Unmanned food and beverage manufactruring apparatus and method

Abstract

According to an embodiment of the present invention, an unmanned food and beverage manufacturing apparatus and method collect order and pick-up time information from a customer to schedule manufacturing processes, ensuring that the order can be completed by the pick-up time specified by the customer, thereby allowing the customer to retrieve fresh food and beverages at a desired time. In addition, in an embodiment, when a customer does not pick up their food and beverages at a designated pickup time, the food and beverage are stored separately and can be retrieved through authentication code recognition, thereby preventing an order from being mistakenly provided to wrong customers.

Description

Unmanned beverage manufacturing device and method

[0001] The present disclosure relates to an unmanned beverage manufacturing device and method, and more particularly, to an unmanned beverage manufacturing device and method equipped with a smart waiting system.

[0002]

[0003] Unless otherwise indicated herein, the materials described in this section are not prior art to the claims of this application, and their inclusion in this section is not intended to be admitted as prior art.

[0004] Unmanned food and beverage processing equipment (UAE) is an automated system that prepares and serves food and beverages without human intervention. UAE is primarily used in the food service industry and in various locations, including hotels, cafes, restaurants, airports, and universities. Customers using UAE can place orders through a smartphone app or touchscreen interface, with payments processed automatically. UAE also processes orders quickly, and in some cases, can deliver food or beverages within minutes.

[0005] Additionally, in most cases, unmanned food and beverage manufacturing equipment provides 24-hour service, so it is available at any time, which has the advantage of reducing labor costs and saving working hours.

[0006] However, conventional unmanned food and beverage manufacturing equipment offers a simple process that only processes orders entered directly into the device in the order they are received. This process fails to account for individual customer waiting times, significantly limiting the number of orders it can process. Furthermore, when a large number of orders are received, customers who place subsequent orders face significantly longer waiting times.

[0007]

[0008] An unmanned beverage manufacturing device and method according to an embodiment can collect a menu and pickup time from a customer terminal and provide the menu ordered by the customer at the pickup time.

[0009] In the embodiment, only idle times, which filter the manufacturing times of food and beverages that have already been paid for according to the schedule, can be selected as pick-up times.

[0010] In an embodiment, the unmanned food and beverage manufacturing device recognizes an authentication code for each order created by a customer, stores the customer's phone number, and allows the customer to select a menu and pickup time at the customer terminal and then make payment.

[0011] Additionally, in the embodiment, food and beverages are manufactured in the order of food and beverage manufacturing generated based on the pickup time and order information, and manufacturing process and pickup request notifications are sent to the customer terminal that sent the prepared order information.

[0012] Additionally, the embodiment provides a temporary storage location and temporary storage process for customers who do not pick up their food or beverage immediately after receiving a pickup notification after the food or beverage is prepared.

[0013] In this embodiment, after food and beverages are prepared, they are moved onto a conveyor belt so that they can be picked up at the designated pickup time. If the food and beverages are not picked up at the designated pickup time, they are moved to multiple storage spaces equipped with transparent covers after preparation.

[0014] Additionally, in the embodiment, when a customer tags a mobile phone to a pickup sensor installed in a storage space, the cover of the space opens, allowing the customer to retrieve food and beverage.

[0015] In addition, in the embodiment, for manufacturing scheduling, the user's waiting time and pickup time are input, and the optimal menu preparation order is generated by considering the preparation time for each menu, the congestion level of the store, and the time and number of menus waiting to be prepared.

[0016] Additionally, in the embodiment, fresh food and beverages can be provided to customers by starting to prepare food and beverages close to the pickup time entered by the user.

[0017]

[0018] In an unmanned beverage manufacturing device according to an embodiment, a memory storing at least one command; and a processor, wherein the at least one command is executed by the processor to collect order information and a pickup time from a customer terminal, and generate a menu preparation order based on the collected order information, pickup time, and the manufacturing time of each food or beverage included in the order information, and when the food or beverage included in the order information is completed according to the generated menu preparation order, the food or beverage is moved to a conveyor, and when the food or beverage on the conveyor is not picked up even after the pickup time, the food or beverage is moved to a storage space.

[0019] In the embodiment, the storage space; opens the cover of the storage space based on the result of the sensed authentication code verification to provide food and beverage to the customer.

[0020]

[0021] The unmanned beverage manufacturing device and method described above collects order and pickup time information from customers, and performs manufacturing scheduling to complete orders at the customer's pickup time, thereby enabling customers to pick up fresh food and beverages at their desired time.

[0022] Additionally, in the embodiment, food and beverages of customers who do not pick up food and beverages at the pick-up time are stored separately, and food and beverages that have been prepared can be picked up by recognizing an authentication code, thereby preventing orders from being provided to other customers.

[0023] In addition, the example can prevent the mixing of manufactured food and beverages even if the pickup time is not observed.

[0024] The effects of the present invention are not limited to the effects described above, and should be understood to include all effects that can be inferred from the detailed description of the present invention or the composition of the invention described in the claims.

[0025]

[0026] Figure 1 is a drawing showing an unmanned beverage manufacturing device according to an embodiment.

[0027] Figure 2 is a drawing showing a block diagram of an unmanned beverage manufacturing device according to an embodiment.

[0028] Figure 3 is a diagram showing the configuration of a command set stored in memory according to an embodiment.

[0029] Figure 4 is a diagram showing an example of a model that learns data stored in a learning unit according to an embodiment.

[0030] Figure 5 is a diagram showing the data processing process of an unmanned beverage manufacturing device according to an embodiment.

[0031]

[0032] In an unmanned beverage manufacturing device according to an embodiment, a memory storing at least one command; and a processor, wherein the at least one command is executed by the processor to collect order information and a pickup time from a customer terminal, and generate a menu preparation order based on the collected order information, pickup time, and the manufacturing time of each food or beverage included in the order information, and when the food or beverage included in the order information is completed according to the generated menu preparation order, the food or beverage is moved to a conveyor, and when the food or beverage on the conveyor is not picked up even after the pickup time, the food or beverage is moved to a storage space.

[0033]

[0034] Hereinafter, the embodiments disclosed in this specification will be described in detail with reference to the attached drawings. Regardless of the drawing numbers, identical or similar components will be given the same reference numbers, and redundant descriptions thereof will be omitted. The suffixes "module" and "part" used for components in the following description are assigned or used interchangeably only for the convenience of writing the specification, and do not in themselves have distinct meanings or roles. In addition, when describing the embodiments disclosed in this specification, if it is determined that a specific description of a related known technology may obscure the gist of the embodiments disclosed in this specification, a detailed description thereof will be omitted. In addition, the attached drawings are only intended to facilitate easy understanding of the embodiments disclosed in this specification, and the technical ideas disclosed in this specification are not limited by the attached drawings, and should be understood to include all modifications, equivalents, and substitutes included in the spirit and technical scope of the present invention.

[0035] Terms that include ordinal numbers, such as first, second, etc., may be used to describe various components, but the components are not limited by these terms. These terms are used solely to distinguish one component from another.

[0036] When a component is referred to as being "connected" or "connected" to another component, it should be understood that it may be directly connected or connected to that other component, but that there may be other components intervening. Conversely, when a component is referred to as being "directly connected" or "connected" to another component, it should be understood that there are no other components intervening.

[0037] In this application, terms such as “include” or “have” are intended to specify the presence of a feature, number, step, operation, component, part or combination thereof described in the specification, but should be understood not to exclude in advance the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts or combinations thereof.

[0038] In this specification, the term "unit" includes a unit realized by hardware, a unit realized by software, and a unit realized using both. Furthermore, a single unit may be realized using two or more pieces of hardware, and two or more units may be realized by a single piece of hardware.

[0039] Some of the operations or functions described herein as being performed by a terminal, apparatus, or device may instead be performed by a server connected to the terminal, apparatus, or device. Similarly, some of the operations or functions described herein as being performed by a server may also be performed by a terminal, apparatus, or device connected to the server.

[0040] Hereinafter, the present invention will be described in detail with reference to the attached drawings.

[0041] Fig. 1 is a drawing showing an unmanned beverage manufacturing device according to an embodiment.

[0042] Referring to FIG. 1, an unmanned beverage manufacturing device (100) according to an embodiment may be configured to include a conveyor (200) and a storage space (301 to 304).

[0043] The conveyor (200) is a space where customers can pick up food or beverages that have been completed in the unmanned beverage manufacturing device (100). In an embodiment, if the food or beverages placed on the conveyor (200) are not picked up, the conveyor moves the food or beverages to a storage space (301).

[0044] As illustrated in FIG. 1, a conveyor (200) is configured in both directions of the unmanned beverage manufacturing device (100), and the manufactured food or beverage can be placed in a container (200) depending on the temperature of the food or beverage. For example, hot food or beverage can be moved to a container (200) connected to one side of the unmanned beverage manufacturing device (100), and cold food or beverage can be moved to a container (200) connected to the other side of the unmanned beverage manufacturing device (100). A plurality of storage spaces are also configured in the container (200) connected to the other side of the unmanned beverage manufacturing device (100) to store cold food or beverage that has not been picked up from the container (200).

[0045] In an embodiment, the unmanned beverage manufacturing device (100) collects order information and pickup time from a customer terminal, and generates a menu preparation order based on the collected order information, pickup time, and food and beverage manufacturing time included in the order information. Thereafter, when the food and beverage included in the order information is manufactured according to the generated menu preparation order, the food and beverage is moved to a conveyor (200), and if the food and beverage on the conveyor (200) is not picked up even after the pickup time, the food and beverage is moved to a storage space (301). In an embodiment, the cover of the storage space where the food and beverage is stored is opened based on the result of the authentication code sensed from the customer terminal, and the food and beverage is provided to the customer.

[0046] In an embodiment, the unmanned beverage manufacturing device (100) can optionally set a customer pickup time selection. This means that the unmanned beverage manufacturing device (100) can select whether to manufacture food and beverage in the order in which order information is received, or to select a customer pickup time and manufacture food and beverage according to the selected pickup time. The unmanned beverage manufacturing device (100) according to the embodiment optionally provides a customer pickup time selection function, which can be set on the administrator terminal of the unmanned beverage manufacturing device (100), and can be set according to the number of collected order information, inventory amount, and the status of the unmanned beverage manufacturing device (100).

[0047] Fig. 2 is a block diagram showing an unmanned beverage manufacturing device according to an embodiment.

[0048] In the embodiment, the unmanned beverage manufacturing device (100) is a computing system that manufactures food and beverages included in order information, provides information on food and beverage manufacturing rates and manufacturing completion to a customer terminal via a computer network, or stores and manages data. The unmanned beverage manufacturing device (100) collects order information and pickup times from a client (customer terminal), and provides a response or data regarding the order information. The configuration of the unmanned beverage manufacturing device (100) illustrated in FIG. 2 is merely a simplified example.

[0049] The communication unit (110) may be configured regardless of the communication mode, such as wired or wireless, and may be configured with various communication networks, such as a personal area network (PAN) and a wide area network (WAN). In addition, the communication unit (110) may operate based on the well-known World Wide Web (WWW), and may also utilize a wireless transmission technology used for short-distance communication, such as infrared (IrDA: Infrared Data Association) or Bluetooth. For example, the communication unit (110) may be responsible for transmitting and receiving data required to perform a technique according to an embodiment of the present disclosure.

[0050] The memory (120) may refer to any type of storage medium. For example, the memory (120) may include at least one type of storage medium among a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (e.g., SD or XD memory, etc.), a RAM (Random Access Memory), a SRAM (Static Random Access Memory), a ROM (Read-Only Memory), an EEPROM (Electrically Erasable Programmable Read-Only Memory), a PROM (Programmable Read-Only Memory), a magnetic memory, a magnetic disk, and an optical disk. Such a memory (120) may also constitute a database as illustrated in FIG. 1.

[0051] The memory (120) can store at least one instruction that can be executed by the processor (130). In addition, the memory (120) can store any type of information generated or determined by the processor (130) and any type of information received by the server (200). For example, the memory (120) stores RM data and RM protocols according to the user, as will be described later. In addition, the memory (120) stores various types of modules, instruction sets, and models.

[0052] The processor (130) may perform technical features according to embodiments of the present disclosure, which will be described later, by executing at least one instruction stored in the memory (120). In one embodiment, the processor (130) may be configured with at least one core and may include a processor for data analysis and / or processing, such as a central processing unit (CPU), a general purpose graphics processing unit (GPGPU), or a tensor processing unit (TPU) of a computer device.

[0053] FIG. 3 is a diagram showing the configuration of a command set stored in memory according to an embodiment.

[0054] Referring to FIG. 3, the instruction set according to the embodiment may be configured to include a collection unit (121), a preprocessing unit (122), a learning unit (123), a generation unit (124), and a feedback unit (125). The term 'unit' used in this specification should be interpreted to include software, hardware, or a combination thereof, depending on the context in which the term is used. For example, the software may be machine language, firmware, embedded code, and application software. As another example, the hardware may be a circuit, a processor, a computer, an integrated circuit, an integrated circuit core, a sensor, a MEMS (Micro-Electro-Mechanical System), a passive device, or a combination thereof.

[0055] The collection unit (121) collects order information, pickup time, and customer information from the customer terminal. In the embodiment, the order information includes information on the type and quantity of beverages and food ordered, and the pickup time is the time for picking up the ordered food and beverage. In the embodiment, the pickup time may be collected in 15-minute and 30-minute time slots. The customer information may include payment completion information and the customer's phone number. In the embodiment, when order information is generated on the customer terminal, the system receives information on available pickup time slots and idle time from the unmanned food and beverage manufacturing device (100), outputs the corresponding time slot and idle time information, and allows the customer to select a desired pickup time. In the embodiment, the idle time refers to an empty time during which food and beverage manufacturing is not performed, and when an additional order is received, the idle time may be changed to a time for manufacturing the food and beverage. In addition, in the embodiment, only idle time information, excluding the manufacturing time, is provided to the customer terminal, and the customer terminal allows the customer to select a pickup time from the idle time.

[0056] In an embodiment, the collection unit (121) collects a learning data set for model generation of an unmanned food and beverage manufacturing device. In an embodiment, the model may include a preparation sequence generation model and a time prediction model. In an embodiment, the learning data set may include manufacturing times based on the type and quantity of food and beverages, and actual food and beverage manufacturing times based on the manufacturing sequence.

[0057] The preprocessing unit (122) preprocesses the collected training data to remove biased or discriminatory data from the collected artificial intelligence learning data set. In an embodiment, the preprocessing unit (122) preprocesses the collected training data set and processes it into a form suitable for artificial intelligence model learning. For example, the preprocessing unit (122) may perform processes such as noise removal, outlier removal, and missing value processing. In addition, the preprocessing unit (122) may normalize data, remove outliers, or adjust the scale of data through data preprocessing to prevent the model from learning unnecessary patterns.

[0058] The learning unit (123) trains a deep learning neural network with the collected training data set to implement a deep learning model. Fig. 4 is a diagram illustrating an example of a model stored in the learning unit and learning data according to an embodiment. Referring to Fig. 4, a preparation order generation model (1) and an order completion time prediction model (2) may be stored in the learning unit (123) of the memory. Each module or model may be in the form of an application executable by the processor (130).

[0059] The preparation order generation model (1) is an artificial neural network model that generates an optimal preparation order for each order piece by considering the creation time of the order piece collected from the unmanned food and beverage manufacturing device, the pickup time, and the types and quantities of the food and beverage included in the order piece. In an embodiment, the preparation order generation model (1) generates an order piece by considering the pickup time so that the food and beverage ordered by the customer is prepared a certain amount of time (e.g., 5 minutes) before the pickup time. This allows the customer to pick up the food and beverage in a fresh state at the time of their choice. In an embodiment, the preparation order generation model (1) can learn by learning the menu type and quantity and the manufacturing time according to the menu type and quantity as a learning data set, and by collecting the actual manufacturing time for the order processing order.

[0060] The order completion time prediction model (2) is an artificial neural network model that calculates the actual food and beverage manufacturing completion time based on the number of order information, the type and quantity of food and beverages included in the order information, and the status of the unmanned food and beverage manufacturing device. In the embodiment, the order completion time prediction model (2) can predict the order information processing and food and beverage manufacturing completion time by determining the food and beverage manufacturing speed based on the status of the food and beverage manufacturing device.

[0061] In an embodiment, the order completion time prediction model (2) collects analysis data that affects order processing and food and beverage manufacturing. In an embodiment, the analysis data may include order time, order contents, food and beverage manufacturing start and completion times, and status data of the food and beverage manufacturing device. In an embodiment, the status data of the food and beverage manufacturing device may include temperature, pressure, inventory, control status, manufacturing stage, error and warning messages, maintenance history, environmental conditions, etc. In an embodiment, the control status is status information including the open / close status of the valve of the food and beverage manufacturing device, the rotation speed of the motor, etc., and can be used to control and monitor the manufacturing process. The manufacturing stage information is the stage or status information of the current manufacturing process, such as mixing, heating, cooling, etc. In an embodiment, the manufacturing process is tracked to more accurately predict the order completion time.

[0062] Afterwards, the order completion time prediction model (2) selects and generates features to be used in the model. These features may include order details, order time, status data of the food and beverage manufacturing equipment, and past order processing and manufacturing times. Afterwards, an appropriate model for predicting order processing and food and beverage manufacturing times is selected. Predictive models for time series data may include linear regression, time series analysis, or deep learning models (e.g., LSTM, GRU). In addition, the order completion time prediction model (2) trains the selected model using a training data set. The model learns the relationship between given input features and outputs (order processing and manufacturing times). In an embodiment, the order completion time prediction model (2) receives order information and the status of the food and beverage manufacturing equipment as inputs each time an order is received, and predicts the order completion time.

[0063] A model in this specification may refer to any form of computer program that operates based on a network function, an artificial neural network, and / or a neural network. Throughout this specification, the terms model, neural network, network function, and neural network may be used interchangeably. A neural network is a network in which one or more nodes are interconnected through one or more links to form input node and output node relationships within the neural network. The characteristics of a neural network can be determined based on the number of nodes and links within the neural network, the correlation between the nodes and links, and the weight value assigned to each link. A neural network may be composed of a set of one or more nodes. A subset of the nodes constituting the neural network may constitute a layer.

[0064] A deep neural network (DNN) may refer to a neural network that includes multiple hidden layers in addition to an input layer and an output layer. A deep neural network may include a convolutional neural network (CNN), a recurrent neural network (RNN), an autoencoder, a generative adversarial network (GAN), a restricted boltzmann machine (RBM), a deep belief network (DBN), a Q network, a U network, a Siamese network, a generative adversarial network (GAN), a transformer, and the like. The description of the above-described deep neural network is merely an example, and the present disclosure is not limited thereto.

[0065] Neural networks can learn through at least one of the following methods: supervised learning, unsupervised learning, semi-supervised learning, self-supervised learning, or reinforcement learning. Neural network learning can be the process of applying knowledge to the neural network to perform a specific action.

[0066] Neural networks can be trained to minimize output errors. This process involves repeatedly inputting training data into the neural network, calculating the neural network output and target error for the training data, and backpropagating the neural network error from the output layer to the input layer to update the weights of each node in the neural network to reduce the error. In supervised learning, labeled data is used for each training data, while unsupervised learning uses unlabeled data. The amount of change in the connection weights of each updated node can be determined by the learning rate. The neural network's calculation of input data and backpropagation of errors can constitute a learning cycle (epoch). The learning rate can vary depending on the number of iterations in the neural network's training cycle. Additionally, to prevent overfitting, methods such as increasing the learning data, regularization, dropout that disables some nodes, and batch normalization layers can be applied.

[0067] In one embodiment, the model may borrow at least a portion of a transformer. The transformer may be composed of an encoder that encodes embedded data and a decoder that decodes the encoded data. The transformer may have a structure that receives a series of data and outputs a series of data of different types through encoding and decoding steps. In one embodiment, the series of data may be processed into a form operable by the transformer. The process of processing the series of data into a form operable by the transformer may include an embedding process. Expressions such as data tokens, embedding vectors, and embedding tokens may refer to data embedded in a form operable by the transformer.

[0068] To encode and decode a series of data, a transformer can utilize an attention algorithm to process the encoders and decoders within the transformer. An attention algorithm can refer to an algorithm that, for a given query, calculates the similarity for one or more keys, reflects this similarity in the values ​​corresponding to each key, and then weights and sums the values ​​to which the similarity is reflected to calculate an attention value.

[0069] Depending on how the query, key, and value are configured, various types of attention algorithms can be categorized. For example, if attention is obtained by setting the query, key, and value all to the same value, this could be a self-attention algorithm. If attention is obtained by reducing the dimensionality of the embedding vector to process a series of input data in parallel and then generating individual attention heads for each segmented embedding vector, this could be a multi-head attention algorithm.

[0070] In one embodiment, the transformer may be composed of modules that perform multiple multi-head self-attention algorithms or multi-head encoder-decoder algorithms. In one embodiment, the transformer may also include additional components other than attention algorithms, such as embedding, normalization, and softmax. Methods for constructing a transformer using attention algorithms may include methods disclosed in Vaswani et al., Attention Is All You Need, 2017 NIPS, which is incorporated herein by reference.

[0071] A transformer can be applied to various data domains, such as embedded natural language, segmented image data, and audio waveforms, to transform a series of input data into a series of output data. To transform data with various data domains into a series of data that can be input to a transformer, the transformer can embed the data. The transformer can process additional data that expresses the relative positional relationship or phase relationship between the series of input data. Alternatively, vectors expressing the relative positional relationship or phase relationship between the input data can be additionally reflected in the series of input data to embed the series of input data. In one example, the relative positional relationship between the series of input data may include, but is not limited to, word order within a natural language sentence, the relative positional relationship between each segmented image, and the time order of segmented audio waveforms. The process of adding information expressing the relative positional relationship or phase relationship between the series of input data may be referred to as positional encoding.

[0072] In one embodiment, the model may include, but is not limited to, at least one of a Recurrent Neural Network (RNN), a Long Short Term Memory (LSTM) network, a Deep Neural Network (DNN), a Convolutional Neural Network (CNN), and a Bidirectional Recurrent Deep Neural Network (BRDNN).

[0073] In one embodiment, the model may be a model trained using transfer learning. Transfer learning, in this context, refers to a learning method that pre-trains a large amount of unlabeled training data using semi-supervised or self-learning methods to obtain a pre-trained model for a first task, then fine-tunes the pre-trained model to suit a second task, and trains it on labeled training data using supervised learning to implement a target model.

[0074] Referring again to FIG. 3, the generation unit (124) determines the types and number of food and beverages included in the order information, and calculates the order completion time required to complete the production of all food and beverages included in the order information using an order completion time prediction model.

[0075] Thereafter, the production unit (124) calculates the preparation time including the order completion time and the reserve time, and controls the unmanned food and beverage production device (100) to start producing the food and beverage included in the order information before the preparation time from the pickup time.

[0076] In an embodiment, the production unit (124) calculates the preparation time and determines when the unmanned food and beverage manufacturing device (100) should start producing the food and beverage. Considering the order completion time and the reserve time, production should begin before the pickup time. In an embodiment, when the determined production start time is reached, the unmanned food and beverage manufacturing device (100) begins producing the food and beverage according to the order information. In an embodiment, the production unit (124) continuously monitors the status of the unmanned food and beverage manufacturing device (100) during food and beverage production to determine whether the device is operating normally and to detect any unexpected problems or errors during the production process.

[0077] In an embodiment, the unmanned beverage manufacturing device (100) places food and beverages on a conveyor belt when they are completed, and if the food and beverages placed on the conveyor belt are not picked up within the pick-up time, the food and beverages are moved to a storage space. In an embodiment, the storage space may include multiple spaces for storing food and beverages that have been prepared but not picked up by customers, and may include a sensor that detects the presence of food and beverages.

[0078] In this embodiment, sensors installed in the storage space detect whether food or beverages are available for pickup. If food or beverages stored in the storage space are not picked up after a certain amount of time from the pickup time, a pickup request message is resent to the customer terminal that ordered the food or beverage, and the food or beverages are moved to the adjacent storage space.

[0079] For example, if the food or beverage on the conveyor is not picked up after a certain period of time from the pickup time, the unmanned food and beverage manufacturing device moves the food or beverage to the first storage space among multiple storage spaces, and if the food or beverage stored in the first storage space is not picked up after a certain period of time, the device moves the food or beverage to the space next to the first storage space.

[0080] In addition, in the embodiment, if the customer does not pick up the stored food or beverage in the storage space, a message indicating the remaining storage time and a food pickup request message may be transmitted to the customer terminal. In the embodiment, each compartment of the storage space may store the food or beverage for a certain period of time (e.g., 30 minutes) and then move it to the next compartment. Accordingly, the generation unit (124) may calculate the remaining food or beverage storage time information according to the storage location of the food or beverage and the start time of storage, and transmit the calculated remaining food or beverage storage time information to the customer terminal. Specifically, if there are a total of five storage spaces, and the food or beverage starts to be located in the second storage space and is stored in each storage space for 30 minutes, the generation unit (124) may calculate the remaining food or beverage storage time as two hours, which is four times 30 minutes. In the embodiment, the generation unit (124) may calculate the pickup request message and the remaining food or beverage storage time and transmit them to the customer terminal every time the food or beverage is moved to the next compartment of the storage space.

[0081] Additionally, in this embodiment, if food or beverages are not picked up even from the last compartment of the storage space, a message requesting disposal or moving to another compartment can be sent to the customer terminal that ordered the food or beverage, and a message requesting disposal of the food or beverage can be sent to the administrator terminal. This allows food or beverages stored in the storage space for a certain period of time but not picked up to be disposed of or moved to another compartment by the administrator.

[0082] In one embodiment, if food or beverage is in the last compartment of a storage space, a food or beverage disposal message is transmitted to the customer terminal. In one embodiment, the food or beverage disposal message may include the remaining storage time for the food or beverage in the last compartment of the storage space, as well as the location of the space to which the food or beverage is to be moved if it is not picked up within the remaining time.

[0083] In the embodiment, the generation unit (124) generates an authentication code corresponding to each order information received from the customer terminal and transmits it to the customer terminal. When the authentication code is entered into the storage space, the entered authentication code is compared with the transmitted authentication code. Thereafter, if the entered authentication code matches the transmitted authentication code, the storage space is opened so that food and beverages stored in the storage space can be picked up.

[0084] In addition, when a bulk order is received, the generation unit (124) enables processing of the bulk order according to the pickup time and preparation time of the bulk order. For example, in the case of a bulk order in which the food and beverage preparation time included in the order information exceeds a certain time, the generation unit (124) checks the pickup time of the bulk order and checks whether there is an idle time in which the bulk order can be prepared before the pickup time. If there is an idle time in which the bulk order can be prepared at once, the bulk order is processed during the idle time. In an embodiment, the generation unit (124) calculates the bulk order preparation time, and if the idle time is greater than the calculated bulk order preparation time, the bulk order is processed during the corresponding idle time.

[0085] In an embodiment, if there is no idle time, the generation unit (124) divides the food and beverages included in the bulk order and prepares each of the divided food and beverages to complete the bulk order. For example, if the bulk order includes 10 drinks, after processing order information for each drink, the drinks included in the bulk order are prepared one by one before processing small orders for making one drink, thereby completing the bulk order. In an embodiment, the bulk order is divided and processed until a certain amount of time before the pickup time of the bulk order, and when the pickup time of the bulk order is approaching (e.g., 15 minutes before pickup), the remaining food and beverages included in the bulk order are prepared to complete the bulk order. In an embodiment, the time approaching the pickup time of the bulk order can be calculated based on the remaining order quantity of the bulk order and the received order information. Specifically, the preparation time for the remaining order quantity can be calculated, and whether to prepare the remaining orders can be determined by comparing the preparation time with the time remaining until the pickup time. In an embodiment, the remaining orders included in the bulk order can be processed from the time when the preparation time matches the time remaining until the pickup time.

[0086] Additionally, in the embodiment, if an idle time exists but is shorter than the bulk order preparation time, the generation unit (124) calculates the difference between the idle time and the bulk order preparation time. Thereafter, the types of food and beverage included in the bulk order information that can be prepared during the difference time are extracted. Thereafter, the generation unit (124) prepares the extracted food and beverage between small orders each containing one beverage, and prepares the remaining food and beverage during the idle time to complete the bulk order.

[0087] In an embodiment, when a bulk order is received, the generation unit (124) can generate a food and beverage preparation order by considering the idle time, the preparation time for each order information included in the bulk order, the pickup time, and other order information through the order generation model.

[0088] The feedback unit (125) evaluates the learned artificial neural network model and deep learning model. In an embodiment, the feedback unit (125) can evaluate the artificial neural network model through at least one of accuracy, precision, and recall. Accuracy is an index that measures how well the results predicted by the artificial neural network model match the actual results. Precision is an index that measures the ratio of actual positives among the results predicted as positive. Recall is an index that measures the ratio of actual positives predicted by the model as positives. In an embodiment, the feedback unit (125) can calculate the accuracy, precision, and recall of the artificial neural network model, and evaluate the artificial neural network model based on at least one of the calculated indexes.

[0089] In an embodiment, the feedback unit (125) can measure the accuracy of the artificial neural network model using an evaluation dataset. The evaluation dataset consists of data that the model did not use for training and is used to objectively evaluate the model's performance. In an embodiment, the feedback unit (125) executes the artificial neural network model using the evaluation dataset and compares the predicted value of the artificial neural network model for each input data with the actual correct answer value of the corresponding data. Thereafter, the accuracy of the model's predictions can be measured based on the comparison results. For example, the accuracy in the feedback unit (125) can be calculated as the ratio of data correctly predicted by the model among the entire data.

[0090] In addition, the feedback unit (125) can calculate the F1 score, which is an index indicating the balance of precision and recall, which is an index calculated as the harmonic mean of precision and recall, evaluate the artificial neural network model based on the calculated F1 score, generate an AUC-ROC curve, which is an index that visualizes the performance of the classification model in a graph, and evaluate the artificial neural network model based on the generated AUC-ROC curve. In an embodiment, the feedback unit (125) can evaluate that the performance of the model is better as the area under the ROC curve (AUC) is closer to 1.

[0091] In addition, the feedback unit (125) can evaluate the interpretability of the artificial neural network model. In an embodiment, the feedback unit (125) evaluates the interpretability of the artificial neural network model through SHAP (SHapley Additive exPlanations) and LIME (Local Interpretable Model-agnostic Explanations) methods. SHAP (SHapley Additive exPlanations) is a library that provides an interpretation of the results predicted by the model, and the feedback unit (125) extracts SHAP values ​​from the library. In an embodiment, the feedback unit (125) can predict how much the characteristic information input to the model influenced the model prediction through the extraction of SHAP values.

[0092] The Local Interpretable Model-agnostic Explanations (LIME) method is a method for explaining model predictions for individual samples. In one embodiment, the feedback unit (125) uses the LIME method to approximate the sample as an interpretable model and calculate the importance of each characteristic. Furthermore, the feedback unit (125) can estimate the influence of each characteristic variable by analyzing the model's internal weights and bias values.

[0093] Below, the data processing process of the unmanned beverage manufacturing device is sequentially described. Since the operation (function) of the method according to the embodiment is essentially the same as the function of the system, any description overlapping with that in FIGS. 1 to 4 will be omitted.

[0094] Fig. 5 is a diagram showing a data processing process of an unmanned beverage manufacturing device according to an embodiment.

[0095] Referring to FIG. 5, in step S100, order information and pickup time are collected from the customer terminal, and in step S200, a menu preparation order is generated based on the collected order information, pickup time, and food and beverage preparation time included in the order information. In step S300, when the food and beverage included in the order information is completed according to the generated menu preparation order, the food and beverage is moved to a conveyor, and if the food and beverage on the conveyor is not picked up after the pickup time, the food and beverage is moved to a storage space. In step S400, an authentication code sensed from the customer terminal is verified, and in step S500, the cover of the storage space is opened based on the authentication code verification result to provide the food and beverage to the customer. In the embodiment, if the authentication code transmitted to the customer terminal and the sensed authentication code match, the cover of the storage space is opened.

[0096] An unmanned beverage manufacturing device and method according to an embodiment can collect a menu and pickup time from a customer terminal and provide the menu ordered by the customer at the pickup time.

[0097] In the embodiment, only idle times, which filter the manufacturing times of food and beverages that have already been paid for according to the schedule, can be selected as pick-up times.

[0098] In an embodiment, the unmanned food and beverage manufacturing device recognizes an authentication code for each order created by a customer, stores the customer's phone number, and allows the customer to select a menu and pickup time at the customer terminal and then make payment.

[0099] Additionally, in the embodiment, food and beverages are manufactured in the order of food and beverage manufacturing generated based on the pickup time and order information, and manufacturing process and pickup request notifications are sent to the customer terminal that sent the prepared order information.

[0100] Additionally, the embodiment provides a temporary storage location and temporary storage process for customers who do not pick up their food or beverage immediately after receiving a pickup notification after the food or beverage is prepared.

[0101] In this embodiment, after food and beverages are prepared, they are moved onto a conveyor belt so that they can be picked up at the designated pickup time. If the food and beverages are not picked up at the designated pickup time, they are moved to multiple storage spaces equipped with transparent covers after preparation.

[0102] Additionally, in the embodiment, when a customer tags a mobile phone to a pickup sensor installed in a storage space, the cover of the space opens, allowing the customer to retrieve food and beverage.

[0103] In addition, in the embodiment, for manufacturing scheduling, the user's waiting time and pickup time are input, and the optimal menu preparation order is generated by considering the preparation time for each menu, the congestion level of the store, and the time and number of menus waiting to be prepared.

[0104] Additionally, in the embodiment, fresh food and beverages can be provided to customers by starting to prepare food and beverages close to the pickup time entered by the user.

[0105] The unmanned beverage manufacturing device and method described above collects order and pickup time information from customers, and performs manufacturing scheduling to complete orders at the customer's pickup time, thereby enabling customers to pick up fresh food and beverages at their desired time.

[0106] Additionally, in the embodiment, food and beverages of customers who do not pick up food and beverages at the pick-up time are stored separately, and food and beverages that have been prepared can be picked up by recognizing an authentication code, thereby preventing orders from being provided to other customers.

[0107] In addition, the example can prevent the mixing of manufactured food and beverages even if the pickup time is not observed.

[0108] The disclosed content is merely an example, and various modifications and implementations can be made by a person skilled in the art without departing from the gist of the claims claimed in the patent, so the scope of protection of the disclosed content is not limited to the specific embodiments described above.

[0109]

[0110] The unmanned beverage manufacturing device and method described above collects order and pickup time information from customers, and performs manufacturing scheduling to complete orders at the customer's pickup time, thereby enabling customers to pick up fresh food and beverages at their desired time.

Claims

1. In an unmanned beverage manufacturing device, a memory storing at least one instruction; and Includes a processor, By executing at least one instruction by the processor, An unmanned beverage manufacturing device that collects order information and pickup time from a customer terminal and generates a menu preparation order based on the collected order information, pickup time, and manufacturing time of each food and beverage included in the order information.

2. In the first paragraph, the unmanned beverage manufacturing device; When the food and beverage included in the order information is completed according to the menu preparation order created, the food and beverage is moved to the conveyor, and if the food and beverage on the conveyor is not picked up after the pick-up time, the food and beverage is moved to the storage space. The above storage space; An unmanned beverage manufacturing device that opens the cover of the storage space and provides the food and beverage to the customer based on the result of the sensed authentication code verification.

3. In the first paragraph, the unmanned beverage manufacturing device; An unmanned food and beverage manufacturing device characterized in that it identifies the types and quantity of food and beverages included in order information, calculates an order completion time required to complete the production of all food and beverages included in the order information, calculates a preparation time including the order completion time and reserve time, and starts producing the food and beverages included in the order information before the preparation time from the pickup time.

4. In the first paragraph, the unmanned beverage manufacturing device; An unmanned beverage manufacturing device characterized by implementing a preparation order generation model by learning the manufacturing time according to the menu type, quantity, and order quantity as a learning data set.

5. In the first paragraph, the unmanned beverage manufacturing device; An unmanned food and beverage manufacturing device having a plurality of storage spaces for storing prepared food and beverages, recognizing whether food and beverages are picked up in the storage spaces, and moving the food and beverages to a storage space in the next compartment if the food and beverages are not picked up after a certain period of time from the time they are placed in the storage spaces.

6. In the first paragraph, the unmanned beverage manufacturing device; An unmanned beverage provision device characterized in that it generates an authentication code corresponding to each order information received from a customer terminal and transmits it to the customer terminal, and when the authentication code is entered into a storage space, it compares the entered authentication code with the transmitted authentication code, and if the entered authentication code and the transmitted authentication code match, it opens the storage space.

7. In the first paragraph, the unmanned beverage manufacturing device; A conveyor for placing finished food and beverages; and A storage space for storing food and beverages not picked up from the conveyor; If the food and beverage on the above conveyor is not picked up after a certain period of time from the pickup time, the food and beverage is moved to the first storage space among the multiple storage spaces, If the food and beverage stored in the first storage space above is not picked up after a certain period of time, the food and beverage is moved to the space next to the first storage space. An unmanned beverage manufacturing device characterized by transmitting a food and beverage pickup request message and food and beverage storage remaining time information to a customer terminal.

Images