Server for calculating order quantity on basis of material usage and demand prediction of unmanned store, and control method therefor

Abstract

The present disclosure relates to a server for calculating an order quantity on the basis of material usage and demand prediction of an unmanned store, and a control method therefor, wherein a machine learning model may be trained on the basis of material usage data of the unmanned store, and the order quantity may be calculated by calculating, on the basis of a plurality of first prediction variables and second prediction variables, a result value including the order quantity and an available sales period for each product of the unmanned store, by using the trained machine learning model.

Description

A server for calculating order quantity based on material usage and demand forecast of an unmanned store and a control method thereof

[0001] This disclosure calculates the order quantity of an unmanned store, and more specifically, calculates the order quantity based on the material usage and demand forecast of the unmanned store.

[0002] Recently, the number of unmanned cafes has been increasing.

[0003] In the case of these unmanned cafes, since the manager is not present within the store, it is necessary to accurately predict demand and place orders accordingly to ensure a smooth supply of materials.

[0004] However, because the supply of materials is currently being conducted by only predicting approximate demand, there is a problem of materials being insufficient or materials being discarded after their expiration date due to oversupply depending on the situation.

[0005] Accordingly, there is a need for technology that can solve the above problems, but such technology is not currently available.

[0006] The purpose of the embodiment disclosed in this disclosure is to provide a server that calculates an order quantity based on the material usage amount and demand forecast of an unmanned store.

[0007] The problems to be solved by the present disclosure are not limited to the problems mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the description below.

[0008] In order to achieve the above-described technical task, the order quantity calculation server of the unmanned store according to the present disclosure comprises: a communication unit for receiving material usage data of the unmanned store; a memory for storing at least one instruction related to order quantity calculation of the unmanned store; And a processor that performs an operation related to the at least one instruction, and calculates a result value including the order quantity of the unmanned store and the sales period for each product based on a machine learning model, wherein the processor trains the machine learning model based on the material usage data of the unmanned store, and calculates the result value based on a plurality of first predictive variables and second predictive variables using the learned machine learning model, wherein the first predictive variable is a variable related to the entire inventory in the unmanned store, and is for predicting the order quantity for a preset future date from the prediction time point based on the machine learning model, and the second predictive variable is a variable related to the remaining amount of food ingredients to be manufactured through a food manufacturing machine installed in the unmanned store, and is for predicting the food ingredient usage for a preset future time from the prediction time point using a value checked for the remaining amount at preset time units based on the machine learning model, and performs post-processing on the result value based on additional data to obtain a final result value, wherein the additional data is data other than conditions preset for the operation of the unmanned store, and is for predicting the order quantity for a preset future date from the prediction time point based on the machine learning model. It includes at least one of a breakdown of a manufacturing machine, an actual operating time different from a preset operating time for the unmanned store, and marketing information conducted in the unmanned store, and based on the occurrence pattern of the additional data, the data of each item included in the additional data is classified as continuous data or temporary data, and the continuous data can be included in learning data for learning the machine learning model, and the temporary data can be classified as data for post-processing.

[0009] In addition, a method for calculating an order quantity of an unmanned store performed by a processor of a server according to the present disclosure for achieving the above-described technical task includes: a step of training a machine learning model based on material usage data of an unmanned store; a step of using the trained machine learning model to produce a result value including an order quantity of the unmanned store and a sales period for each product based on a plurality of first predictive variables and second predictive variables, wherein the first predictive variable is a variable related to the total inventory in the unmanned store, and is for predicting an order quantity for a preset future date (Day) from a prediction time point based on the machine learning model, and the second predictive variable is a variable related to a remaining amount of food ingredients to be manufactured through a food manufacturing machine installed in the unmanned store, and is for predicting an amount of food ingredients used for a preset future time (Hour) from the prediction time point using a value checked for the remaining amount at preset time units based on the machine learning model; A step of performing post-processing on the result value based on additional data to obtain a final result value, wherein the additional data is data other than conditions preset for the operation of the unmanned store, and includes at least one of a breakdown of a food preparation machine in the unmanned store, an actual operating time different from the preset operating time for the unmanned store, and marketing information conducted in the unmanned store; and a step of classifying data of each item included in the additional data into continuous data or temporary data based on a pattern of occurrence of the additional data, wherein the classification step includes the continuous data in learning data for learning the machine learning model, and the temporary data can be classified as data for post-processing.

[0010] In addition, a computer program stored in a computer-readable recording medium for executing the present disclosure may be further provided.

[0011] In addition, a computer-readable recording medium recording a computer program for executing a method for implementing the present disclosure may be further provided.

[0012] According to the aforementioned problem solving means of the present disclosure, an effect of calculating an order quantity based on the material usage amount and demand forecast of an unmanned store is provided.

[0013] The effects of the present disclosure are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

[0014] FIG. 1 and FIG. 2 are schematic diagrams of an order quantity calculation system of an unmanned store according to an embodiment of the present disclosure.

[0015] FIG. 3 is a block diagram of an order quantity calculation server of an unmanned store according to an embodiment of the present disclosure.

[0016] Figure 4 is a flowchart of a method for calculating an order quantity in an unmanned store according to an embodiment of the present disclosure.

[0017] Figure 5 is a diagram illustrating a flow for creating a logistics order list for operating an unmanned store.

[0018] FIG. 6 and FIG. 7 are diagrams illustrating a process in which an order quantity calculation system of an unmanned store according to an embodiment of the present disclosure calculates an order quantity using a machine learning model.

[0019] Figure 8 is a diagram illustrating the packaging specifications, predicted demand, inventory on hand, order quantity, and expected arrival date of each material item required in an unmanned store.

[0020] Figure 9 is a diagram illustrating the schedule and status of coupon issuance provided at an unmanned store.

[0021] Figure 10 is a drawing illustrating a detailed description of the coupon of Figure 9.

[0022] Figures 11 and 12 are diagrams illustrating statistical figures according to coupon provision.

[0023] Figure 13 is a diagram illustrating a flow for predicting the sales availability time of an unmanned store.

[0024] Throughout this disclosure, the same reference numerals denote the same components. This disclosure does not describe all elements of the embodiments, and any content that is common in the technical field to which this disclosure pertains or that overlaps between embodiments is omitted. The terms "part, module, element, block" used in the specification may be implemented in software or hardware, and depending on the embodiments, multiple "parts, modules, elements, blocks" may be implemented as a single component, or a single "part, module, element, block" may include multiple components.

[0025] Throughout the specification, when a part is said to be "connected" to another part, this includes not only direct connection but also indirect connection, and indirect connection includes connection via a wireless communication network.

[0026] Additionally, when a part is said to "include" a component, this does not mean that it excludes other components, but rather that it may include other components, unless otherwise specifically stated.

[0027] Throughout the specification, when we say that an element is "on" another element, this includes not only cases where the element is in contact with the other element, but also cases where another element exists between the two elements.

[0028] The terms first, second, etc. are used to distinguish one component from another, and the components are not limited by the aforementioned terms.

[0029] Singular expressions include plural expressions unless the context clearly indicates otherwise.

[0030] The identification codes for each step are used for convenience of explanation and do not describe the order of each step. Each step may be performed in a different order than specified unless the context clearly indicates a specific order.

[0031] The operating principle and embodiments of the present disclosure are described below with reference to the attached drawings.

[0032] In this specification, the "order quantity calculation server for an unmanned store according to the present disclosure" includes various devices capable of performing computational processing and providing results to the user. For example, the order quantity calculation server for an unmanned store according to the present disclosure may include a computer, a server device, and a mobile terminal, or may be any one of them.

[0033] Here, the computer may include, for example, a notebook, desktop, laptop, tablet PC, slate PC, etc. equipped with a web browser.

[0034] The above server device is a server that processes information by communicating with an external device, and may include an application server, a computing server, a database server, a file server, a game server, a mail server, a proxy server, and a web server.

[0035] The above portable terminal may include, for example, all kinds of handheld-based wireless communication devices such as PCS, GSM, 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) terminals, smart phones, etc., as well as wearable devices such as watches, rings, bracelets, anklets, necklaces, glasses, contact lenses, or head-mounted devices (HMD).

[0036] The artificial intelligence-related functions according to the present disclosure are operated through a processor and a storage unit. The processor may be composed of one or more processors. In this case, one or more processors may be a general-purpose processor such as a CPU, an AP, a Digital Signal Processor (DSP), a graphics-only processor such as a GPU or a Vision Processing Unit (VPU), or an artificial intelligence-only processor such as an NPU. One or more processors control the processing of input data according to predefined operation rules or artificial intelligence models stored in the storage unit. Alternatively, if one or more processors are artificial intelligence-only processors, the artificial intelligence-only processor may be designed with a hardware structure specialized for processing a specific artificial intelligence model.

[0037] The predefined operation rules or artificial intelligence models are characterized by being created through learning. Here, being created through learning means that the basic artificial intelligence model is trained using a learning algorithm using a plurality of learning data, thereby creating the predefined operation rules or artificial intelligence models set to perform a desired characteristic (or purpose). This learning may be performed on the device itself on which the artificial intelligence according to the present disclosure is performed, or may be performed through a separate server and / or system. Examples of the learning algorithm include, but are not limited to, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning.

[0038] An artificial intelligence model may be composed of multiple neural network layers. Each of the multiple neural network layers has multiple weights, and performs neural network operations through operations between the operation results of the previous layer and the multiple weights. The multiple weights of the multiple neural network layers may be optimized based on the learning results of the artificial intelligence model. For example, the multiple weights may be updated so that the loss value or cost value obtained from the artificial intelligence model is reduced or minimized during the learning process. The artificial neural network may include a deep neural network (DNN), and examples thereof include, but are not limited to, a convolutional neural network (CNN), a deep neural network (DNN), a recurrent neural network (RNN), a restricted boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), or a deep Q-network.

[0039] According to an exemplary embodiment of the present disclosure, a processor can implement artificial intelligence. Artificial intelligence refers to a machine learning method based on an artificial neural network that mimics human neurons (biological neurons) to enable machines to learn. AI methodologies can be categorized into supervised learning, where input and output data are provided together as training data, thereby determining the solution (output data) to a problem (input data); unsupervised learning, where only input data is provided without output data, so the solution (output data) to a problem (input data) is not determined; and reinforcement learning, where a reward is provided from an external environment each time an action is taken in the current state, and learning proceeds in a direction that maximizes this reward. Furthermore, AI methodologies can be categorized by the architecture of the learning model. The architectures of widely used deep learning technologies can be categorized into convolutional neural networks, recurrent neural networks, transformers, and generative adversarial networks.

[0040] The device may include an artificial intelligence model. The artificial intelligence model may be a single artificial intelligence model or may be implemented as multiple artificial intelligence models. The artificial intelligence model may be composed of a neural network (or artificial neural network) and may include statistical learning algorithms that mimic biological neurons in machine learning and cognitive science. A neural network may refer to a model in general that has problem-solving capabilities by changing the binding strength of synapses through learning, formed by artificial neurons (nodes) that form a network by combining synapses. The neurons of the neural network may include a combination of weights or biases. The neural network may include one or more layers composed of one or more neurons or nodes. For example, the device may include an input layer, a hidden layer, and an output layer. The neural network constituting the device can infer a desired outcome from an arbitrary input by changing the weights of the neurons through learning.

[0041] The processor can create a neural network, train (or learn) a neural network, perform a calculation based on received input data, generate an information signal based on the calculation result, or retrain the neural network. The models of the neural network can include various types of models such as CNN, R-CNN, RPN, RNN, S-DNN, S-SDNN, Deconvolution Network, DBN, RBM, Fully Convolutional Network, LSTM Network, Classification Network, etc., such as GoogleNet, AlexNet, VGG Network, etc., but are not limited thereto. The processor can include one or more processors for performing calculations according to the models of the neural network. For example, the neural network can include a deep neural network.

[0042] Neural networks include CNN, RNN, perceptron, multilayer perceptron, Feed Forward (FF), Radial Basis Network (RBF), Deep Feed Forward (DFF), Long Short Term Memory (LSTM), Gated Recurrent Unit (GRU), Auto Encoder (AE), Variational Auto Encoder (VAE), Denoising Auto Encoder (DAE), Sparse Auto Encoder (SAE), MC (Markov Chain), HN (Hopfield Network), BM (Boltzmann Machine), RBM (Restricted Boltzmann Machine), DBN (Depp Belief Network), DCN (Deep Convolutional Network), DN (Deconvolutional Network), DCIGN (Deep Convolutional Inverse Graphics Network), GAN (Generative Adversarial Network), LSM (Liquid State Machine), ELM (Extreme Learning) Machine), ESN (Echo State Network), DRN (Deep Residual Network), DNC (Differentiable Network) It will be understood by those skilled in the art that the neural network may include any neural network, including but not limited to a Neural Computer (NN), a Neural Turning Machine (NTM), a Capsule Network (CN), a Kohonen Network (KN), and an Attention Network (AN).

[0043] According to an exemplary embodiment of the present disclosure, the processor may be configured to perform a process for generating a CNN (Convolution Neural Network) such as GoogleNet, AlexNet, VGG Network, Region with Convolution Neural Network (R-CNN), Region Proposal Network (RPN), Recurrent Neural Network (RNN), Stacking-based deep Neural Network (S-DNN), State-Space Dynamic Neural Network (S-SDNN), Deconvolution Network, Deep Belief Network (DBN), Restrcted Boltzman Machine (RBM), Fully Convolutional Network, Long Short-Term Memory (LSTM) Network, Classification Network, Generative Modeling, eXplainable AI, Continual AI, Representation Learning, AI for Material Design, BERT, SP-BERT, MRC / QA for natural language processing, Text Analysis, Dialog System, GPT-3, GPT-4, Visual Analytics for vision processing, Visual Understanding, Video Synthesis, ResNet for data intelligence, Anomaly Detection, Prediction, Time-Series Forecasting, Various artificial intelligence structures and algorithms, including optimization, recommendation, and data creation, can be utilized, but are not limited thereto. Hereinafter, embodiments of the present disclosure will be described in detail with reference to the attached drawings.

[0044] Figures 1 and 2 are schematic diagrams of an order quantity calculation system (10) of an unmanned store according to an embodiment of the present disclosure.

[0045] Referring to FIG. 1, the order quantity calculation system (10) of an unmanned store according to an embodiment of the present disclosure includes a server, a cloud server (200), a store management system (300), and an order server (400).

[0046] However, in some embodiments, the order quantity calculation system (10) of an unmanned store may include fewer or more components than the components illustrated in FIG. 1.

[0047] The server can receive material usage data of each unmanned store from the store management system (300).

[0048] The server can use stored commands, algorithms, and programs to produce results that include the order quantity for each unmanned store and the sales period for each product.

[0049] As shown in Fig. 2, the server can produce a result value using a machine learning model (210). The machine learning model (210) may be stored in a cloud server (200), and at least some of the algorithms and programs may use those stored in the cloud server (200). At this time, the server can set the data input to the machine learning model (210) by considering the material usage amount of each unmanned store, the predicted situation during the ordering period, etc.

[0050] And, the server can request an order to the ordering server (400) based on the produced result.

[0051] FIG. 3 is a block diagram of an order quantity calculation server (100) of an unmanned store according to an embodiment of the present disclosure.

[0052] Referring to FIG. 3, the order quantity calculation server (100) of an unmanned store according to an embodiment of the present disclosure includes a processor (110), a communication unit (120), and a memory (130).

[0053] However, in some embodiments, the order quantity calculation server (100) of the unmanned store may include fewer or more components than the components illustrated in FIG. 2.

[0054] The processor (110) may be implemented as a storage unit that stores data regarding an algorithm for controlling the operation of components within the device or a program that reproduces the algorithm, and at least one processor (110) that performs the aforementioned operation using the data stored in the storage unit. In this case, the storage unit and the processor (110) may each be implemented as separate chips. Alternatively, the storage unit and the processor (110) may be implemented as a single chip.

[0055] In addition, the processor (110) can control any one or a combination of the components described above to implement various embodiments according to the present disclosure described in the drawings below on the device.

[0056] In addition to operations related to the above-described application, the processor (110) can typically control the overall operation of the device. The processor (110) can process signals, data, information, etc. input or output through the components described above, or run application programs stored in the storage unit, thereby providing or processing appropriate information or functions to the user.

[0057] In addition, the processor (110) may control at least some of the components of the device to run an application program stored in the storage unit. Furthermore, the processor (110) may operate at least two or more of the components included in the device in combination to run the application program.

[0058] The processor (110) may be implemented as one or more. Hereinafter, even if the processor (110) is expressed as singular, it may be considered as plural. The processor (110) may control the configurations of the order quantity calculation server (100) of the unmanned store. The processor (110) may refer to a data processing device built into hardware that has a physically structured circuit to perform a function expressed by a code or command included in a program. As such, the processor (110) is an example of a data processing device built into hardware, and may encompass processing devices such as a microprocessor, a central processing unit (CPU), a processor (110) core, a multiprocessor, an application-specific integrated circuit (ASIC), and a field programmable gate array (FPGA), but the scope of the present invention is not limited thereto. The processor (110) may be equipped with a separate learning processor (110) for performing artificial intelligence operations, or may be equipped with a learning processor (110) on its own.

[0059] The communication unit (120) may include one or more modules that connect the order quantity calculation server (100) of the unmanned store to one or more networks.

[0060] The communication unit (120) may include one or more components that enable communication with an external device, and may include, for example, at least one of a broadcast reception module, a wired communication module, a wireless communication module, a short-range communication module, and a location information module.

[0061] The wired communication module may include various wired communication modules such as a Local Area Network (LAN) module, a Wide Area Network (WAN) module, or a Value Added Network (VAN) module, as well as various cable communication modules such as a Universal Serial Bus (USB), a High Definition Multimedia Interface (HDMI), a Digital Visual Interface (DVI), RS-232 (recommended standard 232), power line communication, or plain old telephone service (POTS).

[0062] The wireless communication module may include a wireless communication module that supports various wireless communication methods such as GSM (global System for Mobile Communication), CDMA (Code Division Multiple Access), WCDMA (Wideband Code Division Multiple Access), UMTS (universal mobile telecommunications system), TDMA (Time Division Multiple Access), LTE (Long Term Evolution), 4G, 5G, and 6G, in addition to a WiFi module and a Wireless Broadband module.

[0063] The wireless communication module may include a wireless communication interface including an antenna and a transmitter for transmitting communication signals. Furthermore, the wireless communication module may further include a signal conversion module that modulates a digital control signal output from the processor (110) through the wireless communication interface into an analog wireless signal under the control of the processor (110).

[0064] The short-range communication module is for short-range communication, and can support short-range communication using at least one of Bluetooth, RFID (Radio Frequency Identification), Infrared Data Association (IrDA), UWB (Ultra-Wideband), ZigBee, NFC (Near Field Communication), Wi-Fi (Wireless-Fidelity), Wi-Fi Direct, and Wireless USB (Wireless Universal Serial Bus) technologies.

[0065] The memory (130) can store data supporting various functions of the device. The memory (130) can store a plurality of application programs (or applications) running on the device, data for the operation of the device, and commands. At least some of these application programs may exist for the basic functions of the device. Meanwhile, the application programs can be stored in the memory (130), installed on the device, and driven to perform operations (or functions) by the processor (110).

[0066] The memory (130) can store data supporting various functions of the device and programs for the operation of the processor (110), input / output data (e.g., music files, still images, moving images, etc.) can be stored, and a plurality of application programs (or applications) run on the device, data for the operation of the device, and commands can be stored. At least some of these application programs can be downloaded from an external server via wireless communication.

[0067] The memory (130) may include at least one type of storage medium among a flash memory (130) type, a hard disk type, an SSD (Solid State Disk type), an SDD (Silicon Disk Drive) type, a multimedia card micro type, a card type memory (e.g., an SD or XD memory (130)), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory (130), a magnetic disk, and an optical disk. In addition, the memory (130) may be a database that is separate from the device but is connected by wire or wirelessly.

[0068] The memory (130) may be electrically connected to the processor (110) and may store at least one code executed by the processor (110). The memory (130) may collectively refer to various types of storage devices. The memory (130) may store information necessary for performing operations using artificial intelligence, machine learning, and artificial neural networks.

[0069] The memory (130) can store various learning models. The learning models stored in the memory (130) can infer result values ​​for new input data other than learning data, and the inferred values ​​can be used as a basis for judgment to perform a certain action. The learning models stored in the memory (130) can perform learning based on label information, and various backpropagation algorithms can be applied so that the loss function has a target value to increase the accuracy of learning.

[0070] Additionally, the memory (130) may be equipped with multiple processes for the order quantity calculation server (100) of the unmanned store.

[0071] In addition, the order quantity prediction server of an unmanned store may further include components such as an input section, an output section, and an interface section.

[0072] The input unit is for inputting video information (or signal), audio information (or signal), data, or information input from a user, and may include at least one camera, at least one microphone, and at least one user input unit. Voice data or image data collected from the input unit may be analyzed and processed into a user control command.

[0073] The input unit is for receiving information from the user, and when information is input through the input unit, the processor (110) can control the operation of the device to correspond to the input information. The input unit may include a hardware physical key (e.g., a button located on at least one of the front, rear, and side of the device, a dome switch, a jog wheel, a jog switch, etc.) and a software touch key. As an example, the touch key may be a virtual key, a soft key, or a visual key displayed on a touch screen type display unit through software processing, or may be a touch key disposed on a part other than the touch screen. Meanwhile, the virtual key or visual key may have various forms and be displayed on the touch screen, and may be, for example, formed of a graphic, text, an icon, a video, or a combination thereof.

[0074] The output unit is for generating output related to visual, auditory, or tactile sensations, and may include at least one of a display unit, an audio output unit, a haptic module, and an optical output unit. The display unit may be formed as a layer structure with a touch sensor or formed as an integral part, thereby implementing a touch screen. Such a touch screen may function as a user input unit that provides an input interface between the device and a user, and at the same time, may provide an output interface between the device and the user.

[0075] The interface unit serves as a conduit for various types of external devices connected to the device. The interface unit may include at least one of a wired / wireless headset port, an external charger port, a wired / wireless data port, a memory card port, a port for connecting a device equipped with an identification module (SIM), an audio I / O (Input / Output) port, a video I / O (Input / Output) port, and an earphone port. The device may perform appropriate control related to the external device connected to the interface unit.

[0076] Figure 4 is a flowchart of a method for calculating an order quantity in an unmanned store according to an embodiment of the present disclosure.

[0077] Figure 5 is a diagram illustrating a flow for creating a logistics order list for operating an unmanned store.

[0078] FIG. 6 and FIG. 7 are diagrams illustrating a process in which an order quantity calculation system (10) of an unmanned store according to an embodiment of the present disclosure calculates an order quantity using a machine learning model (210).

[0079] Referring to Figures 4 to 7, the flow of a method for calculating an order quantity in an unmanned store will be described.

[0080] The server receives material usage data of an unmanned store from the store management system (300). (S100)

[0081] The store management system (300) can collect data of stores managed by the server and transmit the data to the server. At this time, the stores managed by the server can be directly managed stores, franchise stores, etc.

[0082] In some embodiments, the server may receive material usage data of the unmanned store directly from the unmanned store terminal.

[0083] The processor (110) trains a machine learning model (210) based on the material usage data received from S100. (S200)

[0084] The processor (110) uses the learned machine learning model (210) to produce a result value based on a plurality of first and second predictive variables. (S300)

[0085] At this time, the result value includes the order quantity of the unmanned store and the sales period for each product.

[0086] That is, the processor (110) can teach the machine learning model (210) the amount of material used during a preset period of time for each unmanned store, obtain an output value based on the first predictive variable and the second predictive variable designed according to the situation of each unmanned store and the situation of the analysis target period, and calculate the order quantity of the unmanned store and the sales period for each product based on the obtained output value.

[0087] The first predictor variable (Logistics Predictors) is a variable related to the total inventory in an unmanned store, and is used to predict orders for a predetermined future date (Day) from the prediction time based on a machine learning model (210).

[0088] The second predictor variable (Realtime Predictors) is a variable related to the remaining amount of food ingredients to be manufactured through a food manufacturing machine installed in an unmanned store, and is used to predict the amount of food ingredients used during a preset future time (Hour) from the prediction time using the checked value for the remaining amount at preset time units based on a machine learning model (210).

[0089] That is, the first predictor variable is a variable related to the total inventory stored in the unmanned store, so it is possible to predict orders for a preset future period (Day).

[0090] Beverage machines (e.g., coffee machines) installed in unmanned stores operate by storing ingredients like coffee beans and milk in dispensers or cartridges, which are used to make beverages whenever the machine is in operation. Even if the store has stock, if the dispenser or cartridge runs out of ingredients, a staff member must manually refill the ingredients.

[0091] The processor (110) can predict the real-time sales availability time for each product through the second prediction variable.

[0092] The first predictor variable and learning method may be the same, but the difference is that the inventory is checked every 5 minutes to obtain prediction results for 200 hours.

[0093] At this time, since the processor (110) learns and performs prediction only in a unit period, a gap or error may occur between the timing at which the result value is produced and the timing at which learning is performed, a buffer of about 1.5 times the unit period may be provided.

[0094] In one embodiment, the processor (110) may predict the material demand of the unmanned store for a first future date set from the prediction time point and configure a first prediction variable for predicting an order for a second future date set based on the forecast.

[0095] At this time, the preset future date used in the first predictor variable may include a date set later than the predicted time point. For example, the first predictor variable may apply to one week from one week after the predicted time point.

[0096] In addition, the processor (110) can predict the material demand of the unmanned store for twice the number of days after the above-mentioned preset time from the prediction time, and based on this, configure a first prediction variable for predicting an order for one week from one week after the prediction time.

[0097] That is, the processor (110) can predict the material demand of the unmanned store for two weeks from the prediction time, and based on this, configure a first prediction variable for predicting an order for one week starting one week after the prediction time.

[0098] This is for the order quantity calculation server (100) of the unmanned store according to the embodiment of the present disclosure to predict orders, and based on a model trained for orders for a unit period (one week), it predicts demand for two weeks, which is twice the unit period.

[0099] At this time, the server can configure the first predictive variable as described above to place orders for the following week, taking into account the delivery period for the requested materials. For example, if the results for 2 / 1 to 2 / 14 are available on 2 / 1, the processor (110) can use the predicted values ​​from 2 / 1 to place orders for sales from 2 / 8 to 2 / 14.

[0100] In one embodiment, the processor (110) may obtain the quantity (hereinafter, “first required quantity”) predicted to be needed in the unmanned store for twice the number of days after the preset time from the predicted time based on the machine learning model (210), and predict the order based on this.

[0101] And, the processor (110) can calculate the quantity (hereinafter, “second quantity required”) expected to be required at the unmanned store for a period of time after the preset date from the predicted time based on the first required quantity acquired above, and calculate an order prediction variable based on the second quantity required.

[0102] Referring to FIG. 5, the processor (110) checks whether the predicted demand can be calculated. (S510)

[0103] The processor (110) provides unpredictable guidance when the predicted demand is unpredictable. (S590)

[0104] If the demand forecast is correct, the processor (110) calculates the actual demand of the previous week. (S520)

[0105] The processor (110) checks the inventory. (S530)

[0106] And, the processor (110) calculates the required quantity. (S540)

[0107] Next, the processor (110) calculates the recommended order quantity. (S550)

[0108] The processor (110) calculates the order quantity. (S560)

[0109] The processor (110) generates an order guide list based on CMS logistics management raw material attribute information (S570). (S580)

[0110] Below, implementation of the machine learning system (620) will be described in more detail with reference to FIGS. 6 and 7.

[0111] Referring to FIG. 6, the order quantity calculation system (10) of an unmanned store is configured to include an order quantity calculation server (100) of an unmanned store, a CMS (300), REDIS (210), a BATCH SERVER (220), an RDB (230), Lambda (240), and an S3 Bucket (250), and can implement a machine learning system (620).

[0112] Referring to Fig. 7, the order quantity calculation system (10) of an unmanned store includes a data collection system (710), the Internet (720), a platform (730), and a machine learning system (740).

[0113] In one embodiment, the configuration indicated by M in FIG. 7 is a configuration corresponding to Management, the configuration indicated by A is a configuration corresponding to Automation, and the configuration indicated by D is a configuration corresponding to Data.

[0114] The server (100) analyzes big data collected through IoT equipment installed in an unmanned store (booth) through a machine learning model to convert various data such as the store's equipment status, inventory status and order prediction, unmanned store operating hours, sales quantity and revenue, customer visit status, and marketing effectiveness analysis into useful information, thereby providing a platform that helps make strategic decisions.

[0115] In addition, the server (100) can provide a system (10) that can simultaneously perform presentation (view) of indicators that can be identified in the area of ​​a general data analysis dashboard based on management and operation (Management) and management (action) through the same.

[0116] CMS (300) refers to a store management system (300).

[0117] RDB (230) is a relational database in which various types of data can be stored.

[0118] The order quantity calculation system (10) of an unmanned store can obtain prediction results using the following machine learning system (620).

[0119] Lambda (240) can receive data and perform various processing.

[0120] The order quantity calculation system (10) of an unmanned store according to an embodiment of the present disclosure can utilize a cloud service such as AWS (Amazon Web Services).

[0121] S3 Bucket (250) is an object storage service that provides scalability, data availability, security, and performance, and can provide management functions that can optimize, structure, and configure access to data according to requests from the server.

[0122] Data processed in this way can be organized into a dataset as shown in Fig. 6, and can be classified as Target_Time_Series, Related_Time_Series, and Item_Metadata.

[0123] In addition, the processor (110) processes the dataset to configure a first predictor variable (Logistics Predictors) and a second predictor variable (Realtime Predictors), and can obtain a prediction result (Forecast) based on the predictor variable using a machine learning model (210).

[0124] In an embodiment of the present disclosure, a machine learning model can output a prediction result through statistical time series analysis by learning material usage data corresponding to time series data.

[0125] Additionally, the machine learning model (210) can output prediction results based on a weight-based quantile loss function.

[0126] The processor (110) can obtain a prediction result by inputting one of a plurality of preset moods within the mood range into the machine learning model (210).

[0127] At this time, the processor (110) may select one mood range in which the prediction success rate of the machine learning model (210) is expected to be the highest, based on at least one of the location of the unmanned store, the promotion of the unmanned store, the type of menu sold by the unmanned store, the weather during the prediction period, the day of the week included in the prediction period, and the holiday included in the prediction period.

[0128] For example, the processor (110) can preset a plurality of moods suitable for calculating the order quantity of an unmanned store among moods of P1 to P99, and can perform the above process to select one mood among them to obtain a prediction result.

[0129] The processor (110) can calculate the expected sales volume of an unmanned store by day of the week and weather, as well as the sales volume for each menu item by day of the week and weather. Accordingly, the processor (110) considers these factors to determine the mood level for obtaining a prediction result, and obtains a prediction result expected to have the highest prediction success rate.

[0130] At this time, the weather can include various factors such as rain, snow, humidity, sunlight, precipitation, rainfall, and fine dust.

[0131] The dataset of Fig. 6 includes information on the analysis target period, related data, and item data, and the related data may include at least one of a promotion, a holiday, a day of the week, weather, latitude, longitude, and a menu code.

[0132] Next, the processor (110) may perform a post-processing process based on additional data. Specifically, the processor (110) may perform post-processing (e.g., correction) on the prediction result based on additional data that corresponds to unusual situations for inputting and training the machine learning model (210).

[0133] In one embodiment, the processor (110) may perform post-processing on the result value obtained from S300 based on additional data to obtain a final result value.

[0134] At this time, additional data may include at least one of the following: data other than the conditions preset for the operation of the unmanned store, such as a breakdown of a food preparation machine in the unmanned store, actual operating hours different from the preset operating hours for the unmanned store, and marketing information conducted in the unmanned store.

[0135] In one embodiment, the processor (110) may classify data for each item included in the additional data as either persistent data or transient data based on preset conditions for the operation of the unmanned store and the occurrence pattern of the additional data. The processor (110) may include the persistent data in the learning data for training the machine learning model (210), and classify the transient data as data for post-processing.

[0136] Referring to FIG. 6, the processor (110) can also obtain a prediction result regarding the operating hours of an unmanned store corresponding to the third predictive variable. An embodiment of predicting the operating hours of an unmanned store will be described below with reference to FIG. 13.

[0137] Figure 8 is a diagram illustrating the packaging specifications, predicted demand, inventory on hand, order quantity, and expected arrival date of each material item required in an unmanned store.

[0138] Referring to the UI (810) of FIG. 8, the order quantity calculation server (100) of the unmanned store according to the embodiment of the present disclosure automatically stores packaging specifications for each raw material item to proceed with the order application.

[0139] The processor (110) can obtain predicted demand based on a machine learning model (210) and calculate an order quantity using information such as that in FIG. 8 to automatically place an order.

[0140] Additionally, in the embodiment of the present disclosure, the materials include raw materials and auxiliary materials for producing food (beverage).

[0141] For example, the processor (110) can calculate the logistics order quantity for raw materials using the following mathematical equations 1 to 6.

[0142] [Mathematical Formula 1]

[0143] Inventory on hand this Monday = Inventory on hand last week + Orders placed two weeks ago - Actual usage on hand last week

[0144] [Equation 2]

[0145] Inventory held last week = Inventory held as of last Monday

[0146] [Equation 3]

[0147] Expected inventory on hand next Monday = Expected consumption next week - Expected inventory on hand next Monday + Safety stock

[0148] [Equation 4]

[0149] Next week's required quantity = Next week's expected consumption quantity - Expected inventory on hand next Monday + Safety stock

[0150] [Equation 5]

[0151] Recommended Order Quantity = Quantity Needed Next Week ÷ Minimum Order Quantity (rounded up)

[0152] [Equation 6]

[0153] Order quantity = Recommended order quantity × Minimum order quantity × Packaging specifications

[0154] For example, the processor (110) can calculate the logistics order quantity for auxiliary materials using the following calculation formulas.

[0155] The processor (110) can calculate the predicted order quantity by applying the order ratio for each raw material to the actual usage amount of the raw material cup and the predicted demand.

[0156] Figure 9 is a diagram illustrating the schedule and status of coupon issuance provided at an unmanned store.

[0157] Figure 10 is a drawing illustrating a detailed description of the coupon of Figure 9.

[0158] Figures 11 and 12 are diagrams illustrating statistical figures according to coupon provision.

[0159] The coupons shown in Figures 9 to 12 may be applied to the aforementioned promotions and marketing.

[0160] Referring to the UI (910) of FIG. 9, the processor (110) can output the coupon issuance schedule and coupon issuance status to the store management system (300).

[0161] Referring to the UI (1010) of FIG. 10, the processor (110) can output various coupon options, including the coupon's discount type, issuance-available days, issuance-available period, discount-applicable products, expiration date, and other options, to the store management system (300). The store owner or manager can set various options for the coupons they wish to issue through this UI.

[0162] Referring to the UI (1110) of FIG. 11, the processor (110) can provide information such as the performance status, operation status, operation index, and equipment operation of the unmanned store through the store management system (300).

[0163] Additionally, the processor (110) can provide statistics on the number of orders placed using coupons by period.

[0164] In one embodiment, the processor (110) may generate statistical data on whether a customer who used a free drink coupon subsequently purchased a paid drink and how many times the customer subsequently purchased a drink.

[0165] Referring to the UI (1210) of FIG. 12, the processor (110) can calculate and provide the number of coupons issued during a preset period, the number of coupon users, and the number of users who subsequently converted to paid payment, and can also provide detailed statistical data for each coupon.

[0166] Figure 13 is a diagram illustrating a flow for predicting the sales availability time of an unmanned store.

[0167] The processor (110) uses a machine learning model (210) to predict the amount of food ingredients to be used for a preset future time (e.g., 240 hours) from the prediction time using a value checked for the remaining amount at each preset time unit based on variables related to the remaining amount of food ingredients to be manufactured through a food manufacturing machine installed in an unmanned store. (S1310)

[0168] The processor (110) obtains the demand prediction result of the unmanned store for the requested prediction period based on the prediction result of S1310. (S1320, S1330)

[0169] As an example, the processor (110) may use a machine learning model to obtain a demand forecast for K days from the predicted time based on the predicted food ingredient usage. Furthermore, the processor (110) may predict / calculate the operating hours of the unmanned store based on the obtained demand forecast results.

[0170] More specifically, since the processor (110) knows the amount of food ingredients in the material receiving means (e.g., dispenser) of the food manufacturing machine installed in the unmanned store at the time of prediction, it can predict / calculate how long it will be possible to manufacture and provide food in the unmanned store in the future based on the amount of remaining food ingredients and the demand prediction result, and the result can be directly applied to the operating time of the unmanned store.

[0171] In one embodiment, since the processor (110) knows the inventory of each material in the unmanned store at the time of prediction, it can predict / calculate the time for which each menu sold in the unmanned store can be provided based on the inventory and demand prediction results for each food menu, and the result can be directly applied to the operating hours of the unmanned store.

[0172] In detail, the operating hours of an unmanned store may include the number of items available for sale and the hours of sale for each menu sold in the unmanned store.

[0173] For example, the processor (110) can obtain the prediction result for +9 days (total of 10 days) from Monday of that week.

[0174] This forecast period can be set by considering the inventory status within the unmanned store or the specifications of the material storage containers (e.g., dispensers) of the food preparation machines installed in the unmanned store.

[0175] Next, the processor (110) calculates the operating hours of the unmanned store based on the predicted results obtained through S1330 and the predicted values ​​that are consistent or have the minimum error compared to the actual demand of the previous week. (S1340)

[0176] The processor (110) controls a load cell (not shown) at preset time intervals to obtain a weight measurement value. (S1350) At this time, the processor (110) recalculates the operating time of the unmanned store based on the measurement value obtained through S1350, and if the recalculated result is outside the preset error range of the result of S1340, the processor updates the predicted result for the operating time.

[0177] And, if the recalculated result is within the set error range of the result of S1340, the processor (110) displays the predicted operating time for the unmanned store through the output unit. (S1360)

[0178] A material storage container (e.g., dispenser) related to food production in an unmanned store may include a load cell capable of measuring weight, and the processor (110) may receive a weight value measured through the load cell at a preset time or timing.

[0179] For example, the processor (110) may receive a weight value measured through a load cell at preset intervals, or may receive a weight value measured through a load cell whenever a food order is placed.

[0180] As an example of the operation of S1310 to S1360, the processor (110) can predict demand by hour from 00:00:01 every Monday to 23:59:59 the following Wednesday (total of 240 hours), and check and update the operating time by receiving the weight measured by the load cell at 5-minute intervals.

[0181] The processor (110) can display the required time until the time when the expected demand at the time corresponding to the update point and the expected demand for each subsequent hour are equal to or greater than the load cell measured weight as the available operating time.

[0182] The method according to one embodiment of the present disclosure described above can be implemented as a program (or application) and stored in a medium to be executed in combination with a hardware server.

[0183] The above-described program may include codes coded in a computer language, such as C, C++, JAVA, or machine language, that can be read by the processor (CPU) of the computer through the device interface of the computer, so that the computer reads the program and executes the methods implemented as a program. Such codes may include functional codes related to functions that define functions necessary for executing the methods, and may include control codes related to execution procedures necessary for the processor of the computer to execute the functions according to a predetermined procedure. In addition, such codes may further include memory reference-related codes regarding which location (address address) of the internal or external memory of the computer should reference additional information or media necessary for the processor of the computer to execute the functions. In addition, if the processor of the computer needs to communicate with any other computer or server located remotely in order to execute the functions, the code may further include communication-related code regarding how to communicate with any other computer or server located remotely using the communication module of the computer, and what information or media to send and receive during communication.

[0184] The above storage medium refers to a medium that stores data semi-permanently and can be read by a device, rather than a medium that stores data for a short period of time, such as a register, cache, or memory. Specifically, examples of the storage medium include, but are not limited to, ROM, RAM, CD-ROM, magnetic tape, floppy disk, and optical data storage device. That is, the program can be stored in various recording media on various servers that the computer can access or in various recording media on the user's computer. In addition, the medium can be distributed across network-connected computer systems, so that computer-readable code can be stored in a distributed manner.

[0185] The steps of a method or algorithm described in connection with the embodiments of the present disclosure may be implemented directly in hardware, implemented as a software module executed by hardware, or implemented by a combination thereof. The software module may reside in a random access memory (RAM), a read only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a flash memory, a hard disk, a removable disk, a CD-ROM, or any other form of computer-readable recording medium well known in the art to which the present disclosure pertains.

[0186] While the embodiments of the present disclosure have been described above with reference to the attached drawings, those skilled in the art will appreciate that the present disclosure can be implemented in other specific forms without altering the technical spirit or essential features thereof. Therefore, the embodiments described above should be understood to be illustrative in all respects and not restrictive.

Claims

1. A communication unit that receives data on material usage in an unmanned store; A memory storing at least one instruction related to calculating an order quantity of the unmanned store; and A processor that performs an operation related to at least one instruction and produces a result value including the order quantity of the unmanned store and the sales period for each product based on a machine learning model, The above processor, The machine learning model is trained based on the material usage data of the unmanned store. The above-mentioned learned machine learning model is used to calculate the result value based on a plurality of first predictor variables and second predictor variables, wherein the first predictor variable is a variable related to the total inventory in the unmanned store, and is for predicting the order quantity for a preset future date from the prediction time point based on the machine learning model, and the second predictor variable is a variable related to the remaining amount of food ingredients to be manufactured through a food manufacturing machine installed in the unmanned store, and is for predicting the amount of food ingredients used for a preset future time from the prediction time point using a value checked for the remaining amount at each preset time unit based on the machine learning model, The final result is obtained by performing post-processing on the result value based on additional data, wherein the additional data is data other than conditions preset for the operation of the unmanned store, and includes at least one of a breakdown of a food preparation machine in the unmanned store, an actual operating time different from the preset operating time for the unmanned store, and marketing information conducted in the unmanned store. Based on the occurrence pattern of the additional data, the data of each item included in the additional data is classified as continuous data or temporary data, and the continuous data is included in the learning data for learning the machine learning model, and the temporary data is classified as data for post-processing. Order quantity calculation server for unmanned stores.

2. In paragraph 1, The above-mentioned preset future date includes a date after the preset date from the above-mentioned prediction time. Order quantity calculation server for unmanned stores.

3. In paragraph 2, The above processor, A method characterized in that, based on the machine learning model, the quantity predicted to be needed in the unmanned store for twice the number of days after the preset time from the predicted time (hereinafter, “first required quantity”) is obtained, and the order quantity is predicted based on the first required quantity. Order quantity calculation server for unmanned stores.

4. In paragraph 3, The above processor, A method characterized in that the quantity predicted to be needed in the unmanned store during the preset date from the prediction time based on the first required quantity (hereinafter, “second required quantity”) is calculated, and a prediction variable is calculated based on the second required quantity. Order quantity calculation server for unmanned stores.

5. In paragraph 1, The above machine learning model is, By learning the above material usage data corresponding to time series data, a prediction result is output through statistical time series analysis, and the prediction result is output based on a weight-based quantile loss function. The above processor, The prediction result is obtained by inputting one of the preset multiple mood levels within the range of the above mood levels into the machine learning model, A method characterized in that, based on at least one of the location of the unmanned store, the promotion of the unmanned store, the type of menu sold by the unmanned store, the weather during the prediction period, the day of the week included in the prediction period, and the holiday included in the prediction period, the machine learning model selects the one quantile in which the prediction success rate is expected to be the highest. Order quantity calculation server for unmanned stores.

6. In paragraph 1, The above processor, Using the machine learning model, based on the predicted food ingredient usage, a demand forecast for a preset period of time from the predicted point in time is obtained, Characterized in that the operating hours of the unmanned store are predicted based on the above demand forecast. Order quantity calculation server for unmanned stores.

7. In a method for calculating order quantity of an unmanned store performed by a server processor, A step for training a machine learning model based on material usage data from an unmanned store; A step of using the learned machine learning model to produce a result value including the order quantity and the sales period for each product of the unmanned store based on a plurality of first and second predictive variables - the first predictive variable is a variable related to the total inventory in the unmanned store, and is for predicting the order quantity for a preset future date (Day) from the prediction time point based on the machine learning model, and the second predictive variable is a variable related to the remaining amount of food ingredients to be manufactured through a food manufacturing machine installed in the unmanned store, and is for predicting the amount of food ingredients used for a preset future time (Hour) from the prediction time point using a value checked for the remaining amount at preset time units based on the machine learning model -; A step of performing post-processing on the result value based on additional data to obtain a final result value, wherein the additional data is data other than conditions preset for the operation of the unmanned store, and includes at least one of a breakdown of a food preparation machine in the unmanned store, an actual operating time different from the preset operating time for the unmanned store, and marketing information conducted in the unmanned store; and A step of classifying data of each item included in the additional data into persistent data or temporary data based on the occurrence pattern of the additional data, The above classification step is characterized in that the continuous data is included in the learning data for learning the machine learning model, and the temporary data is classified as data for post-processing. How to calculate order quantity for unmanned stores.

Images