to their urgency, determining the priority order according to the order of order urgency, the higher the order urgency, the higher the order priority, the lower the order urgency, the lower the order priority, orders with the same order urgency have the same priority, and orders with the same priority are executed in order of precedence.

[0021] Furthermore, the adjusting the scheduling plan according to the reordered order sequence includes the following steps: evaluating the planned but unexecuted feeding tasks, first determining whether there are any tasks that are inconsistent with the new order sequence; if not, reordering the new order; if consistent, continuing to execute in the original order, and then determining whether the priority has changed: if so, rearranging the order according to the priority; if not, continuing to execute in the original order; and displaying the adjusted scheduling plan.

[0022] The embodiment of the present application provides an efficient feeding intelligent warehousing management device based on the Internet of Things, including: a data acquisition module, a data preprocessing module, a model building module, a demand forecasting and scheduling plan module, an inventory warning module, a priority sorting module, a scheduling plan adjustment module, and an automatic feeding module; wherein the data acquisition module is used to obtain data elements from Internet of Things devices and big data sources; the data preprocessing module is used to clean, convert and format the acquired data elements; the model building module is used to construct a demand forecasting model for the preprocessed data elements through Fourier algorithm, autoregressive algorithm and parallel shift method, and continuously adjust and optimize model parameters; the demand forecasting and scheduling plan module is used to obtain the demand forecasting result according to the demand forecasting model and determine the feeding sequence and scheduling plan according to the forecasting result; the inventory warning module is used to set the inventory warning threshold and set the three-level inventory warning mechanism and the corresponding warning strategy according to the threshold; the priority sorting module is used to obtain the order urgency and determine the order priority according to the order urgency, and re-sort the order; the scheduling plan adjustment module is used to adjust the existing scheduling plan; the automatic feeding module is used to perform the feeding task according to the adjusted scheduling plan using automated equipment such as AGV carts and robots.

[0023] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0024] 1. Through Fourier algorithm, autoregressive algorithm and parallel shift method, the order demand in the future period is predicted, thereby realizing efficient material supply and scientific replenishment strategy, ensuring that inventory is always maintained at a reasonable level, and effectively solving the problem of low material supply efficiency caused by insufficient inventory in the existing technology.

[0025] 2. By setting up a multi-level inventory early warning mechanism, corresponding replenishment measures can be taken in time according to different levels of early warnings, thereby achieving the timeliness and effectiveness of inventory management, reducing information asymmetry and delays in the supply chain, and improving the response speed and flexibility of the supply chain.

[0026] 3. By predicting order demand and setting system priorities, we can reasonably arrange the scheduling plans of AGV carts and robots to ensure that during the order processing, resources can be reasonably allocated according to different order characteristics and urgency, and the designated tasks can be completed in the shortest time, thereby realizing priority processing of urgent orders. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 A flow chart of an efficient material feeding intelligent warehousing management method based on the Internet of Things provided in an embodiment of the present application;

[0028] Figure 2 This is a structural diagram of the efficient feeding intelligent warehousing management device based on the Internet of Things provided in an embodiment of the present application. DETAILED DESCRIPTION

[0029] The embodiments of the present application solve the problem of low feeding efficiency in the prior art by providing an efficient feeding intelligent warehousing management method and device based on the Internet of Things, thereby achieving efficient feeding.

[0030] The technical solution in the embodiment of the present application is to solve the above-mentioned problem of low feeding efficiency, and the overall idea is as follows:

[0031] By using predictive analysis technology to collect multi-dimensional information of historical sales data, market trends, and seasonal factors, and using Fourier algorithm, autoregressive algorithm, and parallel shift method to build a prediction model, the demand in the future period is accurately predicted to optimize the supply plan. Different inventory warning thresholds are set according to different seasons, and different levels of warnings are triggered by thresholds. Including first-level warning, second-level warning, and third-level warning. The first-level warning indicates that the inventory is slightly low, and attention should be paid and replenishment should be prepared; the second-level warning indicates that the inventory is low and the replenishment process needs to be started immediately; the third-level warning is the highest level, and the inventory is seriously insufficient. Emergency measures need to be taken to replenish the inventory to cope with inventory changes and ensure stable operations. In this way, a scientific replenishment strategy can be formulated according to the warning level and the speed of incoming materials required. Enable the system to issue a warning in time when the inventory is lower than the safety level, trigger the replenishment process, and calculate the optimal replenishment quantity combined with the predicted demand, to ensure that the inventory can meet future sales needs and avoid insufficient inventory, and the prediction results are used to optimize the supply path and scheduling plan. Use the forecast data to predict the demand distribution in different time periods, so as to reasonably arrange the work of AGV carts and robots, thereby reducing the waiting time caused by insufficient supply and improving operation efficiency. For urgent supply orders, the computer automatically enters the time interval from the submission date required by the order to the current date to determine the urgency. The longer the time interval, the lower the urgency, and the shorter the time interval, the higher the urgency.

[0032] Set the system priority for emergency processing, automatically set high priority for orders with high urgency, and automatically set low priority for orders with low urgency. Orders with the same priority will be rotated on a first-come, first-served basis. This has achieved an efficient solution to the feeding problem.

[0033] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0034] like Figure 1 As shown, it is a flow chart of an efficient material feeding intelligent warehousing management method based on the Internet of Things provided in an embodiment of the present application. The method is applied to an efficient material feeding intelligent warehousing management device based on the Internet of Things. The method includes the following steps: acquiring data elements and preprocessing the data elements; constructing a demand forecasting model based on the preprocessed data elements through Fourier algorithm, autoregressive algorithm and parallel movement method; obtaining demand forecasting results based on the demand forecasting model; determining the feeding sequence and scheduling plan based on the demand forecasting results; acquiring the predicted inventory remaining amount and setting a multi-level inventory early warning mechanism based on the predicted inventory remaining amount; acquiring the order urgency, determining the order priority according to the order urgency and reordering the order sequence; adjusting the scheduling plan according to the reordered order sequence; and using AGV carts and robots to feed according to the scheduling plan.

[0035] In this embodiment, the trolley arranges the scheduling plan by obtaining the demand forecast results and the order urgency, calculates the shortest distance from the trolley to the feeding location, calculates the time required for the trolley on the way to the feeding according to the shortest distance, and calculates the number of trolleys required to complete the feeding within the specified time. The remaining trolleys perform the feeding tasks of other orders according to the same principle in the order of priority. Determine the order priority according to the order urgency and re-sort the order order to prevent the occurrence of new temporary emergency orders due to the failure to update the order order in time. Order delay caused. Adjusting the scheduling plan according to the re-sorted order order is conducive to the trolley to process temporary orders more efficiently. The role of determining the feeding order and scheduling plan for the first time is to plan the urgency and feeding order of the existing orders to ensure the efficient completion of the current order. The role of determining the feeding order and scheduling plan for the second time is to prevent the occurrence of new emergency orders or temporary conditions from affecting the order feeding. The difference between the first determination of the feeding order and scheduling plan and the second determination of the feeding order and scheduling plan is whether there are new emergency orders or temporary conditions. The demand data preprocessing provides a high-quality data basis for subsequent analysis and modeling. Accurate and clean data can improve the performance of the model and make the prediction results more reliable. The demand forecasting model can help enterprises understand the future demand trend in advance, so as to make more reasonable supply and storage arrangements. The demand forecasting results provide a basis for decision-making for enterprises, helping them to formulate more reasonable supply and storage plans to meet market demand. Reasonable supply sequence and scheduling plan can ensure that materials or products are supplied on time and in quantity, reduce waiting time and resource waste, and improve production efficiency. The setting of inventory warning thresholds can help enterprises to understand the inventory status in time, avoid insufficient or excessive inventory, and ensure the continuity and stability of production. The three-level inventory warning mechanism can enable enterprises to manage inventory more finely, take different measures according to different levels of warnings, and effectively deal with inventory risks. If there are unexpected factors affecting the original order sequence during the order completion process. At this time, the system will re-evaluate the urgency of the order according to the unexpected factors, and re-determine the priority and order of the order accordingly, and then adjust the corresponding scheduling plan to avoid production interruptions or delays caused by unexpected factors. Finally, the use of AGV carts and robots to feed can reduce manual operations, improve the accuracy and efficiency of feeding, reduce labor costs, and reduce the occurrence of human errors and safety accidents.

[0036] Furthermore, the data elements are preprocessed, and the preprocessing steps include: data cleaning, data noise reduction, data integration, feature extraction, and data normalization based on the collected data to obtain preprocessed data elements; the data elements include: order urgency, order demand, order profit, latest delivery date, cycle length of historical feed speed, and coefficient of seasonal factors.

[0037] In this embodiment, by obtaining historical data to more accurately reflect the real situation of the enterprise operation process, data cleaning, noise reduction and formatting can remove noise and outliers in the original data to ensure the accuracy and reliability of the data. At the same time, data integration can integrate data from different sources to form a complete data set, which is convenient for subsequent data analysis and processing.

[0038] Furthermore, the efficient material feeding intelligent warehousing management method based on the Internet of Things is characterized in that the demand forecasting model includes a demand quantity forecasting model, and the step of establishing the demand quantity forecasting model includes: using a multi-model fusion method to establish multiple time series forecasting models according to the preprocessed data elements; receiving input data of the forecast time period, inputting it into multiple time series models to predict the demand for the required forecast time period, and using the demand for the forecast time period as output data; comparing the output data with the actual data, and saving the time series forecasting model with the smallest error as the demand quantity forecasting model; and analyzing and learning according to the demand quantity forecasting model to predict the forecast demand and supply trends in a future period.

[0039] In this embodiment, multiple time series forecasting models can be targeted and modeled according to different data characteristics and requirements, so as to more comprehensively capture the changing trend of demand. Error analysis is a commonly used model evaluation method, which evaluates the performance of the model by calculating the difference between the predicted value and the true value. Selecting the model with the smallest error means that the model has a better performance in fitting historical data. The selection of the optimal model helps to reduce the forecast deviation caused by improper model selection. The introduction of Internet of Things technology can realize real-time monitoring and collection of information such as the internal environment of the warehouse and the status of the goods. Combined with the demand forecasting model, it can improve the forecast accuracy and management efficiency.

[0040] Furthermore, the principle of the demand forecasting model is as follows: according to the periodicity, the Fourier series part is decomposed into the sum of a series of sine functions and cosine functions to capture the periodic changes of the data; according to the autoregressive part, the autocorrelation of the time series is captured; according to the moving average part, the random fluctuations in the smoothed data are obtained, and the average value of the specific time steps in the past is calculated as the estimated value of the predicted demand; the influence of the coefficient change of the seasonal factor on the feeding speed is obtained; the predicted demand is obtained based on the autocorrelation of the time series, the estimated value of the predicted demand, and the influence of the coefficient change of the seasonal factor on the feeding speed.

[0041] In this embodiment, the feeding speed is used to reflect the predicted feeding speed of the future time step, so as to facilitate timely inventory replenishment.

[0042]

[0043] Where, VS T+1is the predicted feed rate at the future time step T+1, a n is the coefficient of the corresponding cosine term in the Fourier series, which is used to capture periodic changes, b n It is the coefficient of the corresponding sine term of the Fourier series, which is used to capture periodic changes. N is the number of terms in the Fourier series, Z is the period length of the historical feed rate, S is the correction factor of the feed rate, 2n represents the multiple of the trigonometric function frequency, x represents any point on the trigonometric function, and the value range of x is (0, +∞). π represents the pi. The above feed rate can also be obtained by combining big data with the feed rate of the same event point in previous years and taking the average value. The forecast demand is used to predict the future supply to prevent low feed efficiency caused by insufficient inventory. The forecast demand can also be used to deeply understand the needs and expectations of market players such as consumers and distributors through market research methods, and use economic factors to indirectly infer future market demand by combining industry development trends.

[0044] Demand forecast formula:

[0045]

[0046] Where D T+1 represents the predicted demand corresponding to the future time step T+1, ω represents the influence of demand on the supply speed, and is used to represent the correlation between the predicted supply speed and the predicted demand. ω obtains the order demand and supply speed data of the same industry through big data, and calculates the data using the linear regression method. w 1 is a constant term representing the order demand error.

[0047] Furthermore, the demand forecasting model includes an order urgency forecasting model, and an order urgency forecasting model is established:

[0048]

[0049] In the formula, i represents the order number, y i represents the predicted value of the order urgency of order i, α is the weight of the delivery time interval corresponding to the order urgency calculation, T i is the latest delivery date for order i, T C is the current time, β is the weight of the order demand corresponding to the order urgency calculation, Q i is the demand for order i, Q max is the maximum order demand that the current production system can handle, γ is the weight of the order profit corresponding to the order urgency calculation, P i is the profit of order i, P avg is the average profit of all current orders.

[0050] In this embodiment, P avg The process of obtaining is:

[0051]

[0052] Where P 1 Represents the profit of the first order, P 2 represents the profit of the second order, ..., P r Represents the profit of the rth order, and r represents the total number of orders.

[0053] Furthermore, setting a multi-level inventory warning mechanism includes: setting a multi-level inventory warning mechanism, including a first-level warning, a second-level warning and a third-level warning, corresponding to different degrees of inventory reduction:

[0054] When the predicted inventory remaining amount is within the first limited range, no warning is issued; when the predicted inventory remaining amount is within the second limited range, a first-level warning is issued; when the predicted inventory remaining amount is within the third limited range, a second-level warning is issued; when the predicted inventory remaining amount is within the fourth limited range, a third-level warning is issued.

[0055] In this embodiment, the advantage of setting up a three-level inventory early warning mechanism is that it can take corresponding countermeasures according to different inventory reduction situations to ensure the stability of the enterprise's supply chain and operational continuity. This early warning mechanism not only improves the inventory management efficiency of the enterprise, but also helps to reduce operating costs and enhance the market competitiveness of the enterprise. For example, the first limit range is 500 to 600, the second limit range is 300 to 499, the third limit range is 100 to 299, and the fourth limit range is 0 to 99.

[0056] Furthermore, the calculation formula for the predicted inventory remaining quantity is set as:

[0057]

[0058] In the formula, i represents the order number, A represents the inventory capacity, and Q i is the demand for order i, M i represents the predicted inventory remaining for order i, ω represents the influence of demand on the feeding speed, b is a constant term used to adjust the basic feeding speed, VS T+1 Represents the predicted feed rate at the future time step T+1.

[0059] In this embodiment, the formula can comprehensively consider multiple key factors, including the historical average daily demand, basic inventory turnover days, safety inventory days, replenishment cycle and seasonal factors, so as to obtain a more accurate and comprehensive inventory warning threshold. This helps enterprises to grasp the inventory status more accurately and avoid the risks caused by insufficient or excessive inventory. Secondly, by setting thresholds with different limited ranges, the formula can realize a multi-level warning mechanism. This mechanism can take corresponding countermeasures according to different inventory reduction situations, so as to ensure the operational continuity and supply chain stability of the enterprise. From the first level warning to the third level warning, each level corresponds to a different degree of inventory risk. Enterprises can adjust their inventory strategies in time according to the warning level to avoid potential production interruptions or sales losses. In addition, the formula also takes into account the coefficient variables of seasonal factors, which makes the setting of the warning threshold more in line with the actual situation. The introduction of the coefficient of seasonal factors can reflect the impact of different seasons on inventory demand, making inventory warnings more targeted and accurate so as to better cope with potential market fluctuations.

[0060] Furthermore, the step of determining order priority includes: automatically calculating a time interval based on order information; the time interval is the time interval from the submission date required by the order to the current date; sorting according to the length of the time interval, the longer the time interval, the lower the order urgency, the shorter the time interval, the higher the order urgency, and the same time intervals have the same order urgency; sorting the orders according to their urgency, determining the priority order according to the order urgency order, the higher the order urgency, the higher the order priority, the lower the order urgency, the lower the order priority, orders with the same order urgency have the same priority, and orders with the same priority are executed in order of precedence.

[0061] In this embodiment, priorities are automatically assigned according to the urgency of the orders, so that limited resources can be used to process orders with high urgency first, achieving reasonable allocation and efficient use of resources, and helping to avoid production interruptions and supply chain risks caused by delays.

[0062] Furthermore, adjusting the scheduling plan according to the reordered order sequence includes the following steps: evaluating the planned but unexecuted feeding tasks, first determining whether there are any tasks that are inconsistent with the new order sequence; if not, reordering the new order; if consistent, continuing to execute in the original order, and then determining whether the priority has changed: if so, rearranging the order according to the priority; if not, continuing to execute in the original order; and displaying the adjusted scheduling plan.

[0063] In this embodiment, by obtaining the priority of urgent orders and reordering the orders according to their urgency, the order urgency model can allocate resources more accurately, ensuring that high-priority and urgent orders are processed first, thereby maximizing resource utilization efficiency and avoiding resource waste and cost increase caused by improper scheduling.

[0064] like Figure 2 As shown, it is a structural diagram of an efficient feeding intelligent warehousing management device based on the Internet of Things provided by an embodiment of the present application. The efficient feeding intelligent warehousing management device based on the Internet of Things provided by an embodiment of the present application includes: a data acquisition and preprocessing module, a model building module, a model result acquisition module, a demand feeding and scheduling module, an inventory warning module, an order urgency module, a scheduling plan adjustment module, and an automatic feeding module. Among them, the data acquisition and preprocessing module is used to obtain data elements and preprocess the data elements; the model building module: according to the preprocessed data elements, a demand forecasting model is constructed by Fourier algorithm, autoregressive algorithm and parallel movement method; the model result acquisition module: according to the demand forecasting model, the demand forecasting result is obtained; the demand feeding and scheduling module: according to the demand forecasting result, the feeding sequence and scheduling plan are determined; the inventory warning module: obtains the predicted inventory remaining amount and sets a multi-level inventory warning mechanism according to the predicted inventory remaining amount; the order urgency module: obtains the order urgency, determines the order priority according to the order urgency, and reorders the order sequence; the scheduling plan adjustment module: adjusts the scheduling plan according to the reordered order sequence; the automatic feeding module: according to the scheduling plan, the AGV car and the robot are used to feed.

[0065] In this embodiment, through the coordinated work of various modules, it realizes the whole process management and optimization of the feeding process, and improves the efficiency and accuracy of feeding.

[0066] The technical scheme in the above-mentioned embodiment of the present application has at least the following technical effects or advantages: relative to a warehouse management method and device announced in the invention patent with publication number: CN108074058B, the embodiment of the present application predicts the order demand in the future period through Fourier algorithm, autoregressive algorithm and parallel movement method, thereby realizing a scientific replenishment strategy, ensuring that the inventory is always maintained at a reasonable level, and effectively solving the problem of low feeding efficiency caused by insufficient inventory in the prior art; relative to a material transportation system and warehouse disclosed in the patent application with publication number: CN110046864A, the embodiment of the present application predicts the order demand and sets the system priority, thereby reasonably arranging the scheduling plan of the AGV cart and the robot, ensuring that in the order processing process, resources can be reasonably allocated according to different order characteristics and urgency, and the designated task can be completed in the shortest time, thereby realizing priority processing of urgent orders.

[0067] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0068] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0069] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0070] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0071] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0072] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. An efficient feeding intelligent warehousing management method based on the Internet of Things, characterized in that: The following steps are involved: Acquire data elements and pre-process the data elements; According to the pre-processed data elements, the demand forecasting model is constructed through Fourier algorithm, autoregressive algorithm and parallel shift method; Determine the demand forecast result according to the demand forecast model; Determine the supply sequence and scheduling plan based on demand forecast results; Obtain the predicted inventory remaining quantity and set up a multi-level inventory warning mechanism based on the predicted inventory remaining quantity; Obtain the order urgency, determine the order priority according to the order urgency and re-sort the order sequence; Adjust the dispatch plan according to the reordered order sequence; Use AGV carts and robots to supply materials according to the scheduling plan.

2. The efficient feeding intelligent warehousing management method based on the Internet of Things as claimed in claim 1 is characterized in that: The data elements are preprocessed, and the preprocessing steps include: According to the collected data, data cleaning, data noise reduction, data integration, feature extraction, and data normalization are performed to obtain pre-processed data elements; The data elements include: order urgency, order demand, order profit, latest delivery date, cycle length of historical feed speed and coefficient of seasonal factors.

3. The efficient feeding intelligent warehousing management method based on the Internet of Things as claimed in claim 1 is characterized in that: The demand forecasting model includes a demand quantity forecasting model, and the steps of establishing the demand quantity forecasting model include: The multi-model fusion method is used to establish multiple time series prediction models based on the preprocessed data elements; By receiving input data of a forecast time period, inputting it into a plurality of time series models to forecast the demand in the required forecast time period, and using the demand in the forecast time period as output data; By comparing the output data with the real data, the time series forecasting model with the smallest error is saved as the demand forecasting model; Learn to predict demand and supply trends over a period of time in the future based on demand forecasting model analysis.

4. The efficient material feeding intelligent warehousing management method based on the Internet of Things as claimed in claim 3 is characterized in that: The principle of the demand forecasting model: The Fourier series is partially decomposed into a series of sums of sine and cosine functions according to the periodicity to capture the periodic changes of the data; Capturing the autocorrelation of the time series based on the autoregressive part; The moving average part obtains random fluctuations in the smoothed data and calculates the average value of a specific time step in the past as an estimate of the forecast demand; Obtain the effect of seasonal factor coefficient changes on the feeding rate; The forecast demand is obtained based on the autocorrelation of the time series, the estimated value of the forecast demand, and the impact of the change in the coefficient of seasonal factors on the feeding rate.

5. The efficient material feeding intelligent warehousing management method based on the Internet of Things as claimed in claim 1 is characterized in that: The demand forecasting model includes an order urgency forecasting model, and an order urgency forecasting model is established: In the formula, i represents the order number, y i represents the predicted value of the order urgency of order i, α is the weight of the delivery time interval corresponding to the order urgency calculation, T i is the latest delivery date for order i, T C is the current time, β is the weight of the order demand corresponding to the order urgency calculation, Q i is the demand for order i, Q max is the maximum order demand that the current production system can handle, γ is the weight of the order profit corresponding to the order urgency calculation, P i is the profit of order i, P avg is the average profit of all current orders.

6. The efficient material feeding intelligent warehousing management method based on the Internet of Things as claimed in claim 1 is characterized in that: The multi-level inventory warning mechanism is set up including: A multi-level inventory warning mechanism is set up, including level 1 warning, level 2 warning and level 3 warning, corresponding to different degrees of inventory reduction: When the predicted inventory remaining amount is within the first limited range, no warning is issued; when the predicted inventory remaining amount is within the second limited range, a first-level warning is issued; when the predicted inventory remaining amount is within the third limited range, a second-level warning is issued; when the predicted inventory remaining amount is within the fourth limited range, a third-level warning is issued.

7. The efficient feeding intelligent warehousing management method based on the Internet of Things as claimed in claim 1 is characterized in that: The calculation formula for the predicted inventory remaining quantity is set as: In the formula, i represents the order number, A represents the inventory capacity, and Q i is the demand for order i, M i represents the predicted inventory remaining for order i, ω represents the influence of demand on the feeding speed, b is a constant term used to adjust the basic feeding speed, VS T+1 It represents the predicted feeding rate at the future time step T+1, where T represents the future time step.

8. The efficient material feeding intelligent warehousing management method based on the Internet of Things as claimed in claim 1, characterized in that: The step of determining order priority includes: Automatically calculate the time interval based on the order information; The time interval is the time interval from the submission date of the order requirement to the current date; Sort by time interval. The longer the time interval, the lower the order urgency. The shorter the time interval, the higher the order urgency. If the time interval is the same, the orders have the same urgency. Sort the orders by urgency and determine the priority order based on the urgency of the orders. The higher the order urgency, the higher the order priority, and the lower the order urgency, the lower the order priority. Orders with the same urgency have the same priority, and orders with the same priority are executed in order of precedence.

9. The efficient material feeding intelligent warehousing management method based on the Internet of Things as claimed in claim 1, characterized in that: The step of adjusting the scheduling plan according to the reordered order sequence comprises the following steps: Evaluate the planned but unexecuted supply tasks, first determine whether there are any tasks that do not match the new order sequence; If not, reorder the new order; If they match, continue to execute in the original order and then determine whether the priority has changed: If so, re-arrange the order according to priority; If not, continue to execute according to the original order; The adjusted scheduling plan will be displayed.

10. An efficient material feeding intelligent storage management device based on the Internet of Things, characterized in that: It includes data acquisition and preprocessing module, model building module, model result acquisition module, demand supply and scheduling module, inventory warning module, order urgency module, scheduling plan adjustment module and automatic supply module: The data acquisition and preprocessing module is used to acquire data elements and preprocess the data elements; The model building module: constructs a demand forecasting model based on the preprocessed data elements through Fourier algorithm, autoregressive algorithm and parallel shift method; The model result acquisition module is used to obtain the demand forecast result according to the demand forecast model; The demand-based material supply and scheduling module determines the material supply sequence and scheduling plan based on the demand forecast results; The inventory warning module: obtains the predicted inventory remaining quantity and sets a multi-level inventory warning mechanism according to the predicted inventory remaining quantity; The order urgency module: obtains the order urgency, determines the order priority according to the order urgency and reorders the order sequence; The scheduling plan adjustment module: adjusts the scheduling plan according to the reordered order sequence; The automated feeding module uses AGV carts and robots to feed materials according to the scheduling plan.

Images