System for providing table management service for boosting operational efficiency in restaurant

Abstract

A system for providing table management services for efficient store management is provided, comprising: at least one piezoelectric sensor for detecting pressure on each seat placed at a table; a display for indicating occupancy status, non-occupancy status, and a state requiring cleanup based on detection data monitored by at least one piezoelectric sensor; a seat storage unit for storing a mapping between at least one piezoelectric sensor and a seat number; a table storage unit for storing a mapping between a table number where at least one piezoelectric sensor is placed and a seat number; an occupancy display unit for outputting an occupancy status indicating that the table number and seat number mapped to at least one piezoelectric sensor are in use when pressure is monitored by at least one piezoelectric sensor; a cleanup guide unit for re-checking the presence of pressure after waiting for a preset time when pressure is not applied to at least one piezoelectric sensor in the occupancy status, and if pressure is not monitored as a result of the re-check, displaying the occupancy status as a state requiring cleanup; and an available seat display unit for outputting the state requiring cleanup as a non-occupancy status indicating available seats when a clear button is selected for a table number in the state requiring cleanup.

Description

Technology Field

[0001] The present invention relates to a table management service provision system for efficient store management, and provides a system capable of providing real-time guidance on tables requiring organization by displaying occupancy status, status requiring organization, and non-occupancy status. Background Technology

[0002] Servicescape is a concept defining the physical environment as an intentionally created space. It originated from the perspective that the location where a product is consumed is one of its most important characteristics, and that the atmosphere of that place can have a greater influence on a consumer's purchasing decision than the product itself, effectively viewing the atmosphere as a product. It refers to an objective and artificially created physical space within a company's control where a service takes place. Since this physical environment cannot be hidden and can significantly impact customers' perceptions of the service experience, the physical environment is effective in influencing the value customers perceive from products and services. It exerts a powerful influence on the customer's consumption experience and serves as a means to satisfy customer needs, shape a corporate image, and differentiate itself from competitors. The components of servicescape include atmosphere, cleanliness, comfort, aesthetics, and spatial layout functionality.

[0003] At this time, a system for organizing tables to make the physical environment pleasant was researched and developed. In this regard, prior art Korean Registered Patent No. 10-1221644 (published January 14, 2013) and Korean Published Patent No. 2014-0059678 (published May 16, 2014) disclose a configuration in which, after collecting video information using a camera installed in a store, the occupancy or non-occupancy of a table is determined based on the video information, and if the table is non-occupied, it is determined whether table organization is required, and if table organization is required, a table number is provided to a user terminal to enable store management; and a configuration in which, using a piezoelectric element installed on a seat in a vehicle, the seat occupancy is determined based on whether the passenger is seated, the arrival information of the passenger occupying the seat is extracted, and the train's location information and ticket issuance information are linked to provide a vibration notification that the passenger is scheduled to arrive based on the arrival information.

[0004] However, the former merely indicates whether a table is occupied or unoccupied; it does not provide guidance on whether the table has transitioned from occupied to unoccupied, or consequently whether cleaning is required. Similarly, the latter merely identifies passenger seat occupancy within the train and does not provide information on whether the seat has transitioned from occupied to unoccupied or vice versa, or whether seat tidying is necessary. With the recent increase in prepaid establishments, self-service models where customers clear their own cups and dishes rather than managing table status through POS systems are becoming more common. Since customers do not wipe the tables themselves, timing often fails when owners or staff attempt to clean tables—such as when customers are still present or another customer arrives immediately—resulting in inefficient movement for the owners or staff. Therefore, research and development are required for a system that enables efficient table tidying by distinguishing and displaying not only the occupied and unoccupied status of a seat, but also the state requiring cleaning, which is the transition from occupied to unoccupied. The problem to be solved

[0005] One embodiment of the present invention provides a table management service provision system for efficient store management, which displays the "In Use" occupancy status when pressure is monitored by a piezoelectric sensor installed on at least one seat mapped to a table, changes the occupancy status to a "Cleaning Needed" status and displays it along with a "Clean" button when the pressure is not monitored and a preset time is exceeded, and displays the "Cleaning Needed" status of the table as an "Available Seat" in an "Unoccupied" state when the "Clean" button is selected. This allows for the rapid cleaning of tables after a customer leaves, even when table management is not performed due to prepayment, while efficiently maintaining the cleanliness and comfort of the servicescape without wasting movement by staff or the store owner. However, the technical problem that this embodiment aims to solve is not limited to the technical problem described above, and other technical problems may exist. means of solving the problem

[0006] As a technical means for achieving the aforementioned technical problem, one embodiment of the present invention comprises a management service providing server including: at least one piezoelectric sensor for detecting pressure on each seat placed on a table; a display for displaying an occupied state, an unoccupied state, and a state requiring cleanup based on detection data monitored by at least one piezoelectric sensor; a seat storage unit for storing a mapping between at least one piezoelectric sensor and a seat number; a table storage unit for storing a mapping between a table number of a table where at least one piezoelectric sensor is placed and a seat number; an occupancy display unit for outputting an occupied state indicating that the table number and seat number mapped to at least one piezoelectric sensor are in use when pressure is monitored by at least one piezoelectric sensor; a cleanup guide unit for re-checking the presence of pressure after waiting for a preset time when pressure is not applied to at least one piezoelectric sensor in the occupied state, and displaying the occupancy state as a state requiring cleanup when pressure is not monitored as a result of the re-check; and an available seat display unit for outputting the state requiring cleanup as an unoccupied state indicating available seats when a clearing button is selected on a table number in the state requiring cleanup. Effects of the invention

[0007] According to any one of the means for solving the problem of the present invention described above, when pressure is monitored by a piezoelectric sensor installed on at least one seat mapped to a table, the occupied state is displayed as "in use"; when the pressure is not monitored and a preset time is exceeded, the occupied state is changed to a state requiring cleaning and displayed along with a "Clean" button; and when the "Clean" button is selected, the state requiring cleaning of the table is displayed as an available seat in an unoccupied state. This allows for the rapid handling of table cleaning management after a customer leaves, even when the table is not managed due to prepayment, while efficiently maintaining the cleanliness and comfort of the servicescape without wasting movement by staff or the owner. Brief explanation of the drawing

[0008] FIG. 1 is a drawing illustrating a table management service provision system for efficient store management according to one embodiment of the present invention. Figure 2 is a block diagram illustrating a management service provider server included in the system of Figure 1. FIGS. 3 and 4 are drawings for explaining an embodiment in which a table management service for efficient store management according to an embodiment of the present invention is implemented. FIG. 5 is a flowchart illustrating a method for providing a table management service for efficient store management according to an embodiment of the present invention. Specific details for implementing the invention

[0009] Embodiments of the present invention are described below with reference to the attached drawings so that those skilled in the art can easily implement the invention. However, the present invention may be embodied in various different forms and is not limited to the embodiments described herein. Furthermore, in order to clearly explain the present invention in the drawings, parts unrelated to the explanation have been omitted, and similar parts throughout the specification are denoted by similar reference numerals.

[0010] Throughout the specification, when a part is described as being "connected" to another part, this includes not only cases where they are "directly connected" but also cases where they are "electrically connected" with other elements interposed between them. Furthermore, when a part is described as "including" a component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components, and it should be understood that this does not preclude the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0011] Terms such as “about,” “substantially,” etc., used throughout the specification, are used to mean at or near the stated value when inherent manufacturing and material tolerances are presented in the stated meaning, and are used to prevent unscrupulous infringers from unfairly exploiting the disclosure in which precise or absolute values ​​are mentioned to aid in understanding the invention. Terms such as “step” or “step of” used throughout the specification of the invention do not mean “step for”.

[0012] In this specification, the term "part" includes a unit realized by hardware, a unit realized by software, and a unit realized using both. Additionally, one unit may be realized using two or more pieces of hardware, and two or more units may be realized by one piece of hardware. Meanwhile, "part" is not limited to software or hardware, and "part" may be configured to reside in an addressable storage medium or configured to run on one or more processors. Accordingly, as an example, "part" includes components such as software components, object-oriented software components, class components, and task components, as well as processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functions provided within the components and "parts" may be combined into a smaller number of components and "parts" or further separated into additional components and "parts." In addition, the components and '~parts' may be implemented to play one or more CPUs within the device or secure multimedia card.

[0013] Some of the operations or functions described herein as being performed by a terminal, device, or device may instead be performed by a server connected to said terminal, device, or device. Likewise, some of the operations or functions described as being performed by a server may also be performed by a terminal, device, or device connected to said server.

[0014] In this specification, some of the operations or functions described as mapping or matching with a terminal may be interpreted as meaning mapping or matching the terminal's unique number or personal identification information, which is the terminal's identifying data.

[0015] The present invention will be described in detail below with reference to the attached drawings.

[0016] FIG. 1 is a diagram illustrating a table management service provision system for efficient store management according to an embodiment of the present invention. Referring to FIG. 1, the table management service provision system (1) for efficient store management may include at least one user terminal (100), a management service provision server (300), at least one display (400), at least one piezoelectric sensor (500), and a kiosk (600). However, since the table management service provision system (1) for efficient store management of FIG. 1 is merely an embodiment of the present invention, the present invention is not to be interpreted as being limited by FIG. 1.

[0017] At this time, each component of FIG. 1 is generally connected through a network (Network, 200). For example, as shown in FIG. 1, at least one user terminal (100) can be connected to a management service provider server (300) through the network (200). And, the management service provider server (300) can be connected to at least one user terminal (100), at least one display (400), at least one piezoelectric sensor (500), and a kiosk (600) through the network (200). Also, at least one display (400) can be connected to the management service provider server (300) through the network (200). And, at least one piezoelectric sensor (500) can be connected to at least one user terminal (100), the management service provider server (300), and at least one display (400) through the network (200). Finally, the kiosk (600) can be connected to a user terminal (100), a display (400), a management service provider server (300), and at least one piezoelectric sensor (500) through a network (200).

[0018] Here, a network refers to a connection structure capable of exchanging information among individual nodes, such as multiple terminals and servers. Examples of such networks include Local Area Networks (LANs), Wide Area Networks (WANs), the World Wide Web (WWW), wired and wireless data networks, telephone networks, and wired and wireless television networks. Examples of wireless data communication networks include, but are not limited to, 3G, 4G, 5G, 3GPP (3rd Generation Partnership Project), 5GPP (5th Generation Partnership Project), LTE (Long Term Evolution), WIMAX (World Interoperability for Microwave Access), Wi-Fi, Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network), RF (Radio Frequency), Bluetooth network, NFC (Near-Field Communication) network, satellite broadcasting network, analog broadcasting network, DMB (Digital Multimedia Broadcasting) network, etc.

[0019] In the following, the term "at least one" is defined as a term including both singular and plural forms, and it will be obvious that even if the term "at least one" does not exist, each component may exist in a singular or plural form and may mean singular or plural. Furthermore, whether each component is provided in a singular or plural form may be changed according to the embodiment.

[0020] At least one user terminal (100) may be a terminal of a store that displays the occupancy status, non-occupancy status, and status requiring cleaning of tables by table and seat number using a web page, app page, program, or application related to a table management service for efficient store management. In this case, the user terminal (100) may include a POS, but it is not essential. Also, if it is installed as a standalone in only one store, a program including the functions of a management service provider server (300) may be installed on the user terminal (100) so that the processes of the management service provider server (300) can be performed on the user terminal (100), and in this case, the management service provider server (300) may be deleted. If multiple stores are managed by the management service provider server (300) and operated on a SaaS basis, the user terminal (100) may perform only the role of a display (400) that displays only results. However, since each component can be changed according to the embodiment, it is not limited to the configuration according to any one embodiment.

[0021] Here, at least one user terminal (100) may be implemented as a computer capable of connecting to a remote server or terminal via a network. Here, the computer may include, for example, a laptop, desktop, or laptop equipped with a navigation system or a web browser. At this time, at least one user terminal (100) may be implemented as a terminal capable of connecting to a remote server or terminal via a network. At least one user terminal (100) may include all kinds of handheld-based wireless communication devices, such as navigation, PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet) terminal, smartphone, smartpad, tablet PC, etc.

[0022] The management service providing server (300) may be a server that provides a table management service web page, app page, program, or application for efficient store management. Additionally, the management service providing server (300) may be a server that enables the occupancy status, cleanup need status, and non-occupancy status of each table to be displayed on the user terminal (100) or display (400) when at least one piezoelectric sensor (500) is registered to each seat of each table on the user terminal (100). At this time, the management service providing server (300) may be a server that measures and outputs the table turnover rate according to the order of the kiosk (600) and [occupancy status - cleanup need status - non-occupancy status]. Additionally, the management service providing server (300) may be a server that performs labeling by synchronizing the frames of video input from the camera with the occupancy status, cleanup need status, and non-occupancy status when a camera is installed in the store, and performs modeling by building a dataset and learning and verifying an image recognition model. Accordingly, the management service providing server (300) may be a server that outputs whether each table and seat needs to be organized through a camera when the image recognition model is modeled with a sufficient dataset.

[0023] Here, the management service providing server (300) may be implemented as a computer capable of connecting to a remote server or terminal via a network. Here, the computer may include, for example, a laptop, desktop, laptop, etc. equipped with a navigation system and a web browser.

[0024] At least one display (400) may be a device that outputs a table number, occupancy status, cleanup need status, and non-occupancy status respectively using a web page, app page, program, or application related to a table management service for efficient store management, outputs a cleanup button on the cleanup need status, and when the cleanup button is selected, switches the cleanup need status to a non-occupancy status and displays it.

[0025] Here, at least one display (400) may be implemented as a computer capable of connecting to a remote server or terminal via a network. Here, the computer may include, for example, a laptop, desktop, or laptop equipped with a navigation system or a web browser. At this time, at least one display (400) may be implemented as a terminal capable of connecting to a remote server or terminal via a network. At least one display (400) may include all kinds of handheld-based wireless communication devices, such as navigation, PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet) terminal, smartphone, smartpad, tablet PC, etc.

[0026] At least one piezoelectric sensor (500) may be a sensor that detects whether pressure is applied and outputs an output value, whether or not a web page, app page, program, or application related to a table management service for efficient store management is used. At this time, the output value of the piezoelectric sensor (500) may be transmitted to a management service providing server (300) via a wired or wireless network, and the management service providing server (300) may use this to determine the occupied state, the state requiring cleanup, and the non-occupied state, and then output it to a user terminal (100) or a display (400).

[0027] The kiosk (600) may be a device that accepts orders and proceeds with the payment process with or without using a web page, app page, program, or application related to a table management service for efficient store management.

[0028] Here, the kiosk (600) may be implemented as a computer capable of connecting to a remote server or terminal via a network. Here, the computer may include, for example, a laptop, desktop, or laptop equipped with a navigation system or a web browser. At this time, the kiosk (600) may be implemented as a terminal capable of connecting to a remote server or terminal via a network. The kiosk (600) may include all kinds of handheld-based wireless communication devices, such as navigation, PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet) terminal, smartphone, smartpad, tablet PC, etc.

[0029] FIG. 2 is a block diagram for explaining a management service providing server included in the system of FIG. 1, and FIG. 3 and FIG. 4 are drawings for explaining an embodiment in which a table management service for efficient store management according to an embodiment of the present invention is implemented.

[0030] Referring to FIG. 2, the management service providing server (300) may include a seat storage unit (310), a table storage unit (320), an occupancy display unit (330), a sorting guide unit (340), an available seat display unit (350), a table confirmation unit (360), an image analysis unit (370), a status change unit (380), a modeling unit (390), a turnover rate measurement unit (391), and a remaining seat notification unit (393).

[0031] When a management service providing server (300) or another server (not shown) operating in conjunction with one embodiment of the present invention transmits a table management service application, program, app page, web page, etc. for efficient store management to at least one user terminal (100) and at least one display (400), the at least one user terminal (100) and at least one display (400) may install or open the table management service application, program, app page, web page, etc. for efficient store management. Additionally, a service program may be operated on at least one user terminal (100) and at least one display (400) using a script executed in a web browser. Here, a web browser refers to a program that enables the use of web (WWW: World Wide Web) services and receives and displays hypertext described in HTML (Hyper Text Mark-up Language), and includes, for example, Netscape, Explorer, Chrome, etc. In addition, "application" refers to an application on a terminal, and includes, for example, an app running on a mobile terminal (smartphone).

[0032] Referring to FIG. 2, the seat storage unit (310) can store a seat number by mapping at least one piezoelectric sensor (500) to the seat number. The number of piezoelectric sensors (500) is equal to the number of seats and can be stored by mapping them one-to-one. At this time, at least one piezoelectric sensor (500) can detect pressure on each seat placed on the table. In the case where there are four seats on a table, even if a customer sits on only one of the four seats, the table is considered occupied, so a piezoelectric sensor (500) can be provided on each seat to determine whether it is occupied.

[0033] In this case, the sensor converts various input information into electrical signals. Smart sensors, as intelligent sensors, consist of a sensor, a microprocessor signal processor, a wireless communication interface, and a power supply. The signal processor collects and processes information for IoT services from the sensor's output signal and performs the function of transmitting it to the sensor network via the wireless communication interface. Although smart sensors are applied in various fields as a central component for implementing IoT services, there are issues regarding maintenance and costs associated with battery replacement. Additionally, battery-operated smart sensors are constrained by the requirement to operate on a low-power basis. To resolve the battery issues of IoT devices, including smart sensors, energy harvesting technology can be applied to obtain electrical energy from ambient energy sources such as light, vibration, heat, and RF signals. Since smart sensors, which are core devices for implementing IoT services, require a continuous power supply to periodically and repeatedly transmit sensed data to a gateway, an auxiliary battery was connected in the prototype fabrication and demonstration shown in Fig. 4c; however, energy harvesting can be applied to resolve the battery issue.

[0034] At this time, since relatively high output energy is required compared to the data collection process to transmit collected data to a management service provider server (300) or a router via wireless communication, it is common to use an energy storage device such as a battery. However, using an energy storage device is difficult to manage, such as replacing it according to the usage cycle, and increases in size and cost depending on the capacity. To solve these problems, implementing a system that can supply energy without using an energy storage device by utilizing an energy harvesting system can be one alternative. However, an energy harvesting system utilizing sensor nodes has a significantly limited scope of application due to difficulties in processes such as wireless communication that require a lot of power. Furthermore, the operation of the system is unstable because power is not supplied consistently depending on the environment or the energy to be converted. Accordingly, to compensate for the disadvantages of general energy harvesting, a Switch Control Unit can be used to design the system so that the harvested energy is stored in an energy storage device or all harvested and stored energy can be used instantaneously by the application, depending on the amount of harvested energy and the application operation mode. Of course, it is not limited to the configuration described above, and it may also be equipped to perform power supply and communication via a wired connection.

[0035] The table storage unit (320) can store the table number of a table in which at least one piezoelectric sensor (500) is placed by mapping it to the seat number. At this time, each seat in which at least one piezoelectric sensor (500) is installed can be stored by mapping it to each table. Since there are 2, 3, 4, etc. chairs in each table, it can be stored by mapping as [Table-Seat-Piezoelectric Sensor]. The table number may be the same as the number listed on the POS of the user terminal (100), but it may also be different.

[0036] The occupancy indicator (330) can output the table number and seat number mapped to at least one piezoelectric sensor (500) as an occupancy status indicating use when pressure is monitored at at least one piezoelectric sensor (500). The display (400) can display an occupancy status, an unoccupied status, and a status requiring cleaning based on detection data monitored at at least one piezoelectric sensor (500).

[0037] The cleanup guide (340) may wait for a preset time and then recheck whether pressure is present when pressure is not applied to at least one piezoelectric sensor (500) in the occupied state, and if pressure is not monitored as a result of the recheck, the occupied state may be displayed as a state requiring cleanup. At this time, the preset time may be, for example, 5 minutes, but is not limited thereto.

[0038] The available seat indicator (350) can output the state requiring cleaning as an unoccupied state indicating available seats when the clear button is selected for the table number in the state requiring cleaning. The clear button can be selected by touch on the display (400) or user terminal (100), but a button method is not excluded. Alternatively, if a button is provided on each seat, the design may be such that the clear button is selected by pressing each button.

[0039] The table checking unit (360) is equipped with at least one piezoelectric sensor (500) that detects pressure applied to the table, and checks the pressure applied to the table when the pressure applied to the seat is not monitored, and can change the occupancy status to a state requiring cleaning when no pressure is applied to the table. At this time, the table management service provision system (1) for efficient store management may further include at least one piezoelectric sensor (500) that detects pressure applied to the table. For example, if a seat is vacated while briefly going to the restroom, items such as coffee or a laptop may remain on the table. In this case, to prevent the table from being cleared, an additional piezoelectric sensor (500) may be provided to determine whether there are items on the table. At this time, the number of cases for determining whether cleaning is required based on the detection of the piezoelectric sensor (500) of the table and seat may be set as shown in Table 1 below.

[0040] Table piezoelectric sensor Seat piezoelectric sensor Needs cleaning detect detect X detect Not detected △ (Employee check required) Not detected detect X Not detected Not detected O

[0041] If the table piezoelectric sensor (500) detects something but the seat is not, it may be ambiguous whether the customer has not cleaned up trash, such as coffee or a hamburger, or will return. In this case, the number of the table may be displayed to the staff to check, and a status indicating that a check is required may be further displayed on the display (400).

[0042] The image analysis unit (370) can determine whether at least one table is occupied based on an image recognition model from an image captured by at least one camera, and display the occupied state, the state requiring cleaning, and the state of non-occupancy on the table number. At this time, at least one additional camera capturing the store may be included. For example, a large dataset is required to train and verify the image recognition model. To build the dataset, images of tables in an occupied state, images of tables in a state requiring cleaning, and images of tables in a non-occupied state are required, and all of these images must be manually labeled to determine what kind of image it is, that is, whether it is in an occupied state, a state requiring cleaning, or a state of non-occupancy. When a labeler is hired, not only does the labeling cost increase, but the time also increases. However, in one embodiment of the present invention, the occupancy state, non-occupancy state, and state requiring cleanup are identified using a piezoelectric sensor (500). Therefore, when a frame of the image at this point is extracted and each state is stored as a label in the image corresponding to this frame, the construction of a labeled dataset is completed without hiring a labeler.

[0043] The state change unit (380) can change the state of occupancy to a state requiring cleanup when it is determined that the table number is in an occupied state and that an object corresponding to a human located at the table is moving toward the exit of the store while in the occupied state. The state change unit (380) can change the state of occupancy to a state requiring cleanup when it is determined that an object corresponding to a human is moving toward the exit of the store while carrying an object corresponding to personal belongings. If there are no personal belongings, beverages such as coffee, or laptops on the table, it is an empty seat, i.e., an available seat, in a non-occupied state. However, if there is no person but only coffee on the table, it is difficult to determine whether the person has briefly left, for example, gone to the restroom, went out to smoke, or actually left the store without clearing the cup in a self-service situation. In this case, if the person has gathered all personal belongings and gone to the exit, and the coffee, etc., is empty, the state can be changed to a state requiring cleanup, and to determine this case, it can determine whether the object includes all personal belongings.

[0044] Object detection, which aims to replicate human visual capabilities using artificial intelligence, involves analyzing a given image to identify the location and class of a specific object. Object detection algorithms must first locate the object's position (localization) within the image and then classify what kind of object it is. Various methods have been attempted to achieve this, but recently, the focus has narrowed down to single-stage and two-stage detection methods. The single-stage detection method performs location detection and classification simultaneously across all regions. The two-stage detection method performs approximate location detection and then classifies the selected candidate groups. Since single-stage detection performs location detection and classification simultaneously across all regions, it is faster but has the disadvantage of slightly lower accuracy compared to the two-stage method. Conversely, because the two-stage detector performs location detection and classification sequentially, it offers relatively superior accuracy but suffers from the disadvantage of slower speed. Representative examples of single-stage detectors include YOLO and SSD algorithms, while representative examples of two-stage detectors include R-CNN and Faster R-CNN. Single-stage and two-stage methods each have their own advantages in terms of recognition speed and accuracy. In this case, a single-stage or two-stage detection method can be used to determine whether a customer is carrying personal belongings or if any belongings remain on a table or seat.

[0045] In addition, while the need for cleanup can be identified by classifying objects using the method described above, a model can also be utilized to determine whether a customer has actually left or is merely stepping outside for a brief moment by analyzing a series of actions—such as entering a store, placing an order, sitting down, spending a certain amount of time, and then exiting—and using a model to classify human behavior. Recently, various camera equipment and technologies have become widespread, and intelligent video systems utilizing image and video data are being developed; consequently, methods for analyzing human intent using a series of video frames are also being developed. In this context, to identify human intent, it is necessary to examine video frames over a specific period of time. Since 3D convolution extracts features by considering not only spatial features but also specific frames—that is, time—it is well-suited for analyzing human behavior using continuous video.

[0046] Accordingly, in one embodiment of the present invention, human behavior using a Large Human Motion Database (HMDB) may be analyzed using 3D convolution, or a video recognition model may be modeled by collecting a series of human actions [entry-ordering-sitting-exiting] after constructing CCTVs of each cafe as big data. Furthermore, since the purpose according to one embodiment of the present invention is to determine whether cleaning is necessary, in cases where cleaning is not necessary—for example, when going to the restroom, a series of video frames may be secured showing the user moving toward the restroom after asking a staff member for the location or password of the restroom with or without personal belongings, and this can be determined as 'staying' to display the table as 'in use' (occupancy state). In cases where the user goes to smoke, a series of video frames may be secured showing the user putting cigarettes in their pocket or checking a lighter while leaving personal belongings behind, and this can be determined as 'staying' to display the table as 'in use' (occupancy state). This is because if the table is cleared when the user is in use (occupancy state) even after finishing their coffee, the customer may perceive it as an intention to leave quickly, and other customers may sit at the table, so caution must be exercised. In addition, although the number of study cafes has increased recently, there are still people who study in cafes, known as "cafe study groups." Consequently, there are instances where a person leaves their seat for a long time and takes their belongings with them, or returns after going out to eat. Since the seat must not be cleaned in such cases, the system can learn whether a person has actually left or is still staying by training on a series of these actions through video frames. If the video recognition model makes an incorrect check, an employee can press an error button to collect the video frames again and perform retraining to correct the error.

[0047] A ResNet using general 2D convolution analyzes images using a network that extracts features from the spatial information of an image, whereas a 3D ResNet using 3D convolution is composed of a network that extracts features from the spatial information of an image and the time-series information of a continuous image, and can be used for recognizing, detecting, and predicting human behavior in continuous images. Accordingly, in one embodiment of the present invention, spatial and time-series features are extracted and each feature is used as an attention map to compare the performance of the networks.

[0048] 3D Convolution

[0049] 2D convolution uses image inputs as c×h×w, i.e., the number of channels (c), height (h), and width (w), and extracts spatial features using a default kernel size of 3×3. However, video inputs use continuous image data as c×l×h×w, i.e., the number of channels, length of frames, height, and width. With the addition of the number of frames, it has a 3×3×3 convolution kernel size capable of extracting spatiotemporal features. 3D convolution can classify human behavior by extracting prominent features from frames.

[0050] 3D Attention Map

[0051] An attention map utilizing spatial information extracts a mask of an object within an image and incorporates spatial information into the corresponding region through an addition operation, thereby having the effect of emphasizing the object. A 3D attention map according to an embodiment of the present invention constructs a network capable of emphasizing continuous temporal information regarding human behavior by adding spatiotemporal information in addition to spatial information to a continuous series of images. The 3D attention map is applied through a multiplication operation as shown in Equation 1 of the Temporal and Spatial feature maps.

[0052]

[0053] <Space-Time Attention Map>

[0054] 3D convolution using video images can generate a spatiotemporal attention map that considers spacetime. An attention map is generated by extracting feature values ​​for each time step of changes in motion within the video over time through Average Pooling and Max Pooling. The generated attention map applies spatiotemporal information by performing a multiplication operation with the feature map generated through the previous Convolution Block.

[0055] Spatial Attention Map

[0056] A Spatial Attention Map can utilize Dilated Convolution to extract spatial information using a Feature Map with applied spatiotemporal attention. Dilated Convolution has the advantage of extracting morphological features of objects by extracting context from a wide area. In the case of a 3×3 convolution with a Dilated Rate of 2, it covers the area of ​​a 5×5 convolution while having the same effect as a 3×3 convolution in terms of total computational amount. Spatial features can be generated by applying these two Dilated Convolutions along with a 1×1 Convolution and applied to a Feature Map containing spatiotemporal information.

[0057] The modeling unit (390) constructs a dataset by labeling the occupied state, the state requiring cleaning, and the non-occupied state based on the piezoelectric sensor (500) onto images of tables and seats confirmed by a camera, and performs modeling by training and verifying at least one image recognition model using the dataset, and can extract and set the image recognition model with the highest accuracy among at least one image recognition model. At this time, by analyzing a series of customer actions, it is possible to predict whether the customer will leave or go to the restroom. For example, a person attempting to get off a bus or subway exhibits specific behaviors, such as rummaging through their bag to organize their belongings, looking outside to check the stop, or attempting to press the bell. Similarly, in cafes, if such a series of actions is identified, it is possible to determine whether the customer intends to leave or go to the restroom. By using a Long Short-Term Memory (LSTM) capable of analyzing a series of time-series data, the customer's behavior can be predicted, and an informational message can be provided when an employee cleans and wipes the table.

[0058] The turnover rate measurement unit (391) can measure the occupied state, the state requiring tidying up, and the non-occupied state as a single turnover, calculate the table turnover rate of the table, and transmit it to the user terminal (100). For example, if there are 60 seats and a total of 200 people sit in one day, the seat turnover rate becomes 3.34. In addition, by utilizing the process of [occupied state - state requiring tidying up - non-occupied state], not only the seat turnover rate but also the seat occupancy rate can be provided, and a report can be provided to perform price differentiation using the seat turnover rate, and downsizing and TableMix using the seat occupancy rate. Through this, it can be used as basic data when conducting consulting to improve RevPASH (Revenue Per Available Seat Hour). In addition, consulting results can be provided to improve the customer mix through marketing, advertising, coupon provision, events, etc., for customer demand leveling work, after identifying how to disperse the congestion level during peak times by day of the week and time of day using the seat occupancy rate.

[0059] The remaining seat alarm unit (393) can upload the occupancy status, the status requiring cleaning, and the non-occupancy status in real time, and can display and output the number of remaining seats and tables. Looking at many restaurant and cafe applications released recently, they are designed so that customers directly select whether to occupy a seat and make a reservation. In this case, although the customer directly performs the reservation, there is a problem in that the customer does not necessarily mark it as non-occupancy when leaving, so a problem occurs where a seat that is not actually occupied—that is, a seat that the customer has left—appears to be occupied on the application. At this time, since the status is automatically uploaded through the piezoelectric sensor (500) in one embodiment of the present invention, the status of the seat can be identified from a remote location without pressing the reservation or exit button, and even if the entire third floor is a cafe, it is efficient in terms of convenience because one can determine whether to go up after identifying where the seat is empty and not empty without having to search for a seat from the first floor to the third floor.

[0060] Hereinafter, the operation process according to the configuration of the management service providing server of FIG. 2 described above will be explained in detail with reference to FIG. 3 and FIG. 4. However, it is obvious that the embodiment is merely one of the various embodiments of the present invention and is not limited thereto.

[0061] Referring to FIG. 3, (a) a management service provider server (300) can store maps of tables and seats and can build a database by mapping each piezoelectric sensor (500) to a seat. Additionally, by defining each status as in (b), it is possible to define when to display an occupied state, when to display an unoccupied state, when to display a state requiring cleaning, and when to return to the initial screen, which is an available seat, i.e., an unoccupied state, if an action is taken in the state requiring cleaning. Through the sensor values ​​collected by the piezoelectric sensor (500) and the state definition of (b), outputs can be made to a display (400) or user terminal (100) as in (c), and ultimately, as in (d), modeling can be performed by learning and verifying an image recognition model so that the occupancy, unoccupancy, and need for cleaning of the table can be determined solely through image recognition via camera integration. At this time, since errors can be checked and labeled based on feedback from each employee, the dataset containing errors can be re-labeled as a dataset corrected by feedback and retrained. The applicant constructed an algorithm using programming (Python) as shown in FIG. 4a, manufactured a prototype piezoelectric sensor (500) as shown in FIG. 4b, supplied power as shown in FIG. 4c, and applied it to a cushion as shown in FIG. 4d and FIG. 4e. As shown in FIG. 4f, when the [Cleaned] button is clicked or touched in the [Cleaning Needed State] on the screen, that is, when an employee cleans the table and [Cleaned] is touched or clicked, a screen showing the [Can Use] state can be displayed as shown in FIG. 4g, and the initial screen of the [Can Use] state can be displayed as a available seat.

[0062] As for matters not described in the method for providing a table management service for efficient store management shown in FIGS. 2 to 4, they are identical to or can be easily inferred from the content described above regarding the method for providing a table management service for efficient store management shown in FIG. 1, so further explanation will be omitted.

[0063] FIG. 5 is a diagram illustrating the process of transmitting and receiving data between each component included in the table management service providing system for efficient store management of FIG. 1 according to an embodiment of the present invention. Hereinafter, an example of the process of transmitting and receiving data between each component will be described through FIG. 5, but the present invention is not to be interpreted as being limited to such an embodiment, and it is obvious to those skilled in the art that the process of transmitting and receiving data illustrated in FIG. 5 may be changed according to various embodiments described above.

[0064] Referring to FIG. 5, the management service providing server,

[0065] The order of the steps described above (S5100~S5400) is merely an example and is not limited thereto. That is, the order of the steps described above (S5100~S5400) may vary, and some of these steps may be executed simultaneously or deleted.

[0066] As for matters not described regarding the method for providing a table management service for efficient store management shown in Fig. 5, they are identical to or can be easily inferred from the content described above regarding the method for providing a table management service for efficient store management shown in Figs. 1 to 4, so further explanation will be omitted.

[0067] A method for providing a table management service for efficient store management according to one embodiment described through FIG. 5 may also be implemented in the form of a recording medium containing computer-executable instructions, such as an application or program module executed by a computer. A computer-readable medium may be any available medium accessible by a computer and includes both volatile and non-volatile media, and both removable and non-removable media. Additionally, a computer-readable medium may include all computer storage media. Computer storage media include both volatile and non-volatile, removable and non-removable media implemented by any method or technique for storing information such as computer-readable instructions, data structures, program modules, or other data.

[0068] The method for providing a table management service for efficient store management according to one embodiment of the present invention described above may be executed by an application basically installed on a terminal (which may include a program included in a platform or operating system, etc., basically installed on the terminal), or by an application (i.e., a program) directly installed by a user on a master terminal through an application providing server, such as an application store server, an application, or a web server related to the service. In this sense, the method for providing a table management service for efficient store management according to one embodiment of the present invention described above may be implemented as an application (i.e., a program) that is basically installed on the terminal or directly installed by a user, and may be recorded on a computer-readable recording medium such as a terminal.

[0069] The foregoing description of the present invention is for illustrative purposes only, and those skilled in the art will understand that other specific forms can be easily modified without altering the technical spirit or essential features of the present invention. Therefore, the embodiments described above should be understood as illustrative in all respects and not restrictive. For example, each component described as a single unit may be implemented in a distributed manner, and components described as distributed may likewise be implemented in a combined form.

[0070] The scope of the present invention is defined by the claims set forth below rather than by the detailed description above, and all modifications or variations derived from the meaning and scope of the claims and equivalent concepts thereof should be interpreted as being included within the scope of the present invention.

Claims

Claim 1 At least one camera for filming the store; at least one piezoelectric sensor for detecting pressure on each seat placed on the table; and a display for displaying occupancy, non-occupancy, and a state requiring cleanup based on detection data monitored by the at least one piezoelectric sensor; and a seat storage unit that stores a mapping of at least one piezoelectric sensor and a seat number; a table storage unit that stores a mapping of a table number on which the at least one piezoelectric sensor is placed to the seat number; an occupancy display unit that outputs the table number and seat number mapped to the at least one piezoelectric sensor as an occupied state indicating use when pressure is monitored at the at least one piezoelectric sensor; a cleaning guide unit that waits for a preset time and then re-checks the pressure status when no pressure is applied to the at least one piezoelectric sensor in the occupancy state, and if the pressure is not monitored as a result of the re-check, displays the occupancy state as a state requiring cleaning; an available seat display unit that outputs the state requiring cleaning as an unoccupied state indicating available seats when a clear button is selected on the table number in the state requiring cleaning; an image analysis unit that identifies the occupancy status of at least one table based on an image recognition model from an image captured by the at least one camera and displays the occupancy status, state requiring cleaning, and unoccupied state on the table number; and when the table number is in an occupied state, the A table management service providing system for efficient store management, comprising: a management service providing server including a state change unit that changes the occupancy state to a state requiring cleanup when it is detected that an object corresponding to a human located at a table in an occupancy state is moving toward the exit of the store. Claim 2 In claim 1, the table management service providing system for efficient store management further comprises at least one piezoelectric sensor for detecting pressure applied to the table. Claim 3 A table management service providing system for efficient store management, characterized in that, in claim 2, the management service providing server further comprises a table checking unit that is equipped with at least one piezoelectric sensor for detecting pressure applied to the table, checks the pressure applied to the table when the pressure applied to the seat is not monitored, and changes the occupancy status to a state requiring cleanup when no pressure is applied to the table. Claim 4 delete Claim 5 delete Claim 6 delete Claim 7 A table management service providing system for efficient store management, wherein, in claim 1, the state changing unit changes the occupancy state to a state requiring cleanup when it is detected that an object corresponding to the human is moving toward the exit of the store while possessing an object corresponding to the possession. Claim 8 A table management service providing system for efficient store management, characterized in that, in claim 1, the management service providing server further comprises a modeling unit that constructs a dataset by labeling images of tables and seats confirmed by the camera with occupancy status, cleanup need status, and non-occupancy status based on the piezoelectric sensor, performs modeling by learning and verifying at least one image recognition model using the dataset, and extracts and sets the image recognition model with the highest accuracy among the at least one image recognition model. Claim 9 A table management service providing system for efficient store management, characterized in that, in claim 1, the management service providing server further includes a turnover rate measuring unit that measures the occupied state, the state requiring cleanup, and the non-occupied state as a single rotation, calculates the table turnover rate of the table, and transmits it to a user terminal. Claim 10 A table management service providing system for efficient store management, characterized in that, in claim 1, the management service providing server further includes a remaining seat alarm unit that uploads the occupancy status, the status requiring cleanup, and the non-occupancy status in real time, and displays and outputs the number of remaining seats and tables.

Images