KR102340179B1 - Method for providing machine learning based picking location inventory replenishment service using demand forecasting - Google Patents

Abstract

The present invention relates to a method for providing a picking location replenishment service using demand forecasting based on machine learning. The method includes: a step of collecting attribute data including the category, volume, and seasonality of an item loaded in a warehouse; a step of outputting an estimated daily shipment of the item using at least one artificial intelligence algorithm; a step of calculating a maximum inventory quantity by dividing the volume of the picking location in the warehouse by the volume of the item; a step of setting 100% of the estimated daily shipment as a minimum shipment quantity and determining 200% of the maximum inventory quantity as a minimum inventory quantity; a step of extracting the current inventory quantity in the picking location; a step of checking whether the current inventory quantity in the picking location is smaller than the minimum shipment quantity or the minimum inventory quantity; and a step of calculating a replenishment quantity and assigning an inventory replenishment instruction in a case where the current inventory quantity is smaller than the minimum shipment quantity or the minimum inventory quantity.

Description

A method for providing a pick-up location supplementary service using machine learning-based demand forecasting

The present invention relates to a method of providing a picking location replenishment service using machine learning-based demand forecasting, and a platform for performing demand forecasting for inventory management and calculating the stock replenishment quantity in consideration of the area and volume in the picking location and the volume for each item. to provide.

As competition between companies intensifies, the role of logistics centers is becoming increasingly important. The work process of a logistics center is largely divided into warehousing, storage, picking, packing, and shipment types, and among logistics center activities, the picking process is one of the labor-intensive activities that account for half of the logistics warehouse operating cost. Many companies have conducted various studies to increase the operational efficiency of the picking process, but they are divided into research on picking operation methods, research on optimizing the picking movement, and research on item placement methods to increase picking efficiency. It is possible to review all of the above-mentioned measures in the design stage of the distribution center, but the measures that can be applied during center operation are inevitably relatively limited. Recently, with the development of IT technology, real-time exchange of information has become possible, and the change trend of customer needs has also been accelerated. It is a situation in which the arrangement is based on general intuition rather than the scientific arrangement of the city.

At this time, a method of supplementing the picking location in connection with the warehouse management system-based inventory was researched and developed. In No. 10-1847194 (announced on April 09, 2018), the warehouse management system calculates the minimum standard quantity and minimum expected sales volume for products at each picking location, and the warehouse management system counts the current quantity at each picking location Thus, when the current quantity is less than the minimum standard quantity or the current quantity is less than the expected minimum sales volume, a replenishment instruction is issued. is input and creates inventory information by identifying the stock quantity for each item stored in the warehouse Each of the configurations for generating a list and providing it to the business owner is disclosed.

However, in the former case, since the quantity is quantitatively adjusted, if the predicted order quantity is greater than a certain quantity, an inventory shortage occurs and vice versa. In the latter case, it is a configuration that places an order after grasping inventory information, not a system that predicts demand and manages the warehouse. Inventory replenishment in the logistics center is being carried out when the quantity of items in the picking location is actually exhausted, so the picking and replenishment tasks are duplicated and it is difficult to preemptively respond, which is a factor that reduces work efficiency, productivity and profitability. . Accordingly, research and development of a platform that can preemptively respond to inventory exhaustion and separate replenishment and picking tasks is required by performing demand forecasting and replenishment work using artificial intelligence algorithms.

In one embodiment of the present invention, in order to set the standard value of replenishment of inventory, the attribute and volume of the item are identified, the expected daily shipment quantity is calculated for each item using machine learning, the maximum inventory quantity is calculated for each item, and the maximum Calculating the stock replenishment operation execution standard based on the storage quantity and expected shipment quantity, extracting the current inventory quantity of the picking location, and calculating the replenishment quantity if the current inventory quantity of the picking location is less than the minimum expected shipment quantity or the minimum storage quantity; After selecting a replenishment location to move the item, it is possible to provide a picking location replenishment service providing system using machine learning-based demand forecasting, which calculates the replenishment quantity as a unit and allocates an inventory replenishment instruction. However, the technical task to be achieved by the present embodiment is not limited to the technical task as described above, and other technical tasks may exist.

As a technical means for achieving the above technical problem, an embodiment of the present invention collects attribute data including category, volume and seasonality of an item loaded in a distribution warehouse, using at least one artificial intelligence algorithm outputting the expected daily shipment volume of the item, dividing the volume of the Picking Location in the logistics warehouse by the item volume to calculate the maximum inventory quantity setting, determining 2 times the maximum inventory quantity as the minimum inventory quantity, extracting the current inventory quantity in the picking location, and checking whether the current inventory quantity in the picking location is less than the minimum shipment quantity or the minimum inventory quantity and when the current inventory quantity is less than the minimum shipment quantity or the minimum inventory quantity, calculating the replenishment quantity and allocating a replenishment order.

According to any one of the above-described problem solving means of the present invention, in order to set the standard value of replenishment of inventory, the properties and volume of the item are identified, the expected daily shipment amount is calculated for each item by using machine learning, and the maximum stock quantity is determined Calculation for each item, calculating the execution standard value of replenishment operation based on the maximum storage quantity and expected shipment quantity, extracting the current inventory quantity at the picking location, and when the current inventory quantity at the picking location is less than the minimum expected shipment quantity or the minimum storage quantity After calculating the replenishment quantity and selecting a replenishment location to move the item, by calculating the replenishment quantity as a unit and assigning an inventory replenishment instruction, it is possible to reduce the number of replenishment tasks and increase work efficiency.

1 is a view for explaining a system for providing a supplementary picking location service using machine learning-based demand forecasting according to an embodiment of the present invention.
FIG. 2 is a block diagram illustrating a supplementary service providing server included in the system of FIG. 1 .
3 is a diagram for explaining an embodiment in which a picking location supplementary service using machine learning-based demand prediction according to an embodiment of the present invention is implemented.
4 is an operation flowchart for explaining a method of providing a supplemental picking location service using machine learning-based demand forecasting according to an embodiment of the present invention.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those of ordinary skill in the art can easily implement them. However, the present invention may be embodied in several different forms and is not limited to the embodiments described herein. And in order to clearly explain the present invention in the drawings, parts irrelevant to the description are omitted, and similar reference numerals are attached to similar parts throughout the specification.

Throughout the specification, when a part is "connected" with another part, this includes not only the case of being "directly connected" but also the case of being "electrically connected" with another element interposed therebetween. . In addition, when a part "includes" a certain component, it means that other components may be further included, rather than excluding other components, unless otherwise stated, and one or more other features However, it is to be understood that the existence or addition of numbers, steps, operations, components, parts, or combinations thereof is not precluded in advance.

The terms "about", "substantially", etc. to the extent used throughout the specification are used in or close to the numerical value when manufacturing and material tolerances inherent in the stated meaning are presented, and are intended to enhance the understanding of the present invention. To help, precise or absolute figures are used to prevent unfair use by unconscionable infringers of the stated disclosure. As used throughout the specification of the present invention, the term "step of (to)" or "step of" does not mean "step for".

In this specification, a "part" includes a unit realized by hardware, a unit realized by software, and a unit realized using both. In addition, one unit may be implemented using two or more hardware, and two or more units may be implemented by one hardware. Meanwhile, '~ unit' is not limited to software or hardware, and '~ unit' may be configured to be in an addressable storage medium or to reproduce one or more processors. Thus, as an example, '~' denotes components such as software components, object-oriented software components, class components, and task components, and processes, functions, properties, and procedures. , subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays and variables. The functions provided in the components and '~ units' may be combined into a smaller number of components and '~ units' or further separated into additional components and '~ units'. In addition, components and '~ units' may be implemented to play one or more CPUs in a device or secure multimedia card.

Some of the operations or functions described as being performed by the terminal, apparatus, or device in the present specification may be performed instead of by a server connected to the terminal, apparatus, or device. Similarly, some of the operations or functions described as being performed by the server may also be performed in a terminal, apparatus, or device connected to the server.

In this specification, some of the operations or functions described as mapping or matching with the terminal means mapping or matching the terminal's unique number or personal identification information, which is the identification data of the terminal. can be interpreted as

Hereinafter, the present invention will be described in detail with reference to the accompanying drawings.

1 is a view for explaining a system for providing a supplementary picking location service using machine learning-based demand forecasting according to an embodiment of the present invention. Referring to FIG. 1 , the picking location supplementary service providing system 1 using machine learning-based demand forecasting is at least one user terminal 100 , a supplementary service providing server 300 , and at least one employee terminal 400 . may include However, since the picking location supplementary service providing system 1 using the machine learning-based demand prediction of FIG. 1 is only an embodiment of the present invention, the present invention is not limitedly interpreted through FIG. 1 .

At this time, each component of FIG. 1 is generally connected through a network (Network, 200). For example, as shown in FIG. 1 , at least one user terminal 100 may be connected to the supplementary service providing server 300 through the network 200 . And, the supplementary service providing server 300 may be connected to at least one user terminal 100 and at least one employee terminal 400 through the network 200 . In addition, at least one employee terminal 400 may be connected to the supplementary service providing server 300 through the network 200 .

Here, the network refers to a connection structure in which information exchange is possible between each node, such as a plurality of terminals and servers, and an example of such a network includes a local area network (LAN), a wide area network (WAN: Wide Area Network), the Internet (WWW: World Wide Web), wired and wireless data communication networks, telephone networks, wired and wireless television networks, and the like. Examples of wireless data communication networks include 3G, 4G, 5G, 3rd Generation Partnership Project (3GPP), 5th Generation Partnership Project (5GPP), Long Term Evolution (LTE), World Interoperability for Microwave Access (WIMAX), Wi-Fi (Wi-Fi) , Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network), RF (Radio Frequency), Bluetooth (Bluetooth) network, NFC ( Near-Field Communication) networks, satellite broadcast networks, analog broadcast networks, Digital Multimedia Broadcasting (DMB) networks, and the like are included, but are not limited thereto.

In the following, the term at least one is defined as a term including the singular and the plural, and even if the at least one term does not exist, each element may exist in the singular or plural, and may mean the singular or plural. it will be self-evident In addition, that each component is provided in singular or plural may be changed according to embodiments.

At least one user terminal 100, a terminal such as a seller who requests a logistics service using a web page, an app page, a program or an application related to a picking location supplement service using machine learning-based demand prediction and reports the process and results can be

Here, the at least one user terminal 100 may be implemented as a computer that can access a remote server or terminal through a network. Here, the computer may include, for example, navigation, a laptop equipped with a web browser, a desktop, and a laptop. In this case, the at least one user terminal 100 may be implemented as a terminal capable of accessing a remote server or terminal through a network. At least one user terminal 100 is, for example, as a wireless communication device that guarantees portability and mobility, navigation, PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS(Personal Handyphone System), PDA(Personal Digital Assistant), IMT(International Mobile Telecommunication)-2000, CDMA(Code Division Multiple Access)-2000, W-CDMA(W-Code Division Multiple Access), Wibro(Wireless Broadband Internet) ) terminal, a smart phone, a smart pad, a tablet PC, etc. may include all kinds of handheld-based wireless communication devices.

The supplementary service providing server 300 may be a server that provides a picking location supplementary service web page, an app page, a program or an application using machine learning-based demand forecasting. In addition, the supplementary service providing server 300 may be a server receiving a request for a logistics service from the user terminal 100 . The supplementary service providing server 300 may be a server that performs demand forecasting based on machine learning for inventory management in a warehouse management system, and based on the volume of the picking location in the warehouse and the volume of each item To calculate the replenishment quantity to be replenished with inventory, it may be a server that allocates replenishment tasks to the employee terminal 400 .

Here, the supplementary service providing server 300 may be implemented as a computer capable of accessing a remote server or terminal through a network. Here, the computer may include, for example, navigation, a laptop equipped with a web browser, a desktop, and a laptop.

The at least one employee terminal 400 may be a terminal of a warehouse employee who performs replenishment work using a web page, an app page, a program or an application related to a picking location supplementation service using machine learning-based demand forecasting.

Here, at least one employee terminal 400 may be implemented as a computer that can connect to a remote server or terminal through a network. Here, the computer may include, for example, navigation, a laptop equipped with a web browser, a desktop, and a laptop. In this case, at least one employee terminal 400 may be implemented as a terminal that can connect to a remote server or terminal through a network. At least one employee terminal 400, for example, as a wireless communication device that is guaranteed portability and mobility, navigation, PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS(Personal Handyphone System), PDA(Personal Digital Assistant), IMT(International Mobile Telecommunication)-2000, CDMA(Code Division Multiple Access)-2000, W-CDMA(W-Code Division Multiple Access), Wibro(Wireless Broadband Internet) ) terminal, a smart phone, a smart pad, a tablet PC, etc. may include all kinds of handheld-based wireless communication devices.

2 is a block diagram illustrating a supplementary service providing server included in the system of FIG. 1, and FIG. 3 is an embodiment in which a picking location supplementary service using machine learning-based demand forecasting according to an embodiment of the present invention is implemented. It is a figure for demonstrating an example.

Referring to FIG. 2 , the supplementary service providing server 300 includes a collection unit 310 , an output unit 320 , a calculation unit 330 , a determination unit 340 , an extraction unit 350 , and a confirmation unit 360 . , an allocator 370 and an artificial intelligence unit 380 may be included.

A supplementary service providing server 300 according to an embodiment of the present invention or another server (not shown) operating in conjunction with at least one user terminal 100 and at least one employee terminal 400 machine learning-based demand forecasting When transmitting a picking location supplement service application, program, app page, web page, etc. using You can install or open service applications, programs, app pages, web pages, etc. In addition, the service program may be driven in at least one user terminal 100 and at least one employee terminal 400 by using a script executed in a web browser. Here, the web browser is a program that enables the use of a web (WWW: World Wide Web) service, and refers to a program that receives and displays hypertext written in HTML (Hyper Text Mark-up Language), for example, Netscape. , Explorer, Chrome, and the like. In addition, the application means an application on the terminal, for example, includes an app (App) executed in a mobile terminal (smartphone).

Referring to FIG. 2 , the collection unit 310 may collect attribute data including categories, volumes, and seasonality of items loaded in the distribution warehouse. Of course, the attribute data is not limited to those listed

The output unit 320 may output an estimated daily shipment amount of the item using at least one artificial intelligence algorithm. The output unit 320 may collect sales information, weather information, and day information to predict the type and quantity of items (products) to be consumed using a pre-established consumption prediction algorithm. For example, suppose that an online shopping mall that sells dog products sells Royal Canin food, dog clothes, padding, and dried sweet potato snacks. It is assumed that meteorological data are used as independent variables for correlation analysis and prediction models. It is assumed that elements with low correlation with sales are excluded, elements that are difficult for users to secure when the developed forecasting model is actually operated are excluded, and only representative elements are selected and forecasted for elements with overlap between weather elements. .

The meteorological factor may be, for example, average temperature, precipitation duration, daily precipitation, average wind speed, average relative humidity, average sea level pressure, solar radiation, daily deepest snowfall, average total cloudiness, fog duration, and the like. Among dog products, dog padding is generally in high demand in winter and shows a clear trend of seasonal fluctuations in summer. If this trend can be seen in the distribution of weekly fluctuations and monthly average fluctuations, it can be inferred that the sales volume of puppy padding is highly correlated with temperature fluctuations. However, if it is estimated that other weather factors or other variables besides temperature are also affected by the large daily fluctuations at the same time, other variables other than the meteorological factors may be considered.

The daily sales forecasting model of dog products can be grouped into weekdays and weekends. After analyzing the correlation coefficient between the sales volume of dog products and the total sales of other items and weather factors, a multiple regression model can be developed focusing on variables with large correlation coefficient values, and the entire period of Monday to Saturday is developed into one model. After determining the coefficient of determination of the model divided into weekdays and weekends, the better one can be set as the model. Among the independent variables of the weekday and weekend forecasting models, the meteorological factors may be temperature, solar radiation, and clouds, and may include day-of-week variables. In the weekend model, the sales volume of the previous weekend was included in the independent variable, but in the weekday model, the increase in the coefficient of determination of the sales variable one day before is small and the response time is short when operating the forecasting model, so it can be excluded because of the low availability. At this time, predictive models for other items can be developed, and different coefficients of determination and independent variables can be shown for each item.

Alternatively, since data that changes according to time series are analyzed, the ARIMA time series research model can be used in consideration of this. For example, based on online order data, the sales of dog products by item that occurred in the online shopping mall called Dog Food King for the past 5 years are estimated (Forecasting) can do. To this end, by using the ARIMA-Intervention, one of the time series analysis techniques, the major time series influence variables that are expected to affect the sales of dog products can be classified and the extent of their change can be estimated. It is possible to estimate the monthly or daily sales of dog products that are expected to occur.

In the time series analysis for the ARIMA-intervention model, major events that are judged to have influenced the sales of each online shopping mall by time in the past are applied as an intervention variable, and the effect can be reflected in the overall demand. The ARIMA-intervention model can use a variety of observations for each time point. In addition, it is evaluated as a multivariate time series forecasting model that can structurally measure external shocks and demands such as specific events. For this reason, it is possible to solve the problem that it is difficult to measure the structural and influence of demand, which has been pointed out as a disadvantage of the time series analysis method. The ARIMA-intervention model is evaluated as a model that overcomes the shortcomings of the time series model by presenting the influence coefficient for each intervention event (event), and its predictive power is high.

Regression analysis is one of the statistical techniques mainly used in data prediction. However, in explaining or forecasting future demand for each online shopping mall using regression analysis, income variables (such as real or nominal income or disposable income or GDP), exchange rates (such as KRW/USD or KRW/YEN or KRW/CNY), or It is recognized that independent variables such as international oil prices do not satisfactorily explain market demand fluctuations. For example, natural disasters or man-made national policy matters such as the case of a rapid increase in online shopping due to Corona (COVID-19), etc. because it cannot be provided.

The ARIMA time series research model analyzes time series data divided by time lag units, constructs the relationship into a model, and predicts future demand or data through the time series model (classical model) and stochastic model. Time series models can be divided into two types. Classical time series analysis methods include moving average method, exponential smoothing method, and decomposition method. The probabilistic time series model, which can be called a modern model, is a research modeled by introducing a stochastic method to time series data (original data), and is also known as the ARIMA analysis method. ARIMA analysis model refers to an analysis model constructed by combining A.R. (Auto Regression) and M.A. (Moving Average).

The autoregression model is a research model that assumes that there is a correlation between the data at every moment for the data x(t) for each lag unit. However, white noise exists in the correlation between data. There is no temporal correlation in white noise. An autoregressive analysis model can be estimated through the Yule-Walker equation under the assumption that the observation data at the present time can be expressed in the form of a function of the data values observed in the past. The moving average analysis model assumes that the current observation value can be expressed in the form of a linear combination of white noises. An Auto Regressive-Moving Average analysis model can also be used by combining autoregressive and moving average models. Using these models, a probabilistic time series analysis model was established as the most stable prediction method, and it is Box-Jenkins' ARIMA time series analysis model that established this methodology. ARIMA time series analysis is applied in various academic and industrial fields, and it is a representative time series analysis method in the field of predicting future demand.

A three-stage research model exists for time series analysis. The first stage is the stage in which the researcher identifies a tentative model from the time series data. The second step is to estimate and test the coefficients of the previously identified time series analysis model (Estimation and Testing). In the parameter estimation and verification stage, iterative calculations and verification of the statistical program for the fit of models and coefficients are performed. This is because it is possible to prevent the intervention of a researcher in advance and improve the reliability of analysis results through repeated calculations and verification. Finally, the suitability of the selected model is diagnosed (Diagnostic Checking), and the diagnostic process is repeated until a satisfactory model is selected. In one embodiment of the present invention, it can be set based on such a three-step model.

<ARIMA Time Series-Intervention Model>

As mentioned above, time-series data related to online shopping mall demand are greatly affected by external political or economic events such as natural disasters (earthquake, tsunami, typhoon, corona (COVID-19), outbreak of war, and the Korean War). External events are called intervention variables in the ARIMA research model. Intervention variables play a difficult role in designing the research model because they cause rapid changes in the normal flow and stochastic structure of time series data. Therefore, these external shocks Using the ARIMA intervention model that can include factors as variables in the research model can greatly improve the predictive power of future demand The ARIMA intervention model is called the ARIMA extended model because it includes external shocks as variables. .

If there is time series data Yt, which is raw data, and external intervention occurs M times, the ARIMA intervention model is as Equation 1 below.

At this time, C = constant term, αi = coefficient of Xi,t, Nt = error term, and the error term can be expressed as ARIMA(p,d,q)(P,D,Q)12 as follows.

D is the number of seasonal differences, d is the number of non-seasonal differences, φp(B) is the non-seasonal AR model, Φp(Bs) is the seasonal AR model, θq(B) is the non-seasonal MA model, ΘQ(Bs) is the seasonal MA model , εt is an error term (White Noise) or the same as in Equation 4 below.

Substituting Equation 4 into Equation 1, it can be defined as Equation 5 below.

In general, intervention variables can be divided into two types: Pulse intervention, which is an event that only temporarily affects the dependent variable, and Step intervention, which is an event that continuously affects the dependent variable. If it is assumed that the pulse intervention occurred during time t = i, the pulse variable Xi,t is defined as

In this case, Xi,t is a dichotomous variable, meaning that Xi,t is intervened only at time i, Xi,t = 0 before time i, Xi,t =1 at time i, Xi,t = again after time i becomes 0. If it is assumed that the step intervention occurred during time t = i, the step variable Xi,t is defined as follows.

The step variable function Xi,t means that the intervention of an external event occurring at a certain point i continues to occur even after that. This is also a dichotomous variable, meaning that Xi,t intervenes at time i and thereafter. Therefore, Xi,t = 0 before time i, Xi,t=1 at time i, and Xi,t = 0 after time i.

The analysis procedure of the ARIMA-intervention model predicts the future using the model finally selected after the above-mentioned model identification, estimation and verification, and model diagnosis. In the identification step, it is possible to determine whether the data is normal or not through a sequential diagram of the data, an autocorrelation function (ACF), a partial autocorrelation function (PACF), and the like. To this end, the difference (d), AR(p), and MA(q) orders may be determined after determining whether the data is a difference or a log transformation.

At this stage, several tentative research models can be selected, and the most appropriate time series analysis model can be selected through estimation and validation and finally model diagnosis. It is possible to determine the parameters and coefficients of the model identified in the estimation step of the model. Determine the values of p autoregression (AR) parameters φ1, φ2,...,φp and q moving average (MA) parameters θ1, θ2,...,θq for the identified model, and calculate the t values of the parameters. It is a step to determine whether it is significant through

In the final stage, model diagnosis, it is verified whether the autocorrelation coefficient value of ACF and the autocorrelation coefficient value of PACF of the model that passed the goodness of fit sufficiently converge to zero. If there is a significance level of 5% for both ACF and PACF, at least one of the lag autocorrelations may exceed this threshold. After the three-step analysis process is complete, predictions can be made.

<Data collection>

For example, suppose you want to collect monthly online sales data from January 2018 to January 2021 of a merchant named Dog Food King (a shopping mall specializing in dog products) using time series data. At this time, cat products may exist in addition to dog products, but cat products may be excluded if it is assumed that the dog food king mainly focuses on dog products. Prior to ARIMA analysis, it is possible to identify whether the monthly sales data for dog products are normal. In order to predict future sales, it is necessary to find and remove abnormalities such as seasonality, and to find stable and fixed trends. For example, raw data is a time series sequence chart of the dog food king's monthly sales of dog products. If there is also a phenomenon of sharp decline in sales, after confirming this trend, seasonal difference and non-seasonal difference can be implemented once. At this time, it can be confirmed that the time series data, which is the raw data, does not show an increase any more and shows a steady state. After performing data difference, autocorrelation function and partial autocorrelation function can be analyzed to determine the ARIMA p, d, and q order numbers. MA (moving average) order q can be determined through the auto correlation function, MA (moving average) order q can be determined through the auto correlation function, and AR (autoregression) order p can be discriminated through a partial autocorrelation function.

After examining the short-term lag of the graphs of the autocorrelation function and partial autocorrelation function, if it is not possible to confirm that the spike protrudes outside the confidence interval, and does not protrude outside the confidence interval of the graph of the autocorrelation function and partial autocorrelation function, MA The ARIMA(0,1,0)(0,1,0) model in which the order of (0) and AR(0) is determined and the scaffolding procedure and the seasonal difference are each 1 can be set as the final model. In addition, the intervention variable can be included in the ARIMA model, and the intervention variable can use the phenomenon of increasing online demand due to the phased distance of the corona (COVID-19).

Also, the accuracy of the estimated value of the ARIMA intervention model can be measured through the process of reviewing the actual value and the prediction error. For example, you can use the MAPE goodness-of-fit coefficient, where MAPE means Mean Absolute Percentage Error. The MAPE goodness-of-fit coefficient can interpret the goodness-of-fit for each interval. If the MAPE value comparing the prediction error between the measured value and the predicted value is less than 5%, it appears and it can be judged that it is showing excellent predictive power. In addition, if the residuals of the autocorrelation function and the partial autocorrelation function are all within the 95% confidence interval, it can be analyzed as satisfying the white noise condition. The output unit 320 may predict the order quantity based on the type, volume, and weight of the inventory. At this time, after learning a pattern according to online sales data through deep learning, automatic inventory replenishment can be performed based on the predicted type and quantity of dog products and the learned purchase pattern. Of course, various methods other than the above-described method may be used.

The calculator 330 may calculate the maximum stock quantity by dividing the volume of the picking location in the distribution warehouse by the volume of the item. In this case, the volume may mean a volume in which an item (product) can be loaded. For example, even if there is a picking location with width X, height Y, and height Z, not all of these volumes and areas can be used. There is a limit to the height that can be stacked, and because items are loaded on a picking rack such as a shelf, not all XYZs can be used. Of course, if the picking station is equipped with a full stacking system in XYZ, it can also be stacked to use all of this volume and area.

The determining unit 340 may set a first time of the expected daily shipment quantity as the minimum shipment quantity, and determine a second time of the maximum inventory quantity as the minimum inventory quantity. For example, when the item is a dried sweet potato and the expected daily shipment amount of the dried sweet potato is 100, the minimum shipment quantity is 300 pieces. And, if the maximum stock quantity is 500 pieces, 1/2, that is, 250 pieces, may be determined as the minimum stock quantity.

The extraction unit 350 may extract the current inventory quantity in the picking location. Continuing the above example, if there are currently 50 dried sweet potatoes at the picking location, 50 is the current stock.

The check unit 360 may check whether the current inventory quantity in the picking location is smaller than the minimum shipment quantity or the minimum inventory quantity. Continuing to cite the above example, the current stock quantity is 50 pieces, the minimum shipment quantity is 300 pieces, and the minimum stock quantity is 250 pieces. At this time, since the conditional expression is or (OR operator), it is necessary to check whether 50 is less than 300 or 50 is less than 250. In other words, if any one (minimum shipment quantity, minimum inventory quantity) is greater than the current inventory quantity, it means that replenishment work, that is, replenishment of the inventory is required. Conversely, if the current inventory quantity is greater than the minimum shipment quantity and (AND operator) the minimum inventory quantity, there is no need to place an order, and calculating the replenishment quantity is completed. If the current stock quantity is 301 pieces, the flow is terminated without calculating the replenishment quantity for the stock because it becomes larger than the minimum shipment quantity of 300 pieces or the minimum stock quantity of 250 pieces.

The allocator 370, when the current inventory quantity is less than the minimum shipment quantity or the minimum inventory quantity, calculates the replenishment quantity and allocates the inventory replenishment instruction. When the current inventory quantity in the allocator 370 is less than the minimum shipment quantity or the minimum inventory quantity, when calculating the replenishment quantity and allocating the replenishment order, when calculating the replenishment quantity, the difference between the maximum inventory quantity and the current inventory quantity It can be calculated as the replenishment quantity to replenish the inventory. In addition, the allocator 370 may select a replenishment location to move the item after calculating the replenishment quantity, and when replenishing inventory among a plurality of replenishment locations based on attribute data including the expiration date and stock date of each item You can choose a supplemental location from which to pick up items. And, the allocator 370, when calculating the replenishment quantity, may be calculated in units of pallets or outer boxes according to the storage form of the item to be replenished. In this case, a pallet is a generic term for a cargo carrier made of wood or plastic used to move cargo from a warehouse to a forklift.

The artificial intelligence unit 380 learns at least one artificial intelligence algorithm before collecting the attribute data including the category, volume, and seasonality of the item loaded in the logistics warehouse in the collection unit 310 to learn one day of the item. It can be modeled to calculate expected shipments. In this case, the at least one artificial intelligence algorithm may be machine learning. When the upper and lower concepts are defined, it is the same as [Machine Learning (Higher Concept)>Artificial Intelligence Algorithm>Deep Learning (Subconcept)]. In this case, the input data input for modeling the at least one artificial intelligence algorithm may include a seasonal value of an item, whether an event is in progress, a large category category, a small category category, an annual data amount of shipment, and a day value for each shipment amount. Here, in order to model an artificial intelligence algorithm, the process of [input data collection-preprocessing-learning dataset-learning-test-output] is passed, and learning data for modeling of at least one artificial intelligence algorithm for creating a learning dataset The set (DataSet) may be generated by calculating the expected shipments for a total of 30 days in units of the expected shipments per day in order to verify the change in shipments according to the day of the week and seasons, and verifying it by comparing it with the actual shipments. The output data output from the at least one artificial intelligence algorithm may be a 3-day expected shipment amount output at a time when learning is performed based on the input data of the item.

In addition, an embodiment of the present invention collects the difference between the predicted order quantity and the actual order quantity ordered from the at least one user terminal 100 and corrects the error with RMSLE (Root Mean Squared Logarithmic Error) that penalizes Under Estimation can That is, RMSLE gives a greater penalty to under estimation than over estimation, and a larger penalty may be given when the predicted value is smaller than the actual value than when the predicted value is larger than the actual value. For example, when predicted value = 600, actual value = 1,000, RMSE = 400, RMSLE = 0.510, when predicted value = 1,400, actual value = 1,000, RMSE = 400, RMSLE = 0.33. The difference between the predicted value and the actual value is 400 in both cases, and the RMSE value is the same for either Over Estimation or Under Estimation, but the RMSLE is under Estimation, that is, when the predicted value is smaller than the actual value, a higher penalty is given. If you predicted 300 pieces when ordering an item called dried sweet potatoes and you actually needed only 200 pieces, you can leave 100 pieces as a spare. Accordingly, using RMSLE rather than RMSE may be more efficient in inventory management. At this time, since the equation of RMSLE is the same as the known one, a description thereof will be omitted.

Hereinafter, an operation process according to the configuration of the supplementary service providing server of FIG. 2 will be described in detail with reference to FIGS. 3 and 4 as an example. However, it will be apparent that the embodiment is only one of various embodiments of the present invention and is not limited thereto.

Referring to FIG. 3 , it is a view showing a supplementary service according to an embodiment of the present invention as a flow. The collection unit 310 of the supplementary service providing server 300 includes categories of individual items required for demand forecasting in step S3100 and Attribute data including seasonality is collected, and the volume of the item is measured to calculate the maximum stock quantity (S) for each picking location. At this time, in FIG. 3 , in order to avoid misunderstanding and confusion of each parameter, alphabetic identifiers are given and described. Here, the output unit 320 of the supplementary service providing server 300 calculates the expected daily shipment amount (A) by using machine learning after comparing the similarity between the attribute data with the existing item in the case of a new item in step S3200 And, in the case of existing items, the expected daily shipment amount (A) is output through machine learning based on the attribute data and the previously shipped shipment amount.

In step S3300, the calculator 330 of the supplementary service providing server 300 calculates the maximum inventory quantity (S) by dividing the volume (Vp) of the picking location by the volume (Vi) of the item, and in step S3400, the supplementary service providing server ( The determination unit 340 of 300) determines 3 matches of the expected daily shipment amount (A) calculated by machine learning as the minimum shipment quantity (Mo), and 50% of the maximum inventory quantity calculated based on the volume is the minimum inventory Set in quantity (Ms).

In step S3500, the extraction unit 350 of the replenishment service providing server 300 extracts the current inventory quantity Sc of the picking location for each item at the time of replenishment of stock, and the confirmation unit 360 in step S3600, picking It is determined whether the current inventory quantity Sc of the location is smaller than the minimum shipment quantity Mo or the minimum inventory quantity Ms. At this time, the confirmation unit 360, if the current inventory quantity Sc is greater than the minimum shipment quantity Mo and the minimum inventory quantity Ms, it does not calculate the replenishment quantity. In addition, the allocation unit 370 of the replenishment service providing server 300 in step S3700, the difference (S-Sc) between the maximum stock quantity (S) and the current inventory quantity (Sc) to replenish the stock replenishment quantity (C) and the allocator 370 of the replenishment service providing server 300 in step S3800, based on the attribute data including the expiration date or stock date of the item, a replenishment location to bring the item from among a plurality of replenishment locations when replenishing stock to select

In step S3900, the allocation unit 370 of the supplementary service providing server 300 calculates the replenishment quantity (C) in units such as pallets or outer boxes according to the storage form of the item, and in step S3910, the supplementary service providing server ( 300), the allocation unit 370, when allocating supplementary work, transmits the unit (EA) quantity and the unit conversion quantity at the same time so that the worker selects an efficient supplementation method.

The details that have not been described with respect to the method of providing a supplemental picking location service using the machine learning-based demand prediction of FIGS. 2 and 3 are described above with respect to the method of providing a supplemental picking location service using the machine learning-based demand forecasting through FIG. 1. Since it is the same as the content or can be easily inferred from the described content, the following description will be omitted.

4 is a diagram illustrating a process in which data is transmitted/received between components included in the system for providing a pick-up location supplementary service using the machine learning-based demand prediction of FIG. 1 according to an embodiment of the present invention. Hereinafter, an example of a process in which data is transmitted and received between the respective components will be described with reference to FIG. 4 , but the present application is not limited to such an embodiment, and the example shown in FIG. 4 according to the various embodiments described above will be described. It is apparent to those skilled in the art that the data transmission/reception process may be changed.

Referring to FIG. 4 , the supplementary service providing server collects attribute data including category, volume, and seasonality of items loaded in the distribution warehouse ( S4100 ).

Then, the supplementary service providing server outputs the expected daily shipment amount of the item using at least one artificial intelligence algorithm (S4200), and divides the volume of the Picking Location in the logistics warehouse by the volume of the item to the maximum stock quantity is calculated (S4300).

In addition, the replenishment service providing server sets the first time (N) of the expected daily shipment quantity as the minimum shipment quantity, and determines the second time (M) of the maximum inventory quantity as the minimum inventory quantity (S4400), and the picking location My current inventory quantity is extracted (S4500). And, the replenishment service providing server checks whether the current stock quantity in the picking location is less than the minimum shipment quantity or the minimum stock quantity (S4600), and if the current inventory quantity is less than the minimum shipment quantity or the minimum stock quantity, the replenishment quantity Calculates and allocates an inventory replenishment instruction (S4700).

The order between the above-described steps ( S4100 to S4700 ) is merely an example and is not limited thereto. That is, the order between the above-described steps S4100 to S4700 may be mutually changed, and some of these steps may be simultaneously executed or deleted.

Matters that have not been described with respect to the method of providing a picking location supplementary service using the machine learning-based demand prediction of FIG. Since it is the same as the content or can be easily inferred from the described content, the following description will be omitted.

The method of providing a picking location supplementary service using machine learning-based demand forecasting according to an embodiment described through FIG. 4 is in the form of a recording medium including instructions executable by a computer, such as an application or program module executed by a computer can also be implemented. Computer-readable media can be any available media that can be accessed by a computer and includes both volatile and nonvolatile media, removable and non-removable media. Also, computer-readable media may include all computer storage media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data.

The method for providing a picking location supplementary service using machine learning-based demand forecasting according to an embodiment of the present invention described above includes an application basically installed in a terminal (which may include a program included in a platform or operating system basically installed in the terminal) ), and may be executed by an application (ie, a program) installed directly on the master terminal by a user through an application providing server such as an application store server, an application, or a web server related to the corresponding service. In this sense, the method for providing a picking location supplementary service using machine learning-based demand forecasting according to an embodiment of the present invention described above is implemented as an application (ie, program) installed in a terminal or installed directly by a user and installed in the terminal. It may be recorded on a computer-readable recording medium, such as.

The above description of the present invention is for illustration, and those of ordinary skill in the art to which the present invention pertains can understand that it can be easily modified into other specific forms without changing the technical spirit or essential features of the present invention. will be. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive. For example, each component described as a single type may be implemented in a dispersed form, and likewise components described as distributed may be implemented in a combined form.

The scope of the present invention is indicated by the following claims rather than the above detailed description, and all changes or modifications derived from the meaning and scope of the claims and their equivalent concepts should be interpreted as being included in the scope of the present invention. do.

Claims (5)

In the supplementary service providing method executed in the supplementary service providing server,
Collecting attribute data including category, volume, and seasonality of the items loaded in the warehouse;
outputting an expected daily shipment amount of the item using at least one artificial intelligence algorithm;
calculating a maximum inventory quantity by dividing the volume of a picking location in the warehouse by the volume of the item;
setting a first time (Times) of the expected daily shipment quantity as a minimum shipment quantity, and determining a second time of the maximum inventory quantity as a minimum inventory quantity;
extracting the current inventory quantity in the picking location;
checking whether the current inventory quantity in the picking location is smaller than the minimum shipment quantity or the minimum inventory quantity; and
If the current inventory quantity is less than the minimum shipment quantity or the minimum inventory quantity, calculating a replenishment quantity and allocating an inventory replenishment instruction;
including,
The at least one artificial intelligence algorithm is a picking location supplement service providing method using machine learning-based demand forecasting, characterized in that it includes machine learning.
The method of claim 1,
In the step of calculating the replenishment quantity and allocating the inventory replenishment instruction when the current inventory quantity is less than the minimum shipment quantity or the minimum inventory quantity,
When calculating the replenishment quantity, calculating the difference between the maximum inventory quantity and the current inventory quantity as a replenishment quantity to replenish the inventory;
Picking location supplementary service providing method using machine learning-based demand forecasting, characterized in that it comprises a.
The method of claim 1,
In the step of calculating the replenishment quantity and allocating the inventory replenishment instruction when the current inventory quantity is less than the minimum shipment quantity or the minimum inventory quantity,
selecting a replenishment location to move the item to after calculating the replenishment quantity;
Picking location supplementary service providing method using machine learning-based demand forecasting, characterized in that it comprises a.
4. The method of claim 3,
If the current inventory quantity is less than the minimum shipment quantity or the minimum inventory quantity, calculating the replenishment quantity and allocating the inventory replenishment instruction,
selecting a replenishment location from which an item is to be retrieved from among a plurality of replenishment locations based on attribute data including the expiration date and stock date of each item;
Picking location supplementary service providing method using machine learning-based demand forecasting, characterized in that it comprises a.
The method of claim 1,
If the current inventory quantity is less than the minimum shipment quantity or the minimum inventory quantity, calculating the replenishment quantity and allocating the inventory replenishment instruction,
Calculating the replenishment quantity in units of pallets or outer boxes according to the storage type of the item to be replenished when calculating the replenishment quantity;
Picking location supplementary service providing method using machine learning-based demand forecasting, characterized in that it comprises a.

Images